zephyr-7b-math-case-8
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the EunsuKim/GSM8K dataset. It achieves the following results on the evaluation set:
- Loss: 0.0276
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: 4
- total_train_batch_size: 32
- 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: 0.03
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0201 | 1.0 | 4 | 0.8704 |
| 0.9676 | 2.0 | 8 | 0.6483 |
| 0.7053 | 3.0 | 12 | 0.4601 |
| 0.4784 | 4.0 | 16 | 0.2716 |
| 0.2487 | 5.0 | 20 | 0.1375 |
| 0.2487 | 6.0 | 24 | 0.0688 |
| 0.1048 | 7.0 | 28 | 0.0426 |
| 0.0523 | 8.0 | 32 | 0.0332 |
| 0.0354 | 9.0 | 36 | 0.0287 |
| 0.0285 | 10.0 | 40 | 0.0276 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 9
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-case-8
Base model
mistralai/Mistral-7B-v0.1
Finetuned
alignment-handbook/zephyr-7b-sft-full