Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a28a1f7a5bd912e06dd15455ce08a9bad56f205c155f331d0ee5c6ed365375
+oid sha256:10975cd45cca99b5a53512ecb93237b5769b337819196a4c155f8c809d8ab671
 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": "4.40.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f1d0a510f13f21456290ee48b066245999b74431c38af99b03bf4bee4595c9
+size 267832560

run-8/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002b1a9f3ebc91c92de96c827efa7492af3b6f5cf22b58367a0e1a284b0bce2f
+size 535727290

run-8/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1df6b7b1ff6335db58bce89e3cedae9f448c487e2a4943b7e6ed61881bccbfd
+size 14244

run-8/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13cbf730a570beb1cbdd11a5453150a31d229c6fd09e7c6c552ededa0c7b7b9
+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": 1000000000000000019884624838656,
+  "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 +1,85 @@
+{
+  "best_metric": 0.11716571434177496,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-1070",
+  "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": 0.6113265752792358,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7181,
+      "eval_samples_per_second": 1452.535,
+      "eval_steps_per_second": 91.915,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6063526272773743,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.817,
+      "eval_samples_per_second": 1276.639,
+      "eval_steps_per_second": 80.784,
+      "step": 428
+    },
+    {
+      "epoch": 2.336448598130841,
+      "grad_norm": 4.553454875946045,
+      "learning_rate": 1.5211627581163973e-06,
+      "loss": 0.6057,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5852556228637695,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8015,
+      "eval_samples_per_second": 1301.354,
+      "eval_steps_per_second": 82.348,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5820844173431396,
+      "eval_matthews_correlation": 0.04161454566059593,
+      "eval_runtime": 0.8079,
+      "eval_samples_per_second": 1291.002,
+      "eval_steps_per_second": 81.693,
+      "step": 856
+    },
+    {
+      "epoch": 4.672897196261682,
+      "grad_norm": 5.679166793823242,
+      "learning_rate": 1.8680946152306634e-07,
+      "loss": 0.541,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5788400769233704,
+      "eval_matthews_correlation": 0.11716571434177496,
+      "eval_runtime": 1.3063,
+      "eval_samples_per_second": 798.409,
+      "eval_steps_per_second": 50.523,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 22137320373444.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.8555160547097285e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 12
+  }
+}

run-8/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affaaf499b0bd474ec9330b36eb26ce187228c0390efde0fe9bd4b1b0f1775da
+size 5048

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": "4.40.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92c6d050f17c866408d65d416726987f8358d71ca47bf903664470ae155d46f
+size 267832560

run-8/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbeab260ee19b36407602c8bddf76988396267a1e1b07f8bf59a77716081378e
+size 535727290

run-8/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123a5343f68ec13b68a2b560055939797bee709d54072612e9bb907a91476f28
+size 14244

run-8/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1db741919e3de876f26d79c24bbd05efbb1971375c0eaa701767f4af4fb3b5
+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": 1000000000000000019884624838656,
+  "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": 0.6113265752792358,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7181,
+      "eval_samples_per_second": 1452.535,
+      "eval_steps_per_second": 91.915,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6063526272773743,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.817,
+      "eval_samples_per_second": 1276.639,
+      "eval_steps_per_second": 80.784,
+      "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": 2.8555160547097285e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 12
+  }
+}

run-8/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affaaf499b0bd474ec9330b36eb26ce187228c0390efde0fe9bd4b1b0f1775da
+size 5048

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": "4.40.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81331b9c9709241991a4994bd56003cd4554683c39301d5f632851c944faa862
+size 267832560

run-8/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870a67736ae7649d22cf7a18fa6f95d66c456a578a14de43fe6ac6e515ee1770
+size 535727290

run-8/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459a440c9d15ba5e5b2229c7ffbe3145e047b6e5e97660610634d47c20f261e5
+size 14244

run-8/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ccb58ff070d2f1640734745f85d5d9398c07c157892728fa1550f972d8067a
+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": 1000000000000000019884624838656,
+  "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 +1,60 @@
+{
+  "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": 0.6113265752792358,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7181,
+      "eval_samples_per_second": 1452.535,
+      "eval_steps_per_second": 91.915,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6063526272773743,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.817,
+      "eval_samples_per_second": 1276.639,
+      "eval_steps_per_second": 80.784,
+      "step": 428
+    },
+    {
+      "epoch": 2.336448598130841,
+      "grad_norm": 4.553454875946045,
+      "learning_rate": 1.5211627581163973e-06,
+      "loss": 0.6057,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5852556228637695,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8015,
+      "eval_samples_per_second": 1301.354,
+      "eval_steps_per_second": 82.348,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 13764449366988.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.8555160547097285e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 12
+  }
+}

run-8/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affaaf499b0bd474ec9330b36eb26ce187228c0390efde0fe9bd4b1b0f1775da
+size 5048

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": "4.40.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f49ab24e7d22d11ea5fb3ec8978279b279a248c2352b0bc078a8a5c86e2ce6
+size 267832560

run-8/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe702d1ea48a951017b9c507d5da793328f373f1afd0fc8d157ecb28d7696706
+size 535727290

run-8/checkpoint-856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0959e4fc49f256382e0dc2b5eaaf6de1ebc7372d1c9b5b34f8bda98d7f54a5b9
+size 14244

run-8/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804b4fbdfb9d63b5e676e7dd2f217c2f522198918f56ba5eb71a98a9018ff3af
+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": 1000000000000000019884624838656,
+  "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 +1,69 @@
+{
+  "best_metric": 0.04161454566059593,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-856",
+  "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": 0.6113265752792358,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7181,
+      "eval_samples_per_second": 1452.535,
+      "eval_steps_per_second": 91.915,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6063526272773743,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.817,
+      "eval_samples_per_second": 1276.639,
+      "eval_steps_per_second": 80.784,
+      "step": 428
+    },
+    {
+      "epoch": 2.336448598130841,
+      "grad_norm": 4.553454875946045,
+      "learning_rate": 1.5211627581163973e-06,
+      "loss": 0.6057,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5852556228637695,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8015,
+      "eval_samples_per_second": 1301.354,
+      "eval_steps_per_second": 82.348,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5820844173431396,
+      "eval_matthews_correlation": 0.04161454566059593,
+      "eval_runtime": 0.8079,
+      "eval_samples_per_second": 1291.002,
+      "eval_steps_per_second": 81.693,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 13764449366988.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.8555160547097285e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 12
+  }
+}

run-8/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affaaf499b0bd474ec9330b36eb26ce187228c0390efde0fe9bd4b1b0f1775da
+size 5048

run-9/checkpoint-107/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": "4.40.1",
+  "vocab_size": 30522
+}

run-9/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10975cd45cca99b5a53512ecb93237b5769b337819196a4c155f8c809d8ab671
+size 267832560

run-9/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f47081ad5906b050150b4523996190145fc3cae463f2e6482915be7814ff3e
+size 535727290

run-9/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66755335e6748a75fdabe0d7df9f0951658c11d0b7f82a50b7a6da403db52f29
+size 14308

run-9/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595c6bfef730728da4d2e55fdd9562ecb44b9c8380544da90784a3b9261783e5
+size 1064