End of training
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -42,15 +42,14 @@ The following hyperparameters were used during training:
|
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
-
- num_epochs:
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
-
| No log | 1.0 | 56 |
|
| 52 |
-
| No log | 2.0 | 112 |
|
| 53 |
-
| No log | 3.0 | 168 | 7.9476 |
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
|
@@ -58,5 +57,5 @@ The following hyperparameters were used during training:
|
|
| 58 |
- PEFT 0.14.0
|
| 59 |
- Transformers 4.48.3
|
| 60 |
- Pytorch 2.6.0+cu124
|
| 61 |
-
- Datasets 3.4.
|
| 62 |
-
- Tokenizers 0.21.
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 8.1414
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 2
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| No log | 1.0 | 56 | 7.9756 |
|
| 52 |
+
| No log | 2.0 | 112 | 8.1414 |
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
|
|
|
| 57 |
- PEFT 0.14.0
|
| 58 |
- Transformers 4.48.3
|
| 59 |
- Pytorch 2.6.0+cu124
|
| 60 |
+
- Datasets 3.4.1
|
| 61 |
+
- Tokenizers 0.21.1
|