Update README.md
Browse files
README.md
CHANGED
|
@@ -8,20 +8,6 @@ license: mit
|
|
| 8 |
|
| 9 |
This model is a fine-tuned version of [/root/LLaMA-Factory/models/Qwen2.5-14B-Instruct-GPTQ-Int8](https://huggingface.co//root/LLaMA-Factory/models/Qwen2.5-14B-Instruct-GPTQ-Int8) on the airboros-31_en and the airboros-31_zh datasets.
|
| 10 |
|
| 11 |
-
## Model description
|
| 12 |
-
|
| 13 |
-
More information needed
|
| 14 |
-
|
| 15 |
-
## Intended uses & limitations
|
| 16 |
-
|
| 17 |
-
More information needed
|
| 18 |
-
|
| 19 |
-
## Training and evaluation data
|
| 20 |
-
|
| 21 |
-
More information needed
|
| 22 |
-
|
| 23 |
-
## Training procedure
|
| 24 |
-
|
| 25 |
### Training hyperparameters
|
| 26 |
|
| 27 |
The following hyperparameters were used during training:
|
|
@@ -37,7 +23,15 @@ The following hyperparameters were used during training:
|
|
| 37 |
- mixed_precision_training: Native AMP
|
| 38 |
|
| 39 |
### Training results
|
| 40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
|
| 43 |
### Framework versions
|
|
|
|
| 8 |
|
| 9 |
This model is a fine-tuned version of [/root/LLaMA-Factory/models/Qwen2.5-14B-Instruct-GPTQ-Int8](https://huggingface.co//root/LLaMA-Factory/models/Qwen2.5-14B-Instruct-GPTQ-Int8) on the airboros-31_en and the airboros-31_zh datasets.
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
### Training hyperparameters
|
| 12 |
|
| 13 |
The following hyperparameters were used during training:
|
|
|
|
| 23 |
- mixed_precision_training: Native AMP
|
| 24 |
|
| 25 |
### Training results
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9997864616698697,
|
| 28 |
+
"num_input_tokens_seen": 74083488,
|
| 29 |
+
"total_flos": 4.6864422704480256e+17,
|
| 30 |
+
"train_loss": 0.692321076499046,
|
| 31 |
+
"train_runtime": 65496.9949,
|
| 32 |
+
"train_samples_per_second": 1.144,
|
| 33 |
+
"train_steps_per_second": 0.036
|
| 34 |
+
}
|
| 35 |
|
| 36 |
|
| 37 |
### Framework versions
|