Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f8bfe5bcf362861fb56c7bb964c016e49919e22fd066bb44a1cc8eba8abe99
+oid sha256:06c43e1215f73fc568c514acceabd2a44f14d7a9c925ccf50e2729458b993e75
 size 267832560

run-6/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-6/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3725e5b02608dc5530f85f3d8de9648f0322bc73be9aabbc14aa13e5de2d36a
+size 267832560

run-6/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4b6aa1d2f97da431f87095da5bb03b490888449af70e3d53c29e2cc2a3c45c
+size 535727290

run-6/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c91714c6b2f0f09885139e31866886a2f77c59c074835c8cbc6409ac6c8a5ac
+size 14244

run-6/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24aa567e76f80e8af52de559a916d2fe815c7c6e5eb5bafb9dbeaa3250bd70a
+size 1064

run-6/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-6/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-6/checkpoint-1070/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.4637527852072172,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/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": 5.238464832305908,
+      "learning_rate": 3.402333319834233e-05,
+      "loss": 0.5511,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.49575698375701904,
+      "eval_matthews_correlation": 0.39308651644145964,
+      "eval_runtime": 0.7715,
+      "eval_samples_per_second": 1351.958,
+      "eval_steps_per_second": 85.551,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 2.997009515762329,
+      "learning_rate": 4.178304076989409e-06,
+      "loss": 0.3322,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5316250920295715,
+      "eval_matthews_correlation": 0.4637527852072172,
+      "eval_runtime": 0.8931,
+      "eval_samples_per_second": 1167.804,
+      "eval_steps_per_second": 73.897,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 85503307500852.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.386836231969526e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 36
+  }
+}

run-6/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251611c4bfb6b20f8af90da9319a02e669878d68a9a3f9531f54a41f4e7e6a09
+size 5176

run-7/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-7/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41e2e4bd60847bf9b9006f6c345dcab2d2b3785657717a61ae8a1bcd0bdad1b
+size 267832560

run-7/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791a807b6c39cf75b38c75893a6f2364208800a973278829c193eac2461133c4
+size 535727290

run-7/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a469ef23f380f6f6e5e8b45ad8cd59ac4c05b1dfa32ea32f62d1f50c455270
+size 14244

run-7/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901af64e161e9abaccdffb563e304a1ddf41c99ef0a043b282b2593ef15a3974
+size 1064

run-7/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-7/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-7/checkpoint-1070/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.4994543232175365,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 7.454558372497559,
+      "learning_rate": 4.179162949014749e-05,
+      "loss": 0.5295,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4814288020133972,
+      "eval_matthews_correlation": 0.4180033304707719,
+      "eval_runtime": 0.7741,
+      "eval_samples_per_second": 1347.455,
+      "eval_steps_per_second": 85.266,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 5.427362442016602,
+      "learning_rate": 3.218435834298715e-05,
+      "loss": 0.3193,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5887653827667236,
+      "eval_matthews_correlation": 0.4994543232175365,
+      "eval_runtime": 0.8397,
+      "eval_samples_per_second": 1242.051,
+      "eval_steps_per_second": 78.596,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 85847929717668.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.1398900637307834e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 2
+  }
+}

run-7/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9c11c5c4c8fd505118306685caa5ac2c15c0e0e7eba1c3401d416b60ed5b92
+size 5176

run-7/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-7/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323aeabbd2a109a32adf0c1bc97292baffb475bd2c1d384b5548984b1496135d
+size 267832560

run-7/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da83b94354743e2e9ec7c7a3a2473a43013c75df78b8e7d4da0c72f14ceb3bf9
+size 535727290

run-7/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683361f3d50302cd9f205ea62dde6f48e8d09e4abc6c35277c9c279dba7becd9
+size 14244

run-7/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c32f1f5acbf3868981e1087d29227aff84ecad1fbdb0988423d4ca1db457718
+size 1064

