Commit
•
284fee6
1
Parent(s):
290558a
Model save
Browse files- README.md +74 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Unbabel/TowerInstruct-7B-v0.2
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: cc-by-nc-4.0
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: BioTowerInstruct-7b-v0.2-run09
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# BioTowerInstruct-7b-v0.2-run09
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Unbabel/TowerInstruct-7B-v0.2](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.2) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.3265
|
| 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 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 2.1703 | 0.08 | 30 | 2.0597 |
|
| 55 |
+
| 1.7574 | 0.16 | 60 | 1.8526 |
|
| 56 |
+
| 1.5809 | 0.24 | 90 | 1.7084 |
|
| 57 |
+
| 1.3437 | 0.32 | 120 | 1.5682 |
|
| 58 |
+
| 1.3627 | 0.4 | 150 | 1.5074 |
|
| 59 |
+
| 1.2534 | 0.48 | 180 | 1.4496 |
|
| 60 |
+
| 1.1732 | 0.56 | 210 | 1.4031 |
|
| 61 |
+
| 1.1735 | 0.64 | 240 | 1.3727 |
|
| 62 |
+
| 1.1581 | 0.72 | 270 | 1.3522 |
|
| 63 |
+
| 1.2024 | 0.8 | 300 | 1.3389 |
|
| 64 |
+
| 1.1346 | 0.88 | 330 | 1.3315 |
|
| 65 |
+
| 1.0714 | 0.96 | 360 | 1.3265 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- PEFT 0.12.0
|
| 71 |
+
- Transformers 4.44.2
|
| 72 |
+
- Pytorch 2.4.0
|
| 73 |
+
- Datasets 2.21.0
|
| 74 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40036040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:787250e17e7524c1efd9bc306bfc2096d969269d10a641b5b8752c86cfc2ab5a
|
| 3 |
size 40036040
|