Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e80b5fc4829c06ee5a48d0a318a2ef8e95139870c66a79e51a1d080a31076f
+oid sha256:7bdbb64a9e67336fb6cc7806800da88f7100104d2e52ce62066624e571395ac3
 size 267832560

run-3/checkpoint-268/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": "4.48.3",
+  "vocab_size": 30522
+}

run-3/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237a916e5f8c5a47129a1827bde2f5d00d2c481240c33c36441c1dca71cda232
+size 267832560

run-3/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6655731c24c57a98ca8f57fc92b303de84724f09e6bb2fb5dc63f3092632906
+size 535727290

run-3/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b996d7caa4103895dfa60531b124c2d9ea4cef3e44cd97511725509589a954b
+size 14244

run-3/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49adecfd70518273aaf4138199d7f7699683f07c1b95f8e864daa5cfa4f47ae
+size 1064

run-3/checkpoint-268/special_tokens_map.json

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

run-3/checkpoint-268/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-3/checkpoint-268/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-134",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6144593358039856,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7489,
+      "eval_samples_per_second": 1392.645,
+      "eval_steps_per_second": 88.125,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6049911379814148,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.758,
+      "eval_samples_per_second": 1375.912,
+      "eval_steps_per_second": 87.066,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3649276296248327e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 6
+  }
+}

run-3/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845b24e3a517263602d92bf6e2f7b080fcbbe1a2695fa05abf42b943f9701fb1
+size 5432

run-3/checkpoint-402/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": "4.48.3",
+  "vocab_size": 30522
+}

run-3/checkpoint-402/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46660c4f6bb374fc46d9b702e4077dfa9d9a4260ab5d9f62be5e4bd7f7da5b25
+size 267832560

run-3/checkpoint-402/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb93b0bd9d7db882351046f52593965d3e755d117226f45f459008638f56e926
+size 535727290

run-3/checkpoint-402/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69597b7d4fd24dc94b98ae631e40972c8d673add7c5e408eca6cb87b851f9869
+size 14244

run-3/checkpoint-402/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63dc38e269e74159ce90b24610d4a70769acbff6b7782dcdd41e64a10e6f780
+size 1064

run-3/checkpoint-402/special_tokens_map.json

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

run-3/checkpoint-402/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-3/checkpoint-402/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-134",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 402,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6144593358039856,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7489,
+      "eval_samples_per_second": 1392.645,
+      "eval_steps_per_second": 88.125,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6049911379814148,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.758,
+      "eval_samples_per_second": 1375.912,
+      "eval_steps_per_second": 87.066,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5914560556411743,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8251,
+      "eval_samples_per_second": 1264.161,
+      "eval_steps_per_second": 79.995,
+      "step": 402
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3649276296248327e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 6
+  }
+}

run-3/checkpoint-402/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845b24e3a517263602d92bf6e2f7b080fcbbe1a2695fa05abf42b943f9701fb1
+size 5432

run-3/checkpoint-536/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": "4.48.3",
+  "vocab_size": 30522
+}

run-3/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e55042c81b238d1d435b68880d1ee2b98d7fc22bc986099ae62144f5cbe7998
+size 267832560

run-3/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7a3ea8ae7cf13033dd9bc1c48a6c9aa043a4b61a63ce800922fcdf655f3e32
+size 535727290

run-3/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18483368d40989a65b63647aa376d3aeadd898d9e876a710f30d626eb8398e1
+size 14244

run-3/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40ecc11a51e99fba679e241559f8714efcc00d43fff535df3e3aa47085cd7a0
+size 1064

run-3/checkpoint-536/special_tokens_map.json

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

run-3/checkpoint-536/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-3/checkpoint-536/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-134",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6144593358039856,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7489,
+      "eval_samples_per_second": 1392.645,
+      "eval_steps_per_second": 88.125,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6049911379814148,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.758,
+      "eval_samples_per_second": 1375.912,
+      "eval_steps_per_second": 87.066,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5914560556411743,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8251,
+      "eval_samples_per_second": 1264.161,
+      "eval_steps_per_second": 79.995,
+      "step": 402
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 1.6488499641418457,
+      "learning_rate": 3.4632492094958444e-07,
+      "loss": 0.6052,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.581691563129425,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7691,
+      "eval_samples_per_second": 1356.064,
+      "eval_steps_per_second": 85.81,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 209861476320768.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3649276296248327e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 6
+  }
+}

run-3/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845b24e3a517263602d92bf6e2f7b080fcbbe1a2695fa05abf42b943f9701fb1
+size 5432

run-3/checkpoint-670/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": "4.48.3",
+  "vocab_size": 30522
+}

run-3/checkpoint-670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2f9942f1e6654cb0d9315bb2461efae9adcc44a4a28deac4a523b5cf04662f
+size 267832560

run-3/checkpoint-670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3b98c9dbeb1b6b8321a2c86b8e9cba579398abfa95917207d11f1c224a1e3a
+size 535727290

run-3/checkpoint-670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892936dd35fda46017947111a87761cdf9ba7687b1f1194155d9ac0f902423a2
+size 14244

run-3/checkpoint-670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530dc60d43d6cd19fc9bc748b595615e2b4aa49c85c513bf6544e637bd686b75
+size 1064

run-3/checkpoint-670/special_tokens_map.json

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

run-3/checkpoint-670/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-3/checkpoint-670/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-134",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 670,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6144593358039856,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7489,
+      "eval_samples_per_second": 1392.645,
+      "eval_steps_per_second": 88.125,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6049911379814148,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.758,
+      "eval_samples_per_second": 1375.912,
+      "eval_steps_per_second": 87.066,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5914560556411743,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8251,
+      "eval_samples_per_second": 1264.161,
+      "eval_steps_per_second": 79.995,
+      "step": 402
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 1.6488499641418457,
+      "learning_rate": 3.4632492094958444e-07,
+      "loss": 0.6052,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.581691563129425,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7691,
+      "eval_samples_per_second": 1356.064,
+      "eval_steps_per_second": 85.81,
+      "step": 536
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5788252353668213,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2149,
+      "eval_samples_per_second": 858.531,
+      "eval_steps_per_second": 54.327,
+      "step": 670
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 209861476320768.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3649276296248327e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 6
+  }
+}

run-3/checkpoint-670/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845b24e3a517263602d92bf6e2f7b080fcbbe1a2695fa05abf42b943f9701fb1
+size 5432

run-4/checkpoint-535/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": "4.48.3",
+  "vocab_size": 30522
+}

run-4/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bdbb64a9e67336fb6cc7806800da88f7100104d2e52ce62066624e571395ac3
+size 267832560

run-4/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec0e325a83ab44885e458dcbcda2cbeeaab43f0173cd2ca10cf707e751e8edb
+size 535727290

run-4/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59237f4fd2f8c07a76e23240bce7402c0f46c2167f93e061fbee7e3cf43ed8b9
+size 14244

run-4/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043d792e3a4beb907140c2ddc23cf0dc7fb29e5a1e099f8ce4f18bf3d201c05b
+size 1064