Commit
•
fbbff64
1
Parent(s):
b8d08cf
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: gpt_tos
|
| 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 |
+
# gpt_tos
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 5.6644
|
| 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-06
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- lr_scheduler_warmup_steps: 500
|
| 43 |
+
- num_epochs: 20
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 8.4766 | 0.62 | 1000 | 7.0356 |
|
| 50 |
+
| 6.6906 | 1.24 | 2000 | 6.4523 |
|
| 51 |
+
| 6.3735 | 1.86 | 3000 | 6.2716 |
|
| 52 |
+
| 6.2028 | 2.48 | 4000 | 6.1586 |
|
| 53 |
+
| 6.1092 | 3.09 | 5000 | 6.0782 |
|
| 54 |
+
| 6.0136 | 3.71 | 6000 | 6.0102 |
|
| 55 |
+
| 5.9325 | 4.33 | 7000 | 5.9612 |
|
| 56 |
+
| 5.8906 | 4.95 | 8000 | 5.9175 |
|
| 57 |
+
| 5.8132 | 5.57 | 9000 | 5.8860 |
|
| 58 |
+
| 5.7793 | 6.19 | 10000 | 5.8571 |
|
| 59 |
+
| 5.7357 | 6.81 | 11000 | 5.8311 |
|
| 60 |
+
| 5.6976 | 7.43 | 12000 | 5.8051 |
|
| 61 |
+
| 5.6553 | 8.04 | 13000 | 5.7859 |
|
| 62 |
+
| 5.6192 | 8.66 | 14000 | 5.7713 |
|
| 63 |
+
| 5.591 | 9.28 | 15000 | 5.7608 |
|
| 64 |
+
| 5.5728 | 9.9 | 16000 | 5.7453 |
|
| 65 |
+
| 5.5361 | 10.52 | 17000 | 5.7339 |
|
| 66 |
+
| 5.5166 | 11.14 | 18000 | 5.7259 |
|
| 67 |
+
| 5.5008 | 11.76 | 19000 | 5.7151 |
|
| 68 |
+
| 5.47 | 12.38 | 20000 | 5.7067 |
|
| 69 |
+
| 5.4621 | 13.0 | 21000 | 5.7004 |
|
| 70 |
+
| 5.4327 | 13.61 | 22000 | 5.6935 |
|
| 71 |
+
| 5.4219 | 14.23 | 23000 | 5.6876 |
|
| 72 |
+
| 5.4101 | 14.85 | 24000 | 5.6832 |
|
| 73 |
+
| 5.3975 | 15.47 | 25000 | 5.6778 |
|
| 74 |
+
| 5.3848 | 16.09 | 26000 | 5.6751 |
|
| 75 |
+
| 5.3707 | 16.71 | 27000 | 5.6726 |
|
| 76 |
+
| 5.3582 | 17.33 | 28000 | 5.6695 |
|
| 77 |
+
| 5.3569 | 17.95 | 29000 | 5.6667 |
|
| 78 |
+
| 5.3451 | 18.56 | 30000 | 5.6663 |
|
| 79 |
+
| 5.3487 | 19.18 | 31000 | 5.6652 |
|
| 80 |
+
| 5.3335 | 19.8 | 32000 | 5.6644 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.29.2
|
| 86 |
+
- Pytorch 2.0.1+cu118
|
| 87 |
+
- Datasets 2.12.0
|
| 88 |
+
- Tokenizers 0.13.3
|