trainer_log.jsonl

{"current_steps": 2, "total_steps": 24, "loss": 1.4111, "learning_rate": 9.829629131445342e-05, "epoch": 0.23880597014925373, "percentage": 8.33, "elapsed_time": "0:00:09", "remaining_time": "0:01:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 4, "total_steps": 24, "loss": 1.4368, "learning_rate": 9.330127018922194e-05, "epoch": 0.47761194029850745, "percentage": 16.67, "elapsed_time": "0:00:18", "remaining_time": "0:01:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 6, "total_steps": 24, "loss": 1.2286, "learning_rate": 8.535533905932738e-05, "epoch": 0.7164179104477612, "percentage": 25.0, "elapsed_time": "0:00:27", "remaining_time": "0:01:22", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 8, "total_steps": 24, "loss": 1.1773, "learning_rate": 7.500000000000001e-05, "epoch": 0.9552238805970149, "percentage": 33.33, "elapsed_time": "0:00:34", "remaining_time": "0:01:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 10, "total_steps": 24, "loss": 0.9521, "learning_rate": 6.294095225512603e-05, "epoch": 1.1940298507462686, "percentage": 41.67, "elapsed_time": "0:00:42", "remaining_time": "0:00:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 12, "total_steps": 24, "loss": 0.9986, "learning_rate": 5e-05, "epoch": 1.4328358208955223, "percentage": 50.0, "elapsed_time": "0:00:50", "remaining_time": "0:00:50", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 14, "total_steps": 24, "loss": 0.9659, "learning_rate": 3.705904774487396e-05, "epoch": 1.671641791044776, "percentage": 58.33, "elapsed_time": "0:00:59", "remaining_time": "0:00:42", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 16, "total_steps": 24, "loss": 0.9646, "learning_rate": 2.500000000000001e-05, "epoch": 1.9104477611940298, "percentage": 66.67, "elapsed_time": "0:01:07", "remaining_time": "0:00:33", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 18, "total_steps": 24, "loss": 0.9083, "learning_rate": 1.4644660940672627e-05, "epoch": 2.1492537313432836, "percentage": 75.0, "elapsed_time": "0:01:17", "remaining_time": "0:00:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 20, "total_steps": 24, "loss": 0.9453, "learning_rate": 6.698729810778065e-06, "epoch": 2.388059701492537, "percentage": 83.33, "elapsed_time": "0:01:24", "remaining_time": "0:00:16", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 22, "total_steps": 24, "loss": 0.9429, "learning_rate": 1.70370868554659e-06, "epoch": 2.626865671641791, "percentage": 91.67, "elapsed_time": "0:01:33", "remaining_time": "0:00:08", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 24, "total_steps": 24, "loss": 0.8827, "learning_rate": 0.0, "epoch": 2.8656716417910446, "percentage": 100.0, "elapsed_time": "0:01:42", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 24, "total_steps": 24, "epoch": 2.8656716417910446, "percentage": 100.0, "elapsed_time": "0:01:42", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}