azma-phi-2-instruct-structured
Browse files- README.md +1 -8
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# results
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.8575
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -45,16 +43,11 @@ The following hyperparameters were used during training:
|
|
| 45 |
- lr_scheduler_type: constant
|
| 46 |
- lr_scheduler_warmup_ratio: 0.03
|
| 47 |
- lr_scheduler_warmup_steps: 150
|
| 48 |
-
- num_epochs: 0.
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
| 0.6839 | 0.03 | 25 | 0.9049 |
|
| 56 |
-
| 0.7678 | 0.06 | 50 | 0.8707 |
|
| 57 |
-
| 0.8489 | 0.09 | 75 | 0.8575 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 15 |
# results
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 43 |
- lr_scheduler_type: constant
|
| 44 |
- lr_scheduler_warmup_ratio: 0.03
|
| 45 |
- lr_scheduler_warmup_steps: 150
|
| 46 |
+
- num_epochs: 0.5
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1115659992
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d74caff28ba59f74016fd12ff2419b553e4fd124a67b719faa70d5ec25336211
|
| 3 |
size 1115659992
|