Fine-R1-3B-Stage1 / trainer_log.jsonl
StevenHH2000's picture
Upload 19 files
ab217d5 verified
{"current_steps": 1, "total_steps": 60, "loss": 1.2032, "lr": 8.333333333333333e-07, "epoch": 0.15384615384615385, "percentage": 1.67, "elapsed_time": "0:00:51", "remaining_time": "0:50:26"}
{"current_steps": 2, "total_steps": 60, "loss": 1.2132, "lr": 1.6666666666666667e-06, "epoch": 0.3076923076923077, "percentage": 3.33, "elapsed_time": "0:01:18", "remaining_time": "0:38:09"}
{"current_steps": 3, "total_steps": 60, "loss": 1.2137, "lr": 2.5e-06, "epoch": 0.46153846153846156, "percentage": 5.0, "elapsed_time": "0:01:44", "remaining_time": "0:32:57"}
{"current_steps": 4, "total_steps": 60, "loss": 1.1822, "lr": 3.3333333333333333e-06, "epoch": 0.6153846153846154, "percentage": 6.67, "elapsed_time": "0:02:10", "remaining_time": "0:30:20"}
{"current_steps": 5, "total_steps": 60, "loss": 1.2146, "lr": 4.166666666666667e-06, "epoch": 0.7692307692307693, "percentage": 8.33, "elapsed_time": "0:02:41", "remaining_time": "0:29:36"}
{"current_steps": 6, "total_steps": 60, "loss": 1.1544, "lr": 5e-06, "epoch": 0.9230769230769231, "percentage": 10.0, "elapsed_time": "0:03:09", "remaining_time": "0:28:25"}
{"current_steps": 7, "total_steps": 60, "loss": 0.5766, "lr": 4.995770395678171e-06, "epoch": 1.0, "percentage": 11.67, "elapsed_time": "0:03:28", "remaining_time": "0:26:19"}
{"current_steps": 8, "total_steps": 60, "loss": 1.1065, "lr": 4.983095894354858e-06, "epoch": 1.1538461538461537, "percentage": 13.33, "elapsed_time": "0:03:55", "remaining_time": "0:25:33"}
{"current_steps": 9, "total_steps": 60, "loss": 1.0679, "lr": 4.962019382530521e-06, "epoch": 1.3076923076923077, "percentage": 15.0, "elapsed_time": "0:04:25", "remaining_time": "0:25:04"}
{"current_steps": 10, "total_steps": 60, "loss": 1.0155, "lr": 4.93261217644956e-06, "epoch": 1.4615384615384617, "percentage": 16.67, "elapsed_time": "0:04:56", "remaining_time": "0:24:43"}
{"current_steps": 11, "total_steps": 60, "loss": 1.0063, "lr": 4.894973780788722e-06, "epoch": 1.6153846153846154, "percentage": 18.33, "elapsed_time": "0:05:25", "remaining_time": "0:24:08"}
{"current_steps": 12, "total_steps": 60, "loss": 0.9441, "lr": 4.849231551964771e-06, "epoch": 1.7692307692307692, "percentage": 20.0, "elapsed_time": "0:05:52", "remaining_time": "0:23:30"}
{"current_steps": 13, "total_steps": 60, "loss": 0.9214, "lr": 4.7955402672006855e-06, "epoch": 1.9230769230769231, "percentage": 21.67, "elapsed_time": "0:06:18", "remaining_time": "0:22:46"}
{"current_steps": 14, "total_steps": 60, "loss": 0.4572, "lr": 4.734081600808531e-06, "epoch": 2.0, "percentage": 23.33, "elapsed_time": "0:06:34", "remaining_time": "0:21:35"}
{"current_steps": 15, "total_steps": 60, "loss": 0.8955, "lr": 4.665063509461098e-06, "epoch": 2.1538461538461537, "percentage": 25.0, "elapsed_time": "0:07:03", "remaining_time": "0:21:10"}
{"current_steps": 16, "total_steps": 60, "loss": 0.8693, "lr": 4.588719528532342e-06, "epoch": 2.3076923076923075, "percentage": 26.67, "elapsed_time": "0:07:32", "remaining_time": "0:20:43"}
{"current_steps": 17, "total_steps": 60, "loss": 0.841, "lr": 4.50530798188761e-06, "epoch": 2.4615384615384617, "percentage": 28.33, "elapsed_time": "0:08:15", "remaining_time": "0:20:52"}
{"current_steps": 18, "total_steps": 60, "loss": 0.8152, "lr": 4.415111107797445e-06, "epoch": 2.6153846153846154, "percentage": 30.0, "elapsed_time": "0:08:47", "remaining_time": "0:20:31"}
