Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b763b43dc1370e99bcfd95e6f354357e734d71dfa4fa3913bd21719771f6a972
+oid sha256:b94f85ced3957a12bbca9a61ecb642a1a7d42f952309a2f0324b6f60b57969fc
 size 267832560

run-0/checkpoint-10690/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": "4.37.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-10690/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94f85ced3957a12bbca9a61ecb642a1a7d42f952309a2f0324b6f60b57969fc
+size 267832560

run-0/checkpoint-10690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e6307eb69e573c672e70c7ba9e70302d348ff2345ac6f85fb5b415240eeeeb
+size 535727290

run-0/checkpoint-10690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70f8578161ccf0ad0d4df95fea3ddf41384ae8e794c3a2e3f68def93772e68b
+size 14244

run-0/checkpoint-10690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bd730e0e12dcbbc418fbba733b84807ce28e1d38d597931d673e12bd17dcce
+size 1064

run-0/checkpoint-10690/special_tokens_map.json

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

run-0/checkpoint-10690/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-0/checkpoint-10690/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": 0.4314499357014579,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-10690",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 10690,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.5357779776941374e-06,
+      "loss": 0.6168,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4604208639701856e-06,
+      "loss": 0.5776,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.3850637502462338e-06,
+      "loss": 0.5746,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.309706636522282e-06,
+      "loss": 0.5548,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5712242126464844,
+      "eval_matthews_correlation": 0.22434212315736826,
+      "eval_runtime": 0.7031,
+      "eval_samples_per_second": 1483.418,
+      "eval_steps_per_second": 93.869,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2343495227983303e-06,
+      "loss": 0.5154,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1589924090743783e-06,
+      "loss": 0.518,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.0836352953504268e-06,
+      "loss": 0.4936,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0082781816264748e-06,
+      "loss": 0.4994,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5665906071662903,
+      "eval_matthews_correlation": 0.42102695353783776,
+      "eval_runtime": 0.7159,
+      "eval_samples_per_second": 1456.818,
+      "eval_steps_per_second": 92.186,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.329210679025231e-07,
+      "loss": 0.4959,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.575639541785712e-07,
+      "loss": 0.4483,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.822068404546196e-07,
+      "loss": 0.5068,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.068497267306677e-07,
+      "loss": 0.4997,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6059040427207947,
+      "eval_matthews_correlation": 0.4234652946715911,
+      "eval_runtime": 0.7145,
+      "eval_samples_per_second": 1459.68,
+      "eval_steps_per_second": 92.367,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 6.314926130067159e-07,
+      "loss": 0.4698,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 5.561354992827641e-07,
+      "loss": 0.457,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 4.807783855588124e-07,
+      "loss": 0.4799,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 4.0542127183486065e-07,
+      "loss": 0.4688,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 3.3006415811090883e-07,
+      "loss": 0.5131,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6582726240158081,
+      "eval_matthews_correlation": 0.4226368648932913,
+      "eval_runtime": 0.7099,
+      "eval_samples_per_second": 1469.123,
+      "eval_steps_per_second": 92.965,
+      "step": 8552
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 2.54707044386957e-07,
+      "loss": 0.4485,
+      "step": 9000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 1.7934993066300523e-07,
+      "loss": 0.4795,
+      "step": 9500
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 1.0399281693905347e-07,
+      "loss": 0.448,
+      "step": 10000
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 2.8635703215101675e-08,
+      "loss": 0.4804,
+      "step": 10500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6815661787986755,
+      "eval_matthews_correlation": 0.4314499357014579,
+      "eval_runtime": 0.7141,
+      "eval_samples_per_second": 1460.611,
+      "eval_steps_per_second": 92.426,
+      "step": 10690
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 171209973156672.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6111350914180892e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 27
+  }
+}

run-0/checkpoint-10690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97d1b8c846d9a42c4764f2bf68882f0deb7e36410c0809079ec73f45091bff7
+size 4792

run-0/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": "4.37.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0b71f649ea3446956627147e7913ec833950ca1c267e50a8bf0a07111d9728
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f916614b8a526389aaae9dca50db2e77f389f027f38b9379d18505fbca3db0
+size 535727290

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e40a4bd1aa6152f9574d0bf801e5f1e948456d3231238492190cbdbdf60436
+size 14244

