Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926f312e497a0b9044ae97fa511064de3c66f41222b3a7a4bcb1ee1010522694
+oid sha256:a156618563cb316c39ef398efced793ec174eef527371a729064472b9e5e4997
 size 267838720

run-8dyy5elb/checkpoint-48/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-48/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b46cd0af3e93cdf03cdbed5c13cb095936c5d12e5f46d6262a80ab4bbd28013
+size 267838720

run-8dyy5elb/checkpoint-48/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c663cd0d3c9304b741dfb63d44834189eb4d938f50626bfc60cd2a36833553
+size 535741515

run-8dyy5elb/checkpoint-48/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae73655089cef456d2d7dc7dd488a91e579d7fb5cfff5d099d9b254ec013d232
+size 14645

run-8dyy5elb/checkpoint-48/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e59034defe7e9f7405ab358b3b64174065fd110c81ef64b8e4848159c3cf79e
+size 1465

run-8dyy5elb/checkpoint-48/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-48/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-48/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_global_step": 48,
+  "best_metric": 0.38322019577026367,
+  "best_model_checkpoint": "topic_classifier_model/run-8dyy5elb/checkpoint-48",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 48,
+  "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
+    }
+  ],
+  "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-48/training_args.bin

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

run-8dyy5elb/checkpoint-64/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-64/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a156618563cb316c39ef398efced793ec174eef527371a729064472b9e5e4997
+size 267838720

run-8dyy5elb/checkpoint-64/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4fb22f844a5e5beca938ed280678e7ecd860ad1857dbea8a8a48b22e8844eaf
+size 535741515

run-8dyy5elb/checkpoint-64/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386521c3cf559cea69c21b83fd6b20df77cc87ac17da17b37f40ded7b42bb24b
+size 14645

run-8dyy5elb/checkpoint-64/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c44abf12b825eeedc2f01bd9049b34ae0073165c821bee30537b175959572917
+size 1465

run-8dyy5elb/checkpoint-64/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-64/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-64/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 64,
+  "best_metric": 0.382813036441803,
+  "best_model_checkpoint": "topic_classifier_model/run-8dyy5elb/checkpoint-64",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 64,
+  "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
+    }
+  ],
+  "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-64/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0fd4a9512c3725dfe78678d4384765a0d0b7c7838db07942eb9a55e7178223
+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:c0545f6147f600e140f8a073136c822b8c4c14ed9adf087c738ba693876bdc93
-size 6017
+oid sha256:52d6c63410a1d923328e4e53a33d59172d2bb787a78f2d1fac063338285554b2
+size 6968