question_generation_1.5B_model / trainer_log.jsonl
tokhey's picture
Training in progress, step 114
97bd105 verified
{"current_steps": 5, "total_steps": 114, "loss": 0.9293, "lr": 0.00016666666666666666, "epoch": 0.13333333333333333, "percentage": 4.39, "elapsed_time": "0:00:49", "remaining_time": "0:17:57"}
{"current_steps": 10, "total_steps": 114, "loss": 0.8556, "lr": 0.000375, "epoch": 0.26666666666666666, "percentage": 8.77, "elapsed_time": "0:01:36", "remaining_time": "0:16:48"}
{"current_steps": 15, "total_steps": 114, "loss": 0.8414, "lr": 0.0004995258321842611, "epoch": 0.4, "percentage": 13.16, "elapsed_time": "0:02:26", "remaining_time": "0:16:03"}
{"current_steps": 20, "total_steps": 114, "loss": 0.7606, "lr": 0.0004942120794399002, "epoch": 0.5333333333333333, "percentage": 17.54, "elapsed_time": "0:03:13", "remaining_time": "0:15:11"}
{"current_steps": 25, "total_steps": 114, "loss": 0.7522, "lr": 0.00048311805735108893, "epoch": 0.6666666666666666, "percentage": 21.93, "elapsed_time": "0:04:01", "remaining_time": "0:14:19"}
{"current_steps": 30, "total_steps": 114, "loss": 0.7444, "lr": 0.00046650635094610973, "epoch": 0.8, "percentage": 26.32, "elapsed_time": "0:04:49", "remaining_time": "0:13:29"}
{"current_steps": 35, "total_steps": 114, "loss": 0.6762, "lr": 0.0004447701436314176, "epoch": 0.9333333333333333, "percentage": 30.7, "elapsed_time": "0:05:37", "remaining_time": "0:12:40"}
{"current_steps": 40, "total_steps": 114, "loss": 0.7014, "lr": 0.0004184239109116393, "epoch": 1.0533333333333332, "percentage": 35.09, "elapsed_time": "0:06:20", "remaining_time": "0:11:43"}
{"current_steps": 45, "total_steps": 114, "loss": 0.6655, "lr": 0.00038809124324012647, "epoch": 1.1866666666666668, "percentage": 39.47, "elapsed_time": "0:07:11", "remaining_time": "0:11:01"}
{"current_steps": 50, "total_steps": 114, "loss": 0.6315, "lr": 0.00035449008622169586, "epoch": 1.32, "percentage": 43.86, "elapsed_time": "0:07:59", "remaining_time": "0:10:13"}
{"current_steps": 55, "total_steps": 114, "loss": 0.6525, "lr": 0.0003184157475180208, "epoch": 1.4533333333333334, "percentage": 48.25, "elapsed_time": "0:08:46", "remaining_time": "0:09:25"}
{"current_steps": 60, "total_steps": 114, "loss": 0.6398, "lr": 0.00028072207266617854, "epoch": 1.5866666666666667, "percentage": 52.63, "elapsed_time": "0:09:34", "remaining_time": "0:08:37"}
{"current_steps": 65, "total_steps": 114, "loss": 0.6836, "lr": 0.00024230123536095747, "epoch": 1.72, "percentage": 57.02, "elapsed_time": "0:10:22", "remaining_time": "0:07:49"}
{"current_steps": 70, "total_steps": 114, "loss": 0.6227, "lr": 0.0002040626205458574, "epoch": 1.8533333333333335, "percentage": 61.4, "elapsed_time": "0:11:10", "remaining_time": "0:07:01"}
{"current_steps": 75, "total_steps": 114, "loss": 0.6343, "lr": 0.00016691130013008512, "epoch": 1.9866666666666668, "percentage": 65.79, "elapsed_time": "0:11:58", "remaining_time": "0:06:13"}
{"current_steps": 80, "total_steps": 114, "loss": 0.6193, "lr": 0.0001317266107909975, "epoch": 2.1066666666666665, "percentage": 70.18, "elapsed_time": "0:12:41", "remaining_time": "0:05:23"}
{"current_steps": 85, "total_steps": 114, "loss": 0.5563, "lr": 9.934134090518593e-05, "epoch": 2.24, "percentage": 74.56, "elapsed_time": "0:13:36", "remaining_time": "0:04:38"}
{"current_steps": 90, "total_steps": 114, "loss": 0.5774, "lr": 7.052201923388955e-05, "epoch": 2.3733333333333335, "percentage": 78.95, "elapsed_time": "0:14:24", "remaining_time": "0:03:50"}
{"current_steps": 95, "total_steps": 114, "loss": 0.5472, "lr": 4.59507719109446e-05, "epoch": 2.506666666666667, "percentage": 83.33, "elapsed_time": "0:15:11", "remaining_time": "0:03:02"}
{"current_steps": 100, "total_steps": 114, "loss": 0.5133, "lr": 2.6209177161234443e-05, "epoch": 2.64, "percentage": 87.72, "elapsed_time": "0:15:59", "remaining_time": "0:02:14"}
{"current_steps": 100, "total_steps": 114, "eval_loss": 0.8378572463989258, "epoch": 2.64, "percentage": 87.72, "elapsed_time": "0:16:05", "remaining_time": "0:02:15"}
{"current_steps": 105, "total_steps": 114, "loss": 0.5179, "lr": 1.1764499893210877e-05, "epoch": 2.7733333333333334, "percentage": 92.11, "elapsed_time": "0:16:53", "remaining_time": "0:01:26"}
{"current_steps": 110, "total_steps": 114, "loss": 0.525, "lr": 2.9586319796851556e-06, "epoch": 2.9066666666666667, "percentage": 96.49, "elapsed_time": "0:17:41", "remaining_time": "0:00:38"}
{"current_steps": 114, "total_steps": 114, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:18:18", "remaining_time": "0:00:00"}