{"current_steps": 19, "total_steps": 60, "loss": 0.7768, "lr": 4.318434103932622e-06, "epoch": 2.769230769230769, "percentage": 31.67, "elapsed_time": "0:09:14", "remaining_time": "0:19:56"}
{"current_steps": 20, "total_steps": 60, "loss": 0.7846, "lr": 4.215604094671835e-06, "epoch": 2.9230769230769234, "percentage": 33.33, "elapsed_time": "0:09:39", "remaining_time": "0:19:19"}
{"current_steps": 21, "total_steps": 60, "loss": 0.3778, "lr": 4.106969024216348e-06, "epoch": 3.0, "percentage": 35.0, "elapsed_time": "0:10:00", "remaining_time": "0:18:35"}
{"current_steps": 22, "total_steps": 60, "loss": 0.7495, "lr": 3.992896479256966e-06, "epoch": 3.1538461538461537, "percentage": 36.67, "elapsed_time": "0:10:32", "remaining_time": "0:18:12"}
{"current_steps": 23, "total_steps": 60, "loss": 0.7175, "lr": 3.8737724451770155e-06, "epoch": 3.3076923076923075, "percentage": 38.33, "elapsed_time": "0:11:16", "remaining_time": "0:18:08"}
{"current_steps": 24, "total_steps": 60, "loss": 0.7281, "lr": 3.7500000000000005e-06, "epoch": 3.4615384615384617, "percentage": 40.0, "elapsed_time": "0:11:48", "remaining_time": "0:17:42"}
{"current_steps": 25, "total_steps": 60, "loss": 0.7187, "lr": 3.621997950501156e-06, "epoch": 3.6153846153846154, "percentage": 41.67, "elapsed_time": "0:12:19", "remaining_time": "0:17:14"}
{"current_steps": 26, "total_steps": 60, "loss": 0.7123, "lr": 3.4901994150978926e-06, "epoch": 3.769230769230769, "percentage": 43.33, "elapsed_time": "0:13:00", "remaining_time": "0:17:00"}
{"current_steps": 27, "total_steps": 60, "loss": 0.7025, "lr": 3.3550503583141726e-06, "epoch": 3.9230769230769234, "percentage": 45.0, "elapsed_time": "0:13:30", "remaining_time": "0:16:31"}
{"current_steps": 28, "total_steps": 60, "loss": 0.3284, "lr": 3.217008081777726e-06, "epoch": 4.0, "percentage": 46.67, "elapsed_time": "0:13:56", "remaining_time": "0:15:56"}
{"current_steps": 29, "total_steps": 60, "loss": 0.6758, "lr": 3.0765396768561005e-06, "epoch": 4.153846153846154, "percentage": 48.33, "elapsed_time": "0:14:27", "remaining_time": "0:15:27"}
{"current_steps": 30, "total_steps": 60, "loss": 0.6794, "lr": 2.9341204441673267e-06, "epoch": 4.3076923076923075, "percentage": 50.0, "elapsed_time": "0:15:02", "remaining_time": "0:15:02"}
{"current_steps": 31, "total_steps": 60, "loss": 0.6446, "lr": 2.7902322853130758e-06, "epoch": 4.461538461538462, "percentage": 51.67, "elapsed_time": "0:17:03", "remaining_time": "0:15:57"}
{"current_steps": 32, "total_steps": 60, "loss": 0.67, "lr": 2.6453620722761897e-06, "epoch": 4.615384615384615, "percentage": 53.33, "elapsed_time": "0:17:41", "remaining_time": "0:15:28"}
{"current_steps": 33, "total_steps": 60, "loss": 0.636, "lr": 2.5e-06, "epoch": 4.769230769230769, "percentage": 55.0, "elapsed_time": "0:18:51", "remaining_time": "0:15:25"}
{"current_steps": 34, "total_steps": 60, "loss": 0.6559, "lr": 2.3546379277238107e-06, "epoch": 4.923076923076923, "percentage": 56.67, "elapsed_time": "0:19:59", "remaining_time": "0:15:17"}
{"current_steps": 35, "total_steps": 60, "loss": 0.3249, "lr": 2.2097677146869242e-06, "epoch": 5.0, "percentage": 58.33, "elapsed_time": "0:20:17", "remaining_time": "0:14:29"}
{"current_steps": 36, "total_steps": 60, "loss": 0.6344, "lr": 2.0658795558326745e-06, "epoch": 5.153846153846154, "percentage": 60.0, "elapsed_time": "0:21:06", "remaining_time": "0:14:04"}
