Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89d05202561f88efc8b74831bae197cf4ab182b1b67d59bd72b887b89dd9e0f
+oid sha256:2261268f4e83c337376dafb7b415d8024660c66533c5f6118b3c18e6f08a5995
 size 267832560

run-1/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": "4.38.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561413db7ec1ae3d254098bcca99e457362c8312233f29e4b121d6d6c5543aaf
+size 267832560

run-1/checkpoint-670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca637a018cdb13b8aa054a2558d0182b27fee878daa984b7da50c2241acf39f
+size 535727290

run-1/checkpoint-670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08486d113b677466c8c65fe5a1495d08ea9cbd02c118380d05237b1257379e5
+size 14244

run-1/checkpoint-670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d41f8dff069ed0c390b1b28ccb7b37b78f0c07852e6dd9c90c5f5cc8596b793
+size 1064

run-1/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-1/checkpoint-670/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-670/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.5261643004428046,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-670",
+  "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": 0.5111436247825623,
+      "eval_matthews_correlation": 0.3704165163359662,
+      "eval_runtime": 0.7196,
+      "eval_samples_per_second": 1449.402,
+      "eval_steps_per_second": 91.717,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.458956778049469,
+      "eval_matthews_correlation": 0.5008706778439593,
+      "eval_runtime": 0.7749,
+      "eval_samples_per_second": 1345.924,
+      "eval_steps_per_second": 85.169,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4913136959075928,
+      "eval_matthews_correlation": 0.5108951669698317,
+      "eval_runtime": 0.9439,
+      "eval_samples_per_second": 1104.949,
+      "eval_steps_per_second": 69.92,
+      "step": 402
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 8.718708038330078,
+      "learning_rate": 4.5017309553431485e-06,
+      "loss": 0.3868,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5247140526771545,
+      "eval_matthews_correlation": 0.520875943143754,
+      "eval_runtime": 0.7379,
+      "eval_samples_per_second": 1413.511,
+      "eval_steps_per_second": 89.446,
+      "step": 536
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5418965816497803,
+      "eval_matthews_correlation": 0.5261643004428046,
+      "eval_runtime": 0.7965,
+      "eval_samples_per_second": 1309.512,
+      "eval_steps_per_second": 82.865,
+      "step": 670
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 210564174474576.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7742116118117113e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 5
+  }
+}

run-1/checkpoint-670/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85813f8f9164f9360ce3af56ab636de97835d2f503c2f4e4acad37565e88656
+size 4984

run-2/checkpoint-1072/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": "4.38.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091dc9c1e57b65eb8c2fe713e6162eab6c8de901a0095289927429d2259a6f1c
+size 267832560

run-2/checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c083092e5afa7bbb677679d68e2f7f1b5579125ab35f470c810c3d9cab6c74
+size 535727290

run-2/checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4edc5ac78bb132b5789d66b5374bea1d402810a8e37ff4768f2c93b10a67f8e1
+size 14308

run-2/checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edeffe80959f62828df933ebe90153995aa65b70fa0f755ca62424f9e1103895
+size 1064

run-2/checkpoint-1072/special_tokens_map.json

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

run-2/checkpoint-1072/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-2/checkpoint-1072/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.42108781728525657,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1072",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5596779584884644,
+      "eval_matthews_correlation": 0.06558874629318973,
+      "eval_runtime": 0.7398,
+      "eval_samples_per_second": 1409.869,
+      "eval_steps_per_second": 89.215,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.7759640216827393,
+      "learning_rate": 2.1988379475637637e-06,
+      "loss": 0.5503,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5253149271011353,
+      "eval_matthews_correlation": 0.3853198145814999,
+      "eval_runtime": 0.9856,
+      "eval_samples_per_second": 1058.272,
+      "eval_steps_per_second": 66.966,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5222654938697815,
+      "eval_matthews_correlation": 0.4156507632951837,
+      "eval_runtime": 0.7857,
+      "eval_samples_per_second": 1327.408,
+      "eval_steps_per_second": 83.997,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 5.163796424865723,
+      "learning_rate": 8.900058359186663e-07,
+      "loss": 0.4554,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5052011609077454,
+      "eval_matthews_correlation": 0.42108781728525657,
+      "eval_runtime": 1.6038,
+      "eval_samples_per_second": 650.334,
+      "eval_steps_per_second": 41.153,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 191095347752964.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.5076700592088608e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 32
+  }
+}

