Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ccde9a774ec8a26cd631c628ef13c7e5ba109c5ec157a8a40a631f860bf26d2
+oid sha256:be5de4f66806a17f73e9b21a9eb2d755de679ef8de8584d2fb205a0a836466e3
 size 267832560

run-0/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": "4.44.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8862d875c7ffef2d457fa1d5555797ba0c8b35f7bee1f791922e5dce3ce7fcba
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806609b9491d7d2ff71b6782aa85b4d289465b4f58ebb669ae3175bde868ca82
+size 535724410

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88e827600293d68e0d3a74ae63b7019c8e3e6870b358f191616e6f9c7d37e5b
+size 14054

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce2f3fa46b0f6f45ff61702fef19634b2a5aa6d59f4e74457bbb314382c8afc3
+size 1064

run-0/checkpoint-2138/special_tokens_map.json

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

run-0/checkpoint-2138/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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]",
+  "use_fase": true
+}

run-0/checkpoint-2138/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.44455763518973207,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 8.62888240814209,
+      "learning_rate": 5.373752855939329e-06,
+      "loss": 0.5755,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 20.624385833740234,
+      "learning_rate": 4.381186757686775e-06,
+      "loss": 0.5165,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5140782594680786,
+      "eval_matthews_correlation": 0.4102877158206736,
+      "eval_runtime": 2.0196,
+      "eval_samples_per_second": 516.439,
+      "eval_steps_per_second": 32.68,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 10.336002349853516,
+      "learning_rate": 3.38862065943422e-06,
+      "loss": 0.4425,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 11.466729164123535,
+      "learning_rate": 2.396054561181666e-06,
+      "loss": 0.4078,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5298678874969482,
+      "eval_matthews_correlation": 0.44455763518973207,
+      "eval_runtime": 2.0041,
+      "eval_samples_per_second": 520.439,
+      "eval_steps_per_second": 32.933,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 75003196354260.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.366318954191884e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 21
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde6ab59b8d311cad8b5f7d441ed247ee7245fea7cbe6db6367b1fe39301cdc6
+size 5240

run-0/checkpoint-3207/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": "4.44.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1441ad96f5337212b6d7161f1f8b8598f5fe287673c76f4db67d42c112b689
+size 267832560

run-0/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f641094845399c5ae20c6d8593017ae43880bc2124a9df0c6c4d88455cc8d1
+size 535724410

run-0/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3d6b7f550c1ec98c1452af3f648ff3ea6b8ffd3d56c1e5a2a2819527f832be
+size 14054

run-0/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376ce344d81781d426cae7b37563c448f160c6860564eac3ea1c27a0a38ea7a2
+size 1064

run-0/checkpoint-3207/special_tokens_map.json

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

run-0/checkpoint-3207/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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]",
+  "use_fase": true
+}

run-0/checkpoint-3207/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": 0.4756138930857138,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-3207",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3207,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 8.62888240814209,
+      "learning_rate": 5.373752855939329e-06,
+      "loss": 0.5755,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 20.624385833740234,
+      "learning_rate": 4.381186757686775e-06,
+      "loss": 0.5165,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5140782594680786,
+      "eval_matthews_correlation": 0.4102877158206736,
+      "eval_runtime": 2.0196,
+      "eval_samples_per_second": 516.439,
+      "eval_steps_per_second": 32.68,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 10.336002349853516,
+      "learning_rate": 3.38862065943422e-06,
+      "loss": 0.4425,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 11.466729164123535,
+      "learning_rate": 2.396054561181666e-06,
+      "loss": 0.4078,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5298678874969482,
+      "eval_matthews_correlation": 0.44455763518973207,
+      "eval_runtime": 2.0041,
+      "eval_samples_per_second": 520.439,
+      "eval_steps_per_second": 32.933,
+      "step": 2138
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 22.138774871826172,
+      "learning_rate": 1.4034884629291118e-06,
+      "loss": 0.3583,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 7.407865524291992,
+      "learning_rate": 4.1092236467655754e-07,
+      "loss": 0.3541,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5446668267250061,
+      "eval_matthews_correlation": 0.4756138930857138,
+      "eval_runtime": 2.3169,
+      "eval_samples_per_second": 450.175,
+      "eval_steps_per_second": 28.487,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 112738035468672.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.366318954191884e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 21
+  }
+}

run-0/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde6ab59b8d311cad8b5f7d441ed247ee7245fea7cbe6db6367b1fe39301cdc6
+size 5240

run-1/checkpoint-134/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": "4.44.0",
+  "vocab_size": 30522
+}

run-1/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5de4f66806a17f73e9b21a9eb2d755de679ef8de8584d2fb205a0a836466e3
+size 267832560

run-1/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec8efd97b0aeba9e441614e551de112f80a03e43cf459732f5dc77fd82b3d51
+size 535724410

run-1/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec846d15db5dc3e66ff7d11200b479e630b1643fd1e88a94a77a6d42651039b
+size 14054

run-1/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68112e4cdb271691a2a80b63789db8df4f616da2dd0695e0e1b6c859fdb04751
+size 1064

run-1/checkpoint-134/special_tokens_map.json

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

run-1/checkpoint-134/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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]",
+  "use_fase": true
+}

run-1/checkpoint-134/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.4134570857201349,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-134",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4964956045150757,
+      "eval_matthews_correlation": 0.4134570857201349,
+      "eval_runtime": 2.1558,
+      "eval_samples_per_second": 483.816,
+      "eval_steps_per_second": 30.615,
+      "step": 134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 402,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.146319405451159e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 8
+  }
+}

run-1/checkpoint-134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26b743a3008358f63a220f53ba9af8361b467b4e0f76c3ae148f396425a60b6
+size 5240

runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723427584.sunyoungui-MacBookPro.local.38891.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152b0949b7f99fffadf55c51077d5f36e36d79b42c57059d0cfc7a8bd056c1dd
-size 5655
+oid sha256:05587a6093cb874b49e4ac6ba66d0e4d37a980d0ab1079c98f06e0d82b59c01e
+size 7523

runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723428017.sunyoungui-MacBookPro.local.38891.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6c84ff61516b6529709a29362a9de97a7f59630c1d1b9409d038534aeafa38
+size 5233

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde6ab59b8d311cad8b5f7d441ed247ee7245fea7cbe6db6367b1fe39301cdc6
+oid sha256:e26b743a3008358f63a220f53ba9af8361b467b4e0f76c3ae148f396425a60b6
 size 5240