Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b46a03117a30b4cb6728141993318afbd64fbddb7bf76632095e5a0f82136d
+oid sha256:6a80e5530b11666b53e3861f4c0a19db2d4faad020eeee1a0e8205c5a1362c8a
 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": "4.40.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5e07a2bae8bfc07d572f56d4074e9cc305839e244af3053598762d1e1c6c31
+size 267832560

run-3/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd74211a9503aa50ea55d1bc8699460fe7516d8acd068c4f47dcb658548b28d1
+size 535727290

run-3/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7032e9f6b81de2cd0bed3df094b66603cfa4dfa3eec8ec2774abb2539eee10c7
+size 14244

run-3/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8433c2cc1ec47dfc93fd266c88a97d4ae8619676d65706e703c0232085be8b5
+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 +1,55 @@
+{
+  "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-3/checkpoint-268/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.49531265709783606,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-268",
+  "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": 0.5051767230033875,
+      "eval_matthews_correlation": 0.4122249494973531,
+      "eval_runtime": 0.3394,
+      "eval_samples_per_second": 3073.178,
+      "eval_steps_per_second": 194.468,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46091583371162415,
+      "eval_matthews_correlation": 0.49531265709783606,
+      "eval_runtime": 0.3621,
+      "eval_samples_per_second": 2880.741,
+      "eval_steps_per_second": 182.29,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.239666749738152e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 3
+  }
+}

run-3/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfed4eb7f2358e1d44d397d8ad5fb6274af91843133753a59d438505a1610650
+size 5048

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": "4.40.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-402/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9eb5768f96e8248a1404ad5d2c4fe2c39709976a16a81585788057c3873f37f
+size 267832560

run-3/checkpoint-402/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2358381a945da6259a50b5cd892d061bfe6f3c1a8af4bf034fb14abab4122c9
+size 535727290

run-3/checkpoint-402/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3ca775a3466d0ec9c22892aadd0787d630994545a3a904730bf3785ef1fd11
+size 14244

run-3/checkpoint-402/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8842fe935edf8fcfe6792059bcfe9aec30f9c951dd426ffa274d919879b4fd
+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 +1,55 @@
+{
+  "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-3/checkpoint-402/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.5497693861041112,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-402",
+  "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": 0.5051767230033875,
+      "eval_matthews_correlation": 0.4122249494973531,
+      "eval_runtime": 0.3394,
+      "eval_samples_per_second": 3073.178,
+      "eval_steps_per_second": 194.468,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46091583371162415,
+      "eval_matthews_correlation": 0.49531265709783606,
+      "eval_runtime": 0.3621,
+      "eval_samples_per_second": 2880.741,
+      "eval_steps_per_second": 182.29,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5372118353843689,
+      "eval_matthews_correlation": 0.5497693861041112,
+      "eval_runtime": 0.3562,
+      "eval_samples_per_second": 2928.06,
+      "eval_steps_per_second": 185.285,
+      "step": 402
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.239666749738152e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 3
+  }
+}

run-3/checkpoint-402/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfed4eb7f2358e1d44d397d8ad5fb6274af91843133753a59d438505a1610650
+size 5048

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": "4.40.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6b77ff53c6b7b10c553b726a58dab197cb96e5abc2506c58b58e19eae9012c
+size 267832560

run-3/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40406fc9b53cd5de7e60a04a2538ac8bc7b8c7d5f7aaf2620bbdab6df433d2e
+size 535727290

run-3/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae58763a1245543472fb63c49e8ee679973d040c30b5176f18da6bdbd070abc9
+size 14244

