diff --git a/FacebookAI/roberta_base_amazon/README.md b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/README.md similarity index 100% rename from FacebookAI/roberta_base_amazon/README.md rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/README.md diff --git a/FacebookAI/roberta_base_amazon/all_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/all_results.json similarity index 100% rename from FacebookAI/roberta_base_amazon/all_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/all_results.json diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/config.json similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/config.json diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/merges.txt similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/merges.txt diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/model.safetensors diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/optimizer.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/optimizer.pt similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/optimizer.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/optimizer.pt diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/rng_state_0.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/rng_state_0.pth similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/rng_state_0.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/rng_state_0.pth diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/rng_state_1.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/rng_state_1.pth similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/rng_state_1.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/rng_state_1.pth diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/scheduler.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/scheduler.pt similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/scheduler.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/scheduler.pt diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/special_tokens_map.json diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/tokenizer.json diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/tokenizer_config.json diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/trainer_state.json diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/training_args.bin diff --git a/FacebookAI/roberta_base_amazon/checkpoint-550/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/vocab.json similarity index 100% rename from FacebookAI/roberta_base_amazon/checkpoint-550/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/checkpoint-550/vocab.json diff --git a/FacebookAI/roberta_base_amazon/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/config.json similarity index 100% rename from FacebookAI/roberta_base_amazon/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/config.json diff --git a/FacebookAI/roberta_base_amazon/eval_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/eval_results.json similarity index 100% rename from FacebookAI/roberta_base_amazon/eval_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/eval_results.json diff --git a/FacebookAI/roberta_base_amazon/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/merges.txt similarity index 100% rename from FacebookAI/roberta_base_amazon/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/merges.txt diff --git a/FacebookAI/roberta_base_amazon/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_amazon/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/model.safetensors diff --git a/FacebookAI/roberta_base_amazon/run.log b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/run.log similarity index 100% rename from FacebookAI/roberta_base_amazon/run.log rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/run.log diff --git a/FacebookAI/roberta_base_amazon/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/special_tokens_map.json diff --git a/FacebookAI/roberta_base_amazon/test_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/test_results.json similarity index 100% rename from FacebookAI/roberta_base_amazon/test_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/test_results.json diff --git a/FacebookAI/roberta_base_amazon/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_amazon/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/tokenizer.json diff --git a/FacebookAI/roberta_base_amazon/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/tokenizer_config.json diff --git a/FacebookAI/roberta_base_amazon/train_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/train_results.json similarity index 100% rename from FacebookAI/roberta_base_amazon/train_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/train_results.json diff --git a/FacebookAI/roberta_base_amazon/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_amazon/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/trainer_state.json diff --git a/FacebookAI/roberta_base_amazon/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_amazon/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/training_args.bin diff --git a/FacebookAI/roberta_base_amazon/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/vocab.json similarity index 100% rename from FacebookAI/roberta_base_amazon/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_amazon/vocab.json diff --git a/FacebookAI/roberta_base_ledgar/README.md b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/README.md similarity index 100% rename from FacebookAI/roberta_base_ledgar/README.md rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/README.md diff --git a/FacebookAI/roberta_base_ledgar/all_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/all_results.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/all_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/all_results.json diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/config.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/config.json diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/merges.txt similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/merges.txt diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/model.safetensors diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/optimizer.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/optimizer.pt similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/optimizer.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/optimizer.pt diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/scheduler.pt diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/tokenizer.json diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/trainer_state.json diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/training_args.bin diff --git a/FacebookAI/roberta_base_ledgar/checkpoint-2800/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/vocab.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/checkpoint-2800/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/checkpoint-2800/vocab.json diff --git a/FacebookAI/roberta_base_ledgar/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/config.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/config.json diff --git a/FacebookAI/roberta_base_ledgar/eval_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/eval_results.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/eval_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/eval_results.json diff --git a/FacebookAI/roberta_base_ledgar/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/merges.txt similarity index 100% rename from FacebookAI/roberta_base_ledgar/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/merges.txt diff --git a/FacebookAI/roberta_base_ledgar/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_ledgar/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/model.safetensors diff --git a/FacebookAI/roberta_base_ledgar/run.log b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/run.log similarity index 100% rename from FacebookAI/roberta_base_ledgar/run.log rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/run.log diff --git a/FacebookAI/roberta_base_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/special_tokens_map.json diff --git a/FacebookAI/roberta_base_ledgar/test_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/test_results.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/test_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/test_results.json diff --git a/FacebookAI/roberta_base_ledgar/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/tokenizer.json diff --git a/FacebookAI/roberta_base_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/tokenizer_config.json diff --git a/FacebookAI/roberta_base_ledgar/train_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/train_results.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/train_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/train_results.json diff --git a/FacebookAI/roberta_base_ledgar/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/trainer_state.json diff --git a/FacebookAI/roberta_base_ledgar/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_ledgar/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/training_args.bin diff --git a/FacebookAI/roberta_base_ledgar/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/vocab.json similarity index 100% rename from FacebookAI/roberta_base_ledgar/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_ledgar/vocab.json diff --git a/FacebookAI/roberta_base_patent/README.md b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/README.md similarity index 100% rename from FacebookAI/roberta_base_patent/README.md rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/README.md diff --git a/FacebookAI/roberta_base_patent/all_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/all_results.json similarity index 100% rename from FacebookAI/roberta_base_patent/all_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/all_results.json diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/config.json similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/config.json diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/merges.txt similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/merges.txt diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/model.safetensors diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/optimizer.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/optimizer.pt similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/optimizer.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/optimizer.pt diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/rng_state_0.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/rng_state_0.pth similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/rng_state_0.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/rng_state_0.pth diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/rng_state_1.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/rng_state_1.pth similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/rng_state_1.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/rng_state_1.pth diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/scheduler.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/scheduler.pt similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/scheduler.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/scheduler.pt diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/special_tokens_map.json diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/tokenizer.json diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/tokenizer_config.json diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/trainer_state.json diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/training_args.bin diff --git a/FacebookAI/roberta_base_patent/checkpoint-1150/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/vocab.json similarity index 100% rename from FacebookAI/roberta_base_patent/checkpoint-1150/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/checkpoint-1150/vocab.json diff --git a/FacebookAI/roberta_base_patent/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/config.json similarity index 100% rename from FacebookAI/roberta_base_patent/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/config.json diff --git a/FacebookAI/roberta_base_patent/eval_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/eval_results.json similarity index 100% rename from FacebookAI/roberta_base_patent/eval_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/eval_results.json diff --git a/FacebookAI/roberta_base_patent/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/merges.txt similarity index 100% rename from FacebookAI/roberta_base_patent/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/merges.txt diff --git a/FacebookAI/roberta_base_patent/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_patent/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/model.safetensors diff --git a/FacebookAI/roberta_base_patent/run.log b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/run.log similarity index 100% rename from FacebookAI/roberta_base_patent/run.log rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/run.log diff --git a/FacebookAI/roberta_base_patent/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_patent/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/special_tokens_map.json diff --git a/FacebookAI/roberta_base_patent/test_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/test_results.json similarity index 100% rename from FacebookAI/roberta_base_patent/test_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/test_results.json diff --git a/FacebookAI/roberta_base_patent/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_patent/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/tokenizer.json diff --git a/FacebookAI/roberta_base_patent/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_patent/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/tokenizer_config.json diff --git a/FacebookAI/roberta_base_patent/train_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/train_results.json similarity index 100% rename from FacebookAI/roberta_base_patent/train_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/train_results.json diff --git a/FacebookAI/roberta_base_patent/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_patent/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/trainer_state.json diff --git a/FacebookAI/roberta_base_patent/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_patent/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/training_args.bin diff --git a/FacebookAI/roberta_base_patent/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_patent/vocab.json similarity index 100% rename from FacebookAI/roberta_base_patent/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_patent/vocab.json diff --git a/FacebookAI/roberta_base_scotus/README.md b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/README.md similarity index 100% rename from FacebookAI/roberta_base_scotus/README.md rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/README.md diff --git a/FacebookAI/roberta_base_scotus/all_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/all_results.json similarity index 100% rename from FacebookAI/roberta_base_scotus/all_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/all_results.json diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/config.json similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/config.json diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/merges.txt similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/merges.txt diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/model.safetensors diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/optimizer.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/optimizer.pt similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/optimizer.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/optimizer.pt diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/rng_state_0.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/rng_state_0.pth similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/rng_state_0.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/rng_state_0.pth diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/rng_state_1.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/rng_state_1.pth similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/rng_state_1.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/rng_state_1.pth diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/scheduler.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/scheduler.pt similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/scheduler.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/scheduler.pt diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/special_tokens_map.json diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/tokenizer.json diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/tokenizer_config.json diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/trainer_state.json diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/training_args.bin diff --git a/FacebookAI/roberta_base_scotus/checkpoint-200/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/vocab.json similarity index 100% rename from FacebookAI/roberta_base_scotus/checkpoint-200/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/checkpoint-200/vocab.json diff --git a/FacebookAI/roberta_base_scotus/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/config.json similarity index 100% rename from FacebookAI/roberta_base_scotus/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/config.json diff --git a/FacebookAI/roberta_base_scotus/eval_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/eval_results.json similarity index 100% rename from FacebookAI/roberta_base_scotus/eval_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/eval_results.json diff --git a/FacebookAI/roberta_base_scotus/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/merges.txt similarity index 100% rename from FacebookAI/roberta_base_scotus/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/merges.txt diff --git a/FacebookAI/roberta_base_scotus/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_scotus/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/model.safetensors diff --git a/FacebookAI/roberta_base_scotus/run.log b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/run.log similarity index 100% rename from FacebookAI/roberta_base_scotus/run.log rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/run.log diff --git a/FacebookAI/roberta_base_scotus/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/special_tokens_map.json diff --git a/FacebookAI/roberta_base_scotus/test_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/test_results.json similarity index 100% rename from FacebookAI/roberta_base_scotus/test_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/test_results.json diff --git a/FacebookAI/roberta_base_scotus/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_scotus/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/tokenizer.json diff --git a/FacebookAI/roberta_base_scotus/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/tokenizer_config.json diff --git a/FacebookAI/roberta_base_scotus/train_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/train_results.json similarity index 100% rename from FacebookAI/roberta_base_scotus/train_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/train_results.json diff --git a/FacebookAI/roberta_base_scotus/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_scotus/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/trainer_state.json diff --git a/FacebookAI/roberta_base_scotus/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_scotus/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/training_args.bin diff --git a/FacebookAI/roberta_base_scotus/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/vocab.json similarity index 100% rename from FacebookAI/roberta_base_scotus/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_scotus/vocab.json diff --git a/FacebookAI/roberta_base_twitter/README.md b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/README.md similarity index 100% rename from FacebookAI/roberta_base_twitter/README.md rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/README.md diff --git a/FacebookAI/roberta_base_twitter/all_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/all_results.json similarity index 100% rename from FacebookAI/roberta_base_twitter/all_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/all_results.json diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/config.json similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/config.json diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/merges.txt similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/merges.txt diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/model.safetensors diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/optimizer.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/optimizer.pt similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/optimizer.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/optimizer.pt diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/rng_state_0.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/rng_state_0.pth similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/rng_state_0.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/rng_state_0.pth diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/rng_state_1.pth b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/rng_state_1.pth similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/rng_state_1.pth rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/rng_state_1.pth diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/scheduler.pt b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/scheduler.pt similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/scheduler.pt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/scheduler.pt diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/special_tokens_map.json diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/tokenizer.json diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/tokenizer_config.json diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/trainer_state.json diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/training_args.bin diff --git a/FacebookAI/roberta_base_twitter/checkpoint-50/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/vocab.json similarity index 100% rename from FacebookAI/roberta_base_twitter/checkpoint-50/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/checkpoint-50/vocab.json diff --git a/FacebookAI/roberta_base_twitter/config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/config.json similarity index 100% rename from FacebookAI/roberta_base_twitter/config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/config.json diff --git a/FacebookAI/roberta_base_twitter/eval_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/eval_results.json similarity index 100% rename from FacebookAI/roberta_base_twitter/eval_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/eval_results.json diff --git a/FacebookAI/roberta_base_twitter/merges.txt b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/merges.txt similarity index 100% rename from FacebookAI/roberta_base_twitter/merges.txt rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/merges.txt diff --git a/FacebookAI/roberta_base_twitter/model.safetensors b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/model.safetensors similarity index 100% rename from FacebookAI/roberta_base_twitter/model.safetensors rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/model.safetensors diff --git a/FacebookAI/roberta_base_twitter/run.log b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/run.log similarity index 100% rename from FacebookAI/roberta_base_twitter/run.log rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/run.log diff --git a/FacebookAI/roberta_base_twitter/special_tokens_map.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/special_tokens_map.json similarity index 100% rename from FacebookAI/roberta_base_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/special_tokens_map.json diff --git a/FacebookAI/roberta_base_twitter/test_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/test_results.json similarity index 100% rename from FacebookAI/roberta_base_twitter/test_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/test_results.json diff --git a/FacebookAI/roberta_base_twitter/tokenizer.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/tokenizer.json similarity index 100% rename from FacebookAI/roberta_base_twitter/tokenizer.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/tokenizer.json diff --git a/FacebookAI/roberta_base_twitter/tokenizer_config.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/tokenizer_config.json similarity index 100% rename from FacebookAI/roberta_base_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/tokenizer_config.json diff --git a/FacebookAI/roberta_base_twitter/train_results.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/train_results.json similarity index 100% rename from FacebookAI/roberta_base_twitter/train_results.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/train_results.json diff --git a/FacebookAI/roberta_base_twitter/trainer_state.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/trainer_state.json similarity index 100% rename from FacebookAI/roberta_base_twitter/trainer_state.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/trainer_state.json diff --git a/FacebookAI/roberta_base_twitter/training_args.bin b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/training_args.bin similarity index 100% rename from FacebookAI/roberta_base_twitter/training_args.bin rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/training_args.bin diff --git a/FacebookAI/roberta_base_twitter/vocab.json b/max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/vocab.json similarity index 100% rename from FacebookAI/roberta_base_twitter/vocab.json rename to max_seq_length_128_experiments/FacebookAI/roberta_base_twitter/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/all_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/all_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/all_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/all_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/global_step350/mp_rank_00_model_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/latest b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/latest similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/latest rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/latest diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/rng_state_0.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/rng_state_0.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/rng_state_1.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/rng_state_1.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/scheduler.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/scheduler.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/scheduler.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/scheduler.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/zero_to_fp32.py similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-350/zero_to_fp32.py diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/run.log b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/run.log similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/run.log rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/run.log diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/test_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/test_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/test_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/test_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/train_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/train_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/train_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/train_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/all_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/all_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/all_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/all_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/eval_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/eval_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/eval_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/eval_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/run.log b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/run.log similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/run.log rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/run.log diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/test_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/test_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/test_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/test_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/train_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/train_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/train_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/train_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/all_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/all_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/all_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/all_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/eval_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/eval_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/eval_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/eval_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/run.log b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/run.log similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/run.log rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/run.log diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/test_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/test_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/test_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/test_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/train_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/train_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/train_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/train_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_ccdv/patent_classification_abstract/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/all_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/all_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/all_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/all_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/global_step400/mp_rank_00_model_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/latest b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/latest similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/latest rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/latest diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/rng_state_0.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/rng_state_0.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/rng_state_1.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/rng_state_1.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/scheduler.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/scheduler.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/scheduler.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/scheduler.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/zero_to_fp32.py similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/checkpoint-400/zero_to_fp32.py diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/eval_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/eval_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/eval_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/eval_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/run.log b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/run.log similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/run.log rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/run.log diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/test_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/test_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/test_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/test_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/train_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/train_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/train_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/train_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/all_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/all_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/all_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/all_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/added_tokens.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/added_tokens.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/added_tokens.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/added_tokens.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/vocab.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/eval_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/eval_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/eval_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/eval_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/merges.txt b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/merges.txt similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/merges.txt rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/merges.txt diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/run.log b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/run.log similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/run.log rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/run.log diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/test_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/test_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/test_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/test_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/train_results.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/train_results.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/train_results.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/train_results.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/training_args.bin b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/training_args.bin similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/training_args.bin rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/training_args.bin diff --git a/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/vocab.json b/max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/vocab.json similarity index 100% rename from LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/vocab.json rename to max_seq_length_128_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_coastalcph/lex_glue_ledgar/vocab.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/README.md diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/all_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/all_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/all_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/all_results.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/run.log b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/run.log similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/run.log rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/run.log diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/test_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/test_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/test_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/test_results.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/train_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/train_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/train_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/train_results.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/README.md diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/all_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/all_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/all_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/all_results.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/eval_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/eval_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/eval_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/eval_results.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/run.log b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/run.log similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/run.log rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/run.log diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/test_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/test_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/test_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/test_results.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/train_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/train_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/train_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/train_results.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/README.md diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/all_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/all_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/all_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/all_results.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/eval_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/eval_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/eval_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/eval_results.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/run.log b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/run.log similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/run.log rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/run.log diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/test_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/test_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/test_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/test_results.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/train_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/train_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/train_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/train_results.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/README.md diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/all_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/all_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/all_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/all_results.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/eval_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/eval_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/eval_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/eval_results.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/run.log b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/run.log similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/run.log rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/run.log diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/test_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/test_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/test_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/test_results.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/train_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/train_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/train_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/train_results.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/README.md diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/all_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/all_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/all_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/all_results.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/README.md b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/README.md similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/README.md rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/README.md diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/adapter_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/adapter_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/adapter_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/adapter_config.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/adapter_model.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/adapter_model.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/adapter_model.bin diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/global_step450/mp_rank_00_model_states.pt diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/latest b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/latest similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/latest rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/latest diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/rng_state_0.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/rng_state_0.pth diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/rng_state_1.pth similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/rng_state_1.pth diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/scheduler.pt b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/scheduler.pt similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/scheduler.pt rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/scheduler.pt diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/training_args.bin diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/zero_to_fp32.py similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-450/zero_to_fp32.py diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/eval_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/eval_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/eval_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/eval_results.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/run.log b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/run.log similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/run.log rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/run.log diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/test_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/test_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/test_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/test_results.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.model b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.model similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.model rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.model diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/train_results.