Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae7365b4441db001b03894e59cf649e018406508851e0aadce19c02ec65de1a
+oid sha256:8e047e40e4d52567caf922d0d8f136b6c059ca4d2254a3dc5d2e2e8922c98219
 size 267838720

run-046iv1ov/checkpoint-126/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Business",
+    "1": "Personal",
+    "2": "Government",
+    "3": "Others"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Business": 0,
+    "Government": 2,
+    "Others": 3,
+    "Personal": 1
+  },
+  "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": "4.51.3",
+  "vocab_size": 30522
+}

run-046iv1ov/checkpoint-126/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70aa19e309ac7c08abd170e07abc9de1dd90799c9a169eb12ddbfaaaea6d00f9
+size 267838720

run-046iv1ov/checkpoint-126/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7745bd1c75afee26bc90118cd0ad72bf0c5e28d4ebae0dc2361e783653d993e
+size 535739578

run-046iv1ov/checkpoint-126/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0b189d6d9463dbad3c125fe5f2cea53c68e26f097367595277084295c7b914
+size 14308

run-046iv1ov/checkpoint-126/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e306f5de10abbcbff5d0784b18df3082b01fef4f6bbec9935680de8a481c6f7
+size 1064

run-046iv1ov/checkpoint-126/special_tokens_map.json

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

run-046iv1ov/checkpoint-126/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": true,
+  "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-046iv1ov/checkpoint-126/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_global_step": 126,
+  "best_metric": 0.9333333333333333,
+  "best_model_checkpoint": "website_prediction_model/run-046iv1ov/checkpoint-126",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 126,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.76,
+      "eval_loss": 0.8799358010292053,
+      "eval_runtime": 0.7525,
+      "eval_samples_per_second": 99.671,
+      "eval_steps_per_second": 6.645,
+      "step": 42
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.92,
+      "eval_loss": 0.2813997268676758,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 99.678,
+      "eval_steps_per_second": 6.645,
+      "step": 84
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9333333333333333,
+      "eval_loss": 0.23722220957279205,
+      "eval_runtime": 0.7746,
+      "eval_samples_per_second": 96.828,
+      "eval_steps_per_second": 6.455,
+      "step": 126
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 210,
+  "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": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 4.0484005469889746e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 32
+  }
+}

run-046iv1ov/checkpoint-126/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e971b4bdc92741dd99c588836c3a276605ecc9ec801502c48b485aa8aacba576
+size 5304

run-046iv1ov/checkpoint-168/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Business",
+    "1": "Personal",
+    "2": "Government",
+    "3": "Others"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Business": 0,
+    "Government": 2,
+    "Others": 3,
+    "Personal": 1
+  },
+  "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": "4.51.3",
+  "vocab_size": 30522
+}

run-046iv1ov/checkpoint-168/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49be4c14965e34ed51b85a34b845c67a9dace3aad8f59bbea31c0407e56ddcf2
+size 267838720

run-046iv1ov/checkpoint-168/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67a24b0466b58a68e12ddc81ed27da1556e883a6cbf21d9fb1b6ffad56276fc
+size 535739578

run-046iv1ov/checkpoint-168/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a56da527ae07b7ec0feebf92ba7aaccc43848b978eedbd3ebc260008562274
+size 14308

run-046iv1ov/checkpoint-168/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cb903d352b3d5386a3271e63b737b5dfd0df0e9af33bfae1fb575aa4f4abbd
+size 1064

run-046iv1ov/checkpoint-168/special_tokens_map.json

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

run-046iv1ov/checkpoint-168/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": true,
+  "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-046iv1ov/checkpoint-168/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_global_step": 168,
+  "best_metric": 0.9466666666666667,
+  "best_model_checkpoint": "website_prediction_model/run-046iv1ov/checkpoint-168",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 168,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.76,
+      "eval_loss": 0.8799358010292053,
+      "eval_runtime": 0.7525,
+      "eval_samples_per_second": 99.671,
+      "eval_steps_per_second": 6.645,
+      "step": 42
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.92,
+      "eval_loss": 0.2813997268676758,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 99.678,
+      "eval_steps_per_second": 6.645,
+      "step": 84
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9333333333333333,
+      "eval_loss": 0.23722220957279205,
+      "eval_runtime": 0.7746,
+      "eval_samples_per_second": 96.828,
+      "eval_steps_per_second": 6.455,
+      "step": 126
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9466666666666667,
+      "eval_loss": 0.21807293593883514,
+      "eval_runtime": 0.7739,
+      "eval_samples_per_second": 96.913,
+      "eval_steps_per_second": 6.461,
+      "step": 168
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 210,
+  "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": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 4.0484005469889746e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 32
+  }
+}

run-046iv1ov/checkpoint-168/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e971b4bdc92741dd99c588836c3a276605ecc9ec801502c48b485aa8aacba576
+size 5304

run-046iv1ov/checkpoint-210/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Business",
+    "1": "Personal",
+    "2": "Government",
+    "3": "Others"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Business": 0,
+    "Government": 2,
+    "Others": 3,
+    "Personal": 1
+  },
+  "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": "4.51.3",
+  "vocab_size": 30522
+}

