Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec41c06410822efe0d1cceabc14e18037e38f1ce94122d4ed867e47a5975d1d
+oid sha256:3b461a0f10db195dda246162d1c81b579a0475c7de3d0e5c666b5a94c259f402
 size 267832560

run-8/checkpoint-107/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-8/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b461a0f10db195dda246162d1c81b579a0475c7de3d0e5c666b5a94c259f402
+size 267832560

run-8/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19e028e8bcccab50785b167b06739e1b15c841933e340c16032714f3f58558e
+size 535727290

run-8/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce8bf176f233b3f8fabc03fd982b5e88184098789c0cdd12487029cb039054a
+size 14244

run-8/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83e30d7c12ba81678da4b722ab2d26d56bacd4e772b31ee79150eef33cd63aa
+size 1064

run-8/checkpoint-107/special_tokens_map.json

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

run-8/checkpoint-107/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-8/checkpoint-107/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-107",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 107,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5813318490982056,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4888,
+      "eval_samples_per_second": 2133.724,
+      "eval_steps_per_second": 135.02,
+      "step": 107
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 321,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.438273396233882e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 36
+  }
+}

run-8/checkpoint-107/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8238f446d69fcc6cc9010ead2f33f328df1196aac5b15d9bdce1a4f9bead8e06
+size 4984

runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685268.ec6659c07f12.1051.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af2497570cec05073ddd718408958cbe6fe1b8a8f440996525ff5c89ccf9c81
+size 5894

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50a685198f26eae14f5a354156c245a895e2f4a69a4ef06f7692ec99269431f
+oid sha256:8238f446d69fcc6cc9010ead2f33f328df1196aac5b15d9bdce1a4f9bead8e06
 size 4984