metadata
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: opt-random_error_5pct_42_1e-3
results: []
opt-random_error_5pct_42_1e-3
This model is a fine-tuned version of /work/10368/siyuansong/vista/models/opt-random_error_5pct_42_1e-3/config.json on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.8654
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: 0.001
- train_batch_size: 256
- eval_batch_size: 256
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 2048
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 32000
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 263 | 7.1276 |
| No log | 2.0 | 526 | 5.5885 |
| No log | 3.0 | 789 | 5.0248 |
| 6.3546 | 4.0 | 1052 | 4.7230 |
| 6.3546 | 5.0 | 1315 | 4.4934 |
| 6.3546 | 6.0 | 1578 | 4.3174 |
| 6.3546 | 7.0 | 1841 | 4.1762 |
| 4.4088 | 8.0 | 2104 | 4.0604 |
| 4.4088 | 9.0 | 2367 | 3.9579 |
| 4.4088 | 10.0 | 2630 | 3.8654 |
Framework versions
- Transformers 4.54.0.dev0
- Pytorch 2.5.1
- Datasets 3.6.0
- Tokenizers 0.21.1