|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: reverse_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. --> |
|
|
|
# reverse_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: 3.2532 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 4.6781 | 0.0254 | 1000 | 4.4922 | |
|
| 4.3077 | 0.0508 | 2000 | 4.1938 | |
|
| 4.112 | 0.0762 | 3000 | 4.0437 | |
|
| 4.0246 | 0.1016 | 4000 | 3.9360 | |
|
| 3.9453 | 0.1270 | 5000 | 3.8491 | |
|
| 3.8408 | 0.1524 | 6000 | 3.8078 | |
|
| 3.8155 | 0.1778 | 7000 | 3.7247 | |
|
| 3.7213 | 0.2032 | 8000 | 3.6968 | |
|
| 3.7151 | 0.2286 | 9000 | 3.6513 | |
|
| 3.7075 | 0.2540 | 10000 | 3.6007 | |
|
| 3.5585 | 0.2794 | 11000 | 3.5847 | |
|
| 3.6149 | 0.3047 | 12000 | 3.5467 | |
|
| 3.5912 | 0.3301 | 13000 | 3.5183 | |
|
| 3.4807 | 0.3555 | 14000 | 3.4998 | |
|
| 3.5226 | 0.3809 | 15000 | 3.4750 | |
|
| 3.498 | 0.4063 | 16000 | 3.4569 | |
|
| 3.4416 | 0.4317 | 17000 | 3.4453 | |
|
| 3.4828 | 0.4571 | 18000 | 3.4140 | |
|
| 3.3674 | 0.4825 | 19000 | 3.4138 | |
|
| 3.4523 | 0.5079 | 20000 | 3.3858 | |
|
| 3.4875 | 0.5333 | 21000 | 3.3705 | |
|
| 3.2789 | 0.5587 | 22000 | 3.3777 | |
|
| 3.3742 | 0.5841 | 23000 | 3.3513 | |
|
| 3.3978 | 0.6095 | 24000 | 3.3461 | |
|
| 3.2839 | 0.6349 | 25000 | 3.3452 | |
|
| 3.3467 | 0.6603 | 26000 | 3.3287 | |
|
| 3.3192 | 0.6857 | 27000 | 3.3149 | |
|
| 3.3158 | 0.7111 | 28000 | 3.3185 | |
|
| 3.3437 | 0.7365 | 29000 | 3.2969 | |
|
| 3.217 | 0.7619 | 30000 | 3.3135 | |
|
| 3.2955 | 0.7873 | 31000 | 3.2879 | |
|
| 3.3673 | 0.8127 | 32000 | 3.2781 | |
|
| 3.166 | 0.8381 | 33000 | 3.2869 | |
|
| 3.2655 | 0.8634 | 34000 | 3.2728 | |
|
| 3.3123 | 0.8888 | 35000 | 3.2662 | |
|
| 3.1935 | 0.9142 | 36000 | 3.2696 | |
|
| 3.2581 | 0.9396 | 37000 | 3.2558 | |
|
| 3.2193 | 0.9650 | 38000 | 3.2571 | |
|
| 3.2243 | 0.9904 | 39000 | 3.2532 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.1 |
|
|
