Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a156618563cb316c39ef398efced793ec174eef527371a729064472b9e5e4997
+oid sha256:518df0167f5e52a689a5383e0e6d3e753204b7d0eeef00e6369e0d5b8ec371b0
 size 267838720

run-8dyy5elb/checkpoint-80/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-8dyy5elb/checkpoint-80/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c14cfb45af8029334695b37739c39c7bb42332af7b1c774b329e3df2d47a683
+size 267838720

run-8dyy5elb/checkpoint-80/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51b46b4b757e42729a88fa87a48e06373d0e9bcf61ca1e7084f00df22d1ac25
+size 535741515

run-8dyy5elb/checkpoint-80/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9def46a21f17b56fd58164cc604e2dfeb4f2f530e068545484b23866758d346e
+size 14645

run-8dyy5elb/checkpoint-80/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2213c8b2f7f7f5f402deb856c5331ce64040cc001b89d6f08608cc4ffe3637
+size 1465

run-8dyy5elb/checkpoint-80/special_tokens_map.json

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

run-8dyy5elb/checkpoint-80/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-8dyy5elb/checkpoint-80/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_global_step": 64,
+  "best_metric": 0.382813036441803,
+  "best_model_checkpoint": "topic_classifier_model/run-8dyy5elb/checkpoint-64",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.873,
+      "eval_loss": 0.48823022842407227,
+      "eval_runtime": 2.7343,
+      "eval_samples_per_second": 365.722,
+      "eval_steps_per_second": 23.041,
+      "step": 16
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.871,
+      "eval_loss": 0.4071064293384552,
+      "eval_runtime": 4.9987,
+      "eval_samples_per_second": 200.05,
+      "eval_steps_per_second": 12.603,
+      "step": 32
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.888,
+      "eval_loss": 0.38322019577026367,
+      "eval_runtime": 2.7954,
+      "eval_samples_per_second": 357.728,
+      "eval_steps_per_second": 22.537,
+      "step": 48
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.881,
+      "eval_loss": 0.382813036441803,
+      "eval_runtime": 2.9386,
+      "eval_samples_per_second": 340.296,
+      "eval_steps_per_second": 21.439,
+      "step": 64
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.883,
+      "eval_loss": 0.3931596577167511,
+      "eval_runtime": 2.8959,
+      "eval_samples_per_second": 345.32,
+      "eval_steps_per_second": 21.755,
+      "step": 80
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 96,
+  "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": 0,
+  "train_batch_size": 64,
+  "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": 7.283547429832169e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 64,
+    "seed": 36
+  }
+}

run-8dyy5elb/checkpoint-80/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0fd4a9512c3725dfe78678d4384765a0d0b7c7838db07942eb9a55e7178223
+size 5777

run-8dyy5elb/checkpoint-96/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-8dyy5elb/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b816bc448948b9297c61f7710f4b39f687d6258f7a1b44fc66f412c2bec8196c
+size 267838720

run-8dyy5elb/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c098ecbb21889d7d4c04db8021aa153ab8e8042ae8a2a004b8ced271397f4d
+size 535741515

run-8dyy5elb/checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afbe8c91b12dce511de6cae9f1e3a087cacdb2f76e6183755b5aa2ce975ee8f
+size 14645

run-8dyy5elb/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5914df06271c3c4591027dfb62f64ec0021be238f87e4c7afed71b69547aef18
+size 1465

run-8dyy5elb/checkpoint-96/special_tokens_map.json

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

run-8dyy5elb/checkpoint-96/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-8dyy5elb/checkpoint-96/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_global_step": 64,
+  "best_metric": 0.382813036441803,
+  "best_model_checkpoint": "topic_classifier_model/run-8dyy5elb/checkpoint-64",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.873,
+      "eval_loss": 0.48823022842407227,
+      "eval_runtime": 2.7343,
+      "eval_samples_per_second": 365.722,
+      "eval_steps_per_second": 23.041,
+      "step": 16
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.871,
+      "eval_loss": 0.4071064293384552,
+      "eval_runtime": 4.9987,
+      "eval_samples_per_second": 200.05,
+      "eval_steps_per_second": 12.603,
+      "step": 32
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.888,
+      "eval_loss": 0.38322019577026367,
+      "eval_runtime": 2.7954,
+      "eval_samples_per_second": 357.728,
+      "eval_steps_per_second": 22.537,
+      "step": 48
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.881,
+      "eval_loss": 0.382813036441803,
+      "eval_runtime": 2.9386,
+      "eval_samples_per_second": 340.296,
+      "eval_steps_per_second": 21.439,
+      "step": 64
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.883,
+      "eval_loss": 0.3931596577167511,
+      "eval_runtime": 2.8959,
+      "eval_samples_per_second": 345.32,
+      "eval_steps_per_second": 21.755,
+      "step": 80
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.878,
+      "eval_loss": 0.4034556746482849,
+      "eval_runtime": 2.7956,
+      "eval_samples_per_second": 357.7,
+      "eval_steps_per_second": 22.535,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 96,
+  "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": 0,
+  "train_batch_size": 64,
+  "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": 7.283547429832169e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 64,
+    "seed": 36
+  }
+}

run-8dyy5elb/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0fd4a9512c3725dfe78678d4384765a0d0b7c7838db07942eb9a55e7178223
+size 5777

run-zeh4dysu/checkpoint-32/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-zeh4dysu/checkpoint-32/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518df0167f5e52a689a5383e0e6d3e753204b7d0eeef00e6369e0d5b8ec371b0
+size 267838720

run-zeh4dysu/checkpoint-32/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081c9658725d33ee4357ef32651cefde7cc3fa5477e13096884522ad600490df
+size 535741515

run-zeh4dysu/checkpoint-32/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac85510012105b589aa1e6621caecac7d36b20ef405a7c8e4f79a86bb83a7ca2
+size 14645

run-zeh4dysu/checkpoint-32/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b723c2142e1908b051223d68f971b223879a19ed37aca40d24c8dffa1231a454
+size 1465

run-zeh4dysu/checkpoint-32/special_tokens_map.json

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

run-zeh4dysu/checkpoint-32/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-zeh4dysu/checkpoint-32/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": 32,
+  "best_metric": 0.8360655307769775,
+  "best_model_checkpoint": "topic_classifier_model/run-zeh4dysu/checkpoint-32",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 32,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.857,
+      "eval_loss": 0.8360655307769775,
+      "eval_runtime": 2.7448,
+      "eval_samples_per_second": 364.332,
+      "eval_steps_per_second": 22.953,
+      "step": 32
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 64,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": {
+      "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": 1.8536225665241115e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 39
+  }
+}

run-zeh4dysu/checkpoint-32/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10845e9713fabf872b25ddb9ed63eafca4fa9a7091856ece546c057e4bdac1dd
+size 5777

runs/Sep19_08-00-22_8a8f19444048/events.out.tfevents.1758271905.8a8f19444048.1681.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d6c63410a1d923328e4e53a33d59172d2bb787a78f2d1fac063338285554b2
-size 6968
+oid sha256:531c7990f4651f709387c3e68e0865a0ec446852086f7da144732decdcc6e5b5
+size 7316

runs/Sep19_08-00-22_8a8f19444048/events.out.tfevents.1758272115.8a8f19444048.1681.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2352e8842f7a4a4c6c93ba4a0ad59ebb2e9b3326f4283b3b278e184a6214edb0
+size 6049

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0fd4a9512c3725dfe78678d4384765a0d0b7c7838db07942eb9a55e7178223
+oid sha256:10845e9713fabf872b25ddb9ed63eafca4fa9a7091856ece546c057e4bdac1dd
 size 5777