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 |
|
|
@@ -45,32 +45,31 @@ The following hyperparameters were used during training:
|
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 100
|
| 47 |
- training_steps: 400
|
| 48 |
-
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
-
| 2.
|
| 55 |
-
| 1.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
|
| 75 |
|
| 76 |
### 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: 0.4621
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 100
|
| 47 |
- training_steps: 400
|
|
|
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 2.1563 | 0.04 | 20 | 1.9767 |
|
| 54 |
+
| 1.1222 | 0.07 | 40 | 0.8267 |
|
| 55 |
+
| 0.814 | 0.11 | 60 | 0.6637 |
|
| 56 |
+
| 0.5956 | 0.14 | 80 | 0.5908 |
|
| 57 |
+
| 0.405 | 0.18 | 100 | 0.5643 |
|
| 58 |
+
| 0.5643 | 0.22 | 120 | 0.5204 |
|
| 59 |
+
| 0.4326 | 0.25 | 140 | 0.5107 |
|
| 60 |
+
| 0.6401 | 0.29 | 160 | 0.5211 |
|
| 61 |
+
| 0.4789 | 0.33 | 180 | 0.4908 |
|
| 62 |
+
| 0.3577 | 0.36 | 200 | 0.5069 |
|
| 63 |
+
| 0.5289 | 0.4 | 220 | 0.4851 |
|
| 64 |
+
| 0.3971 | 0.43 | 240 | 0.4811 |
|
| 65 |
+
| 0.5972 | 0.47 | 260 | 0.4807 |
|
| 66 |
+
| 0.4683 | 0.51 | 280 | 0.4712 |
|
| 67 |
+
| 0.3442 | 0.54 | 300 | 0.4790 |
|
| 68 |
+
| 0.5148 | 0.58 | 320 | 0.4692 |
|
| 69 |
+
| 0.3917 | 0.62 | 340 | 0.4661 |
|
| 70 |
+
| 0.5769 | 0.65 | 360 | 0.4661 |
|
| 71 |
+
| 0.4603 | 0.69 | 380 | 0.4629 |
|
| 72 |
+
| 0.3461 | 0.72 | 400 | 0.4621 |
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|