Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f19fdfd0493a182edb5fa666ac51bd975bd01f8af00e04463c041880bc34da
+oid sha256:ac241b7f5878d7c3e877b7d2441730b388f259765419905ee924bf705a6d59fe
 size 267832560

run-6/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": "4.38.1",
+  "vocab_size": 30522
+}

run-6/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f19fdfd0493a182edb5fa666ac51bd975bd01f8af00e04463c041880bc34da
+size 267832560

run-6/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c0862ea2bd6fadcfbea242aa2491bfbc5ba1feccf312cd79933afbd9244347
+size 535727290

run-6/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c11b6dbe080adf2eda189dce5f92ef4381571eea160f90f82ac93882d28815
+size 14244

run-6/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e38d98a963ef97f9935b2454b41bea55efc72a38a4e5dec3dc4ef7fcf1d5240
+size 1064

run-6/checkpoint-107/special_tokens_map.json

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

run-6/checkpoint-107/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-6/checkpoint-107/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-107",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 107,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6016368865966797,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7752,
+      "eval_samples_per_second": 1345.485,
+      "eval_steps_per_second": 85.141,
+      "step": 107
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 535,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.617587098011209e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 40
+  }
+}

run-6/checkpoint-107/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76371698f5e5e033ea9e0985edf1634d0e473bb92c31fdb1f3c784d2a40e74a9
+size 4984

run-6/checkpoint-214/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": "4.38.1",
+  "vocab_size": 30522
+}

run-6/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45a31323e3adc3b9c173231ba2b7d665e90df1eb0d6c45b0d8f5c3712b7796c
+size 267832560

run-6/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10eb4d7230348739c4d263fb2a5f5ae191b00735579fa8b07818c58dcba50347
+size 535727290

run-6/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4fd978e38e9ebddb06024aa38394cce6a1f7746787c4eb221c96e9f65f21ea
+size 14244

run-6/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a27f6530b58bd79ee43db764fcac0217155346d1dc83376b36804456b22f84c
+size 1064

run-6/checkpoint-214/special_tokens_map.json

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

run-6/checkpoint-214/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-6/checkpoint-214/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.04161454566059593,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-214",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6016368865966797,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7752,
+      "eval_samples_per_second": 1345.485,
+      "eval_steps_per_second": 85.141,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5731037259101868,
+      "eval_matthews_correlation": 0.04161454566059593,
+      "eval_runtime": 0.8647,
+      "eval_samples_per_second": 1206.137,
+      "eval_steps_per_second": 76.323,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 535,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.617587098011209e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 40
+  }
+}

run-6/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76371698f5e5e033ea9e0985edf1634d0e473bb92c31fdb1f3c784d2a40e74a9
+size 4984

run-6/checkpoint-321/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": "4.38.1",
+  "vocab_size": 30522
+}

run-6/checkpoint-321/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d8147c2db9848193e60f1d935f3d1116f029cb2a7d870a089f27cff92606e0
+size 267832560

run-6/checkpoint-321/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5578c01f083bccb4f96473292e8e024c0eafef22aac9b075df9eed50cecae87
+size 535727290

run-6/checkpoint-321/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55827faff1424c9e07a6c2a283b30f48811da781a4d90331f0fd1046756af59b
+size 14244

run-6/checkpoint-321/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7507cbb9c2addea47712aa114f979be53d01170a932260de86fed48f8ab6751
+size 1064

run-6/checkpoint-321/special_tokens_map.json

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

run-6/checkpoint-321/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-6/checkpoint-321/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.21831999836205823,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-321",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 321,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6016368865966797,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7752,
+      "eval_samples_per_second": 1345.485,
+      "eval_steps_per_second": 85.141,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5731037259101868,
+      "eval_matthews_correlation": 0.04161454566059593,
+      "eval_runtime": 0.8647,
+      "eval_samples_per_second": 1206.137,
+      "eval_steps_per_second": 76.323,
+      "step": 214
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5632128715515137,
+      "eval_matthews_correlation": 0.21831999836205823,
+      "eval_runtime": 0.8666,
+      "eval_samples_per_second": 1203.603,
+      "eval_steps_per_second": 76.163,
+      "step": 321
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 535,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.617587098011209e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 40
+  }
+}

run-6/checkpoint-321/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76371698f5e5e033ea9e0985edf1634d0e473bb92c31fdb1f3c784d2a40e74a9
+size 4984

run-7/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": "4.38.1",
+  "vocab_size": 30522
+}

run-7/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2b4c4c37df28d07ac6d2b0f120ec8e4f2a2f6af8e1848b085a2037fb320052
+size 267832560

run-7/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175ef2cea1fd76be64e45c21e8d8ab7f75c964522372f252f631c3cc02eb7d74
+size 535727290

run-7/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6eb0fda4d0a1bf6c3be76eb0c874ca5ae569586decb8166420e1c4bf2edbb2
+size 14244

run-7/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2119d0627d052a18065886cac138ba3b374be6114afe86a6ab0267fbea6a1343
+size 1064

run-7/checkpoint-107/special_tokens_map.json

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

run-7/checkpoint-107/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-7/checkpoint-107/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-107",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 107,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5890523195266724,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8765,
+      "eval_samples_per_second": 1190.006,
+      "eval_steps_per_second": 75.302,
+      "step": 107
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4377950583990715e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 38
+  }
+}

run-7/checkpoint-107/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc558f0f6327d053b3ec0c0bebd34a8955203ccfc2d7e8f0bc1f72b49ced6e0
+size 4984

run-7/checkpoint-214/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": "4.38.1",
+  "vocab_size": 30522
+}

run-7/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923273fb9b5554242f5ab6466b75b019b7d1ef1e9fa96a41d570869e15e2c790
+size 267832560

run-7/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74abae3b81fb80526869e35d0c938fc662c68b68923b4bc665c3844da61b96e9
+size 535727290

run-7/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58997b79d332a117dfe4409a060177890c712813170883f7ef9e106e38e7ea7b
+size 14244

run-7/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e852c9bed423936788e7694c7d3d94a5d754a65b7515c4d76a92b66d942b13e
+size 1064