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/train_results.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/train_results.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/train_results.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/trainer_state.json b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/trainer_state.json similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/trainer_state.json rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/trainer_state.json diff --git a/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/training_args.bin b/max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/training_args.bin similarity index 100% rename from LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/training_args.bin rename to max_seq_length_128_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/all_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/all_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/all_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/all_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/run.log b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/run.log similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/run.log rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/run.log diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/test_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/test_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/test_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/test_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/train_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/train_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/train_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/train_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/all_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/all_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/all_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/all_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/global_step250/mp_rank_00_model_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/latest diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_0.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/rng_state_1.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/scheduler.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/checkpoint-250/zero_to_fp32.py diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/eval_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/eval_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/eval_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/eval_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/run.log b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/run.log similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/run.log rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/run.log diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/test_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/test_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/test_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/test_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/train_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/train_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/train_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/train_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_MAdAiLab/twitter_disaster/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/all_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/all_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/all_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/all_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/global_step800/mp_rank_00_model_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/latest b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/latest similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/latest rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/latest diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/rng_state_0.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/rng_state_0.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/rng_state_1.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/rng_state_1.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/scheduler.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/scheduler.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/scheduler.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/scheduler.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/zero_to_fp32.py similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/checkpoint-800/zero_to_fp32.py diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/eval_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/eval_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/eval_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/eval_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/run.log b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/run.log similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/run.log rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/run.log diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/test_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/test_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/test_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/test_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/train_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/train_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/train_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/train_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_ccdv/patent_classification_abstract/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/all_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/all_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/all_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/all_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/global_step3700/mp_rank_00_model_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/latest diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_0.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/rng_state_1.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/scheduler.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/checkpoint-3700/zero_to_fp32.py diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/eval_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/eval_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/eval_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/eval_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/run.log b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/run.log similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/run.log rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/run.log diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/test_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/test_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/test_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/test_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/train_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/train_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/train_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/train_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_ledgar/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/all_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/all_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/all_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/all_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/README.md b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/README.md similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/README.md rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/README.md diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/adapter_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/adapter_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/adapter_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/adapter_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/adapter_model.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/adapter_model.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/adapter_model.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/global_step150/mp_rank_00_model_states.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/latest b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/latest similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/latest rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/latest diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/rng_state_0.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/rng_state_0.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/rng_state_1.pth similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/rng_state_1.pth diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/scheduler.pt b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/scheduler.pt similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/scheduler.pt rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/scheduler.pt diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/training_args.bin diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/zero_to_fp32.py similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/checkpoint-150/zero_to_fp32.py diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/eval_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/eval_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/eval_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/eval_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/run.log b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/run.log similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/run.log rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/run.log diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/test_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/test_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/test_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/test_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer.model b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer.model similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer.model rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer.model diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/train_results.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/train_results.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/train_results.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/train_results.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/trainer_state.json b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/trainer_state.json similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/trainer_state.json rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/trainer_state.json diff --git a/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/training_args.bin b/max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/training_args.bin similarity index 100% rename from LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/training_args.bin rename to max_seq_length_128_experiments/LoRA/meta_llama/Llama_2_7b_hf_LoRA_coastalcph/lex_glue_scotus/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/all_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/all_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/all_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/all_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/global_step750/mp_rank_00_model_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/latest diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_0.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/rng_state_1.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/scheduler.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/checkpoint-750/zero_to_fp32.py diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/eval_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/run.log b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/run.log similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/run.log rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/run.log diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/test_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/test_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/test_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/test_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/train_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/train_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/train_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/train_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/amazon_attrprompt/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/all_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/all_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/all_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/all_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/global_step200/mp_rank_00_model_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/latest b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/latest similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/latest rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/latest diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/rng_state_0.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/rng_state_0.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/rng_state_1.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/rng_state_1.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/scheduler.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/scheduler.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/scheduler.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/scheduler.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/zero_to_fp32.py similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/checkpoint-200/zero_to_fp32.py diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/eval_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/eval_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/eval_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/eval_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/run.log b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/run.log similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/run.log rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/run.log diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/test_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/test_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/test_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/test_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/train_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/train_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/train_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/train_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_MAdAiLab/twitter_disaster/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/all_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/all_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/all_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/all_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/global_step1400/mp_rank_00_model_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/latest diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_0.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/rng_state_1.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/scheduler.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/checkpoint-1400/zero_to_fp32.py diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/eval_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/eval_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/eval_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/eval_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/run.log b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/run.log similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/run.log rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/run.log diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/test_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/test_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/test_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/test_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/train_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/train_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/train_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/train_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_ccdv/patent_classification_abstract/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/all_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/all_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/all_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/all_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/global_step1000/mp_rank_00_model_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/latest b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/latest similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/latest rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/latest diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/rng_state_0.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/rng_state_0.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/rng_state_1.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/rng_state_1.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/scheduler.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/scheduler.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/scheduler.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/scheduler.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/zero_to_fp32.py similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1000/zero_to_fp32.py diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/eval_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/eval_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/eval_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/eval_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/run.log b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/run.log similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/run.log rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/run.log diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/test_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/test_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/test_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/test_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/train_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/train_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/train_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/train_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/all_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/all_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/all_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/all_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/global_step1750/mp_rank_00_model_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/latest b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/latest similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/latest rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/latest diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/rng_state_0.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/rng_state_0.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/rng_state_1.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/rng_state_1.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/scheduler.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/scheduler.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/scheduler.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/scheduler.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/zero_to_fp32.py similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/checkpoint-1750/zero_to_fp32.py diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/eval_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/eval_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/eval_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/eval_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/run.log b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/run.log similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/run.log rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/run.log diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/test_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/test_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/test_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/test_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/train_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/train_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/train_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/train_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_ledgar_2/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/all_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/all_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/all_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/all_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/README.md b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/README.md similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/README.md rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/README.md diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/adapter_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/adapter_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/adapter_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/adapter_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/adapter_model.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/adapter_model.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/adapter_model.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/adapter_model.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/latest b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/latest similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/latest rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/latest diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/rng_state_0.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/rng_state_0.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/rng_state_0.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/rng_state_0.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/rng_state_1.pth b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/rng_state_1.pth similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/rng_state_1.pth rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/rng_state_1.pth diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/scheduler.pt b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/scheduler.pt similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/scheduler.pt rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/scheduler.pt diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/training_args.bin diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/zero_to_fp32.py b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/zero_to_fp32.py similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/zero_to_fp32.py rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/checkpoint-300/zero_to_fp32.py diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/eval_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/eval_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/eval_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/eval_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/run.log b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/run.log similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/run.log rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/run.log diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/special_tokens_map.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/test_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/test_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/test_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/test_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer.model b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer.model similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer.model rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer.model diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/tokenizer_config.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/train_results.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/train_results.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/train_results.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/train_results.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/trainer_state.json b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/trainer_state.json similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/trainer_state.json rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/trainer_state.json diff --git a/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/training_args.bin b/max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/training_args.bin similarity index 100% rename from LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/training_args.bin rename to max_seq_length_128_experiments/LoRA/mistralai/Mistral_7B_v0.1_LoRA_coastalcph/lex_glue_scotus/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_amazon/README.md b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/README.md similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/README.md rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/README.md diff --git a/Qwen/Qwen1.5_1.8B_amazon/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/all_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/all_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/all_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/all_results.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/config.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/latest b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/latest similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/latest rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/latest diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/model.safetensors b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/model.safetensors similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/model.safetensors rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/model.safetensors diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_0.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_0.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_0.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_0.pth diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_1.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_1.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_1.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_1.pth diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/scheduler.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/scheduler.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/scheduler.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/scheduler.pt diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/zero_to_fp32.py b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/zero_to_fp32.py similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/zero_to_fp32.py rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/zero_to_fp32.py diff --git a/Qwen/Qwen1.5_1.8B_amazon/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/config.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/eval_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/eval_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/eval_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/eval_results.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_amazon/model.safetensors b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/model.safetensors similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/model.safetensors rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/model.safetensors diff --git a/Qwen/Qwen1.5_1.8B_amazon/run.log b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/run.log similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/run.log rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/run.log diff --git a/Qwen/Qwen1.5_1.8B_amazon/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/test_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/test_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/test_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/test_results.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/train_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/train_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/train_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/train_results.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_amazon/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_amazon/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_amazon/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_amazon/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/README.md b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/README.md similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/README.md rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/README.md diff --git a/Qwen/Qwen1.5_1.8B_ledgar/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/all_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/all_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/all_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/all_results.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/config.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/mp_rank_00_model_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/global_step1800/mp_rank_00_model_states.pt diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/latest b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/latest similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/latest rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/latest diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/model.safetensors b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/model.safetensors similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/model.safetensors rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/model.safetensors diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/rng_state_0.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/rng_state_0.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/rng_state_0.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/rng_state_0.pth diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/rng_state_1.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/rng_state_1.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/rng_state_1.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/rng_state_1.pth diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/scheduler.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/scheduler.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/scheduler.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/scheduler.pt diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/zero_to_fp32.py b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/zero_to_fp32.py similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/zero_to_fp32.py rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/checkpoint-1800/zero_to_fp32.py diff --git a/Qwen/Qwen1.5_1.8B_ledgar/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/config.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/eval_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/eval_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/eval_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/eval_results.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_ledgar/model.safetensors b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/model.safetensors similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/model.safetensors rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/model.safetensors diff --git a/Qwen/Qwen1.5_1.8B_ledgar/run.log b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/run.log similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/run.log rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/run.log diff --git a/Qwen/Qwen1.5_1.8B_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/test_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/test_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/test_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/test_results.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/train_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/train_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/train_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/train_results.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_ledgar/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_ledgar/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_ledgar/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_ledgar/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_patent/README.md b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/README.md similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/README.md rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/README.md diff --git a/Qwen/Qwen1.5_1.8B_patent/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_patent/all_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/all_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/all_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/all_results.json diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/config.json diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/mp_rank_00_model_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/mp_rank_00_model_states.pt diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/latest b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/latest similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/latest rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/latest diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/pytorch_model.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/pytorch_model.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/pytorch_model.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/pytorch_model.bin diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_0.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_0.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_0.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_0.pth diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_1.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_1.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_1.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_1.pth diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/scheduler.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/scheduler.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/scheduler.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/scheduler.pt diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/zero_to_fp32.py b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/zero_to_fp32.py similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/checkpoint-750/zero_to_fp32.py rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/checkpoint-750/zero_to_fp32.py diff --git a/Qwen/Qwen1.5_1.8B_patent/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/config.json diff --git a/Qwen/Qwen1.5_1.8B_patent/eval_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/eval_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/eval_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/eval_results.json diff --git a/Qwen/Qwen1.5_1.8B_patent/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_patent/pytorch_model.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/pytorch_model.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/pytorch_model.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/pytorch_model.bin diff --git a/Qwen/Qwen1.5_1.8B_patent/run.log b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/run.log similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/run.log rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/run.log diff --git a/Qwen/Qwen1.5_1.8B_patent/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_patent/test_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/test_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/test_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/test_results.json diff --git a/Qwen/Qwen1.5_1.8B_patent/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_patent/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_patent/train_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/train_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/train_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/train_results.json diff --git a/Qwen/Qwen1.5_1.8B_patent/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_patent/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_patent/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_patent/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_patent/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/README.md b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/README.md similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/README.md rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/README.md diff --git a/Qwen/Qwen1.5_1.8B_scotus/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/all_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/all_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/all_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/all_results.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/config.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/latest b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/latest similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/latest rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/latest diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/model.safetensors b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/model.safetensors similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/model.safetensors rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/model.safetensors diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/rng_state_0.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/rng_state_0.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/rng_state_0.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/rng_state_0.pth diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/rng_state_1.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/rng_state_1.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/rng_state_1.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/rng_state_1.pth diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/scheduler.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/scheduler.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/scheduler.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/scheduler.pt diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/zero_to_fp32.py b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/zero_to_fp32.py similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/zero_to_fp32.py rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/checkpoint-300/zero_to_fp32.py diff --git a/Qwen/Qwen1.5_1.8B_scotus/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/config.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/eval_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/eval_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/eval_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/eval_results.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_scotus/model.safetensors b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/model.safetensors similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/model.safetensors rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/model.safetensors diff --git a/Qwen/Qwen1.5_1.8B_scotus/run.log b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/run.log similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/run.log rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/run.log diff --git a/Qwen/Qwen1.5_1.8B_scotus/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/test_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/test_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/test_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/test_results.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/train_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/train_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/train_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/train_results.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_scotus/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_scotus/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_scotus/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_scotus/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/README.md b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/README.md similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/README.md rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/README.md diff --git a/Qwen/Qwen1.5_1.8B_twitter/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/all_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/all_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/all_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/all_results.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/added_tokens.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/added_tokens.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/added_tokens.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/added_tokens.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/config.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/mp_rank_00_model_states.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/global_step250/mp_rank_00_model_states.pt diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/latest b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/latest similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/latest rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/latest diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/pytorch_model.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/pytorch_model.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/pytorch_model.