update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: gpt2-synth-real
|
| 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 |
+
# gpt2-synth-real
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.4267
|
| 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: 5e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 4
|
| 39 |
+
- seed: 21
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 43 |
+
- num_epochs: 3.0
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 80.0811 | 0.01 | 10 | 76.0005 |
|
| 50 |
+
| 63.2867 | 0.02 | 20 | 55.5177 |
|
| 51 |
+
| 30.7747 | 0.03 | 30 | 19.9807 |
|
| 52 |
+
| 17.8136 | 0.04 | 40 | 12.4432 |
|
| 53 |
+
| 6.5809 | 0.05 | 50 | 5.7868 |
|
| 54 |
+
| 3.8801 | 0.06 | 60 | 3.3238 |
|
| 55 |
+
| 2.2807 | 0.07 | 70 | 1.8328 |
|
| 56 |
+
| 1.3763 | 0.08 | 80 | 1.1114 |
|
| 57 |
+
| 0.8658 | 0.09 | 90 | 1.0464 |
|
| 58 |
+
| 0.748 | 0.1 | 100 | 0.8199 |
|
| 59 |
+
| 0.5694 | 0.12 | 110 | 0.5984 |
|
| 60 |
+
| 0.6427 | 0.13 | 120 | 0.6168 |
|
| 61 |
+
| 0.5534 | 0.14 | 130 | 0.5981 |
|
| 62 |
+
| 0.5483 | 0.15 | 140 | 0.5450 |
|
| 63 |
+
| 0.5384 | 0.16 | 150 | 0.4926 |
|
| 64 |
+
| 0.4926 | 0.17 | 160 | 0.4924 |
|
| 65 |
+
| 0.5059 | 0.18 | 170 | 0.4762 |
|
| 66 |
+
| 0.4372 | 0.19 | 180 | 0.4733 |
|
| 67 |
+
| 0.4833 | 0.2 | 190 | 0.4785 |
|
| 68 |
+
| 0.4511 | 0.21 | 200 | 0.4511 |
|
| 69 |
+
| 0.4163 | 0.22 | 210 | 0.4534 |
|
| 70 |
+
| 0.4849 | 0.23 | 220 | 0.4420 |
|
| 71 |
+
| 0.4857 | 0.24 | 230 | 0.4421 |
|
| 72 |
+
| 0.6163 | 0.25 | 240 | 0.4336 |
|
| 73 |
+
| 0.5151 | 0.26 | 250 | 0.4344 |
|
| 74 |
+
| 0.4533 | 0.27 | 260 | 0.4280 |
|
| 75 |
+
| 0.3812 | 0.28 | 270 | 0.4387 |
|
| 76 |
+
| 0.475 | 0.29 | 280 | 0.4274 |
|
| 77 |
+
| 0.4354 | 0.3 | 290 | 0.4272 |
|
| 78 |
+
| 0.3912 | 0.31 | 300 | 0.4305 |
|
| 79 |
+
| 0.3944 | 0.32 | 310 | 0.4204 |
|
| 80 |
+
| 0.4166 | 0.33 | 320 | 0.4239 |
|
| 81 |
+
| 0.3677 | 0.35 | 330 | 0.4246 |
|
| 82 |
+
| 0.4135 | 0.36 | 340 | 0.4267 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.24.0
|
| 88 |
+
- Pytorch 1.11.0+cu113
|
| 89 |
+
- Datasets 2.6.1
|
| 90 |
+
- Tokenizers 0.12.1
|