BS-riche-Qwen2.5-lora-2 / trainer_log.jsonl
jpraysz's picture
Upload 20 files
620b87d verified
{"current_steps": 5, "total_steps": 195, "loss": 0.3151, "lr": 4.9918932703355256e-05, "epoch": 0.0761904761904762, "percentage": 2.56, "elapsed_time": "0:02:48", "remaining_time": "1:46:36", "throughput": 1255.09, "total_tokens": 211280}
{"current_steps": 10, "total_steps": 195, "loss": 0.2406, "lr": 4.967625656594782e-05, "epoch": 0.1523809523809524, "percentage": 5.13, "elapsed_time": "0:05:24", "remaining_time": "1:39:59", "throughput": 1292.42, "total_tokens": 419136}
{"current_steps": 15, "total_steps": 195, "loss": 0.1707, "lr": 4.92735454356513e-05, "epoch": 0.22857142857142856, "percentage": 7.69, "elapsed_time": "0:08:10", "remaining_time": "1:38:08", "throughput": 1287.26, "total_tokens": 631632}
{"current_steps": 20, "total_steps": 195, "loss": 0.1223, "lr": 4.8713411048678635e-05, "epoch": 0.3047619047619048, "percentage": 10.26, "elapsed_time": "0:10:48", "remaining_time": "1:34:35", "throughput": 1290.33, "total_tokens": 836896}
{"current_steps": 25, "total_steps": 195, "loss": 0.0945, "lr": 4.799948609147061e-05, "epoch": 0.38095238095238093, "percentage": 12.82, "elapsed_time": "0:13:29", "remaining_time": "1:31:45", "throughput": 1287.55, "total_tokens": 1042416}
{"current_steps": 30, "total_steps": 195, "loss": 0.0874, "lr": 4.713640064133025e-05, "epoch": 0.45714285714285713, "percentage": 15.38, "elapsed_time": "0:16:06", "remaining_time": "1:28:36", "throughput": 1287.33, "total_tokens": 1244384}
{"current_steps": 35, "total_steps": 195, "loss": 0.0631, "lr": 4.6129752138594874e-05, "epoch": 0.5333333333333333, "percentage": 17.95, "elapsed_time": "0:18:37", "remaining_time": "1:25:10", "throughput": 1292.66, "total_tokens": 1445168}
{"current_steps": 40, "total_steps": 195, "loss": 0.0786, "lr": 4.498606908508754e-05, "epoch": 0.6095238095238096, "percentage": 20.51, "elapsed_time": "0:21:19", "remaining_time": "1:22:37", "throughput": 1291.15, "total_tokens": 1651760}
{"current_steps": 45, "total_steps": 195, "loss": 0.0628, "lr": 4.371276870427753e-05, "epoch": 0.6857142857142857, "percentage": 23.08, "elapsed_time": "0:23:45", "remaining_time": "1:19:12", "throughput": 1297.62, "total_tokens": 1849920}
{"current_steps": 50, "total_steps": 195, "loss": 0.0712, "lr": 4.231810883773999e-05, "epoch": 0.7619047619047619, "percentage": 25.64, "elapsed_time": "0:26:26", "remaining_time": "1:16:41", "throughput": 1296.17, "total_tokens": 2056592}
{"current_steps": 55, "total_steps": 195, "loss": 0.059, "lr": 4.0811134389884433e-05, "epoch": 0.8380952380952381, "percentage": 28.21, "elapsed_time": "0:29:04", "remaining_time": "1:13:59", "throughput": 1298.59, "total_tokens": 2265056}
{"current_steps": 60, "total_steps": 195, "loss": 0.0635, "lr": 3.920161866827889e-05, "epoch": 0.9142857142857143, "percentage": 30.77, "elapsed_time": "0:31:37", "remaining_time": "1:11:09", "throughput": 1302.47, "total_tokens": 2471328}
{"current_steps": 65, "total_steps": 195, "loss": 0.058, "lr": 3.7500000000000003e-05, "epoch": 0.9904761904761905, "percentage": 33.33, "elapsed_time": "0:33:52", "remaining_time": "1:07:45", "throughput": 1316.89, "total_tokens": 2676640}
