metadata
base_model: pharaouk/zeta-1B
tags:
- generated_from_trainer
model-index:
- name: Scribe
results: []
Scribe
This model is a fine-tuned version of pharaouk/zeta-1B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3360
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 512
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8223 | 0.01 | 1 | 1.8049 |
| 0.7051 | 0.2 | 32 | 1.4195 |
| 0.6256 | 0.4 | 64 | 1.3457 |
| 0.6337 | 0.6 | 96 | 1.3160 |
| 0.633 | 0.8 | 128 | 1.3076 |
| 0.6384 | 1.0 | 160 | 1.3060 |
| 0.5921 | 1.2 | 192 | 1.3058 |
| 0.5906 | 1.4 | 224 | 1.3152 |
| 0.5798 | 1.6 | 256 | 1.3133 |
| 0.592 | 1.8 | 288 | 1.3086 |
| 0.584 | 2.0 | 320 | 1.3070 |
| 0.5358 | 2.2 | 352 | 1.3183 |
| 0.5431 | 2.4 | 384 | 1.3199 |
| 0.5349 | 2.6 | 416 | 1.3217 |
| 0.543 | 2.8 | 448 | 1.3203 |
| 0.5298 | 3.0 | 480 | 1.3195 |
| 0.5029 | 3.2 | 512 | 1.3363 |
| 0.5157 | 3.4 | 544 | 1.3375 |
| 0.4971 | 3.6 | 576 | 1.3365 |
| 0.502 | 3.8 | 608 | 1.3360 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0