{"current_steps": 37, "total_steps": 60, "loss": 0.6334, "lr": 1.9234603231439e-06, "epoch": 5.3076923076923075, "percentage": 61.67, "elapsed_time": "0:21:38", "remaining_time": "0:13:27"}
{"current_steps": 38, "total_steps": 60, "loss": 0.6159, "lr": 1.7829919182222752e-06, "epoch": 5.461538461538462, "percentage": 63.33, "elapsed_time": "0:22:23", "remaining_time": "0:12:57"}
{"current_steps": 39, "total_steps": 60, "loss": 0.6194, "lr": 1.6449496416858285e-06, "epoch": 5.615384615384615, "percentage": 65.0, "elapsed_time": "0:22:50", "remaining_time": "0:12:18"}
{"current_steps": 40, "total_steps": 60, "loss": 0.6215, "lr": 1.509800584902108e-06, "epoch": 5.769230769230769, "percentage": 66.67, "elapsed_time": "0:23:23", "remaining_time": "0:11:41"}
{"current_steps": 41, "total_steps": 60, "loss": 0.6164, "lr": 1.3780020494988447e-06, "epoch": 5.923076923076923, "percentage": 68.33, "elapsed_time": "0:24:08", "remaining_time": "0:11:11"}
{"current_steps": 42, "total_steps": 60, "loss": 0.306, "lr": 1.2500000000000007e-06, "epoch": 6.0, "percentage": 70.0, "elapsed_time": "0:24:21", "remaining_time": "0:10:26"}
{"current_steps": 43, "total_steps": 60, "loss": 0.6098, "lr": 1.1262275548229852e-06, "epoch": 6.153846153846154, "percentage": 71.67, "elapsed_time": "0:24:54", "remaining_time": "0:09:50"}
{"current_steps": 44, "total_steps": 60, "loss": 0.5961, "lr": 1.0071035207430352e-06, "epoch": 6.3076923076923075, "percentage": 73.33, "elapsed_time": "0:25:26", "remaining_time": "0:09:14"}
{"current_steps": 45, "total_steps": 60, "loss": 0.5896, "lr": 8.930309757836517e-07, "epoch": 6.461538461538462, "percentage": 75.0, "elapsed_time": "0:25:55", "remaining_time": "0:08:38"}
{"current_steps": 46, "total_steps": 60, "loss": 0.6085, "lr": 7.843959053281663e-07, "epoch": 6.615384615384615, "percentage": 76.67, "elapsed_time": "0:26:21", "remaining_time": "0:08:01"}
{"current_steps": 47, "total_steps": 60, "loss": 0.6024, "lr": 6.815658960673782e-07, "epoch": 6.769230769230769, "percentage": 78.33, "elapsed_time": "0:26:48", "remaining_time": "0:07:24"}
{"current_steps": 48, "total_steps": 60, "loss": 0.5954, "lr": 5.848888922025553e-07, "epoch": 6.923076923076923, "percentage": 80.0, "elapsed_time": "0:27:18", "remaining_time": "0:06:49"}
{"current_steps": 49, "total_steps": 60, "loss": 0.2997, "lr": 4.946920181123904e-07, "epoch": 7.0, "percentage": 81.67, "elapsed_time": "0:27:37", "remaining_time": "0:06:12"}
{"current_steps": 50, "total_steps": 60, "loss": 0.5838, "lr": 4.1128047146765936e-07, "epoch": 7.153846153846154, "percentage": 83.33, "elapsed_time": "0:28:05", "remaining_time": "0:05:37"}
{"current_steps": 51, "total_steps": 60, "loss": 0.5993, "lr": 3.3493649053890325e-07, "epoch": 7.3076923076923075, "percentage": 85.0, "elapsed_time": "0:28:34", "remaining_time": "0:05:02"}
{"current_steps": 52, "total_steps": 60, "loss": 0.5908, "lr": 2.6591839919146963e-07, "epoch": 7.461538461538462, "percentage": 86.67, "elapsed_time": "0:29:09", "remaining_time": "0:04:29"}
{"current_steps": 53, "total_steps": 60, "loss": 0.5756, "lr": 2.044597327993153e-07, "epoch": 7.615384615384615, "percentage": 88.33, "elapsed_time": "0:29:41", "remaining_time": "0:03:55"}
{"current_steps": 54, "total_steps": 60, "loss": 0.6084, "lr": 1.507684480352292e-07, "epoch": 7.769230769230769, "percentage": 90.0, "elapsed_time": "0:30:20", "remaining_time": "0:03:22"}
