Training in progress, step 2500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad42b6ab341bd7a90d102409f7c2f9f84506f833273e302d2ef5444cb44c6eb
+oid sha256:ba88df82084094bc409117729c56e9915f519fe11511336d3518480a59910d1a
 size 1340618660

run-17/checkpoint-1000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-17/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057b9e1867677fbd5499053a29400081b7298d170f8b93c45c629ae2f3618862
+size 1340618660

run-17/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f6e28532186d34520ebd7bf1eeaa1a58d5b9cf7aebb380b01eeb01f294a15b
+size 2681472237

run-17/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6949adde667cc7db368e471ea1969496fea33ff9958e5640141668dd757db138
+size 14244

run-17/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab7c664234ee2f7d316303541148769993682d56ee70d6dea91baa228f2f55c
+size 1064

run-17/checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-1000/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.680965147453083,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.758632242679596,
+      "eval_loss": 0.4715859889984131,
+      "eval_runtime": 9.5006,
+      "eval_samples_per_second": 313.981,
+      "eval_steps_per_second": 19.683,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 9.62618637084961,
+      "learning_rate": 1.4776902224208135e-05,
+      "loss": 0.5101,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7727120518684387,
+      "eval_loss": 0.47308608889579773,
+      "eval_runtime": 9.4715,
+      "eval_samples_per_second": 314.944,
+      "eval_steps_per_second": 19.743,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 17.83710289001465,
+      "learning_rate": 1.2489456059470035e-05,
+      "loss": 0.2485,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6202193407669944.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7064348388946237e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-17/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
+size 5048

run-17/checkpoint-1500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-17/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a245021c89ae0f4b30755f412484cd177be18bb3ba3c45ba24ecf5b32aae536
+size 1340618660

run-17/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf92448bb65174d2675ba5841372631e866a84d073ca95a85a8df81af445ea3
+size 2681472237

run-17/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d6297fc05e3c669d3d417f48b67e1a84e4173733817fe3972c260ec2f9f2dd
+size 14244

run-17/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1ca2346581968dfb9a14faf67f7694ee2d13ebad847376e5aca3f3b13cf19d
+size 1064

run-17/checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-1500/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.021447721179625,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.758632242679596,
+      "eval_loss": 0.4715859889984131,
+      "eval_runtime": 9.5006,
+      "eval_samples_per_second": 313.981,
+      "eval_steps_per_second": 19.683,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 9.62618637084961,
+      "learning_rate": 1.4776902224208135e-05,
+      "loss": 0.5101,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7727120518684387,
+      "eval_loss": 0.47308608889579773,
+      "eval_runtime": 9.4715,
+      "eval_samples_per_second": 314.944,
+      "eval_steps_per_second": 19.743,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 17.83710289001465,
+      "learning_rate": 1.2489456059470035e-05,
+      "loss": 0.2485,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7743881940841675,
+      "eval_loss": 0.7006397843360901,
+      "eval_runtime": 9.4464,
+      "eval_samples_per_second": 315.781,
+      "eval_steps_per_second": 19.796,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7750586867332458,
+      "eval_loss": 0.8257986903190613,
+      "eval_runtime": 9.4942,
+      "eval_samples_per_second": 314.193,
+      "eval_steps_per_second": 19.696,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.4933696985244751,
+      "learning_rate": 1.0202009894731932e-05,
+      "loss": 0.0969,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 8976711158170848.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7064348388946237e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-17/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
+size 5048

run-17/checkpoint-2000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-17/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f103ac74e7190e9bd7dde45c303121cc8f057045a2e8489d0a0c847d923dd22
+size 1340618660

run-17/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c92ee584307e7e6ed7a632220970b18583b4ec0562256ea6375b1d578f5b55a
+size 2681472237

run-17/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:721c19c3e780a4dbbdea0a58f53b8fa2858454326b4fe853dc8a1ee3b6a9fe47
+size 14244

run-17/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3d96c59fbd383bfccad8d540bb15c6155a04ecca599781e03be94652ee230a
+size 1064

