Simon Tang
commited on
Commit
•
14d6885
1
Parent(s):
d59c54f
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- anli
|
| 7 |
+
model-index:
|
| 8 |
+
- name: sft-trl-claim-128
|
| 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 |
+
# sft-trl-claim-128
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [EleutherAI/gpt-j-6b](https://huggingface.co/EleutherAI/gpt-j-6b) on the anli dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.3201
|
| 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: 5e-05
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 100
|
| 45 |
+
- num_epochs: 3.0
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 1.4364 | 0.08 | 1000 | 1.8760 |
|
| 52 |
+
| 0.9805 | 0.16 | 2000 | 1.2595 |
|
| 53 |
+
| 0.6629 | 0.24 | 3000 | 1.2970 |
|
| 54 |
+
| 0.4647 | 0.32 | 4000 | 0.9789 |
|
| 55 |
+
| 0.4579 | 0.4 | 5000 | 0.8591 |
|
| 56 |
+
| 0.383 | 0.48 | 6000 | 0.8866 |
|
| 57 |
+
| 0.4915 | 0.56 | 7000 | 0.4281 |
|
| 58 |
+
| 0.4139 | 0.64 | 8000 | 0.3946 |
|
| 59 |
+
| 0.2563 | 0.72 | 9000 | 0.3653 |
|
| 60 |
+
| 0.3179 | 0.8 | 10000 | 0.3528 |
|
| 61 |
+
| 0.4199 | 0.88 | 11000 | 0.3602 |
|
| 62 |
+
| 0.3877 | 0.96 | 12000 | 0.3457 |
|
| 63 |
+
| 0.2332 | 1.04 | 13000 | 0.3882 |
|
| 64 |
+
| 0.3817 | 1.11 | 14000 | 0.3604 |
|
| 65 |
+
| 0.2734 | 1.19 | 15000 | 0.3613 |
|
| 66 |
+
| 0.213 | 1.27 | 16000 | 0.3722 |
|
| 67 |
+
| 0.3154 | 1.35 | 17000 | 0.3378 |
|
| 68 |
+
| 0.2258 | 1.43 | 18000 | 0.3117 |
|
| 69 |
+
| 0.3198 | 1.51 | 19000 | 0.3213 |
|
| 70 |
+
| 0.2959 | 1.59 | 20000 | 0.3050 |
|
| 71 |
+
| 0.2588 | 1.67 | 21000 | 0.3190 |
|
| 72 |
+
| 0.2279 | 1.75 | 22000 | 0.3065 |
|
| 73 |
+
| 0.2988 | 1.83 | 23000 | 0.3077 |
|
| 74 |
+
| 0.3701 | 1.91 | 24000 | 0.3092 |
|
| 75 |
+
| 0.281 | 1.99 | 25000 | 0.3038 |
|
| 76 |
+
| 0.1743 | 2.07 | 26000 | 0.3542 |
|
| 77 |
+
| 0.1374 | 2.15 | 27000 | 0.3550 |
|
| 78 |
+
| 0.1282 | 2.23 | 28000 | 0.3386 |
|
| 79 |
+
| 0.1757 | 2.31 | 29000 | 0.3489 |
|
| 80 |
+
| 0.1371 | 2.39 | 30000 | 0.3316 |
|
| 81 |
+
| 0.1689 | 2.47 | 31000 | 0.3291 |
|
| 82 |
+
| 0.1882 | 2.55 | 32000 | 0.3292 |
|
| 83 |
+
| 0.1685 | 2.63 | 33000 | 0.3196 |
|
| 84 |
+
| 0.1775 | 2.71 | 34000 | 0.3320 |
|
| 85 |
+
| 0.1963 | 2.79 | 35000 | 0.3278 |
|
| 86 |
+
| 0.1733 | 2.87 | 36000 | 0.3221 |
|
| 87 |
+
| 0.1503 | 2.95 | 37000 | 0.3201 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 4.30.2
|
| 93 |
+
- Pytorch 2.0.1+cu117
|
| 94 |
+
- Datasets 2.13.1
|
| 95 |
+
- Tokenizers 0.13.3
|