Commit
•
0deaef8
1
Parent(s):
0e1657a
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: 6.7b-ri-reproduce-combined-4-gpu-20-val-v3
|
| 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 |
+
# 6.7b-ri-reproduce-combined-4-gpu-20-val-v3
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/opt-6.7b](https://huggingface.co/facebook/opt-6.7b) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 3.9434
|
| 20 |
+
- Accuracy: 0.0329
|
| 21 |
+
- Perplexity: 51.5916
|
| 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: 9e-07
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 100
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- total_train_batch_size: 4
|
| 47 |
+
- total_eval_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: constant
|
| 50 |
+
- num_epochs: 15.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Perplexity |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|
|
| 56 |
+
| 2.5731 | 1.0 | 79 | 2.6113 | 0.0317 | 13.6171 |
|
| 57 |
+
| 2.206 | 2.0 | 158 | 2.4805 | 0.0328 | 11.9469 |
|
| 58 |
+
| 1.9105 | 3.0 | 237 | 2.4512 | 0.0333 | 11.6019 |
|
| 59 |
+
| 1.6301 | 4.0 | 316 | 2.5078 | 0.0345 | 12.2780 |
|
| 60 |
+
| 1.3733 | 5.0 | 395 | 2.6816 | 0.0342 | 14.6090 |
|
| 61 |
+
| 1.1337 | 6.0 | 474 | 3.0078 | 0.0330 | 20.2431 |
|
| 62 |
+
| 0.9619 | 7.0 | 553 | 3.1777 | 0.0330 | 23.9923 |
|
| 63 |
+
| 0.798 | 8.0 | 632 | 3.2559 | 0.0330 | 25.9419 |
|
| 64 |
+
| 0.6653 | 9.0 | 711 | 3.4277 | 0.0331 | 30.8068 |
|
| 65 |
+
| 0.552 | 10.0 | 790 | 3.5566 | 0.0333 | 35.0453 |
|
| 66 |
+
| 0.4568 | 11.0 | 869 | 3.7324 | 0.0324 | 41.7802 |
|
| 67 |
+
| 0.3756 | 12.0 | 948 | 3.8184 | 0.0328 | 45.5295 |
|
| 68 |
+
| 0.3119 | 13.0 | 1027 | 3.8477 | 0.0331 | 46.8831 |
|
| 69 |
+
| 0.2448 | 14.0 | 1106 | 3.9062 | 0.0329 | 49.7122 |
|
| 70 |
+
| 0.1986 | 15.0 | 1185 | 3.9434 | 0.0329 | 51.5916 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.26.0.dev0
|
| 76 |
+
- Pytorch 1.12.1+cu113
|
| 77 |
+
- Datasets 2.3.2
|
| 78 |
+
- Tokenizers 0.12.1
|