Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:503898bb4f7bb12354efafb4d17d0b3a026feab26cf41e45595c46c050e0c6f7
+oid sha256:37bbe8d27f5d1f173234e5bd80404b9fe1a13f43af7d4b32966b99328c7963f4
 size 267838720

run-9816kcc3/checkpoint-1000/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

run-9816kcc3/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2913f25555ecf46c8691607cce6c0d26dc8cd255bc6ff29a7bccf76b03fc9063
+size 267838720

run-9816kcc3/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9a59fa6736b7e8f77d0b9098ccc78d350205d9068453979db2adcd4dc72754
+size 535741515

run-9816kcc3/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca80971fc3b053d99bcec33c7fa42f0c99f5be30e2055ed7f758b7cfe5cf96fe
+size 14645

run-9816kcc3/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f2334f50a87db5c2689868f8c2196ba38d7bb3402188b805def30f603c443e
+size 1465

run-9816kcc3/checkpoint-1000/special_tokens_map.json

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

run-9816kcc3/checkpoint-1000/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-9816kcc3/checkpoint-1000/trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_global_step": 250,
+  "best_metric": 0.3948093354701996,
+  "best_model_checkpoint": "topic_classifier_model/run-9816kcc3/checkpoint-250",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.3948093354701996,
+      "eval_runtime": 2.6827,
+      "eval_samples_per_second": 372.763,
+      "eval_steps_per_second": 23.484,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 39.29621887207031,
+      "learning_rate": 7.500895564789535e-06,
+      "loss": 0.5523,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.4520011842250824,
+      "eval_runtime": 2.7875,
+      "eval_samples_per_second": 358.749,
+      "eval_steps_per_second": 22.601,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.873,
+      "eval_loss": 0.5025014281272888,
+      "eval_runtime": 2.7727,
+      "eval_samples_per_second": 360.655,
+      "eval_steps_per_second": 22.721,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12481679767370224,
+      "learning_rate": 3.754194483476081e-06,
+      "loss": 0.2399,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.887,
+      "eval_loss": 0.5078921318054199,
+      "eval_runtime": 2.7405,
+      "eval_samples_per_second": 364.894,
+      "eval_steps_per_second": 22.988,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 73263293866560.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {
+      "cli_version": "0.21.3",
+      "m": [],
+      "python_version": "3.12.11",
+      "t": {
+        "1": [
+          1,
+          2,
+          3,
+          5,
+          11,
+          12,
+          41,
+          49,
+          51,
+          53,
+          71,
+          98,
+          100,
+          105
+        ],
+        "12": "0.21.3",
+        "13": "linux-x86_64",
+        "3": [
+          14
+        ],
+        "4": "3.12.11",
+        "5": "0.21.3",
+        "6": "4.56.1",
+        "8": [
+          1,
+          12
+        ]
+      }
+    },
+    "assignments": {},
+    "learning_rate": 1.1240103243940362e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 4,
+    "seed": 2
+  }
+}

run-9816kcc3/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348c9a7783dc1814fcc5d9bc464e430840421ea1ee3a083be1b16c81dc13b1c1
+size 5777

run-9816kcc3/checkpoint-1250/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

run-9816kcc3/checkpoint-1250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d3bff94003998d7374798a57ddb3d49130b04a0683f855bb6722d4b04dd76e
+size 267838720

run-9816kcc3/checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96c14de5aae88f2ed676434e1975b9ff97b054532cae731e2ad54ad38949b29
+size 535741515

run-9816kcc3/checkpoint-1250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ec2b43cd45f8cd74b6d7894d63f4be066f4900ac2a485e2b1b21e062df5bc0
+size 14645

run-9816kcc3/checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba24379c51f147cdc8fd7ab5fb809d725765b906c2f33ad7aae54aa94910c2e0
+size 1465

run-9816kcc3/checkpoint-1250/special_tokens_map.json

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

run-9816kcc3/checkpoint-1250/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-9816kcc3/checkpoint-1250/trainer_state.json

