Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e109e9db1e806359f9f80344ae5b92c21b483e1ec5e90d159af324b7ea7835f6
+oid sha256:9a68461a17fd4260acf9ef0fa76418a9e4c92faffa45aa6228266734d0963c61
 size 267832560

run-0/checkpoint-268/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": "4.36.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a68461a17fd4260acf9ef0fa76418a9e4c92faffa45aa6228266734d0963c61
+size 267832560

run-0/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f056b2a5d25f6849c3a70773a587900b8e104a5e81271ad0adc3d79b30601436
+size 535724410

run-0/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a082b5bdd2bf00c89fb62ba5d9e1d6b8e5fcb6f7f6ec6f17a6ab2c291ff41d5a
+size 13990

run-0/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a2eb9d9ebf22f5236edfac447e09b019ca7326c59fb8dc93cb28d7cf27a1d1
+size 1064

run-0/checkpoint-268/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-268/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-268/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-0\\checkpoint-268",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5734525918960571,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 6.1223,
+      "eval_samples_per_second": 170.361,
+      "eval_steps_per_second": 10.78,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.110280688187178e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 22
+  }
+}

run-0/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cc95a7867972a8a3e5df6082d22b5af5d6d813216b363e3dca2eafb740bdec
+size 4792

runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702383514.DESKTOP-UUVDD26.9476.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f1647289f2fb659f49f60e3fa46f477d174818552debe0db937718b0c65338
+size 5025

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0bafcf40a203ff1dd9c259a3287958fc555711767855ffdaf73c5c5553f359
+oid sha256:12cc95a7867972a8a3e5df6082d22b5af5d6d813216b363e3dca2eafb740bdec
 size 4792