Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99caf0eb1878e80d479c62b9aad8f39bd1f863accc563d43d194e0602a791e2
+oid sha256:03913a01f62ca0fae77c8ed97bdd00742f1b2d42850996356229d5b3123eed96
 size 267832560

run-1/checkpoint-5345/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-1/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03913a01f62ca0fae77c8ed97bdd00742f1b2d42850996356229d5b3123eed96
+size 267832560

run-1/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa0aa7540a1a556817674799fffc03802bf6f7519ee59ca6673a909ecc4df7b
+size 535727290

run-1/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fc6508ba45e9e0842afb0e5dacc6abe7b220936e427628ec9427a8e21c7e48
+size 14244

run-1/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c407bc28f908e4a86d50fc8530f1bbdc1e92ba51a7a271734e874eae0e877a5
+size 1064

run-1/checkpoint-5345/special_tokens_map.json

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

run-1/checkpoint-5345/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-1/checkpoint-5345/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_metric": 0.4587117762521935,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-5345",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5345,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 3.3249642848968506,
+      "learning_rate": 2.6473754154284133e-06,
+      "loss": 0.5965,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 8.79763126373291,
+      "learning_rate": 2.374168458211859e-06,
+      "loss": 0.5425,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5592656135559082,
+      "eval_matthews_correlation": 0.3185499653238633,
+      "eval_runtime": 0.8547,
+      "eval_samples_per_second": 1220.347,
+      "eval_steps_per_second": 77.222,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 11.57971477508545,
+      "learning_rate": 2.1009615009953043e-06,
+      "loss": 0.4787,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 27.781993865966797,
+      "learning_rate": 1.8277545437787497e-06,
+      "loss": 0.481,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5462123155593872,
+      "eval_matthews_correlation": 0.4094622199164031,
+      "eval_runtime": 0.8507,
+      "eval_samples_per_second": 1226.054,
+      "eval_steps_per_second": 77.583,
+      "step": 2138
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 13.08643913269043,
+      "learning_rate": 1.554547586562195e-06,
+      "loss": 0.4459,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 9.741808891296387,
+      "learning_rate": 1.2813406293456407e-06,
+      "loss": 0.4186,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5483449101448059,
+      "eval_matthews_correlation": 0.4402056101061122,
+      "eval_runtime": 0.8619,
+      "eval_samples_per_second": 1210.174,
+      "eval_steps_per_second": 76.579,
+      "step": 3207
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 16.822460174560547,
+      "learning_rate": 1.008133672129086e-06,
+      "loss": 0.4234,
+      "step": 3500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 16.580455780029297,
+      "learning_rate": 7.349267149125318e-07,
+      "loss": 0.3852,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5416076183319092,
+      "eval_matthews_correlation": 0.45272024342354794,
+      "eval_runtime": 0.7844,
+      "eval_samples_per_second": 1329.746,
+      "eval_steps_per_second": 84.145,
+      "step": 4276
+    },
+    {
+      "epoch": 4.209541627689429,
+      "grad_norm": 42.24811553955078,
+      "learning_rate": 4.617197576959771e-07,
+      "loss": 0.3772,
+      "step": 4500
+    },
+    {
+      "epoch": 4.677268475210477,
+      "grad_norm": 15.730141639709473,
+      "learning_rate": 1.8851280047942264e-07,
+      "loss": 0.381,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5439215302467346,
+      "eval_matthews_correlation": 0.4587117762521935,
+      "eval_runtime": 0.9757,
+      "eval_samples_per_second": 1068.975,
+      "eval_steps_per_second": 67.644,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 188221943593836.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.9205823726449678e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 30
+  }
+}

run-1/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42c4d2a999c1e4ff66df89319e9d95837c30aff779cc4f7616f920a4e6d2f28
+size 5240

runs/Aug17_02-12-22_2566451b250f/events.out.tfevents.1723861941.2566451b250f.233.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a64a764662ac4df6f7ff7e9486711b88db3530f070b7cafbdf535576c259b50
-size 8133
+oid sha256:aaf0e860fd158c8a4f6908aec94a2ba7bd83acc13b28bc3761ccdcd67f11ad0d
+size 9033