Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa786a4c8e38cceeda6cfea8b92771a71615edb332838c173c4826c08110269
+oid sha256:27fa513ba81ff8294def91cdbe7efab084da8262d31de1a21d7e2b069b18cda1
 size 267832560

run-9/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": "4.44.0",
+  "vocab_size": 30522
+}

run-9/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27fa513ba81ff8294def91cdbe7efab084da8262d31de1a21d7e2b069b18cda1
+size 267832560

run-9/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a07c5dc3d8efbb5391239af9af7815a1da4f59dbbc13fca8aa24bf4c01f514
+size 535727290

run-9/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf4e24f2f10c1479c3cc0c08f6c5b0ec1f4f7435d026a8a835334c7aebd88cb
+size 14244

run-9/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d15e35cd849e22d73f744bcb39704340567bc96c1c4bc303ed1bf5224297b3
+size 1064

run-9/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-9/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-9/checkpoint-268/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.4182979471843555,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/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": 0.5013087391853333,
+      "eval_matthews_correlation": 0.4182979471843555,
+      "eval_runtime": 0.7144,
+      "eval_samples_per_second": 1460.02,
+      "eval_steps_per_second": 92.389,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1793106961773818e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 28
+  }
+}

run-9/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19a56ef7d40281592b2e30bbf6caa0b549e649a11a8acc7147b89674c39f156
+size 5240

runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864514.b5f02c58e851.301.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da028a2ff01aece6291308b412800e694fa0f48356a8fb5b4fbcf82f837d7c4
+size 5653

runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864564.b5f02c58e851.301.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4505f7bb2cb9d89dab1313a4ac9266a4d5e3bdc38dde4c40aee26eb5e88b388f
+size 6468

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
+oid sha256:f19a56ef7d40281592b2e30bbf6caa0b549e649a11a8acc7147b89674c39f156
 size 5240