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/pytorch_model.bin diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/rng_state_0.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/rng_state_0.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/rng_state_0.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/rng_state_0.pth diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/rng_state_1.pth b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/rng_state_1.pth similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/rng_state_1.pth rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/rng_state_1.pth diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/scheduler.pt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/scheduler.pt similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/scheduler.pt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/scheduler.pt diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/vocab.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/zero_to_fp32.py b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/zero_to_fp32.py similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/zero_to_fp32.py rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/checkpoint-250/zero_to_fp32.py diff --git a/Qwen/Qwen1.5_1.8B_twitter/config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/config.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/eval_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/eval_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/eval_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/eval_results.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/merges.txt b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/merges.txt similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/merges.txt rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/merges.txt diff --git a/Qwen/Qwen1.5_1.8B_twitter/pytorch_model.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/pytorch_model.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/pytorch_model.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/pytorch_model.bin diff --git a/Qwen/Qwen1.5_1.8B_twitter/run.log b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/run.log similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/run.log rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/run.log diff --git a/Qwen/Qwen1.5_1.8B_twitter/special_tokens_map.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/special_tokens_map.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/special_tokens_map.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/test_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/test_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/test_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/test_results.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/tokenizer.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/tokenizer.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/tokenizer.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/tokenizer.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/tokenizer_config.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/tokenizer_config.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/tokenizer_config.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/train_results.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/train_results.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/train_results.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/train_results.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/trainer_state.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/trainer_state.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/trainer_state.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/trainer_state.json diff --git a/Qwen/Qwen1.5_1.8B_twitter/training_args.bin b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/training_args.bin similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/training_args.bin rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/training_args.bin diff --git a/Qwen/Qwen1.5_1.8B_twitter/vocab.json b/max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/vocab.json similarity index 100% rename from Qwen/Qwen1.5_1.8B_twitter/vocab.json rename to max_seq_length_128_experiments/Qwen/Qwen1.5_1.8B_twitter/vocab.json diff --git a/distilbert/distilbert_base_uncased_amazon/README.md b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/README.md similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/README.md rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/README.md diff --git a/distilbert/distilbert_base_uncased_amazon/all_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/all_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/all_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/all_results.json diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/config.json diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/model.safetensors diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/optimizer.pt similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/optimizer.pt diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_0.pth similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_0.pth diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_1.pth similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_1.pth diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/scheduler.pt similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/scheduler.pt diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/training_args.bin diff --git a/distilbert/distilbert_base_uncased_amazon/checkpoint-550/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/checkpoint-550/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/checkpoint-550/vocab.txt diff --git a/distilbert/distilbert_base_uncased_amazon/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/config.json diff --git a/distilbert/distilbert_base_uncased_amazon/eval_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/eval_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/eval_results.json diff --git a/distilbert/distilbert_base_uncased_amazon/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/model.safetensors diff --git a/distilbert/distilbert_base_uncased_amazon/run.log b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/run.log similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/run.log rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/run.log diff --git a/distilbert/distilbert_base_uncased_amazon/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_amazon/test_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/test_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/test_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/test_results.json diff --git a/distilbert/distilbert_base_uncased_amazon/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_amazon/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_amazon/train_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/train_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/train_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/train_results.json diff --git a/distilbert/distilbert_base_uncased_amazon/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_amazon/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/training_args.bin diff --git a/distilbert/distilbert_base_uncased_amazon/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_amazon/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_amazon/vocab.txt diff --git a/distilbert/distilbert_base_uncased_ledgar/README.md b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/README.md similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/README.md rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/README.md diff --git a/distilbert/distilbert_base_uncased_ledgar/all_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/all_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/all_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/all_results.json diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/config.json diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/model.safetensors diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/optimizer.pt similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/optimizer.pt diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/scheduler.pt diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/training_args.bin diff --git a/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/vocab.txt diff --git a/distilbert/distilbert_base_uncased_ledgar/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/config.json diff --git a/distilbert/distilbert_base_uncased_ledgar/eval_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/eval_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/eval_results.json diff --git a/distilbert/distilbert_base_uncased_ledgar/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/model.safetensors diff --git a/distilbert/distilbert_base_uncased_ledgar/run.log b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/run.log similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/run.log rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/run.log diff --git a/distilbert/distilbert_base_uncased_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_ledgar/test_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/test_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/test_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/test_results.json diff --git a/distilbert/distilbert_base_uncased_ledgar/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_ledgar/train_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/train_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/train_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/train_results.json diff --git a/distilbert/distilbert_base_uncased_ledgar/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_ledgar/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/training_args.bin diff --git a/distilbert/distilbert_base_uncased_ledgar/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_ledgar/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_ledgar/vocab.txt diff --git a/distilbert/distilbert_base_uncased_patent/README.md b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/README.md similarity index 100% rename from distilbert/distilbert_base_uncased_patent/README.md rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/README.md diff --git a/distilbert/distilbert_base_uncased_patent/all_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/all_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/all_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/all_results.json diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/config.json diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/model.safetensors diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/optimizer.pt similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/optimizer.pt diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/rng_state_0.pth similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/rng_state_0.pth diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/rng_state_1.pth similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/rng_state_1.pth diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/scheduler.pt similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/scheduler.pt diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/training_args.bin diff --git a/distilbert/distilbert_base_uncased_patent/checkpoint-1100/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_patent/checkpoint-1100/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/checkpoint-1100/vocab.txt diff --git a/distilbert/distilbert_base_uncased_patent/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/config.json diff --git a/distilbert/distilbert_base_uncased_patent/eval_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/eval_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/eval_results.json diff --git a/distilbert/distilbert_base_uncased_patent/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_patent/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/model.safetensors diff --git a/distilbert/distilbert_base_uncased_patent/run.log b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/run.log similarity index 100% rename from distilbert/distilbert_base_uncased_patent/run.log rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/run.log diff --git a/distilbert/distilbert_base_uncased_patent/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_patent/test_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/test_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/test_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/test_results.json diff --git a/distilbert/distilbert_base_uncased_patent/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_patent/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_patent/train_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/train_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/train_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/train_results.json diff --git a/distilbert/distilbert_base_uncased_patent/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_patent/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_patent/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_patent/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/training_args.bin diff --git a/distilbert/distilbert_base_uncased_patent/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_patent/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_patent/vocab.txt diff --git a/distilbert/distilbert_base_uncased_scotus/README.md b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/README.md similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/README.md rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/README.md diff --git a/distilbert/distilbert_base_uncased_scotus/all_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/all_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/all_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/all_results.json diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/config.json diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/model.safetensors diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/optimizer.pt similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/optimizer.pt diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/rng_state_0.pth similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/rng_state_0.pth diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/rng_state_1.pth similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/rng_state_1.pth diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/scheduler.pt similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/scheduler.pt diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/training_args.bin diff --git a/distilbert/distilbert_base_uncased_scotus/checkpoint-200/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/checkpoint-200/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/checkpoint-200/vocab.txt diff --git a/distilbert/distilbert_base_uncased_scotus/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/config.json diff --git a/distilbert/distilbert_base_uncased_scotus/eval_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/eval_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/eval_results.json diff --git a/distilbert/distilbert_base_uncased_scotus/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/model.safetensors diff --git a/distilbert/distilbert_base_uncased_scotus/run.log b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/run.log similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/run.log rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/run.log diff --git a/distilbert/distilbert_base_uncased_scotus/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_scotus/test_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/test_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/test_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/test_results.json diff --git a/distilbert/distilbert_base_uncased_scotus/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_scotus/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_scotus/train_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/train_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/train_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/train_results.json diff --git a/distilbert/distilbert_base_uncased_scotus/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_scotus/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/training_args.bin diff --git a/distilbert/distilbert_base_uncased_scotus/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_scotus/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_scotus/vocab.txt diff --git a/distilbert/distilbert_base_uncased_twitter/README.md b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/README.md similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/README.md rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/README.md diff --git a/distilbert/distilbert_base_uncased_twitter/all_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/all_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/all_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/all_results.json diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/config.json diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/model.safetensors diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/optimizer.pt similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/optimizer.pt diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/rng_state_0.pth similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/rng_state_0.pth diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/rng_state_1.pth similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/rng_state_1.pth diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/scheduler.pt similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/scheduler.pt diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/training_args.bin diff --git a/distilbert/distilbert_base_uncased_twitter/checkpoint-100/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/checkpoint-100/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/checkpoint-100/vocab.txt diff --git a/distilbert/distilbert_base_uncased_twitter/config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/config.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/config.json diff --git a/distilbert/distilbert_base_uncased_twitter/eval_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/eval_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/eval_results.json diff --git a/distilbert/distilbert_base_uncased_twitter/model.safetensors b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/model.safetensors similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/model.safetensors diff --git a/distilbert/distilbert_base_uncased_twitter/run.log b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/run.log similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/run.log rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/run.log diff --git a/distilbert/distilbert_base_uncased_twitter/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/special_tokens_map.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/special_tokens_map.json diff --git a/distilbert/distilbert_base_uncased_twitter/test_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/test_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/test_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/test_results.json diff --git a/distilbert/distilbert_base_uncased_twitter/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/tokenizer.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/tokenizer.json diff --git a/distilbert/distilbert_base_uncased_twitter/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/tokenizer_config.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/tokenizer_config.json diff --git a/distilbert/distilbert_base_uncased_twitter/train_results.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/train_results.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/train_results.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/train_results.json diff --git a/distilbert/distilbert_base_uncased_twitter/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/trainer_state.json similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/trainer_state.json diff --git a/distilbert/distilbert_base_uncased_twitter/training_args.bin b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/training_args.bin similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/training_args.bin diff --git a/distilbert/distilbert_base_uncased_twitter/vocab.txt b/max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/vocab.txt similarity index 100% rename from distilbert/distilbert_base_uncased_twitter/vocab.txt rename to max_seq_length_128_experiments/distilbert/distilbert_base_uncased_twitter/vocab.txt diff --git a/distilbert/distilroberta_base_amazon/README.md b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/README.md similarity index 100% rename from distilbert/distilroberta_base_amazon/README.md rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/README.md diff --git a/distilbert/distilroberta_base_amazon/all_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/all_results.json similarity index 100% rename from distilbert/distilroberta_base_amazon/all_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/all_results.json diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/config.json similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/config.json diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/merges.txt similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/merges.txt diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/model.safetensors diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/optimizer.pt similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/optimizer.pt diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/rng_state_0.pth similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/rng_state_0.pth diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/rng_state_1.pth similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/rng_state_1.pth diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/scheduler.pt similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/scheduler.pt diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/special_tokens_map.json diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/tokenizer.json diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/tokenizer_config.json diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/trainer_state.json diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/training_args.bin diff --git a/distilbert/distilroberta_base_amazon/checkpoint-550/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/vocab.json similarity index 100% rename from distilbert/distilroberta_base_amazon/checkpoint-550/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/checkpoint-550/vocab.json diff --git a/distilbert/distilroberta_base_amazon/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/config.json similarity index 100% rename from distilbert/distilroberta_base_amazon/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/config.json diff --git a/distilbert/distilroberta_base_amazon/eval_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/eval_results.json similarity index 100% rename from distilbert/distilroberta_base_amazon/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/eval_results.json diff --git a/distilbert/distilroberta_base_amazon/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/merges.txt similarity index 100% rename from distilbert/distilroberta_base_amazon/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/merges.txt diff --git a/distilbert/distilroberta_base_amazon/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_amazon/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/model.safetensors diff --git a/distilbert/distilroberta_base_amazon/run.log b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/run.log similarity index 100% rename from distilbert/distilroberta_base_amazon/run.log rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/run.log diff --git a/distilbert/distilroberta_base_amazon/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/special_tokens_map.json diff --git a/distilbert/distilroberta_base_amazon/test_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/test_results.json similarity index 100% rename from distilbert/distilroberta_base_amazon/test_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/test_results.json diff --git a/distilbert/distilroberta_base_amazon/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_amazon/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/tokenizer.json diff --git a/distilbert/distilroberta_base_amazon/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/tokenizer_config.json diff --git a/distilbert/distilroberta_base_amazon/train_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/train_results.json similarity index 100% rename from distilbert/distilroberta_base_amazon/train_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/train_results.json diff --git a/distilbert/distilroberta_base_amazon/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_amazon/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/trainer_state.json diff --git a/distilbert/distilroberta_base_amazon/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_amazon/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/training_args.bin diff --git a/distilbert/distilroberta_base_amazon/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/vocab.json similarity index 100% rename from distilbert/distilroberta_base_amazon/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_amazon/vocab.json diff --git a/distilbert/distilroberta_base_ledgar/README.md b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/README.md similarity index 100% rename from distilbert/distilroberta_base_ledgar/README.md rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/README.md diff --git a/distilbert/distilroberta_base_ledgar/all_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/all_results.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/all_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/all_results.json diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/config.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/config.json diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/merges.txt similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/merges.txt diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/model.safetensors diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/optimizer.pt similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/optimizer.pt diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/scheduler.pt diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/tokenizer.json diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/trainer_state.json diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/training_args.bin diff --git a/distilbert/distilroberta_base_ledgar/checkpoint-2800/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/vocab.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/checkpoint-2800/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/checkpoint-2800/vocab.json diff --git a/distilbert/distilroberta_base_ledgar/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/config.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/config.json diff --git a/distilbert/distilroberta_base_ledgar/eval_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/eval_results.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/eval_results.json diff --git a/distilbert/distilroberta_base_ledgar/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/merges.txt similarity index 100% rename from distilbert/distilroberta_base_ledgar/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/merges.txt diff --git a/distilbert/distilroberta_base_ledgar/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_ledgar/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/model.safetensors diff --git a/distilbert/distilroberta_base_ledgar/run.log b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/run.log similarity index 100% rename from distilbert/distilroberta_base_ledgar/run.log rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/run.log diff --git a/distilbert/distilroberta_base_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/special_tokens_map.json diff --git a/distilbert/distilroberta_base_ledgar/test_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/test_results.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/test_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/test_results.json diff --git a/distilbert/distilroberta_base_ledgar/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/tokenizer.json diff --git a/distilbert/distilroberta_base_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/tokenizer_config.json diff --git a/distilbert/distilroberta_base_ledgar/train_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/train_results.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/train_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/train_results.json diff --git a/distilbert/distilroberta_base_ledgar/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/trainer_state.json diff --git a/distilbert/distilroberta_base_ledgar/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_ledgar/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/training_args.bin diff --git a/distilbert/distilroberta_base_ledgar/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/vocab.json similarity index 100% rename from distilbert/distilroberta_base_ledgar/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_ledgar/vocab.json diff --git a/distilbert/distilroberta_base_patent/README.md b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/README.md similarity index 100% rename from distilbert/distilroberta_base_patent/README.md rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/README.md diff --git a/distilbert/distilroberta_base_patent/all_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/all_results.json similarity index 100% rename from distilbert/distilroberta_base_patent/all_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/all_results.json diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/config.json similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/config.json diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/merges.txt similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/merges.txt diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/model.safetensors diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/optimizer.pt similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/optimizer.pt diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/rng_state_0.pth similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/rng_state_0.pth diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/rng_state_1.pth similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/rng_state_1.pth diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/scheduler.pt similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/scheduler.pt diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/special_tokens_map.json diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/tokenizer.json diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/tokenizer_config.json diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/trainer_state.json diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/training_args.bin diff --git a/distilbert/distilroberta_base_patent/checkpoint-1150/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/vocab.json similarity index 100% rename from distilbert/distilroberta_base_patent/checkpoint-1150/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/checkpoint-1150/vocab.json diff --git a/distilbert/distilroberta_base_patent/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/config.json similarity index 100% rename from distilbert/distilroberta_base_patent/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/config.json diff --git a/distilbert/distilroberta_base_patent/eval_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/eval_results.json similarity index 100% rename from distilbert/distilroberta_base_patent/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/eval_results.json diff --git a/distilbert/distilroberta_base_patent/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/merges.txt similarity index 100% rename from distilbert/distilroberta_base_patent/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/merges.txt diff --git a/distilbert/distilroberta_base_patent/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_patent/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/model.safetensors diff --git a/distilbert/distilroberta_base_patent/run.log b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/run.log similarity index 100% rename from distilbert/distilroberta_base_patent/run.log rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/run.log diff --git a/distilbert/distilroberta_base_patent/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_patent/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/special_tokens_map.json diff --git a/distilbert/distilroberta_base_patent/test_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/test_results.json similarity index 100% rename from distilbert/distilroberta_base_patent/test_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/test_results.json diff --git a/distilbert/distilroberta_base_patent/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_patent/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/tokenizer.json diff --git a/distilbert/distilroberta_base_patent/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_patent/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/tokenizer_config.json diff --git a/distilbert/distilroberta_base_patent/train_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/train_results.json similarity index 100% rename from distilbert/distilroberta_base_patent/train_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/train_results.json diff --git a/distilbert/distilroberta_base_patent/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_patent/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/trainer_state.json diff --git a/distilbert/distilroberta_base_patent/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_patent/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/training_args.bin diff --git a/distilbert/distilroberta_base_patent/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_patent/vocab.json similarity index 100% rename from distilbert/distilroberta_base_patent/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_patent/vocab.json diff --git a/distilbert/distilroberta_base_scotus/README.md b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/README.md similarity index 100% rename from distilbert/distilroberta_base_scotus/README.md rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/README.md diff --git a/distilbert/distilroberta_base_scotus/all_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/all_results.json similarity index 100% rename from distilbert/distilroberta_base_scotus/all_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/all_results.json diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/config.json similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/config.json diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/merges.txt similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/merges.txt diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/model.safetensors diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/optimizer.pt similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/optimizer.pt diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/rng_state_0.pth similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/rng_state_0.pth diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/rng_state_1.pth similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/rng_state_1.pth diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/scheduler.pt similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/scheduler.pt diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/special_tokens_map.json diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/tokenizer.json diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/tokenizer_config.json diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/trainer_state.json diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/training_args.bin diff --git a/distilbert/distilroberta_base_scotus/checkpoint-200/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/vocab.json similarity index 100% rename from distilbert/distilroberta_base_scotus/checkpoint-200/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/checkpoint-200/vocab.json diff --git a/distilbert/distilroberta_base_scotus/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/config.json similarity index 100% rename from distilbert/distilroberta_base_scotus/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/config.json diff --git a/distilbert/distilroberta_base_scotus/eval_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/eval_results.json similarity index 100% rename from distilbert/distilroberta_base_scotus/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/eval_results.json diff --git a/distilbert/distilroberta_base_scotus/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/merges.txt similarity index 100% rename from distilbert/distilroberta_base_scotus/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/merges.txt diff --git a/distilbert/distilroberta_base_scotus/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_scotus/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/model.safetensors diff --git a/distilbert/distilroberta_base_scotus/run.log b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/run.log similarity index 100% rename from distilbert/distilroberta_base_scotus/run.log rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/run.log diff --git a/distilbert/distilroberta_base_scotus/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/special_tokens_map.json diff --git a/distilbert/distilroberta_base_scotus/test_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/test_results.json similarity index 100% rename from distilbert/distilroberta_base_scotus/test_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/test_results.json diff --git a/distilbert/distilroberta_base_scotus/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_scotus/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/tokenizer.json diff --git a/distilbert/distilroberta_base_scotus/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/tokenizer_config.json diff --git a/distilbert/distilroberta_base_scotus/train_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/train_results.json similarity index 100% rename from distilbert/distilroberta_base_scotus/train_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/train_results.json diff --git a/distilbert/distilroberta_base_scotus/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_scotus/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/trainer_state.json diff --git a/distilbert/distilroberta_base_scotus/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_scotus/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/training_args.bin diff --git a/distilbert/distilroberta_base_scotus/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/vocab.json similarity index 100% rename from distilbert/distilroberta_base_scotus/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_scotus/vocab.json diff --git a/distilbert/distilroberta_base_twitter/README.md b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/README.md similarity index 100% rename from distilbert/distilroberta_base_twitter/README.md rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/README.md diff --git a/distilbert/distilroberta_base_twitter/all_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/all_results.json similarity index 100% rename from distilbert/distilroberta_base_twitter/all_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/all_results.json diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/config.json similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/config.json diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/merges.txt similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/merges.txt diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/model.safetensors diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/optimizer.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/optimizer.pt similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/optimizer.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/optimizer.pt diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/rng_state_0.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/rng_state_0.pth similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/rng_state_0.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/rng_state_0.pth diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/rng_state_1.pth b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/rng_state_1.pth similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/rng_state_1.pth rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/rng_state_1.pth diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/scheduler.pt b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/scheduler.pt similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/scheduler.pt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/scheduler.pt diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/special_tokens_map.json diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/tokenizer.json diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/tokenizer_config.json diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/trainer_state.json diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/training_args.bin diff --git a/distilbert/distilroberta_base_twitter/checkpoint-200/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/vocab.json similarity index 100% rename from distilbert/distilroberta_base_twitter/checkpoint-200/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/checkpoint-200/vocab.json diff --git a/distilbert/distilroberta_base_twitter/config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/config.json similarity index 100% rename from distilbert/distilroberta_base_twitter/config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/config.json diff --git a/distilbert/distilroberta_base_twitter/eval_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/eval_results.json similarity index 100% rename from distilbert/distilroberta_base_twitter/eval_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/eval_results.json diff --git a/distilbert/distilroberta_base_twitter/merges.txt b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/merges.txt similarity index 100% rename from distilbert/distilroberta_base_twitter/merges.txt rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/merges.txt diff --git a/distilbert/distilroberta_base_twitter/model.safetensors b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/model.safetensors similarity index 100% rename from distilbert/distilroberta_base_twitter/model.safetensors rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/model.safetensors diff --git a/distilbert/distilroberta_base_twitter/run.log b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/run.log similarity index 100% rename from distilbert/distilroberta_base_twitter/run.log rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/run.log diff --git a/distilbert/distilroberta_base_twitter/special_tokens_map.