Commit
•
5bd277b
1
Parent(s):
2d359cf
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: outputs
|
| 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 |
+
# outputs
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6286
|
| 20 |
+
- Accuracy: 0.7095
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 1
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 51 |
+
| 0.7716 | 0.05 | 20 | 1.1077 | 0.2355 |
|
| 52 |
+
| 0.7058 | 0.09 | 40 | 0.8183 | 0.5443 |
|
| 53 |
+
| 0.6877 | 0.14 | 60 | 0.8182 | 0.5443 |
|
| 54 |
+
| 0.6154 | 0.18 | 80 | 0.7467 | 0.6070 |
|
| 55 |
+
| 0.6188 | 0.23 | 100 | 0.7712 | 0.5810 |
|
| 56 |
+
| 0.549 | 0.28 | 120 | 0.9027 | 0.4847 |
|
| 57 |
+
| 0.5617 | 0.32 | 140 | 0.7137 | 0.6300 |
|
| 58 |
+
| 0.5573 | 0.37 | 160 | 0.7936 | 0.5642 |
|
| 59 |
+
| 0.5382 | 0.41 | 180 | 0.7245 | 0.6346 |
|
| 60 |
+
| 0.5121 | 0.46 | 200 | 0.7282 | 0.6422 |
|
| 61 |
+
| 0.5577 | 0.51 | 220 | 0.7301 | 0.6376 |
|
| 62 |
+
| 0.4909 | 0.55 | 240 | 0.6293 | 0.6957 |
|
| 63 |
+
| 0.5057 | 0.6 | 260 | 0.6421 | 0.6896 |
|
| 64 |
+
| 0.4774 | 0.64 | 280 | 0.6944 | 0.6697 |
|
| 65 |
+
| 0.4786 | 0.69 | 300 | 0.7043 | 0.6682 |
|
| 66 |
+
| 0.4403 | 0.74 | 320 | 0.6020 | 0.7217 |
|
| 67 |
+
| 0.5914 | 0.78 | 340 | 0.5944 | 0.7217 |
|
| 68 |
+
| 0.459 | 0.83 | 360 | 0.6188 | 0.7171 |
|
| 69 |
+
| 0.4654 | 0.87 | 380 | 0.6424 | 0.7110 |
|
| 70 |
+
| 0.3851 | 0.92 | 400 | 0.6387 | 0.7095 |
|
| 71 |
+
| 0.4811 | 0.97 | 420 | 0.6286 | 0.7095 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.29.0.dev0
|
| 77 |
+
- Pytorch 1.13.0
|
| 78 |
+
- Datasets 2.1.0
|
| 79 |
+
- Tokenizers 0.13.2
|