kykim0/gemma-2-2b-tulu-v2-mix-uf-rm
08
<!-- 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. -->
b64-lr1.41e-05-s0-e1-btbinf-seed42
This model is a fine-tuned version of kykim0/gemma-2-2b-tulu-v2-mix on the allenai/ultrafeedbackbinarizedcleaned dataset. It achieves the following results on the evaluation set:
- Loss: 0.4495
- Accuracy: 0.7714
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: 1.41e-05
- trainbatchsize: 1
- evalbatchsize: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradientaccumulationsteps: 16
- totaltrainbatch_size: 64
- totalevalbatch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: linear
- num_epochs: 1
Training results
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.19.1