Upload folder using huggingface_hub

__init__.py

@@ -0,0 +1 @@
+from .modeling_custom import CustomDistilBertClassifier

config.json

@@ -1,37 +1,37 @@
-{
-  "_name_or_path": "../distilbert-prompt-classifier/checkpoint-24",
-  "activation": "gelu",
-  "architectures": [
-    "FineTunedDistilBertWithStringLabels"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "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,
-  "torch_dtype": "float32",
-  "transformers_version": "4.48.1",
-  "vocab_size": 30522
-}
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "CustomDistilBertClassifier"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "vocab_size": 30522
+}

modeling_custom.py

@@ -0,0 +1,21 @@
+import torch
+from transformers import DistilBertForSequenceClassification
+
+label_dict = {0: "Clarification", 1: "Factual", 2: "Operational", 3: "Summarization"}
+
+
+class CustomDistilBertClassifier(DistilBertForSequenceClassification):
+    def __init__(self, config):
+        super().__init__(config)
+        self.label_map = label_dict  # Use your predefined label mapping
+
+    def forward(self, input_ids, attention_mask):
+        outputs = super().forward(input_ids=input_ids, attention_mask=attention_mask)
+        logits = outputs.logits
+        predicted_class = torch.argmax(logits, dim=-1).item()
+        return self.label_map[predicted_class]  # Return the string label directly
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs):
+        model = super().from_pretrained(pretrained_model_name_or_path, *model_args, **kwargs)
+        return model

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e323d86ca66e592b2f16e8e3e224a9c2c7e5d8fe354b0ca929c9646b9c6d42c6
+size 535736698

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffb5e793dd475a09e9f2ff870c6fa547ca8d17b32e983b9e3a10a9adc4d7ed1
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c964619ec20c2b1ddf3699d812c3c717630e29566857ae4c8e10cd3cf5f7d7d7
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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,
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.7773577098978421e-07,
+      "learning_rate": 1.3285352466760777e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.970873786407767,
+      "eval_f1": 0.9708202209574825,
+      "eval_loss": 0.3374857008457184,
+      "eval_runtime": 1.5469,
+      "eval_samples_per_second": 66.584,
+      "eval_steps_per_second": 1.293,
+      "step": 8
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.6692462168066413e-07,
+      "learning_rate": 7.814913215741634e-06,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.970873786407767,
+      "eval_f1": 0.9708202209574825,
+      "eval_loss": 0.33735620975494385,
+      "eval_runtime": 1.5393,
+      "eval_samples_per_second": 66.912,
+      "eval_steps_per_second": 1.299,
+      "step": 16
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 1.698020923868171e-07,
+      "learning_rate": 2.34447396472249e-06,
+      "loss": 0.0,
+      "step": 21
+    }
+  ],
+  "logging_steps": 7,
+  "max_steps": 24,
+  "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": 47491256236032.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ca6260af351c39ea1e60a29d92923e9b727973a9f67e9d13d7397bca2424ff6
+size 5304