Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1d8792b9e5b1a38a470736c5c3296d6aeeeb6889d417282c56c97622d21b01
+oid sha256:427f25221a88c6378e1bef9c6b7fdf559ab1100bb06c7a3709d3c6893bff0d0f
 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": "4.39.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427f25221a88c6378e1bef9c6b7fdf559ab1100bb06c7a3709d3c6893bff0d0f
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b93eab5a661a4bccb362617e80fc2f01a54762c60c5acc10c40445ae265db23
+size 535727290

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d9ddd14b56ab83bc4d8ac0fdbc08a63711e37f31433d8c9459731b91be4d45
+size 14244

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4699be2d0bbac1d76bd58bb4c1a4f6d5b1ff04fccb1f1244023a2405c7cffd0
+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 +1,55 @@
+{
+  "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-0/checkpoint-2138/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.2045620264226157,
+  "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": 0.47,
+      "grad_norm": 3.136430025100708,
+      "learning_rate": 1.057670968337005e-06,
+      "loss": 0.6141,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.4976818561553955,
+      "learning_rate": 9.485201976107919e-07,
+      "loss": 0.5835,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5739973187446594,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.1959,
+      "eval_samples_per_second": 474.985,
+      "eval_steps_per_second": 30.057,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 5.231539249420166,
+      "learning_rate": 8.393694268845788e-07,
+      "loss": 0.5608,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 7.4941792488098145,
+      "learning_rate": 7.302186561583657e-07,
+      "loss": 0.5232,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5443820953369141,
+      "eval_matthews_correlation": 0.2045620264226157,
+      "eval_runtime": 0.9649,
+      "eval_samples_per_second": 1080.926,
+      "eval_steps_per_second": 68.4,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 75421814032044.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.166821739063218e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 23
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec708c48a1d20e757d0e32ebecb11c5a942f99a1c01da631d491c2e4de94629
+size 4984