End of training
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -44,32 +44,17 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 100
|
| 47 |
-
- training_steps:
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
-
| 2.
|
| 54 |
-
| 1.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.5695 | 0.22 | 120 | 0.5218 |
|
| 59 |
-
| 0.4224 | 0.25 | 140 | 0.5122 |
|
| 60 |
-
| 0.6429 | 0.29 | 160 | 0.5232 |
|
| 61 |
-
| 0.4826 | 0.33 | 180 | 0.4914 |
|
| 62 |
-
| 0.3566 | 0.36 | 200 | 0.5035 |
|
| 63 |
-
| 0.5297 | 0.4 | 220 | 0.4846 |
|
| 64 |
-
| 0.4034 | 0.43 | 240 | 0.4812 |
|
| 65 |
-
| 0.6001 | 0.47 | 260 | 0.4841 |
|
| 66 |
-
| 0.4673 | 0.51 | 280 | 0.4717 |
|
| 67 |
-
| 0.3482 | 0.54 | 300 | 0.4801 |
|
| 68 |
-
| 0.5158 | 0.58 | 320 | 0.4717 |
|
| 69 |
-
| 0.3967 | 0.62 | 340 | 0.4658 |
|
| 70 |
-
| 0.5728 | 0.65 | 360 | 0.4661 |
|
| 71 |
-
| 0.4584 | 0.69 | 380 | 0.4630 |
|
| 72 |
-
| 0.3529 | 0.72 | 400 | 0.4620 |
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5699
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 100
|
| 47 |
+
- training_steps: 100
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 2.1594 | 0.04 | 20 | 1.9765 |
|
| 54 |
+
| 1.1079 | 0.07 | 40 | 0.8140 |
|
| 55 |
+
| 0.8124 | 0.11 | 60 | 0.6610 |
|
| 56 |
+
| 0.5827 | 0.14 | 80 | 0.5901 |
|
| 57 |
+
| 0.4148 | 0.18 | 100 | 0.5699 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|