Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d51b1f7fb21cc21a79270b93502d2534799a43c337dd7c6dd693ea2b02780d
+oid sha256:e255d9da0a1fa2b436a65e914a613f21666b79601d9ce780863dd74b7b4cdb43
 size 267832560

run-2/checkpoint-1072/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": "4.41.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbdd714a61b1c729ef52f62a82f953ce0e864100cf1bfe2c9878506ea22cb397
+size 267832560

run-2/checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090dd0d660ecc3ff45869e7f97fc967535d8d30248d0eb9f2bb8ce8c5fe78cf1
+size 535727290

run-2/checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155267efce647da5f4ae787f7665da52e0813d6d35f1dd512f9a41788c0b2689
+size 14244

run-2/checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9679fe976d9a1907986b778550d3ff6880c276fcb2ece41d08fd93ee3a99568f
+size 1064

run-2/checkpoint-1072/special_tokens_map.json

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

run-2/checkpoint-1072/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-2/checkpoint-1072/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": 0.5218569449731576,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1072",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4662579298019409,
+      "eval_matthews_correlation": 0.4371942629400363,
+      "eval_runtime": 0.7823,
+      "eval_samples_per_second": 1333.256,
+      "eval_steps_per_second": 84.367,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 7.156657695770264,
+      "learning_rate": 1.779275357921531e-05,
+      "loss": 0.4221,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4933030307292938,
+      "eval_matthews_correlation": 0.5051600900029769,
+      "eval_runtime": 0.9851,
+      "eval_samples_per_second": 1058.779,
+      "eval_steps_per_second": 66.998,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5625799298286438,
+      "eval_matthews_correlation": 0.51728018358102,
+      "eval_runtime": 0.73,
+      "eval_samples_per_second": 1428.672,
+      "eval_steps_per_second": 90.405,
+      "step": 804
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 10.139643669128418,
+      "learning_rate": 2.2396473036774517e-06,
+      "loss": 0.1708,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7123728394508362,
+      "eval_matthews_correlation": 0.5218569449731576,
+      "eval_runtime": 0.8073,
+      "eval_samples_per_second": 1292.023,
+      "eval_steps_per_second": 81.758,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 190307528946504.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.334585985475317e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 40
+  }
+}

run-2/checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:797662c4918b42e253fb8a23d373f0129a7aea17f9f7db8453fabf187f249502
+size 5176

run-3/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": "4.41.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e255d9da0a1fa2b436a65e914a613f21666b79601d9ce780863dd74b7b4cdb43
+size 267832560

run-3/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8526e8fa77da2e64228b947049f9aaed5e69fbdb3375ca74585618b218ef78
+size 535727290

run-3/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7420204ce756934358b74169b5e7ac1f0b50022ac6b5031ceea68686e63995f4
+size 14244

run-3/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df0704e57f9f54c81ddc326445961ccfd767ae16da35d1ac529ba18158dcd52
+size 1064

run-3/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-3/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-3/checkpoint-2138/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": 0.39789056142736157,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/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": 0.23386342376052385,
+      "grad_norm": 5.432587623596191,
+      "learning_rate": 4.647117896599981e-06,
+      "loss": 0.5853,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 9.158794403076172,
+      "learning_rate": 3.2285837401286797e-06,
+      "loss": 0.5473,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 12.113940238952637,
+      "learning_rate": 1.8100495836573793e-06,
+      "loss": 0.5397,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 34.98690414428711,
+      "learning_rate": 3.91515427186079e-07,
+      "loss": 0.5173,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5481561422348022,
+      "eval_matthews_correlation": 0.39789056142736157,
+      "eval_runtime": 0.7673,
+      "eval_samples_per_second": 1359.242,
+      "eval_steps_per_second": 86.011,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 32610782805072.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.065652053071281e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 1
+  }
+}

run-3/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8659f2ed11d2c46b28f17647b3484357873136979f2f45d86163cc1e3e0975bb
+size 5176

runs/Jun05_17-06-49_52616c5e4acb/events.out.tfevents.1717608156.52616c5e4acb.227.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9721d5e670a69bcd63720096be0bec0e66a1937cfefc2118c49d53ea8721072f
+size 6319

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797662c4918b42e253fb8a23d373f0129a7aea17f9f7db8453fabf187f249502
+oid sha256:8659f2ed11d2c46b28f17647b3484357873136979f2f45d86163cc1e3e0975bb
 size 5176