{"current_steps": 70, "total_steps": 195, "loss": 0.0693, "lr": 3.5717314035076355e-05, "epoch": 1.0761904761904761, "percentage": 35.9, "elapsed_time": "0:36:18", "remaining_time": "1:04:50", "throughput": 1330.04, "total_tokens": 2897712}
{"current_steps": 75, "total_steps": 195, "loss": 0.0537, "lr": 3.386512217606339e-05, "epoch": 1.1523809523809523, "percentage": 38.46, "elapsed_time": "0:38:16", "remaining_time": "1:01:14", "throughput": 1345.47, "total_tokens": 3089808}
{"current_steps": 80, "total_steps": 195, "loss": 0.0547, "lr": 3.195543659791132e-05, "epoch": 1.2285714285714286, "percentage": 41.03, "elapsed_time": "0:40:38", "remaining_time": "0:58:25", "throughput": 1351.94, "total_tokens": 3296576}
{"current_steps": 85, "total_steps": 195, "loss": 0.0446, "lr": 3.0000642344401113e-05, "epoch": 1.3047619047619048, "percentage": 43.59, "elapsed_time": "0:43:01", "remaining_time": "0:55:40", "throughput": 1359.21, "total_tokens": 3508416}
{"current_steps": 90, "total_steps": 195, "loss": 0.0535, "lr": 2.8013417006383076e-05, "epoch": 1.380952380952381, "percentage": 46.15, "elapsed_time": "0:45:11", "remaining_time": "0:52:43", "throughput": 1366.99, "total_tokens": 3706512}
{"current_steps": 95, "total_steps": 195, "loss": 0.049, "lr": 2.600664850273538e-05, "epoch": 1.457142857142857, "percentage": 48.72, "elapsed_time": "0:47:33", "remaining_time": "0:50:03", "throughput": 1371.57, "total_tokens": 3913120}
{"current_steps": 100, "total_steps": 195, "loss": 0.0438, "lr": 2.399335149726463e-05, "epoch": 1.5333333333333332, "percentage": 51.28, "elapsed_time": "0:49:54", "remaining_time": "0:47:24", "throughput": 1376.4, "total_tokens": 4121248}
{"current_steps": 105, "total_steps": 195, "loss": 0.0474, "lr": 2.1986582993616926e-05, "epoch": 1.6095238095238096, "percentage": 53.85, "elapsed_time": "0:52:12", "remaining_time": "0:44:44", "throughput": 1381.66, "total_tokens": 4327824}
{"current_steps": 110, "total_steps": 195, "loss": 0.0443, "lr": 1.9999357655598893e-05, "epoch": 1.6857142857142857, "percentage": 56.41, "elapsed_time": "0:54:36", "remaining_time": "0:42:11", "throughput": 1384.98, "total_tokens": 4537936}
{"current_steps": 115, "total_steps": 195, "loss": 0.0429, "lr": 1.8044563402088684e-05, "epoch": 1.7619047619047619, "percentage": 58.97, "elapsed_time": "0:56:59", "remaining_time": "0:39:38", "throughput": 1387.43, "total_tokens": 4744432}
{"current_steps": 120, "total_steps": 195, "loss": 0.0421, "lr": 1.613487782393661e-05, "epoch": 1.8380952380952382, "percentage": 61.54, "elapsed_time": "0:59:41", "remaining_time": "0:37:18", "throughput": 1383.54, "total_tokens": 4955296}
{"current_steps": 125, "total_steps": 195, "loss": 0.0438, "lr": 1.4282685964923642e-05, "epoch": 1.9142857142857141, "percentage": 64.1, "elapsed_time": "1:02:06", "remaining_time": "0:34:46", "throughput": 1383.17, "total_tokens": 5154784}
{"current_steps": 130, "total_steps": 195, "loss": 0.0387, "lr": 1.2500000000000006e-05, "epoch": 1.9904761904761905, "percentage": 66.67, "elapsed_time": "1:04:40", "remaining_time": "0:32:20", "throughput": 1380.84, "total_tokens": 5358160}
