Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e047e40e4d52567caf922d0d8f136b6c059ca4d2254a3dc5d2e2e8922c98219
+oid sha256:34a1039fae28e14d42335d5babe6173c6eea5e9e678e138367230091e9ed0d02
 size 267838720

run-awg0cb8s/checkpoint-105/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-105/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d851b3bc0a3d569d60613b1fdf7fb58403edf75b236fe9507757fa8fcd596eb2
+size 267838720

run-awg0cb8s/checkpoint-105/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a48533dc3190f4c4871201ced2e9a4088f4e2a6a659a39c375adf638574353
+size 535739578

run-awg0cb8s/checkpoint-105/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db0ea37604b56de9f3251b62faff9fb0b1a670c1669d23323abbf775bdbe665
+size 14308

run-awg0cb8s/checkpoint-105/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d24f59599d66afd2ea4f1c3cd38166d4b1c52cd3274fa47c61889f0e2aafed
+size 1064

run-awg0cb8s/checkpoint-105/special_tokens_map.json

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

run-awg0cb8s/checkpoint-105/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-awg0cb8s/checkpoint-105/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_global_step": 84,
+  "best_metric": 0.6266666666666667,
+  "best_model_checkpoint": "website_prediction_model/run-awg0cb8s/checkpoint-84",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.16,
+      "eval_loss": 1.4040924310684204,
+      "eval_runtime": 0.7569,
+      "eval_samples_per_second": 99.09,
+      "eval_steps_per_second": 6.606,
+      "step": 21
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3466666666666667,
+      "eval_loss": 1.3794679641723633,
+      "eval_runtime": 0.8305,
+      "eval_samples_per_second": 90.312,
+      "eval_steps_per_second": 6.021,
+      "step": 42
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5733333333333334,
+      "eval_loss": 1.3347134590148926,
+      "eval_runtime": 0.7913,
+      "eval_samples_per_second": 94.782,
+      "eval_steps_per_second": 6.319,
+      "step": 63
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6266666666666667,
+      "eval_loss": 1.2955228090286255,
+      "eval_runtime": 0.768,
+      "eval_samples_per_second": 97.656,
+      "eval_steps_per_second": 6.51,
+      "step": 84
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6133333333333333,
+      "eval_loss": 1.2866833209991455,
+      "eval_runtime": 0.7614,
+      "eval_samples_per_second": 98.498,
+      "eval_steps_per_second": 6.567,
+      "step": 105
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 105,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 3.359133095753484e-06,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 31
+  }
+}

run-awg0cb8s/checkpoint-105/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3415fd6a97c7531df70729b90c88efee28cae66f8b27cb03a7aedd137f28be6a
+size 5304

run-awg0cb8s/checkpoint-42/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-42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb8f6cdf5e25748a1045c3d445fc3aa48c813f46377d3f74d2ce15a5b719f29
+size 267838720

run-awg0cb8s/checkpoint-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b50bc5c6bc7cf1ff1f45e3361dea3ea31b4035efe0764c6a3774448a916631ad
+size 535739578

run-awg0cb8s/checkpoint-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9243e1be13e73eb21494103651e6a05e3e289f91606f6ea0ea24cbf6ed54a03
+size 14308

run-awg0cb8s/checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08d6f103c777a3bd1b90f0ead622fead4cf7b8ff58b0cc22167948d83e0c6ef
+size 1064

run-awg0cb8s/checkpoint-42/special_tokens_map.json

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

run-awg0cb8s/checkpoint-42/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-awg0cb8s/checkpoint-42/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_global_step": 42,
+  "best_metric": 0.3466666666666667,
+  "best_model_checkpoint": "website_prediction_model/run-awg0cb8s/checkpoint-42",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.16,
+      "eval_loss": 1.4040924310684204,
+      "eval_runtime": 0.7569,
+      "eval_samples_per_second": 99.09,
+      "eval_steps_per_second": 6.606,
+      "step": 21
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3466666666666667,
+      "eval_loss": 1.3794679641723633,
+      "eval_runtime": 0.8305,
+      "eval_samples_per_second": 90.312,
+      "eval_steps_per_second": 6.021,
+      "step": 42
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 105,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 3.359133095753484e-06,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 31
+  }
+}

run-awg0cb8s/checkpoint-42/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3415fd6a97c7531df70729b90c88efee28cae66f8b27cb03a7aedd137f28be6a
+size 5304

run-awg0cb8s/checkpoint-63/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-63/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59cc65ffbfc987b2bc65865e2c1d9502d67fe6881901be6a12ccfbff7c7ed4f
+size 267838720

