BS2-riche-lora / trainer_log.jsonl
jpraysz's picture
Upload 20 files
9df2023 verified
{"current_steps": 5, "total_steps": 195, "loss": 0.2783, "lr": 4.9918932703355256e-05, "epoch": 0.0761904761904762, "percentage": 2.56, "elapsed_time": "0:01:35", "remaining_time": "1:00:12", "throughput": 2222.37, "total_tokens": 211280}
{"current_steps": 10, "total_steps": 195, "loss": 0.1989, "lr": 4.967625656594782e-05, "epoch": 0.1523809523809524, "percentage": 5.13, "elapsed_time": "0:03:11", "remaining_time": "0:58:53", "throughput": 2194.13, "total_tokens": 419136}
{"current_steps": 15, "total_steps": 195, "loss": 0.1331, "lr": 4.92735454356513e-05, "epoch": 0.22857142857142856, "percentage": 7.69, "elapsed_time": "0:04:51", "remaining_time": "0:58:16", "throughput": 2167.74, "total_tokens": 631632}
{"current_steps": 20, "total_steps": 195, "loss": 0.1029, "lr": 4.8713411048678635e-05, "epoch": 0.3047619047619048, "percentage": 10.26, "elapsed_time": "0:06:27", "remaining_time": "0:56:30", "throughput": 2159.97, "total_tokens": 836896}
{"current_steps": 25, "total_steps": 195, "loss": 0.08, "lr": 4.799948609147061e-05, "epoch": 0.38095238095238093, "percentage": 12.82, "elapsed_time": "0:08:03", "remaining_time": "0:54:48", "throughput": 2155.84, "total_tokens": 1042416}
{"current_steps": 30, "total_steps": 195, "loss": 0.0767, "lr": 4.713640064133025e-05, "epoch": 0.45714285714285713, "percentage": 15.38, "elapsed_time": "0:09:38", "remaining_time": "0:53:01", "throughput": 2151.49, "total_tokens": 1244384}
{"current_steps": 35, "total_steps": 195, "loss": 0.0596, "lr": 4.6129752138594874e-05, "epoch": 0.5333333333333333, "percentage": 17.95, "elapsed_time": "0:11:10", "remaining_time": "0:51:06", "throughput": 2154.2, "total_tokens": 1445168}
{"current_steps": 40, "total_steps": 195, "loss": 0.0619, "lr": 4.498606908508754e-05, "epoch": 0.6095238095238096, "percentage": 20.51, "elapsed_time": "0:12:47", "remaining_time": "0:49:34", "throughput": 2151.53, "total_tokens": 1651760}
{"current_steps": 45, "total_steps": 195, "loss": 0.0585, "lr": 4.371276870427753e-05, "epoch": 0.6857142857142857, "percentage": 23.08, "elapsed_time": "0:14:18", "remaining_time": "0:47:41", "throughput": 2154.83, "total_tokens": 1849920}
{"current_steps": 50, "total_steps": 195, "loss": 0.0642, "lr": 4.231810883773999e-05, "epoch": 0.7619047619047619, "percentage": 25.64, "elapsed_time": "0:15:55", "remaining_time": "0:46:11", "throughput": 2151.56, "total_tokens": 2056592}
{"current_steps": 55, "total_steps": 195, "loss": 0.053, "lr": 4.0811134389884433e-05, "epoch": 0.8380952380952381, "percentage": 28.21, "elapsed_time": "0:17:32", "remaining_time": "0:44:39", "throughput": 2151.91, "total_tokens": 2265056}
{"current_steps": 60, "total_steps": 195, "loss": 0.0566, "lr": 3.920161866827889e-05, "epoch": 0.9142857142857143, "percentage": 30.77, "elapsed_time": "0:19:08", "remaining_time": "0:43:04", "throughput": 2151.74, "total_tokens": 2471328}
{"current_steps": 65, "total_steps": 195, "loss": 0.0496, "lr": 3.7500000000000003e-05, "epoch": 0.9904761904761905, "percentage": 33.33, "elapsed_time": "0:20:43", "remaining_time": "0:41:26", "throughput": 2152.63, "total_tokens": 2676640}
