metadata
license: mit
base_model: microsoft/Phi-3-small-8k-instruct
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- AmberYifan/spin-v
model-index:
- name: phi3-spin-zephyr-data
results: []
phi3-spin-zephyr-data
This model is a fine-tuned version of microsoft/Phi-3-small-8k-instruct on the AmberYifan/spin-v dataset. It achieves the following results on the evaluation set:
- Loss: 0.1748
- Rewards/real: -6.0641
- Rewards/generated: -21.7894
- Rewards/accuracies: 0.9443
- Rewards/margins: 15.7252
- Logps/generated: -509.3286
- Logps/real: -313.0280
- Logits/generated: -inf
- Logits/real: -inf
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
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2945 | 0.64 | 500 | 0.1748 | -6.0641 | -21.7894 | 0.9443 | 15.7252 | -509.3286 | -313.0280 | -inf | -inf |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2