Commit
·
0dec054
1
Parent(s):
2a5c27d
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: model-v3
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# model-v3
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 5.0643
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0001372
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 1268669541
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 20
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 2.7294 | 1.0 | 39 | 3.5148 |
|
| 49 |
+
| 2.6148 | 2.0 | 78 | 3.5284 |
|
| 50 |
+
| 2.157 | 3.0 | 117 | 3.6368 |
|
| 51 |
+
| 2.1294 | 4.0 | 156 | 3.6644 |
|
| 52 |
+
| 1.9443 | 5.0 | 195 | 3.7962 |
|
| 53 |
+
| 1.8812 | 6.0 | 234 | 3.8349 |
|
| 54 |
+
| 1.6243 | 7.0 | 273 | 4.0135 |
|
| 55 |
+
| 1.5363 | 8.0 | 312 | 4.1426 |
|
| 56 |
+
| 1.3983 | 9.0 | 351 | 4.1834 |
|
| 57 |
+
| 1.3106 | 10.0 | 390 | 4.1304 |
|
| 58 |
+
| 0.9305 | 11.0 | 429 | 4.3527 |
|
| 59 |
+
| 1.0721 | 12.0 | 468 | 4.4012 |
|
| 60 |
+
| 0.8783 | 13.0 | 507 | 4.5971 |
|
| 61 |
+
| 0.8152 | 14.0 | 546 | 4.6419 |
|
| 62 |
+
| 0.6485 | 15.0 | 585 | 4.7665 |
|
| 63 |
+
| 0.6553 | 16.0 | 624 | 4.9744 |
|
| 64 |
+
| 0.5309 | 17.0 | 663 | 4.8834 |
|
| 65 |
+
| 0.5271 | 18.0 | 702 | 4.9749 |
|
| 66 |
+
| 0.4727 | 19.0 | 741 | 5.0540 |
|
| 67 |
+
| 0.4828 | 20.0 | 780 | 5.0643 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.26.0
|
| 73 |
+
- Pytorch 1.13.1
|
| 74 |
+
- Datasets 2.9.0
|
| 75 |
+
- Tokenizers 0.13.2
|