Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06bdda8a0812ab342f9708cb66dc2f30eff252432291dcb0dbecdbb37acf6bf7
+oid sha256:8015a5b0b59e6d48c0885bba8a647fd2a66786c3787f3ffa18068d637c362dd1
 size 267832560

run-6/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": "4.35.2",
+  "vocab_size": 30522
+}

run-6/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb5bdb2c6e083f79af3aeda72f1c0d5222d89d7a72793f56a86bbf9a66bcb47
+size 267832560

run-6/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000a2ece2051ad9ca1bc1d837b356f467d3ba70678e993179cf180635cfd410f
+size 535727290

run-6/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb778fffeb1278f440ebc7400eb643617db07320baad8cd830e10ed5373b7ab7
+size 14244

run-6/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1cda6d795e70b0ceb608dfee1c6d17cd0783d67682aea7c55cfc3ac6ef7b5b
+size 1064

run-6/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-6/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-6/checkpoint-2138/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.3853198145814999,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/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": 0.23,
+      "learning_rate": 3.3885155454850214e-06,
+      "loss": 0.6304,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.2222488356967473e-06,
+      "loss": 0.5538,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.0559821259084737e-06,
+      "loss": 0.5115,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8897154161201995e-06,
+      "loss": 0.5259,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5689446926116943,
+      "eval_matthews_correlation": 0.3853198145814999,
+      "eval_runtime": 0.6776,
+      "eval_samples_per_second": 1539.305,
+      "eval_steps_per_second": 97.406,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 32740145499072.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.554782255273295e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 38
+  }
+}

run-6/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6342a7c997a6c93f51f97f51c3102162aa9080f52fd78ae3d35b10dc7a1b7a
+size 4664

run-6/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": "4.35.2",
+  "vocab_size": 30522
+}

run-6/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e08813fb7baf2dbac3777adaf80aef28d0c19aeacd476077d784930d95404a6
+size 267832560

run-6/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4859d5e9eadf47540f839edfdc8f6e7fcd2e1fc020350ea0dbfc3586393affaf
+size 535727290

run-6/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ae3ec550278c676b15f4cf5c41ef0ce68008f6b85ae00cca23d58c2cacac89
+size 14244

run-6/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63dfa494e40c2d95098dcf91749008f4ef5be5fe3c1cb2ccbc7cc4c733efe7e
+size 1064

run-6/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-6/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-6/checkpoint-4276/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.4384136507504086,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/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": 0.23,
+      "learning_rate": 3.3885155454850214e-06,
+      "loss": 0.6304,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.2222488356967473e-06,
+      "loss": 0.5538,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.0559821259084737e-06,
+      "loss": 0.5115,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8897154161201995e-06,
+      "loss": 0.5259,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5689446926116943,
+      "eval_matthews_correlation": 0.3853198145814999,
+      "eval_runtime": 0.6776,
+      "eval_samples_per_second": 1539.305,
+      "eval_steps_per_second": 97.406,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.723448706331926e-06,
+      "loss": 0.4906,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.5571819965436518e-06,
+      "loss": 0.4698,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.390915286755378e-06,
+      "loss": 0.5102,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.224648576967104e-06,
+      "loss": 0.5109,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6553956866264343,
+      "eval_matthews_correlation": 0.4384136507504086,
+      "eval_runtime": 0.7058,
+      "eval_samples_per_second": 1477.67,
+      "eval_steps_per_second": 93.506,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 65144982895296.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.554782255273295e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 38
+  }
+}

run-6/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6342a7c997a6c93f51f97f51c3102162aa9080f52fd78ae3d35b10dc7a1b7a
+size 4664

run-7/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": "4.35.2",
+  "vocab_size": 30522
+}

run-7/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8015a5b0b59e6d48c0885bba8a647fd2a66786c3787f3ffa18068d637c362dd1
+size 267832560

run-7/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f5e2bf3b462edc2311b6b49f24796d0be142a342c35679550a5c83db20f4be
+size 535727290

run-7/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51effa2d3a6ace934fb656524b2608b2a15b842a50342237d1442cb181fdb0b0
+size 14308

run-7/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f116728839bdc58c6c18e9dc3f251f46953b31d599bf3a4e689beb9053b2b4
+size 1064

run-7/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-7/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-7/checkpoint-2138/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.41811934780166404,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 0.23,
+      "learning_rate": 2.7071875903581973e-06,
+      "loss": 0.5979,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.5390810584184183e-06,
+      "loss": 0.57,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.3709745264786396e-06,
+      "loss": 0.5455,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.202867994538861e-06,
+      "loss": 0.5236,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5138241648674011,
+      "eval_matthews_correlation": 0.41811934780166404,
+      "eval_runtime": 0.5106,
+      "eval_samples_per_second": 2042.773,
+      "eval_steps_per_second": 129.265,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 39258731649732.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.875294122297976e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 8
+  }
+}

run-7/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f94afec3137acb97928db163d93043fac47e11daafef46a80ab44daa849b5b3
+size 4664

runs/Jan08_03-19-08_fe6f5592002e/events.out.tfevents.1704685956.fe6f5592002e.4919.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901e4decf4867a195dd73f4d8bb0f667c610dd95980eebe41b68cf2e4e03ed05
+size 7078

runs/Jan08_03-19-08_fe6f5592002e/events.out.tfevents.1704686179.fe6f5592002e.4919.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75350f0b0da6676404647b1830ef3a1fde9eae7eced954c79dfe54b7da21907
+size 6114

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e9f8ddd121ee145851cc2a247c980484855726d6ec121946fc43c7f3d39b8ac
+oid sha256:1f94afec3137acb97928db163d93043fac47e11daafef46a80ab44daa849b5b3
 size 4664