Delete mt5-base

mt5-base/config.json

@@ -1,33 +0,0 @@
-{
-  "_name_or_path": "google/mt5-base",
-  "architectures": [
-    "MT5ForConditionalGeneration"
-  ],
-  "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "mt5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
-  "use_cache": true,
-  "vocab_size": 250112
-}

mt5-base/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.36.2"
-}

mt5-base/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:afc1c54ab762a88b4dba15a0d6b1e36d229ca343076a85cc27e8af298335a61f
-size 2329638768

mt5-base/model_args.json

@@ -1 +0,0 @@
-{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": false, "adafactor_scale_parameter": false, "adafactor_warmup_init": false, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 1, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 10000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 0.001, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 50, "model_name": "google/mt5-base", "model_type": "mt5", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": true, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "Adafactor", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 46, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": -1, "scheduler": "constant_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 15, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 7228, "weight_decay": 0.0, "model_class": "T5Model", "dataset_class": null, "do_sample": false, "early_stopping": true, "evaluate_generated_text": false, "length_penalty": 2.0, "max_length": 20, "max_steps": -1, "num_beams": 1, "num_return_sequences": 1, "preprocess_inputs": false, "repetition_penalty": 1.0, "special_tokens_list": [], "top_k": null, "top_p": null, "use_multiprocessed_decoding": true}

mt5-base/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6e70f36e574ea7417d0a663c93a2c0b35b89beb1c7acfc5de8a779c88b30ba8
-size 4115589

mt5-base/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8e9d252f87a99ceaccee84bec8731f9e397c766fa87922839de46efd8bd8b79d
-size 627

mt5-base/special_tokens_map.json

@@ -1,23 +0,0 @@
-{
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

mt5-base/spiece.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
-size 4309802

mt5-base/tokenizer_config.json

@@ -1,39 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
-  "extra_ids": 0,
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "T5Tokenizer",
-  "truncate": true,
-  "unk_token": "<unk>"
-}

mt5-base/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a6df679392a03d10cc3b2c7b76ec6b26b942f53f116b095249e4d782d84cbb6b
-size 3195