Quantization made by Richard Erkhov.
llama_3b_step2_batch_v5 - GGUF
Original model description:
library_name: transformers
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: llama_3b_step2_batch_v5
results: []
llama_3b_step2_batch_v5
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 40
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|
| 0.9071 | 0.1363 | 50 | 0.8211 |
| 0.7063 | 0.2727 | 100 | 0.6140 |
| 0.5548 | 0.4090 | 150 | 0.5100 |
| 0.3776 | 0.5453 | 200 | 0.4445 |
| 0.4611 | 0.6817 | 250 | 0.4011 |
| 0.3701 | 0.8180 | 300 | 0.3742 |
| 0.325 | 0.9543 | 350 | 0.3529 |
| 0.2093 | 1.0913 | 400 | 0.3522 |
| 0.2459 | 1.2277 | 450 | 0.3428 |
| 0.201 | 1.3640 | 500 | 0.3355 |
| 0.2741 | 1.5003 | 550 | 0.3312 |
| 0.2596 | 1.6367 | 600 | 0.3283 |
| 0.2138 | 1.7730 | 650 | 0.3281 |
| 0.2181 | 1.9093 | 700 | 0.3275 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.1.0+cu118
- Datasets 3.0.2
- Tokenizers 0.20.1
