agent1 / trainer_log.jsonl
Albert-CAC's picture
Upload folder using huggingface_hub
da0b817 verified
{"current_steps": 5, "total_steps": 111, "loss": 0.7555, "lr": 4.9839963190492576e-05, "epoch": 0.13559322033898305, "percentage": 4.5, "elapsed_time": "0:00:32", "remaining_time": "0:11:36", "throughput": 7817.07, "total_tokens": 256960}
{"current_steps": 10, "total_steps": 111, "loss": 0.4688, "lr": 4.9193323673337476e-05, "epoch": 0.2711864406779661, "percentage": 9.01, "elapsed_time": "0:00:58", "remaining_time": "0:09:50", "throughput": 8901.7, "total_tokens": 520160}
{"current_steps": 15, "total_steps": 111, "loss": 0.4121, "lr": 4.806299712081172e-05, "epoch": 0.4067796610169492, "percentage": 13.51, "elapsed_time": "0:01:23", "remaining_time": "0:08:57", "throughput": 9287.4, "total_tokens": 780072}
{"current_steps": 20, "total_steps": 111, "loss": 0.3846, "lr": 4.647158168051066e-05, "epoch": 0.5423728813559322, "percentage": 18.02, "elapsed_time": "0:01:49", "remaining_time": "0:08:18", "throughput": 9525.22, "total_tokens": 1044392}
{"current_steps": 25, "total_steps": 111, "loss": 0.3815, "lr": 4.445089385796099e-05, "epoch": 0.6779661016949152, "percentage": 22.52, "elapsed_time": "0:02:14", "remaining_time": "0:07:44", "throughput": 9669.2, "total_tokens": 1304776}
{"current_steps": 30, "total_steps": 111, "loss": 0.3832, "lr": 4.204133242248832e-05, "epoch": 0.8135593220338984, "percentage": 27.03, "elapsed_time": "0:02:40", "remaining_time": "0:07:13", "throughput": 9794.67, "total_tokens": 1570800}
{"current_steps": 35, "total_steps": 111, "loss": 0.3741, "lr": 3.929107073146197e-05, "epoch": 0.9491525423728814, "percentage": 31.53, "elapsed_time": "0:03:05", "remaining_time": "0:06:43", "throughput": 9863.82, "total_tokens": 1832200}
{"current_steps": 40, "total_steps": 111, "loss": 0.2731, "lr": 3.6255093620441834e-05, "epoch": 1.0813559322033899, "percentage": 36.04, "elapsed_time": "0:03:30", "remaining_time": "0:06:13", "throughput": 9935.76, "total_tokens": 2090208}
{"current_steps": 45, "total_steps": 111, "loss": 0.1815, "lr": 3.2994098114281134e-05, "epoch": 1.2169491525423728, "percentage": 40.54, "elapsed_time": "0:03:55", "remaining_time": "0:05:45", "throughput": 9987.42, "total_tokens": 2354848}
{"current_steps": 50, "total_steps": 111, "loss": 0.1772, "lr": 2.9573279936809667e-05, "epoch": 1.352542372881356, "percentage": 45.05, "elapsed_time": "0:04:21", "remaining_time": "0:05:18", "throughput": 10010.96, "total_tokens": 2613552}
{"current_steps": 55, "total_steps": 111, "loss": 0.1767, "lr": 2.606103007990371e-05, "epoch": 1.488135593220339, "percentage": 49.55, "elapsed_time": "0:04:46", "remaining_time": "0:04:51", "throughput": 10049.65, "total_tokens": 2880040}
{"current_steps": 60, "total_steps": 111, "loss": 0.1729, "lr": 2.2527567490893758e-05, "epoch": 1.623728813559322, "percentage": 54.05, "elapsed_time": "0:05:12", "remaining_time": "0:04:25", "throughput": 10064.23, "total_tokens": 3141872}
{"current_steps": 65, "total_steps": 111, "loss": 0.1704, "lr": 1.904353521442088e-05, "epoch": 1.759322033898305, "percentage": 58.56, "elapsed_time": "0:05:37", "remaining_time": "0:03:58", "throughput": 10085.85, "total_tokens": 3402088}
{"current_steps": 70, "total_steps": 111, "loss": 0.1628, "lr": 1.567858805549229e-05, "epoch": 1.8949152542372882, "percentage": 63.06, "elapsed_time": "0:06:03", "remaining_time": "0:03:32", "throughput": 10090.28, "total_tokens": 3663008}
{"current_steps": 75, "total_steps": 111, "loss": 0.1438, "lr": 1.2500000000000006e-05, "epoch": 2.0271186440677966, "percentage": 67.57, "elapsed_time": "0:06:27", "remaining_time": "0:03:06", "throughput": 10108.77, "total_tokens": 3918864}
{"current_steps": 80, "total_steps": 111, "loss": 0.0713, "lr": 9.571319233963627e-06, "epoch": 2.1627118644067798, "percentage": 72.07, "elapsed_time": "0:06:53", "remaining_time": "0:02:40", "throughput": 10126.38, "total_tokens": 4183256}
{"current_steps": 85, "total_steps": 111, "loss": 0.0633, "lr": 6.951097651136889e-06, "epoch": 2.298305084745763, "percentage": 76.58, "elapsed_time": "0:07:18", "remaining_time": "0:02:14", "throughput": 10139.14, "total_tokens": 4448016}
{"current_steps": 90, "total_steps": 111, "loss": 0.0599, "lr": 4.691720249402856e-06, "epoch": 2.4338983050847456, "percentage": 81.08, "elapsed_time": "0:07:44", "remaining_time": "0:01:48", "throughput": 10132.39, "total_tokens": 4701808}
{"current_steps": 95, "total_steps": 111, "loss": 0.0574, "lr": 2.8383578193475315e-06, "epoch": 2.5694915254237287, "percentage": 85.59, "elapsed_time": "0:08:09", "remaining_time": "0:01:22", "throughput": 10133.63, "total_tokens": 4960648}
{"current_steps": 100, "total_steps": 111, "loss": 0.0534, "lr": 1.428063863472895e-06, "epoch": 2.705084745762712, "percentage": 90.09, "elapsed_time": "0:08:34", "remaining_time": "0:00:56", "throughput": 10144.55, "total_tokens": 5224432}
{"current_steps": 105, "total_steps": 111, "loss": 0.0536, "lr": 4.890338009668316e-07, "epoch": 2.840677966101695, "percentage": 94.59, "elapsed_time": "0:12:34", "remaining_time": "0:00:43", "throughput": 7270.79, "total_tokens": 5489120}
{"current_steps": 110, "total_steps": 111, "loss": 0.0559, "lr": 4.004126844042444e-08, "epoch": 2.976271186440678, "percentage": 99.1, "elapsed_time": "0:13:00", "remaining_time": "0:00:07", "throughput": 7369.91, "total_tokens": 5751896}
{"current_steps": 111, "total_steps": 111, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:15:33", "remaining_time": "0:00:00", "throughput": 6210.35, "total_tokens": 5798376}