Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1016a5a77f129ce7538745a2501f88da50a1cf573c128f6ace57e1fe87d34a00
+oid sha256:c1041a2b755d0618c627bfa31d39e515627fcb1e921499e92ebbb2b1a83b961f
 size 267832560

run-8/checkpoint-1070/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6307af4d4b37421b705ddaf12385300fd3f588160402fcbb523cb9aeb743a1c3
+size 267832560

run-8/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34bab2f347e3bd28147a17f372c6a9d09a91030e4deb113019a0c4e51aca86a
+size 535727290

run-8/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8767056bb678d64a54473583698b4028ad547e7ad1a4ff0ac38dc5ba6a7e94
+size 14244

run-8/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b1079860bf3fda0fa883090fff8d2c900bb3c9d355d40442dd6c90e676475f
+size 1064

run-8/checkpoint-1070/special_tokens_map.json

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

run-8/checkpoint-1070/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-1070/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-214",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6276215314865112,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4827,
+      "eval_samples_per_second": 2160.983,
+      "eval_steps_per_second": 136.745,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6136105060577393,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4872,
+      "eval_samples_per_second": 2140.832,
+      "eval_steps_per_second": 135.47,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.881247813091862e-07,
+      "loss": 0.6266,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6146718859672546,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.5034,
+      "eval_samples_per_second": 2071.912,
+      "eval_steps_per_second": 131.109,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6129891276359558,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4795,
+      "eval_samples_per_second": 2175.064,
+      "eval_steps_per_second": 137.636,
+      "step": 856
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 1.0906795559937375e-07,
+      "loss": 0.598,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6126168370246887,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4759,
+      "eval_samples_per_second": 2191.577,
+      "eval_steps_per_second": 138.681,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 16729183588080.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.667181607018999e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 36
+  }
+}

run-8/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0dfd725b53c74b1c8ffd2377bb7b0876680c49a3fc0a67fc0c08a7077bfcd8
+size 4792

run-8/checkpoint-428/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f581fc07ae383afec08f55577a9e7f4285063f073aedab3299e876a1cf4e3cac
+size 267832560

run-8/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4560e68223ab83ff37acc779e60f493aecf62ec7e76e8a2db726153dbf2c72a
+size 535727290

run-8/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82ce845687c7cd0ddce943007f4c4ccbd06a0fe328e09c4bd702a82cd53444d
+size 14244

run-8/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfbe6feb9a491256d85e51ee600471d108fbaeb5a1da69355c187ab0003539a4
+size 1064

run-8/checkpoint-428/special_tokens_map.json

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

run-8/checkpoint-428/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-428/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-214",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6276215314865112,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4827,
+      "eval_samples_per_second": 2160.983,
+      "eval_steps_per_second": 136.745,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6136105060577393,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4872,
+      "eval_samples_per_second": 2140.832,
+      "eval_steps_per_second": 135.47,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.667181607018999e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 36
+  }
+}

run-8/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0dfd725b53c74b1c8ffd2377bb7b0876680c49a3fc0a67fc0c08a7077bfcd8
+size 4792

run-8/checkpoint-642/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfefc495d29e12ff77337fc1f30d2d389bb0e3d045c34e6679b56c7ea4fbc4d
+size 267832560

run-8/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d8d2e8aa09a71ebfbc9c2c909dd5d52d227720d0d189748779fe439ca677a4
+size 535727290

run-8/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511731f9389ed8c194d750dedd668a3df30f32f35250ae88778c3fae85a9af6a
+size 14244

run-8/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046b4158b7fc26c8c7cf0be55b71ea2e5c5ad757e30869b17b0b62ead28fdb57
+size 1064

run-8/checkpoint-642/special_tokens_map.json

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

run-8/checkpoint-642/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-642/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-214",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 642,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6276215314865112,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4827,
+      "eval_samples_per_second": 2160.983,
+      "eval_steps_per_second": 136.745,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6136105060577393,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4872,
+      "eval_samples_per_second": 2140.832,
+      "eval_steps_per_second": 135.47,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.881247813091862e-07,
+      "loss": 0.6266,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6146718859672546,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.5034,
+      "eval_samples_per_second": 2071.912,
+      "eval_steps_per_second": 131.109,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 8351655524640.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.667181607018999e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 36
+  }
+}

run-8/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0dfd725b53c74b1c8ffd2377bb7b0876680c49a3fc0a67fc0c08a7077bfcd8
+size 4792

run-8/checkpoint-856/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c304a82f086ab60c6e943a4cd75e49270096eb1ef020158a52261c1a55868871
+size 267832560

run-8/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d41246777224caa52be031cbbdfc231a563277f00e85b0b3f37ac151b22543
+size 535727290

run-8/checkpoint-856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb777daaab37c0c001711a8be61f4633de5d05ff8da6bed94ba874e85227ca23
+size 14244

run-8/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83481f526a4fe330aaec4098d55bace6552bf68835dd3625556c4ac33c442eb2
+size 1064

run-8/checkpoint-856/special_tokens_map.json

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

run-8/checkpoint-856/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-856/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-214",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 856,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6276215314865112,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4827,
+      "eval_samples_per_second": 2160.983,
+      "eval_steps_per_second": 136.745,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6136105060577393,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4872,
+      "eval_samples_per_second": 2140.832,
+      "eval_steps_per_second": 135.47,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.881247813091862e-07,
+      "loss": 0.6266,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6146718859672546,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.5034,
+      "eval_samples_per_second": 2071.912,
+      "eval_steps_per_second": 131.109,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6129891276359558,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4795,
+      "eval_samples_per_second": 2175.064,
+      "eval_steps_per_second": 137.636,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 8351655524640.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.667181607018999e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 36
+  }
+}

run-8/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0dfd725b53c74b1c8ffd2377bb7b0876680c49a3fc0a67fc0c08a7077bfcd8
+size 4792

runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706536226.f96070633581.4947.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ef4a42bcccb6467a8435f2db46517f75c615b3061f5457b9daf0a58c393371
+size 4660

runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706537463.f96070633581.4947.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3c458fb1304e4a1aeb6ac73908c92675371983a09f8e8c2e5710e18719a98c
+size 5677

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0dfd725b53c74b1c8ffd2377bb7b0876680c49a3fc0a67fc0c08a7077bfcd8
+oid sha256:fe1109669fdc81f8d310b4dd7aeb333be85e0b51262046c765f4a0c37a09db90
 size 4792