Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206fae79d17296218a9d3d778b99f79bd898285505f68e6f4f86815e588fe52b
+oid sha256:31af0226b8031aeacee5d2e12897fc0347e10d3e4d6527ffd742dc1fa8541e28
 size 267832560

run-5/checkpoint-1070/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-5/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35e552fd6ecf29a3ee8cf9158215c6f45ad90fcdb4b019b5420423c1e31dfcf6
+size 267832560

run-5/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3911264cda0115a18d96d7f79f71d32f150378d14069b95d42f347856f61d9b
+size 535727290

run-5/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840b3d4b08161378e7753e4f3bf25def98d15d6bc1d1cf0ce104ad57f4c62688
+size 14244

run-5/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d457e89e341552124d6bd58afcc9fed415422b798551074a1a1772469a9606
+size 1064

run-5/checkpoint-1070/special_tokens_map.json

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

run-5/checkpoint-1070/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-5/checkpoint-1070/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.08036809130702588,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1070",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 1.418704867362976,
+      "learning_rate": 9.051429251998609e-07,
+      "loss": 0.6201,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5985676646232605,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7973,
+      "eval_samples_per_second": 1308.083,
+      "eval_steps_per_second": 82.774,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 4.440581798553467,
+      "learning_rate": 6.291847162974642e-07,
+      "loss": 0.5727,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5634607076644897,
+      "eval_matthews_correlation": 0.08036809130702588,
+      "eval_runtime": 0.8821,
+      "eval_samples_per_second": 1182.372,
+      "eval_steps_per_second": 74.819,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 85650780972012.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1811011341022575e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 22
+  }
+}

run-5/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d11ff39f07e33d5b6301458d31e37c56a9a2f71decad6414000b44e051ae7a4
+size 5176

run-5/checkpoint-1605/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-5/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157adb374d8772477bd235681f65537d5d7db99294adc0ee80c4b842d8a60ef5
+size 267832560

run-5/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb023ec4e7f9285b4f35510787ec42408a0a28223ccda2a19cb09b4524064282
+size 535727290

run-5/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f36b248d0a1373fe1d5ce2897793689764ac936c3c7e61022d97a767d838314
+size 14244

run-5/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550649ac49ccad1cd5489b6fe01b59422292e358afd3c5998f3b9c053e36f84a
+size 1064

run-5/checkpoint-1605/special_tokens_map.json

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

run-5/checkpoint-1605/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-5/checkpoint-1605/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.20740621404954238,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1605",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1605,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 1.418704867362976,
+      "learning_rate": 9.051429251998609e-07,
+      "loss": 0.6201,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5985676646232605,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7973,
+      "eval_samples_per_second": 1308.083,
+      "eval_steps_per_second": 82.774,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 4.440581798553467,
+      "learning_rate": 6.291847162974642e-07,
+      "loss": 0.5727,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5634607076644897,
+      "eval_matthews_correlation": 0.08036809130702588,
+      "eval_runtime": 0.8821,
+      "eval_samples_per_second": 1182.372,
+      "eval_steps_per_second": 74.819,
+      "step": 1070
+    },
+    {
+      "epoch": 2.803738317757009,
+      "grad_norm": 5.3037919998168945,
+      "learning_rate": 3.5322650739506763e-07,
+      "loss": 0.5395,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5501772165298462,
+      "eval_matthews_correlation": 0.20740621404954238,
+      "eval_runtime": 0.8916,
+      "eval_samples_per_second": 1169.764,
+      "eval_steps_per_second": 74.021,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 128305542064632.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1811011341022575e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 22
+  }
+}

run-5/checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d11ff39f07e33d5b6301458d31e37c56a9a2f71decad6414000b44e051ae7a4
+size 5176

run-5/checkpoint-2140/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-5/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31af0226b8031aeacee5d2e12897fc0347e10d3e4d6527ffd742dc1fa8541e28
+size 267832560

run-5/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168b08a6f528e1c5253ef9199f02d9223005d04352ee53bab2fae944d5752c16
+size 535727290

run-5/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6c2311613ba99327614dc4b2344db16aa2f641149cf5c979eec6a6828d86ac
+size 14244

run-5/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebac54f0aa27727c03184bfba6477b3c2ca6a05bd08fa525fdd52264d1b010b3
+size 1064

run-5/checkpoint-2140/special_tokens_map.json

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

run-5/checkpoint-2140/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-5/checkpoint-2140/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.272543584642415,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-2140",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 1.418704867362976,
+      "learning_rate": 9.051429251998609e-07,
+      "loss": 0.6201,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5985676646232605,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7973,
+      "eval_samples_per_second": 1308.083,
+      "eval_steps_per_second": 82.774,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 4.440581798553467,
+      "learning_rate": 6.291847162974642e-07,
+      "loss": 0.5727,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5634607076644897,
+      "eval_matthews_correlation": 0.08036809130702588,
+      "eval_runtime": 0.8821,
+      "eval_samples_per_second": 1182.372,
+      "eval_steps_per_second": 74.819,
+      "step": 1070
+    },
+    {
+      "epoch": 2.803738317757009,
+      "grad_norm": 5.3037919998168945,
+      "learning_rate": 3.5322650739506763e-07,
+      "loss": 0.5395,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5501772165298462,
+      "eval_matthews_correlation": 0.20740621404954238,
+      "eval_runtime": 0.8916,
+      "eval_samples_per_second": 1169.764,
+      "eval_steps_per_second": 74.021,
+      "step": 1605
+    },
+    {
+      "epoch": 3.7383177570093458,
+      "grad_norm": 7.205862045288086,
+      "learning_rate": 7.726829849267105e-08,
+      "loss": 0.5215,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5470464825630188,
+      "eval_matthews_correlation": 0.272543584642415,
+      "eval_runtime": 0.7782,
+      "eval_samples_per_second": 1340.19,
+      "eval_steps_per_second": 84.806,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "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": 171337783498344.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1811011341022575e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 22
+  }
+}

run-5/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d11ff39f07e33d5b6301458d31e37c56a9a2f71decad6414000b44e051ae7a4
+size 5176

runs/Jun05_17-06-49_52616c5e4acb/events.out.tfevents.1717608445.52616c5e4acb.227.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d69c9bae36865d5f9c36fd0f17aca85a6147b41bcfe3e6265cbc83228309c1a
-size 5881
+oid sha256:3a2049fa9cb2870884e53d4dd75b3d8232f181e430f3bd4289e95e78a262ca7b
+size 7327