Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06a752745e3362eea4655f7c2008fdb7aa097039b823f70215a24702bb532e7
+oid sha256:ef0d6ddff4e2ee5ac7477ba4d65bd74537573a771cf4f7a0eda6c9fcaa9bedf2
 size 267832560

run-2/checkpoint-1340/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-2/checkpoint-1340/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a8ad2613c7609ae97b786f7cc6c518f1cba9f6eb91feed303476c02504ef7d
+size 267832560

run-2/checkpoint-1340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada8836f11e28c42c200a5d0f0b4642c6dbddbba10166a53e8c43972ce0bf4f9
+size 535727290

run-2/checkpoint-1340/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4588875a5fbed58e929a85f3d56b0d55e9bcd483ab055f6f849f6d129245a124
+size 14244

run-2/checkpoint-1340/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b6e92c49006b638e66a6003f39809c5b153d11e91b761c4cd7eb5c64dd090e
+size 1064

run-2/checkpoint-1340/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-1340/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-1340/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": 0.2615244673892003,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1340",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1340,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.602029025554657,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7285,
+      "eval_samples_per_second": 1431.715,
+      "eval_steps_per_second": 90.598,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 1.8423285484313965,
+      "learning_rate": 9.08259470497268e-07,
+      "loss": 0.605,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5747156739234924,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 0.8181,
+      "eval_samples_per_second": 1274.974,
+      "eval_steps_per_second": 80.679,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.557612419128418,
+      "eval_matthews_correlation": 0.1504867919191043,
+      "eval_runtime": 1.1383,
+      "eval_samples_per_second": 916.265,
+      "eval_steps_per_second": 57.98,
+      "step": 804
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 2.6135356426239014,
+      "learning_rate": 3.676288332965132e-07,
+      "loss": 0.5415,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5473177433013916,
+      "eval_matthews_correlation": 0.24305007868019401,
+      "eval_runtime": 0.7383,
+      "eval_samples_per_second": 1412.795,
+      "eval_steps_per_second": 89.4,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5427306890487671,
+      "eval_matthews_correlation": 0.2615244673892003,
+      "eval_runtime": 0.8749,
+      "eval_samples_per_second": 1192.069,
+      "eval_steps_per_second": 75.433,
+      "step": 1340
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "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": 191380204405152.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4488901076980227e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 3
+  }
+}

run-2/checkpoint-1340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af4e47fab4bdf5c020fd9bae4771a8cf62c8b1f615f2e7b84ba1d5d152fb998d
+size 5240

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": "4.44.0",
+  "vocab_size": 30522
+}

run-3/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533e43a32eabd3d31651bfb5320974d7358b68ad78e99131806707b12c45c36e
+size 267832560

run-3/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a9fb667d8781a7be51bee199ce4a929c03862ebfaf05a3ba293d9d940bcc98
+size 535727290

run-3/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c302216188c4bc94dd62a381cf63165141489162d815e75082aac4ec8f39e4
+size 14308

run-3/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da14496037ae59fcd17f35d7574c01a9a0c07246cc30cfe498fa1b2261d48cf9
+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": 0.4181278600904661,
+  "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": 9.916498184204102,
+      "learning_rate": 1.0352460846585169e-05,
+      "loss": 0.588,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 2.0442557334899902,
+      "learning_rate": 9.709610570468354e-06,
+      "loss": 0.5642,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 25.158737182617188,
+      "learning_rate": 9.066760294351542e-06,
+      "loss": 0.5358,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 21.2142276763916,
+      "learning_rate": 8.423910018234727e-06,
+      "loss": 0.5288,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6297594904899597,
+      "eval_matthews_correlation": 0.4181278600904661,
+      "eval_runtime": 0.8372,
+      "eval_samples_per_second": 1245.804,
+      "eval_steps_per_second": 78.833,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "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": 32523851074704.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0995311122701982e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 21
+  }
+}

run-3/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34730fac82fbb430a2d34761a01c6cb30b23aa40dc0ad7758d1ffd45727f8d7
+size 5240

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": "4.44.0",
+  "vocab_size": 30522
+}

run-3/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0d6ddff4e2ee5ac7477ba4d65bd74537573a771cf4f7a0eda6c9fcaa9bedf2
+size 267832560

run-3/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01901cd8b1ee576fe32dd356bf9cec5810df26963a6d69fafb727783351939a1
+size 535727290

run-3/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2012023543bf0763126d6321bf049c2b21c3bb0d40e6595859fd419050a1602a
+size 14308

run-3/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40025f5568fbc984b39d10b0700323e6137278e3592748229635bd25588578c3
+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": 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-4276/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": 0.4622674649892012,
+  "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": 9.916498184204102,
+      "learning_rate": 1.0352460846585169e-05,
+      "loss": 0.588,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 2.0442557334899902,
+      "learning_rate": 9.709610570468354e-06,
+      "loss": 0.5642,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 25.158737182617188,
+      "learning_rate": 9.066760294351542e-06,
+      "loss": 0.5358,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 21.2142276763916,
+      "learning_rate": 8.423910018234727e-06,
+      "loss": 0.5288,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6297594904899597,
+      "eval_matthews_correlation": 0.4181278600904661,
+      "eval_runtime": 0.8372,
+      "eval_samples_per_second": 1245.804,
+      "eval_steps_per_second": 78.833,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 40.90157699584961,
+      "learning_rate": 7.781059742117914e-06,
+      "loss": 0.4866,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 0.11679931730031967,
+      "learning_rate": 7.138209466001099e-06,
+      "loss": 0.4601,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 9.670472145080566,
+      "learning_rate": 6.495359189884285e-06,
+      "loss": 0.4758,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 1.609247088432312,
+      "learning_rate": 5.852508913767472e-06,
+      "loss": 0.4517,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9118176102638245,
+      "eval_matthews_correlation": 0.4622674649892012,
+      "eval_runtime": 0.7476,
+      "eval_samples_per_second": 1395.206,
+      "eval_steps_per_second": 88.287,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "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": 65141619465252.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0995311122701982e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 21
+  }
+}

run-3/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34730fac82fbb430a2d34761a01c6cb30b23aa40dc0ad7758d1ffd45727f8d7
+size 5240

runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723863304.b5f02c58e851.301.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e02871ac9219eb985dfd18672fd140fd45fb31e8195f98eb5bc8ec7a966e7a2
+size 7888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af4e47fab4bdf5c020fd9bae4771a8cf62c8b1f615f2e7b84ba1d5d152fb998d
+oid sha256:e34730fac82fbb430a2d34761a01c6cb30b23aa40dc0ad7758d1ffd45727f8d7
 size 5240