|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pp-mod-subj2-transformer-1 |
|
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-1 |
|
|
|
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: 3.9262 |
|
|
|
## 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: 1 |
|
- 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.2239 | 0.03 | 76320 | 4.2376 | |
|
| 4.0224 | 1.03 | 152640 | 4.0686 | |
|
| 3.9119 | 0.03 | 228960 | 3.9972 | |
|
| 3.844 | 1.03 | 305280 | 3.9558 | |
|
| 3.7955 | 0.03 | 381600 | 3.9310 | |
|
| 3.7466 | 1.03 | 457920 | 3.9171 | |
|
| 3.7114 | 0.03 | 534240 | 3.9071 | |
|
| 3.678 | 1.03 | 610560 | 3.9014 | |
|
| 3.6505 | 0.03 | 686880 | 3.8976 | |
|
| 3.6283 | 1.03 | 763200 | 3.8972 | |
|
| 3.604 | 0.03 | 839520 | 3.8951 | |
|
| 3.5821 | 1.03 | 915840 | 3.8951 | |
|
| 3.5663 | 0.03 | 992160 | 3.8951 | |
|
| 3.5503 | 1.03 | 1068480 | 3.8963 | |
|
| 3.5299 | 0.03 | 1144800 | 3.8980 | |
|
| 3.5172 | 1.03 | 1221120 | 3.8993 | |
|
| 3.5033 | 0.03 | 1297440 | 3.9014 | |
|
| 3.4932 | 1.03 | 1373760 | 3.9026 | |
|
| 3.4776 | 0.03 | 1450080 | 3.9043 | |
|
| 3.4675 | 1.03 | 1526400 | 3.9066 | |
|
| 3.463 | 0.03 | 1602720 | 3.9080 | |
|
| 3.4455 | 1.03 | 1679040 | 3.9105 | |
|
| 3.4337 | 0.03 | 1755360 | 3.9127 | |
|
| 3.4207 | 0.03 | 1831680 | 3.9144 | |
|
| 3.4094 | 1.03 | 1908000 | 3.9159 | |
|
| 3.4 | 0.03 | 1984320 | 3.9178 | |
|
| 3.3854 | 1.03 | 2060640 | 3.9192 | |
|
| 3.3739 | 0.03 | 2136960 | 3.9209 | |
|
| 3.366 | 1.03 | 2213280 | 3.9216 | |
|
| 3.3551 | 0.03 | 2289600 | 3.9244 | |
|
| 3.3427 | 1.03 | 2365920 | 3.9252 | |
|
| 3.3348 | 0.03 | 2442240 | 3.9254 | |
|
| 3.3254 | 1.03 | 2518560 | 3.9270 | |
|
| 3.3187 | 0.03 | 2594880 | 3.9282 | |
|
| 3.3089 | 1.03 | 2671200 | 3.9282 | |
|
| 3.3021 | 0.03 | 2747520 | 3.9279 | |
|
| 3.2982 | 1.03 | 2823840 | 3.9286 | |
|
| 3.2864 | 0.03 | 2900160 | 3.9283 | |
|
| 3.279 | 1.03 | 2976480 | 3.9276 | |
|
| 3.2717 | 0.02 | 3052726 | 3.9262 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|