Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6bc8f2c476cdf221059a09cdd59fdc414ad543144746ab93d529c28824af76f
+oid sha256:d2c92881e353adce583369c730349621aafed388f473a2721a35d5ad5fb6bee2
 size 267832560

run-0/checkpoint-1605/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2c234aee9933e055264744fcb872dcc809640cb8e545186a2d6323d08ca225
+size 267832560

run-0/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02dd145371c229d214cab79549601e432d9031a18ef3fa1a6c30727e4901d907
+size 535727290

run-0/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e78921a270157ba80696aaea2f9c67cec0df2394959940b59f082e9789e97b
+size 14308

run-0/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc7f1e67aaf62053a76f78ad541ae1386ae4234d62328cfafefc3097524ba90
+size 1064

run-0/checkpoint-1605/special_tokens_map.json

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

run-0/checkpoint-1605/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-0/checkpoint-1605/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.4465618323468758,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1070",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1605,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.355229248248623e-05,
+      "loss": 0.5639,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5066079497337341,
+      "eval_matthews_correlation": 0.3915828968181581,
+      "eval_runtime": 0.697,
+      "eval_samples_per_second": 1496.499,
+      "eval_steps_per_second": 94.697,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.8942570072719275e-05,
+      "loss": 0.3737,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5427648425102234,
+      "eval_matthews_correlation": 0.4465618323468758,
+      "eval_runtime": 0.7057,
+      "eval_samples_per_second": 1478.025,
+      "eval_steps_per_second": 93.528,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.433284766295233e-05,
+      "loss": 0.2331,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6696511507034302,
+      "eval_matthews_correlation": 0.44079021569318316,
+      "eval_runtime": 0.736,
+      "eval_samples_per_second": 1417.068,
+      "eval_steps_per_second": 89.671,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 128020426687056.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.816201489225318e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 37
+  }
+}

run-0/checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb2d563a1a63fc11ba4d05f1b4a9a4f37d59cc535c711b0aa9d5040b632ff21
+size 4792

run-0/checkpoint-2140/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ee79af019849757a95a655c4052d75fc5c626794d2308b0f8eefe009b01bcf
+size 267832560

run-0/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189dbc244478341631e6723d9fd9c450b9957472bdd95fdf0f588ab15b6b3ce2
+size 535727290

run-0/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1c89d325fc9f19e2f23684587aaf24482b57286af9e787a7af4c80388d42a2
+size 14308

run-0/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc0f78a408d0c052360d07aa30a0851e4c2f3a03e17fa7324c825dd4b65d358
+size 1064

run-0/checkpoint-2140/special_tokens_map.json

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

run-0/checkpoint-2140/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-0/checkpoint-2140/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.47078712112764887,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2140",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.355229248248623e-05,
+      "loss": 0.5639,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5066079497337341,
+      "eval_matthews_correlation": 0.3915828968181581,
+      "eval_runtime": 0.697,
+      "eval_samples_per_second": 1496.499,
+      "eval_steps_per_second": 94.697,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.8942570072719275e-05,
+      "loss": 0.3737,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5427648425102234,
+      "eval_matthews_correlation": 0.4465618323468758,
+      "eval_runtime": 0.7057,
+      "eval_samples_per_second": 1478.025,
+      "eval_steps_per_second": 93.528,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.433284766295233e-05,
+      "loss": 0.2331,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6696511507034302,
+      "eval_matthews_correlation": 0.44079021569318316,
+      "eval_runtime": 0.736,
+      "eval_samples_per_second": 1417.068,
+      "eval_steps_per_second": 89.671,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.9723125253185378e-05,
+      "loss": 0.1434,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8634324669837952,
+      "eval_matthews_correlation": 0.47078712112764887,
+      "eval_runtime": 0.7355,
+      "eval_samples_per_second": 1417.988,
+      "eval_steps_per_second": 89.729,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 170832234090192.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.816201489225318e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 37
+  }
+}

run-0/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb2d563a1a63fc11ba4d05f1b4a9a4f37d59cc535c711b0aa9d5040b632ff21
+size 4792

run-0/checkpoint-2675/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2675/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a19cc1a4d37e9287281938e315787711303fd93400c3745dcbf5307fa5cf49
+size 267832560

run-0/checkpoint-2675/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a9999c9d96349beb8c603387858652a70dcc493100c00d056c0b53aa08e0df
+size 535727290

