Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db73e09af08a7ae2d1efb78eb8dacef819bdfa6537d0bb1a308cfa0c2386320f
+oid sha256:01e37ec40f27baf59831267cd31bca2337e778e9b1758b8f0f95468372c1c4e4
 size 267838720

run-m5alrfwj/checkpoint-250/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-m5alrfwj/checkpoint-250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e37ec40f27baf59831267cd31bca2337e778e9b1758b8f0f95468372c1c4e4
+size 267838720

run-m5alrfwj/checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea53c64515df4b7bcf319581f0c9fd0399ceeda84e1b96f9f5a64941f0057585
+size 535741515

run-m5alrfwj/checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ede38909b5cbc02b735e05d2f27cae806d7e77693ec983d1581ae79acb8dcb
+size 14645

run-m5alrfwj/checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15307c976c20361b2408ccc53060417ed2e8850e7e9ec381dd5eb6fe60ac2b0
+size 1465

run-m5alrfwj/checkpoint-250/special_tokens_map.json

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

run-m5alrfwj/checkpoint-250/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-m5alrfwj/checkpoint-250/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": 250,
+  "best_metric": 0.6556681394577026,
+  "best_model_checkpoint": "topic_classifier_model/run-m5alrfwj/checkpoint-250",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.852,
+      "eval_loss": 0.6556681394577026,
+      "eval_runtime": 3.5365,
+      "eval_samples_per_second": 282.762,
+      "eval_steps_per_second": 17.814,
+      "step": 250
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1250,
+  "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": {
+      "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": 6.130901902872614e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 40
+  }
+}

run-m5alrfwj/checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934cbbb308e8e2a43d3dfa9540bc12899ee79a766bc5434b122ad1473158b50e
+size 5777

runs/Sep19_08-00-22_8a8f19444048/events.out.tfevents.1758272386.8a8f19444048.1681.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2bc6d0227df216d0ced317678e4a0bd70ef7acd3ce3d52301c6cda911bd4c6d
+size 6779

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff15783133772fdd5c4dec70c61e1ea01a6ff2b24ee94ea5da01bf42fe053b3
+oid sha256:934cbbb308e8e2a43d3dfa9540bc12899ee79a766bc5434b122ad1473158b50e
 size 5777