End of training
Browse files
README.md
CHANGED
|
@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# peft-starcoder-lora-a100
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.0590
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,7 +33,7 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate: 0.
|
| 39 |
- train_batch_size: 16
|
| 40 |
- eval_batch_size: 16
|
| 41 |
- seed: 42
|
|
@@ -46,34 +44,12 @@ The following hyperparameters were used during training:
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
-
| 0.9653 | 0.05 | 100 | 0.9191 |
|
| 52 |
-
| 0.9895 | 0.1 | 200 | 0.9461 |
|
| 53 |
-
| 0.6513 | 0.15 | 300 | 0.9696 |
|
| 54 |
-
| 0.896 | 0.2 | 400 | 0.9813 |
|
| 55 |
-
| 0.9494 | 0.25 | 500 | 0.9743 |
|
| 56 |
-
| 0.5737 | 0.3 | 600 | 1.0091 |
|
| 57 |
-
| 0.7981 | 0.35 | 700 | 1.0210 |
|
| 58 |
-
| 0.8263 | 0.4 | 800 | 1.0138 |
|
| 59 |
-
| 0.5202 | 0.45 | 900 | 1.0217 |
|
| 60 |
-
| 0.7506 | 0.5 | 1000 | 1.0347 |
|
| 61 |
-
| 0.7716 | 0.55 | 1100 | 1.0356 |
|
| 62 |
-
| 0.4743 | 0.6 | 1200 | 1.0495 |
|
| 63 |
-
| 0.6959 | 0.65 | 1300 | 1.0401 |
|
| 64 |
-
| 0.6839 | 0.7 | 1400 | 1.0461 |
|
| 65 |
-
| 0.5394 | 0.75 | 1500 | 1.0508 |
|
| 66 |
-
| 0.6568 | 0.8 | 1600 | 1.0550 |
|
| 67 |
-
| 0.6002 | 0.85 | 1700 | 1.0603 |
|
| 68 |
-
| 0.6013 | 0.9 | 1800 | 1.0630 |
|
| 69 |
-
| 0.5552 | 0.95 | 1900 | 1.0617 |
|
| 70 |
-
| 0.5881 | 1.0 | 2000 | 1.0590 |
|
| 71 |
|
| 72 |
|
| 73 |
### Framework versions
|
| 74 |
|
| 75 |
- PEFT 0.14.0
|
| 76 |
-
- Transformers 4.
|
| 77 |
- Pytorch 2.6.0+cu124
|
| 78 |
- Datasets 3.5.0
|
| 79 |
- Tokenizers 0.21.1
|
|
|
|
| 15 |
# peft-starcoder-lora-a100
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0002
|
| 37 |
- train_batch_size: 16
|
| 38 |
- eval_batch_size: 16
|
| 39 |
- seed: 42
|
|
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- PEFT 0.14.0
|
| 52 |
+
- Transformers 4.51.1
|
| 53 |
- Pytorch 2.6.0+cu124
|
| 54 |
- Datasets 3.5.0
|
| 55 |
- Tokenizers 0.21.1
|