M3-quantized-qlora-4bit / trainer_log.jsonl
bziemba's picture
Upload folder using huggingface_hub
5e1e986 verified
{"current_steps": 20, "total_steps": 375, "loss": 2.4397, "lr": 5e-05, "epoch": 0.16, "percentage": 5.33, "elapsed_time": "0:00:52", "remaining_time": "0:15:33"}
{"current_steps": 40, "total_steps": 375, "loss": 2.2225, "lr": 9.999782741484788e-05, "epoch": 0.32, "percentage": 10.67, "elapsed_time": "0:01:44", "remaining_time": "0:14:34"}
{"current_steps": 60, "total_steps": 375, "loss": 1.9769, "lr": 9.904493906342123e-05, "epoch": 0.48, "percentage": 16.0, "elapsed_time": "0:02:36", "remaining_time": "0:13:40"}
{"current_steps": 80, "total_steps": 375, "loss": 1.8957, "lr": 9.639210244594334e-05, "epoch": 0.64, "percentage": 21.33, "elapsed_time": "0:03:28", "remaining_time": "0:12:48"}
{"current_steps": 100, "total_steps": 375, "loss": 1.9327, "lr": 9.213126762075088e-05, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:04:20", "remaining_time": "0:11:55"}
{"current_steps": 120, "total_steps": 375, "loss": 1.902, "lr": 8.641011952560371e-05, "epoch": 0.96, "percentage": 32.0, "elapsed_time": "0:05:12", "remaining_time": "0:11:03"}
{"current_steps": 140, "total_steps": 375, "loss": 1.8109, "lr": 7.94269590651393e-05, "epoch": 1.12, "percentage": 37.33, "elapsed_time": "0:06:04", "remaining_time": "0:10:12"}
{"current_steps": 160, "total_steps": 375, "loss": 1.7861, "lr": 7.142382979661386e-05, "epoch": 1.28, "percentage": 42.67, "elapsed_time": "0:06:56", "remaining_time": "0:09:19"}
{"current_steps": 180, "total_steps": 375, "loss": 1.8054, "lr": 6.26781284501043e-05, "epoch": 1.44, "percentage": 48.0, "elapsed_time": "0:07:48", "remaining_time": "0:08:27"}
{"current_steps": 200, "total_steps": 375, "loss": 1.7685, "lr": 5.3492990071209806e-05, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:08:40", "remaining_time": "0:07:35"}
{"current_steps": 220, "total_steps": 375, "loss": 1.8407, "lr": 4.418678104714214e-05, "epoch": 1.76, "percentage": 58.67, "elapsed_time": "0:09:32", "remaining_time": "0:06:43"}
{"current_steps": 240, "total_steps": 375, "loss": 1.7761, "lr": 3.5082064198777e-05, "epoch": 1.92, "percentage": 64.0, "elapsed_time": "0:10:24", "remaining_time": "0:05:51"}
{"current_steps": 260, "total_steps": 375, "loss": 1.7177, "lr": 2.6494418419978482e-05, "epoch": 2.08, "percentage": 69.33, "elapsed_time": "0:11:16", "remaining_time": "0:04:59"}
{"current_steps": 280, "total_steps": 375, "loss": 1.6397, "lr": 1.872150038705015e-05, "epoch": 2.24, "percentage": 74.67, "elapsed_time": "0:12:08", "remaining_time": "0:04:07"}
{"current_steps": 300, "total_steps": 375, "loss": 1.7622, "lr": 1.203272747076598e-05, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "0:13:00", "remaining_time": "0:03:15"}
{"current_steps": 320, "total_steps": 375, "loss": 1.6719, "lr": 6.659939451910341e-06, "epoch": 2.56, "percentage": 85.33, "elapsed_time": "0:13:52", "remaining_time": "0:02:23"}
{"current_steps": 340, "total_steps": 375, "loss": 1.6602, "lr": 2.7893627149161716e-06, "epoch": 2.7199999999999998, "percentage": 90.67, "elapsed_time": "0:14:43", "remaining_time": "0:01:30"}
{"current_steps": 360, "total_steps": 375, "loss": 1.7036, "lr": 5.551554489528432e-07, "epoch": 2.88, "percentage": 96.0, "elapsed_time": "0:15:35", "remaining_time": "0:00:38"}
{"current_steps": 375, "total_steps": 375, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:16:15", "remaining_time": "0:00:00"}