Quantization made by Richard Erkhov.
llama_1b_step2_batch_grad_v4 - GGUF
Original model description:
library_name: transformers
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: llama_1b_step2_batch_grad_v4
results: []
llama_1b_step2_batch_grad_v4
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
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: 40
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 96
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|
| 0.6188 | 0.4090 | 50 | 0.6047 |
| 0.418 | 0.8180 | 100 | 0.4198 |
| 0.2486 | 1.2270 | 150 | 0.3708 |
| 0.244 | 1.6360 | 200 | 0.3535 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.1.0+cu118
- Datasets 3.0.2
- Tokenizers 0.20.1