{"current_steps": 70, "total_steps": 195, "loss": 0.0577, "lr": 3.5717314035076355e-05, "epoch": 1.0761904761904761, "percentage": 35.9, "elapsed_time": "0:22:26", "remaining_time": "0:40:05", "throughput": 2151.34, "total_tokens": 2897712}
{"current_steps": 75, "total_steps": 195, "loss": 0.0442, "lr": 3.386512217606339e-05, "epoch": 1.1523809523809523, "percentage": 38.46, "elapsed_time": "0:23:53", "remaining_time": "0:38:12", "throughput": 2155.99, "total_tokens": 3089808}
{"current_steps": 80, "total_steps": 195, "loss": 0.0469, "lr": 3.195543659791132e-05, "epoch": 1.2285714285714286, "percentage": 41.03, "elapsed_time": "0:25:31", "remaining_time": "0:36:41", "throughput": 2152.47, "total_tokens": 3296576}
{"current_steps": 85, "total_steps": 195, "loss": 0.0417, "lr": 3.0000642344401113e-05, "epoch": 1.3047619047619048, "percentage": 43.59, "elapsed_time": "0:27:10", "remaining_time": "0:35:10", "throughput": 2151.23, "total_tokens": 3508416}
{"current_steps": 90, "total_steps": 195, "loss": 0.0451, "lr": 2.8013417006383076e-05, "epoch": 1.380952380952381, "percentage": 46.15, "elapsed_time": "0:28:42", "remaining_time": "0:33:29", "throughput": 2151.68, "total_tokens": 3706512}
{"current_steps": 95, "total_steps": 195, "loss": 0.0438, "lr": 2.600664850273538e-05, "epoch": 1.457142857142857, "percentage": 48.72, "elapsed_time": "0:30:19", "remaining_time": "0:31:55", "throughput": 2150.08, "total_tokens": 3913120}
{"current_steps": 100, "total_steps": 195, "loss": 0.038, "lr": 2.399335149726463e-05, "epoch": 1.5333333333333332, "percentage": 51.28, "elapsed_time": "0:31:57", "remaining_time": "0:30:21", "throughput": 2149.01, "total_tokens": 4121248}
{"current_steps": 105, "total_steps": 195, "loss": 0.038, "lr": 2.1986582993616926e-05, "epoch": 1.6095238095238096, "percentage": 53.85, "elapsed_time": "0:33:38", "remaining_time": "0:28:49", "throughput": 2144.53, "total_tokens": 4327824}
{"current_steps": 110, "total_steps": 195, "loss": 0.0397, "lr": 1.9999357655598893e-05, "epoch": 1.6857142857142857, "percentage": 56.41, "elapsed_time": "0:35:17", "remaining_time": "0:27:16", "throughput": 2142.88, "total_tokens": 4537936}
{"current_steps": 115, "total_steps": 195, "loss": 0.0404, "lr": 1.8044563402088684e-05, "epoch": 1.7619047619047619, "percentage": 58.97, "elapsed_time": "0:36:54", "remaining_time": "0:25:40", "throughput": 2142.72, "total_tokens": 4744432}
{"current_steps": 120, "total_steps": 195, "loss": 0.0362, "lr": 1.613487782393661e-05, "epoch": 1.8380952380952382, "percentage": 61.54, "elapsed_time": "0:38:32", "remaining_time": "0:24:05", "throughput": 2142.84, "total_tokens": 4955296}
{"current_steps": 125, "total_steps": 195, "loss": 0.0397, "lr": 1.4282685964923642e-05, "epoch": 1.9142857142857141, "percentage": 64.1, "elapsed_time": "0:40:02", "remaining_time": "0:22:25", "throughput": 2145.15, "total_tokens": 5154784}
{"current_steps": 130, "total_steps": 195, "loss": 0.0343, "lr": 1.2500000000000006e-05, "epoch": 1.9904761904761905, "percentage": 66.67, "elapsed_time": "0:41:36", "remaining_time": "0:20:48", "throughput": 2146.04, "total_tokens": 5358160}
