Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2f397cde449289f623df6c32189ef1695b6ba88c960e9c07632397f03bcb22
+oid sha256:922d24292c562ab25a8c0903d3c345bb8d725760683d303c2c771aa167351edd
 size 267838720

run-atpnwu3p/checkpoint-22/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-atpnwu3p/checkpoint-22/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5625706fa28d976a8b4bc600b85d430f98788b59595785848965109bdb86b55
+size 267838720

run-atpnwu3p/checkpoint-22/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92dd532c3b17c76086b08333d9c7b6b4a983babacf0612749788327765e7a114
+size 535739578

run-atpnwu3p/checkpoint-22/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4c7f21aa61a5a5e6b31161ccad45bb5e5ccc033e12e6e0f804527d25855709
+size 14244

run-atpnwu3p/checkpoint-22/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbaeaecac5a134f9f53efff4f39fee6b8a0b1ab827f18d71c29ba509bcf6a17
+size 1064

run-atpnwu3p/checkpoint-22/special_tokens_map.json

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

run-atpnwu3p/checkpoint-22/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-atpnwu3p/checkpoint-22/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_global_step": 22,
+  "best_metric": 0.5066666666666667,
+  "best_model_checkpoint": "website_prediction_model/run-atpnwu3p/checkpoint-22",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 22,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3333333333333333,
+      "eval_loss": 1.375121831893921,
+      "eval_runtime": 0.7601,
+      "eval_samples_per_second": 98.671,
+      "eval_steps_per_second": 6.578,
+      "step": 11
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5066666666666667,
+      "eval_loss": 1.3217427730560303,
+      "eval_runtime": 0.8234,
+      "eval_samples_per_second": 91.086,
+      "eval_steps_per_second": 6.072,
+      "step": 22
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 33,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 2.5856990326733563e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 40
+  }
+}

run-atpnwu3p/checkpoint-22/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946a301dc931c2cf0e3318f9945b9434a774244244d3b0d6bb80c9c31d47b2f0
+size 5304

run-atpnwu3p/checkpoint-33/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-atpnwu3p/checkpoint-33/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194b18d17377dc69495b2b4be0d61512914fe144a931b535d1c423eb7b5e87e2
+size 267838720

run-atpnwu3p/checkpoint-33/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16c85505163f858f93ea801f6721ae79b2195cade112cd62b1d8145eceae69f
+size 535739578

run-atpnwu3p/checkpoint-33/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009c3876b49f23f3e67f14fe84acdf3bb8a880fbdd16ce92ffeb6418584e59f2
+size 14244

run-atpnwu3p/checkpoint-33/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97fc2cbede911c4b2dc27b17c02a5dcd767d70062e76c4cbe9d197d7a7d9f71f
+size 1064

run-atpnwu3p/checkpoint-33/special_tokens_map.json

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

run-atpnwu3p/checkpoint-33/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-atpnwu3p/checkpoint-33/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_global_step": 33,
+  "best_metric": 0.6933333333333334,
+  "best_model_checkpoint": "website_prediction_model/run-atpnwu3p/checkpoint-33",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 33,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3333333333333333,
+      "eval_loss": 1.375121831893921,
+      "eval_runtime": 0.7601,
+      "eval_samples_per_second": 98.671,
+      "eval_steps_per_second": 6.578,
+      "step": 11
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5066666666666667,
+      "eval_loss": 1.3217427730560303,
+      "eval_runtime": 0.8234,
+      "eval_samples_per_second": 91.086,
+      "eval_steps_per_second": 6.072,
+      "step": 22
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6933333333333334,
+      "eval_loss": 1.1559292078018188,
+      "eval_runtime": 0.7635,
+      "eval_samples_per_second": 98.234,
+      "eval_steps_per_second": 6.549,
+      "step": 33
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 33,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 2.5856990326733563e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 40
+  }
+}

run-atpnwu3p/checkpoint-33/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946a301dc931c2cf0e3318f9945b9434a774244244d3b0d6bb80c9c31d47b2f0
+size 5304

run-sgvshopq/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-sgvshopq/checkpoint-167/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922d24292c562ab25a8c0903d3c345bb8d725760683d303c2c771aa167351edd
+size 267838720

run-sgvshopq/checkpoint-167/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e56e5ab4926f697092cb14f20fea5f0c9950d39df8950a0f5751cfabfd9a6c
+size 535739578

run-sgvshopq/checkpoint-167/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ea3b62db2894925f8ecd36a22aa9b2c45fab2469b1d4acf15a23a42a977dab
+size 14244

run-sgvshopq/checkpoint-167/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0271318c43951553cd68ac131917f7c6389071f610618d4e3a8f3f48896f7639
+size 1064

run-sgvshopq/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-sgvshopq/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-sgvshopq/checkpoint-167/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_global_step": 167,
+  "best_metric": 0.9333333333333333,
+  "best_model_checkpoint": "website_prediction_model/run-sgvshopq/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": 0.9333333333333333,
+      "eval_loss": 0.3241618275642395,
+      "eval_runtime": 0.7614,
+      "eval_samples_per_second": 98.503,
+      "eval_steps_per_second": 6.567,
+      "step": 167
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 835,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 5.207464397831743e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 2
+  }
+}

run-sgvshopq/checkpoint-167/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7be1702138e1071acaefa1fe9267dc149c7295ba57326c5725d4b5bcc2e156f
+size 5304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946a301dc931c2cf0e3318f9945b9434a774244244d3b0d6bb80c9c31d47b2f0
+oid sha256:d7be1702138e1071acaefa1fe9267dc149c7295ba57326c5725d4b5bcc2e156f
 size 5304