metadata
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- alignment_handbook-handbook
- generated_from_trainer
datasets:
- princeton-nlp/mistral-instruct-ultrafeedback
model-index:
- name: Mistral-7B-Base-MI-1e-6
results: []
Mistral-7B-Base-MI-1e-6
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the princeton-nlp/mistral-instruct-ultrafeedback dataset. It achieves the following results on the evaluation set:
- Loss: 1.8911
- Rewards/chosen: -0.9791
- Rewards/rejected: -1.1183
- Rewards/accuracies: 0.6263
- Rewards/margins: 0.1393
- Logps/rejected: -1.1183
- Logps/chosen: -0.9791
- Logits/rejected: -2.7752
- Logits/chosen: -2.7881
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: 1e-06
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.8319 | 0.8573 | 400 | 1.8911 | -0.9791 | -1.1183 | 0.6263 | 0.1393 | -1.1183 | -0.9791 | -2.7752 | -2.7881 |
Framework versions
- Transformers 4.42.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1