run-awg0cb8s/checkpoint-63/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0661f2396645b3c295d55f5def551c154a897bc24a4b2b884ec87e28b2c4ab76
+size 535739578

run-awg0cb8s/checkpoint-63/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a1abef3d0504995e03710560c4ec2705928a91f703d8b3a82c9eba18df1574
+size 14308

run-awg0cb8s/checkpoint-63/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53fc8b27cdc056f2439304f83dcdc633581f95541cc169552b0b8b0d543c1d0f
+size 1064

run-awg0cb8s/checkpoint-63/special_tokens_map.json

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

run-awg0cb8s/checkpoint-63/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-awg0cb8s/checkpoint-63/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_global_step": 63,
+  "best_metric": 0.5733333333333334,
+  "best_model_checkpoint": "website_prediction_model/run-awg0cb8s/checkpoint-63",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.16,
+      "eval_loss": 1.4040924310684204,
+      "eval_runtime": 0.7569,
+      "eval_samples_per_second": 99.09,
+      "eval_steps_per_second": 6.606,
+      "step": 21
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3466666666666667,
+      "eval_loss": 1.3794679641723633,
+      "eval_runtime": 0.8305,
+      "eval_samples_per_second": 90.312,
+      "eval_steps_per_second": 6.021,
+      "step": 42
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5733333333333334,
+      "eval_loss": 1.3347134590148926,
+      "eval_runtime": 0.7913,
+      "eval_samples_per_second": 94.782,
+      "eval_steps_per_second": 6.319,
+      "step": 63
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 105,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 3.359133095753484e-06,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 31
+  }
+}

run-awg0cb8s/checkpoint-63/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3415fd6a97c7531df70729b90c88efee28cae66f8b27cb03a7aedd137f28be6a
+size 5304

run-awg0cb8s/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-awg0cb8s/checkpoint-84/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca996a4559e2439c0a13b5d03f567a1d2d77f00c5acf0276c10cec22ffe7ff9
+size 267838720

run-awg0cb8s/checkpoint-84/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cafd6c177a35df8b75f996f05a9dd11c62a23f3155065bb76a585aaf7318890f
+size 535739578

run-awg0cb8s/checkpoint-84/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ef1c320c6a72fc4a7e4ce47ab07c8ead78221670659a15d0fb338a0b7403a05
+size 14308

run-awg0cb8s/checkpoint-84/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68cec1021445246508d03dd16375477c3e1e7c1105190d18bc7349f16372c5a5
+size 1064

run-awg0cb8s/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-awg0cb8s/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-awg0cb8s/checkpoint-84/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_global_step": 84,
+  "best_metric": 0.6266666666666667,
+  "best_model_checkpoint": "website_prediction_model/run-awg0cb8s/checkpoint-84",
+  "epoch": 4.0,
+  "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": 0.16,
+      "eval_loss": 1.4040924310684204,
+      "eval_runtime": 0.7569,
+      "eval_samples_per_second": 99.09,
+      "eval_steps_per_second": 6.606,
+      "step": 21
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3466666666666667,
+      "eval_loss": 1.3794679641723633,
+      "eval_runtime": 0.8305,
+      "eval_samples_per_second": 90.312,
+      "eval_steps_per_second": 6.021,
+      "step": 42
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5733333333333334,
+      "eval_loss": 1.3347134590148926,
+      "eval_runtime": 0.7913,
+      "eval_samples_per_second": 94.782,
+      "eval_steps_per_second": 6.319,
+      "step": 63
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6266666666666667,
+      "eval_loss": 1.2955228090286255,
+      "eval_runtime": 0.768,
+      "eval_samples_per_second": 97.656,
+      "eval_steps_per_second": 6.51,
+      "step": 84
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 105,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 3.359133095753484e-06,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 31
+  }
+}

run-awg0cb8s/checkpoint-84/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3415fd6a97c7531df70729b90c88efee28cae66f8b27cb03a7aedd137f28be6a
+size 5304

run-pp3enhq8/checkpoint-11/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-pp3enhq8/checkpoint-11/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a1039fae28e14d42335d5babe6173c6eea5e9e678e138367230091e9ed0d02
+size 267838720

run-pp3enhq8/checkpoint-11/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052f52cdf13da198de7ac21e9206079e685d5dc863fe5a1b1616801b33252c60
+size 535739578

run-pp3enhq8/checkpoint-11/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf303f7772d5efe65359bfe8d5d0931737f1732b7553d55e6b2efba08796f1c
+size 14244

run-pp3enhq8/checkpoint-11/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70b75a19a095f81747985a3bf6624b9d5d834f845a2d17b931b69d2ba24ab84
+size 1064