m-aliababs1/urdu_clf

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: mit
+base_model: urduhack/roberta-urdu-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-urdu-small-clf
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# roberta-urdu-small-clf
+
+This model is a fine-tuned version of [urduhack/roberta-urdu-small](https://huggingface.co/urduhack/roberta-urdu-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7478
+- Accuracy: 0.7945
+- Macro F1: 0.7322
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| No log        | 1.0   | 247  | 1.0007          | 0.6849   | 0.5277   |
+| No log        | 2.0   | 494  | 0.6376          | 0.7648   | 0.6772   |
+| 1.3343        | 3.0   | 741  | 0.5805          | 0.7968   | 0.7311   |
+| 1.3343        | 4.0   | 988  | 0.6192          | 0.8037   | 0.7334   |
+| 0.3891        | 5.0   | 1235 | 0.6002          | 0.7968   | 0.7313   |
+| 0.3891        | 6.0   | 1482 | 0.7478          | 0.7945   | 0.7322   |
+
+
+### Framework versions
+
+- Transformers 4.52.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "DNC",
+    "1": "Do_not_call_again",
+    "2": "Do_not_qualify",
+    "3": "Greeting",
+    "4": "Not_Interested",
+    "5": "interested",
+    "6": "negative",
+    "7": "other",
+    "8": "positive",
+    "9": "provide_age",
+    "10": "say_again",
+    "11": "where_get_number"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "DNC": 0,
+    "Do_not_call_again": 1,
+    "Do_not_qualify": 2,
+    "Greeting": 3,
+    "Not_Interested": 4,
+    "interested": 5,
+    "negative": 6,
+    "other": 7,
+    "positive": 8,
+    "provide_age": 9,
+    "say_again": 10,
+    "where_get_number": 11
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5c1702bccb671dd1aad6b657f900c6a5ff5b2727d8a0c82854c6f9252f97c5
+size 503973504

runs/May29_10-34-16_dc14c7b2bb49/events.out.tfevents.1748514863.dc14c7b2bb49.1293.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5704b648cbdf4babcd5b4135526346d933bff8407da67a9d063f3ef2659a08ed
+size 20000

runs/May29_10-45-35_dc14c7b2bb49/events.out.tfevents.1748515575.dc14c7b2bb49.5146.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ab55bf0e99bc59e783cda607256c8009a3761514ddf0a1e3b55bcef22184a9
+size 8612

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "full_tokenizer_file": null,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296597932dfb7b0a0367ee14aebc9abfe117b7f35bae89d53447416da424108d
+size 5368