zephyr-spin-phi3-data
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Rewards/real: 0.3501
- Rewards/generated: -23.8099
- Rewards/accuracies: 1.0
- Rewards/margins: 24.1600
- Logps/generated: -916.0912
- Logps/real: -130.5047
- Logits/generated: -2.8901
- Logits/real: -2.6092
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0 | 0.32 | 500 | 0.0001 | 0.3931 | -14.9119 | 1.0 | 15.3050 | -827.1113 | -130.0747 | -2.7616 | -2.7055 |
| 0.0 | 0.64 | 1000 | 0.0000 | 0.4203 | -16.5266 | 1.0 | 16.9469 | -843.2585 | -129.8029 | -2.8325 | -2.7464 |
| 0.0 | 0.96 | 1500 | 0.0000 | 0.3501 | -23.8099 | 1.0 | 24.1600 | -916.0912 | -130.5047 | -2.8901 | -2.6092 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.