Qwen-32B-8a4e8f3a / trainer_log.jsonl
AlexCuadron's picture
Upload trainer_log.jsonl with huggingface_hub
d4d81c3 verified
{"current_steps": 1, "total_steps": 32, "loss": 0.8407, "lr": 2.5e-06, "epoch": 0.12121212121212122, "percentage": 3.12, "elapsed_time": "0:01:22", "remaining_time": "0:42:33"}
{"current_steps": 1, "total_steps": 32, "loss": 0.8407, "lr": 2.5e-06, "epoch": 0.12121212121212122, "percentage": 3.12, "elapsed_time": "0:01:22", "remaining_time": "0:42:24"}
{"current_steps": 2, "total_steps": 32, "loss": 0.7878, "lr": 5e-06, "epoch": 0.24242424242424243, "percentage": 6.25, "elapsed_time": "0:03:34", "remaining_time": "0:53:34"}
{"current_steps": 3, "total_steps": 32, "loss": 0.8026, "lr": 7.500000000000001e-06, "epoch": 0.36363636363636365, "percentage": 9.38, "elapsed_time": "0:05:36", "remaining_time": "0:54:11"}
{"current_steps": 4, "total_steps": 32, "loss": 0.8133, "lr": 1e-05, "epoch": 0.48484848484848486, "percentage": 12.5, "elapsed_time": "0:07:11", "remaining_time": "0:50:18"}
{"current_steps": 5, "total_steps": 32, "loss": 0.7608, "lr": 9.968561049466214e-06, "epoch": 0.6060606060606061, "percentage": 15.62, "elapsed_time": "0:08:50", "remaining_time": "0:47:43"}
{"current_steps": 6, "total_steps": 32, "loss": 0.7272, "lr": 9.874639560909118e-06, "epoch": 0.7272727272727273, "percentage": 18.75, "elapsed_time": "0:11:39", "remaining_time": "0:50:30"}
{"current_steps": 7, "total_steps": 32, "loss": 0.6923, "lr": 9.719416651541839e-06, "epoch": 0.8484848484848485, "percentage": 21.88, "elapsed_time": "0:13:41", "remaining_time": "0:48:53"}
{"current_steps": 8, "total_steps": 32, "loss": 0.6853, "lr": 9.504844339512096e-06, "epoch": 0.9696969696969697, "percentage": 25.0, "elapsed_time": "0:16:01", "remaining_time": "0:48:03"}
{"current_steps": 9, "total_steps": 32, "loss": 0.6532, "lr": 9.233620996141421e-06, "epoch": 1.0, "percentage": 28.12, "elapsed_time": "0:17:44", "remaining_time": "0:45:20"}
{"current_steps": 10, "total_steps": 32, "loss": 0.6334, "lr": 8.90915741234015e-06, "epoch": 1.121212121212121, "percentage": 31.25, "elapsed_time": "0:19:57", "remaining_time": "0:43:54"}
{"current_steps": 11, "total_steps": 32, "loss": 0.6171, "lr": 8.535533905932739e-06, "epoch": 1.2424242424242424, "percentage": 34.38, "elapsed_time": "0:21:27", "remaining_time": "0:40:57"}
{"current_steps": 12, "total_steps": 32, "loss": 0.5768, "lr": 8.117449009293668e-06, "epoch": 1.3636363636363638, "percentage": 37.5, "elapsed_time": "0:23:16", "remaining_time": "0:38:47"}
{"current_steps": 13, "total_steps": 32, "loss": 0.5852, "lr": 7.660160382576683e-06, "epoch": 1.4848484848484849, "percentage": 40.62, "elapsed_time": "0:25:09", "remaining_time": "0:36:46"}
{"current_steps": 14, "total_steps": 32, "loss": 0.5752, "lr": 7.169418695587791e-06, "epoch": 1.606060606060606, "percentage": 43.75, "elapsed_time": "0:27:24", "remaining_time": "0:35:14"}
{"current_steps": 15, "total_steps": 32, "loss": 0.5949, "lr": 6.651395309775837e-06, "epoch": 1.7272727272727273, "percentage": 46.88, "elapsed_time": "0:29:15", "remaining_time": "0:33:09"}
{"current_steps": 16, "total_steps": 32, "loss": 0.5568, "lr": 6.112604669781572e-06, "epoch": 1.8484848484848486, "percentage": 50.0, "elapsed_time": "0:31:02", "remaining_time": "0:31:02"}
