Model save
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -55,20 +55,29 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
- PEFT 0.11.1
|
| 71 |
- Transformers 4.41.0
|
| 72 |
-
- Pytorch 2.
|
| 73 |
- Datasets 2.19.1
|
| 74 |
- Tokenizers 0.19.1
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.4093
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.7006 | 0.1116 | 20 | 0.6798 |
|
| 59 |
+
| 0.6142 | 0.2232 | 40 | 0.6206 |
|
| 60 |
+
| 0.5765 | 0.3347 | 60 | 0.5811 |
|
| 61 |
+
| 0.5665 | 0.4463 | 80 | 0.5487 |
|
| 62 |
+
| 0.5511 | 0.5579 | 100 | 0.5362 |
|
| 63 |
+
| 0.5297 | 0.6695 | 120 | 0.5161 |
|
| 64 |
+
| 0.5028 | 0.7810 | 140 | 0.4949 |
|
| 65 |
+
| 0.4922 | 0.8926 | 160 | 0.4742 |
|
| 66 |
+
| 0.4844 | 1.0042 | 180 | 0.4652 |
|
| 67 |
+
| 0.367 | 1.1158 | 200 | 0.4576 |
|
| 68 |
+
| 0.3784 | 1.2273 | 220 | 0.4493 |
|
| 69 |
+
| 0.3198 | 1.3389 | 240 | 0.4465 |
|
| 70 |
+
| 0.336 | 1.4505 | 260 | 0.4360 |
|
| 71 |
+
| 0.3084 | 1.5621 | 280 | 0.4293 |
|
| 72 |
+
| 0.3707 | 1.6736 | 300 | 0.4211 |
|
| 73 |
+
| 0.3358 | 1.7852 | 320 | 0.4141 |
|
| 74 |
+
| 0.3307 | 1.8968 | 340 | 0.4093 |
|
| 75 |
|
| 76 |
|
| 77 |
### Framework versions
|
| 78 |
|
| 79 |
- PEFT 0.11.1
|
| 80 |
- Transformers 4.41.0
|
| 81 |
+
- Pytorch 2.3.0+cu121
|
| 82 |
- Datasets 2.19.1
|
| 83 |
- Tokenizers 0.19.1
|