This model is a fine-tuned version of llava-hf/llava-v1.6-mistral-7b-hf on the AA_preference_cocour_0_25 dataset. It achieves the following results on the evaluation set:

Loss: 0.5255
Rewards/chosen: 2.4023
Rewards/rejected: -0.3121
Rewards/accuracies: 0.8583
Rewards/margins: 2.7144
Logps/rejected: -213.8096
Logps/chosen: -267.1278
Logits/rejected: -2.3534
Logits/chosen: -2.3587

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 256
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.2339	1.4925	50	0.5196	2.3503	-0.2564	0.8500	2.6068	-213.2534	-267.6478	-2.2156	-2.2193

Framework versions

Transformers 4.45.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.20.3

htlou/mm-interp-AA_preference_cocour_0_25

AA_preference_cocour_0_25

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

htlou/
mm-interp-AA_preference_cocour_0_25