qwen3-4b-sft / trainer_log.jsonl
3N3G's picture
Training in progress, step 28
4ce2f57 verified
{"current_steps": 1, "total_steps": 28, "loss": 0.6626, "lr": 0.0, "epoch": 0.14285714285714285, "percentage": 3.57, "elapsed_time": "0:00:21", "remaining_time": "0:09:39"}
{"current_steps": 2, "total_steps": 28, "loss": 0.6659, "lr": 3.3333333333333335e-05, "epoch": 0.2857142857142857, "percentage": 7.14, "elapsed_time": "0:00:40", "remaining_time": "0:08:40"}
{"current_steps": 3, "total_steps": 28, "loss": 0.63, "lr": 6.666666666666667e-05, "epoch": 0.42857142857142855, "percentage": 10.71, "elapsed_time": "0:00:58", "remaining_time": "0:08:04"}
{"current_steps": 4, "total_steps": 28, "loss": 0.8161, "lr": 0.0001, "epoch": 0.5714285714285714, "percentage": 14.29, "elapsed_time": "0:01:15", "remaining_time": "0:07:34"}
{"current_steps": 5, "total_steps": 28, "loss": 1.5894, "lr": 9.964516155915151e-05, "epoch": 0.7142857142857143, "percentage": 17.86, "elapsed_time": "0:01:33", "remaining_time": "0:07:12"}
{"current_steps": 6, "total_steps": 28, "loss": 0.8261, "lr": 9.858624225078841e-05, "epoch": 0.8571428571428571, "percentage": 21.43, "elapsed_time": "0:01:52", "remaining_time": "0:06:51"}
{"current_steps": 7, "total_steps": 28, "loss": 0.7116, "lr": 9.683994186497132e-05, "epoch": 1.0, "percentage": 25.0, "elapsed_time": "0:02:10", "remaining_time": "0:06:32"}
{"current_steps": 8, "total_steps": 28, "loss": 0.6494, "lr": 9.443380060197387e-05, "epoch": 1.1428571428571428, "percentage": 28.57, "elapsed_time": "0:02:30", "remaining_time": "0:06:15"}
{"current_steps": 9, "total_steps": 28, "loss": 0.507, "lr": 9.140576474687264e-05, "epoch": 1.2857142857142856, "percentage": 32.14, "elapsed_time": "0:02:47", "remaining_time": "0:05:54"}
{"current_steps": 10, "total_steps": 28, "loss": 0.4906, "lr": 8.780358823396352e-05, "epoch": 1.4285714285714286, "percentage": 35.71, "elapsed_time": "0:03:05", "remaining_time": "0:05:34"}
{"current_steps": 11, "total_steps": 28, "loss": 0.4666, "lr": 8.368407953869104e-05, "epoch": 1.5714285714285714, "percentage": 39.29, "elapsed_time": "0:03:23", "remaining_time": "0:05:14"}
{"current_steps": 12, "total_steps": 28, "loss": 0.4357, "lr": 7.911220577405484e-05, "epoch": 1.7142857142857144, "percentage": 42.86, "elapsed_time": "0:03:40", "remaining_time": "0:04:54"}
{"current_steps": 13, "total_steps": 28, "loss": 0.4024, "lr": 7.416006812042828e-05, "epoch": 1.8571428571428572, "percentage": 46.43, "elapsed_time": "0:03:57", "remaining_time": "0:04:34"}
{"current_steps": 14, "total_steps": 28, "loss": 0.4064, "lr": 6.890576474687263e-05, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "0:04:15", "remaining_time": "0:04:15"}
{"current_steps": 14, "total_steps": 28, "eval_loss": 0.4329422414302826, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "0:04:19", "remaining_time": "0:04:19"}
{"current_steps": 15, "total_steps": 28, "loss": 0.3543, "lr": 6.343215915635762e-05, "epoch": 2.142857142857143, "percentage": 53.57, "elapsed_time": "0:05:21", "remaining_time": "0:04:39"}
{"current_steps": 16, "total_steps": 28, "loss": 0.3089, "lr": 5.782557337881911e-05, "epoch": 2.2857142857142856, "percentage": 57.14, "elapsed_time": "0:05:44", "remaining_time": "0:04:18"}
{"current_steps": 17, "total_steps": 28, "loss": 0.2729, "lr": 5.2174426621180906e-05, "epoch": 2.4285714285714284, "percentage": 60.71, "elapsed_time": "0:06:06", "remaining_time": "0:03:56"}
{"current_steps": 18, "total_steps": 28, "loss": 0.2858, "lr": 4.6567840843642384e-05, "epoch": 2.571428571428571, "percentage": 64.29, "elapsed_time": "0:06:27", "remaining_time": "0:03:35"}
{"current_steps": 19, "total_steps": 28, "loss": 0.2778, "lr": 4.109423525312738e-05, "epoch": 2.7142857142857144, "percentage": 67.86, "elapsed_time": "0:06:46", "remaining_time": "0:03:12"}
{"current_steps": 20, "total_steps": 28, "loss": 0.2704, "lr": 3.583993187957173e-05, "epoch": 2.857142857142857, "percentage": 71.43, "elapsed_time": "0:07:05", "remaining_time": "0:02:50"}
{"current_steps": 21, "total_steps": 28, "loss": 0.2588, "lr": 3.088779422594514e-05, "epoch": 3.0, "percentage": 75.0, "elapsed_time": "0:07:24", "remaining_time": "0:02:28"}
{"current_steps": 22, "total_steps": 28, "loss": 0.2056, "lr": 2.6315920461308964e-05, "epoch": 3.142857142857143, "percentage": 78.57, "elapsed_time": "0:07:43", "remaining_time": "0:02:06"}
{"current_steps": 23, "total_steps": 28, "loss": 0.1908, "lr": 2.219641176603649e-05, "epoch": 3.2857142857142856, "percentage": 82.14, "elapsed_time": "0:08:02", "remaining_time": "0:01:44"}
{"current_steps": 24, "total_steps": 28, "loss": 0.1778, "lr": 1.8594235253127375e-05, "epoch": 3.4285714285714284, "percentage": 85.71, "elapsed_time": "0:08:22", "remaining_time": "0:01:23"}
{"current_steps": 25, "total_steps": 28, "loss": 0.179, "lr": 1.556619939802615e-05, "epoch": 3.571428571428571, "percentage": 89.29, "elapsed_time": "0:08:42", "remaining_time": "0:01:02"}
{"current_steps": 26, "total_steps": 28, "loss": 0.173, "lr": 1.3160058135028691e-05, "epoch": 3.7142857142857144, "percentage": 92.86, "elapsed_time": "0:09:01", "remaining_time": "0:00:41"}
{"current_steps": 27, "total_steps": 28, "loss": 0.1666, "lr": 1.1413757749211602e-05, "epoch": 3.857142857142857, "percentage": 96.43, "elapsed_time": "0:09:19", "remaining_time": "0:00:20"}
{"current_steps": 28, "total_steps": 28, "loss": 0.1653, "lr": 1.0354838440848503e-05, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:09:38", "remaining_time": "0:00:00"}
{"current_steps": 28, "total_steps": 28, "eval_loss": 0.46450117230415344, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:09:42", "remaining_time": "0:00:00"}
{"current_steps": 28, "total_steps": 28, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:10:19", "remaining_time": "0:00:00"}