training_logs.json

[{"loss": 2.638, "grad_norm": 4.636992454528809, "learning_rate": 2.917947288614859e-05, "epoch": 0.30303030303030304, "step": 10}, {"loss": 2.697, "grad_norm": 4.417375087738037, "learning_rate": 2.597293740415424e-05, "epoch": 0.6060606060606061, "step": 20}, {"eval_loss": 2.6609995365142822, "eval_runtime": 0.2598, "eval_samples_per_second": 57.735, "eval_steps_per_second": 7.698, "epoch": 0.7575757575757576, "step": 25}, {"loss": 2.6419, "grad_norm": 4.872715950012207, "learning_rate": 2.2766401922159886e-05, "epoch": 0.9090909090909091, "step": 30}, {"loss": 2.5786, "grad_norm": 2.9368369579315186, "learning_rate": 1.955986644016554e-05, "epoch": 1.2121212121212122, "step": 40}, {"loss": 2.5536, "grad_norm": 5.432003021240234, "learning_rate": 1.635333095817119e-05, "epoch": 1.5151515151515151, "step": 50}, {"eval_loss": 2.6232733726501465, "eval_runtime": 0.2581, "eval_samples_per_second": 58.107, "eval_steps_per_second": 7.748, "epoch": 1.5151515151515151, "step": 50}, {"loss": 2.5014, "grad_norm": 4.152248859405518, "learning_rate": 1.3146795476176838e-05, "epoch": 1.8181818181818183, "step": 60}, {"loss": 2.4509, "grad_norm": 4.726781845092773, "learning_rate": 9.940259994182487e-06, "epoch": 2.121212121212121, "step": 70}, {"eval_loss": 2.590834140777588, "eval_runtime": 0.2587, "eval_samples_per_second": 57.985, "eval_steps_per_second": 7.731, "epoch": 2.2727272727272725, "step": 75}, {"loss": 2.4679, "grad_norm": 3.5614612102508545, "learning_rate": 6.733724512188137e-06, "epoch": 2.4242424242424243, "step": 80}, {"loss": 2.4602, "grad_norm": 3.2132833003997803, "learning_rate": 3.5271890301937856e-06, "epoch": 2.7272727272727275, "step": 90}, {"train_runtime": 64.4383, "train_samples_per_second": 6.006, "train_steps_per_second": 1.536, "total_flos": 748116924825600.0, "train_loss": 2.5458066150395555, "epoch": 3.0, "step": 99}]