CharlesLi/OpenELM-1_1B-DPO-full-max-random-reward
019
<!-- 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. -->
OpenELM-1_1B-DPO-full-max-random-reward
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 194.2460
- Rewards/chosen: -660.0
- Rewards/rejected: -568.0
- Rewards/accuracies: 0.4277
- Rewards/margins: -89.5
- Logps/rejected: -57344.0
- Logps/chosen: -66560.0
- Logits/rejected: 7.5
- Logits/chosen: 7.0
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-05
- trainbatchsize: 8
- evalbatchsize: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradientaccumulationsteps: 2
- totaltrainbatch_size: 64
- totalevalbatch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: cosine
- lrschedulerwarmup_ratio: 0.1
- num_epochs: 3
Training results
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.0
- Datasets 2.21.0
- Tokenizers 0.19.1