{"current_steps": 55, "total_steps": 60, "loss": 0.5859, "lr": 1.0502621921127776e-07, "epoch": 7.923076923076923, "percentage": 91.67, "elapsed_time": "0:30:47", "remaining_time": "0:02:47"}
{"current_steps": 56, "total_steps": 60, "loss": 0.2892, "lr": 6.738782355044048e-08, "epoch": 8.0, "percentage": 93.33, "elapsed_time": "0:31:03", "remaining_time": "0:02:13"}
{"current_steps": 57, "total_steps": 60, "loss": 0.586, "lr": 3.798061746947995e-08, "epoch": 8.153846153846153, "percentage": 95.0, "elapsed_time": "0:31:30", "remaining_time": "0:01:39"}
{"current_steps": 58, "total_steps": 60, "loss": 0.5827, "lr": 1.6904105645142443e-08, "epoch": 8.307692307692308, "percentage": 96.67, "elapsed_time": "0:31:55", "remaining_time": "0:01:06"}
{"current_steps": 59, "total_steps": 60, "loss": 0.5837, "lr": 4.229604321829561e-09, "epoch": 8.461538461538462, "percentage": 98.33, "elapsed_time": "0:32:26", "remaining_time": "0:00:32"}
{"current_steps": 60, "total_steps": 60, "loss": 0.5892, "lr": 0.0, "epoch": 8.615384615384615, "percentage": 100.0, "elapsed_time": "0:32:59", "remaining_time": "0:00:00"}
{"current_steps": 60, "total_steps": 60, "epoch": 8.615384615384615, "percentage": 100.0, "elapsed_time": "0:33:57", "remaining_time": "0:00:00"}
{"current_steps": 61, "total_steps": 120, "loss": 0.6829, "lr": 2.637719400889664e-06, "epoch": 5.078431372549019, "percentage": 50.83, "elapsed_time": "0:00:35", "remaining_time": "0:00:34"}
{"current_steps": 62, "total_steps": 120, "loss": 0.6898, "lr": 2.5688858559204056e-06, "epoch": 5.1568627450980395, "percentage": 51.67, "elapsed_time": "0:01:04", "remaining_time": "0:01:00"}
{"current_steps": 63, "total_steps": 120, "loss": 0.6957, "lr": 2.5e-06, "epoch": 5.235294117647059, "percentage": 52.5, "elapsed_time": "0:01:25", "remaining_time": "0:01:17"}
{"current_steps": 64, "total_steps": 120, "loss": 0.6916, "lr": 2.4311141440795956e-06, "epoch": 5.313725490196078, "percentage": 53.33, "elapsed_time": "0:01:47", "remaining_time": "0:01:34"}
{"current_steps": 65, "total_steps": 120, "loss": 0.6901, "lr": 2.362280599110336e-06, "epoch": 5.392156862745098, "percentage": 54.17, "elapsed_time": "0:02:14", "remaining_time": "0:01:53"}
{"current_steps": 66, "total_steps": 120, "loss": 0.6779, "lr": 2.2935516363191695e-06, "epoch": 5.470588235294118, "percentage": 55.0, "elapsed_time": "0:02:43", "remaining_time": "0:02:13"}
{"current_steps": 67, "total_steps": 120, "loss": 0.6761, "lr": 2.224979447514802e-06, "epoch": 5.549019607843137, "percentage": 55.83, "elapsed_time": "0:03:08", "remaining_time": "0:02:29"}
{"current_steps": 68, "total_steps": 120, "loss": 0.687, "lr": 2.1566161054539797e-06, "epoch": 5.627450980392156, "percentage": 56.67, "elapsed_time": "0:03:33", "remaining_time": "0:02:43"}
{"current_steps": 69, "total_steps": 120, "loss": 0.6596, "lr": 2.088513524298165e-06, "epoch": 5.705882352941177, "percentage": 57.5, "elapsed_time": "0:04:00", "remaining_time": "0:02:58"}
{"current_steps": 70, "total_steps": 120, "loss": 0.6802, "lr": 2.0207234201906546e-06, "epoch": 5.784313725490196, "percentage": 58.33, "elapsed_time": "0:04:27", "remaining_time": "0:03:11"}
{"current_steps": 71, "total_steps": 120, "loss": 0.6745, "lr": 1.953297271984061e-06, "epoch": 5.862745098039216, "percentage": 59.17, "elapsed_time": "0:04:56", "remaining_time": "0:03:24"}
{"current_steps": 72, "total_steps": 120, "loss": 0.6509, "lr": 1.8862862821480023e-06, "epoch": 5.9411764705882355, "percentage": 60.0, "elapsed_time": "0:05:24", "remaining_time": "0:03:36"}
