lora_0-3_3B / trainer_log.jsonl
gulaschnascher4000's picture
Training in progress, step 555
7585bc4 verified
{"current_steps": 10, "total_steps": 555, "loss": 3.0329, "lr": 1.785714285714286e-05, "epoch": 0.009009009009009009, "percentage": 1.8, "elapsed_time": "0:00:08", "remaining_time": "0:07:51"}
{"current_steps": 20, "total_steps": 555, "loss": 2.963, "lr": 3.571428571428572e-05, "epoch": 0.018018018018018018, "percentage": 3.6, "elapsed_time": "0:00:16", "remaining_time": "0:07:08"}
{"current_steps": 30, "total_steps": 555, "loss": 2.5483, "lr": 5.3571428571428575e-05, "epoch": 0.02702702702702703, "percentage": 5.41, "elapsed_time": "0:00:23", "remaining_time": "0:06:47"}
{"current_steps": 40, "total_steps": 555, "loss": 2.2173, "lr": 7.142857142857143e-05, "epoch": 0.036036036036036036, "percentage": 7.21, "elapsed_time": "0:00:30", "remaining_time": "0:06:35"}
{"current_steps": 50, "total_steps": 555, "loss": 2.0999, "lr": 8.92857142857143e-05, "epoch": 0.04504504504504504, "percentage": 9.01, "elapsed_time": "0:00:38", "remaining_time": "0:06:28"}
{"current_steps": 60, "total_steps": 555, "loss": 2.065, "lr": 9.998414611537681e-05, "epoch": 0.05405405405405406, "percentage": 10.81, "elapsed_time": "0:00:45", "remaining_time": "0:06:19"}
{"current_steps": 70, "total_steps": 555, "loss": 2.0001, "lr": 9.980590535514233e-05, "epoch": 0.06306306306306306, "percentage": 12.61, "elapsed_time": "0:00:53", "remaining_time": "0:06:12"}
{"current_steps": 80, "total_steps": 555, "loss": 1.9977, "lr": 9.943031509146825e-05, "epoch": 0.07207207207207207, "percentage": 14.41, "elapsed_time": "0:01:01", "remaining_time": "0:06:03"}
{"current_steps": 90, "total_steps": 555, "loss": 2.0185, "lr": 9.885886355253758e-05, "epoch": 0.08108108108108109, "percentage": 16.22, "elapsed_time": "0:01:08", "remaining_time": "0:05:55"}
{"current_steps": 100, "total_steps": 555, "loss": 1.9265, "lr": 9.809381504168234e-05, "epoch": 0.09009009009009009, "percentage": 18.02, "elapsed_time": "0:01:16", "remaining_time": "0:05:46"}
{"current_steps": 110, "total_steps": 555, "loss": 1.9129, "lr": 9.713820096537225e-05, "epoch": 0.0990990990990991, "percentage": 19.82, "elapsed_time": "0:01:23", "remaining_time": "0:05:38"}
{"current_steps": 120, "total_steps": 555, "loss": 1.9642, "lr": 9.599580782165598e-05, "epoch": 0.10810810810810811, "percentage": 21.62, "elapsed_time": "0:01:30", "remaining_time": "0:05:29"}
{"current_steps": 130, "total_steps": 555, "loss": 1.9043, "lr": 9.467116219664894e-05, "epoch": 0.11711711711711711, "percentage": 23.42, "elapsed_time": "0:01:38", "remaining_time": "0:05:21"}
{"current_steps": 140, "total_steps": 555, "loss": 1.8833, "lr": 9.316951282851707e-05, "epoch": 0.12612612612612611, "percentage": 25.23, "elapsed_time": "0:01:45", "remaining_time": "0:05:13"}
{"current_steps": 150, "total_steps": 555, "loss": 1.9395, "lr": 9.149680981002609e-05, "epoch": 0.13513513513513514, "percentage": 27.03, "elapsed_time": "0:01:53", "remaining_time": "0:05:05"}
{"current_steps": 160, "total_steps": 555, "loss": 1.8237, "lr": 8.965968101206291e-05, "epoch": 0.14414414414414414, "percentage": 28.83, "elapsed_time": "0:02:00", "remaining_time": "0:04:57"}
{"current_steps": 170, "total_steps": 555, "loss": 1.9039, "lr": 8.766540582154859e-05, "epoch": 0.15315315315315314, "percentage": 30.63, "elapsed_time": "0:02:08", "remaining_time": "0:04:50"}
{"current_steps": 180, "total_steps": 555, "loss": 1.8434, "lr": 8.552188629780244e-05, "epoch": 0.16216216216216217, "percentage": 32.43, "elapsed_time": "0:02:15", "remaining_time": "0:04:42"}
{"current_steps": 190, "total_steps": 555, "loss": 1.8668, "lr": 8.323761586164695e-05, "epoch": 0.17117117117117117, "percentage": 34.23, "elapsed_time": "0:02:23", "remaining_time": "0:04:35"}
