Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19b69c7ad6b6305a78ee7a62eb2b4a76e1f64937bf04a6cb2a9610ed0624cdd5
+oid sha256:09610a27c594ea3d6ad7f3269226be50f2b90d324d4ba44ac4dc3ac42e57fdcc
 size 267832560

run-9/checkpoint-535/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-9/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09610a27c594ea3d6ad7f3269226be50f2b90d324d4ba44ac4dc3ac42e57fdcc
+size 267832560

run-9/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fa81260a055066364f08eaec8edbc46081b0a353fd05c8cce36d7efced8ae4
+size 535727290

run-9/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af77c0b23e3a66be9934e6578488d77a1b8cd26be2e61c9a8b75efda601230ce
+size 14244

run-9/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1253af0eaed34f70f35a7c7c6a698333690f8e9b9484604ba5f806ad464c3a
+size 1064

run-9/checkpoint-535/special_tokens_map.json

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

run-9/checkpoint-535/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-9/checkpoint-535/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.47192796522130964,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-9\\checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "grad_norm": 6.588393688201904,
+      "learning_rate": 1.008167296920146e-05,
+      "loss": 0.5294,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4878699779510498,
+      "eval_matthews_correlation": 0.47192796522130964,
+      "eval_runtime": 0.7915,
+      "eval_samples_per_second": 1317.833,
+      "eval_steps_per_second": 83.391,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 42973252045248.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3155353752494588e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 15
+  }
+}

run-9/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92c852bb39d5954aded9fe8be9a3f4080f8cf089dcfbdae1e33dcddc4d88efa
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c933d4a33d4156fc3a8e1969ff2362d7028ce0add44b6246de99b35eb978b54b
+oid sha256:c92c852bb39d5954aded9fe8be9a3f4080f8cf089dcfbdae1e33dcddc4d88efa
 size 4984