@@ -0,0 +1,135 @@
+{
+  "best_global_step": 250,
+  "best_metric": 0.3948093354701996,
+  "best_model_checkpoint": "topic_classifier_model/run-9816kcc3/checkpoint-250",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.3948093354701996,
+      "eval_runtime": 2.6827,
+      "eval_samples_per_second": 372.763,
+      "eval_steps_per_second": 23.484,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 39.29621887207031,
+      "learning_rate": 7.500895564789535e-06,
+      "loss": 0.5523,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.4520011842250824,
+      "eval_runtime": 2.7875,
+      "eval_samples_per_second": 358.749,
+      "eval_steps_per_second": 22.601,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.873,
+      "eval_loss": 0.5025014281272888,
+      "eval_runtime": 2.7727,
+      "eval_samples_per_second": 360.655,
+      "eval_steps_per_second": 22.721,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12481679767370224,
+      "learning_rate": 3.754194483476081e-06,
+      "loss": 0.2399,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.887,
+      "eval_loss": 0.5078921318054199,
+      "eval_runtime": 2.7405,
+      "eval_samples_per_second": 364.894,
+      "eval_steps_per_second": 22.988,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.539190411567688,
+      "eval_runtime": 2.8515,
+      "eval_samples_per_second": 350.696,
+      "eval_steps_per_second": 22.094,
+      "step": 1250
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 73263293866560.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {
+      "cli_version": "0.21.3",
+      "m": [],
+      "python_version": "3.12.11",
+      "t": {
+        "1": [
+          1,
+          2,
+          3,
+          5,
+          11,
+          12,
+          41,
+          49,
+          51,
+          53,
+          71,
+          98,
+          100,
+          105
+        ],
+        "12": "0.21.3",
+        "13": "linux-x86_64",
+        "3": [
+          14
+        ],
+        "4": "3.12.11",
+        "5": "0.21.3",
+        "6": "4.56.1",
+        "8": [
+          1,
+          12
+        ]
+      }
+    },
+    "assignments": {},
+    "learning_rate": 1.1240103243940362e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 4,
+    "seed": 2
+  }
+}

run-9816kcc3/checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348c9a7783dc1814fcc5d9bc464e430840421ea1ee3a083be1b16c81dc13b1c1
+size 5777

run-9816kcc3/checkpoint-1500/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

run-9816kcc3/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35e4f75b7f4973e0843f4b8ad39ac45b7b253168ca15f849246f3371f3adfe51
+size 267838720

run-9816kcc3/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559b55ee343d3e64e4994b69a57245d8f796e617f2975d579788a97aa8f1ae93
+size 535741515

run-9816kcc3/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6904daf183d86f1a2d0341299aca5533fc15d88947d780dcd4629030ebfdeec2
+size 14645

run-9816kcc3/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4412c97a2efb92f7c35a1d19d13d59fd14407f618193dbbfc0411ca867fb481b
+size 1465

run-9816kcc3/checkpoint-1500/special_tokens_map.json

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

run-9816kcc3/checkpoint-1500/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-9816kcc3/checkpoint-1500/trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_global_step": 250,
+  "best_metric": 0.3948093354701996,
+  "best_model_checkpoint": "topic_classifier_model/run-9816kcc3/checkpoint-250",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.3948093354701996,
+      "eval_runtime": 2.6827,
+      "eval_samples_per_second": 372.763,
+      "eval_steps_per_second": 23.484,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 39.29621887207031,
+      "learning_rate": 7.500895564789535e-06,
+      "loss": 0.5523,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.4520011842250824,
+      "eval_runtime": 2.7875,
+      "eval_samples_per_second": 358.749,
+      "eval_steps_per_second": 22.601,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.873,
+      "eval_loss": 0.5025014281272888,
+      "eval_runtime": 2.7727,
+      "eval_samples_per_second": 360.655,
+      "eval_steps_per_second": 22.721,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12481679767370224,
+      "learning_rate": 3.754194483476081e-06,
+      "loss": 0.2399,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.887,
+      "eval_loss": 0.5078921318054199,
+      "eval_runtime": 2.7405,
+      "eval_samples_per_second": 364.894,
+      "eval_steps_per_second": 22.988,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.539190411567688,
+      "eval_runtime": 2.8515,
+      "eval_samples_per_second": 350.696,
+      "eval_steps_per_second": 22.094,
+      "step": 1250
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.2626676559448242,
+      "learning_rate": 7.493402162626908e-09,
+      "loss": 0.1805,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.5392631888389587,
+      "eval_runtime": 2.8102,
+      "eval_samples_per_second": 355.846,
+      "eval_steps_per_second": 22.418,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 109874242030560.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {
+      "cli_version": "0.21.3",
+      "m": [],
+      "python_version": "3.12.11",
+      "t": {
+        "1": [
+          1,
+          2,
+          3,
+          5,
+          11,
+          12,
+          41,
+          49,
+          51,
+          53,
+          71,
+          98,
+          100,
+          105
+        ],
+        "12": "0.21.3",
+        "13": "linux-x86_64",
+        "3": [
+          14
+        ],
+        "4": "3.12.11",
+        "5": "0.21.3",
+        "6": "4.56.1",
+        "8": [
+          1,
+          12
+        ]
+      }
+    },
+    "assignments": {},
+    "learning_rate": 1.1240103243940362e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 4,
+    "seed": 2
+  }
+}

