Model save
Browse files- README.md +10 -20
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -16,9 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# results_1
|
| 18 |
|
| 19 |
-
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
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -38,33 +43,18 @@ More information needed
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 1e-05
|
| 41 |
-
- train_batch_size:
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
- gradient_accumulation_steps: 4
|
| 45 |
-
- total_train_batch_size:
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- num_epochs: 12
|
| 49 |
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
-
|:-------------:|:-------:|:----:|:---------------:|
|
| 54 |
-
| 0.7711 | 1.1844 | 53 | 0.6969 |
|
| 55 |
-
| 0.614 | 2.3687 | 106 | 0.6113 |
|
| 56 |
-
| 0.5994 | 3.5531 | 159 | 0.5945 |
|
| 57 |
-
| 0.5602 | 4.7374 | 212 | 0.5745 |
|
| 58 |
-
| 0.5807 | 5.9218 | 265 | 0.5630 |
|
| 59 |
-
| 0.5484 | 7.1061 | 318 | 0.5532 |
|
| 60 |
-
| 0.543 | 8.2905 | 371 | 0.5472 |
|
| 61 |
-
| 0.4977 | 9.4749 | 424 | 0.5436 |
|
| 62 |
-
| 0.5072 | 10.6592 | 477 | 0.5411 |
|
| 63 |
-
|
| 64 |
-
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
-
- PEFT 0.
|
| 68 |
- Transformers 4.42.3
|
| 69 |
- Pytorch 2.3.1+cu121
|
| 70 |
- Datasets 2.18.0
|
|
|
|
| 16 |
|
| 17 |
# results_1
|
| 18 |
|
| 19 |
+
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 an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- eval_loss: 1.3737
|
| 22 |
+
- eval_runtime: 77.6899
|
| 23 |
+
- eval_samples_per_second: 5.779
|
| 24 |
+
- eval_steps_per_second: 0.734
|
| 25 |
+
- epoch: 2.4053
|
| 26 |
+
- step: 270
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
- learning_rate: 1e-05
|
| 46 |
+
- train_batch_size: 4
|
| 47 |
- eval_batch_size: 8
|
| 48 |
- seed: 42
|
| 49 |
- gradient_accumulation_steps: 4
|
| 50 |
+
- total_train_batch_size: 16
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- num_epochs: 12
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
+
- PEFT 0.11.1
|
| 58 |
- Transformers 4.42.3
|
| 59 |
- Pytorch 2.3.1+cu121
|
| 60 |
- Datasets 2.18.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 125889008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2d33e80f0005f1074da3326773743efdfcd82e44609befee1b774c786c2106f
|
| 3 |
size 125889008
|