|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: random_transcript_conv |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# random_transcript_conv |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.2220 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: reduce_lr_on_plateau |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 4.7264 | 0.0254 | 1000 | 4.4961 | |
|
| 4.2766 | 0.0508 | 2000 | 4.2143 | |
|
| 4.1231 | 0.0762 | 3000 | 4.0323 | |
|
| 4.0307 | 0.1016 | 4000 | 3.9221 | |
|
| 3.8887 | 0.1270 | 5000 | 3.8578 | |
|
| 3.8689 | 0.1524 | 6000 | 3.7800 | |
|
| 3.7808 | 0.1778 | 7000 | 3.7245 | |
|
| 3.742 | 0.2032 | 8000 | 3.6854 | |
|
| 3.7303 | 0.2285 | 9000 | 3.6259 | |
|
| 3.5985 | 0.2539 | 10000 | 3.6000 | |
|
| 3.6448 | 0.2793 | 11000 | 3.5646 | |
|
| 3.6531 | 0.3047 | 12000 | 3.5310 | |
|
| 3.463 | 0.3301 | 13000 | 3.5120 | |
|
| 3.5609 | 0.3555 | 14000 | 3.4827 | |
|
| 3.5348 | 0.3809 | 15000 | 3.4513 | |
|
| 3.4552 | 0.4063 | 16000 | 3.4491 | |
|
| 3.4829 | 0.4317 | 17000 | 3.4177 | |
|
| 3.4333 | 0.4571 | 18000 | 3.3998 | |
|
| 3.4369 | 0.4825 | 19000 | 3.3927 | |
|
| 3.4465 | 0.5079 | 20000 | 3.3694 | |
|
| 3.2959 | 0.5333 | 21000 | 3.3755 | |
|
| 3.3914 | 0.5587 | 22000 | 3.3508 | |
|
| 3.419 | 0.5841 | 23000 | 3.3296 | |
|
| 3.2619 | 0.6095 | 24000 | 3.3346 | |
|
| 3.3485 | 0.6349 | 25000 | 3.3173 | |
|
| 3.3355 | 0.6603 | 26000 | 3.3090 | |
|
| 3.3004 | 0.6856 | 27000 | 3.3027 | |
|
| 3.3105 | 0.7110 | 28000 | 3.2894 | |
|
| 3.2625 | 0.7364 | 29000 | 3.2808 | |
|
| 3.3031 | 0.7618 | 30000 | 3.2878 | |
|
| 3.3047 | 0.7872 | 31000 | 3.2691 | |
|
| 3.1521 | 0.8126 | 32000 | 3.2749 | |
|
| 3.2836 | 0.8380 | 33000 | 3.2561 | |
|
| 3.2872 | 0.8634 | 34000 | 3.2511 | |
|
| 3.1762 | 0.8888 | 35000 | 3.2519 | |
|
| 3.2412 | 0.9142 | 36000 | 3.2455 | |
|
| 3.2428 | 0.9396 | 37000 | 3.2323 | |
|
| 3.2216 | 0.9650 | 38000 | 3.2419 | |
|
| 3.2271 | 0.9904 | 39000 | 3.2220 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.1 |
|
|
