Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a01bdb988f1c97690d3fac8a8ff1c2e2f594556f1ab09b79b3d4d23474093e28
+oid sha256:22928d17b7cf85646f64715ed75107c992575418ec391da005ca461fb827e282
 size 267832560

run-4/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": "4.36.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24efea07f6d3f2675597ef0bd1bd479b726f711ae2dcaacaf0ffd84d8944c8a2
+size 267832560

run-4/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2dad8c82e021dd4626ae87f422401f58aea0b7c3be63fcef31c8539b7b0040b
+size 535727290

run-4/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc83786c2e09e3e97e1464c0d9f91e38a4847017560416273e78a2508a4762b8
+size 14244

run-4/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5629529b3e87f4933da174e6d5334e4862efa5e851e87f8831fc90b45e0d9d
+size 1064

run-4/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-4/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-4/checkpoint-268/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.2954790621433495,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.5752326250076294,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7283,
+      "eval_samples_per_second": 1432.034,
+      "eval_steps_per_second": 90.618,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5425477623939514,
+      "eval_matthews_correlation": 0.2954790621433495,
+      "eval_runtime": 0.7867,
+      "eval_samples_per_second": 1325.81,
+      "eval_steps_per_second": 83.896,
+      "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": 3.992038585719908e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 30
+  }
+}

run-4/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec57e4789d5ed5a7c40ab1e2287bcaa6748aca422b5eca6d70308e9abedcbaaf
+size 4792

run-4/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": "4.36.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-402/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e8d7fc5df7b5ec9c6c047f6c098eba0dfc9401ae50f48537af5c7998387b99
+size 267832560

run-4/checkpoint-402/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b18c5d63382bdbcfca4e76126f04f65a9ebcc714ca133f17f6e1b0f0db05ff
+size 535727290

run-4/checkpoint-402/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c518b593a30205b2e9f7eb1e8c5f9382b326ae25b1338b39140c48fc61792291
+size 14244

run-4/checkpoint-402/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0e8b3a214a4d586e87204d3fd9119ab23051ba600120902f57d830517b301f
+size 1064

run-4/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-4/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-4/checkpoint-402/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.3852798937176324,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.5752326250076294,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7283,
+      "eval_samples_per_second": 1432.034,
+      "eval_steps_per_second": 90.618,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5425477623939514,
+      "eval_matthews_correlation": 0.2954790621433495,
+      "eval_runtime": 0.7867,
+      "eval_samples_per_second": 1325.81,
+      "eval_steps_per_second": 83.896,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5229371786117554,
+      "eval_matthews_correlation": 0.3852798937176324,
+      "eval_runtime": 0.7902,
+      "eval_samples_per_second": 1319.959,
+      "eval_steps_per_second": 83.526,
+      "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": 3.992038585719908e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 30
+  }
+}

run-4/checkpoint-402/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec57e4789d5ed5a7c40ab1e2287bcaa6748aca422b5eca6d70308e9abedcbaaf
+size 4792

run-4/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": "4.36.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78fe6018259c5d5cc0ce44432f728dcaf82bcea1f2a70b60a29ab45e0bebd004
+size 267832560

run-4/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68588b1117ea9135600866b806322eacf0a23fbbe65d54cc3a23c42c08bb9a6e
+size 535727290

run-4/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e722c6c09253e66350f18d1533878e8841f5b9a27c61fc4fe849e713bf5e31
+size 14244

run-4/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59997d8f43ef2c63b79d6bacb3d2b580e14200926cbf66ee72d0846e5f26ed09
+size 1064

run-4/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-4/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-4/checkpoint-536/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.4007092981807332,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-536",
+  "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": 0.5752326250076294,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7283,
+      "eval_samples_per_second": 1432.034,
+      "eval_steps_per_second": 90.618,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5425477623939514,
+      "eval_matthews_correlation": 0.2954790621433495,
+      "eval_runtime": 0.7867,
+      "eval_samples_per_second": 1325.81,
+      "eval_steps_per_second": 83.896,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5229371786117554,
+      "eval_matthews_correlation": 0.3852798937176324,
+      "eval_runtime": 0.7902,
+      "eval_samples_per_second": 1319.959,
+      "eval_steps_per_second": 83.526,
+      "step": 402
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.0129053127946036e-06,
+      "loss": 0.53,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5189032554626465,
+      "eval_matthews_correlation": 0.4007092981807332,
+      "eval_runtime": 0.7768,
+      "eval_samples_per_second": 1342.666,
+      "eval_steps_per_second": 84.963,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 210972443136840.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.992038585719908e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 30
+  }
+}

run-4/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec57e4789d5ed5a7c40ab1e2287bcaa6748aca422b5eca6d70308e9abedcbaaf
+size 4792

run-4/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": "4.36.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbac5aa9b74c8eec08d5831fc2b6ef2615c523e4f874a5fe492a41056962cd0
+size 267832560

run-4/checkpoint-670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7abcf94e676dfd7c37dea8d7b0d571f62a4432e1f55bf9bee46de405d8ac26f
+size 535727290

run-4/checkpoint-670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f253b002a05c1f3bb14746d04b574daadeaa1c3500d02f1454c1f51c301d20
+size 14244

run-4/checkpoint-670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0eccc2732fab789bfb133f6ae274a8b4a3a70282253a8be31f5bad2bac7959d
+size 1064

run-4/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-4/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-4/checkpoint-670/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": 0.4007092981807332,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-536",
+  "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": 0.5752326250076294,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7283,
+      "eval_samples_per_second": 1432.034,
+      "eval_steps_per_second": 90.618,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5425477623939514,
+      "eval_matthews_correlation": 0.2954790621433495,
+      "eval_runtime": 0.7867,
+      "eval_samples_per_second": 1325.81,
+      "eval_steps_per_second": 83.896,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5229371786117554,
+      "eval_matthews_correlation": 0.3852798937176324,
+      "eval_runtime": 0.7902,
+      "eval_samples_per_second": 1319.959,
+      "eval_steps_per_second": 83.526,
+      "step": 402
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.0129053127946036e-06,
+      "loss": 0.53,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5189032554626465,
+      "eval_matthews_correlation": 0.4007092981807332,
+      "eval_runtime": 0.7768,
+      "eval_samples_per_second": 1342.666,
+      "eval_steps_per_second": 84.963,
+      "step": 536
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5227140188217163,
+      "eval_matthews_correlation": 0.3946394560910553,
+      "eval_runtime": 0.797,
+      "eval_samples_per_second": 1308.695,
+      "eval_steps_per_second": 82.813,
+      "step": 670
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 210972443136840.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.992038585719908e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 30
+  }
+}

run-4/checkpoint-670/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec57e4789d5ed5a7c40ab1e2287bcaa6748aca422b5eca6d70308e9abedcbaaf
+size 4792

run-8/checkpoint-2138/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-8/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22928d17b7cf85646f64715ed75107c992575418ec391da005ca461fb827e282
+size 267832560

run-8/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a634b4b0036c5bd8edcb38c783da54852fdeb27e82daa380eeb97c257b0744
+size 535727290

run-8/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4c9ff1c71ee8121f0314181957522c6c8d7a18065898939ce4c1996fcaa79f
+size 14308

run-8/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6332ad5b92fcf767b5a9c7bb3197ad344acff0740dc1ee8e68064b813c1a4c10
+size 1064