RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-ui-coding-dpo-2-gguf
0948
Quantization made by Richard Erkhov.
tinyllama-1.1b-chat-v1.0-ui-coding-dpo-2 - GGUF
- Model creator: https://huggingface.co/NicholasCorrado/
- Original model: https://huggingface.co/NicholasCorrado/tinyllama-1.1b-chat-v1.0-ui-coding-dpo-2/
Original model description: --- libraryname: transformers license: apache-2.0 basemodel: TinyLlama/TinyLlama-1.1B-Chat-v1.0 tags:
- alignment-handbook
- trl
- dpo
- generatedfromtrainer
- trl
- dpo
- generatedfromtrainer datasets:
- data/ui_coding model-index:
- name: tinyllama-1.1b-chat-v1.0-ui-coding-dpo-2 results: [] ---
<!-- 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-coding-dpo-2
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the data/ui_coding dataset. It achieves the following results on the evaluation set:
- Loss: 0.0431
- Rewards/chosen: -3.0407
- Rewards/rejected: -9.3996
- Rewards/accuracies: 0.9375
- Rewards/margins: 6.3590
- Logps/rejected: -1448.7983
- Logps/chosen: -747.9731
- Logits/rejected: -2.8938
- Logits/chosen: -2.7966
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: 8
- evalbatchsize: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradientaccumulationsteps: 4
- totaltrainbatch_size: 256
- totalevalbatch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: cosine
- lrschedulerwarmup_ratio: 0.1
- num_epochs: 2
Training results
Framework versions
- Transformers 4.44.1
- Pytorch 2.1.2+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1