Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4662f4e8dc27c8b2567b4f06b9dbafd4f1b814ede8a5f6f32991cd0b16885e0e
+oid sha256:0bbf877073a9713d16c87b087bcc1bebfe560f12c2c9cba91b180f7cc275c7b1
 size 267832560

run-4/checkpoint-108/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-4/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1199587ed1d031aeff0b2d48d0f514c3de091775d0f4359a399d68dfba0cd680
+size 267832560

run-4/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf82ddb25ca867ef4daab7ac2f6a6a2c63ce87e1346b43d0c80cbc737ce9231
+size 535727290

run-4/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1592c6c7d425e047a040d85ed72274684f3070b72374af37eae3af77db9be0b
+size 14244

run-4/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25447ff2e65e7207e6020e90e6e2061d217b59370b0d392cfc214676353dc946
+size 1064

run-4/checkpoint-108/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-108/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-108/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6172463297843933,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7437,
+      "eval_samples_per_second": 1402.475,
+      "eval_steps_per_second": 88.747,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6110989451408386,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7979,
+      "eval_samples_per_second": 1307.237,
+      "eval_steps_per_second": 82.721,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.60643470287323,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8288,
+      "eval_samples_per_second": 1258.39,
+      "eval_steps_per_second": 79.63,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6032094359397888,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8998,
+      "eval_samples_per_second": 1159.167,
+      "eval_steps_per_second": 73.351,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.784461117596466e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 15
+  }
+}

run-4/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443eb1867eb54327e419f78e290432cb32b5c391fff06995ea104f10aaafb654
+size 4984

run-4/checkpoint-54/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-4/checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e3544906f407e16d666a7f5eb664e97afa7bece2f0df6c07a4af7523ddd6b5
+size 267832560

run-4/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd751e964504a3ccfebdbd24ea228b7bb94bc4378c7d11fb075ddeb8644f6256
+size 535727290

run-4/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e134a945a8c09dbe3c3e74ec36d9a17c0f35f9759b7fc9e96fefe249cf37f0
+size 14244

run-4/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e35b3c3e3dc5b382ab34857dd85a1d461e356705523de6eecc1c61bb1c9045
+size 1064

run-4/checkpoint-54/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-54/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-54/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6172463297843933,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7437,
+      "eval_samples_per_second": 1402.475,
+      "eval_steps_per_second": 88.747,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6110989451408386,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7979,
+      "eval_samples_per_second": 1307.237,
+      "eval_steps_per_second": 82.721,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.784461117596466e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 15
+  }
+}

run-4/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443eb1867eb54327e419f78e290432cb32b5c391fff06995ea104f10aaafb654
+size 4984

run-4/checkpoint-81/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-4/checkpoint-81/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442f4d82a5b9b6e0c6161516092ae6d86ddacc6937290a0cdf173d746517a3b8
+size 267832560

run-4/checkpoint-81/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eaea720e4208f042a73e43c091d722b1f9a763fd7eb828f8793368e6f0d9281
+size 535727290

run-4/checkpoint-81/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165811e503804aa40e47060a62db9408197cf06bf701e9d5009fe4f87d75238c
+size 14244

run-4/checkpoint-81/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fecc908a6f82fa0d261687da216234af2e5f1735cd07a343d2d1ff55946ed5
+size 1064

run-4/checkpoint-81/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-81/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-81/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6172463297843933,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7437,
+      "eval_samples_per_second": 1402.475,
+      "eval_steps_per_second": 88.747,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6110989451408386,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7979,
+      "eval_samples_per_second": 1307.237,
+      "eval_steps_per_second": 82.721,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.60643470287323,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8288,
+      "eval_samples_per_second": 1258.39,
+      "eval_steps_per_second": 79.63,
+      "step": 81
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.784461117596466e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 15
+  }
+}

run-4/checkpoint-81/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443eb1867eb54327e419f78e290432cb32b5c391fff06995ea104f10aaafb654
+size 4984

run-5/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8e094b67327e2df694cc6bfa18daddb4b063fcc412c8f1f3bee1a2166db21e
+oid sha256:0bbf877073a9713d16c87b087bcc1bebfe560f12c2c9cba91b180f7cc275c7b1
 size 267832560

run-5/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f12faf965dff58f40b9355809e8adbe3d9a43764797300f88ddf3b1cb062ac0
+oid sha256:78880a2b0f9fa119b8aff6f6ef5ed9f614faea74bf24354c861845daa4f9cc0d
 size 535727290

run-5/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42e2747302ca66575567cd2ad92e4c499840df43d7c74871abe2a004c812c2b
+oid sha256:8dd2c9f09417dd8fc54a482da6d2926a7da5940a89b7dab8d1b45e1891089a0b
 size 14244

run-5/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748021ffaf65c340e0b18eeeb8068b046adf5b1571541c4525464f22568aed7b
+oid sha256:189625799b8f1b03ee1d0f9d14e5831ebbc462c1ebaa771fe82b21f62403d8b9
 size 1064

run-5/checkpoint-54/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": 0.0,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-27",
-  "epoch": 2.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-54",
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 54,
   "is_hyper_param_search": true,
@@ -10,35 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6419833302497864,
+      "eval_loss": 0.6223766207695007,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.8978,
-      "eval_samples_per_second": 1161.719,
-      "eval_steps_per_second": 73.512,
-      "step": 27
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.6295746564865112,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.8402,
-      "eval_samples_per_second": 1241.318,
-      "eval_steps_per_second": 78.549,
+      "eval_runtime": 0.7165,
+      "eval_samples_per_second": 1455.603,
+      "eval_steps_per_second": 92.109,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 81,
+  "max_steps": 216,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.2137358701553763e-06,
-    "num_train_epochs": 3,
-    "per_device_train_batch_size": 32,
-    "seed": 11
+    "learning_rate": 2.6586381863896615e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 23
   }
 }

run-5/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d0fa30219cd780fa15bb36c41b552337e69f4b8abe90ea1feffc93833591be
+oid sha256:bf05262a2ee600d4bc72f4472c7df009ef0f8da02a622b920dc4c1da59d98947
 size 4984

runs/Feb27_14-43-24_1abfc43efc69/events.out.tfevents.1709045925.1abfc43efc69.155.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ca4bc33d96a4e94016081c1dc7f2c3eee41070a9a6e7e7d9b8119425fc0106
+size 5536

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443eb1867eb54327e419f78e290432cb32b5c391fff06995ea104f10aaafb654
+oid sha256:bf05262a2ee600d4bc72f4472c7df009ef0f8da02a622b920dc4c1da59d98947
 size 4984