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: distilgpt2-emailgen-finetuned-custom-mail
|
| 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 |
+
# distilgpt2-emailgen-finetuned-custom-mail
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [postbot/distilgpt2-emailgen](https://huggingface.co/postbot/distilgpt2-emailgen) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.2633
|
| 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: 2e-05
|
| 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 |
+
- num_epochs: 20
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| No log | 1.0 | 7 | 3.6910 |
|
| 49 |
+
| No log | 2.0 | 14 | 3.5847 |
|
| 50 |
+
| No log | 3.0 | 21 | 3.5208 |
|
| 51 |
+
| No log | 4.0 | 28 | 3.4705 |
|
| 52 |
+
| No log | 5.0 | 35 | 3.4275 |
|
| 53 |
+
| No log | 6.0 | 42 | 3.3903 |
|
| 54 |
+
| No log | 7.0 | 49 | 3.3649 |
|
| 55 |
+
| No log | 8.0 | 56 | 3.3466 |
|
| 56 |
+
| No log | 9.0 | 63 | 3.3280 |
|
| 57 |
+
| No log | 10.0 | 70 | 3.3129 |
|
| 58 |
+
| No log | 11.0 | 77 | 3.3008 |
|
| 59 |
+
| No log | 12.0 | 84 | 3.2890 |
|
| 60 |
+
| No log | 13.0 | 91 | 3.2806 |
|
| 61 |
+
| No log | 14.0 | 98 | 3.2754 |
|
| 62 |
+
| No log | 15.0 | 105 | 3.2721 |
|
| 63 |
+
| No log | 16.0 | 112 | 3.2696 |
|
| 64 |
+
| No log | 17.0 | 119 | 3.2663 |
|
| 65 |
+
| No log | 18.0 | 126 | 3.2644 |
|
| 66 |
+
| No log | 19.0 | 133 | 3.2639 |
|
| 67 |
+
| No log | 20.0 | 140 | 3.2633 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.23.1
|
| 73 |
+
- Pytorch 1.12.1+cu113
|
| 74 |
+
- Datasets 2.6.1
|
| 75 |
+
- Tokenizers 0.13.1
|