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568fe4a63e22c6cd3e67816b33bb12de21e7f6d335180942bffa199ac505062a
+size 1064

run-0/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-0/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-0/checkpoint-2138/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.22434212315736826,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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": 1.5357779776941374e-06,
+      "loss": 0.6168,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4604208639701856e-06,
+      "loss": 0.5776,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.3850637502462338e-06,
+      "loss": 0.5746,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.309706636522282e-06,
+      "loss": 0.5548,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5712242126464844,
+      "eval_matthews_correlation": 0.22434212315736826,
+      "eval_runtime": 0.7031,
+      "eval_samples_per_second": 1483.418,
+      "eval_steps_per_second": 93.869,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 32601468691104.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6111350914180892e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 27
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97d1b8c846d9a42c4764f2bf68882f0deb7e36410c0809079ec73f45091bff7
+size 4792

run-0/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": "4.37.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd9b16326fbd5c8566bf5b201dcb6fc6391a56f775f13b6415adff9428e884d
+size 267832560

run-0/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ee2127c216550ec7a16efcc64d0b2324499853bf2481138fbb9ccfef893e16
+size 535727290

run-0/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94bd0730cc567edcdb97fad871e4e15c3c463c901e6b2ff765f2c739787c5fb0
+size 14244

run-0/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a7afaaf76b855e4e808b66fc61d934c0ca1f892f3e7c32b6f30607187b97c1
+size 1064

run-0/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-0/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-0/checkpoint-4276/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 0.42102695353783776,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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": 1.5357779776941374e-06,
+      "loss": 0.6168,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4604208639701856e-06,
+      "loss": 0.5776,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.3850637502462338e-06,
+      "loss": 0.5746,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.309706636522282e-06,
+      "loss": 0.5548,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5712242126464844,
+      "eval_matthews_correlation": 0.22434212315736826,
+      "eval_runtime": 0.7031,
+      "eval_samples_per_second": 1483.418,
+      "eval_steps_per_second": 93.869,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2343495227983303e-06,
+      "loss": 0.5154,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1589924090743783e-06,
+      "loss": 0.518,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.0836352953504268e-06,
+      "loss": 0.4936,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0082781816264748e-06,
+      "loss": 0.4994,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5665906071662903,
+      "eval_matthews_correlation": 0.42102695353783776,
+      "eval_runtime": 0.7159,
+      "eval_samples_per_second": 1456.818,
+      "eval_steps_per_second": 92.186,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 65067882729672.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6111350914180892e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 27
+  }
+}

run-0/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97d1b8c846d9a42c4764f2bf68882f0deb7e36410c0809079ec73f45091bff7
+size 4792

run-0/checkpoint-6414/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": "4.37.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9befe47666d020cfea4ac6e9b8752bf39c0ae3f9cd22e208e9fee9f606368c8
+size 267832560

run-0/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13b136966cb5588d72c21f53ac0a90b2cee39b51cab2e44a44257abf6c3384a
+size 535727290

run-0/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0fe39efe0732b21814a2d84f2cf96fe255d92c9630171ce4c0f6d827a76523
+size 14244

run-0/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e67154423975eae6924c0e45d2f2e650616c2206c477dc3dd3dd0d594899ed
+size 1064

run-0/checkpoint-6414/special_tokens_map.json

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

run-0/checkpoint-6414/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-0/checkpoint-6414/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.4234652946715911,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-6414",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.5357779776941374e-06,
+      "loss": 0.6168,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4604208639701856e-06,
+      "loss": 0.5776,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.3850637502462338e-06,
+      "loss": 0.5746,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.309706636522282e-06,
+      "loss": 0.5548,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5712242126464844,
+      "eval_matthews_correlation": 0.22434212315736826,
+      "eval_runtime": 0.7031,
+      "eval_samples_per_second": 1483.418,
+      "eval_steps_per_second": 93.869,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2343495227983303e-06,
+      "loss": 0.5154,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1589924090743783e-06,
+      "loss": 0.518,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.0836352953504268e-06,
+      "loss": 0.4936,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0082781816264748e-06,
+      "loss": 0.4994,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5665906071662903,
+      "eval_matthews_correlation": 0.42102695353783776,
+      "eval_runtime": 0.7159,
+      "eval_samples_per_second": 1456.818,
+      "eval_steps_per_second": 92.186,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.329210679025231e-07,
+      "loss": 0.4959,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.575639541785712e-07,
+      "loss": 0.4483,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.822068404546196e-07,
+      "loss": 0.5068,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.068497267306677e-07,
+      "loss": 0.4997,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6059040427207947,
+      "eval_matthews_correlation": 0.4234652946715911,
+      "eval_runtime": 0.7145,
+      "eval_samples_per_second": 1459.68,
+      "eval_steps_per_second": 92.367,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 97756024425756.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6111350914180892e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 27
+  }
+}

run-0/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97d1b8c846d9a42c4764f2bf68882f0deb7e36410c0809079ec73f45091bff7
+size 4792

run-0/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": "4.37.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7444890e13ea2874aa4bb0ffac9325f8059ce2cd69abbd22d15a5ebf7184c62a
+size 267832560

run-0/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c4944a2a16867c4466ac528ddf88586b59cbc4ed4b9ce19130c39e7bd902ca
+size 535727290

run-0/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70ddfcdee251a5db17de5c89d7b5561113c773212a7568874bd3490caf88cfc
+size 14244

run-0/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954eb72abf8565d9ced640d104375744330c306e41f055e81ead8b7ee56cd24c
+size 1064