End of training
Browse files
README.md
CHANGED
@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# santacoder-finetuned-the-stack-bash
|
15 |
|
16 |
This model is a fine-tuned version of [bigcode/santacoder](https://huggingface.co/bigcode/santacoder) on an unknown dataset.
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -43,6 +45,22 @@ The following hyperparameters were used during training:
|
|
43 |
- lr_scheduler_warmup_steps: 1
|
44 |
- training_steps: 10
|
45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
### Framework versions
|
47 |
|
48 |
- Transformers 4.33.1
|
|
|
14 |
# santacoder-finetuned-the-stack-bash
|
15 |
|
16 |
This model is a fine-tuned version of [bigcode/santacoder](https://huggingface.co/bigcode/santacoder) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.8294
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
45 |
- lr_scheduler_warmup_steps: 1
|
46 |
- training_steps: 10
|
47 |
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| No log | 0.1 | 1 | 1.6955 |
|
53 |
+
| No log | 0.2 | 2 | 3.6096 |
|
54 |
+
| No log | 0.3 | 3 | 1.5787 |
|
55 |
+
| No log | 0.4 | 4 | 1.8131 |
|
56 |
+
| No log | 0.5 | 5 | 1.0994 |
|
57 |
+
| No log | 0.6 | 6 | 1.0921 |
|
58 |
+
| No log | 0.7 | 7 | 0.9509 |
|
59 |
+
| No log | 0.8 | 8 | 0.8762 |
|
60 |
+
| No log | 0.9 | 9 | 0.8375 |
|
61 |
+
| 1.3831 | 1.0 | 10 | 0.8294 |
|
62 |
+
|
63 |
+
|
64 |
### Framework versions
|
65 |
|
66 |
- Transformers 4.33.1
|