End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: microsoft/phi-1_5
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: phi-1_5-finetuned-model-15-10
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# phi-1_5-finetuned-model-15-10
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.7222
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0002
|
| 38 |
+
- train_batch_size: 1
|
| 39 |
+
- eval_batch_size: 1
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 8
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine
|
| 45 |
+
- training_steps: 1000
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 2.7877 | 0.8 | 100 | 2.7425 |
|
| 52 |
+
| 2.6025 | 1.6 | 200 | 2.6925 |
|
| 53 |
+
| 2.5405 | 2.4 | 300 | 2.6806 |
|
| 54 |
+
| 2.4735 | 3.2 | 400 | 2.6880 |
|
| 55 |
+
| 2.4282 | 4.0 | 500 | 2.6807 |
|
| 56 |
+
| 2.3467 | 4.8 | 600 | 2.6904 |
|
| 57 |
+
| 2.2924 | 5.6 | 700 | 2.7146 |
|
| 58 |
+
| 2.2779 | 6.4 | 800 | 2.7179 |
|
| 59 |
+
| 2.249 | 7.2 | 900 | 2.7212 |
|
| 60 |
+
| 2.2317 | 8.0 | 1000 | 2.7222 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.34.0
|
| 66 |
+
- Pytorch 2.0.1+cu118
|
| 67 |
+
- Datasets 2.14.5
|
| 68 |
+
- Tokenizers 0.14.1
|