{"current_steps": 135, "total_steps": 195, "loss": 0.0462, "lr": 1.0798381331721109e-05, "epoch": 2.0761904761904764, "percentage": 69.23, "elapsed_time": "1:07:30", "remaining_time": "0:30:00", "throughput": 1377.02, "total_tokens": 5577808}
{"current_steps": 140, "total_steps": 195, "loss": 0.0455, "lr": 9.18886561011557e-06, "epoch": 2.1523809523809523, "percentage": 71.79, "elapsed_time": "1:09:56", "remaining_time": "0:27:28", "throughput": 1376.25, "total_tokens": 5775552}
{"current_steps": 145, "total_steps": 195, "loss": 0.0389, "lr": 7.681891162260015e-06, "epoch": 2.2285714285714286, "percentage": 74.36, "elapsed_time": "1:12:44", "remaining_time": "0:25:05", "throughput": 1371.5, "total_tokens": 5986112}
{"current_steps": 150, "total_steps": 195, "loss": 0.0505, "lr": 6.28723129572247e-06, "epoch": 2.3047619047619046, "percentage": 76.92, "elapsed_time": "1:15:12", "remaining_time": "0:22:33", "throughput": 1370.67, "total_tokens": 6185568}
{"current_steps": 155, "total_steps": 195, "loss": 0.0469, "lr": 5.013930914912476e-06, "epoch": 2.380952380952381, "percentage": 79.49, "elapsed_time": "1:17:46", "remaining_time": "0:20:04", "throughput": 1369.24, "total_tokens": 6389392}
{"current_steps": 160, "total_steps": 195, "loss": 0.0382, "lr": 3.8702478614051355e-06, "epoch": 2.4571428571428573, "percentage": 82.05, "elapsed_time": "1:20:23", "remaining_time": "0:17:35", "throughput": 1367.19, "total_tokens": 6594256}
{"current_steps": 165, "total_steps": 195, "loss": 0.0359, "lr": 2.8635993586697553e-06, "epoch": 2.533333333333333, "percentage": 84.62, "elapsed_time": "1:23:00", "remaining_time": "0:15:05", "throughput": 1365.78, "total_tokens": 6802240}
{"current_steps": 170, "total_steps": 195, "loss": 0.0379, "lr": 2.0005139085293945e-06, "epoch": 2.6095238095238096, "percentage": 87.18, "elapsed_time": "1:25:32", "remaining_time": "0:12:34", "throughput": 1364.75, "total_tokens": 7004816}
{"current_steps": 175, "total_steps": 195, "loss": 0.0416, "lr": 1.286588951321363e-06, "epoch": 2.685714285714286, "percentage": 89.74, "elapsed_time": "1:28:10", "remaining_time": "0:10:04", "throughput": 1362.63, "total_tokens": 7208608}
{"current_steps": 180, "total_steps": 195, "loss": 0.0394, "lr": 7.264545643486997e-07, "epoch": 2.761904761904762, "percentage": 92.31, "elapsed_time": "1:30:56", "remaining_time": "0:07:34", "throughput": 1359.56, "total_tokens": 7418320}
{"current_steps": 185, "total_steps": 195, "loss": 0.0421, "lr": 3.237434340521789e-07, "epoch": 2.8380952380952382, "percentage": 94.87, "elapsed_time": "1:33:56", "remaining_time": "0:05:04", "throughput": 1354.2, "total_tokens": 7633248}
{"current_steps": 190, "total_steps": 195, "loss": 0.0377, "lr": 8.106729664475176e-08, "epoch": 2.914285714285714, "percentage": 97.44, "elapsed_time": "1:36:32", "remaining_time": "0:02:32", "throughput": 1353.29, "total_tokens": 7838576}
{"current_steps": 195, "total_steps": 195, "loss": 0.0468, "lr": 0.0, "epoch": 2.9904761904761905, "percentage": 100.0, "elapsed_time": "1:39:04", "remaining_time": "0:00:00", "throughput": 1352.45, "total_tokens": 8039616}
{"current_steps": 195, "total_steps": 195, "epoch": 2.9904761904761905, "percentage": 100.0, "elapsed_time": "1:39:05", "remaining_time": "0:00:00", "throughput": 1352.21, "total_tokens": 8039616}