Commit
•
a8495a8
1
Parent(s):
14a6c64
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: dalio-all-io-1.3b
|
| 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-all-io-1.3b
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.3652
|
| 20 |
+
- Accuracy: 0.0558
|
| 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: 3e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 8
|
| 45 |
+
- total_train_batch_size: 16
|
| 46 |
+
- total_eval_batch_size: 16
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- num_epochs: 1.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 2.6543 | 0.03 | 1 | 2.6113 | 0.0513 |
|
| 56 |
+
| 2.6077 | 0.07 | 2 | 2.6113 | 0.0513 |
|
| 57 |
+
| 2.5964 | 0.1 | 3 | 2.5605 | 0.0519 |
|
| 58 |
+
| 2.7302 | 0.14 | 4 | 2.5234 | 0.0527 |
|
| 59 |
+
| 2.7 | 0.17 | 5 | 2.5078 | 0.0528 |
|
| 60 |
+
| 2.5674 | 0.21 | 6 | 2.4941 | 0.0532 |
|
| 61 |
+
| 2.6406 | 0.24 | 7 | 2.4883 | 0.0534 |
|
| 62 |
+
| 2.5315 | 0.28 | 8 | 2.4805 | 0.0536 |
|
| 63 |
+
| 2.7202 | 0.31 | 9 | 2.4727 | 0.0537 |
|
| 64 |
+
| 2.5144 | 0.34 | 10 | 2.4648 | 0.0536 |
|
| 65 |
+
| 2.4983 | 0.38 | 11 | 2.4512 | 0.0537 |
|
| 66 |
+
| 2.7029 | 0.41 | 12 | 2.4414 | 0.0539 |
|
| 67 |
+
| 2.5198 | 0.45 | 13 | 2.4336 | 0.0540 |
|
| 68 |
+
| 2.5706 | 0.48 | 14 | 2.4258 | 0.0545 |
|
| 69 |
+
| 2.5688 | 0.52 | 15 | 2.4180 | 0.0548 |
|
| 70 |
+
| 2.3793 | 0.55 | 16 | 2.4102 | 0.0552 |
|
| 71 |
+
| 2.4785 | 0.59 | 17 | 2.4043 | 0.0554 |
|
| 72 |
+
| 2.4688 | 0.62 | 18 | 2.3984 | 0.0553 |
|
| 73 |
+
| 2.5674 | 0.66 | 19 | 2.3984 | 0.0553 |
|
| 74 |
+
| 2.5054 | 0.69 | 20 | 2.3945 | 0.0554 |
|
| 75 |
+
| 2.452 | 0.72 | 21 | 2.3887 | 0.0555 |
|
| 76 |
+
| 2.5999 | 0.76 | 22 | 2.3828 | 0.0556 |
|
| 77 |
+
| 2.3665 | 0.79 | 23 | 2.3789 | 0.0556 |
|
| 78 |
+
| 2.6223 | 0.83 | 24 | 2.375 | 0.0557 |
|
| 79 |
+
| 2.3562 | 0.86 | 25 | 2.3711 | 0.0557 |
|
| 80 |
+
| 2.429 | 0.9 | 26 | 2.3691 | 0.0557 |
|
| 81 |
+
| 2.563 | 0.93 | 27 | 2.3672 | 0.0558 |
|
| 82 |
+
| 2.4573 | 0.97 | 28 | 2.3652 | 0.0558 |
|
| 83 |
+
| 2.4883 | 1.0 | 29 | 2.3652 | 0.0558 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.25.0.dev0
|
| 89 |
+
- Pytorch 1.12.1+cu113
|
| 90 |
+
- Datasets 2.3.2
|
| 91 |
+
- Tokenizers 0.12.1
|