run-3/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e768164ee03c2c8a7785e686d2c3633f4cc648ccc0a4aa15655c65bc6f862e9a
+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 +1,55 @@
+{
+  "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-3/checkpoint-536/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.5497693861041112,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-402",
+  "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": 0.5051767230033875,
+      "eval_matthews_correlation": 0.4122249494973531,
+      "eval_runtime": 0.3394,
+      "eval_samples_per_second": 3073.178,
+      "eval_steps_per_second": 194.468,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46091583371162415,
+      "eval_matthews_correlation": 0.49531265709783606,
+      "eval_runtime": 0.3621,
+      "eval_samples_per_second": 2880.741,
+      "eval_steps_per_second": 182.29,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5372118353843689,
+      "eval_matthews_correlation": 0.5497693861041112,
+      "eval_runtime": 0.3562,
+      "eval_samples_per_second": 2928.06,
+      "eval_steps_per_second": 185.285,
+      "step": 402
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 7.611693382263184,
+      "learning_rate": 1.3294676827693819e-05,
+      "loss": 0.2966,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6680317521095276,
+      "eval_matthews_correlation": 0.53798066544186,
+      "eval_runtime": 0.3571,
+      "eval_samples_per_second": 2920.44,
+      "eval_steps_per_second": 184.803,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 210091224465312.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.239666749738152e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 3
+  }
+}

run-3/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfed4eb7f2358e1d44d397d8ad5fb6274af91843133753a59d438505a1610650
+size 5048

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": "4.40.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cc3230aeddfe68767890ae34253ae08d5d7f64c577507536758b34ec9dbdc6
+size 267832560

run-3/checkpoint-670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0ab229c7904d2e8ab4dd61cac98b4372b9d78d6241a8b9102bd3a476dd95c4
+size 535727290

run-3/checkpoint-670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8bb6102be59d87ffca48055af2ab74065bd21eeeff89509075d8a87d49cb7b
+size 14244

run-3/checkpoint-670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee9648678c2fd72135876ad4c4729c81fd557a051178cdc0cb8a1e2d7633cf2
+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 +1,55 @@
+{
+  "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-3/checkpoint-670/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.5546789239242798,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/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": 0.5051767230033875,
+      "eval_matthews_correlation": 0.4122249494973531,
+      "eval_runtime": 0.3394,
+      "eval_samples_per_second": 3073.178,
+      "eval_steps_per_second": 194.468,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46091583371162415,
+      "eval_matthews_correlation": 0.49531265709783606,
+      "eval_runtime": 0.3621,
+      "eval_samples_per_second": 2880.741,
+      "eval_steps_per_second": 182.29,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5372118353843689,
+      "eval_matthews_correlation": 0.5497693861041112,
+      "eval_runtime": 0.3562,
+      "eval_samples_per_second": 2928.06,
+      "eval_steps_per_second": 185.285,
+      "step": 402
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 7.611693382263184,
+      "learning_rate": 1.3294676827693819e-05,
+      "loss": 0.2966,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6680317521095276,
+      "eval_matthews_correlation": 0.53798066544186,
+      "eval_runtime": 0.3571,
+      "eval_samples_per_second": 2920.44,
+      "eval_steps_per_second": 184.803,
+      "step": 536
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7205518484115601,
+      "eval_matthews_correlation": 0.5546789239242798,
+      "eval_runtime": 0.358,
+      "eval_samples_per_second": 2913.26,
+      "eval_steps_per_second": 184.348,
+      "step": 670
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 210091224465312.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.239666749738152e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 3
+  }
+}

run-3/checkpoint-670/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfed4eb7f2358e1d44d397d8ad5fb6274af91843133753a59d438505a1610650
+size 5048

run-4/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": "4.40.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a80e5530b11666b53e3861f4c0a19db2d4faad020eeee1a0e8205c5a1362c8a
+size 267832560

run-4/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa3c3245ff863727ce54ef3575900d46f12926eb4cfd0d8e86bfe682928ac71
+size 535727290

run-4/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0a766a99e900924c8ed901017ca14e9bf98845f42c21490f29ab90067f69be
+size 14244

run-4/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62063bbf4764d28b8e51544d21bd6e779091b564c2fbf412a2b298ecb5a1a72b
+size 1064