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/special_tokens_map.json similarity index 100% rename from distilbert/distilroberta_base_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/special_tokens_map.json diff --git a/distilbert/distilroberta_base_twitter/test_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/test_results.json similarity index 100% rename from distilbert/distilroberta_base_twitter/test_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/test_results.json diff --git a/distilbert/distilroberta_base_twitter/tokenizer.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/tokenizer.json similarity index 100% rename from distilbert/distilroberta_base_twitter/tokenizer.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/tokenizer.json diff --git a/distilbert/distilroberta_base_twitter/tokenizer_config.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/tokenizer_config.json similarity index 100% rename from distilbert/distilroberta_base_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/tokenizer_config.json diff --git a/distilbert/distilroberta_base_twitter/train_results.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/train_results.json similarity index 100% rename from distilbert/distilroberta_base_twitter/train_results.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/train_results.json diff --git a/distilbert/distilroberta_base_twitter/trainer_state.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/trainer_state.json similarity index 100% rename from distilbert/distilroberta_base_twitter/trainer_state.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/trainer_state.json diff --git a/distilbert/distilroberta_base_twitter/training_args.bin b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/training_args.bin similarity index 100% rename from distilbert/distilroberta_base_twitter/training_args.bin rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/training_args.bin diff --git a/distilbert/distilroberta_base_twitter/vocab.json b/max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/vocab.json similarity index 100% rename from distilbert/distilroberta_base_twitter/vocab.json rename to max_seq_length_128_experiments/distilbert/distilroberta_base_twitter/vocab.json diff --git a/google/flan_t5_base_amazon/README.md b/max_seq_length_128_experiments/google/flan_t5_base_amazon/README.md similarity index 100% rename from google/flan_t5_base_amazon/README.md rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/README.md diff --git a/google/flan_t5_base_amazon/all_results.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/all_results.json similarity index 100% rename from google/flan_t5_base_amazon/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/all_results.json diff --git a/google/flan_t5_base_amazon/checkpoint-750/config.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/config.json similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/config.json diff --git a/google/flan_t5_base_amazon/checkpoint-750/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/model.safetensors similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/model.safetensors diff --git a/google/flan_t5_base_amazon/checkpoint-750/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/optimizer.pt similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/optimizer.pt diff --git a/google/flan_t5_base_amazon/checkpoint-750/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/rng_state_0.pth similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/rng_state_0.pth diff --git a/google/flan_t5_base_amazon/checkpoint-750/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/rng_state_1.pth similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/rng_state_1.pth diff --git a/google/flan_t5_base_amazon/checkpoint-750/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/scheduler.pt similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/scheduler.pt diff --git a/google/flan_t5_base_amazon/checkpoint-750/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/special_tokens_map.json diff --git a/google/flan_t5_base_amazon/checkpoint-750/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/spiece.model similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/spiece.model diff --git a/google/flan_t5_base_amazon/checkpoint-750/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/tokenizer.json similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/tokenizer.json diff --git a/google/flan_t5_base_amazon/checkpoint-750/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/tokenizer_config.json diff --git a/google/flan_t5_base_amazon/checkpoint-750/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/trainer_state.json similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/trainer_state.json diff --git a/google/flan_t5_base_amazon/checkpoint-750/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/training_args.bin similarity index 100% rename from google/flan_t5_base_amazon/checkpoint-750/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/checkpoint-750/training_args.bin diff --git a/google/flan_t5_base_amazon/config.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/config.json similarity index 100% rename from google/flan_t5_base_amazon/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/config.json diff --git a/google/flan_t5_base_amazon/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/eval_results.json similarity index 100% rename from google/flan_t5_base_amazon/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/eval_results.json diff --git a/google/flan_t5_base_amazon/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_amazon/model.safetensors similarity index 100% rename from google/flan_t5_base_amazon/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/model.safetensors diff --git a/google/flan_t5_base_amazon/run.log b/max_seq_length_128_experiments/google/flan_t5_base_amazon/run.log similarity index 100% rename from google/flan_t5_base_amazon/run.log rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/run.log diff --git a/google/flan_t5_base_amazon/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/special_tokens_map.json diff --git a/google/flan_t5_base_amazon/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_amazon/spiece.model similarity index 100% rename from google/flan_t5_base_amazon/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/spiece.model diff --git a/google/flan_t5_base_amazon/test_results.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/test_results.json similarity index 100% rename from google/flan_t5_base_amazon/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/test_results.json diff --git a/google/flan_t5_base_amazon/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/tokenizer.json similarity index 100% rename from google/flan_t5_base_amazon/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/tokenizer.json diff --git a/google/flan_t5_base_amazon/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/tokenizer_config.json diff --git a/google/flan_t5_base_amazon/train_results.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/train_results.json similarity index 100% rename from google/flan_t5_base_amazon/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/train_results.json diff --git a/google/flan_t5_base_amazon/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_amazon/trainer_state.json similarity index 100% rename from google/flan_t5_base_amazon/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/trainer_state.json diff --git a/google/flan_t5_base_amazon/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_amazon/training_args.bin similarity index 100% rename from google/flan_t5_base_amazon/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_amazon/training_args.bin diff --git a/google/flan_t5_base_ledgar/README.md b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/README.md similarity index 100% rename from google/flan_t5_base_ledgar/README.md rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/README.md diff --git a/google/flan_t5_base_ledgar/all_results.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/all_results.json similarity index 100% rename from google/flan_t5_base_ledgar/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/all_results.json diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/config.json similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/config.json diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/model.safetensors similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/model.safetensors diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/optimizer.pt similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/optimizer.pt diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/scheduler.pt diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/spiece.model similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/spiece.model diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/tokenizer.json diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/trainer_state.json diff --git a/google/flan_t5_base_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from google/flan_t5_base_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/checkpoint-2800/training_args.bin diff --git a/google/flan_t5_base_ledgar/config.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/config.json similarity index 100% rename from google/flan_t5_base_ledgar/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/config.json diff --git a/google/flan_t5_base_ledgar/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/eval_results.json similarity index 100% rename from google/flan_t5_base_ledgar/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/eval_results.json diff --git a/google/flan_t5_base_ledgar/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/model.safetensors similarity index 100% rename from google/flan_t5_base_ledgar/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/model.safetensors diff --git a/google/flan_t5_base_ledgar/run.log b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/run.log similarity index 100% rename from google/flan_t5_base_ledgar/run.log rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/run.log diff --git a/google/flan_t5_base_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/special_tokens_map.json diff --git a/google/flan_t5_base_ledgar/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/spiece.model similarity index 100% rename from google/flan_t5_base_ledgar/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/spiece.model diff --git a/google/flan_t5_base_ledgar/test_results.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/test_results.json similarity index 100% rename from google/flan_t5_base_ledgar/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/test_results.json diff --git a/google/flan_t5_base_ledgar/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/tokenizer.json similarity index 100% rename from google/flan_t5_base_ledgar/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/tokenizer.json diff --git a/google/flan_t5_base_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/tokenizer_config.json diff --git a/google/flan_t5_base_ledgar/train_results.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/train_results.json similarity index 100% rename from google/flan_t5_base_ledgar/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/train_results.json diff --git a/google/flan_t5_base_ledgar/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/trainer_state.json similarity index 100% rename from google/flan_t5_base_ledgar/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/trainer_state.json diff --git a/google/flan_t5_base_ledgar/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_ledgar/training_args.bin similarity index 100% rename from google/flan_t5_base_ledgar/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_ledgar/training_args.bin diff --git a/google/flan_t5_base_patent/README.md b/max_seq_length_128_experiments/google/flan_t5_base_patent/README.md similarity index 100% rename from google/flan_t5_base_patent/README.md rename to max_seq_length_128_experiments/google/flan_t5_base_patent/README.md diff --git a/google/flan_t5_base_patent/all_results.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/all_results.json similarity index 100% rename from google/flan_t5_base_patent/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/all_results.json diff --git a/google/flan_t5_base_patent/checkpoint-1450/config.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/config.json similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/config.json diff --git a/google/flan_t5_base_patent/checkpoint-1450/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/model.safetensors similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/model.safetensors diff --git a/google/flan_t5_base_patent/checkpoint-1450/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/optimizer.pt similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/optimizer.pt diff --git a/google/flan_t5_base_patent/checkpoint-1450/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/rng_state_0.pth similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/rng_state_0.pth diff --git a/google/flan_t5_base_patent/checkpoint-1450/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/rng_state_1.pth similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/rng_state_1.pth diff --git a/google/flan_t5_base_patent/checkpoint-1450/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/scheduler.pt similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/scheduler.pt diff --git a/google/flan_t5_base_patent/checkpoint-1450/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/special_tokens_map.json diff --git a/google/flan_t5_base_patent/checkpoint-1450/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/spiece.model similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/spiece.model diff --git a/google/flan_t5_base_patent/checkpoint-1450/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/tokenizer.json similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/tokenizer.json diff --git a/google/flan_t5_base_patent/checkpoint-1450/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/tokenizer_config.json diff --git a/google/flan_t5_base_patent/checkpoint-1450/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/trainer_state.json similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/trainer_state.json diff --git a/google/flan_t5_base_patent/checkpoint-1450/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/training_args.bin similarity index 100% rename from google/flan_t5_base_patent/checkpoint-1450/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_patent/checkpoint-1450/training_args.bin diff --git a/google/flan_t5_base_patent/config.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/config.json similarity index 100% rename from google/flan_t5_base_patent/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/config.json diff --git a/google/flan_t5_base_patent/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/eval_results.json similarity index 100% rename from google/flan_t5_base_patent/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/eval_results.json diff --git a/google/flan_t5_base_patent/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_patent/model.safetensors similarity index 100% rename from google/flan_t5_base_patent/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_patent/model.safetensors diff --git a/google/flan_t5_base_patent/run.log b/max_seq_length_128_experiments/google/flan_t5_base_patent/run.log similarity index 100% rename from google/flan_t5_base_patent/run.log rename to max_seq_length_128_experiments/google/flan_t5_base_patent/run.log diff --git a/google/flan_t5_base_patent/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_patent/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/special_tokens_map.json diff --git a/google/flan_t5_base_patent/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_patent/spiece.model similarity index 100% rename from google/flan_t5_base_patent/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_patent/spiece.model diff --git a/google/flan_t5_base_patent/test_results.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/test_results.json similarity index 100% rename from google/flan_t5_base_patent/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/test_results.json diff --git a/google/flan_t5_base_patent/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/tokenizer.json similarity index 100% rename from google/flan_t5_base_patent/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/tokenizer.json diff --git a/google/flan_t5_base_patent/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_patent/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/tokenizer_config.json diff --git a/google/flan_t5_base_patent/train_results.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/train_results.json similarity index 100% rename from google/flan_t5_base_patent/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/train_results.json diff --git a/google/flan_t5_base_patent/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_patent/trainer_state.json similarity index 100% rename from google/flan_t5_base_patent/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_patent/trainer_state.json diff --git a/google/flan_t5_base_patent/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_patent/training_args.bin similarity index 100% rename from google/flan_t5_base_patent/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_patent/training_args.bin diff --git a/google/flan_t5_base_scotus/README.md b/max_seq_length_128_experiments/google/flan_t5_base_scotus/README.md similarity index 100% rename from google/flan_t5_base_scotus/README.md rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/README.md diff --git a/google/flan_t5_base_scotus/all_results.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/all_results.json similarity index 100% rename from google/flan_t5_base_scotus/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/all_results.json diff --git a/google/flan_t5_base_scotus/checkpoint-450/config.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/config.json similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/config.json diff --git a/google/flan_t5_base_scotus/checkpoint-450/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/model.safetensors similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/model.safetensors diff --git a/google/flan_t5_base_scotus/checkpoint-450/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/optimizer.pt similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/optimizer.pt diff --git a/google/flan_t5_base_scotus/checkpoint-450/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/rng_state_0.pth similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/rng_state_0.pth diff --git a/google/flan_t5_base_scotus/checkpoint-450/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/rng_state_1.pth similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/rng_state_1.pth diff --git a/google/flan_t5_base_scotus/checkpoint-450/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/scheduler.pt similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/scheduler.pt diff --git a/google/flan_t5_base_scotus/checkpoint-450/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/special_tokens_map.json diff --git a/google/flan_t5_base_scotus/checkpoint-450/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/spiece.model similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/spiece.model diff --git a/google/flan_t5_base_scotus/checkpoint-450/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/tokenizer.json similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/tokenizer.json diff --git a/google/flan_t5_base_scotus/checkpoint-450/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/tokenizer_config.json diff --git a/google/flan_t5_base_scotus/checkpoint-450/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/trainer_state.json similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/trainer_state.json diff --git a/google/flan_t5_base_scotus/checkpoint-450/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/training_args.bin similarity index 100% rename from google/flan_t5_base_scotus/checkpoint-450/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/checkpoint-450/training_args.bin diff --git a/google/flan_t5_base_scotus/config.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/config.json similarity index 100% rename from google/flan_t5_base_scotus/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/config.json diff --git a/google/flan_t5_base_scotus/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/eval_results.json similarity index 100% rename from google/flan_t5_base_scotus/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/eval_results.json diff --git a/google/flan_t5_base_scotus/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_scotus/model.safetensors similarity index 100% rename from google/flan_t5_base_scotus/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/model.safetensors diff --git a/google/flan_t5_base_scotus/run.log b/max_seq_length_128_experiments/google/flan_t5_base_scotus/run.log similarity index 100% rename from google/flan_t5_base_scotus/run.log rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/run.log diff --git a/google/flan_t5_base_scotus/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/special_tokens_map.json diff --git a/google/flan_t5_base_scotus/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_scotus/spiece.model similarity index 100% rename from google/flan_t5_base_scotus/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/spiece.model diff --git a/google/flan_t5_base_scotus/test_results.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/test_results.json similarity index 100% rename from google/flan_t5_base_scotus/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/test_results.json diff --git a/google/flan_t5_base_scotus/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/tokenizer.json similarity index 100% rename from google/flan_t5_base_scotus/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/tokenizer.json diff --git a/google/flan_t5_base_scotus/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/tokenizer_config.json diff --git a/google/flan_t5_base_scotus/train_results.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/train_results.json similarity index 100% rename from google/flan_t5_base_scotus/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/train_results.json diff --git a/google/flan_t5_base_scotus/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_scotus/trainer_state.json similarity index 100% rename from google/flan_t5_base_scotus/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/trainer_state.json diff --git a/google/flan_t5_base_scotus/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_scotus/training_args.bin similarity index 100% rename from google/flan_t5_base_scotus/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_scotus/training_args.bin diff --git a/google/flan_t5_base_twitter/README.md b/max_seq_length_128_experiments/google/flan_t5_base_twitter/README.md similarity index 100% rename from google/flan_t5_base_twitter/README.md rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/README.md diff --git a/google/flan_t5_base_twitter/all_results.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/all_results.json similarity index 100% rename from google/flan_t5_base_twitter/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/all_results.json diff --git a/google/flan_t5_base_twitter/checkpoint-50/config.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/config.json similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/config.json diff --git a/google/flan_t5_base_twitter/checkpoint-50/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/model.safetensors similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/model.safetensors diff --git a/google/flan_t5_base_twitter/checkpoint-50/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/optimizer.pt similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/optimizer.pt diff --git a/google/flan_t5_base_twitter/checkpoint-50/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/rng_state_0.pth similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/rng_state_0.pth diff --git a/google/flan_t5_base_twitter/checkpoint-50/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/rng_state_1.pth similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/rng_state_1.pth diff --git a/google/flan_t5_base_twitter/checkpoint-50/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/scheduler.pt similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/scheduler.pt diff --git a/google/flan_t5_base_twitter/checkpoint-50/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/special_tokens_map.json diff --git a/google/flan_t5_base_twitter/checkpoint-50/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/spiece.model similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/spiece.model diff --git a/google/flan_t5_base_twitter/checkpoint-50/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/tokenizer.json similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/tokenizer.json diff --git a/google/flan_t5_base_twitter/checkpoint-50/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/tokenizer_config.json diff --git a/google/flan_t5_base_twitter/checkpoint-50/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/trainer_state.json similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/trainer_state.json diff --git a/google/flan_t5_base_twitter/checkpoint-50/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/training_args.bin similarity index 100% rename from google/flan_t5_base_twitter/checkpoint-50/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/checkpoint-50/training_args.bin diff --git a/google/flan_t5_base_twitter/config.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/config.json similarity index 100% rename from google/flan_t5_base_twitter/config.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/config.json diff --git a/google/flan_t5_base_twitter/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/eval_results.json similarity index 100% rename from google/flan_t5_base_twitter/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/eval_results.json diff --git a/google/flan_t5_base_twitter/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_base_twitter/model.safetensors similarity index 100% rename from google/flan_t5_base_twitter/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/model.safetensors diff --git a/google/flan_t5_base_twitter/run.log b/max_seq_length_128_experiments/google/flan_t5_base_twitter/run.log similarity index 100% rename from google/flan_t5_base_twitter/run.log rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/run.log diff --git a/google/flan_t5_base_twitter/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/special_tokens_map.json similarity index 100% rename from google/flan_t5_base_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/special_tokens_map.json diff --git a/google/flan_t5_base_twitter/spiece.model b/max_seq_length_128_experiments/google/flan_t5_base_twitter/spiece.model similarity index 100% rename from google/flan_t5_base_twitter/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/spiece.model diff --git a/google/flan_t5_base_twitter/test_results.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/test_results.json similarity index 100% rename from google/flan_t5_base_twitter/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/test_results.json diff --git a/google/flan_t5_base_twitter/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/tokenizer.json similarity index 100% rename from google/flan_t5_base_twitter/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/tokenizer.json diff --git a/google/flan_t5_base_twitter/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/tokenizer_config.json similarity index 100% rename from google/flan_t5_base_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/tokenizer_config.json diff --git a/google/flan_t5_base_twitter/train_results.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/train_results.json similarity index 100% rename from google/flan_t5_base_twitter/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/train_results.json diff --git a/google/flan_t5_base_twitter/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_base_twitter/trainer_state.json similarity index 100% rename from google/flan_t5_base_twitter/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/trainer_state.json diff --git a/google/flan_t5_base_twitter/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_base_twitter/training_args.bin similarity index 100% rename from google/flan_t5_base_twitter/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_base_twitter/training_args.bin diff --git a/google/flan_t5_small_amazon/README.md b/max_seq_length_128_experiments/google/flan_t5_small_amazon/README.md similarity index 100% rename from google/flan_t5_small_amazon/README.md rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/README.md diff --git a/google/flan_t5_small_amazon/all_results.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/all_results.json similarity index 100% rename from google/flan_t5_small_amazon/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/all_results.json diff --git a/google/flan_t5_small_amazon/checkpoint-1100/config.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/config.json similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/config.json diff --git a/google/flan_t5_small_amazon/checkpoint-1100/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/model.safetensors similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/model.safetensors diff --git a/google/flan_t5_small_amazon/checkpoint-1100/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/optimizer.pt similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/optimizer.pt diff --git a/google/flan_t5_small_amazon/checkpoint-1100/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/rng_state_0.pth similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/rng_state_0.pth diff --git a/google/flan_t5_small_amazon/checkpoint-1100/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/rng_state_1.pth similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/rng_state_1.pth diff --git a/google/flan_t5_small_amazon/checkpoint-1100/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/scheduler.pt similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/scheduler.pt diff --git a/google/flan_t5_small_amazon/checkpoint-1100/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/special_tokens_map.json diff --git a/google/flan_t5_small_amazon/checkpoint-1100/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/spiece.model similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/spiece.model diff --git a/google/flan_t5_small_amazon/checkpoint-1100/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/tokenizer.json similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/tokenizer.json diff --git a/google/flan_t5_small_amazon/checkpoint-1100/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/tokenizer_config.json diff --git a/google/flan_t5_small_amazon/checkpoint-1100/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/trainer_state.json similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/trainer_state.json diff --git a/google/flan_t5_small_amazon/checkpoint-1100/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/training_args.bin similarity index 100% rename from google/flan_t5_small_amazon/checkpoint-1100/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/checkpoint-1100/training_args.bin diff --git a/google/flan_t5_small_amazon/config.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/config.json similarity index 100% rename from google/flan_t5_small_amazon/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/config.json diff --git a/google/flan_t5_small_amazon/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/eval_results.json similarity index 100% rename from google/flan_t5_small_amazon/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/eval_results.json diff --git a/google/flan_t5_small_amazon/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_amazon/model.safetensors similarity index 100% rename from google/flan_t5_small_amazon/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/model.safetensors diff --git a/google/flan_t5_small_amazon/run.log b/max_seq_length_128_experiments/google/flan_t5_small_amazon/run.log similarity index 100% rename from google/flan_t5_small_amazon/run.log rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/run.log diff --git a/google/flan_t5_small_amazon/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/special_tokens_map.json diff --git a/google/flan_t5_small_amazon/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_amazon/spiece.model similarity index 100% rename from google/flan_t5_small_amazon/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/spiece.model diff --git a/google/flan_t5_small_amazon/test_results.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/test_results.json similarity index 100% rename from google/flan_t5_small_amazon/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/test_results.json diff --git a/google/flan_t5_small_amazon/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/tokenizer.json similarity index 100% rename from google/flan_t5_small_amazon/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/tokenizer.json diff --git a/google/flan_t5_small_amazon/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/tokenizer_config.json diff --git a/google/flan_t5_small_amazon/train_results.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/train_results.json similarity index 100% rename from google/flan_t5_small_amazon/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/train_results.json diff --git a/google/flan_t5_small_amazon/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_amazon/trainer_state.json similarity index 100% rename from google/flan_t5_small_amazon/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/trainer_state.json diff --git a/google/flan_t5_small_amazon/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_amazon/training_args.bin similarity index 100% rename from google/flan_t5_small_amazon/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_amazon/training_args.bin diff --git a/google/flan_t5_small_ledgar/README.md b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/README.md similarity index 100% rename from google/flan_t5_small_ledgar/README.md rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/README.md diff --git a/google/flan_t5_small_ledgar/all_results.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/all_results.json similarity index 100% rename from google/flan_t5_small_ledgar/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/all_results.json diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/config.json similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/config.json diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/model.safetensors similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/model.safetensors diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/optimizer.pt similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/optimizer.pt diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/scheduler.pt diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/spiece.model similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/spiece.model diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/tokenizer.json diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/trainer_state.json diff --git a/google/flan_t5_small_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from google/flan_t5_small_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/checkpoint-2800/training_args.bin diff --git a/google/flan_t5_small_ledgar/config.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/config.json similarity index 100% rename from google/flan_t5_small_ledgar/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/config.json diff --git a/google/flan_t5_small_ledgar/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/eval_results.json similarity index 100% rename from google/flan_t5_small_ledgar/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/eval_results.json diff --git a/google/flan_t5_small_ledgar/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/model.safetensors similarity index 100% rename from google/flan_t5_small_ledgar/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/model.safetensors diff --git a/google/flan_t5_small_ledgar/run.log b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/run.log similarity index 100% rename from google/flan_t5_small_ledgar/run.log rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/run.log diff --git a/google/flan_t5_small_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/special_tokens_map.json diff --git a/google/flan_t5_small_ledgar/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/spiece.model similarity index 100% rename from google/flan_t5_small_ledgar/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/spiece.model diff --git a/google/flan_t5_small_ledgar/test_results.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/test_results.json similarity index 100% rename from google/flan_t5_small_ledgar/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/test_results.json diff --git a/google/flan_t5_small_ledgar/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/tokenizer.json similarity index 100% rename from google/flan_t5_small_ledgar/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/tokenizer.json diff --git a/google/flan_t5_small_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/tokenizer_config.json diff --git a/google/flan_t5_small_ledgar/train_results.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/train_results.json similarity index 100% rename from google/flan_t5_small_ledgar/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/train_results.json diff --git a/google/flan_t5_small_ledgar/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/trainer_state.json similarity index 100% rename from google/flan_t5_small_ledgar/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/trainer_state.json diff --git a/google/flan_t5_small_ledgar/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_ledgar/training_args.bin similarity index 100% rename from google/flan_t5_small_ledgar/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_ledgar/training_args.bin diff --git a/google/flan_t5_small_patent/README.md b/max_seq_length_128_experiments/google/flan_t5_small_patent/README.md similarity index 100% rename from google/flan_t5_small_patent/README.md rename to max_seq_length_128_experiments/google/flan_t5_small_patent/README.md diff --git a/google/flan_t5_small_patent/all_results.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/all_results.json similarity index 100% rename from google/flan_t5_small_patent/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/all_results.json diff --git a/google/flan_t5_small_patent/checkpoint-1450/config.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/config.json similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/config.json diff --git a/google/flan_t5_small_patent/checkpoint-1450/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/model.safetensors similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/model.safetensors diff --git a/google/flan_t5_small_patent/checkpoint-1450/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/optimizer.pt similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/optimizer.pt diff --git a/google/flan_t5_small_patent/checkpoint-1450/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/rng_state_0.pth similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/rng_state_0.pth diff --git a/google/flan_t5_small_patent/checkpoint-1450/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/rng_state_1.pth similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/rng_state_1.pth diff --git a/google/flan_t5_small_patent/checkpoint-1450/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/scheduler.pt similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/scheduler.pt diff --git a/google/flan_t5_small_patent/checkpoint-1450/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/special_tokens_map.json diff --git a/google/flan_t5_small_patent/checkpoint-1450/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/spiece.model similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/spiece.model diff --git a/google/flan_t5_small_patent/checkpoint-1450/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/tokenizer.json similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/tokenizer.json diff --git a/google/flan_t5_small_patent/checkpoint-1450/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/tokenizer_config.json diff --git a/google/flan_t5_small_patent/checkpoint-1450/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/trainer_state.json similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/trainer_state.json diff --git a/google/flan_t5_small_patent/checkpoint-1450/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/training_args.bin similarity index 100% rename from google/flan_t5_small_patent/checkpoint-1450/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_patent/checkpoint-1450/training_args.bin diff --git a/google/flan_t5_small_patent/config.