|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: pp-mod-subj2-transformer-3 |
|
|
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. --> |
|
|
|
|
|
# pp-mod-subj2-transformer-3 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.9229 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 3 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- training_steps: 3052726 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2304 | 0.03 | 76320 | 4.2434 | |
|
|
| 4.0273 | 1.03 | 152640 | 4.0739 | |
|
|
| 3.9168 | 0.03 | 228960 | 3.9985 | |
|
|
| 3.8483 | 1.03 | 305280 | 3.9588 | |
|
|
| 3.799 | 0.03 | 381600 | 3.9349 | |
|
|
| 3.75 | 0.03 | 457920 | 3.9180 | |
|
|
| 3.7146 | 1.03 | 534240 | 3.9084 | |
|
|
| 3.6816 | 0.03 | 610560 | 3.9017 | |
|
|
| 3.6536 | 1.03 | 686880 | 3.8982 | |
|
|
| 3.6321 | 0.03 | 763200 | 3.8960 | |
|
|
| 3.6052 | 1.03 | 839520 | 3.8936 | |
|
|
| 3.5849 | 0.03 | 915840 | 3.8942 | |
|
|
| 3.5686 | 1.03 | 992160 | 3.8936 | |
|
|
| 3.5512 | 0.03 | 1068480 | 3.8955 | |
|
|
| 3.5337 | 1.03 | 1144800 | 3.8962 | |
|
|
| 3.5182 | 0.03 | 1221120 | 3.8980 | |
|
|
| 3.5053 | 1.03 | 1297440 | 3.9001 | |
|
|
| 3.4935 | 0.03 | 1373760 | 3.9003 | |
|
|
| 3.4789 | 1.03 | 1450080 | 3.9032 | |
|
|
| 3.4708 | 0.03 | 1526400 | 3.9033 | |
|
|
| 3.4644 | 1.03 | 1602720 | 3.9063 | |
|
|
| 3.4495 | 0.03 | 1679040 | 3.9084 | |
|
|
| 3.4367 | 1.03 | 1755360 | 3.9119 | |
|
|
| 3.4234 | 0.03 | 1831680 | 3.9138 | |
|
|
| 3.4104 | 1.03 | 1908000 | 3.9149 | |
|
|
| 3.403 | 0.03 | 1984320 | 3.9162 | |
|
|
| 3.3885 | 1.03 | 2060640 | 3.9171 | |
|
|
| 3.3782 | 0.03 | 2136960 | 3.9195 | |
|
|
| 3.3693 | 1.03 | 2213280 | 3.9197 | |
|
|
| 3.3588 | 0.03 | 2289600 | 3.9216 | |
|
|
| 3.3474 | 0.03 | 2365920 | 3.9225 | |
|
|
| 3.3383 | 0.03 | 2442240 | 3.9235 | |
|
|
| 3.3305 | 1.03 | 2518560 | 3.9250 | |
|
|
| 3.322 | 0.03 | 2594880 | 3.9253 | |
|
|
| 3.3136 | 1.03 | 2671200 | 3.9247 | |
|
|
| 3.3064 | 0.03 | 2747520 | 3.9262 | |
|
|
| 3.3045 | 0.03 | 2823840 | 3.9255 | |
|
|
| 3.2906 | 1.03 | 2900160 | 3.9256 | |
|
|
| 3.2833 | 0.03 | 2976480 | 3.9249 | |
|
|
| 3.2756 | 1.02 | 3052726 | 3.9229 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
