metadata
license: apache-2.0
base_model: albert/albert-base-v2
tags:
- generated_from_trainer
model-index:
- name: output
results: []
output
This model is a fine-tuned version of albert/albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3331
- Memory Allocated (gb): 5.75
- Max Memory Allocated (gb): 10.76
- Total Memory Available (gb): 94.62
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: reduce_lr_on_plateau
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Allocated (gb) | Memory Allocated (gb) | Memory Available (gb) |
|---|---|---|---|---|---|---|
| No log | 1.0 | 391 | 0.2682 | 5.75 | 10.76 | 94.62 |
| No log | 2.0 | 782 | 0.2636 | 5.75 | 10.76 | 94.62 |
| No log | 3.0 | 1173 | 0.2861 | 5.75 | 10.76 | 94.62 |
| 0.2178 | 4.0 | 1564 | 0.3331 | 5.75 | 10.76 | 94.62 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.2a0+gitb5d0b9b
- Datasets 2.19.1
- Tokenizers 0.19.1