run-17/checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-2000/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.361930294906166,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.758632242679596,
+      "eval_loss": 0.4715859889984131,
+      "eval_runtime": 9.5006,
+      "eval_samples_per_second": 313.981,
+      "eval_steps_per_second": 19.683,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 9.62618637084961,
+      "learning_rate": 1.4776902224208135e-05,
+      "loss": 0.5101,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7727120518684387,
+      "eval_loss": 0.47308608889579773,
+      "eval_runtime": 9.4715,
+      "eval_samples_per_second": 314.944,
+      "eval_steps_per_second": 19.743,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 17.83710289001465,
+      "learning_rate": 1.2489456059470035e-05,
+      "loss": 0.2485,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7743881940841675,
+      "eval_loss": 0.7006397843360901,
+      "eval_runtime": 9.4464,
+      "eval_samples_per_second": 315.781,
+      "eval_steps_per_second": 19.796,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7750586867332458,
+      "eval_loss": 0.8257986903190613,
+      "eval_runtime": 9.4942,
+      "eval_samples_per_second": 314.193,
+      "eval_steps_per_second": 19.696,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.4933696985244751,
+      "learning_rate": 1.0202009894731932e-05,
+      "loss": 0.0969,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.782433807849884,
+      "eval_loss": 0.9035575985908508,
+      "eval_runtime": 9.4688,
+      "eval_samples_per_second": 315.034,
+      "eval_steps_per_second": 19.749,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 15.212503433227539,
+      "learning_rate": 7.91456372999383e-06,
+      "loss": 0.0396,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.1737297309933476e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7064348388946237e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-17/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
+size 5048

run-17/checkpoint-2500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-17/checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba88df82084094bc409117729c56e9915f519fe11511336d3518480a59910d1a
+size 1340618660

run-17/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c70ce5067a322a7e93d01b7405dd7a797129d852ccdc6a0480cba789284552
+size 2681472237

run-17/checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba21e6de271ea59300bf3a1775b2bf5221b252ebeca24277a3f0a7fb49d6db7
+size 14244

run-17/checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0161288af8ce9e511aaa937c8b5a4565158059f54cb614b06746e2035b2424
+size 1064

run-17/checkpoint-2500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-2500/trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.702412868632708,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.758632242679596,
+      "eval_loss": 0.4715859889984131,
+      "eval_runtime": 9.5006,
+      "eval_samples_per_second": 313.981,
+      "eval_steps_per_second": 19.683,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 9.62618637084961,
+      "learning_rate": 1.4776902224208135e-05,
+      "loss": 0.5101,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7727120518684387,
+      "eval_loss": 0.47308608889579773,
+      "eval_runtime": 9.4715,
+      "eval_samples_per_second": 314.944,
+      "eval_steps_per_second": 19.743,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 17.83710289001465,
+      "learning_rate": 1.2489456059470035e-05,
+      "loss": 0.2485,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7743881940841675,
+      "eval_loss": 0.7006397843360901,
+      "eval_runtime": 9.4464,
+      "eval_samples_per_second": 315.781,
+      "eval_steps_per_second": 19.796,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7750586867332458,
+      "eval_loss": 0.8257986903190613,
+      "eval_runtime": 9.4942,
+      "eval_samples_per_second": 314.193,
+      "eval_steps_per_second": 19.696,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.4933696985244751,
+      "learning_rate": 1.0202009894731932e-05,
+      "loss": 0.0969,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.782433807849884,
+      "eval_loss": 0.9035575985908508,
+      "eval_runtime": 9.4688,
+      "eval_samples_per_second": 315.034,
+      "eval_steps_per_second": 19.749,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 15.212503433227539,
+      "learning_rate": 7.91456372999383e-06,
+      "loss": 0.0396,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7844451665878296,
+      "eval_loss": 1.023715853691101,
+      "eval_runtime": 9.6126,
+      "eval_samples_per_second": 310.323,
+      "eval_steps_per_second": 19.454,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 1.1762652397155762,
+      "learning_rate": 5.627117565255729e-06,
+      "loss": 0.0231,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.4515495448812848e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7064348388946237e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-17/checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
+size 5048