results
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5280
- Rewards/chosen: 0.1420
- Rewards/rejected: -0.2222
- Rewards/accuracies: 1.0
- Rewards/margins: 0.3642
- Logps/rejected: -26.8968
- Logps/chosen: -21.7992
- Logits/rejected: -3.3945
- Logits/chosen: -3.3949
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6171 | 0.992 | 31 | 0.5925 | 0.0898 | -0.1233 | 1.0 | 0.2130 | -25.9077 | -22.3215 | -3.3928 | -3.3934 |
| 0.5355 | 1.984 | 62 | 0.5280 | 0.1420 | -0.2222 | 1.0 | 0.3642 | -26.8968 | -21.7992 | -3.3945 | -3.3949 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.11.0+cu128
- Datasets 3.0.1
- Tokenizers 0.20.3
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Ila99/results
Base model
TinyLlama/TinyLlama-1.1B-Chat-v1.0