End of training
Browse files- README.md +86 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: microsoft/phi-1_5
|
| 7 |
+
model-index:
|
| 8 |
+
- name: phi-1_5-finetuned-qlora-cluster-gsm8k-v2
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# phi-1_5-finetuned-qlora-cluster-gsm8k-v2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.9003
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 32
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- num_epochs: 25
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 1.0468 | 1.0 | 233 | 1.1314 |
|
| 54 |
+
| 0.9635 | 2.0 | 467 | 1.1069 |
|
| 55 |
+
| 0.9293 | 3.0 | 701 | 1.1129 |
|
| 56 |
+
| 0.8905 | 4.0 | 935 | 1.1269 |
|
| 57 |
+
| 0.8478 | 5.0 | 1168 | 1.1509 |
|
| 58 |
+
| 0.7686 | 6.0 | 1402 | 1.1727 |
|
| 59 |
+
| 0.7125 | 7.0 | 1636 | 1.2254 |
|
| 60 |
+
| 0.6637 | 8.0 | 1870 | 1.2571 |
|
| 61 |
+
| 0.6155 | 9.0 | 2103 | 1.3230 |
|
| 62 |
+
| 0.574 | 10.0 | 2337 | 1.3985 |
|
| 63 |
+
| 0.5273 | 11.0 | 2571 | 1.4532 |
|
| 64 |
+
| 0.451 | 12.0 | 2805 | 1.5160 |
|
| 65 |
+
| 0.4102 | 13.0 | 3038 | 1.5888 |
|
| 66 |
+
| 0.3802 | 14.0 | 3272 | 1.6469 |
|
| 67 |
+
| 0.3586 | 15.0 | 3506 | 1.6916 |
|
| 68 |
+
| 0.3391 | 16.0 | 3740 | 1.7576 |
|
| 69 |
+
| 0.3194 | 17.0 | 3973 | 1.7898 |
|
| 70 |
+
| 0.293 | 18.0 | 4207 | 1.8284 |
|
| 71 |
+
| 0.2815 | 19.0 | 4441 | 1.8460 |
|
| 72 |
+
| 0.2739 | 20.0 | 4675 | 1.8681 |
|
| 73 |
+
| 0.2693 | 21.0 | 4908 | 1.8821 |
|
| 74 |
+
| 0.2646 | 22.0 | 5142 | 1.8908 |
|
| 75 |
+
| 0.2614 | 23.0 | 5376 | 1.8954 |
|
| 76 |
+
| 0.2577 | 24.0 | 5610 | 1.8993 |
|
| 77 |
+
| 0.2566 | 24.92 | 5825 | 1.9003 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- PEFT 0.11.1
|
| 83 |
+
- Transformers 4.37.2
|
| 84 |
+
- Pytorch 2.3.0
|
| 85 |
+
- Datasets 2.19.1
|
| 86 |
+
- Tokenizers 0.15.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40926200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6c4efb7c07537b86212aa97416d7defc1aaf890a53b5503bb205c64bde3c0e3
|
| 3 |
size 40926200
|