Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: google/muril-base-cased
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- f1
|
| 10 |
+
- precision
|
| 11 |
+
- recall
|
| 12 |
+
model-index:
|
| 13 |
+
- name: nepali-grammar-20250304_1523
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# nepali-grammar-20250304_1523
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.2026
|
| 25 |
+
- Accuracy: 0.9301
|
| 26 |
+
- F1: 0.9274
|
| 27 |
+
- Precision: 0.9637
|
| 28 |
+
- Recall: 0.8938
|
| 29 |
+
|
| 30 |
+
## Model description
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training and evaluation data
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training procedure
|
| 43 |
+
|
| 44 |
+
### Training hyperparameters
|
| 45 |
+
|
| 46 |
+
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 3e-05
|
| 48 |
+
- train_batch_size: 64
|
| 49 |
+
- eval_batch_size: 128
|
| 50 |
+
- seed: 42
|
| 51 |
+
- gradient_accumulation_steps: 2
|
| 52 |
+
- total_train_batch_size: 128
|
| 53 |
+
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 54 |
+
- lr_scheduler_type: linear
|
| 55 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 56 |
+
- num_epochs: 3
|
| 57 |
+
- mixed_precision_training: Native AMP
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 62 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 63 |
+
| 0.2193 | 1.0 | 14942 | 0.2048 | 0.9236 | 0.9205 | 0.9584 | 0.8855 |
|
| 64 |
+
| 0.1789 | 2.0 | 29884 | 0.1992 | 0.9288 | 0.9257 | 0.9677 | 0.8872 |
|
| 65 |
+
| 0.1536 | 2.9998 | 44823 | 0.2026 | 0.9301 | 0.9274 | 0.9637 | 0.8938 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.47.0
|
| 71 |
+
- Pytorch 2.5.1+cu121
|
| 72 |
+
- Datasets 3.2.0
|
| 73 |
+
- Tokenizers 0.21.0
|