zephyr-7b-math-test-half
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the EunsuKim/MATH dataset. It achieves the following results on the evaluation set:
- Loss: 0.0186
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: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.969 | 1.0 | 3 | 1.2659 |
| 1.0058 | 2.0 | 6 | 0.7385 |
| 1.0058 | 3.0 | 9 | 0.4851 |
| 0.6526 | 4.0 | 12 | 0.3110 |
| 0.3241 | 5.0 | 15 | 0.1611 |
| 0.3241 | 6.0 | 18 | 0.0703 |
| 0.1058 | 7.0 | 21 | 0.0349 |
| 0.1058 | 8.0 | 24 | 0.0240 |
| 0.033 | 9.0 | 27 | 0.0196 |
| 0.0202 | 10.0 | 30 | 0.0186 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for interview-eval/zephyr-7b-math-test-half
Base model
mistralai/Mistral-7B-v0.1
Finetuned
alignment-handbook/zephyr-7b-sft-full