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/config.json similarity index 100% rename from google/flan_t5_small_patent/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/config.json diff --git a/google/flan_t5_small_patent/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/eval_results.json similarity index 100% rename from google/flan_t5_small_patent/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/eval_results.json diff --git a/google/flan_t5_small_patent/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_patent/model.safetensors similarity index 100% rename from google/flan_t5_small_patent/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_patent/model.safetensors diff --git a/google/flan_t5_small_patent/run.log b/max_seq_length_128_experiments/google/flan_t5_small_patent/run.log similarity index 100% rename from google/flan_t5_small_patent/run.log rename to max_seq_length_128_experiments/google/flan_t5_small_patent/run.log diff --git a/google/flan_t5_small_patent/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_patent/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/special_tokens_map.json diff --git a/google/flan_t5_small_patent/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_patent/spiece.model similarity index 100% rename from google/flan_t5_small_patent/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_patent/spiece.model diff --git a/google/flan_t5_small_patent/test_results.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/test_results.json similarity index 100% rename from google/flan_t5_small_patent/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/test_results.json diff --git a/google/flan_t5_small_patent/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/tokenizer.json similarity index 100% rename from google/flan_t5_small_patent/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/tokenizer.json diff --git a/google/flan_t5_small_patent/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_patent/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/tokenizer_config.json diff --git a/google/flan_t5_small_patent/train_results.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/train_results.json similarity index 100% rename from google/flan_t5_small_patent/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/train_results.json diff --git a/google/flan_t5_small_patent/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_patent/trainer_state.json similarity index 100% rename from google/flan_t5_small_patent/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_patent/trainer_state.json diff --git a/google/flan_t5_small_patent/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_patent/training_args.bin similarity index 100% rename from google/flan_t5_small_patent/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_patent/training_args.bin diff --git a/google/flan_t5_small_scotus/README.md b/max_seq_length_128_experiments/google/flan_t5_small_scotus/README.md similarity index 100% rename from google/flan_t5_small_scotus/README.md rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/README.md diff --git a/google/flan_t5_small_scotus/all_results.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/all_results.json similarity index 100% rename from google/flan_t5_small_scotus/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/all_results.json diff --git a/google/flan_t5_small_scotus/checkpoint-450/config.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/config.json similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/config.json diff --git a/google/flan_t5_small_scotus/checkpoint-450/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/model.safetensors similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/model.safetensors diff --git a/google/flan_t5_small_scotus/checkpoint-450/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/optimizer.pt similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/optimizer.pt diff --git a/google/flan_t5_small_scotus/checkpoint-450/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/rng_state_0.pth similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/rng_state_0.pth diff --git a/google/flan_t5_small_scotus/checkpoint-450/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/rng_state_1.pth similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/rng_state_1.pth diff --git a/google/flan_t5_small_scotus/checkpoint-450/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/scheduler.pt similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/scheduler.pt diff --git a/google/flan_t5_small_scotus/checkpoint-450/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/special_tokens_map.json diff --git a/google/flan_t5_small_scotus/checkpoint-450/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/spiece.model similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/spiece.model diff --git a/google/flan_t5_small_scotus/checkpoint-450/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/tokenizer.json similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/tokenizer.json diff --git a/google/flan_t5_small_scotus/checkpoint-450/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/tokenizer_config.json diff --git a/google/flan_t5_small_scotus/checkpoint-450/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/trainer_state.json similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/trainer_state.json diff --git a/google/flan_t5_small_scotus/checkpoint-450/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/training_args.bin similarity index 100% rename from google/flan_t5_small_scotus/checkpoint-450/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/checkpoint-450/training_args.bin diff --git a/google/flan_t5_small_scotus/config.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/config.json similarity index 100% rename from google/flan_t5_small_scotus/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/config.json diff --git a/google/flan_t5_small_scotus/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/eval_results.json similarity index 100% rename from google/flan_t5_small_scotus/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/eval_results.json diff --git a/google/flan_t5_small_scotus/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_scotus/model.safetensors similarity index 100% rename from google/flan_t5_small_scotus/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/model.safetensors diff --git a/google/flan_t5_small_scotus/run.log b/max_seq_length_128_experiments/google/flan_t5_small_scotus/run.log similarity index 100% rename from google/flan_t5_small_scotus/run.log rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/run.log diff --git a/google/flan_t5_small_scotus/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/special_tokens_map.json diff --git a/google/flan_t5_small_scotus/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_scotus/spiece.model similarity index 100% rename from google/flan_t5_small_scotus/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/spiece.model diff --git a/google/flan_t5_small_scotus/test_results.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/test_results.json similarity index 100% rename from google/flan_t5_small_scotus/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/test_results.json diff --git a/google/flan_t5_small_scotus/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/tokenizer.json similarity index 100% rename from google/flan_t5_small_scotus/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/tokenizer.json diff --git a/google/flan_t5_small_scotus/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/tokenizer_config.json diff --git a/google/flan_t5_small_scotus/train_results.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/train_results.json similarity index 100% rename from google/flan_t5_small_scotus/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/train_results.json diff --git a/google/flan_t5_small_scotus/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_scotus/trainer_state.json similarity index 100% rename from google/flan_t5_small_scotus/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/trainer_state.json diff --git a/google/flan_t5_small_scotus/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_scotus/training_args.bin similarity index 100% rename from google/flan_t5_small_scotus/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_scotus/training_args.bin diff --git a/google/flan_t5_small_twitter/README.md b/max_seq_length_128_experiments/google/flan_t5_small_twitter/README.md similarity index 100% rename from google/flan_t5_small_twitter/README.md rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/README.md diff --git a/google/flan_t5_small_twitter/all_results.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/all_results.json similarity index 100% rename from google/flan_t5_small_twitter/all_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/all_results.json diff --git a/google/flan_t5_small_twitter/checkpoint-200/config.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/config.json similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/config.json diff --git a/google/flan_t5_small_twitter/checkpoint-200/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/model.safetensors similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/model.safetensors diff --git a/google/flan_t5_small_twitter/checkpoint-200/optimizer.pt b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/optimizer.pt similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/optimizer.pt rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/optimizer.pt diff --git a/google/flan_t5_small_twitter/checkpoint-200/rng_state_0.pth b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/rng_state_0.pth similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/rng_state_0.pth rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/rng_state_0.pth diff --git a/google/flan_t5_small_twitter/checkpoint-200/rng_state_1.pth b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/rng_state_1.pth similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/rng_state_1.pth rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/rng_state_1.pth diff --git a/google/flan_t5_small_twitter/checkpoint-200/scheduler.pt b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/scheduler.pt similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/scheduler.pt rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/scheduler.pt diff --git a/google/flan_t5_small_twitter/checkpoint-200/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/special_tokens_map.json diff --git a/google/flan_t5_small_twitter/checkpoint-200/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/spiece.model similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/spiece.model diff --git a/google/flan_t5_small_twitter/checkpoint-200/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/tokenizer.json similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/tokenizer.json diff --git a/google/flan_t5_small_twitter/checkpoint-200/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/tokenizer_config.json diff --git a/google/flan_t5_small_twitter/checkpoint-200/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/trainer_state.json similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/trainer_state.json diff --git a/google/flan_t5_small_twitter/checkpoint-200/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/training_args.bin similarity index 100% rename from google/flan_t5_small_twitter/checkpoint-200/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/checkpoint-200/training_args.bin diff --git a/google/flan_t5_small_twitter/config.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/config.json similarity index 100% rename from google/flan_t5_small_twitter/config.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/config.json diff --git a/google/flan_t5_small_twitter/eval_results.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/eval_results.json similarity index 100% rename from google/flan_t5_small_twitter/eval_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/eval_results.json diff --git a/google/flan_t5_small_twitter/model.safetensors b/max_seq_length_128_experiments/google/flan_t5_small_twitter/model.safetensors similarity index 100% rename from google/flan_t5_small_twitter/model.safetensors rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/model.safetensors diff --git a/google/flan_t5_small_twitter/run.log b/max_seq_length_128_experiments/google/flan_t5_small_twitter/run.log similarity index 100% rename from google/flan_t5_small_twitter/run.log rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/run.log diff --git a/google/flan_t5_small_twitter/special_tokens_map.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/special_tokens_map.json similarity index 100% rename from google/flan_t5_small_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/special_tokens_map.json diff --git a/google/flan_t5_small_twitter/spiece.model b/max_seq_length_128_experiments/google/flan_t5_small_twitter/spiece.model similarity index 100% rename from google/flan_t5_small_twitter/spiece.model rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/spiece.model diff --git a/google/flan_t5_small_twitter/test_results.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/test_results.json similarity index 100% rename from google/flan_t5_small_twitter/test_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/test_results.json diff --git a/google/flan_t5_small_twitter/tokenizer.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/tokenizer.json similarity index 100% rename from google/flan_t5_small_twitter/tokenizer.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/tokenizer.json diff --git a/google/flan_t5_small_twitter/tokenizer_config.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/tokenizer_config.json similarity index 100% rename from google/flan_t5_small_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/tokenizer_config.json diff --git a/google/flan_t5_small_twitter/train_results.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/train_results.json similarity index 100% rename from google/flan_t5_small_twitter/train_results.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/train_results.json diff --git a/google/flan_t5_small_twitter/trainer_state.json b/max_seq_length_128_experiments/google/flan_t5_small_twitter/trainer_state.json similarity index 100% rename from google/flan_t5_small_twitter/trainer_state.json rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/trainer_state.json diff --git a/google/flan_t5_small_twitter/training_args.bin b/max_seq_length_128_experiments/google/flan_t5_small_twitter/training_args.bin similarity index 100% rename from google/flan_t5_small_twitter/training_args.bin rename to max_seq_length_128_experiments/google/flan_t5_small_twitter/training_args.bin diff --git a/google/gemma_2b_amazon/README.md b/max_seq_length_128_experiments/google/gemma_2b_amazon/README.md similarity index 100% rename from google/gemma_2b_amazon/README.md rename to max_seq_length_128_experiments/google/gemma_2b_amazon/README.md diff --git a/google/gemma_2b_amazon/all_results.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/all_results.json similarity index 100% rename from google/gemma_2b_amazon/all_results.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/all_results.json diff --git a/google/gemma_2b_amazon/checkpoint-350/config.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/config.json similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/config.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/config.json diff --git a/google/gemma_2b_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt diff --git a/google/gemma_2b_amazon/checkpoint-350/latest b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/latest similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/latest rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/latest diff --git a/google/gemma_2b_amazon/checkpoint-350/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/model-00001-of-00002.safetensors similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/model-00001-of-00002.safetensors diff --git a/google/gemma_2b_amazon/checkpoint-350/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/model-00002-of-00002.safetensors similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/model-00002-of-00002.safetensors diff --git a/google/gemma_2b_amazon/checkpoint-350/model.safetensors.index.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/model.safetensors.index.json similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/model.safetensors.index.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/model.safetensors.index.json diff --git a/google/gemma_2b_amazon/checkpoint-350/rng_state_0.pth b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/rng_state_0.pth similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/rng_state_0.pth rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/rng_state_0.pth diff --git a/google/gemma_2b_amazon/checkpoint-350/rng_state_1.pth b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/rng_state_1.pth similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/rng_state_1.pth rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/rng_state_1.pth diff --git a/google/gemma_2b_amazon/checkpoint-350/scheduler.pt b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/scheduler.pt similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/scheduler.pt rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/scheduler.pt diff --git a/google/gemma_2b_amazon/checkpoint-350/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/special_tokens_map.json similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/special_tokens_map.json diff --git a/google/gemma_2b_amazon/checkpoint-350/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/tokenizer.json similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/tokenizer.json diff --git a/google/gemma_2b_amazon/checkpoint-350/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/tokenizer.model similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/tokenizer.model diff --git a/google/gemma_2b_amazon/checkpoint-350/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/tokenizer_config.json similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/tokenizer_config.json diff --git a/google/gemma_2b_amazon/checkpoint-350/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/trainer_state.json similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/trainer_state.json diff --git a/google/gemma_2b_amazon/checkpoint-350/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/training_args.bin similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/training_args.bin diff --git a/google/gemma_2b_amazon/checkpoint-350/zero_to_fp32.py b/max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/zero_to_fp32.py similarity index 100% rename from google/gemma_2b_amazon/checkpoint-350/zero_to_fp32.py rename to max_seq_length_128_experiments/google/gemma_2b_amazon/checkpoint-350/zero_to_fp32.py diff --git a/google/gemma_2b_amazon/config.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/config.json similarity index 100% rename from google/gemma_2b_amazon/config.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/config.json diff --git a/google/gemma_2b_amazon/eval_results.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/eval_results.json similarity index 100% rename from google/gemma_2b_amazon/eval_results.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/eval_results.json diff --git a/google/gemma_2b_amazon/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_amazon/model-00001-of-00002.safetensors similarity index 100% rename from google/gemma_2b_amazon/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_amazon/model-00001-of-00002.safetensors diff --git a/google/gemma_2b_amazon/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_amazon/model-00002-of-00002.safetensors similarity index 100% rename from google/gemma_2b_amazon/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_amazon/model-00002-of-00002.safetensors diff --git a/google/gemma_2b_amazon/model.safetensors.index.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/model.safetensors.index.json similarity index 100% rename from google/gemma_2b_amazon/model.safetensors.index.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/model.safetensors.index.json diff --git a/google/gemma_2b_amazon/run.log b/max_seq_length_128_experiments/google/gemma_2b_amazon/run.log similarity index 100% rename from google/gemma_2b_amazon/run.log rename to max_seq_length_128_experiments/google/gemma_2b_amazon/run.log diff --git a/google/gemma_2b_amazon/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/special_tokens_map.json similarity index 100% rename from google/gemma_2b_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/special_tokens_map.json diff --git a/google/gemma_2b_amazon/test_results.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/test_results.json similarity index 100% rename from google/gemma_2b_amazon/test_results.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/test_results.json diff --git a/google/gemma_2b_amazon/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/tokenizer.json similarity index 100% rename from google/gemma_2b_amazon/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/tokenizer.json diff --git a/google/gemma_2b_amazon/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_amazon/tokenizer.model similarity index 100% rename from google/gemma_2b_amazon/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_amazon/tokenizer.model diff --git a/google/gemma_2b_amazon/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/tokenizer_config.json similarity index 100% rename from google/gemma_2b_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/tokenizer_config.json diff --git a/google/gemma_2b_amazon/train_results.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/train_results.json similarity index 100% rename from google/gemma_2b_amazon/train_results.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/train_results.json diff --git a/google/gemma_2b_amazon/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_amazon/trainer_state.json similarity index 100% rename from google/gemma_2b_amazon/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_amazon/trainer_state.json diff --git a/google/gemma_2b_amazon/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_amazon/training_args.bin similarity index 100% rename from google/gemma_2b_amazon/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_amazon/training_args.bin diff --git a/google/gemma_2b_ledgar/README.md b/max_seq_length_128_experiments/google/gemma_2b_ledgar/README.md similarity index 100% rename from google/gemma_2b_ledgar/README.md rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/README.md diff --git a/google/gemma_2b_ledgar/all_results.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/all_results.json similarity index 100% rename from google/gemma_2b_ledgar/all_results.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/all_results.json diff --git a/google/gemma_2b_ledgar/checkpoint-1800/config.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/config.json similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/config.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/config.json diff --git a/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/mp_rank_00_model_states.pt similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/global_step1800/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/global_step1800/mp_rank_00_model_states.pt diff --git a/google/gemma_2b_ledgar/checkpoint-1800/latest b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/latest similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/latest rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/latest diff --git a/google/gemma_2b_ledgar/checkpoint-1800/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/model-00001-of-00002.safetensors similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/model-00001-of-00002.safetensors diff --git a/google/gemma_2b_ledgar/checkpoint-1800/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/model-00002-of-00002.safetensors similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/model-00002-of-00002.safetensors diff --git a/google/gemma_2b_ledgar/checkpoint-1800/model.safetensors.index.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/model.safetensors.index.json similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/model.safetensors.index.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/model.safetensors.index.json diff --git a/google/gemma_2b_ledgar/checkpoint-1800/rng_state_0.pth b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/rng_state_0.pth similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/rng_state_0.pth rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/rng_state_0.pth diff --git a/google/gemma_2b_ledgar/checkpoint-1800/rng_state_1.pth b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/rng_state_1.pth similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/rng_state_1.pth rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/rng_state_1.pth diff --git a/google/gemma_2b_ledgar/checkpoint-1800/scheduler.pt b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/scheduler.pt similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/scheduler.pt rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/scheduler.pt diff --git a/google/gemma_2b_ledgar/checkpoint-1800/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/special_tokens_map.json similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/special_tokens_map.json diff --git a/google/gemma_2b_ledgar/checkpoint-1800/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/tokenizer.json similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/tokenizer.json diff --git a/google/gemma_2b_ledgar/checkpoint-1800/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/tokenizer.model similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/tokenizer.model diff --git a/google/gemma_2b_ledgar/checkpoint-1800/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/tokenizer_config.json similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/tokenizer_config.json diff --git a/google/gemma_2b_ledgar/checkpoint-1800/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/trainer_state.json similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/trainer_state.json diff --git a/google/gemma_2b_ledgar/checkpoint-1800/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/training_args.bin similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/training_args.bin diff --git a/google/gemma_2b_ledgar/checkpoint-1800/zero_to_fp32.py b/max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/zero_to_fp32.py similarity index 100% rename from google/gemma_2b_ledgar/checkpoint-1800/zero_to_fp32.py rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/checkpoint-1800/zero_to_fp32.py diff --git a/google/gemma_2b_ledgar/config.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/config.json similarity index 100% rename from google/gemma_2b_ledgar/config.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/config.json diff --git a/google/gemma_2b_ledgar/eval_results.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/eval_results.json similarity index 100% rename from google/gemma_2b_ledgar/eval_results.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/eval_results.json diff --git a/google/gemma_2b_ledgar/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_ledgar/model-00001-of-00002.safetensors similarity index 100% rename from google/gemma_2b_ledgar/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/model-00001-of-00002.safetensors diff --git a/google/gemma_2b_ledgar/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_ledgar/model-00002-of-00002.safetensors similarity index 100% rename from google/gemma_2b_ledgar/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/model-00002-of-00002.safetensors diff --git a/google/gemma_2b_ledgar/model.safetensors.index.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/model.safetensors.index.json similarity index 100% rename from google/gemma_2b_ledgar/model.safetensors.index.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/model.safetensors.index.json diff --git a/google/gemma_2b_ledgar/run.log b/max_seq_length_128_experiments/google/gemma_2b_ledgar/run.log similarity index 100% rename from google/gemma_2b_ledgar/run.log rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/run.log diff --git a/google/gemma_2b_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/special_tokens_map.json similarity index 100% rename from google/gemma_2b_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/special_tokens_map.json diff --git a/google/gemma_2b_ledgar/test_results.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/test_results.json similarity index 100% rename from google/gemma_2b_ledgar/test_results.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/test_results.json diff --git a/google/gemma_2b_ledgar/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/tokenizer.json similarity index 100% rename from google/gemma_2b_ledgar/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/tokenizer.json diff --git a/google/gemma_2b_ledgar/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_ledgar/tokenizer.model similarity index 100% rename from google/gemma_2b_ledgar/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/tokenizer.model diff --git a/google/gemma_2b_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/tokenizer_config.json similarity index 100% rename from google/gemma_2b_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/tokenizer_config.json diff --git a/google/gemma_2b_ledgar/train_results.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/train_results.json similarity index 100% rename from google/gemma_2b_ledgar/train_results.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/train_results.json diff --git a/google/gemma_2b_ledgar/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_ledgar/trainer_state.json similarity index 100% rename from google/gemma_2b_ledgar/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/trainer_state.json diff --git a/google/gemma_2b_ledgar/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_ledgar/training_args.bin similarity index 100% rename from google/gemma_2b_ledgar/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_ledgar/training_args.bin diff --git a/google/gemma_2b_patent/README.md b/max_seq_length_128_experiments/google/gemma_2b_patent/README.md similarity index 100% rename from google/gemma_2b_patent/README.md rename to max_seq_length_128_experiments/google/gemma_2b_patent/README.md diff --git a/google/gemma_2b_patent/all_results.json b/max_seq_length_128_experiments/google/gemma_2b_patent/all_results.json similarity index 100% rename from google/gemma_2b_patent/all_results.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/all_results.json diff --git a/google/gemma_2b_patent/checkpoint-400/config.json b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/config.json similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/config.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/config.json diff --git a/google/gemma_2b_patent/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_patent/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_patent/checkpoint-400/global_step400/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/global_step400/mp_rank_00_model_states.pt similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/global_step400/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/global_step400/mp_rank_00_model_states.pt diff --git a/google/gemma_2b_patent/checkpoint-400/latest b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/latest similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/latest rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/latest diff --git a/google/gemma_2b_patent/checkpoint-400/pytorch_model-00001-of-00002.bin b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/pytorch_model-00001-of-00002.bin similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/pytorch_model-00001-of-00002.bin rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/pytorch_model-00001-of-00002.bin diff --git a/google/gemma_2b_patent/checkpoint-400/pytorch_model-00002-of-00002.bin b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/pytorch_model-00002-of-00002.bin similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/pytorch_model-00002-of-00002.bin rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/pytorch_model-00002-of-00002.bin diff --git a/google/gemma_2b_patent/checkpoint-400/pytorch_model.bin.index.json b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/pytorch_model.bin.index.json similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/pytorch_model.bin.index.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/pytorch_model.bin.index.json diff --git a/google/gemma_2b_patent/checkpoint-400/rng_state_0.pth b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/rng_state_0.pth similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/rng_state_0.pth rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/rng_state_0.pth diff --git a/google/gemma_2b_patent/checkpoint-400/rng_state_1.pth b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/rng_state_1.pth similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/rng_state_1.pth rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/rng_state_1.pth diff --git a/google/gemma_2b_patent/checkpoint-400/scheduler.pt b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/scheduler.pt similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/scheduler.pt rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/scheduler.pt diff --git a/google/gemma_2b_patent/checkpoint-400/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/special_tokens_map.json similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/special_tokens_map.json diff --git a/google/gemma_2b_patent/checkpoint-400/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/tokenizer.json similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/tokenizer.json diff --git a/google/gemma_2b_patent/checkpoint-400/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/tokenizer.model similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/tokenizer.model diff --git a/google/gemma_2b_patent/checkpoint-400/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/tokenizer_config.json similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/tokenizer_config.json diff --git a/google/gemma_2b_patent/checkpoint-400/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/trainer_state.json similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/trainer_state.json diff --git a/google/gemma_2b_patent/checkpoint-400/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/training_args.bin similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/training_args.bin diff --git a/google/gemma_2b_patent/checkpoint-400/zero_to_fp32.py b/max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/zero_to_fp32.py similarity index 100% rename from google/gemma_2b_patent/checkpoint-400/zero_to_fp32.py rename to max_seq_length_128_experiments/google/gemma_2b_patent/checkpoint-400/zero_to_fp32.py diff --git a/google/gemma_2b_patent/config.json b/max_seq_length_128_experiments/google/gemma_2b_patent/config.json similarity index 100% rename from google/gemma_2b_patent/config.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/config.json diff --git a/google/gemma_2b_patent/eval_results.json b/max_seq_length_128_experiments/google/gemma_2b_patent/eval_results.json similarity index 100% rename from google/gemma_2b_patent/eval_results.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/eval_results.json diff --git a/google/gemma_2b_patent/pytorch_model-00001-of-00002.bin b/max_seq_length_128_experiments/google/gemma_2b_patent/pytorch_model-00001-of-00002.bin similarity index 100% rename from google/gemma_2b_patent/pytorch_model-00001-of-00002.bin rename to max_seq_length_128_experiments/google/gemma_2b_patent/pytorch_model-00001-of-00002.bin diff --git a/google/gemma_2b_patent/pytorch_model-00002-of-00002.bin b/max_seq_length_128_experiments/google/gemma_2b_patent/pytorch_model-00002-of-00002.bin similarity index 100% rename from google/gemma_2b_patent/pytorch_model-00002-of-00002.bin rename to max_seq_length_128_experiments/google/gemma_2b_patent/pytorch_model-00002-of-00002.bin diff --git a/google/gemma_2b_patent/pytorch_model.bin.index.json b/max_seq_length_128_experiments/google/gemma_2b_patent/pytorch_model.bin.index.json similarity index 100% rename from google/gemma_2b_patent/pytorch_model.bin.index.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/pytorch_model.bin.index.json diff --git a/google/gemma_2b_patent/run.log b/max_seq_length_128_experiments/google/gemma_2b_patent/run.log similarity index 100% rename from google/gemma_2b_patent/run.log rename to max_seq_length_128_experiments/google/gemma_2b_patent/run.log diff --git a/google/gemma_2b_patent/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_patent/special_tokens_map.json similarity index 100% rename from google/gemma_2b_patent/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/special_tokens_map.json diff --git a/google/gemma_2b_patent/test_results.json b/max_seq_length_128_experiments/google/gemma_2b_patent/test_results.json similarity index 100% rename from google/gemma_2b_patent/test_results.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/test_results.json diff --git a/google/gemma_2b_patent/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_patent/tokenizer.json similarity index 100% rename from google/gemma_2b_patent/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/tokenizer.json diff --git a/google/gemma_2b_patent/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_patent/tokenizer.model similarity index 100% rename from google/gemma_2b_patent/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_patent/tokenizer.model diff --git a/google/gemma_2b_patent/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_patent/tokenizer_config.json similarity index 100% rename from google/gemma_2b_patent/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/tokenizer_config.json diff --git a/google/gemma_2b_patent/train_results.json b/max_seq_length_128_experiments/google/gemma_2b_patent/train_results.json similarity index 100% rename from google/gemma_2b_patent/train_results.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/train_results.json diff --git a/google/gemma_2b_patent/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_patent/trainer_state.json similarity index 100% rename from google/gemma_2b_patent/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_patent/trainer_state.json diff --git a/google/gemma_2b_patent/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_patent/training_args.bin similarity index 100% rename from google/gemma_2b_patent/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_patent/training_args.bin diff --git a/google/gemma_2b_scotus/README.md b/max_seq_length_128_experiments/google/gemma_2b_scotus/README.md similarity index 100% rename from google/gemma_2b_scotus/README.md rename to max_seq_length_128_experiments/google/gemma_2b_scotus/README.md diff --git a/google/gemma_2b_scotus/all_results.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/all_results.json similarity index 100% rename from google/gemma_2b_scotus/all_results.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/all_results.json diff --git a/google/gemma_2b_scotus/checkpoint-300/config.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/config.json similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/config.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/config.json diff --git a/google/gemma_2b_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/global_step300/mp_rank_00_model_states.pt diff --git a/google/gemma_2b_scotus/checkpoint-300/latest b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/latest similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/latest rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/latest diff --git a/google/gemma_2b_scotus/checkpoint-300/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/model-00001-of-00002.safetensors similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/model-00001-of-00002.safetensors diff --git a/google/gemma_2b_scotus/checkpoint-300/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/model-00002-of-00002.safetensors similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/model-00002-of-00002.safetensors diff --git a/google/gemma_2b_scotus/checkpoint-300/model.safetensors.index.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/model.safetensors.index.json similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/model.safetensors.index.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/model.safetensors.index.json diff --git a/google/gemma_2b_scotus/checkpoint-300/rng_state_0.pth b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/rng_state_0.pth similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/rng_state_0.pth rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/rng_state_0.pth diff --git a/google/gemma_2b_scotus/checkpoint-300/rng_state_1.pth b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/rng_state_1.pth similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/rng_state_1.pth rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/rng_state_1.pth diff --git a/google/gemma_2b_scotus/checkpoint-300/scheduler.pt b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/scheduler.pt similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/scheduler.pt rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/scheduler.pt diff --git a/google/gemma_2b_scotus/checkpoint-300/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/special_tokens_map.json similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/special_tokens_map.json diff --git a/google/gemma_2b_scotus/checkpoint-300/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/tokenizer.json similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/tokenizer.json diff --git a/google/gemma_2b_scotus/checkpoint-300/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/tokenizer.model similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/tokenizer.model diff --git a/google/gemma_2b_scotus/checkpoint-300/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/tokenizer_config.json similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/tokenizer_config.json diff --git a/google/gemma_2b_scotus/checkpoint-300/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/trainer_state.json similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/trainer_state.json diff --git a/google/gemma_2b_scotus/checkpoint-300/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/training_args.bin similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/training_args.bin diff --git a/google/gemma_2b_scotus/checkpoint-300/zero_to_fp32.py b/max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/zero_to_fp32.py similarity index 100% rename from google/gemma_2b_scotus/checkpoint-300/zero_to_fp32.py rename to max_seq_length_128_experiments/google/gemma_2b_scotus/checkpoint-300/zero_to_fp32.py diff --git a/google/gemma_2b_scotus/config.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/config.json similarity index 100% rename from google/gemma_2b_scotus/config.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/config.json diff --git a/google/gemma_2b_scotus/eval_results.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/eval_results.json similarity index 100% rename from google/gemma_2b_scotus/eval_results.