{"current_steps": 73, "total_steps": 120, "loss": 0.5203, "lr": 1.819741337886662e-06, "epoch": 6.0, "percentage": 60.83, "elapsed_time": "0:05:42", "remaining_time": "0:03:40"}
{"current_steps": 74, "total_steps": 120, "loss": 0.6479, "lr": 1.7537129724957644e-06, "epoch": 6.078431372549019, "percentage": 61.67, "elapsed_time": "0:06:14", "remaining_time": "0:03:52"}
{"current_steps": 75, "total_steps": 120, "loss": 0.6729, "lr": 1.6882513269882916e-06, "epoch": 6.1568627450980395, "percentage": 62.5, "elapsed_time": "0:06:38", "remaining_time": "0:03:59"}
{"current_steps": 76, "total_steps": 120, "loss": 0.6316, "lr": 1.6234061120181144e-06, "epoch": 6.235294117647059, "percentage": 63.33, "elapsed_time": "0:07:05", "remaining_time": "0:04:06"}
{"current_steps": 77, "total_steps": 120, "loss": 0.6517, "lr": 1.5592265701304116e-06, "epoch": 6.313725490196078, "percentage": 64.17, "elapsed_time": "0:07:31", "remaining_time": "0:04:12"}
{"current_steps": 78, "total_steps": 120, "loss": 0.6377, "lr": 1.495761438367577e-06, "epoch": 6.392156862745098, "percentage": 65.0, "elapsed_time": "0:07:57", "remaining_time": "0:04:16"}
{"current_steps": 79, "total_steps": 120, "loss": 0.6377, "lr": 1.433058911258991e-06, "epoch": 6.470588235294118, "percentage": 65.83, "elapsed_time": "0:08:25", "remaining_time": "0:04:22"}
{"current_steps": 80, "total_steps": 120, "loss": 0.633, "lr": 1.3711666042227772e-06, "epoch": 6.549019607843137, "percentage": 66.67, "elapsed_time": "0:08:49", "remaining_time": "0:04:24"}
{"current_steps": 81, "total_steps": 120, "loss": 0.6106, "lr": 1.3101315174073162e-06, "epoch": 6.627450980392156, "percentage": 67.5, "elapsed_time": "0:09:18", "remaining_time": "0:04:28"}
{"current_steps": 82, "total_steps": 120, "loss": 0.6263, "lr": 1.2500000000000007e-06, "epoch": 6.705882352941177, "percentage": 68.33, "elapsed_time": "0:09:44", "remaining_time": "0:04:30"}
{"current_steps": 83, "total_steps": 120, "loss": 0.631, "lr": 1.1908177150303055e-06, "epoch": 6.784313725490196, "percentage": 69.17, "elapsed_time": "0:10:10", "remaining_time": "0:04:32"}
{"current_steps": 84, "total_steps": 120, "loss": 0.6436, "lr": 1.1326296046939334e-06, "epoch": 6.862745098039216, "percentage": 70.0, "elapsed_time": "0:10:34", "remaining_time": "0:04:31"}
{"current_steps": 85, "total_steps": 120, "loss": 0.6684, "lr": 1.0754798562243347e-06, "epoch": 6.9411764705882355, "percentage": 70.83, "elapsed_time": "0:10:56", "remaining_time": "0:04:30"}
{"current_steps": 86, "total_steps": 120, "loss": 0.4598, "lr": 1.0194118683375502e-06, "epoch": 7.0, "percentage": 71.67, "elapsed_time": "0:11:17", "remaining_time": "0:04:27"}
{"current_steps": 87, "total_steps": 120, "loss": 0.6107, "lr": 9.644682182758305e-07, "epoch": 7.078431372549019, "percentage": 72.5, "elapsed_time": "0:11:41", "remaining_time": "0:04:26"}
{"current_steps": 88, "total_steps": 120, "loss": 0.6293, "lr": 9.106906294750806e-07, "epoch": 7.1568627450980395, "percentage": 73.33, "elapsed_time": "0:12:08", "remaining_time": "0:04:25"}
{"current_steps": 89, "total_steps": 120, "loss": 0.5975, "lr": 8.581199398806642e-07, "epoch": 7.235294117647059, "percentage": 74.17, "elapsed_time": "0:12:34", "remaining_time": "0:04:22"}
{"current_steps": 60, "total_steps": 60, "epoch": 8.615384615384615, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}