NicholasCorrado/tinyllama-1.1b-chat-v1.0-ui-math-coding-group-dpo

<!-- 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. -->

tinyllama-1.1b-chat-v1.0-ui-math-coding-group-dpo

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the data/uimathref and the data/uicodingref datasets. It achieves the following results on the evaluation set:

• —Loss: 0.4193
• —Rewards/chosen: -0.6057
• —Rewards/rejected: -1.6972
• —Rewards/accuracies: 0.7188
• —Rewards/margins: 1.0915
• —Logps/rejected: -538.1440
• —Logps/chosen: -448.5587
• —Logits/rejected: -2.6494
• —Logits/chosen: -2.6509

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-07
• —trainbatchsize: 16
• —evalbatchsize: 16
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 1024
• —totalevalbatch_size: 128
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.44.1
• —Pytorch 2.1.2+cu121
• —Datasets 2.21.0
• —Tokenizers 0.19.1