run-7/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-7/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-7/checkpoint-1605/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.5168734231170928,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 7.454558372497559,
+      "learning_rate": 4.179162949014749e-05,
+      "loss": 0.5295,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4814288020133972,
+      "eval_matthews_correlation": 0.4180033304707719,
+      "eval_runtime": 0.7741,
+      "eval_samples_per_second": 1347.455,
+      "eval_steps_per_second": 85.266,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 5.427362442016602,
+      "learning_rate": 3.218435834298715e-05,
+      "loss": 0.3193,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5887653827667236,
+      "eval_matthews_correlation": 0.4994543232175365,
+      "eval_runtime": 0.8397,
+      "eval_samples_per_second": 1242.051,
+      "eval_steps_per_second": 78.596,
+      "step": 1070
+    },
+    {
+      "epoch": 2.803738317757009,
+      "grad_norm": 15.598775863647461,
+      "learning_rate": 2.2577087195826806e-05,
+      "loss": 0.2049,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6870770454406738,
+      "eval_matthews_correlation": 0.5168734231170928,
+      "eval_runtime": 0.8182,
+      "eval_samples_per_second": 1274.691,
+      "eval_steps_per_second": 80.661,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 128329086074940.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.1398900637307834e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 2
+  }
+}

run-7/checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9c11c5c4c8fd505118306685caa5ac2c15c0e0e7eba1c3401d416b60ed5b92
+size 5176

run-7/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-7/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afeb34689fd0c2147c3cb6788ad5c94e79c02ce231bda8a5ca562ff0765dbe5
+size 267832560

run-7/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02652c727536486beab3ffdf5c60392e045086f9a1e4a0e5bbb3cb3d44356207
+size 535727290

run-7/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9841d77a931e8a16f89bbb51637dfb9e99e88554821ef0287ef2761b110a11
+size 14244

run-7/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c312d60b1f607f14da8deb1ca92af077e440f11561468451d7ce5a5483c06913
+size 1064

run-7/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-7/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-7/checkpoint-2140/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.532072854687201,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 7.454558372497559,
+      "learning_rate": 4.179162949014749e-05,
+      "loss": 0.5295,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4814288020133972,
+      "eval_matthews_correlation": 0.4180033304707719,
+      "eval_runtime": 0.7741,
+      "eval_samples_per_second": 1347.455,
+      "eval_steps_per_second": 85.266,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 5.427362442016602,
+      "learning_rate": 3.218435834298715e-05,
+      "loss": 0.3193,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5887653827667236,
+      "eval_matthews_correlation": 0.4994543232175365,
+      "eval_runtime": 0.8397,
+      "eval_samples_per_second": 1242.051,
+      "eval_steps_per_second": 78.596,
+      "step": 1070
+    },
+    {
+      "epoch": 2.803738317757009,
+      "grad_norm": 15.598775863647461,
+      "learning_rate": 2.2577087195826806e-05,
+      "loss": 0.2049,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6870770454406738,
+      "eval_matthews_correlation": 0.5168734231170928,
+      "eval_runtime": 0.8182,
+      "eval_samples_per_second": 1274.691,
+      "eval_steps_per_second": 80.661,
+      "step": 1605
+    },
+    {
+      "epoch": 3.7383177570093458,
+      "grad_norm": 24.2171630859375,
+      "learning_rate": 1.296981604866646e-05,
+      "loss": 0.1294,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8434147238731384,
+      "eval_matthews_correlation": 0.532072854687201,
+      "eval_runtime": 1.2184,
+      "eval_samples_per_second": 856.074,
+      "eval_steps_per_second": 54.172,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 170953317571776.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.1398900637307834e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 2
+  }
+}

run-7/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9c11c5c4c8fd505118306685caa5ac2c15c0e0e7eba1c3401d416b60ed5b92
+size 5176

run-7/checkpoint-2675/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-7/checkpoint-2675/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c43e1215f73fc568c514acceabd2a44f14d7a9c925ccf50e2729458b993e75
+size 267832560

run-7/checkpoint-2675/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b731bfa6a968a710526d36464b9db3d5ad5b60d0fef3828c4a0b7bad3279e8ce
+size 535727290

run-7/checkpoint-2675/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcae3bc46d8594ee396c93fdc6d61c811fab3fcd2a22a3d71fcbae972ff78ed
+size 14244

run-7/checkpoint-2675/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b01824afcc6c50627193c16a4307056b8948a9330fad410baadc48baec2d213
+size 1064