llama3.2-3b-instruct-lima / trainer_log.jsonl
Fan
finetuned llama3.2-3b on lima with train set
3106b28
{"current_steps": 10, "total_steps": 270, "loss": 2.203, "lr": 3.7037037037037037e-05, "epoch": 0.1111111111111111, "percentage": 3.7, "elapsed_time": "0:00:13", "remaining_time": "0:05:46"}
{"current_steps": 20, "total_steps": 270, "loss": 2.2318, "lr": 7.407407407407407e-05, "epoch": 0.2222222222222222, "percentage": 7.41, "elapsed_time": "0:00:27", "remaining_time": "0:05:40"}
{"current_steps": 30, "total_steps": 270, "loss": 2.1844, "lr": 9.996239762521151e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:00:39", "remaining_time": "0:05:17"}
{"current_steps": 40, "total_steps": 270, "loss": 2.1017, "lr": 9.929548316723982e-05, "epoch": 0.4444444444444444, "percentage": 14.81, "elapsed_time": "0:00:54", "remaining_time": "0:05:12"}
{"current_steps": 50, "total_steps": 270, "loss": 2.0372, "lr": 9.780577808869398e-05, "epoch": 0.5555555555555556, "percentage": 18.52, "elapsed_time": "0:01:09", "remaining_time": "0:05:04"}
{"current_steps": 60, "total_steps": 270, "loss": 2.1209, "lr": 9.551814704830734e-05, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:01:22", "remaining_time": "0:04:47"}
{"current_steps": 70, "total_steps": 270, "loss": 2.092, "lr": 9.247077288236488e-05, "epoch": 0.7777777777777778, "percentage": 25.93, "elapsed_time": "0:01:37", "remaining_time": "0:04:37"}
{"current_steps": 80, "total_steps": 270, "loss": 2.214, "lr": 8.871451929520663e-05, "epoch": 0.8888888888888888, "percentage": 29.63, "elapsed_time": "0:01:52", "remaining_time": "0:04:26"}
{"current_steps": 90, "total_steps": 270, "loss": 2.1295, "lr": 8.43120818934367e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:02:06", "remaining_time": "0:04:13"}
{"current_steps": 100, "total_steps": 270, "loss": 2.1204, "lr": 7.93369417339209e-05, "epoch": 1.1111111111111112, "percentage": 37.04, "elapsed_time": "0:02:20", "remaining_time": "0:03:59"}
{"current_steps": 110, "total_steps": 270, "loss": 2.0444, "lr": 7.387213885189746e-05, "epoch": 1.2222222222222223, "percentage": 40.74, "elapsed_time": "0:02:33", "remaining_time": "0:03:43"}
{"current_steps": 120, "total_steps": 270, "loss": 2.1076, "lr": 6.800888624023553e-05, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:02:45", "remaining_time": "0:03:27"}
{"current_steps": 130, "total_steps": 270, "loss": 2.134, "lr": 6.184504741390596e-05, "epoch": 1.4444444444444444, "percentage": 48.15, "elapsed_time": "0:02:58", "remaining_time": "0:03:12"}
{"current_steps": 140, "total_steps": 270, "loss": 1.993, "lr": 5.548350297062659e-05, "epoch": 1.5555555555555556, "percentage": 51.85, "elapsed_time": "0:03:13", "remaining_time": "0:02:59"}
{"current_steps": 150, "total_steps": 270, "loss": 2.0616, "lr": 4.903043341140879e-05, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:03:27", "remaining_time": "0:02:46"}
{"current_steps": 160, "total_steps": 270, "loss": 2.1526, "lr": 4.259354688243757e-05, "epoch": 1.7777777777777777, "percentage": 59.26, "elapsed_time": "0:03:43", "remaining_time": "0:02:33"}
{"current_steps": 170, "total_steps": 270, "loss": 2.0105, "lr": 3.628028141903493e-05, "epoch": 1.8888888888888888, "percentage": 62.96, "elapsed_time": "0:03:58", "remaining_time": "0:02:20"}
{"current_steps": 180, "total_steps": 270, "loss": 1.9649, "lr": 3.019601169804216e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:04:14", "remaining_time": "0:02:07"}
{"current_steps": 190, "total_steps": 270, "loss": 1.973, "lr": 2.4442290229706344e-05, "epoch": 2.111111111111111, "percentage": 70.37, "elapsed_time": "0:04:28", "remaining_time": "0:01:52"}
{"current_steps": 200, "total_steps": 270, "loss": 1.973, "lr": 1.9115152345327152e-05, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "0:04:42", "remaining_time": "0:01:38"}
{"current_steps": 210, "total_steps": 270, "loss": 1.995, "lr": 1.4303513272105057e-05, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:04:56", "remaining_time": "0:01:24"}
{"current_steps": 220, "total_steps": 270, "loss": 2.0065, "lr": 1.008768404960535e-05, "epoch": 2.4444444444444446, "percentage": 81.48, "elapsed_time": "0:05:10", "remaining_time": "0:01:10"}
{"current_steps": 230, "total_steps": 270, "loss": 1.9803, "lr": 6.53803105866761e-06, "epoch": 2.5555555555555554, "percentage": 85.19, "elapsed_time": "0:05:24", "remaining_time": "0:00:56"}
{"current_steps": 240, "total_steps": 270, "loss": 1.911, "lr": 3.7138015365554833e-06, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:05:40", "remaining_time": "0:00:42"}
{"current_steps": 250, "total_steps": 270, "loss": 2.1055, "lr": 1.6621346816668992e-06, "epoch": 2.7777777777777777, "percentage": 92.59, "elapsed_time": "0:05:54", "remaining_time": "0:00:28"}
{"current_steps": 260, "total_steps": 270, "loss": 1.9595, "lr": 4.1727485344994486e-07, "epoch": 2.888888888888889, "percentage": 96.3, "elapsed_time": "0:06:08", "remaining_time": "0:00:14"}
{"current_steps": 270, "total_steps": 270, "loss": 2.0491, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:06:21", "remaining_time": "0:00:00"}
{"current_steps": 270, "total_steps": 270, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:06:22", "remaining_time": "0:00:00"}