Commit
•
e5c78c1
1
Parent(s):
3e89bf2
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: dalio-1.3b-test
|
| 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 |
+
# dalio-1.3b-test
|
| 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: 2.6035
|
| 20 |
+
- Accuracy: 0.0672
|
| 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: 5e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 4
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 8
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- total_eval_batch_size: 32
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- num_epochs: 2.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 2.6133 | 0.08 | 1 | 2.625 | 0.0652 |
|
| 56 |
+
| 2.6199 | 0.15 | 2 | 2.625 | 0.0652 |
|
| 57 |
+
| 2.7202 | 0.23 | 3 | 2.6113 | 0.0658 |
|
| 58 |
+
| 2.6177 | 0.31 | 4 | 2.6113 | 0.0658 |
|
| 59 |
+
| 2.5422 | 0.38 | 5 | 2.5703 | 0.0661 |
|
| 60 |
+
| 2.5627 | 0.46 | 6 | 2.5566 | 0.0662 |
|
| 61 |
+
| 2.5784 | 0.54 | 7 | 2.5469 | 0.0664 |
|
| 62 |
+
| 2.5264 | 0.62 | 8 | 2.5371 | 0.0663 |
|
| 63 |
+
| 2.3396 | 0.69 | 9 | 2.5332 | 0.0670 |
|
| 64 |
+
| 2.4297 | 0.77 | 10 | 2.5273 | 0.0673 |
|
| 65 |
+
| 2.3914 | 0.85 | 11 | 2.5234 | 0.0672 |
|
| 66 |
+
| 2.429 | 0.92 | 12 | 2.5195 | 0.0671 |
|
| 67 |
+
| 2.3055 | 1.0 | 13 | 2.5117 | 0.0672 |
|
| 68 |
+
| 1.7162 | 1.08 | 14 | 2.5215 | 0.0672 |
|
| 69 |
+
| 1.7264 | 1.15 | 15 | 2.5469 | 0.0677 |
|
| 70 |
+
| 1.7559 | 1.23 | 16 | 2.5879 | 0.0671 |
|
| 71 |
+
| 1.7899 | 1.31 | 17 | 2.6113 | 0.0667 |
|
| 72 |
+
| 1.6465 | 1.38 | 18 | 2.6191 | 0.0666 |
|
| 73 |
+
| 1.5955 | 1.46 | 19 | 2.6074 | 0.0671 |
|
| 74 |
+
| 1.5389 | 1.54 | 20 | 2.5957 | 0.0672 |
|
| 75 |
+
| 1.5356 | 1.62 | 21 | 2.5859 | 0.0670 |
|
| 76 |
+
| 1.386 | 1.69 | 22 | 2.5820 | 0.0672 |
|
| 77 |
+
| 1.7698 | 1.77 | 23 | 2.5742 | 0.0670 |
|
| 78 |
+
| 1.3923 | 1.85 | 24 | 2.5801 | 0.0669 |
|
| 79 |
+
| 1.4723 | 1.92 | 25 | 2.5898 | 0.0672 |
|
| 80 |
+
| 1.5653 | 2.0 | 26 | 2.6035 | 0.0672 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.25.0.dev0
|
| 86 |
+
- Pytorch 1.12.1+cu113
|
| 87 |
+
- Datasets 2.3.2
|
| 88 |
+
- Tokenizers 0.12.1
|