{"current_steps": 200, "total_steps": 555, "loss": 1.8238, "lr": 8.082164564131845e-05, "epoch": 0.18018018018018017, "percentage": 36.04, "elapsed_time": "0:02:31", "remaining_time": "0:04:28"}
{"current_steps": 210, "total_steps": 555, "loss": 1.8616, "lr": 7.828354860853399e-05, "epoch": 0.1891891891891892, "percentage": 37.84, "elapsed_time": "0:02:38", "remaining_time": "0:04:20"}
{"current_steps": 220, "total_steps": 555, "loss": 1.795, "lr": 7.563338164682036e-05, "epoch": 0.1981981981981982, "percentage": 39.64, "elapsed_time": "0:02:45", "remaining_time": "0:04:12"}
{"current_steps": 230, "total_steps": 555, "loss": 1.7992, "lr": 7.288164570240463e-05, "epoch": 0.2072072072072072, "percentage": 41.44, "elapsed_time": "0:02:53", "remaining_time": "0:04:05"}
{"current_steps": 240, "total_steps": 555, "loss": 1.7634, "lr": 7.003924417556343e-05, "epoch": 0.21621621621621623, "percentage": 43.24, "elapsed_time": "0:03:01", "remaining_time": "0:03:58"}
{"current_steps": 250, "total_steps": 555, "loss": 1.796, "lr": 6.711743971729967e-05, "epoch": 0.22522522522522523, "percentage": 45.05, "elapsed_time": "0:03:08", "remaining_time": "0:03:50"}
{"current_steps": 260, "total_steps": 555, "loss": 1.839, "lr": 6.412780960253436e-05, "epoch": 0.23423423423423423, "percentage": 46.85, "elapsed_time": "0:03:16", "remaining_time": "0:03:42"}
{"current_steps": 270, "total_steps": 555, "loss": 1.8259, "lr": 6.108219985664161e-05, "epoch": 0.24324324324324326, "percentage": 48.65, "elapsed_time": "0:03:23", "remaining_time": "0:03:34"}
{"current_steps": 280, "total_steps": 555, "loss": 1.7566, "lr": 5.799267831709442e-05, "epoch": 0.25225225225225223, "percentage": 50.45, "elapsed_time": "0:03:30", "remaining_time": "0:03:27"}
{"current_steps": 290, "total_steps": 555, "loss": 1.7795, "lr": 5.487148681620862e-05, "epoch": 0.26126126126126126, "percentage": 52.25, "elapsed_time": "0:03:38", "remaining_time": "0:03:19"}
{"current_steps": 300, "total_steps": 555, "loss": 1.7507, "lr": 5.173099267445451e-05, "epoch": 0.2702702702702703, "percentage": 54.05, "elapsed_time": "0:03:46", "remaining_time": "0:03:12"}
{"current_steps": 310, "total_steps": 555, "loss": 1.7462, "lr": 4.858363969653781e-05, "epoch": 0.27927927927927926, "percentage": 55.86, "elapsed_time": "0:03:53", "remaining_time": "0:03:04"}
{"current_steps": 320, "total_steps": 555, "loss": 1.8059, "lr": 4.544189886442162e-05, "epoch": 0.2882882882882883, "percentage": 57.66, "elapsed_time": "0:04:00", "remaining_time": "0:02:56"}
{"current_steps": 330, "total_steps": 555, "loss": 1.7456, "lr": 4.23182189226621e-05, "epoch": 0.2972972972972973, "percentage": 59.46, "elapsed_time": "0:04:08", "remaining_time": "0:02:49"}
{"current_steps": 340, "total_steps": 555, "loss": 1.7294, "lr": 3.9224977051856904e-05, "epoch": 0.3063063063063063, "percentage": 61.26, "elapsed_time": "0:04:15", "remaining_time": "0:02:41"}
{"current_steps": 350, "total_steps": 555, "loss": 1.7287, "lr": 3.6174429825656685e-05, "epoch": 0.3153153153153153, "percentage": 63.06, "elapsed_time": "0:04:22", "remaining_time": "0:02:33"}
{"current_steps": 360, "total_steps": 555, "loss": 1.7555, "lr": 3.3178664645666066e-05, "epoch": 0.32432432432432434, "percentage": 64.86, "elapsed_time": "0:04:30", "remaining_time": "0:02:26"}
{"current_steps": 370, "total_steps": 555, "loss": 1.7149, "lr": 3.0249551846667207e-05, "epoch": 0.3333333333333333, "percentage": 66.67, "elapsed_time": "0:04:38", "remaining_time": "0:02:19"}
{"current_steps": 380, "total_steps": 555, "loss": 1.7532, "lr": 2.739869766194263e-05, "epoch": 0.34234234234234234, "percentage": 68.47, "elapsed_time": "0:04:45", "remaining_time": "0:02:11"}
