gagan3012
/

ViTGPT2I2A

Transformers PyTorch vision-encoder-decoder image-captioning generated_from_trainer Inference Endpoints

Model card Files Files and versions Community

File size: 308 Bytes

45a3289

{
    "epoch": 5.0,
    "eval_loss": 0.0708099901676178,
    "eval_runtime": 220.4842,
    "eval_samples_per_second": 35.15,
    "eval_steps_per_second": 8.79,
    "train_loss": 0.07038866728798608,
    "train_runtime": 25445.4127,
    "train_samples_per_second": 4.604,
    "train_steps_per_second": 1.151
}