metadata
library_name: transformers
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- EunsuKim/GSM8K
- EunsuKim/MATH
model-index:
- name: zephyr-7b-math-case-6-ep5
results: []
zephyr-7b-math-case-6-ep5
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the EunsuKim/GSM8K and the EunsuKim/MATH datasets. It achieves the following results on the evaluation set:
- Loss: 0.3117
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0402 | 1.0 | 5 | 0.7510 |
| 0.691 | 2.0 | 10 | 0.5701 |
| 0.5239 | 3.0 | 15 | 0.4264 |
| 0.3917 | 4.0 | 20 | 0.3359 |
| 0.3221 | 5.0 | 25 | 0.3117 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1