run-2/checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ee90a2a4781720d2002e2ad3f0576be511712b9097c21abc78dc6d3f3ad486
+size 4984

run-2/checkpoint-1340/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": "4.38.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-1340/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2261268f4e83c337376dafb7b415d8024660c66533c5f6118b3c18e6f08a5995
+size 267832560

run-2/checkpoint-1340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d6cccd97d120ce663506ec22fad8d57e00c9470c1f48545835f91cbb45166c
+size 535727290

run-2/checkpoint-1340/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055cc432b896f955bde8789500d4586cf62bce2c65dbb3e0a360de4d1d0e51bb
+size 14308

run-2/checkpoint-1340/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32109e9333ff622a6d763f6e5750ceccaa205464dc0ece01291b2c9d4efe4a9
+size 1064

run-2/checkpoint-1340/special_tokens_map.json

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

run-2/checkpoint-1340/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-2/checkpoint-1340/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.4286063983911785,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1340",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1340,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5596779584884644,
+      "eval_matthews_correlation": 0.06558874629318973,
+      "eval_runtime": 0.7398,
+      "eval_samples_per_second": 1409.869,
+      "eval_steps_per_second": 89.215,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.7759640216827393,
+      "learning_rate": 2.1988379475637637e-06,
+      "loss": 0.5503,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5253149271011353,
+      "eval_matthews_correlation": 0.3853198145814999,
+      "eval_runtime": 0.9856,
+      "eval_samples_per_second": 1058.272,
+      "eval_steps_per_second": 66.966,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5222654938697815,
+      "eval_matthews_correlation": 0.4156507632951837,
+      "eval_runtime": 0.7857,
+      "eval_samples_per_second": 1327.408,
+      "eval_steps_per_second": 83.997,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 5.163796424865723,
+      "learning_rate": 8.900058359186663e-07,
+      "loss": 0.4554,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5052011609077454,
+      "eval_matthews_correlation": 0.42108781728525657,
+      "eval_runtime": 1.6038,
+      "eval_samples_per_second": 650.334,
+      "eval_steps_per_second": 41.153,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5154977440834045,
+      "eval_matthews_correlation": 0.4286063983911785,
+      "eval_runtime": 0.848,
+      "eval_samples_per_second": 1229.909,
+      "eval_steps_per_second": 77.827,
+      "step": 1340
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 191095347752964.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.5076700592088608e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 32
+  }
+}

run-2/checkpoint-1340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ee90a2a4781720d2002e2ad3f0576be511712b9097c21abc78dc6d3f3ad486
+size 4984

run-2/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": "4.38.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4895bf26051d5c255f5fea3bd8255ec8f25c19af86e9acbc7c2b43cdb2b229
+size 267832560

run-2/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8034e0c73894ce3bdd22f2746ea28ad2aa076a758512d6e8aaf1e0f1e1327e4f
+size 535727290

run-2/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:395cb400fa1f16255165dfda9a50ff7c28f13984f361932a1470b9a0215e2466
+size 14308

run-2/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66236d3e5b304399a8a4939f21fd61c76c4cf9576e9347103095e14b12295476
+size 1064

run-2/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-2/checkpoint-268/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-2/checkpoint-268/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.06558874629318973,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-268",
+  "epoch": 1.0,
+  "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": 0.5596779584884644,
+      "eval_matthews_correlation": 0.06558874629318973,
+      "eval_runtime": 0.7398,
+      "eval_samples_per_second": 1409.869,
+      "eval_steps_per_second": 89.215,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.5076700592088608e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 32
+  }
+}

run-2/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ee90a2a4781720d2002e2ad3f0576be511712b9097c21abc78dc6d3f3ad486
+size 4984

run-2/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": "4.38.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb17ee4d60829212ff294614f43ac4d1887b50b5f7f73bb57e21760046448db
+size 267832560

run-2/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911d63a1f7e2f8774f1acc397c5c7ed812375753fb4a1be4e1ed3a317667d89c
+size 535727290

run-2/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542c9c238227da1240d39bbd348eeb095ba248f904eff91f53483bc727359b82
+size 14308

run-2/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd40f3cc2ec6d5eeecfe431a20140a635b0d89d73654d484de14e34a70113db
+size 1064