metadata

license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
  - generated_from_trainer
model-index:
  - name: zephyr-ds
    results: []

zephyr-ds

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: 0.6618
Rewards/chosen: 0.0116
Rewards/rejected: -0.0133
Rewards/accuracies: 0.6150
Rewards/margins: 0.0249
Logps/rejected: -262.4203
Logps/chosen: -281.8592
Logits/rejected: -2.8344
Logits/chosen: -2.8413
Use Label: 18709.0195
Pred Label: 13352.9805

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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 8
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/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen	Use Label	Pred Label
0.6628	1.0	955	0.6618	0.0116	-0.0133	0.6150	0.0249	-262.4203	-281.8592	-2.8344	-2.8413	18206.0195	12855.9805

Framework versions

Transformers 4.35.0
Pytorch 2.1.1+cu121
Datasets 2.14.6
Tokenizers 0.14.1