{"current_steps": 17, "total_steps": 32, "loss": 0.5506, "lr": 5.559822380516539e-06, "epoch": 1.9696969696969697, "percentage": 53.12, "elapsed_time": "0:35:22", "remaining_time": "0:31:12"}
{"current_steps": 18, "total_steps": 32, "loss": 0.5339, "lr": 5e-06, "epoch": 2.0, "percentage": 56.25, "elapsed_time": "0:36:02", "remaining_time": "0:28:02"}
{"current_steps": 19, "total_steps": 32, "loss": 0.5415, "lr": 4.4401776194834615e-06, "epoch": 2.121212121212121, "percentage": 59.38, "elapsed_time": "0:37:46", "remaining_time": "0:25:50"}
{"current_steps": 20, "total_steps": 32, "loss": 0.5077, "lr": 3.887395330218429e-06, "epoch": 2.242424242424242, "percentage": 62.5, "elapsed_time": "0:39:25", "remaining_time": "0:23:39"}
{"current_steps": 21, "total_steps": 32, "loss": 0.5249, "lr": 3.3486046902241663e-06, "epoch": 2.3636363636363638, "percentage": 65.62, "elapsed_time": "0:41:35", "remaining_time": "0:21:47"}
{"current_steps": 22, "total_steps": 32, "loss": 0.5052, "lr": 2.83058130441221e-06, "epoch": 2.484848484848485, "percentage": 68.75, "elapsed_time": "0:43:45", "remaining_time": "0:19:53"}
{"current_steps": 23, "total_steps": 32, "loss": 0.5087, "lr": 2.339839617423318e-06, "epoch": 2.606060606060606, "percentage": 71.88, "elapsed_time": "0:45:31", "remaining_time": "0:17:48"}
{"current_steps": 24, "total_steps": 32, "loss": 0.4993, "lr": 1.8825509907063328e-06, "epoch": 2.7272727272727275, "percentage": 75.0, "elapsed_time": "0:48:12", "remaining_time": "0:16:04"}
{"current_steps": 25, "total_steps": 32, "loss": 0.4946, "lr": 1.4644660940672628e-06, "epoch": 2.8484848484848486, "percentage": 78.12, "elapsed_time": "0:51:58", "remaining_time": "0:14:33"}
{"current_steps": 26, "total_steps": 32, "loss": 0.4855, "lr": 1.0908425876598512e-06, "epoch": 2.9696969696969697, "percentage": 81.25, "elapsed_time": "0:53:24", "remaining_time": "0:12:19"}
{"current_steps": 27, "total_steps": 32, "loss": 0.5004, "lr": 7.663790038585794e-07, "epoch": 3.0, "percentage": 84.38, "elapsed_time": "0:54:05", "remaining_time": "0:10:01"}
{"current_steps": 28, "total_steps": 32, "loss": 0.4744, "lr": 4.951556604879049e-07, "epoch": 3.121212121212121, "percentage": 87.5, "elapsed_time": "0:56:35", "remaining_time": "0:08:05"}
{"current_steps": 29, "total_steps": 32, "loss": 0.4723, "lr": 2.8058334845816214e-07, "epoch": 3.242424242424242, "percentage": 90.62, "elapsed_time": "0:58:06", "remaining_time": "0:06:00"}
{"current_steps": 30, "total_steps": 32, "loss": 0.5029, "lr": 1.253604390908819e-07, "epoch": 3.3636363636363638, "percentage": 93.75, "elapsed_time": "1:00:17", "remaining_time": "0:04:01"}
{"current_steps": 31, "total_steps": 32, "loss": 0.4881, "lr": 3.143895053378698e-08, "epoch": 3.484848484848485, "percentage": 96.88, "elapsed_time": "1:02:32", "remaining_time": "0:02:01"}
{"current_steps": 32, "total_steps": 32, "loss": 0.5004, "lr": 0.0, "epoch": 3.606060606060606, "percentage": 100.0, "elapsed_time": "1:04:50", "remaining_time": "0:00:00"}
{"current_steps": 32, "total_steps": 32, "epoch": 3.606060606060606, "percentage": 100.0, "elapsed_time": "1:06:51", "remaining_time": "0:00:00"}