run-9816kcc3/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348c9a7783dc1814fcc5d9bc464e430840421ea1ee3a083be1b16c81dc13b1c1
+size 5777

run-9816kcc3/checkpoint-500/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

run-9816kcc3/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84c33c144c6ebe4768f97aef1591573589c962bcce75c3f5eaf62126a484dca
+size 267838720

run-9816kcc3/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa44efc38d6c5c5294c3989d6208cbde58d5472902f0e03154dc3f0a3f7e138
+size 535741515

run-9816kcc3/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0b4dd114649962be5e3678abb33e128d508fd58a82315079df265c646afebe
+size 14645

run-9816kcc3/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c31864ebaa0fa2e3f5e23f94f906026aea30ec13e42861332972aa51a084d24
+size 1465

run-9816kcc3/checkpoint-500/special_tokens_map.json

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

run-9816kcc3/checkpoint-500/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-9816kcc3/checkpoint-500/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_global_step": 250,
+  "best_metric": 0.3948093354701996,
+  "best_model_checkpoint": "topic_classifier_model/run-9816kcc3/checkpoint-250",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.3948093354701996,
+      "eval_runtime": 2.6827,
+      "eval_samples_per_second": 372.763,
+      "eval_steps_per_second": 23.484,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 39.29621887207031,
+      "learning_rate": 7.500895564789535e-06,
+      "loss": 0.5523,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.4520011842250824,
+      "eval_runtime": 2.7875,
+      "eval_samples_per_second": 358.749,
+      "eval_steps_per_second": 22.601,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 36735140779680.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {
+      "cli_version": "0.21.3",
+      "m": [],
+      "python_version": "3.12.11",
+      "t": {
+        "1": [
+          1,
+          2,
+          3,
+          5,
+          11,
+          12,
+          41,
+          49,
+          51,
+          53,
+          71,
+          98,
+          100,
+          105
+        ],
+        "12": "0.21.3",
+        "13": "linux-x86_64",
+        "3": [
+          14
+        ],
+        "4": "3.12.11",
+        "5": "0.21.3",
+        "6": "4.56.1",
+        "8": [
+          1,
+          12
+        ]
+      }
+    },
+    "assignments": {},
+    "learning_rate": 1.1240103243940362e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 4,
+    "seed": 2
+  }
+}

run-9816kcc3/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348c9a7783dc1814fcc5d9bc464e430840421ea1ee3a083be1b16c81dc13b1c1
+size 5777

run-9816kcc3/checkpoint-750/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

run-9816kcc3/checkpoint-750/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d437c422d6596d10d71ba60ef82d36fac049a57078fcc93a4897903f54241f86
+size 267838720

run-9816kcc3/checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ed36089c2fff91778dc02224d2c532d5163bc35f3cc01a1cdd5d1f981882a0
+size 535741515

run-9816kcc3/checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377128c33521065f236908b1d7f167ae8966d1cf5a6560bce745c0787c704ccb
+size 14645

run-9816kcc3/checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb7d862bdb2330909698cafcaabf5bb905849cb83c4d91c09e3a650a6c89c69
+size 1465