Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab58c41b87b85bf8af758ed2ef1dcac1793a59dbc2546e9c0cabbc4895f6a750
+oid sha256:a86fbbecb882b5952331b4110aad93078e87336e0a9a1900929fc354d175bcd3
 size 267838720

run-8kti2kck/checkpoint-167/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-8kti2kck/checkpoint-167/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86fbbecb882b5952331b4110aad93078e87336e0a9a1900929fc354d175bcd3
+size 267838720

run-8kti2kck/checkpoint-167/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2d367a8f4955d0340f8d0b4e91ce7c1b5be7d59e004a14e4c7ab2fb5cfe2e7
+size 535739578

run-8kti2kck/checkpoint-167/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4d5da38f306a4e89a125a5bb5929e8edd5b93a7514f1d7d14b0bd93cb137da
+size 14244

run-8kti2kck/checkpoint-167/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b56e0e3dfd00cd3d70db77074773e0192647c9e3754fd09dc9a9440a534172
+size 1064

run-8kti2kck/checkpoint-167/special_tokens_map.json

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

run-8kti2kck/checkpoint-167/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-8kti2kck/checkpoint-167/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_global_step": 167,
+  "best_metric": 0.84,
+  "best_model_checkpoint": "website_prediction_model/run-8kti2kck/checkpoint-167",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 167,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.84,
+      "eval_loss": 0.5624379515647888,
+      "eval_runtime": 0.7709,
+      "eval_samples_per_second": 97.287,
+      "eval_steps_per_second": 6.486,
+      "step": 167
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 167,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 1.733645257753866e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 34
+  }
+}

run-8kti2kck/checkpoint-167/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6738af2613bb341fd7b491ad146bdcab9effecae27529029990e7db38db2884
+size 5304

run-or32shh7/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-or32shh7/checkpoint-126/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aac64edfeb3cd9e712efce299b25749aeadcdcaf06358038f6f6cdad551f9ac
+size 267838720

run-or32shh7/checkpoint-126/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b667117afdb55b1a3be130762c4f2ead483f11f3e1c184bc1e8931253a5e4671
+size 535739578

run-or32shh7/checkpoint-126/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c3ffef780c9bf889627a3ae03bb3942d4a436c53120cba8333790ecda965e70
+size 14244

run-or32shh7/checkpoint-126/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002d9f0b0aa2ec46a1fc8a8bae8909ebf6be9f8e738354f685c3679463f48c6f
+size 1064

run-or32shh7/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-or32shh7/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-or32shh7/checkpoint-126/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_global_step": 126,
+  "best_metric": 0.6266666666666667,
+  "best_model_checkpoint": "website_prediction_model/run-or32shh7/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": 0.22666666666666666,
+      "eval_loss": 1.3785871267318726,
+      "eval_runtime": 0.7713,
+      "eval_samples_per_second": 97.232,
+      "eval_steps_per_second": 6.482,
+      "step": 42
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4666666666666667,
+      "eval_loss": 1.3057670593261719,
+      "eval_runtime": 0.7732,
+      "eval_samples_per_second": 97.002,
+      "eval_steps_per_second": 6.467,
+      "step": 84
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6266666666666667,
+      "eval_loss": 1.2779515981674194,
+      "eval_runtime": 0.7807,
+      "eval_samples_per_second": 96.072,
+      "eval_steps_per_second": 6.405,
+      "step": 126
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 126,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 3.587550251628584e-06,
+    "metric": "eval/loss",
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 7
+  }
+}

run-or32shh7/checkpoint-126/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886a4d2b0b87834afe0b6aa3b13af6fc8f104e77bac2d15a21daa7042988e85e
+size 5304

run-or32shh7/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-or32shh7/checkpoint-84/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda11eabb180117d9f46f6f921cf004877dbfe595932ba5e21a55b4464c613aa
+size 267838720

run-or32shh7/checkpoint-84/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc8c67a4ee975bc95b7b33397b4e87fa06bd3c28557b29b2618d67c9361b18a
+size 535739578

run-or32shh7/checkpoint-84/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84991375a254a8f29cc61ebcdf71dca782e02e582aee7f97071f8da6618d9b3
+size 14244

run-or32shh7/checkpoint-84/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6b8ffb6c9efd134a22ec82291aa5b73ccb3905af69dc37efff5e1fec063f81
+size 1064

run-or32shh7/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-or32shh7/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-or32shh7/checkpoint-84/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_global_step": 84,
+  "best_metric": 0.4666666666666667,
+  "best_model_checkpoint": "website_prediction_model/run-or32shh7/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": 0.22666666666666666,
+      "eval_loss": 1.3785871267318726,
+      "eval_runtime": 0.7713,
+      "eval_samples_per_second": 97.232,
+      "eval_steps_per_second": 6.482,
+      "step": 42
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4666666666666667,
+      "eval_loss": 1.3057670593261719,
+      "eval_runtime": 0.7732,
+      "eval_samples_per_second": 97.002,
+      "eval_steps_per_second": 6.467,
+      "step": 84
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 126,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 3.587550251628584e-06,
+    "metric": "eval/loss",
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 7
+  }
+}

run-or32shh7/checkpoint-84/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886a4d2b0b87834afe0b6aa3b13af6fc8f104e77bac2d15a21daa7042988e85e
+size 5304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:886a4d2b0b87834afe0b6aa3b13af6fc8f104e77bac2d15a21daa7042988e85e
+oid sha256:e6738af2613bb341fd7b491ad146bdcab9effecae27529029990e7db38db2884
 size 5304