run-046iv1ov/checkpoint-210/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f17d4e5c079f48d0b84d5f453070a6c5c6f974d740b01bce477aa199e9aa887
+size 267838720

run-046iv1ov/checkpoint-210/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9d9bb6006f212ae4411b578db68c33f7aab7d0a30f3f53ff23113eb53928f2
+size 535739578

run-046iv1ov/checkpoint-210/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c56fff8732038f3728082bb733763c22f286192363a444b4eadbac70fb4d61d
+size 14308

run-046iv1ov/checkpoint-210/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1dbbd41e13e48c65896627fc87b484d5bf7bd9d80a475455a68a619d44a308
+size 1064

run-046iv1ov/checkpoint-210/special_tokens_map.json

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

run-046iv1ov/checkpoint-210/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": true,
+  "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-046iv1ov/checkpoint-210/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_global_step": 168,
+  "best_metric": 0.9466666666666667,
+  "best_model_checkpoint": "website_prediction_model/run-046iv1ov/checkpoint-168",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 210,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.76,
+      "eval_loss": 0.8799358010292053,
+      "eval_runtime": 0.7525,
+      "eval_samples_per_second": 99.671,
+      "eval_steps_per_second": 6.645,
+      "step": 42
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.92,
+      "eval_loss": 0.2813997268676758,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 99.678,
+      "eval_steps_per_second": 6.645,
+      "step": 84
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9333333333333333,
+      "eval_loss": 0.23722220957279205,
+      "eval_runtime": 0.7746,
+      "eval_samples_per_second": 96.828,
+      "eval_steps_per_second": 6.455,
+      "step": 126
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9466666666666667,
+      "eval_loss": 0.21807293593883514,
+      "eval_runtime": 0.7739,
+      "eval_samples_per_second": 96.913,
+      "eval_steps_per_second": 6.461,
+      "step": 168
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9466666666666667,
+      "eval_loss": 0.22355476021766663,
+      "eval_runtime": 0.7684,
+      "eval_samples_per_second": 97.604,
+      "eval_steps_per_second": 6.507,
+      "step": 210
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 210,
+  "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": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 4.0484005469889746e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 32
+  }
+}

run-046iv1ov/checkpoint-210/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e971b4bdc92741dd99c588836c3a276605ecc9ec801502c48b485aa8aacba576
+size 5304

run-046iv1ov/checkpoint-84/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Business",
+    "1": "Personal",
+    "2": "Government",
+    "3": "Others"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Business": 0,
+    "Government": 2,
+    "Others": 3,
+    "Personal": 1
+  },
+  "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": "4.51.3",
+  "vocab_size": 30522
+}

run-046iv1ov/checkpoint-84/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92510e4ce41f58345f267387b3300aab4297624a55962cdd82bb2b6fedf2508
+size 267838720

run-046iv1ov/checkpoint-84/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548ada2309dc777f4852301eaf737b4e9dd97fe284c472c8d1d19e28c6a35734
+size 535739578

run-046iv1ov/checkpoint-84/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96eb9ee881d40512a9a361cd73ac6c46287a74ba752bc34e7029c9bc12a5955d
+size 14308

run-046iv1ov/checkpoint-84/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2dcba7df484d1717c1fff36e86b4cf736195a504a7182a9f5a7cc0668b74443
+size 1064

run-046iv1ov/checkpoint-84/special_tokens_map.json

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

run-046iv1ov/checkpoint-84/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": true,
+  "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-046iv1ov/checkpoint-84/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_global_step": 84,
+  "best_metric": 0.92,
+  "best_model_checkpoint": "website_prediction_model/run-046iv1ov/checkpoint-84",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 84,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.76,
+      "eval_loss": 0.8799358010292053,
+      "eval_runtime": 0.7525,
+      "eval_samples_per_second": 99.671,
+      "eval_steps_per_second": 6.645,
+      "step": 42
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.92,
+      "eval_loss": 0.2813997268676758,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 99.678,
+      "eval_steps_per_second": 6.645,
+      "step": 84
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 210,
+  "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": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 4.0484005469889746e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 32
+  }
+}

run-046iv1ov/checkpoint-84/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e971b4bdc92741dd99c588836c3a276605ecc9ec801502c48b485aa8aacba576
+size 5304

run-awg0cb8s/checkpoint-21/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Business",
+    "1": "Personal",
+    "2": "Government",
+    "3": "Others"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Business": 0,
+    "Government": 2,
+    "Others": 3,
+    "Personal": 1
+  },
+  "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": "4.51.3",
+  "vocab_size": 30522
+}

run-awg0cb8s/checkpoint-21/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e047e40e4d52567caf922d0d8f136b6c059ca4d2254a3dc5d2e2e8922c98219
+size 267838720

run-awg0cb8s/checkpoint-21/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bc239c1de0f38c867274c40d824361c4bcc41ea6f9cce2086f1591510aba5c
+size 535739578

run-awg0cb8s/checkpoint-21/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086f24bbabcf1d018a1f3ab8b665ee6cc85cbc21e88d464e70de24dd311c1f44
+size 14308

run-awg0cb8s/checkpoint-21/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510518d5ee13cca66381596af2c4ae1dddf22f8a24efcc914e38d2672a007f62
+size 1064