End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: bert-base-multilingual-cased
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: chakma-bert
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# chakma-bert
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.8670
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 18
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 3.1287 | 1.0 | 59 | 2.8297 |
|
| 54 |
+
| 2.7974 | 2.0 | 118 | 2.5401 |
|
| 55 |
+
| 2.5044 | 3.0 | 177 | 2.4909 |
|
| 56 |
+
| 2.432 | 4.0 | 236 | 2.2127 |
|
| 57 |
+
| 2.3317 | 5.0 | 295 | 2.2474 |
|
| 58 |
+
| 2.1859 | 6.0 | 354 | 2.2014 |
|
| 59 |
+
| 2.1582 | 7.0 | 413 | 2.1784 |
|
| 60 |
+
| 2.0694 | 8.0 | 472 | 2.0472 |
|
| 61 |
+
| 2.0662 | 9.0 | 531 | 2.0296 |
|
| 62 |
+
| 2.0164 | 10.0 | 590 | 2.0319 |
|
| 63 |
+
| 1.9955 | 11.0 | 649 | 1.9045 |
|
| 64 |
+
| 1.8953 | 12.0 | 708 | 1.9912 |
|
| 65 |
+
| 1.9059 | 13.0 | 767 | 1.9668 |
|
| 66 |
+
| 1.8877 | 14.0 | 826 | 1.8459 |
|
| 67 |
+
| 1.8675 | 15.0 | 885 | 1.8975 |
|
| 68 |
+
| 1.8644 | 16.0 | 944 | 1.8578 |
|
| 69 |
+
| 1.8482 | 17.0 | 1003 | 1.9558 |
|
| 70 |
+
| 1.8276 | 18.0 | 1062 | 1.8670 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.56.1
|
| 76 |
+
- Pytorch 2.8.0+cu126
|
| 77 |
+
- Datasets 4.0.0
|
| 78 |
+
- Tokenizers 0.22.0
|