Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91afdaa9ddc53365eabb84aba2855421cf1f0aafed81c9fc51905a052dc361cd
+oid sha256:382f0a6efb23020758110a083609f0e7dc6093ffecd86f65e74d3b801ec3c468
 size 267832560

run-3/checkpoint-4276/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": "4.45.1",
+  "vocab_size": 30522
+}

run-3/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382f0a6efb23020758110a083609f0e7dc6093ffecd86f65e74d3b801ec3c468
+size 267832560

run-3/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c609a00fa8fe076a891acd03706bbfa708bffcf79afdf10ecb118c8b2234394
+size 535727290

run-3/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df2e562f1772f1481ba79ec471bbff5bfda80bc2d12b9d041dc946439c54f80
+size 14308

run-3/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b773d24c88e833b8fa4f69a2b969078870e11b975780f2b182bdd50925b59ac
+size 1064

run-3/checkpoint-4276/special_tokens_map.json

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

run-3/checkpoint-4276/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": false,
+  "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-3/checkpoint-4276/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": 0.4070679974020536,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 3.809316873550415,
+      "learning_rate": 1.6810207979134526e-06,
+      "loss": 0.636,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 7.557185649871826,
+      "learning_rate": 1.5985369511071005e-06,
+      "loss": 0.5765,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 7.614924907684326,
+      "learning_rate": 1.5160531043007487e-06,
+      "loss": 0.568,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 13.481077194213867,
+      "learning_rate": 1.4335692574943967e-06,
+      "loss": 0.5484,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5601772665977478,
+      "eval_matthews_correlation": 0.21725141763919706,
+      "eval_runtime": 0.727,
+      "eval_samples_per_second": 1434.725,
+      "eval_steps_per_second": 90.788,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 17.71332550048828,
+      "learning_rate": 1.3510854106880447e-06,
+      "loss": 0.5331,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 12.712360382080078,
+      "learning_rate": 1.2686015638816928e-06,
+      "loss": 0.5051,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 18.72041893005371,
+      "learning_rate": 1.1861177170753408e-06,
+      "loss": 0.5068,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 38.66783905029297,
+      "learning_rate": 1.1036338702689888e-06,
+      "loss": 0.5094,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.590541422367096,
+      "eval_matthews_correlation": 0.4070679974020536,
+      "eval_runtime": 0.7343,
+      "eval_samples_per_second": 1420.312,
+      "eval_steps_per_second": 89.876,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 65420525433516.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7635046447198044e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 24
+  }
+}

run-3/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2baa45c4818a50850c38ec1f13878f29e4d9a6936edc123180f120c433e1aff2
+size 5304

runs/Oct02_05-18-55_0fd1839bafe2/events.out.tfevents.1727847306.0fd1839bafe2.228.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b28f3d1ce9a74f472d0065da4ca207e4de830442600b180f4ed0069bb7dab0
-size 6316
+oid sha256:5c111c4bb80403a7f1bbb106f1f4f9227c1a6aed0c6c389c962ee64c2fc007c4
+size 7706