Training in progress, epoch 1

config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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,
+  "transformers_version": "4.57.3",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03b5c6d31847af1f9d7fd8b6a39afd0113e67df984dd2ea4886154f079adfdb
+size 263144680

run-0/checkpoint-12/config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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,
+  "transformers_version": "4.57.3",
+  "vocab_size": 28996
+}

run-0/checkpoint-12/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0598948267d7547b8cb2b5fef141c2d82f81af79be7a67483bf0cee040f8d2f
+size 263144680

run-0/checkpoint-12/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25c883008ba9e4bf764c8d67d0ee78ea48b2c606d74abcd1b7b729a871ec374
+size 526353483

run-0/checkpoint-12/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7207873ee6dd8ff0a13b46212f10e8c9c543a5049317a36cc6488e6b76834f
+size 14645

run-0/checkpoint-12/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8c738d3d6ea8d083ca821272b8ca5f6ffe83110656cb74c25e38c4a83645da
+size 1465

run-0/checkpoint-12/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-12/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "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-12/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.658226728439331,
+  "best_model_checkpoint": "distilbert-base-cased-finetuned-acuteCinderellaAphasiaDetection/run-0/checkpoint-3",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.658226728439331,
+      "eval_runtime": 0.0604,
+      "eval_samples_per_second": 182.021,
+      "eval_steps_per_second": 99.284,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6670505404472351,
+      "eval_runtime": 0.0588,
+      "eval_samples_per_second": 186.99,
+      "eval_steps_per_second": 101.995,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6761133074760437,
+      "eval_runtime": 0.0598,
+      "eval_samples_per_second": 184.003,
+      "eval_steps_per_second": 100.365,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6825154423713684,
+      "eval_runtime": 0.0575,
+      "eval_samples_per_second": 191.438,
+      "eval_steps_per_second": 104.421,
+      "step": 12
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15,
+  "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": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.778085328486241e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 15
+  }
+}

run-0/checkpoint-12/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6812e5cab0904abb152713c66b19c036e1303e3b63f3a466131f48a7f1a74b3
+size 5969

run-0/checkpoint-15/config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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,
+  "transformers_version": "4.57.3",
+  "vocab_size": 28996
+}

run-0/checkpoint-15/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e2c55d5ef0210ddc7a4f2fb07a0e43b8341524a7747e9bcceb413f38bba55e
+size 263144680

run-0/checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5905fa17030fa43f9c5771efd0ffbee09890483e076787ff5e0b50d5a862ad19
+size 526353483

run-0/checkpoint-15/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90df7c3332beb2734982b184278255f7bf3eea6cdb2adadb60b26698fbde7f2b
+size 14645

run-0/checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7270a564e7f80ec0ce5aa2b3ca473aeded7bd9f1469f79db62414537086f250
+size 1465

run-0/checkpoint-15/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-15/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "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-15/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.658226728439331,
+  "best_model_checkpoint": "distilbert-base-cased-finetuned-acuteCinderellaAphasiaDetection/run-0/checkpoint-3",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.658226728439331,
+      "eval_runtime": 0.0604,
+      "eval_samples_per_second": 182.021,
+      "eval_steps_per_second": 99.284,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6670505404472351,
+      "eval_runtime": 0.0588,
+      "eval_samples_per_second": 186.99,
+      "eval_steps_per_second": 101.995,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6761133074760437,
+      "eval_runtime": 0.0598,
+      "eval_samples_per_second": 184.003,
+      "eval_steps_per_second": 100.365,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6825154423713684,
+      "eval_runtime": 0.0575,
+      "eval_samples_per_second": 191.438,
+      "eval_steps_per_second": 104.421,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6883839964866638,
+      "eval_runtime": 0.069,
+      "eval_samples_per_second": 159.373,
+      "eval_steps_per_second": 86.931,
+      "step": 15
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15,
+  "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": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.778085328486241e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 15
+  }
+}

run-0/checkpoint-15/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6812e5cab0904abb152713c66b19c036e1303e3b63f3a466131f48a7f1a74b3
+size 5969

run-0/checkpoint-3/config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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,
+  "transformers_version": "4.57.3",
+  "vocab_size": 28996
+}

run-0/checkpoint-3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d320a14dead414ef9b81822b0581b8449ab8ad388529cceb42743f574c4ff3f4
+size 263144680

run-0/checkpoint-3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d01fbb3391126c24499985aa457285ed464d39d99cb855f920fcb7a4d342ac
+size 526353483

run-0/checkpoint-3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4aec02da1f8f604702b6bf8f472d7421add7e5b3b31b98b3480d51ac580e75
+size 14645

run-0/checkpoint-3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a91dfbff9548a7c627a30b04848ba031626b2bb6caf957b400be68c6b29b71d
+size 1465

run-0/checkpoint-3/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-3/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "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-3/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.658226728439331,
+  "best_model_checkpoint": "distilbert-base-cased-finetuned-acuteCinderellaAphasiaDetection/run-0/checkpoint-3",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.658226728439331,
+      "eval_runtime": 0.0604,
+      "eval_samples_per_second": 182.021,
+      "eval_steps_per_second": 99.284,
+      "step": 3
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15,
+  "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": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.778085328486241e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 15
+  }
+}

run-0/checkpoint-3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6812e5cab0904abb152713c66b19c036e1303e3b63f3a466131f48a7f1a74b3
+size 5969

run-0/checkpoint-6/config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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,
+  "transformers_version": "4.57.3",
+  "vocab_size": 28996
+}

run-0/checkpoint-6/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4f4ca1c2822b851fd1e513901349c7c251c88b38bd406d9ccd1552fa15adf1
+size 263144680

run-0/checkpoint-6/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33abb8cdb246e5e2e8cc23846e1112bf49864fb4a8e1ebec882f55d7e2b497a
+size 526353483

run-0/checkpoint-6/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e50a8fcb223a8a4eaf2a9edf85b9c594bbe4af888e339f46b55a730a78091e
+size 14645

run-0/checkpoint-6/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ce3c5cdd4050e619f7a535070f2ac3e293e839589a378c98fa375e6a0ab9d44
+size 1465

run-0/checkpoint-6/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-6/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "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-6/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.658226728439331,
+  "best_model_checkpoint": "distilbert-base-cased-finetuned-acuteCinderellaAphasiaDetection/run-0/checkpoint-3",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.658226728439331,
+      "eval_runtime": 0.0604,
+      "eval_samples_per_second": 182.021,
+      "eval_steps_per_second": 99.284,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6670505404472351,
+      "eval_runtime": 0.0588,
+      "eval_samples_per_second": 186.99,
+      "eval_steps_per_second": 101.995,
+      "step": 6
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15,
+  "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": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.778085328486241e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 15
+  }
+}

run-0/checkpoint-6/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6812e5cab0904abb152713c66b19c036e1303e3b63f3a466131f48a7f1a74b3
+size 5969

run-0/checkpoint-9/config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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,
+  "transformers_version": "4.57.3",
+  "vocab_size": 28996
+}

run-0/checkpoint-9/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089ce606bc8c7a09ccb035f3e710bf00a657f4bc6b631beea2970907f80b150b
+size 263144680

run-0/checkpoint-9/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0450a33ae810e6bde18e8752d40343de04dd4ed5c3bf119f0248cb26f13010
+size 526353483

run-0/checkpoint-9/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480e34b36c51c917eeb3164cf8e9283661bdf9114e3d0ea947f9108a9667605c
+size 14645