llama3.2-3b-instruct-glaive / trainer_log.jsonl
Fan
finetuned llama3.2-3b-instrunct on glaive-en with train set
028d5d6
{"current_steps": 10, "total_steps": 261, "loss": 0.9868, "lr": 3.7037037037037037e-05, "epoch": 0.11428571428571428, "percentage": 3.83, "elapsed_time": "0:00:12", "remaining_time": "0:05:10"}
{"current_steps": 20, "total_steps": 261, "loss": 0.9206, "lr": 7.407407407407407e-05, "epoch": 0.22857142857142856, "percentage": 7.66, "elapsed_time": "0:00:24", "remaining_time": "0:04:52"}
{"current_steps": 30, "total_steps": 261, "loss": 0.7299, "lr": 9.995944990857849e-05, "epoch": 0.34285714285714286, "percentage": 11.49, "elapsed_time": "0:00:35", "remaining_time": "0:04:36"}
{"current_steps": 40, "total_steps": 261, "loss": 0.6769, "lr": 9.924038765061042e-05, "epoch": 0.45714285714285713, "percentage": 15.33, "elapsed_time": "0:00:46", "remaining_time": "0:04:19"}
{"current_steps": 50, "total_steps": 261, "loss": 0.6564, "lr": 9.763511454798268e-05, "epoch": 0.5714285714285714, "percentage": 19.16, "elapsed_time": "0:00:57", "remaining_time": "0:04:04"}
{"current_steps": 60, "total_steps": 261, "loss": 0.668, "lr": 9.517252173051911e-05, "epoch": 0.6857142857142857, "percentage": 22.99, "elapsed_time": "0:01:10", "remaining_time": "0:03:55"}
{"current_steps": 70, "total_steps": 261, "loss": 0.5611, "lr": 9.189693006092907e-05, "epoch": 0.8, "percentage": 26.82, "elapsed_time": "0:01:21", "remaining_time": "0:03:42"}
{"current_steps": 80, "total_steps": 261, "loss": 0.5638, "lr": 8.786729246380901e-05, "epoch": 0.9142857142857143, "percentage": 30.65, "elapsed_time": "0:01:32", "remaining_time": "0:03:29"}
{"current_steps": 90, "total_steps": 261, "loss": 0.612, "lr": 8.315613291203976e-05, "epoch": 1.0285714285714285, "percentage": 34.48, "elapsed_time": "0:01:44", "remaining_time": "0:03:18"}
{"current_steps": 100, "total_steps": 261, "loss": 0.5207, "lr": 7.784824116632197e-05, "epoch": 1.1428571428571428, "percentage": 38.31, "elapsed_time": "0:01:55", "remaining_time": "0:03:06"}
{"current_steps": 110, "total_steps": 261, "loss": 0.5817, "lr": 7.203914675945929e-05, "epoch": 1.2571428571428571, "percentage": 42.15, "elapsed_time": "0:02:07", "remaining_time": "0:02:54"}
{"current_steps": 120, "total_steps": 261, "loss": 0.4891, "lr": 6.583339969007363e-05, "epoch": 1.3714285714285714, "percentage": 45.98, "elapsed_time": "0:02:18", "remaining_time": "0:02:42"}
{"current_steps": 130, "total_steps": 261, "loss": 0.6193, "lr": 5.9342688769210254e-05, "epoch": 1.4857142857142858, "percentage": 49.81, "elapsed_time": "0:02:30", "remaining_time": "0:02:31"}
{"current_steps": 140, "total_steps": 261, "loss": 0.5446, "lr": 5.2683831485156074e-05, "epoch": 1.6, "percentage": 53.64, "elapsed_time": "0:02:41", "remaining_time": "0:02:19"}
{"current_steps": 150, "total_steps": 261, "loss": 0.5892, "lr": 4.597667156416371e-05, "epoch": 1.7142857142857144, "percentage": 57.47, "elapsed_time": "0:02:53", "remaining_time": "0:02:08"}
{"current_steps": 160, "total_steps": 261, "loss": 0.604, "lr": 3.934192206602921e-05, "epoch": 1.8285714285714287, "percentage": 61.3, "elapsed_time": "0:03:05", "remaining_time": "0:01:57"}
{"current_steps": 170, "total_steps": 261, "loss": 0.5201, "lr": 3.289899283371657e-05, "epoch": 1.9428571428571428, "percentage": 65.13, "elapsed_time": "0:03:17", "remaining_time": "0:01:45"}
{"current_steps": 180, "total_steps": 261, "loss": 0.6034, "lr": 2.6763841397811573e-05, "epoch": 2.057142857142857, "percentage": 68.97, "elapsed_time": "0:03:29", "remaining_time": "0:01:34"}
{"current_steps": 190, "total_steps": 261, "loss": 0.4608, "lr": 2.104688601445606e-05, "epoch": 2.1714285714285713, "percentage": 72.8, "elapsed_time": "0:03:40", "remaining_time": "0:01:22"}
{"current_steps": 200, "total_steps": 261, "loss": 0.5035, "lr": 1.585101839715792e-05, "epoch": 2.2857142857142856, "percentage": 76.63, "elapsed_time": "0:03:51", "remaining_time": "0:01:10"}
{"current_steps": 210, "total_steps": 261, "loss": 0.55, "lr": 1.1269751908617277e-05, "epoch": 2.4, "percentage": 80.46, "elapsed_time": "0:04:04", "remaining_time": "0:00:59"}
{"current_steps": 220, "total_steps": 261, "loss": 0.503, "lr": 7.385538540748327e-06, "epoch": 2.5142857142857142, "percentage": 84.29, "elapsed_time": "0:04:15", "remaining_time": "0:00:47"}
{"current_steps": 230, "total_steps": 261, "loss": 0.5168, "lr": 4.268284973287273e-06, "epoch": 2.6285714285714286, "percentage": 88.12, "elapsed_time": "0:04:27", "remaining_time": "0:00:36"}
{"current_steps": 240, "total_steps": 261, "loss": 0.5289, "lr": 1.974094418431388e-06, "epoch": 2.742857142857143, "percentage": 91.95, "elapsed_time": "0:04:38", "remaining_time": "0:00:24"}
{"current_steps": 250, "total_steps": 261, "loss": 0.4854, "lr": 5.442568953384186e-07, "epoch": 2.857142857142857, "percentage": 95.79, "elapsed_time": "0:04:50", "remaining_time": "0:00:12"}
{"current_steps": 260, "total_steps": 261, "loss": 0.4303, "lr": 4.506107163948503e-09, "epoch": 2.9714285714285715, "percentage": 99.62, "elapsed_time": "0:05:02", "remaining_time": "0:00:01"}
{"current_steps": 261, "total_steps": 261, "epoch": 2.982857142857143, "percentage": 100.0, "elapsed_time": "0:05:03", "remaining_time": "0:00:00"}