Update README.md
Browse files
README.md
CHANGED
|
@@ -16,21 +16,21 @@ library_name: adapter-transformers
|
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
-
# phi-
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
| 25 |
-
More information needed
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
-
More information needed
|
| 30 |
|
| 31 |
## Training and evaluation data
|
| 32 |
|
| 33 |
-
More information needed
|
| 34 |
|
| 35 |
## Training procedure
|
| 36 |
|
|
@@ -41,17 +41,29 @@ The following hyperparameters were used during training:
|
|
| 41 |
- train_batch_size: 4
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- training_steps: 51967
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
-
|
| 51 |
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- Transformers 4.35.2
|
| 55 |
- Pytorch 2.1.0+cu121
|
| 56 |
- Datasets 2.15.0
|
| 57 |
-
- Tokenizers 0.15.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
+
# phi-2-instruct
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the filtered ultrachat200k dataset using the SFT technique.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
| 25 |
+
More information about the model architecture and specific modifications made during fine-tuning is needed.
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
+
More information about the intended use cases and any limitations of the model is needed.
|
| 30 |
|
| 31 |
## Training and evaluation data
|
| 32 |
|
| 33 |
+
More information about the datasets used for training and evaluation is needed.
|
| 34 |
|
| 35 |
## Training procedure
|
| 36 |
|
|
|
|
| 41 |
- train_batch_size: 4
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9, 0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- training_steps: 51967
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
Detailed training results and performance metrics are not provided. It's recommended to reach out to the model creator for more information.
|
| 51 |
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- Transformers 4.35.2
|
| 55 |
- Pytorch 2.1.0+cu121
|
| 56 |
- Datasets 2.15.0
|
| 57 |
+
- Tokenizers 0.15.0
|
| 58 |
+
|
| 59 |
+
## Evaluation and Inference Example
|
| 60 |
+
|
| 61 |
+
- For an evaluation of the model and an inference example, refer to the [Inference Notebook](https://huggingface.co/venkycs/phi-2-instruct/blob/main/inference_phi_2_instruct.ipynb).
|
| 62 |
+
|
| 63 |
+
## Full Training Metrics on TensorBoard
|
| 64 |
+
|
| 65 |
+
View the full training metrics on TensorBoard [here](https://huggingface.co/venkycs/phi-2-instruct/tensorboard).
|
| 66 |
+
|
| 67 |
+
## Author's LinkedIn Profile
|
| 68 |
+
|
| 69 |
+
[venkycs](https://linkedin.com/in/venkycs)
|