update model card README.md
Browse files
README.md
CHANGED
|
@@ -13,12 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [theta/gpt2-reporter](https://huggingface.co/theta/gpt2-reporter) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
-
|
| 17 |
-
- eval_runtime: 28.164
|
| 18 |
-
- eval_samples_per_second: 50.667
|
| 19 |
-
- eval_steps_per_second: 3.196
|
| 20 |
-
- epoch: 0.55
|
| 21 |
-
- step: 5200
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -46,8 +41,37 @@ The following hyperparameters were used during training:
|
|
| 46 |
- lr_scheduler_warmup_steps: 500
|
| 47 |
- num_epochs: 1
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.25.1
|
| 52 |
-
- Pytorch 1.13.
|
| 53 |
- Tokenizers 0.13.2
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [theta/gpt2-reporter](https://huggingface.co/theta/gpt2-reporter) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 2.4221
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 41 |
- lr_scheduler_warmup_steps: 500
|
| 42 |
- num_epochs: 1
|
| 43 |
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 2.3859 | 0.04 | 400 | 2.4603 |
|
| 49 |
+
| 2.3069 | 0.08 | 800 | 2.4777 |
|
| 50 |
+
| 2.3114 | 0.13 | 1200 | 2.4806 |
|
| 51 |
+
| 2.3152 | 0.17 | 1600 | 2.4774 |
|
| 52 |
+
| 2.3362 | 0.21 | 2000 | 2.4760 |
|
| 53 |
+
| 2.3354 | 0.25 | 2400 | 2.4728 |
|
| 54 |
+
| 2.344 | 0.3 | 2800 | 2.4685 |
|
| 55 |
+
| 2.366 | 0.34 | 3200 | 2.4632 |
|
| 56 |
+
| 2.3632 | 0.38 | 3600 | 2.4636 |
|
| 57 |
+
| 2.3704 | 0.42 | 4000 | 2.4602 |
|
| 58 |
+
| 2.3791 | 0.47 | 4400 | 2.4552 |
|
| 59 |
+
| 2.3773 | 0.51 | 4800 | 2.4529 |
|
| 60 |
+
| 2.391 | 0.55 | 5200 | 2.4475 |
|
| 61 |
+
| 2.4486 | 0.59 | 5600 | 2.4379 |
|
| 62 |
+
| 2.468 | 0.64 | 6000 | 2.4346 |
|
| 63 |
+
| 2.4602 | 0.68 | 6400 | 2.4323 |
|
| 64 |
+
| 2.4643 | 0.72 | 6800 | 2.4301 |
|
| 65 |
+
| 2.4634 | 0.76 | 7200 | 2.4289 |
|
| 66 |
+
| 2.4632 | 0.81 | 7600 | 2.4266 |
|
| 67 |
+
| 2.4534 | 0.85 | 8000 | 2.4250 |
|
| 68 |
+
| 2.4528 | 0.89 | 8400 | 2.4238 |
|
| 69 |
+
| 2.4618 | 0.93 | 8800 | 2.4222 |
|
| 70 |
+
| 2.4519 | 0.98 | 9200 | 2.4221 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
### Framework versions
|
| 74 |
|
| 75 |
- Transformers 4.25.1
|
| 76 |
+
- Pytorch 1.13.0+cu116
|
| 77 |
- Tokenizers 0.13.2
|