Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c183ff2fd02f9a631531f466f5f0645fee3e51d7ced576aa425e91a5aa6055cc
+oid sha256:a979d9d1a25b69535bfb1d28b1414aef10a3e9edcaba09bac3ba7638deb517c2
 size 267832560

run-9/checkpoint-2138/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": "4.38.2",
+  "vocab_size": 30522
+}

run-9/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a979d9d1a25b69535bfb1d28b1414aef10a3e9edcaba09bac3ba7638deb517c2
+size 267832560

run-9/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5091e8f32dcaceff0c5146b60b108129f8753a08122986840940abc46f1a5d3
+size 535727290

run-9/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d397e91a8e27617cdc21beb7fc232f075b50df3e73f064c98f0b19870d0bd7
+size 14308

run-9/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625f31ab4ed72fdd21dca6a00a6ead0cd54f5f29993a59e1f1c059f72fdf71fb
+size 1064

run-9/checkpoint-2138/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-2138/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-2138/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.4760180026275787,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.149616241455078,
+      "learning_rate": 2.4285530817760866e-05,
+      "loss": 0.5966,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 13.129973411560059,
+      "learning_rate": 1.6872365122473665e-05,
+      "loss": 0.5696,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 8.157123565673828,
+      "learning_rate": 9.459199427186466e-06,
+      "loss": 0.546,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 21.74394989013672,
+      "learning_rate": 2.046033731899267e-06,
+      "loss": 0.5128,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5494452714920044,
+      "eval_matthews_correlation": 0.4760180026275787,
+      "eval_runtime": 0.7703,
+      "eval_samples_per_second": 1353.99,
+      "eval_steps_per_second": 85.679,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 32649074162496.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.1698696513048064e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 26
+  }
+}

run-9/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77069a031998a2ed435bb4f2b1bd0ee42e40799017d3dcac30a63170087f37a
+size 4984

runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709495469.abc5bcbabcce.1176.38

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab68e4f33beb70c8c81a23180326ae4aa56827c74714d963ed68c65a519f7257
+size 6075

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f3fb7a8e469fffcc0514969a4125346a0b60d0d6e062eed71aa43df9aab5e9
+oid sha256:f77069a031998a2ed435bb4f2b1bd0ee42e40799017d3dcac30a63170087f37a
 size 4984