Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: ai4bharat/IndicBART
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: codemix-test
+  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. -->
+
+# codemix-test
+
+This model is a fine-tuned version of [ai4bharat/IndicBART](https://huggingface.co/ai4bharat/IndicBART) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4771
+- Bleu: 30.8359
+- Gen Len: 14.4799
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- 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: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
+| 7.0195        | 0.4555 | 500  | 3.2801          | 33.8167 | 17.7783 |
+| 1.8495        | 0.9110 | 1000 | 0.9274          | 37.2318 | 14.4144 |
+| 1.2111        | 1.3671 | 1500 | 0.5053          | 31.1943 | 14.467  |
+| 0.8509        | 1.8226 | 2000 | 0.4772          | 30.8288 | 14.48   |
+| 0.844         | 2.2788 | 2500 | 0.4771          | 30.8365 | 14.4778 |
+| 0.8527        | 2.7342 | 3000 | 0.4771          | 30.8359 | 14.4799 |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.1

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 64000,
+  "eos_token_id": 64001,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4a9af580c8a4c65f38cc2c42e37f0ef45d998f453ede1221ca25c84d6ec661
+oid sha256:3679594c84aa5b30854a8721e8eb88501f1991daa6aad3c39bdb662879bbf15a
 size 976355336