Commit
•
de9ff5a
1
Parent(s):
7e43e1e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: 6b-gpteacher-role-play-chatml-10epoch
|
| 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 |
+
# 6b-gpteacher-role-play-chatml-10epoch
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [PygmalionAI/pygmalion-6b](https://huggingface.co/PygmalionAI/pygmalion-6b) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.9141
|
| 20 |
+
- Accuracy: 0.1596
|
| 21 |
+
- Entropy: 1.7788
|
| 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: 4
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 99
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 50 |
+
- num_epochs: 10.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|
|
| 56 |
+
| 2.0504 | 1.0 | 238 | 2.0176 | 0.1563 | 1.9978 |
|
| 57 |
+
| 1.8932 | 2.0 | 476 | 1.9707 | 0.1584 | 1.9182 |
|
| 58 |
+
| 1.8611 | 3.0 | 714 | 1.9473 | 0.1602 | 1.8831 |
|
| 59 |
+
| 1.8206 | 4.0 | 952 | 1.9307 | 0.1604 | 1.8725 |
|
| 60 |
+
| 1.7936 | 5.0 | 1190 | 1.9238 | 0.1613 | 1.8354 |
|
| 61 |
+
| 1.7823 | 6.0 | 1428 | 1.9189 | 0.1618 | 1.8175 |
|
| 62 |
+
| 1.7742 | 7.0 | 1666 | 1.9150 | 0.1615 | 1.8082 |
|
| 63 |
+
| 1.762 | 8.0 | 1904 | 1.9141 | 0.1605 | 1.8145 |
|
| 64 |
+
| 1.7437 | 9.0 | 2142 | 1.9160 | 0.1604 | 1.7750 |
|
| 65 |
+
| 1.7358 | 10.0 | 2380 | 1.9141 | 0.1596 | 1.7788 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.28.1
|
| 71 |
+
- Pytorch 2.0.1+cu117
|
| 72 |
+
- Datasets 2.7.1
|
| 73 |
+
- Tokenizers 0.13.3
|