Files
Llama3.2-3B_Paper_Impact_pa…/trainer_log.jsonl

30 lines
5.4 KiB
Plaintext
Raw Normal View History

{"current_steps": 5, "total_steps": 144, "loss": 0.0934, "lr": 5.333333333333334e-06, "epoch": 0.034904013961605584, "percentage": 3.47, "elapsed_time": "0:00:37", "remaining_time": "0:17:32"}
{"current_steps": 10, "total_steps": 144, "loss": 0.0773, "lr": 1.2e-05, "epoch": 0.06980802792321117, "percentage": 6.94, "elapsed_time": "0:01:13", "remaining_time": "0:16:28"}
{"current_steps": 15, "total_steps": 144, "loss": 0.0711, "lr": 1.866666666666667e-05, "epoch": 0.10471204188481675, "percentage": 10.42, "elapsed_time": "0:01:51", "remaining_time": "0:16:01"}
{"current_steps": 20, "total_steps": 144, "loss": 0.0736, "lr": 1.995259033893236e-05, "epoch": 0.13961605584642234, "percentage": 13.89, "elapsed_time": "0:02:29", "remaining_time": "0:15:26"}
{"current_steps": 25, "total_steps": 144, "loss": 0.0697, "lr": 1.9760758775559275e-05, "epoch": 0.17452006980802792, "percentage": 17.36, "elapsed_time": "0:03:07", "remaining_time": "0:14:52"}
{"current_steps": 30, "total_steps": 144, "loss": 0.0699, "lr": 1.9424380828337146e-05, "epoch": 0.2094240837696335, "percentage": 20.83, "elapsed_time": "0:03:45", "remaining_time": "0:14:16"}
{"current_steps": 35, "total_steps": 144, "loss": 0.0697, "lr": 1.894843789440892e-05, "epoch": 0.2443280977312391, "percentage": 24.31, "elapsed_time": "0:04:22", "remaining_time": "0:13:38"}
{"current_steps": 40, "total_steps": 144, "loss": 0.0695, "lr": 1.833997817889878e-05, "epoch": 0.2792321116928447, "percentage": 27.78, "elapsed_time": "0:05:00", "remaining_time": "0:13:02"}
{"current_steps": 45, "total_steps": 144, "loss": 0.07, "lr": 1.760801231854278e-05, "epoch": 0.31413612565445026, "percentage": 31.25, "elapsed_time": "0:05:38", "remaining_time": "0:12:23"}
{"current_steps": 50, "total_steps": 144, "loss": 0.0701, "lr": 1.676337994380903e-05, "epoch": 0.34904013961605584, "percentage": 34.72, "elapsed_time": "0:06:15", "remaining_time": "0:11:45"}
{"current_steps": 55, "total_steps": 144, "loss": 0.0698, "lr": 1.581858915557953e-05, "epoch": 0.38394415357766143, "percentage": 38.19, "elapsed_time": "0:06:52", "remaining_time": "0:11:08"}
{"current_steps": 60, "total_steps": 144, "loss": 0.0699, "lr": 1.4787631293572094e-05, "epoch": 0.418848167539267, "percentage": 41.67, "elapsed_time": "0:07:31", "remaining_time": "0:10:32"}
{"current_steps": 65, "total_steps": 144, "loss": 0.0695, "lr": 1.368577373958362e-05, "epoch": 0.4537521815008726, "percentage": 45.14, "elapsed_time": "0:08:10", "remaining_time": "0:09:56"}
{"current_steps": 70, "total_steps": 144, "loss": 0.0696, "lr": 1.2529333823916807e-05, "epoch": 0.4886561954624782, "percentage": 48.61, "elapsed_time": "0:08:48", "remaining_time": "0:09:19"}
{"current_steps": 75, "total_steps": 144, "loss": 0.0713, "lr": 1.133543718319398e-05, "epoch": 0.5235602094240838, "percentage": 52.08, "elapsed_time": "0:09:26", "remaining_time": "0:08:41"}
{"current_steps": 80, "total_steps": 144, "loss": 0.0696, "lr": 1.0121764148019977e-05, "epoch": 0.5584642233856894, "percentage": 55.56, "elapsed_time": "0:10:03", "remaining_time": "0:08:03"}
{"current_steps": 85, "total_steps": 144, "loss": 0.0696, "lr": 8.906287916221259e-06, "epoch": 0.5933682373472949, "percentage": 59.03, "elapsed_time": "0:10:41", "remaining_time": "0:07:25"}
{"current_steps": 90, "total_steps": 144, "loss": 0.0699, "lr": 7.707008389035102e-06, "epoch": 0.6282722513089005, "percentage": 62.5, "elapsed_time": "0:11:19", "remaining_time": "0:06:47"}
{"current_steps": 95, "total_steps": 144, "loss": 0.0697, "lr": 6.5416856118498874e-06, "epoch": 0.6631762652705061, "percentage": 65.97, "elapsed_time": "0:11:57", "remaining_time": "0:06:10"}
{"current_steps": 100, "total_steps": 144, "loss": 0.0697, "lr": 5.427576766953615e-06, "epoch": 0.6980802792321117, "percentage": 69.44, "elapsed_time": "0:12:34", "remaining_time": "0:05:32"}
{"current_steps": 105, "total_steps": 144, "loss": 0.0695, "lr": 4.381180613146396e-06, "epoch": 0.7329842931937173, "percentage": 72.92, "elapsed_time": "0:13:12", "remaining_time": "0:04:54"}
{"current_steps": 110, "total_steps": 144, "loss": 0.0694, "lr": 3.4179931567925216e-06, "epoch": 0.7678883071553229, "percentage": 76.39, "elapsed_time": "0:13:48", "remaining_time": "0:04:16"}
{"current_steps": 115, "total_steps": 144, "loss": 0.0694, "lr": 2.5522781725621814e-06, "epoch": 0.8027923211169284, "percentage": 79.86, "elapsed_time": "0:14:27", "remaining_time": "0:03:38"}
{"current_steps": 120, "total_steps": 144, "loss": 0.0692, "lr": 1.7968559722048906e-06, "epoch": 0.837696335078534, "percentage": 83.33, "elapsed_time": "0:15:05", "remaining_time": "0:03:01"}
{"current_steps": 125, "total_steps": 144, "loss": 0.0696, "lr": 1.1629135494628097e-06, "epoch": 0.8726003490401396, "percentage": 86.81, "elapsed_time": "0:15:44", "remaining_time": "0:02:23"}
{"current_steps": 130, "total_steps": 144, "loss": 0.0695, "lr": 6.598389126745209e-07, "epoch": 0.9075043630017452, "percentage": 90.28, "elapsed_time": "0:16:22", "remaining_time": "0:01:45"}
{"current_steps": 135, "total_steps": 144, "loss": 0.0695, "lr": 2.9508205842594727e-07, "epoch": 0.9424083769633508, "percentage": 93.75, "elapsed_time": "0:17:00", "remaining_time": "0:01:08"}
{"current_steps": 140, "total_steps": 144, "loss": 0.0693, "lr": 7.404464507973608e-08, "epoch": 0.9773123909249564, "percentage": 97.22, "elapsed_time": "0:17:38", "remaining_time": "0:00:30"}
{"current_steps": 144, "total_steps": 144, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:18:31", "remaining_time": "0:00:00"}