{"current_steps": 135, "total_steps": 195, "loss": 0.0396, "lr": 1.0798381331721109e-05, "epoch": 2.0761904761904764, "percentage": 69.23, "elapsed_time": "0:43:19", "remaining_time": "0:19:15", "throughput": 2145.8, "total_tokens": 5577808}
{"current_steps": 140, "total_steps": 195, "loss": 0.0394, "lr": 9.18886561011557e-06, "epoch": 2.1523809523809523, "percentage": 71.79, "elapsed_time": "0:44:49", "remaining_time": "0:17:36", "throughput": 2147.67, "total_tokens": 5775552}
{"current_steps": 145, "total_steps": 195, "loss": 0.0311, "lr": 7.681891162260015e-06, "epoch": 2.2285714285714286, "percentage": 74.36, "elapsed_time": "0:46:29", "remaining_time": "0:16:01", "throughput": 2146.29, "total_tokens": 5986112}
{"current_steps": 150, "total_steps": 195, "loss": 0.048, "lr": 6.28723129572247e-06, "epoch": 2.3047619047619046, "percentage": 76.92, "elapsed_time": "0:48:00", "remaining_time": "0:14:24", "throughput": 2147.33, "total_tokens": 6185568}
{"current_steps": 155, "total_steps": 195, "loss": 0.0374, "lr": 5.013930914912476e-06, "epoch": 2.380952380952381, "percentage": 79.49, "elapsed_time": "0:49:34", "remaining_time": "0:12:47", "throughput": 2148.07, "total_tokens": 6389392}
{"current_steps": 160, "total_steps": 195, "loss": 0.0334, "lr": 3.8702478614051355e-06, "epoch": 2.4571428571428573, "percentage": 82.05, "elapsed_time": "0:51:09", "remaining_time": "0:11:11", "throughput": 2148.53, "total_tokens": 6594256}
{"current_steps": 165, "total_steps": 195, "loss": 0.0324, "lr": 2.8635993586697553e-06, "epoch": 2.533333333333333, "percentage": 84.62, "elapsed_time": "0:52:45", "remaining_time": "0:09:35", "throughput": 2148.97, "total_tokens": 6802240}
{"current_steps": 170, "total_steps": 195, "loss": 0.0342, "lr": 2.0005139085293945e-06, "epoch": 2.6095238095238096, "percentage": 87.18, "elapsed_time": "0:54:19", "remaining_time": "0:07:59", "throughput": 2149.31, "total_tokens": 7004816}
{"current_steps": 175, "total_steps": 195, "loss": 0.0384, "lr": 1.286588951321363e-06, "epoch": 2.685714285714286, "percentage": 89.74, "elapsed_time": "0:55:53", "remaining_time": "0:06:23", "throughput": 2149.34, "total_tokens": 7208608}
{"current_steps": 180, "total_steps": 195, "loss": 0.0357, "lr": 7.264545643486997e-07, "epoch": 2.761904761904762, "percentage": 92.31, "elapsed_time": "0:57:33", "remaining_time": "0:04:47", "throughput": 2148.19, "total_tokens": 7418320}
{"current_steps": 185, "total_steps": 195, "loss": 0.0351, "lr": 3.237434340521789e-07, "epoch": 2.8380952380952382, "percentage": 94.87, "elapsed_time": "0:59:17", "remaining_time": "0:03:12", "throughput": 2145.47, "total_tokens": 7633248}
{"current_steps": 190, "total_steps": 195, "loss": 0.0324, "lr": 8.106729664475176e-08, "epoch": 2.914285714285714, "percentage": 97.44, "elapsed_time": "1:00:52", "remaining_time": "0:01:36", "throughput": 2146.04, "total_tokens": 7838576}
{"current_steps": 195, "total_steps": 195, "loss": 0.0357, "lr": 0.0, "epoch": 2.9904761904761905, "percentage": 100.0, "elapsed_time": "1:02:25", "remaining_time": "0:00:00", "throughput": 2146.55, "total_tokens": 8039616}
{"current_steps": 195, "total_steps": 195, "epoch": 2.9904761904761905, "percentage": 100.0, "elapsed_time": "1:02:26", "remaining_time": "0:00:00", "throughput": 2145.93, "total_tokens": 8039616}