metadata
license: apache-2.0
base_model: susnato/ernie-m-base_pytorch
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Model
results: []
Model
This model is a fine-tuned version of susnato/ernie-m-base_pytorch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3594
- F1: 0.8030
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.818 | 1.0 | 1469 | 0.7237 | 0.7282 |
| 0.5339 | 2.0 | 2938 | 0.6703 | 0.7587 |
| 0.3487 | 3.0 | 4407 | 0.7401 | 0.7683 |
| 0.2386 | 4.0 | 5876 | 0.7384 | 0.7901 |
| 0.143 | 5.0 | 7345 | 1.0072 | 0.7736 |
| 0.0819 | 6.0 | 8814 | 1.0898 | 0.7979 |
| 0.0438 | 7.0 | 10283 | 1.3199 | 0.7948 |
| 0.0166 | 8.0 | 11752 | 1.3594 | 0.8030 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1