Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba662e8f6628a8ecca2f6281507da3a37d6d28b0bc38ffded77bc5feb72f1d55
+oid sha256:8758dcb0078eefe9adb2f12509a04c3b40cf7cf3666d8278483e41937553d789
 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": "4.36.2",
+  "vocab_size": 30522
+}

run-9/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8758dcb0078eefe9adb2f12509a04c3b40cf7cf3666d8278483e41937553d789
+size 267832560

run-9/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83721ffff1c6aae6a6ba9b2109480def6677a391aecad868952381d1409930c
+size 535727290

run-9/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8cfe25a915f9cc83ad71e9d831288a4edb9a530a69cb0778e7d75bb45a8399
+size 14308

run-9/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db728233ea94ae799817782cbaec3b565f2d263513c3b5bccbbce90de12aa4f5
+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 +1,35 @@
+{
+  "best_metric": 0.4111094454070522,
+  "best_model_checkpoint": "andyWuTw/homework001-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": 0.4982806444168091,
+      "eval_matthews_correlation": 0.4111094454070522,
+      "eval_runtime": 0.7761,
+      "eval_samples_per_second": 1343.821,
+      "eval_steps_per_second": 85.036,
+      "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": 2.7152703474109707e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 20
+  }
+}

run-9/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84aaf52955cc7f2fa3bf197391c0376aab12655399abba40692c6263de93b12f
+size 4792

runs/Dec23_02-16-37_5c7585257882/events.out.tfevents.1703299499.5c7585257882.414.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5f60ed9b3676fdaff3781d1fa473447ecee28a073845153a161cc42f25991d
+size 5030

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:159b8defda3a703e58ab6ee51cb104af5d499eae2b04895d20f80e2432451d20
+oid sha256:84aaf52955cc7f2fa3bf197391c0376aab12655399abba40692c6263de93b12f
 size 4792