metadata
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: hp_ablations_mistral_epoch5_dcftv1.2
results: []
hp_ablations_mistral_epoch5_dcftv1.2
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset. It achieves the following results on the evaluation set:
- Loss: 0.4100
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: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradient_accumulation_steps: 2
- total_train_batch_size: 512
- total_eval_batch_size: 256
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1738
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5735 | 1.0 | 370 | 0.2857 |
| 0.4841 | 2.0 | 740 | 0.2870 |
| 0.408 | 3.0 | 1110 | 0.3072 |
| 0.3066 | 4.0 | 1480 | 0.3499 |
| 0.2144 | 5.0 | 1850 | 0.4100 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.3.0
- Datasets 3.0.2
- Tokenizers 0.20.3