update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- sst2
|
| 7 |
+
model-index:
|
| 8 |
+
- name: finetuned_gpt2-medium_sst2_negation0.0_pretrainedFalse_epochs30
|
| 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 |
+
# finetuned_gpt2-medium_sst2_negation0.0_pretrainedFalse_epochs30
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the sst2 dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 5.8610
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 30
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 2.7927 | 1.0 | 1059 | 3.3242 |
|
| 51 |
+
| 2.4065 | 2.0 | 2118 | 3.5353 |
|
| 52 |
+
| 2.0753 | 3.0 | 3177 | 3.8060 |
|
| 53 |
+
| 1.8186 | 4.0 | 4236 | 4.0682 |
|
| 54 |
+
| 1.6246 | 5.0 | 5295 | 4.3559 |
|
| 55 |
+
| 1.4789 | 6.0 | 6354 | 4.5638 |
|
| 56 |
+
| 1.367 | 7.0 | 7413 | 4.6723 |
|
| 57 |
+
| 1.2762 | 8.0 | 8472 | 4.8568 |
|
| 58 |
+
| 1.2058 | 9.0 | 9531 | 4.9660 |
|
| 59 |
+
| 1.1499 | 10.0 | 10590 | 5.0804 |
|
| 60 |
+
| 1.1047 | 11.0 | 11649 | 5.1751 |
|
| 61 |
+
| 1.0641 | 12.0 | 12708 | 5.2775 |
|
| 62 |
+
| 1.0287 | 13.0 | 13767 | 5.3404 |
|
| 63 |
+
| 1.0026 | 14.0 | 14826 | 5.4163 |
|
| 64 |
+
| 0.9781 | 15.0 | 15885 | 5.4508 |
|
| 65 |
+
| 0.9559 | 16.0 | 16944 | 5.4982 |
|
| 66 |
+
| 0.945 | 17.0 | 18003 | 5.5577 |
|
| 67 |
+
| 0.9267 | 18.0 | 19062 | 5.5923 |
|
| 68 |
+
| 0.9153 | 19.0 | 20121 | 5.6331 |
|
| 69 |
+
| 0.8998 | 20.0 | 21180 | 5.6636 |
|
| 70 |
+
| 0.8864 | 21.0 | 22239 | 5.7158 |
|
| 71 |
+
| 0.8802 | 22.0 | 23298 | 5.7324 |
|
| 72 |
+
| 0.8727 | 23.0 | 24357 | 5.7652 |
|
| 73 |
+
| 0.8586 | 24.0 | 25416 | 5.7807 |
|
| 74 |
+
| 0.8565 | 25.0 | 26475 | 5.7954 |
|
| 75 |
+
| 0.851 | 26.0 | 27534 | 5.8253 |
|
| 76 |
+
| 0.8457 | 27.0 | 28593 | 5.8330 |
|
| 77 |
+
| 0.8432 | 28.0 | 29652 | 5.8485 |
|
| 78 |
+
| 0.8405 | 29.0 | 30711 | 5.8505 |
|
| 79 |
+
| 0.8354 | 30.0 | 31770 | 5.8610 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.25.1
|
| 85 |
+
- Pytorch 1.7.0
|
| 86 |
+
- Datasets 2.8.0
|
| 87 |
+
- Tokenizers 0.13.2
|