{"current_steps": 390, "total_steps": 555, "loss": 1.6948, "lr": 2.4637398235066527e-05, "epoch": 0.35135135135135137, "percentage": 70.27, "elapsed_time": "0:04:52", "remaining_time": "0:02:03"}
{"current_steps": 400, "total_steps": 555, "loss": 1.7533, "lr": 2.1976594860386597e-05, "epoch": 0.36036036036036034, "percentage": 72.07, "elapsed_time": "0:05:00", "remaining_time": "0:01:56"}
{"current_steps": 410, "total_steps": 555, "loss": 1.7752, "lr": 1.9426830629550242e-05, "epoch": 0.36936936936936937, "percentage": 73.87, "elapsed_time": "0:05:07", "remaining_time": "0:01:48"}
{"current_steps": 420, "total_steps": 555, "loss": 1.7286, "lr": 1.6998208655858137e-05, "epoch": 0.3783783783783784, "percentage": 75.68, "elapsed_time": "0:05:15", "remaining_time": "0:01:41"}
{"current_steps": 430, "total_steps": 555, "loss": 1.7331, "lr": 1.4700352041975168e-05, "epoch": 0.38738738738738737, "percentage": 77.48, "elapsed_time": "0:05:22", "remaining_time": "0:01:33"}
{"current_steps": 440, "total_steps": 555, "loss": 1.7582, "lr": 1.2542365749622049e-05, "epoch": 0.3963963963963964, "percentage": 79.28, "elapsed_time": "0:05:29", "remaining_time": "0:01:26"}
{"current_steps": 450, "total_steps": 555, "loss": 1.6628, "lr": 1.0532800522333902e-05, "epoch": 0.40540540540540543, "percentage": 81.08, "elapsed_time": "0:05:37", "remaining_time": "0:01:18"}
{"current_steps": 460, "total_steps": 555, "loss": 1.6957, "lr": 8.67961900423711e-06, "epoch": 0.4144144144144144, "percentage": 82.88, "elapsed_time": "0:05:45", "remaining_time": "0:01:11"}
{"current_steps": 470, "total_steps": 555, "loss": 1.7118, "lr": 6.990164189094589e-06, "epoch": 0.42342342342342343, "percentage": 84.68, "elapsed_time": "0:05:52", "remaining_time": "0:01:03"}
{"current_steps": 480, "total_steps": 555, "loss": 1.6488, "lr": 5.4711303246361144e-06, "epoch": 0.43243243243243246, "percentage": 86.49, "elapsed_time": "0:06:00", "remaining_time": "0:00:56"}
{"current_steps": 490, "total_steps": 555, "loss": 1.6793, "lr": 4.12853638746134e-06, "epoch": 0.44144144144144143, "percentage": 88.29, "elapsed_time": "0:06:07", "remaining_time": "0:00:48"}
{"current_steps": 500, "total_steps": 555, "loss": 1.6649, "lr": 2.9677022336181413e-06, "epoch": 0.45045045045045046, "percentage": 90.09, "elapsed_time": "0:06:15", "remaining_time": "0:00:41"}
{"current_steps": 500, "total_steps": 555, "eval_loss": 1.7574011087417603, "epoch": 0.45045045045045046, "percentage": 90.09, "elapsed_time": "0:07:06", "remaining_time": "0:00:46"}
{"current_steps": 510, "total_steps": 555, "loss": 1.7905, "lr": 1.993227519356189e-06, "epoch": 0.4594594594594595, "percentage": 91.89, "elapsed_time": "0:07:13", "remaining_time": "0:00:38"}
{"current_steps": 520, "total_steps": 555, "loss": 1.7358, "lr": 1.208973475579761e-06, "epoch": 0.46846846846846846, "percentage": 93.69, "elapsed_time": "0:07:21", "remaining_time": "0:00:29"}
{"current_steps": 530, "total_steps": 555, "loss": 1.7079, "lr": 6.180476082162656e-07, "epoch": 0.4774774774774775, "percentage": 95.5, "elapsed_time": "0:07:29", "remaining_time": "0:00:21"}
{"current_steps": 540, "total_steps": 555, "loss": 1.6984, "lr": 2.2279138512300567e-07, "epoch": 0.4864864864864865, "percentage": 97.3, "elapsed_time": "0:07:36", "remaining_time": "0:00:12"}
{"current_steps": 550, "total_steps": 555, "loss": 1.637, "lr": 2.4770958321568283e-08, "epoch": 0.4954954954954955, "percentage": 99.1, "elapsed_time": "0:07:43", "remaining_time": "0:00:04"}
{"current_steps": 555, "total_steps": 555, "epoch": 0.5, "percentage": 100.0, "elapsed_time": "0:07:48", "remaining_time": "0:00:00"}