Virus-Proton/llm_bn_sum
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
# llm_bn_sum
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [hishab/titulm-1b-bn-v1](https://huggingface.co/hishab/titulm-1b-bn-v1) on the crosssum dataset.
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -45,6 +47,22 @@ The following hyperparameters were used during training:
|
|
| 45 |
- num_epochs: 10
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- PEFT 0.10.0
|
|
|
|
| 17 |
# llm_bn_sum
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [hishab/titulm-1b-bn-v1](https://huggingface.co/hishab/titulm-1b-bn-v1) on the crosssum dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: nan
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 47 |
- num_epochs: 10
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 54 |
+
| 0.0 | 1.0 | 2023 | nan |
|
| 55 |
+
| 0.0 | 2.0 | 4046 | nan |
|
| 56 |
+
| 0.0 | 3.0 | 6069 | nan |
|
| 57 |
+
| 0.0 | 4.0 | 8092 | nan |
|
| 58 |
+
| 0.0 | 5.0 | 10115 | nan |
|
| 59 |
+
| 0.0 | 6.0 | 12138 | nan |
|
| 60 |
+
| 0.0 | 7.0 | 14161 | nan |
|
| 61 |
+
| 0.0 | 8.0 | 16184 | nan |
|
| 62 |
+
| 0.0 | 9.0 | 18207 | nan |
|
| 63 |
+
| 0.0 | 10.0 | 20230 | nan |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- PEFT 0.10.0
|