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/eval_results.json diff --git a/google/gemma_2b_scotus/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_scotus/model-00001-of-00002.safetensors similarity index 100% rename from google/gemma_2b_scotus/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_scotus/model-00001-of-00002.safetensors diff --git a/google/gemma_2b_scotus/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/google/gemma_2b_scotus/model-00002-of-00002.safetensors similarity index 100% rename from google/gemma_2b_scotus/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/google/gemma_2b_scotus/model-00002-of-00002.safetensors diff --git a/google/gemma_2b_scotus/model.safetensors.index.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/model.safetensors.index.json similarity index 100% rename from google/gemma_2b_scotus/model.safetensors.index.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/model.safetensors.index.json diff --git a/google/gemma_2b_scotus/run.log b/max_seq_length_128_experiments/google/gemma_2b_scotus/run.log similarity index 100% rename from google/gemma_2b_scotus/run.log rename to max_seq_length_128_experiments/google/gemma_2b_scotus/run.log diff --git a/google/gemma_2b_scotus/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/special_tokens_map.json similarity index 100% rename from google/gemma_2b_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/special_tokens_map.json diff --git a/google/gemma_2b_scotus/test_results.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/test_results.json similarity index 100% rename from google/gemma_2b_scotus/test_results.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/test_results.json diff --git a/google/gemma_2b_scotus/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/tokenizer.json similarity index 100% rename from google/gemma_2b_scotus/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/tokenizer.json diff --git a/google/gemma_2b_scotus/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_scotus/tokenizer.model similarity index 100% rename from google/gemma_2b_scotus/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_scotus/tokenizer.model diff --git a/google/gemma_2b_scotus/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/tokenizer_config.json similarity index 100% rename from google/gemma_2b_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/tokenizer_config.json diff --git a/google/gemma_2b_scotus/train_results.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/train_results.json similarity index 100% rename from google/gemma_2b_scotus/train_results.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/train_results.json diff --git a/google/gemma_2b_scotus/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_scotus/trainer_state.json similarity index 100% rename from google/gemma_2b_scotus/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_scotus/trainer_state.json diff --git a/google/gemma_2b_scotus/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_scotus/training_args.bin similarity index 100% rename from google/gemma_2b_scotus/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_scotus/training_args.bin diff --git a/google/gemma_2b_twitter/README.md b/max_seq_length_128_experiments/google/gemma_2b_twitter/README.md similarity index 100% rename from google/gemma_2b_twitter/README.md rename to max_seq_length_128_experiments/google/gemma_2b_twitter/README.md diff --git a/google/gemma_2b_twitter/all_results.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/all_results.json similarity index 100% rename from google/gemma_2b_twitter/all_results.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/all_results.json diff --git a/google/gemma_2b_twitter/checkpoint-250/config.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/config.json similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/config.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/config.json diff --git a/google/gemma_2b_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/global_step250/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/google/gemma_2b_twitter/checkpoint-250/global_step250/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/global_step250/mp_rank_00_model_states.pt similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/global_step250/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/global_step250/mp_rank_00_model_states.pt diff --git a/google/gemma_2b_twitter/checkpoint-250/latest b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/latest similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/latest rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/latest diff --git a/google/gemma_2b_twitter/checkpoint-250/pytorch_model-00001-of-00002.bin b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/pytorch_model-00001-of-00002.bin similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/pytorch_model-00001-of-00002.bin rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/pytorch_model-00001-of-00002.bin diff --git a/google/gemma_2b_twitter/checkpoint-250/pytorch_model-00002-of-00002.bin b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/pytorch_model-00002-of-00002.bin similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/pytorch_model-00002-of-00002.bin rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/pytorch_model-00002-of-00002.bin diff --git a/google/gemma_2b_twitter/checkpoint-250/pytorch_model.bin.index.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/pytorch_model.bin.index.json similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/pytorch_model.bin.index.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/pytorch_model.bin.index.json diff --git a/google/gemma_2b_twitter/checkpoint-250/rng_state_0.pth b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/rng_state_0.pth similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/rng_state_0.pth rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/rng_state_0.pth diff --git a/google/gemma_2b_twitter/checkpoint-250/rng_state_1.pth b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/rng_state_1.pth similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/rng_state_1.pth rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/rng_state_1.pth diff --git a/google/gemma_2b_twitter/checkpoint-250/scheduler.pt b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/scheduler.pt similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/scheduler.pt rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/scheduler.pt diff --git a/google/gemma_2b_twitter/checkpoint-250/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/special_tokens_map.json similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/special_tokens_map.json diff --git a/google/gemma_2b_twitter/checkpoint-250/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer.json similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer.json diff --git a/google/gemma_2b_twitter/checkpoint-250/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer.model similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer.model diff --git a/google/gemma_2b_twitter/checkpoint-250/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer_config.json similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer_config.json diff --git a/google/gemma_2b_twitter/checkpoint-250/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/trainer_state.json similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/trainer_state.json diff --git a/google/gemma_2b_twitter/checkpoint-250/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/training_args.bin similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/training_args.bin diff --git a/google/gemma_2b_twitter/checkpoint-250/zero_to_fp32.py b/max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/zero_to_fp32.py similarity index 100% rename from google/gemma_2b_twitter/checkpoint-250/zero_to_fp32.py rename to max_seq_length_128_experiments/google/gemma_2b_twitter/checkpoint-250/zero_to_fp32.py diff --git a/google/gemma_2b_twitter/config.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/config.json similarity index 100% rename from google/gemma_2b_twitter/config.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/config.json diff --git a/google/gemma_2b_twitter/eval_results.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/eval_results.json similarity index 100% rename from google/gemma_2b_twitter/eval_results.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/eval_results.json diff --git a/google/gemma_2b_twitter/pytorch_model-00001-of-00002.bin b/max_seq_length_128_experiments/google/gemma_2b_twitter/pytorch_model-00001-of-00002.bin similarity index 100% rename from google/gemma_2b_twitter/pytorch_model-00001-of-00002.bin rename to max_seq_length_128_experiments/google/gemma_2b_twitter/pytorch_model-00001-of-00002.bin diff --git a/google/gemma_2b_twitter/pytorch_model-00002-of-00002.bin b/max_seq_length_128_experiments/google/gemma_2b_twitter/pytorch_model-00002-of-00002.bin similarity index 100% rename from google/gemma_2b_twitter/pytorch_model-00002-of-00002.bin rename to max_seq_length_128_experiments/google/gemma_2b_twitter/pytorch_model-00002-of-00002.bin diff --git a/google/gemma_2b_twitter/pytorch_model.bin.index.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/pytorch_model.bin.index.json similarity index 100% rename from google/gemma_2b_twitter/pytorch_model.bin.index.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/pytorch_model.bin.index.json diff --git a/google/gemma_2b_twitter/run.log b/max_seq_length_128_experiments/google/gemma_2b_twitter/run.log similarity index 100% rename from google/gemma_2b_twitter/run.log rename to max_seq_length_128_experiments/google/gemma_2b_twitter/run.log diff --git a/google/gemma_2b_twitter/special_tokens_map.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/special_tokens_map.json similarity index 100% rename from google/gemma_2b_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/special_tokens_map.json diff --git a/google/gemma_2b_twitter/test_results.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/test_results.json similarity index 100% rename from google/gemma_2b_twitter/test_results.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/test_results.json diff --git a/google/gemma_2b_twitter/tokenizer.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/tokenizer.json similarity index 100% rename from google/gemma_2b_twitter/tokenizer.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/tokenizer.json diff --git a/google/gemma_2b_twitter/tokenizer.model b/max_seq_length_128_experiments/google/gemma_2b_twitter/tokenizer.model similarity index 100% rename from google/gemma_2b_twitter/tokenizer.model rename to max_seq_length_128_experiments/google/gemma_2b_twitter/tokenizer.model diff --git a/google/gemma_2b_twitter/tokenizer_config.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/tokenizer_config.json similarity index 100% rename from google/gemma_2b_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/tokenizer_config.json diff --git a/google/gemma_2b_twitter/train_results.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/train_results.json similarity index 100% rename from google/gemma_2b_twitter/train_results.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/train_results.json diff --git a/google/gemma_2b_twitter/trainer_state.json b/max_seq_length_128_experiments/google/gemma_2b_twitter/trainer_state.json similarity index 100% rename from google/gemma_2b_twitter/trainer_state.json rename to max_seq_length_128_experiments/google/gemma_2b_twitter/trainer_state.json diff --git a/google/gemma_2b_twitter/training_args.bin b/max_seq_length_128_experiments/google/gemma_2b_twitter/training_args.bin similarity index 100% rename from google/gemma_2b_twitter/training_args.bin rename to max_seq_length_128_experiments/google/gemma_2b_twitter/training_args.bin diff --git a/google_bert/bert_base_uncased_amazon/README.md b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/README.md similarity index 100% rename from google_bert/bert_base_uncased_amazon/README.md rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/README.md diff --git a/google_bert/bert_base_uncased_amazon/all_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/all_results.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/all_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/all_results.json diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/config.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/config.json diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/model.safetensors diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/optimizer.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/optimizer.pt similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/optimizer.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/optimizer.pt diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/rng_state_0.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/rng_state_0.pth similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/rng_state_0.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/rng_state_0.pth diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/rng_state_1.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/rng_state_1.pth similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/rng_state_1.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/rng_state_1.pth diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/scheduler.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/scheduler.pt similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/scheduler.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/scheduler.pt diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/tokenizer.json diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/trainer_state.json diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/training_args.bin diff --git a/google_bert/bert_base_uncased_amazon/checkpoint-550/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_amazon/checkpoint-550/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/checkpoint-550/vocab.txt diff --git a/google_bert/bert_base_uncased_amazon/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/config.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/config.json diff --git a/google_bert/bert_base_uncased_amazon/eval_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/eval_results.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/eval_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/eval_results.json diff --git a/google_bert/bert_base_uncased_amazon/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_amazon/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/model.safetensors diff --git a/google_bert/bert_base_uncased_amazon/run.log b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/run.log similarity index 100% rename from google_bert/bert_base_uncased_amazon/run.log rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/run.log diff --git a/google_bert/bert_base_uncased_amazon/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_amazon/test_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/test_results.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/test_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/test_results.json diff --git a/google_bert/bert_base_uncased_amazon/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/tokenizer.json diff --git a/google_bert/bert_base_uncased_amazon/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_amazon/train_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/train_results.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/train_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/train_results.json diff --git a/google_bert/bert_base_uncased_amazon/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_amazon/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/trainer_state.json diff --git a/google_bert/bert_base_uncased_amazon/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_amazon/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/training_args.bin diff --git a/google_bert/bert_base_uncased_amazon/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_amazon/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_amazon/vocab.txt diff --git a/google_bert/bert_base_uncased_ledgar/README.md b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/README.md similarity index 100% rename from google_bert/bert_base_uncased_ledgar/README.md rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/README.md diff --git a/google_bert/bert_base_uncased_ledgar/all_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/all_results.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/all_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/all_results.json diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/config.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/config.json diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/model.safetensors diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/optimizer.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/optimizer.pt similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/optimizer.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/optimizer.pt diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/scheduler.pt diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/tokenizer.json diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/trainer_state.json diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/training_args.bin diff --git a/google_bert/bert_base_uncased_ledgar/checkpoint-2800/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_ledgar/checkpoint-2800/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/checkpoint-2800/vocab.txt diff --git a/google_bert/bert_base_uncased_ledgar/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/config.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/config.json diff --git a/google_bert/bert_base_uncased_ledgar/eval_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/eval_results.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/eval_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/eval_results.json diff --git a/google_bert/bert_base_uncased_ledgar/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_ledgar/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/model.safetensors diff --git a/google_bert/bert_base_uncased_ledgar/run.log b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/run.log similarity index 100% rename from google_bert/bert_base_uncased_ledgar/run.log rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/run.log diff --git a/google_bert/bert_base_uncased_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_ledgar/test_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/test_results.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/test_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/test_results.json diff --git a/google_bert/bert_base_uncased_ledgar/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/tokenizer.json diff --git a/google_bert/bert_base_uncased_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_ledgar/train_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/train_results.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/train_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/train_results.json diff --git a/google_bert/bert_base_uncased_ledgar/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_ledgar/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/trainer_state.json diff --git a/google_bert/bert_base_uncased_ledgar/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_ledgar/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/training_args.bin diff --git a/google_bert/bert_base_uncased_ledgar/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_ledgar/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_ledgar/vocab.txt diff --git a/google_bert/bert_base_uncased_patent/README.md b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/README.md similarity index 100% rename from google_bert/bert_base_uncased_patent/README.md rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/README.md diff --git a/google_bert/bert_base_uncased_patent/all_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/all_results.json similarity index 100% rename from google_bert/bert_base_uncased_patent/all_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/all_results.json diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/config.json similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/config.json diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/model.safetensors diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/optimizer.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/optimizer.pt similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/optimizer.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/optimizer.pt diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/rng_state_0.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/rng_state_0.pth similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/rng_state_0.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/rng_state_0.pth diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/rng_state_1.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/rng_state_1.pth similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/rng_state_1.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/rng_state_1.pth diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/scheduler.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/scheduler.pt similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/scheduler.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/scheduler.pt diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/tokenizer.json diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/trainer_state.json diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/training_args.bin diff --git a/google_bert/bert_base_uncased_patent/checkpoint-1150/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_patent/checkpoint-1150/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/checkpoint-1150/vocab.txt diff --git a/google_bert/bert_base_uncased_patent/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/config.json similarity index 100% rename from google_bert/bert_base_uncased_patent/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/config.json diff --git a/google_bert/bert_base_uncased_patent/eval_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/eval_results.json similarity index 100% rename from google_bert/bert_base_uncased_patent/eval_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/eval_results.json diff --git a/google_bert/bert_base_uncased_patent/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_patent/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/model.safetensors diff --git a/google_bert/bert_base_uncased_patent/run.log b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/run.log similarity index 100% rename from google_bert/bert_base_uncased_patent/run.log rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/run.log diff --git a/google_bert/bert_base_uncased_patent/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_patent/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_patent/test_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/test_results.json similarity index 100% rename from google_bert/bert_base_uncased_patent/test_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/test_results.json diff --git a/google_bert/bert_base_uncased_patent/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_patent/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/tokenizer.json diff --git a/google_bert/bert_base_uncased_patent/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_patent/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_patent/train_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/train_results.json similarity index 100% rename from google_bert/bert_base_uncased_patent/train_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/train_results.json diff --git a/google_bert/bert_base_uncased_patent/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_patent/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/trainer_state.json diff --git a/google_bert/bert_base_uncased_patent/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_patent/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/training_args.bin diff --git a/google_bert/bert_base_uncased_patent/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_patent/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_patent/vocab.txt diff --git a/google_bert/bert_base_uncased_scotus/README.md b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/README.md similarity index 100% rename from google_bert/bert_base_uncased_scotus/README.md rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/README.md diff --git a/google_bert/bert_base_uncased_scotus/all_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/all_results.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/all_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/all_results.json diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/config.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/config.json diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/model.safetensors diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/optimizer.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/optimizer.pt similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/optimizer.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/optimizer.pt diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/rng_state_0.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/rng_state_0.pth similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/rng_state_0.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/rng_state_0.pth diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/rng_state_1.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/rng_state_1.pth similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/rng_state_1.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/rng_state_1.pth diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/scheduler.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/scheduler.pt similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/scheduler.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/scheduler.pt diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/tokenizer.json diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/trainer_state.json diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/training_args.bin diff --git a/google_bert/bert_base_uncased_scotus/checkpoint-200/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_scotus/checkpoint-200/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/checkpoint-200/vocab.txt diff --git a/google_bert/bert_base_uncased_scotus/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/config.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/config.json diff --git a/google_bert/bert_base_uncased_scotus/eval_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/eval_results.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/eval_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/eval_results.json diff --git a/google_bert/bert_base_uncased_scotus/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_scotus/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/model.safetensors diff --git a/google_bert/bert_base_uncased_scotus/run.log b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/run.log similarity index 100% rename from google_bert/bert_base_uncased_scotus/run.log rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/run.log diff --git a/google_bert/bert_base_uncased_scotus/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_scotus/test_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/test_results.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/test_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/test_results.json diff --git a/google_bert/bert_base_uncased_scotus/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/tokenizer.json diff --git a/google_bert/bert_base_uncased_scotus/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_scotus/train_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/train_results.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/train_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/train_results.json diff --git a/google_bert/bert_base_uncased_scotus/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_scotus/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/trainer_state.json diff --git a/google_bert/bert_base_uncased_scotus/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_scotus/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/training_args.bin diff --git a/google_bert/bert_base_uncased_scotus/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_scotus/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_scotus/vocab.txt diff --git a/google_bert/bert_base_uncased_twitter/README.md b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/README.md similarity index 100% rename from google_bert/bert_base_uncased_twitter/README.md rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/README.md diff --git a/google_bert/bert_base_uncased_twitter/all_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/all_results.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/all_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/all_results.json diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/config.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/config.json diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/model.safetensors diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/optimizer.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/optimizer.pt similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/optimizer.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/optimizer.pt diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/rng_state_0.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/rng_state_0.pth similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/rng_state_0.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/rng_state_0.pth diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/rng_state_1.pth b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/rng_state_1.pth similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/rng_state_1.pth rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/rng_state_1.pth diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/scheduler.pt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/scheduler.pt similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/scheduler.pt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/scheduler.pt diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/tokenizer.json diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/trainer_state.json diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/training_args.bin diff --git a/google_bert/bert_base_uncased_twitter/checkpoint-100/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_twitter/checkpoint-100/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/checkpoint-100/vocab.txt diff --git a/google_bert/bert_base_uncased_twitter/config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/config.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/config.json diff --git a/google_bert/bert_base_uncased_twitter/eval_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/eval_results.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/eval_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/eval_results.json diff --git a/google_bert/bert_base_uncased_twitter/model.safetensors b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/model.safetensors similarity index 100% rename from google_bert/bert_base_uncased_twitter/model.safetensors rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/model.safetensors diff --git a/google_bert/bert_base_uncased_twitter/run.log b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/run.log similarity index 100% rename from google_bert/bert_base_uncased_twitter/run.log rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/run.log diff --git a/google_bert/bert_base_uncased_twitter/special_tokens_map.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/special_tokens_map.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/special_tokens_map.json diff --git a/google_bert/bert_base_uncased_twitter/test_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/test_results.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/test_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/test_results.json diff --git a/google_bert/bert_base_uncased_twitter/tokenizer.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/tokenizer.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/tokenizer.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/tokenizer.json diff --git a/google_bert/bert_base_uncased_twitter/tokenizer_config.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/tokenizer_config.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/tokenizer_config.json diff --git a/google_bert/bert_base_uncased_twitter/train_results.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/train_results.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/train_results.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/train_results.json diff --git a/google_bert/bert_base_uncased_twitter/trainer_state.json b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/trainer_state.json similarity index 100% rename from google_bert/bert_base_uncased_twitter/trainer_state.json rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/trainer_state.json diff --git a/google_bert/bert_base_uncased_twitter/training_args.bin b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/training_args.bin similarity index 100% rename from google_bert/bert_base_uncased_twitter/training_args.bin rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/training_args.bin diff --git a/google_bert/bert_base_uncased_twitter/vocab.txt b/max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/vocab.txt similarity index 100% rename from google_bert/bert_base_uncased_twitter/vocab.txt rename to max_seq_length_128_experiments/google_bert/bert_base_uncased_twitter/vocab.txt diff --git a/google_t5/t5_base_amazon/README.md b/max_seq_length_128_experiments/google_t5/t5_base_amazon/README.md similarity index 100% rename from google_t5/t5_base_amazon/README.md rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/README.md diff --git a/google_t5/t5_base_amazon/all_results.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/all_results.json similarity index 100% rename from google_t5/t5_base_amazon/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/all_results.json diff --git a/google_t5/t5_base_amazon/checkpoint-700/config.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/config.json similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/config.json diff --git a/google_t5/t5_base_amazon/checkpoint-700/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/model.safetensors similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/model.safetensors diff --git a/google_t5/t5_base_amazon/checkpoint-700/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/optimizer.pt similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/optimizer.pt diff --git a/google_t5/t5_base_amazon/checkpoint-700/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/rng_state_0.pth similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/rng_state_0.pth diff --git a/google_t5/t5_base_amazon/checkpoint-700/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/rng_state_1.pth similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/rng_state_1.pth diff --git a/google_t5/t5_base_amazon/checkpoint-700/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/scheduler.pt similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/scheduler.pt diff --git a/google_t5/t5_base_amazon/checkpoint-700/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/special_tokens_map.json diff --git a/google_t5/t5_base_amazon/checkpoint-700/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/spiece.model similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/spiece.model diff --git a/google_t5/t5_base_amazon/checkpoint-700/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/tokenizer.json similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/tokenizer.json diff --git a/google_t5/t5_base_amazon/checkpoint-700/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/tokenizer_config.json diff --git a/google_t5/t5_base_amazon/checkpoint-700/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/trainer_state.json similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/trainer_state.json diff --git a/google_t5/t5_base_amazon/checkpoint-700/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/training_args.bin similarity index 100% rename from google_t5/t5_base_amazon/checkpoint-700/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/checkpoint-700/training_args.bin diff --git a/google_t5/t5_base_amazon/config.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/config.json similarity index 100% rename from google_t5/t5_base_amazon/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/config.json diff --git a/google_t5/t5_base_amazon/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/eval_results.json similarity index 100% rename from google_t5/t5_base_amazon/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/eval_results.json diff --git a/google_t5/t5_base_amazon/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_amazon/model.safetensors similarity index 100% rename from google_t5/t5_base_amazon/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/model.safetensors diff --git a/google_t5/t5_base_amazon/run.log b/max_seq_length_128_experiments/google_t5/t5_base_amazon/run.log similarity index 100% rename from google_t5/t5_base_amazon/run.log rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/run.log diff --git a/google_t5/t5_base_amazon/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/special_tokens_map.json diff --git a/google_t5/t5_base_amazon/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_amazon/spiece.model similarity index 100% rename from google_t5/t5_base_amazon/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/spiece.model diff --git a/google_t5/t5_base_amazon/test_results.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/test_results.json similarity index 100% rename from google_t5/t5_base_amazon/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/test_results.json diff --git a/google_t5/t5_base_amazon/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/tokenizer.json similarity index 100% rename from google_t5/t5_base_amazon/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/tokenizer.json diff --git a/google_t5/t5_base_amazon/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/tokenizer_config.json diff --git a/google_t5/t5_base_amazon/train_results.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/train_results.json similarity index 100% rename from google_t5/t5_base_amazon/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/train_results.json diff --git a/google_t5/t5_base_amazon/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_amazon/trainer_state.json similarity index 100% rename from google_t5/t5_base_amazon/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/trainer_state.json diff --git a/google_t5/t5_base_amazon/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_amazon/training_args.bin similarity index 100% rename from google_t5/t5_base_amazon/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_amazon/training_args.bin diff --git a/google_t5/t5_base_ledgar/README.md b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/README.md similarity index 100% rename from google_t5/t5_base_ledgar/README.md rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/README.md diff --git a/google_t5/t5_base_ledgar/all_results.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/all_results.json similarity index 100% rename from google_t5/t5_base_ledgar/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/all_results.json diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/config.json similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/config.json diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/model.safetensors similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/model.safetensors diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/optimizer.pt similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/optimizer.pt diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/scheduler.pt diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/spiece.model similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/spiece.model diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/tokenizer.json diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/trainer_state.json diff --git a/google_t5/t5_base_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from google_t5/t5_base_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/checkpoint-2800/training_args.bin diff --git a/google_t5/t5_base_ledgar/config.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/config.json similarity index 100% rename from google_t5/t5_base_ledgar/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/config.json diff --git a/google_t5/t5_base_ledgar/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/eval_results.json similarity index 100% rename from google_t5/t5_base_ledgar/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/eval_results.json diff --git a/google_t5/t5_base_ledgar/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/model.safetensors similarity index 100% rename from google_t5/t5_base_ledgar/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/model.safetensors diff --git a/google_t5/t5_base_ledgar/run.log b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/run.log similarity index 100% rename from google_t5/t5_base_ledgar/run.log rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/run.log diff --git a/google_t5/t5_base_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/special_tokens_map.json diff --git a/google_t5/t5_base_ledgar/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/spiece.model similarity index 100% rename from google_t5/t5_base_ledgar/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/spiece.model diff --git a/google_t5/t5_base_ledgar/test_results.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/test_results.json similarity index 100% rename from google_t5/t5_base_ledgar/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/test_results.json diff --git a/google_t5/t5_base_ledgar/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/tokenizer.json similarity index 100% rename from google_t5/t5_base_ledgar/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/tokenizer.json diff --git a/google_t5/t5_base_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/tokenizer_config.json diff --git a/google_t5/t5_base_ledgar/train_results.