open-sci/sft__ot30k_open-sci-ref-v0.02-1.7b-fineweb-edu-1.4t-300B-4096-longsft_16k-SFT-Tulu3
07
<!-- 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_f679a5c592c8dffbb2864c4f6c8dc6c0624a_sdpa-open-sci-steps
This model is a fine-tuned version of ali-elganzory/open-sci-ref-v0.02-1.7b-fineweb-edu-1.4t-300B-4096-longsft_16k-SFT-Tulu3-decontaminated on the /gpfs/scratch/ehpc524/ot/hfhub/datasets/open-thoughtsopenthoughts3-1.2m30000samples/default/0.0.0/f679a5c592c8dffb 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: 4e-05
- trainbatchsize: 1
- evalbatchsize: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradientaccumulationsteps: 4
- totaltrainbatch_size: 128
- totalevalbatch_size: 256
- optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lrschedulertype: cosine
- lrschedulerwarmup_ratio: 0.1
- num_epochs: 5.0
Training results
Framework versions
- Transformers 4.55.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.21.4