resultORPO
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9855
- Rewards/chosen: -0.1200
- Rewards/rejected: -0.1292
- Rewards/accuracies: 0.3333
- Rewards/margins: 0.0093
- Logps/rejected: -2.5841
- Logps/chosen: -2.3990
- Logits/rejected: -2.1526
- Logits/chosen: -2.0228
- Nll Loss: 2.9372
- Log Odds Ratio: -0.9667
- Log Odds Chosen: 0.1761
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
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cpu
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Tim-05369/resultORPO
Base model
TinyLlama/TinyLlama-1.1B-Chat-v1.0