autoprogrammer/sdar_4b_trace_sft_openr1math
05
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
sft
This model is a fine-tuned version of SDAR-4B-Chat on an unknown dataset.
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
- trainbatchsize: 2
- evalbatchsize: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradientaccumulationsteps: 4
- totaltrainbatch_size: 32
- totalevalbatch_size: 32
- optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: cosine
- lrschedulerwarmup_ratio: 0.03
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.52.4
- Pytorch 2.8.0a0+34c6371d24.nv25.08
- Datasets 3.6.0
- Tokenizers 0.21.1