metadata
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: zephyr-7b-sft-full
results: []
zephyr-7b-sft-full
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.9296
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-06
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.977 | 0.0923 | 100 | 0.9750 |
| 0.962 | 0.1846 | 200 | 0.9703 |
| 0.9629 | 0.2769 | 300 | 0.9640 |
| 0.9442 | 0.3692 | 400 | 0.9575 |
| 0.9595 | 0.4615 | 500 | 0.9511 |
| 0.9288 | 0.5538 | 600 | 0.9445 |
| 0.9131 | 0.6461 | 700 | 0.9387 |
| 0.9053 | 0.7383 | 800 | 0.9341 |
| 0.9221 | 0.8306 | 900 | 0.9310 |
| 0.9109 | 0.9229 | 1000 | 0.9296 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+rocm6.2
- Datasets 3.5.0
- Tokenizers 0.20.3