Model save
Browse files
README.md
CHANGED
|
@@ -15,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/npcomposer/npcomposer/runs/lpvwn86m)
|
| 16 |
# NPComposer-v2
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [ibm-research/GP-MoLFormer-Uniq](https://huggingface.co/ibm-research/GP-MoLFormer-Uniq) on
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -43,6 +45,20 @@ The following hyperparameters were used during training:
|
|
| 43 |
- lr_scheduler_warmup_ratio: 0.03
|
| 44 |
- num_epochs: 8.0
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.44.2
|
|
|
|
| 15 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/npcomposer/npcomposer/runs/lpvwn86m)
|
| 16 |
# NPComposer-v2
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [ibm-research/GP-MoLFormer-Uniq](https://huggingface.co/ibm-research/GP-MoLFormer-Uniq) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2718
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 45 |
- lr_scheduler_warmup_ratio: 0.03
|
| 46 |
- num_epochs: 8.0
|
| 47 |
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|
|
| 52 |
+
| 0.4069 | 1.0 | 27763 | 0.3820 |
|
| 53 |
+
| 0.3507 | 2.0 | 55526 | 0.3371 |
|
| 54 |
+
| 0.3247 | 3.0 | 83289 | 0.3142 |
|
| 55 |
+
| 0.3074 | 4.0 | 111052 | 0.2995 |
|
| 56 |
+
| 0.291 | 5.0 | 138815 | 0.2888 |
|
| 57 |
+
| 0.2765 | 6.0 | 166578 | 0.2803 |
|
| 58 |
+
| 0.2677 | 7.0 | 194341 | 0.2750 |
|
| 59 |
+
| 0.2569 | 8.0 | 222104 | 0.2718 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.44.2
|