Model save
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# phi-4-openalex
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) on
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -45,8 +45,7 @@ The following hyperparameters were used during training:
|
|
| 45 |
- total_train_batch_size: 256
|
| 46 |
- total_eval_batch_size: 64
|
| 47 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
-
- lr_scheduler_type:
|
| 49 |
-
- lr_scheduler_warmup_ratio: 0.05
|
| 50 |
- num_epochs: 1.0
|
| 51 |
|
| 52 |
### Training results
|
|
@@ -56,6 +55,6 @@ The following hyperparameters were used during training:
|
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
- Transformers 4.48.2
|
| 59 |
-
- Pytorch 2.
|
| 60 |
- Datasets 3.2.0
|
| 61 |
- Tokenizers 0.21.0
|
|
|
|
| 16 |
|
| 17 |
# phi-4-openalex
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) on an unknown dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 45 |
- total_train_batch_size: 256
|
| 46 |
- total_eval_batch_size: 64
|
| 47 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: constant
|
|
|
|
| 49 |
- num_epochs: 1.0
|
| 50 |
|
| 51 |
### Training results
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- Transformers 4.48.2
|
| 58 |
+
- Pytorch 2.5.1+cu124
|
| 59 |
- Datasets 3.2.0
|
| 60 |
- Tokenizers 0.21.0
|