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/train_results.json similarity index 100% rename from google_t5/t5_base_ledgar/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/train_results.json diff --git a/google_t5/t5_base_ledgar/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/trainer_state.json similarity index 100% rename from google_t5/t5_base_ledgar/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/trainer_state.json diff --git a/google_t5/t5_base_ledgar/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_ledgar/training_args.bin similarity index 100% rename from google_t5/t5_base_ledgar/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_ledgar/training_args.bin diff --git a/google_t5/t5_base_patent/README.md b/max_seq_length_128_experiments/google_t5/t5_base_patent/README.md similarity index 100% rename from google_t5/t5_base_patent/README.md rename to max_seq_length_128_experiments/google_t5/t5_base_patent/README.md diff --git a/google_t5/t5_base_patent/all_results.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/all_results.json similarity index 100% rename from google_t5/t5_base_patent/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/all_results.json diff --git a/google_t5/t5_base_patent/checkpoint-1550/config.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/config.json similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/config.json diff --git a/google_t5/t5_base_patent/checkpoint-1550/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/model.safetensors similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/model.safetensors diff --git a/google_t5/t5_base_patent/checkpoint-1550/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/optimizer.pt similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/optimizer.pt diff --git a/google_t5/t5_base_patent/checkpoint-1550/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/rng_state_0.pth similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/rng_state_0.pth diff --git a/google_t5/t5_base_patent/checkpoint-1550/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/rng_state_1.pth similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/rng_state_1.pth diff --git a/google_t5/t5_base_patent/checkpoint-1550/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/scheduler.pt similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/scheduler.pt diff --git a/google_t5/t5_base_patent/checkpoint-1550/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/special_tokens_map.json diff --git a/google_t5/t5_base_patent/checkpoint-1550/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/spiece.model similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/spiece.model diff --git a/google_t5/t5_base_patent/checkpoint-1550/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/tokenizer.json similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/tokenizer.json diff --git a/google_t5/t5_base_patent/checkpoint-1550/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/tokenizer_config.json diff --git a/google_t5/t5_base_patent/checkpoint-1550/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/trainer_state.json similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/trainer_state.json diff --git a/google_t5/t5_base_patent/checkpoint-1550/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/training_args.bin similarity index 100% rename from google_t5/t5_base_patent/checkpoint-1550/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_patent/checkpoint-1550/training_args.bin diff --git a/google_t5/t5_base_patent/config.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/config.json similarity index 100% rename from google_t5/t5_base_patent/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/config.json diff --git a/google_t5/t5_base_patent/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/eval_results.json similarity index 100% rename from google_t5/t5_base_patent/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/eval_results.json diff --git a/google_t5/t5_base_patent/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_patent/model.safetensors similarity index 100% rename from google_t5/t5_base_patent/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_patent/model.safetensors diff --git a/google_t5/t5_base_patent/run.log b/max_seq_length_128_experiments/google_t5/t5_base_patent/run.log similarity index 100% rename from google_t5/t5_base_patent/run.log rename to max_seq_length_128_experiments/google_t5/t5_base_patent/run.log diff --git a/google_t5/t5_base_patent/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_patent/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/special_tokens_map.json diff --git a/google_t5/t5_base_patent/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_patent/spiece.model similarity index 100% rename from google_t5/t5_base_patent/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_patent/spiece.model diff --git a/google_t5/t5_base_patent/test_results.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/test_results.json similarity index 100% rename from google_t5/t5_base_patent/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/test_results.json diff --git a/google_t5/t5_base_patent/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/tokenizer.json similarity index 100% rename from google_t5/t5_base_patent/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/tokenizer.json diff --git a/google_t5/t5_base_patent/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_patent/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/tokenizer_config.json diff --git a/google_t5/t5_base_patent/train_results.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/train_results.json similarity index 100% rename from google_t5/t5_base_patent/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/train_results.json diff --git a/google_t5/t5_base_patent/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_patent/trainer_state.json similarity index 100% rename from google_t5/t5_base_patent/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_patent/trainer_state.json diff --git a/google_t5/t5_base_patent/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_patent/training_args.bin similarity index 100% rename from google_t5/t5_base_patent/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_patent/training_args.bin diff --git a/google_t5/t5_base_scotus/README.md b/max_seq_length_128_experiments/google_t5/t5_base_scotus/README.md similarity index 100% rename from google_t5/t5_base_scotus/README.md rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/README.md diff --git a/google_t5/t5_base_scotus/all_results.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/all_results.json similarity index 100% rename from google_t5/t5_base_scotus/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/all_results.json diff --git a/google_t5/t5_base_scotus/checkpoint-400/config.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/config.json similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/config.json diff --git a/google_t5/t5_base_scotus/checkpoint-400/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/model.safetensors similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/model.safetensors diff --git a/google_t5/t5_base_scotus/checkpoint-400/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/optimizer.pt similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/optimizer.pt diff --git a/google_t5/t5_base_scotus/checkpoint-400/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/rng_state_0.pth similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/rng_state_0.pth diff --git a/google_t5/t5_base_scotus/checkpoint-400/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/rng_state_1.pth similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/rng_state_1.pth diff --git a/google_t5/t5_base_scotus/checkpoint-400/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/scheduler.pt similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/scheduler.pt diff --git a/google_t5/t5_base_scotus/checkpoint-400/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/special_tokens_map.json diff --git a/google_t5/t5_base_scotus/checkpoint-400/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/spiece.model similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/spiece.model diff --git a/google_t5/t5_base_scotus/checkpoint-400/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/tokenizer.json similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/tokenizer.json diff --git a/google_t5/t5_base_scotus/checkpoint-400/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/tokenizer_config.json diff --git a/google_t5/t5_base_scotus/checkpoint-400/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/trainer_state.json similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/trainer_state.json diff --git a/google_t5/t5_base_scotus/checkpoint-400/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/training_args.bin similarity index 100% rename from google_t5/t5_base_scotus/checkpoint-400/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/checkpoint-400/training_args.bin diff --git a/google_t5/t5_base_scotus/config.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/config.json similarity index 100% rename from google_t5/t5_base_scotus/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/config.json diff --git a/google_t5/t5_base_scotus/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/eval_results.json similarity index 100% rename from google_t5/t5_base_scotus/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/eval_results.json diff --git a/google_t5/t5_base_scotus/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_scotus/model.safetensors similarity index 100% rename from google_t5/t5_base_scotus/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/model.safetensors diff --git a/google_t5/t5_base_scotus/run.log b/max_seq_length_128_experiments/google_t5/t5_base_scotus/run.log similarity index 100% rename from google_t5/t5_base_scotus/run.log rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/run.log diff --git a/google_t5/t5_base_scotus/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/special_tokens_map.json diff --git a/google_t5/t5_base_scotus/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_scotus/spiece.model similarity index 100% rename from google_t5/t5_base_scotus/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/spiece.model diff --git a/google_t5/t5_base_scotus/test_results.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/test_results.json similarity index 100% rename from google_t5/t5_base_scotus/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/test_results.json diff --git a/google_t5/t5_base_scotus/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/tokenizer.json similarity index 100% rename from google_t5/t5_base_scotus/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/tokenizer.json diff --git a/google_t5/t5_base_scotus/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/tokenizer_config.json diff --git a/google_t5/t5_base_scotus/train_results.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/train_results.json similarity index 100% rename from google_t5/t5_base_scotus/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/train_results.json diff --git a/google_t5/t5_base_scotus/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_scotus/trainer_state.json similarity index 100% rename from google_t5/t5_base_scotus/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/trainer_state.json diff --git a/google_t5/t5_base_scotus/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_scotus/training_args.bin similarity index 100% rename from google_t5/t5_base_scotus/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_scotus/training_args.bin diff --git a/google_t5/t5_base_twitter/README.md b/max_seq_length_128_experiments/google_t5/t5_base_twitter/README.md similarity index 100% rename from google_t5/t5_base_twitter/README.md rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/README.md diff --git a/google_t5/t5_base_twitter/all_results.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/all_results.json similarity index 100% rename from google_t5/t5_base_twitter/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/all_results.json diff --git a/google_t5/t5_base_twitter/checkpoint-250/config.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/config.json similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/config.json diff --git a/google_t5/t5_base_twitter/checkpoint-250/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/model.safetensors similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/model.safetensors diff --git a/google_t5/t5_base_twitter/checkpoint-250/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/optimizer.pt similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/optimizer.pt diff --git a/google_t5/t5_base_twitter/checkpoint-250/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/rng_state_0.pth similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/rng_state_0.pth diff --git a/google_t5/t5_base_twitter/checkpoint-250/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/rng_state_1.pth similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/rng_state_1.pth diff --git a/google_t5/t5_base_twitter/checkpoint-250/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/scheduler.pt similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/scheduler.pt diff --git a/google_t5/t5_base_twitter/checkpoint-250/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/special_tokens_map.json diff --git a/google_t5/t5_base_twitter/checkpoint-250/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/spiece.model similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/spiece.model diff --git a/google_t5/t5_base_twitter/checkpoint-250/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/tokenizer.json similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/tokenizer.json diff --git a/google_t5/t5_base_twitter/checkpoint-250/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/tokenizer_config.json diff --git a/google_t5/t5_base_twitter/checkpoint-250/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/trainer_state.json similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/trainer_state.json diff --git a/google_t5/t5_base_twitter/checkpoint-250/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/training_args.bin similarity index 100% rename from google_t5/t5_base_twitter/checkpoint-250/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/checkpoint-250/training_args.bin diff --git a/google_t5/t5_base_twitter/config.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/config.json similarity index 100% rename from google_t5/t5_base_twitter/config.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/config.json diff --git a/google_t5/t5_base_twitter/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/eval_results.json similarity index 100% rename from google_t5/t5_base_twitter/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/eval_results.json diff --git a/google_t5/t5_base_twitter/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_base_twitter/model.safetensors similarity index 100% rename from google_t5/t5_base_twitter/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/model.safetensors diff --git a/google_t5/t5_base_twitter/run.log b/max_seq_length_128_experiments/google_t5/t5_base_twitter/run.log similarity index 100% rename from google_t5/t5_base_twitter/run.log rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/run.log diff --git a/google_t5/t5_base_twitter/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/special_tokens_map.json similarity index 100% rename from google_t5/t5_base_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/special_tokens_map.json diff --git a/google_t5/t5_base_twitter/spiece.model b/max_seq_length_128_experiments/google_t5/t5_base_twitter/spiece.model similarity index 100% rename from google_t5/t5_base_twitter/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/spiece.model diff --git a/google_t5/t5_base_twitter/test_results.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/test_results.json similarity index 100% rename from google_t5/t5_base_twitter/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/test_results.json diff --git a/google_t5/t5_base_twitter/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/tokenizer.json similarity index 100% rename from google_t5/t5_base_twitter/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/tokenizer.json diff --git a/google_t5/t5_base_twitter/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/tokenizer_config.json similarity index 100% rename from google_t5/t5_base_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/tokenizer_config.json diff --git a/google_t5/t5_base_twitter/train_results.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/train_results.json similarity index 100% rename from google_t5/t5_base_twitter/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/train_results.json diff --git a/google_t5/t5_base_twitter/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_base_twitter/trainer_state.json similarity index 100% rename from google_t5/t5_base_twitter/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/trainer_state.json diff --git a/google_t5/t5_base_twitter/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_base_twitter/training_args.bin similarity index 100% rename from google_t5/t5_base_twitter/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_base_twitter/training_args.bin diff --git a/google_t5/t5_small_amazon/README.md b/max_seq_length_128_experiments/google_t5/t5_small_amazon/README.md similarity index 100% rename from google_t5/t5_small_amazon/README.md rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/README.md diff --git a/google_t5/t5_small_amazon/all_results.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/all_results.json similarity index 100% rename from google_t5/t5_small_amazon/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/all_results.json diff --git a/google_t5/t5_small_amazon/checkpoint-1100/config.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/config.json similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/config.json diff --git a/google_t5/t5_small_amazon/checkpoint-1100/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/model.safetensors similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/model.safetensors diff --git a/google_t5/t5_small_amazon/checkpoint-1100/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/optimizer.pt similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/optimizer.pt diff --git a/google_t5/t5_small_amazon/checkpoint-1100/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/rng_state_0.pth similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/rng_state_0.pth diff --git a/google_t5/t5_small_amazon/checkpoint-1100/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/rng_state_1.pth similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/rng_state_1.pth diff --git a/google_t5/t5_small_amazon/checkpoint-1100/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/scheduler.pt similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/scheduler.pt diff --git a/google_t5/t5_small_amazon/checkpoint-1100/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/special_tokens_map.json diff --git a/google_t5/t5_small_amazon/checkpoint-1100/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/spiece.model similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/spiece.model diff --git a/google_t5/t5_small_amazon/checkpoint-1100/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/tokenizer.json similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/tokenizer.json diff --git a/google_t5/t5_small_amazon/checkpoint-1100/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/tokenizer_config.json diff --git a/google_t5/t5_small_amazon/checkpoint-1100/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/trainer_state.json similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/trainer_state.json diff --git a/google_t5/t5_small_amazon/checkpoint-1100/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/training_args.bin similarity index 100% rename from google_t5/t5_small_amazon/checkpoint-1100/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/checkpoint-1100/training_args.bin diff --git a/google_t5/t5_small_amazon/config.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/config.json similarity index 100% rename from google_t5/t5_small_amazon/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/config.json diff --git a/google_t5/t5_small_amazon/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/eval_results.json similarity index 100% rename from google_t5/t5_small_amazon/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/eval_results.json diff --git a/google_t5/t5_small_amazon/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_amazon/model.safetensors similarity index 100% rename from google_t5/t5_small_amazon/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/model.safetensors diff --git a/google_t5/t5_small_amazon/run.log b/max_seq_length_128_experiments/google_t5/t5_small_amazon/run.log similarity index 100% rename from google_t5/t5_small_amazon/run.log rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/run.log diff --git a/google_t5/t5_small_amazon/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/special_tokens_map.json diff --git a/google_t5/t5_small_amazon/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_amazon/spiece.model similarity index 100% rename from google_t5/t5_small_amazon/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/spiece.model diff --git a/google_t5/t5_small_amazon/test_results.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/test_results.json similarity index 100% rename from google_t5/t5_small_amazon/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/test_results.json diff --git a/google_t5/t5_small_amazon/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/tokenizer.json similarity index 100% rename from google_t5/t5_small_amazon/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/tokenizer.json diff --git a/google_t5/t5_small_amazon/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/tokenizer_config.json diff --git a/google_t5/t5_small_amazon/train_results.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/train_results.json similarity index 100% rename from google_t5/t5_small_amazon/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/train_results.json diff --git a/google_t5/t5_small_amazon/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_amazon/trainer_state.json similarity index 100% rename from google_t5/t5_small_amazon/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/trainer_state.json diff --git a/google_t5/t5_small_amazon/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_amazon/training_args.bin similarity index 100% rename from google_t5/t5_small_amazon/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_amazon/training_args.bin diff --git a/google_t5/t5_small_ledgar/README.md b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/README.md similarity index 100% rename from google_t5/t5_small_ledgar/README.md rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/README.md diff --git a/google_t5/t5_small_ledgar/all_results.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/all_results.json similarity index 100% rename from google_t5/t5_small_ledgar/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/all_results.json diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/config.json similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/config.json diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/model.safetensors similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/model.safetensors diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/optimizer.pt similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/optimizer.pt diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/scheduler.pt diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/spiece.model similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/spiece.model diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/tokenizer.json diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/trainer_state.json diff --git a/google_t5/t5_small_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from google_t5/t5_small_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/checkpoint-2800/training_args.bin diff --git a/google_t5/t5_small_ledgar/config.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/config.json similarity index 100% rename from google_t5/t5_small_ledgar/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/config.json diff --git a/google_t5/t5_small_ledgar/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/eval_results.json similarity index 100% rename from google_t5/t5_small_ledgar/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/eval_results.json diff --git a/google_t5/t5_small_ledgar/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/model.safetensors similarity index 100% rename from google_t5/t5_small_ledgar/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/model.safetensors diff --git a/google_t5/t5_small_ledgar/run.log b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/run.log similarity index 100% rename from google_t5/t5_small_ledgar/run.log rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/run.log diff --git a/google_t5/t5_small_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/special_tokens_map.json diff --git a/google_t5/t5_small_ledgar/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/spiece.model similarity index 100% rename from google_t5/t5_small_ledgar/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/spiece.model diff --git a/google_t5/t5_small_ledgar/test_results.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/test_results.json similarity index 100% rename from google_t5/t5_small_ledgar/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/test_results.json diff --git a/google_t5/t5_small_ledgar/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/tokenizer.json similarity index 100% rename from google_t5/t5_small_ledgar/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/tokenizer.json diff --git a/google_t5/t5_small_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/tokenizer_config.json diff --git a/google_t5/t5_small_ledgar/train_results.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/train_results.json similarity index 100% rename from google_t5/t5_small_ledgar/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/train_results.json diff --git a/google_t5/t5_small_ledgar/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/trainer_state.json similarity index 100% rename from google_t5/t5_small_ledgar/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/trainer_state.json diff --git a/google_t5/t5_small_ledgar/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_ledgar/training_args.bin similarity index 100% rename from google_t5/t5_small_ledgar/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_ledgar/training_args.bin diff --git a/google_t5/t5_small_patent/README.md b/max_seq_length_128_experiments/google_t5/t5_small_patent/README.md similarity index 100% rename from google_t5/t5_small_patent/README.md rename to max_seq_length_128_experiments/google_t5/t5_small_patent/README.md diff --git a/google_t5/t5_small_patent/all_results.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/all_results.json similarity index 100% rename from google_t5/t5_small_patent/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/all_results.json diff --git a/google_t5/t5_small_patent/checkpoint-1400/config.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/config.json similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/config.json diff --git a/google_t5/t5_small_patent/checkpoint-1400/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/model.safetensors similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/model.safetensors diff --git a/google_t5/t5_small_patent/checkpoint-1400/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/optimizer.pt similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/optimizer.pt diff --git a/google_t5/t5_small_patent/checkpoint-1400/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/rng_state_0.pth similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/rng_state_0.pth diff --git a/google_t5/t5_small_patent/checkpoint-1400/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/rng_state_1.pth similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/rng_state_1.pth diff --git a/google_t5/t5_small_patent/checkpoint-1400/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/scheduler.pt similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/scheduler.pt diff --git a/google_t5/t5_small_patent/checkpoint-1400/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/special_tokens_map.json diff --git a/google_t5/t5_small_patent/checkpoint-1400/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/spiece.model similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/spiece.model diff --git a/google_t5/t5_small_patent/checkpoint-1400/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/tokenizer.json similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/tokenizer.json diff --git a/google_t5/t5_small_patent/checkpoint-1400/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/tokenizer_config.json diff --git a/google_t5/t5_small_patent/checkpoint-1400/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/trainer_state.json similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/trainer_state.json diff --git a/google_t5/t5_small_patent/checkpoint-1400/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/training_args.bin similarity index 100% rename from google_t5/t5_small_patent/checkpoint-1400/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_patent/checkpoint-1400/training_args.bin diff --git a/google_t5/t5_small_patent/config.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/config.json similarity index 100% rename from google_t5/t5_small_patent/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/config.json diff --git a/google_t5/t5_small_patent/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/eval_results.json similarity index 100% rename from google_t5/t5_small_patent/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/eval_results.json diff --git a/google_t5/t5_small_patent/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_patent/model.safetensors similarity index 100% rename from google_t5/t5_small_patent/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_patent/model.safetensors diff --git a/google_t5/t5_small_patent/run.log b/max_seq_length_128_experiments/google_t5/t5_small_patent/run.log similarity index 100% rename from google_t5/t5_small_patent/run.log rename to max_seq_length_128_experiments/google_t5/t5_small_patent/run.log diff --git a/google_t5/t5_small_patent/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_patent/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/special_tokens_map.json diff --git a/google_t5/t5_small_patent/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_patent/spiece.model similarity index 100% rename from google_t5/t5_small_patent/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_patent/spiece.model diff --git a/google_t5/t5_small_patent/test_results.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/test_results.json similarity index 100% rename from google_t5/t5_small_patent/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/test_results.json diff --git a/google_t5/t5_small_patent/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/tokenizer.json similarity index 100% rename from google_t5/t5_small_patent/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/tokenizer.json diff --git a/google_t5/t5_small_patent/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_patent/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/tokenizer_config.json diff --git a/google_t5/t5_small_patent/train_results.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/train_results.json similarity index 100% rename from google_t5/t5_small_patent/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/train_results.json diff --git a/google_t5/t5_small_patent/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_patent/trainer_state.json similarity index 100% rename from google_t5/t5_small_patent/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_patent/trainer_state.json diff --git a/google_t5/t5_small_patent/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_patent/training_args.bin similarity index 100% rename from google_t5/t5_small_patent/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_patent/training_args.bin diff --git a/google_t5/t5_small_scotus/README.md b/max_seq_length_128_experiments/google_t5/t5_small_scotus/README.md similarity index 100% rename from google_t5/t5_small_scotus/README.md rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/README.md diff --git a/google_t5/t5_small_scotus/all_results.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/all_results.json similarity index 100% rename from google_t5/t5_small_scotus/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/all_results.json diff --git a/google_t5/t5_small_scotus/checkpoint-450/config.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/config.json similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/config.json diff --git a/google_t5/t5_small_scotus/checkpoint-450/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/model.safetensors similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/model.safetensors diff --git a/google_t5/t5_small_scotus/checkpoint-450/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/optimizer.pt similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/optimizer.pt diff --git a/google_t5/t5_small_scotus/checkpoint-450/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/rng_state_0.pth similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/rng_state_0.pth diff --git a/google_t5/t5_small_scotus/checkpoint-450/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/rng_state_1.pth similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/rng_state_1.pth diff --git a/google_t5/t5_small_scotus/checkpoint-450/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/scheduler.pt similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/scheduler.pt diff --git a/google_t5/t5_small_scotus/checkpoint-450/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/special_tokens_map.json diff --git a/google_t5/t5_small_scotus/checkpoint-450/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/spiece.model similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/spiece.model diff --git a/google_t5/t5_small_scotus/checkpoint-450/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/tokenizer.json similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/tokenizer.json diff --git a/google_t5/t5_small_scotus/checkpoint-450/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/tokenizer_config.json diff --git a/google_t5/t5_small_scotus/checkpoint-450/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/trainer_state.json similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/trainer_state.json diff --git a/google_t5/t5_small_scotus/checkpoint-450/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/training_args.bin similarity index 100% rename from google_t5/t5_small_scotus/checkpoint-450/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/checkpoint-450/training_args.bin diff --git a/google_t5/t5_small_scotus/config.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/config.json similarity index 100% rename from google_t5/t5_small_scotus/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/config.json diff --git a/google_t5/t5_small_scotus/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/eval_results.json similarity index 100% rename from google_t5/t5_small_scotus/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/eval_results.json diff --git a/google_t5/t5_small_scotus/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_scotus/model.safetensors similarity index 100% rename from google_t5/t5_small_scotus/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/model.safetensors diff --git a/google_t5/t5_small_scotus/run.log b/max_seq_length_128_experiments/google_t5/t5_small_scotus/run.log similarity index 100% rename from google_t5/t5_small_scotus/run.log rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/run.log diff --git a/google_t5/t5_small_scotus/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/special_tokens_map.json diff --git a/google_t5/t5_small_scotus/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_scotus/spiece.model similarity index 100% rename from google_t5/t5_small_scotus/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/spiece.model diff --git a/google_t5/t5_small_scotus/test_results.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/test_results.json similarity index 100% rename from google_t5/t5_small_scotus/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/test_results.json diff --git a/google_t5/t5_small_scotus/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/tokenizer.json similarity index 100% rename from google_t5/t5_small_scotus/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/tokenizer.json diff --git a/google_t5/t5_small_scotus/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/tokenizer_config.json diff --git a/google_t5/t5_small_scotus/train_results.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/train_results.json similarity index 100% rename from google_t5/t5_small_scotus/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/train_results.json diff --git a/google_t5/t5_small_scotus/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_scotus/trainer_state.json similarity index 100% rename from google_t5/t5_small_scotus/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/trainer_state.json diff --git a/google_t5/t5_small_scotus/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_scotus/training_args.bin similarity index 100% rename from google_t5/t5_small_scotus/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_scotus/training_args.bin diff --git a/google_t5/t5_small_twitter/README.md b/max_seq_length_128_experiments/google_t5/t5_small_twitter/README.md similarity index 100% rename from google_t5/t5_small_twitter/README.md rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/README.md diff --git a/google_t5/t5_small_twitter/all_results.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/all_results.json similarity index 100% rename from google_t5/t5_small_twitter/all_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/all_results.json diff --git a/google_t5/t5_small_twitter/checkpoint-200/config.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/config.json similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/config.json diff --git a/google_t5/t5_small_twitter/checkpoint-200/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/model.safetensors similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/model.safetensors diff --git a/google_t5/t5_small_twitter/checkpoint-200/optimizer.pt b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/optimizer.pt similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/optimizer.pt rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/optimizer.pt diff --git a/google_t5/t5_small_twitter/checkpoint-200/rng_state_0.pth b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/rng_state_0.pth similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/rng_state_0.pth rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/rng_state_0.pth diff --git a/google_t5/t5_small_twitter/checkpoint-200/rng_state_1.pth b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/rng_state_1.pth similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/rng_state_1.pth rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/rng_state_1.pth diff --git a/google_t5/t5_small_twitter/checkpoint-200/scheduler.pt b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/scheduler.pt similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/scheduler.pt rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/scheduler.pt diff --git a/google_t5/t5_small_twitter/checkpoint-200/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/special_tokens_map.json diff --git a/google_t5/t5_small_twitter/checkpoint-200/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/spiece.model similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/spiece.model diff --git a/google_t5/t5_small_twitter/checkpoint-200/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/tokenizer.json similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/tokenizer.json diff --git a/google_t5/t5_small_twitter/checkpoint-200/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/tokenizer_config.json diff --git a/google_t5/t5_small_twitter/checkpoint-200/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/trainer_state.json similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/trainer_state.json diff --git a/google_t5/t5_small_twitter/checkpoint-200/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/training_args.bin similarity index 100% rename from google_t5/t5_small_twitter/checkpoint-200/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/checkpoint-200/training_args.bin diff --git a/google_t5/t5_small_twitter/config.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/config.json similarity index 100% rename from google_t5/t5_small_twitter/config.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/config.json diff --git a/google_t5/t5_small_twitter/eval_results.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/eval_results.json similarity index 100% rename from google_t5/t5_small_twitter/eval_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/eval_results.json diff --git a/google_t5/t5_small_twitter/model.safetensors b/max_seq_length_128_experiments/google_t5/t5_small_twitter/model.safetensors similarity index 100% rename from google_t5/t5_small_twitter/model.safetensors rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/model.safetensors diff --git a/google_t5/t5_small_twitter/run.log b/max_seq_length_128_experiments/google_t5/t5_small_twitter/run.log similarity index 100% rename from google_t5/t5_small_twitter/run.log rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/run.log diff --git a/google_t5/t5_small_twitter/special_tokens_map.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/special_tokens_map.json similarity index 100% rename from google_t5/t5_small_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/special_tokens_map.json diff --git a/google_t5/t5_small_twitter/spiece.model b/max_seq_length_128_experiments/google_t5/t5_small_twitter/spiece.model similarity index 100% rename from google_t5/t5_small_twitter/spiece.model rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/spiece.model diff --git a/google_t5/t5_small_twitter/test_results.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/test_results.json similarity index 100% rename from google_t5/t5_small_twitter/test_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/test_results.json diff --git a/google_t5/t5_small_twitter/tokenizer.