htlou/backup_0202_llamafactory_Compcap_cooccur_0_30-llava-mistral

Compcap_cooccur_0_30

This model is a fine-tuned version of llava-hf/llava-v1.6-mistral-7b-hf on the Compcap_cooccur_0_30 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8459

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
0.9534	0.4515	50	0.9351
0.8729	0.9029	100	0.8781
0.8045	1.3544	150	0.8596
0.7875	1.8059	200	0.8477
0.7391	2.2573	250	0.8481
0.7339	2.7088	300	0.8462

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.20.3