Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7833440ea5ed324b14901fee7dc00427dc794e5f2fbcc8293296dc3c07c7f4c6
+oid sha256:6ce3ad60cef1e6feccfea104b5cf8b6d767565705e14682f6f0e8ce22fffb8d2
 size 267832560

run-1/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": "4.39.3",
+  "vocab_size": 30522
+}

run-1/checkpoint-670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce3ad60cef1e6feccfea104b5cf8b6d767565705e14682f6f0e8ce22fffb8d2
+size 267832560

run-1/checkpoint-670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a6fa4c5e963bc860a973d4923d4a5dd93a36e4878d516da23ebe24b12674ef
+size 535724410

run-1/checkpoint-670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12bed73e87999220f84068c4838a3b1df4f1c0f31cf6758113b3621c1aaef10
+size 13990

run-1/checkpoint-670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19f7d24c95eca5131a2ffe64edefecf8a40f0ed6d00b7ea7c6f0de469b6a0aa
+size 1064

run-1/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-1/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-1/checkpoint-670/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-134",
+  "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": 0.6137625575065613,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 36.6021,
+      "eval_samples_per_second": 28.496,
+      "eval_steps_per_second": 1.803,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5987810492515564,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 36.8222,
+      "eval_samples_per_second": 28.325,
+      "eval_steps_per_second": 1.792,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5791416168212891,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 37.6773,
+      "eval_samples_per_second": 27.682,
+      "eval_steps_per_second": 1.752,
+      "step": 402
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 2.049774408340454,
+      "learning_rate": 4.1397348321527435e-07,
+      "loss": 0.5959,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5682925581932068,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 37.2686,
+      "eval_samples_per_second": 27.986,
+      "eval_steps_per_second": 1.771,
+      "step": 536
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5650252103805542,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 38.558,
+      "eval_samples_per_second": 27.05,
+      "eval_steps_per_second": 1.712,
+      "step": 670
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 209861476320768.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.631542551495493e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 6
+  }
+}

run-1/checkpoint-670/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5b935ca08b0b7d98978f23a4eaf03b4afc2e6ee9cc6948f40b4c1adac9206e
+size 4984

runs/Apr06_21-18-55_3b2751949eb5/events.out.tfevents.1712449293.3b2751949eb5.9166.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf2907e06602123943e25717f01f88b8b114f02982b395e000fb5f0dfc0af928
-size 6124
+oid sha256:dd8b1b97f248ba9bbe4d1c7e4d3daa7755cc40822dea2fc13a28ac060584ab5f
+size 6813