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/tokenizer.json similarity index 100% rename from google_t5/t5_small_twitter/tokenizer.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/tokenizer.json diff --git a/google_t5/t5_small_twitter/tokenizer_config.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/tokenizer_config.json similarity index 100% rename from google_t5/t5_small_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/tokenizer_config.json diff --git a/google_t5/t5_small_twitter/train_results.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/train_results.json similarity index 100% rename from google_t5/t5_small_twitter/train_results.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/train_results.json diff --git a/google_t5/t5_small_twitter/trainer_state.json b/max_seq_length_128_experiments/google_t5/t5_small_twitter/trainer_state.json similarity index 100% rename from google_t5/t5_small_twitter/trainer_state.json rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/trainer_state.json diff --git a/google_t5/t5_small_twitter/training_args.bin b/max_seq_length_128_experiments/google_t5/t5_small_twitter/training_args.bin similarity index 100% rename from google_t5/t5_small_twitter/training_args.bin rename to max_seq_length_128_experiments/google_t5/t5_small_twitter/training_args.bin diff --git a/microsoft/phi_2_amazon/README.md b/max_seq_length_128_experiments/microsoft/phi_2_amazon/README.md similarity index 100% rename from microsoft/phi_2_amazon/README.md rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/README.md diff --git a/microsoft/phi_2_amazon/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/added_tokens.json similarity index 100% rename from microsoft/phi_2_amazon/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/added_tokens.json diff --git a/microsoft/phi_2_amazon/all_results.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/all_results.json similarity index 100% rename from microsoft/phi_2_amazon/all_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/all_results.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/added_tokens.json similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/added_tokens.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/config.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/config.json similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/config.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt diff --git a/microsoft/phi_2_amazon/checkpoint-350/latest b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/latest similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/latest rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/latest diff --git a/microsoft/phi_2_amazon/checkpoint-350/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/merges.txt similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/merges.txt diff --git a/microsoft/phi_2_amazon/checkpoint-350/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/model-00001-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/model-00001-of-00002.safetensors diff --git a/microsoft/phi_2_amazon/checkpoint-350/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/model-00002-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/model-00002-of-00002.safetensors diff --git a/microsoft/phi_2_amazon/checkpoint-350/model.safetensors.index.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/model.safetensors.index.json similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/model.safetensors.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/model.safetensors.index.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/rng_state_0.pth b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/rng_state_0.pth similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/rng_state_0.pth rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/rng_state_0.pth diff --git a/microsoft/phi_2_amazon/checkpoint-350/rng_state_1.pth b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/rng_state_1.pth similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/rng_state_1.pth rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/rng_state_1.pth diff --git a/microsoft/phi_2_amazon/checkpoint-350/scheduler.pt b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/scheduler.pt similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/scheduler.pt rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/scheduler.pt diff --git a/microsoft/phi_2_amazon/checkpoint-350/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/special_tokens_map.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/tokenizer.json similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/tokenizer.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/tokenizer_config.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/trainer_state.json similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/trainer_state.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/training_args.bin similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/training_args.bin diff --git a/microsoft/phi_2_amazon/checkpoint-350/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/vocab.json similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/vocab.json diff --git a/microsoft/phi_2_amazon/checkpoint-350/zero_to_fp32.py b/max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/zero_to_fp32.py similarity index 100% rename from microsoft/phi_2_amazon/checkpoint-350/zero_to_fp32.py rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/checkpoint-350/zero_to_fp32.py diff --git a/microsoft/phi_2_amazon/config.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/config.json similarity index 100% rename from microsoft/phi_2_amazon/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/config.json diff --git a/microsoft/phi_2_amazon/eval_results.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/eval_results.json similarity index 100% rename from microsoft/phi_2_amazon/eval_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/eval_results.json diff --git a/microsoft/phi_2_amazon/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_amazon/merges.txt similarity index 100% rename from microsoft/phi_2_amazon/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/merges.txt diff --git a/microsoft/phi_2_amazon/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_amazon/model-00001-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_amazon/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/model-00001-of-00002.safetensors diff --git a/microsoft/phi_2_amazon/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_amazon/model-00002-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_amazon/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/model-00002-of-00002.safetensors diff --git a/microsoft/phi_2_amazon/model.safetensors.index.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/model.safetensors.index.json similarity index 100% rename from microsoft/phi_2_amazon/model.safetensors.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/model.safetensors.index.json diff --git a/microsoft/phi_2_amazon/run.log b/max_seq_length_128_experiments/microsoft/phi_2_amazon/run.log similarity index 100% rename from microsoft/phi_2_amazon/run.log rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/run.log diff --git a/microsoft/phi_2_amazon/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_amazon/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/special_tokens_map.json diff --git a/microsoft/phi_2_amazon/test_results.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/test_results.json similarity index 100% rename from microsoft/phi_2_amazon/test_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/test_results.json diff --git a/microsoft/phi_2_amazon/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/tokenizer.json similarity index 100% rename from microsoft/phi_2_amazon/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/tokenizer.json diff --git a/microsoft/phi_2_amazon/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_amazon/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/tokenizer_config.json diff --git a/microsoft/phi_2_amazon/train_results.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/train_results.json similarity index 100% rename from microsoft/phi_2_amazon/train_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/train_results.json diff --git a/microsoft/phi_2_amazon/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/trainer_state.json similarity index 100% rename from microsoft/phi_2_amazon/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/trainer_state.json diff --git a/microsoft/phi_2_amazon/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_amazon/training_args.bin similarity index 100% rename from microsoft/phi_2_amazon/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/training_args.bin diff --git a/microsoft/phi_2_amazon/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_amazon/vocab.json similarity index 100% rename from microsoft/phi_2_amazon/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_amazon/vocab.json diff --git a/microsoft/phi_2_ledgar/README.md b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/README.md similarity index 100% rename from microsoft/phi_2_ledgar/README.md rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/README.md diff --git a/microsoft/phi_2_ledgar/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/added_tokens.json similarity index 100% rename from microsoft/phi_2_ledgar/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/added_tokens.json diff --git a/microsoft/phi_2_ledgar/all_results.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/all_results.json similarity index 100% rename from microsoft/phi_2_ledgar/all_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/all_results.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/added_tokens.json similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/added_tokens.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/config.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/config.json similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/config.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/mp_rank_00_model_states.pt similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/mp_rank_00_model_states.pt diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/latest b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/latest similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/latest rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/latest diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/merges.txt similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/merges.txt diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/model-00001-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/model-00001-of-00002.safetensors diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/model-00002-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/model-00002-of-00002.safetensors diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/model.safetensors.index.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/model.safetensors.index.json similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/model.safetensors.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/model.safetensors.index.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/rng_state_0.pth b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/rng_state_0.pth similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/rng_state_0.pth rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/rng_state_0.pth diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/rng_state_1.pth b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/rng_state_1.pth similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/rng_state_1.pth rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/rng_state_1.pth diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/scheduler.pt b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/scheduler.pt similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/scheduler.pt rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/scheduler.pt diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/special_tokens_map.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/tokenizer.json similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/tokenizer.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/tokenizer_config.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/trainer_state.json similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/trainer_state.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/training_args.bin similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/training_args.bin diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/vocab.json similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/vocab.json diff --git a/microsoft/phi_2_ledgar/checkpoint-2800/zero_to_fp32.py b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/zero_to_fp32.py similarity index 100% rename from microsoft/phi_2_ledgar/checkpoint-2800/zero_to_fp32.py rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/checkpoint-2800/zero_to_fp32.py diff --git a/microsoft/phi_2_ledgar/config.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/config.json similarity index 100% rename from microsoft/phi_2_ledgar/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/config.json diff --git a/microsoft/phi_2_ledgar/eval_results.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/eval_results.json similarity index 100% rename from microsoft/phi_2_ledgar/eval_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/eval_results.json diff --git a/microsoft/phi_2_ledgar/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/merges.txt similarity index 100% rename from microsoft/phi_2_ledgar/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/merges.txt diff --git a/microsoft/phi_2_ledgar/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/model-00001-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_ledgar/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/model-00001-of-00002.safetensors diff --git a/microsoft/phi_2_ledgar/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/model-00002-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_ledgar/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/model-00002-of-00002.safetensors diff --git a/microsoft/phi_2_ledgar/model.safetensors.index.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/model.safetensors.index.json similarity index 100% rename from microsoft/phi_2_ledgar/model.safetensors.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/model.safetensors.index.json diff --git a/microsoft/phi_2_ledgar/run.log b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/run.log similarity index 100% rename from microsoft/phi_2_ledgar/run.log rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/run.log diff --git a/microsoft/phi_2_ledgar/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_ledgar/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/special_tokens_map.json diff --git a/microsoft/phi_2_ledgar/test_results.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/test_results.json similarity index 100% rename from microsoft/phi_2_ledgar/test_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/test_results.json diff --git a/microsoft/phi_2_ledgar/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/tokenizer.json similarity index 100% rename from microsoft/phi_2_ledgar/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/tokenizer.json diff --git a/microsoft/phi_2_ledgar/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_ledgar/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/tokenizer_config.json diff --git a/microsoft/phi_2_ledgar/train_results.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/train_results.json similarity index 100% rename from microsoft/phi_2_ledgar/train_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/train_results.json diff --git a/microsoft/phi_2_ledgar/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/trainer_state.json similarity index 100% rename from microsoft/phi_2_ledgar/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/trainer_state.json diff --git a/microsoft/phi_2_ledgar/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/training_args.bin similarity index 100% rename from microsoft/phi_2_ledgar/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/training_args.bin diff --git a/microsoft/phi_2_ledgar/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_ledgar/vocab.json similarity index 100% rename from microsoft/phi_2_ledgar/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_ledgar/vocab.json diff --git a/microsoft/phi_2_patent/README.md b/max_seq_length_128_experiments/microsoft/phi_2_patent/README.md similarity index 100% rename from microsoft/phi_2_patent/README.md rename to max_seq_length_128_experiments/microsoft/phi_2_patent/README.md diff --git a/microsoft/phi_2_patent/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/added_tokens.json similarity index 100% rename from microsoft/phi_2_patent/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/added_tokens.json diff --git a/microsoft/phi_2_patent/all_results.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/all_results.json similarity index 100% rename from microsoft/phi_2_patent/all_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/all_results.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/added_tokens.json similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/added_tokens.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/config.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/config.json similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/config.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/global_step1150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/global_step1150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/global_step1150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/global_step1150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_patent/checkpoint-1150/global_step1150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/global_step1150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/global_step1150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/global_step1150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_patent/checkpoint-1150/global_step1150/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/global_step1150/mp_rank_00_model_states.pt similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/global_step1150/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/global_step1150/mp_rank_00_model_states.pt diff --git a/microsoft/phi_2_patent/checkpoint-1150/latest b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/latest similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/latest rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/latest diff --git a/microsoft/phi_2_patent/checkpoint-1150/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/merges.txt similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/merges.txt diff --git a/microsoft/phi_2_patent/checkpoint-1150/pytorch_model-00001-of-00002.bin b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/pytorch_model-00001-of-00002.bin similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/pytorch_model-00001-of-00002.bin rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/pytorch_model-00001-of-00002.bin diff --git a/microsoft/phi_2_patent/checkpoint-1150/pytorch_model-00002-of-00002.bin b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/pytorch_model-00002-of-00002.bin similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/pytorch_model-00002-of-00002.bin rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/pytorch_model-00002-of-00002.bin diff --git a/microsoft/phi_2_patent/checkpoint-1150/pytorch_model.bin.index.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/pytorch_model.bin.index.json similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/pytorch_model.bin.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/pytorch_model.bin.index.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/rng_state_0.pth b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/rng_state_0.pth similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/rng_state_0.pth rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/rng_state_0.pth diff --git a/microsoft/phi_2_patent/checkpoint-1150/rng_state_1.pth b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/rng_state_1.pth similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/rng_state_1.pth rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/rng_state_1.pth diff --git a/microsoft/phi_2_patent/checkpoint-1150/scheduler.pt b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/scheduler.pt similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/scheduler.pt rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/scheduler.pt diff --git a/microsoft/phi_2_patent/checkpoint-1150/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/special_tokens_map.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/tokenizer.json similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/tokenizer.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/tokenizer_config.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/trainer_state.json similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/trainer_state.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/training_args.bin similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/training_args.bin diff --git a/microsoft/phi_2_patent/checkpoint-1150/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/vocab.json similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/vocab.json diff --git a/microsoft/phi_2_patent/checkpoint-1150/zero_to_fp32.py b/max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/zero_to_fp32.py similarity index 100% rename from microsoft/phi_2_patent/checkpoint-1150/zero_to_fp32.py rename to max_seq_length_128_experiments/microsoft/phi_2_patent/checkpoint-1150/zero_to_fp32.py diff --git a/microsoft/phi_2_patent/config.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/config.json similarity index 100% rename from microsoft/phi_2_patent/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/config.json diff --git a/microsoft/phi_2_patent/eval_results.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/eval_results.json similarity index 100% rename from microsoft/phi_2_patent/eval_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/eval_results.json diff --git a/microsoft/phi_2_patent/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_patent/merges.txt similarity index 100% rename from microsoft/phi_2_patent/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_patent/merges.txt diff --git a/microsoft/phi_2_patent/pytorch_model-00001-of-00002.bin b/max_seq_length_128_experiments/microsoft/phi_2_patent/pytorch_model-00001-of-00002.bin similarity index 100% rename from microsoft/phi_2_patent/pytorch_model-00001-of-00002.bin rename to max_seq_length_128_experiments/microsoft/phi_2_patent/pytorch_model-00001-of-00002.bin diff --git a/microsoft/phi_2_patent/pytorch_model-00002-of-00002.bin b/max_seq_length_128_experiments/microsoft/phi_2_patent/pytorch_model-00002-of-00002.bin similarity index 100% rename from microsoft/phi_2_patent/pytorch_model-00002-of-00002.bin rename to max_seq_length_128_experiments/microsoft/phi_2_patent/pytorch_model-00002-of-00002.bin diff --git a/microsoft/phi_2_patent/pytorch_model.bin.index.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/pytorch_model.bin.index.json similarity index 100% rename from microsoft/phi_2_patent/pytorch_model.bin.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/pytorch_model.bin.index.json diff --git a/microsoft/phi_2_patent/run.log b/max_seq_length_128_experiments/microsoft/phi_2_patent/run.log similarity index 100% rename from microsoft/phi_2_patent/run.log rename to max_seq_length_128_experiments/microsoft/phi_2_patent/run.log diff --git a/microsoft/phi_2_patent/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_patent/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/special_tokens_map.json diff --git a/microsoft/phi_2_patent/test_results.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/test_results.json similarity index 100% rename from microsoft/phi_2_patent/test_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/test_results.json diff --git a/microsoft/phi_2_patent/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/tokenizer.json similarity index 100% rename from microsoft/phi_2_patent/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/tokenizer.json diff --git a/microsoft/phi_2_patent/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_patent/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/tokenizer_config.json diff --git a/microsoft/phi_2_patent/train_results.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/train_results.json similarity index 100% rename from microsoft/phi_2_patent/train_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/train_results.json diff --git a/microsoft/phi_2_patent/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/trainer_state.json similarity index 100% rename from microsoft/phi_2_patent/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/trainer_state.json diff --git a/microsoft/phi_2_patent/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_patent/training_args.bin similarity index 100% rename from microsoft/phi_2_patent/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_patent/training_args.bin diff --git a/microsoft/phi_2_patent/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_patent/vocab.json similarity index 100% rename from microsoft/phi_2_patent/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_patent/vocab.json diff --git a/microsoft/phi_2_scotus/README.md b/max_seq_length_128_experiments/microsoft/phi_2_scotus/README.md similarity index 100% rename from microsoft/phi_2_scotus/README.md rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/README.md diff --git a/microsoft/phi_2_scotus/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/added_tokens.json similarity index 100% rename from microsoft/phi_2_scotus/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/added_tokens.json diff --git a/microsoft/phi_2_scotus/all_results.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/all_results.json similarity index 100% rename from microsoft/phi_2_scotus/all_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/all_results.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/added_tokens.json similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/added_tokens.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/config.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/config.json similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/config.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_scotus/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_scotus/checkpoint-400/global_step400/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/global_step400/mp_rank_00_model_states.pt similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/global_step400/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/global_step400/mp_rank_00_model_states.pt diff --git a/microsoft/phi_2_scotus/checkpoint-400/latest b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/latest similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/latest rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/latest diff --git a/microsoft/phi_2_scotus/checkpoint-400/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/merges.txt similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/merges.txt diff --git a/microsoft/phi_2_scotus/checkpoint-400/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/model-00001-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/model-00001-of-00002.safetensors diff --git a/microsoft/phi_2_scotus/checkpoint-400/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/model-00002-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/model-00002-of-00002.safetensors diff --git a/microsoft/phi_2_scotus/checkpoint-400/model.safetensors.index.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/model.safetensors.index.json similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/model.safetensors.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/model.safetensors.index.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/rng_state_0.pth b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/rng_state_0.pth similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/rng_state_0.pth rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/rng_state_0.pth diff --git a/microsoft/phi_2_scotus/checkpoint-400/rng_state_1.pth b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/rng_state_1.pth similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/rng_state_1.pth rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/rng_state_1.pth diff --git a/microsoft/phi_2_scotus/checkpoint-400/scheduler.pt b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/scheduler.pt similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/scheduler.pt rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/scheduler.pt diff --git a/microsoft/phi_2_scotus/checkpoint-400/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/special_tokens_map.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/tokenizer.json similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/tokenizer.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/tokenizer_config.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/trainer_state.json similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/trainer_state.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/training_args.bin similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/training_args.bin diff --git a/microsoft/phi_2_scotus/checkpoint-400/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/vocab.json similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/vocab.json diff --git a/microsoft/phi_2_scotus/checkpoint-400/zero_to_fp32.py b/max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/zero_to_fp32.py similarity index 100% rename from microsoft/phi_2_scotus/checkpoint-400/zero_to_fp32.py rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/checkpoint-400/zero_to_fp32.py diff --git a/microsoft/phi_2_scotus/config.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/config.json similarity index 100% rename from microsoft/phi_2_scotus/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/config.json diff --git a/microsoft/phi_2_scotus/eval_results.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/eval_results.json similarity index 100% rename from microsoft/phi_2_scotus/eval_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/eval_results.json diff --git a/microsoft/phi_2_scotus/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_scotus/merges.txt similarity index 100% rename from microsoft/phi_2_scotus/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/merges.txt diff --git a/microsoft/phi_2_scotus/model-00001-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_scotus/model-00001-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_scotus/model-00001-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/model-00001-of-00002.safetensors diff --git a/microsoft/phi_2_scotus/model-00002-of-00002.safetensors b/max_seq_length_128_experiments/microsoft/phi_2_scotus/model-00002-of-00002.safetensors similarity index 100% rename from microsoft/phi_2_scotus/model-00002-of-00002.safetensors rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/model-00002-of-00002.safetensors diff --git a/microsoft/phi_2_scotus/model.safetensors.index.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/model.safetensors.index.json similarity index 100% rename from microsoft/phi_2_scotus/model.safetensors.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/model.safetensors.index.json diff --git a/microsoft/phi_2_scotus/run.log b/max_seq_length_128_experiments/microsoft/phi_2_scotus/run.log similarity index 100% rename from microsoft/phi_2_scotus/run.log rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/run.log diff --git a/microsoft/phi_2_scotus/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_scotus/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/special_tokens_map.json diff --git a/microsoft/phi_2_scotus/test_results.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/test_results.json similarity index 100% rename from microsoft/phi_2_scotus/test_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/test_results.json diff --git a/microsoft/phi_2_scotus/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/tokenizer.json similarity index 100% rename from microsoft/phi_2_scotus/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/tokenizer.json diff --git a/microsoft/phi_2_scotus/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_scotus/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/tokenizer_config.json diff --git a/microsoft/phi_2_scotus/train_results.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/train_results.json similarity index 100% rename from microsoft/phi_2_scotus/train_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/train_results.json diff --git a/microsoft/phi_2_scotus/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/trainer_state.json similarity index 100% rename from microsoft/phi_2_scotus/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/trainer_state.json diff --git a/microsoft/phi_2_scotus/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_scotus/training_args.bin similarity index 100% rename from microsoft/phi_2_scotus/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/training_args.bin diff --git a/microsoft/phi_2_scotus/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_scotus/vocab.json similarity index 100% rename from microsoft/phi_2_scotus/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_scotus/vocab.json diff --git a/microsoft/phi_2_twitter/README.md b/max_seq_length_128_experiments/microsoft/phi_2_twitter/README.md similarity index 100% rename from microsoft/phi_2_twitter/README.md rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/README.md diff --git a/microsoft/phi_2_twitter/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/added_tokens.json similarity index 100% rename from microsoft/phi_2_twitter/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/added_tokens.json diff --git a/microsoft/phi_2_twitter/all_results.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/all_results.json similarity index 100% rename from microsoft/phi_2_twitter/all_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/all_results.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/added_tokens.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/added_tokens.json similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/added_tokens.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/added_tokens.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/config.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/config.json similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/config.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_twitter/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt diff --git a/microsoft/phi_2_twitter/checkpoint-750/global_step750/mp_rank_00_model_states.pt b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/global_step750/mp_rank_00_model_states.pt similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/global_step750/mp_rank_00_model_states.pt rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/global_step750/mp_rank_00_model_states.pt diff --git a/microsoft/phi_2_twitter/checkpoint-750/latest b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/latest similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/latest rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/latest diff --git a/microsoft/phi_2_twitter/checkpoint-750/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/merges.txt similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/merges.txt diff --git a/microsoft/phi_2_twitter/checkpoint-750/pytorch_model-00001-of-00002.bin b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/pytorch_model-00001-of-00002.bin similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/pytorch_model-00001-of-00002.bin rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/pytorch_model-00001-of-00002.bin diff --git a/microsoft/phi_2_twitter/checkpoint-750/pytorch_model-00002-of-00002.bin b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/pytorch_model-00002-of-00002.bin similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/pytorch_model-00002-of-00002.bin rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/pytorch_model-00002-of-00002.bin diff --git a/microsoft/phi_2_twitter/checkpoint-750/pytorch_model.bin.index.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/pytorch_model.bin.index.json similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/pytorch_model.bin.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/pytorch_model.bin.index.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/rng_state_0.pth b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/rng_state_0.pth similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/rng_state_0.pth rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/rng_state_0.pth diff --git a/microsoft/phi_2_twitter/checkpoint-750/rng_state_1.pth b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/rng_state_1.pth similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/rng_state_1.pth rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/rng_state_1.pth diff --git a/microsoft/phi_2_twitter/checkpoint-750/scheduler.pt b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/scheduler.pt similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/scheduler.pt rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/scheduler.pt diff --git a/microsoft/phi_2_twitter/checkpoint-750/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/special_tokens_map.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/tokenizer.json similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/tokenizer.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/tokenizer_config.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/trainer_state.json similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/trainer_state.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/training_args.bin similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/training_args.bin diff --git a/microsoft/phi_2_twitter/checkpoint-750/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/vocab.json similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/vocab.json diff --git a/microsoft/phi_2_twitter/checkpoint-750/zero_to_fp32.py b/max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/zero_to_fp32.py similarity index 100% rename from microsoft/phi_2_twitter/checkpoint-750/zero_to_fp32.py rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/checkpoint-750/zero_to_fp32.py diff --git a/microsoft/phi_2_twitter/config.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/config.json similarity index 100% rename from microsoft/phi_2_twitter/config.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/config.json diff --git a/microsoft/phi_2_twitter/eval_results.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/eval_results.json similarity index 100% rename from microsoft/phi_2_twitter/eval_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/eval_results.json diff --git a/microsoft/phi_2_twitter/merges.txt b/max_seq_length_128_experiments/microsoft/phi_2_twitter/merges.txt similarity index 100% rename from microsoft/phi_2_twitter/merges.txt rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/merges.txt diff --git a/microsoft/phi_2_twitter/pytorch_model-00001-of-00002.bin b/max_seq_length_128_experiments/microsoft/phi_2_twitter/pytorch_model-00001-of-00002.bin similarity index 100% rename from microsoft/phi_2_twitter/pytorch_model-00001-of-00002.bin rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/pytorch_model-00001-of-00002.bin diff --git a/microsoft/phi_2_twitter/pytorch_model-00002-of-00002.bin b/max_seq_length_128_experiments/microsoft/phi_2_twitter/pytorch_model-00002-of-00002.bin similarity index 100% rename from microsoft/phi_2_twitter/pytorch_model-00002-of-00002.bin rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/pytorch_model-00002-of-00002.bin diff --git a/microsoft/phi_2_twitter/pytorch_model.bin.index.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/pytorch_model.bin.index.json similarity index 100% rename from microsoft/phi_2_twitter/pytorch_model.bin.index.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/pytorch_model.bin.index.json diff --git a/microsoft/phi_2_twitter/run.log b/max_seq_length_128_experiments/microsoft/phi_2_twitter/run.log similarity index 100% rename from microsoft/phi_2_twitter/run.log rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/run.log diff --git a/microsoft/phi_2_twitter/special_tokens_map.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/special_tokens_map.json similarity index 100% rename from microsoft/phi_2_twitter/special_tokens_map.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/special_tokens_map.json diff --git a/microsoft/phi_2_twitter/test_results.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/test_results.json similarity index 100% rename from microsoft/phi_2_twitter/test_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/test_results.json diff --git a/microsoft/phi_2_twitter/tokenizer.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/tokenizer.json similarity index 100% rename from microsoft/phi_2_twitter/tokenizer.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/tokenizer.json diff --git a/microsoft/phi_2_twitter/tokenizer_config.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/tokenizer_config.json similarity index 100% rename from microsoft/phi_2_twitter/tokenizer_config.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/tokenizer_config.json diff --git a/microsoft/phi_2_twitter/train_results.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/train_results.json similarity index 100% rename from microsoft/phi_2_twitter/train_results.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/train_results.json diff --git a/microsoft/phi_2_twitter/trainer_state.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/trainer_state.json similarity index 100% rename from microsoft/phi_2_twitter/trainer_state.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/trainer_state.json diff --git a/microsoft/phi_2_twitter/training_args.bin b/max_seq_length_128_experiments/microsoft/phi_2_twitter/training_args.bin similarity index 100% rename from microsoft/phi_2_twitter/training_args.bin rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/training_args.bin diff --git a/microsoft/phi_2_twitter/vocab.json b/max_seq_length_128_experiments/microsoft/phi_2_twitter/vocab.json similarity index 100% rename from microsoft/phi_2_twitter/vocab.json rename to max_seq_length_128_experiments/microsoft/phi_2_twitter/vocab.json