Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6890a22e9a3d6b853cade6e105a5888d82788eb7d96ae3e31c21b7fcc24ba08
+oid sha256:91a4760e35f6d04cbf7fc5d5f10a2f41f152c6e1a184c4f85e3436e5b0817913
 size 267832560

run-0/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": "4.39.3",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a4760e35f6d04cbf7fc5d5f10a2f41f152c6e1a184c4f85e3436e5b0817913
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600c636d7c4c7baa9fb9657842ee45bf613d564f3210dcb9ccd9939067d6205e
+size 535724410

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff4674e5ddf3601567b45d7f992f44bce897b50ec6561faf05ba80a8eb5b693
+size 13990

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe96d9e84c1d4c69817802f8ecd553c5ea687c1171cb0f1a7f63560e8d1de44
+size 1064

run-0/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-0/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-0/checkpoint-2138/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.44397286177085654,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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": 27.878910064697266,
+      "learning_rate": 6.24294726518935e-06,
+      "loss": 0.5804,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 19.8386287689209,
+      "learning_rate": 4.337285706828742e-06,
+      "loss": 0.5484,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 36.36659240722656,
+      "learning_rate": 2.431624148468135e-06,
+      "loss": 0.5157,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 30.039306640625,
+      "learning_rate": 5.259625901075277e-07,
+      "loss": 0.5107,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5229464769363403,
+      "eval_matthews_correlation": 0.44397286177085654,
+      "eval_runtime": 36.6034,
+      "eval_samples_per_second": 28.495,
+      "eval_steps_per_second": 1.803,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 32664597685776.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.148608823549957e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 10
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb8d1e8e53e7bcc6764a44021d1ec64f2c569a7141dccb77149bcce34fea7de
+size 4984

runs/Apr06_21-18-55_3b2751949eb5/events.out.tfevents.1712438408.3b2751949eb5.9166.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff3738706ebb14a7f3f4950f67b626587a99f7389a2d2de5bd6e24fb29de59e
-size 7288
+oid sha256:7698cf81556a1182141ad336cfdc5c5362fb14e45716474a78afe3705c5dca45
+size 7642

runs/Apr06_21-18-55_3b2751949eb5/events.out.tfevents.1712446043.3b2751949eb5.9166.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee661787f9835b839e1e91a9de2e49e1e9ef94556cc3059037a9e566407dfb9
+size 423

runs/Apr06_21-18-55_3b2751949eb5/events.out.tfevents.1712446225.3b2751949eb5.9166.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e4798e42316ef3251ce3ac695a75e45996fd64dc6ded15f35c77bc0216f392
+size 6106

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a4099796b69e5e40be49e01c3e318bfcd54608a36f3ac809cab3929cc8765a
+oid sha256:9bb8d1e8e53e7bcc6764a44021d1ec64f2c569a7141dccb77149bcce34fea7de
 size 4984