run-0/checkpoint-2675/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c2a4d39f8edf86bcdbcad0dcb7e75f730200d4d1c7ac2b2e64babcd5a9b1f8
+size 14308

run-0/checkpoint-2675/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1ae61e23b8e1b9fd184c5d89bc129139cb61a077c1c8dd916ed6cf24f34a2d
+size 1064

run-0/checkpoint-2675/special_tokens_map.json

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

run-0/checkpoint-2675/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-0/checkpoint-2675/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": 0.474158493716521,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2675",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2675,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.355229248248623e-05,
+      "loss": 0.5639,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5066079497337341,
+      "eval_matthews_correlation": 0.3915828968181581,
+      "eval_runtime": 0.697,
+      "eval_samples_per_second": 1496.499,
+      "eval_steps_per_second": 94.697,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.8942570072719275e-05,
+      "loss": 0.3737,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5427648425102234,
+      "eval_matthews_correlation": 0.4465618323468758,
+      "eval_runtime": 0.7057,
+      "eval_samples_per_second": 1478.025,
+      "eval_steps_per_second": 93.528,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.433284766295233e-05,
+      "loss": 0.2331,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6696511507034302,
+      "eval_matthews_correlation": 0.44079021569318316,
+      "eval_runtime": 0.736,
+      "eval_samples_per_second": 1417.068,
+      "eval_steps_per_second": 89.671,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.9723125253185378e-05,
+      "loss": 0.1434,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8634324669837952,
+      "eval_matthews_correlation": 0.47078712112764887,
+      "eval_runtime": 0.7355,
+      "eval_samples_per_second": 1417.988,
+      "eval_steps_per_second": 89.729,
+      "step": 2140
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 5.113402843418431e-06,
+      "loss": 0.0879,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.2029379606246948,
+      "eval_matthews_correlation": 0.474158493716521,
+      "eval_runtime": 1.0076,
+      "eval_samples_per_second": 1035.179,
+      "eval_steps_per_second": 65.505,
+      "step": 2675
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 213693716767824.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.816201489225318e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 37
+  }
+}

run-0/checkpoint-2675/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb2d563a1a63fc11ba4d05f1b4a9a4f37d59cc535c711b0aa9d5040b632ff21
+size 4792

run-1/checkpoint-1069/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": "4.36.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c92881e353adce583369c730349621aafed388f473a2721a35d5ad5fb6bee2
+size 267832560

run-1/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0114b256fa0583b7253e66b193409761bb919ccae414af61fd12e26cd7a0fffc
+size 535727290

run-1/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca15309e5ba35c7d7fa968cfcef8c6f8dc840d85825e5bc321f5d02f760a2cd7
+size 14244

run-1/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0afe91f9c8d5fbfc0ecb9a47a87f47b2bf52f8300784e2baf25955ad6457a8c
+size 1064

run-1/checkpoint-1069/special_tokens_map.json

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

run-1/checkpoint-1069/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-1/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.41085066245376894,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.280651353565795e-05,
+      "loss": 0.5907,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.97829426003585e-06,
+      "loss": 0.4971,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5098241567611694,
+      "eval_matthews_correlation": 0.41085066245376894,
+      "eval_runtime": 0.7431,
+      "eval_samples_per_second": 1403.585,
+      "eval_steps_per_second": 88.817,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1069,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 37608322399680.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.163473281128005e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 15
+  }
+}

run-1/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0c50ea7fa32747038fcc8eacd8e23a4a64c7c127a347db2073e7058baef7a9
+size 4792

runs/Dec23_02-11-24_38c624d3e13b/events.out.tfevents.1703299070.38c624d3e13b.382.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d25de18fc4d69f27f59d4da4e63bf3d901cf55d437dd5e58e5cbfe761b3e44e
-size 5338
+oid sha256:7d55b301f9c6fb149e7845f710cbd789f1003e2ca13fa408fc114cdc0b4204ae
+size 7168

runs/Dec23_02-11-24_38c624d3e13b/events.out.tfevents.1703299267.38c624d3e13b.382.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2b147aade6927ba84b578a743dc7744ca5d4a0ce751a911c26b6d5e4b11295
+size 5356

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb2d563a1a63fc11ba4d05f1b4a9a4f37d59cc535c711b0aa9d5040b632ff21
+oid sha256:0f0c50ea7fa32747038fcc8eacd8e23a4a64c7c127a347db2073e7058baef7a9
 size 4792