Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a671a30815a62b13b5a43d40b02d8cc7de7e348cba3d600bdc67de75dc5c5c9
+oid sha256:2958ac0dec5191f58d9b4e5a4215e8da99d6aaba16b49946896fa75bf5a65162
 size 267832560

run-3/checkpoint-8552/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-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2958ac0dec5191f58d9b4e5a4215e8da99d6aaba16b49946896fa75bf5a65162
+size 267832560

run-3/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4156b0405ad255c33172027d83dbfc1ab82c482ceab6b13b457fe8dd5384392b
+size 535727290

run-3/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:569df1e78d6ffd826bac93a7f71119d566154a577158a4eda9bf6424b3f02a74
+size 14308

run-3/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529f13dd4051a160e8022d543ba1c29e65f8d7984fdcfd91edd70b52390a533e
+size 1064

run-3/checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 0.4202485934984447,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-8552",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "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
+    },
+    {
+      "epoch": 2.1047708138447145,
+      "grad_norm": 51.199073791503906,
+      "learning_rate": 1.021150023462637e-06,
+      "loss": 0.4941,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 4.427803993225098,
+      "learning_rate": 9.38666176656285e-07,
+      "loss": 0.4566,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5724976613657624,
+      "grad_norm": 4.70788049697876,
+      "learning_rate": 8.561823298499331e-07,
+      "loss": 0.4852,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 14.298940658569336,
+      "learning_rate": 7.736984830435811e-07,
+      "loss": 0.4736,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6443806290626526,
+      "eval_matthews_correlation": 0.42003066615098444,
+      "eval_runtime": 0.7499,
+      "eval_samples_per_second": 1390.864,
+      "eval_steps_per_second": 88.013,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0402245088868103,
+      "grad_norm": 62.8742561340332,
+      "learning_rate": 6.912146362372292e-07,
+      "loss": 0.4843,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 9.63222599029541,
+      "learning_rate": 6.087307894308773e-07,
+      "loss": 0.4431,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5079513564078577,
+      "grad_norm": 25.24190330505371,
+      "learning_rate": 5.262469426245253e-07,
+      "loss": 0.534,
+      "step": 7500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 11.94974136352539,
+      "learning_rate": 4.437630958181735e-07,
+      "loss": 0.4547,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9756782039289056,
+      "grad_norm": 26.345199584960938,
+      "learning_rate": 3.6127924901182145e-07,
+      "loss": 0.4619,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6735975742340088,
+      "eval_matthews_correlation": 0.4202485934984447,
+      "eval_runtime": 0.7591,
+      "eval_samples_per_second": 1374.064,
+      "eval_steps_per_second": 86.949,
+      "step": 8552
+    }
+  ],
+  "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": 138701128154472.0,
+  "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-8552/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 sha256:579a13fdc75b1059885b1d827290014c56946df1526c9102179a418cbb607adb
-size 9096
+oid sha256:41102b87f56e4125d69d859d32a32f2b2cbe9c0880627237a75866c5866a365c
+size 10275