Sailor2-8B-Chat_sft_sg_values / trainer_log.jsonl
Incomple's picture
Training in progress, epoch 0
cd55f3f verified
{"current_steps": 67, "total_steps": 1337, "loss": 2.0415, "lr": 4.925373134328357e-07, "epoch": 0.05009345794392523, "percentage": 5.01, "elapsed_time": "0:01:36", "remaining_time": "0:30:33"}
{"current_steps": 134, "total_steps": 1337, "loss": 1.5231, "lr": 9.925373134328357e-07, "epoch": 0.10018691588785046, "percentage": 10.02, "elapsed_time": "0:03:15", "remaining_time": "0:29:19"}
{"current_steps": 201, "total_steps": 1337, "loss": 0.4422, "lr": 9.451371571072319e-07, "epoch": 0.1502803738317757, "percentage": 15.03, "elapsed_time": "0:04:53", "remaining_time": "0:27:39"}
{"current_steps": 250, "total_steps": 1337, "eval_loss": 0.26753509044647217, "epoch": 0.18691588785046728, "percentage": 18.7, "elapsed_time": "0:06:34", "remaining_time": "0:28:36"}
{"current_steps": 268, "total_steps": 1337, "loss": 0.2826, "lr": 8.894430590191188e-07, "epoch": 0.20037383177570092, "percentage": 20.04, "elapsed_time": "0:07:00", "remaining_time": "0:27:56"}
{"current_steps": 335, "total_steps": 1337, "loss": 0.2107, "lr": 8.337489609310058e-07, "epoch": 0.2504672897196262, "percentage": 25.06, "elapsed_time": "0:08:38", "remaining_time": "0:25:50"}
{"current_steps": 402, "total_steps": 1337, "loss": 0.1864, "lr": 7.780548628428927e-07, "epoch": 0.3005607476635514, "percentage": 30.07, "elapsed_time": "0:10:16", "remaining_time": "0:23:53"}
{"current_steps": 469, "total_steps": 1337, "loss": 0.1727, "lr": 7.223607647547797e-07, "epoch": 0.3506542056074766, "percentage": 35.08, "elapsed_time": "0:11:54", "remaining_time": "0:22:02"}
{"current_steps": 500, "total_steps": 1337, "eval_loss": 0.16795502603054047, "epoch": 0.37383177570093457, "percentage": 37.4, "elapsed_time": "0:13:08", "remaining_time": "0:22:00"}
{"current_steps": 536, "total_steps": 1337, "loss": 0.1551, "lr": 6.666666666666666e-07, "epoch": 0.40074766355140184, "percentage": 40.09, "elapsed_time": "0:14:00", "remaining_time": "0:20:55"}
{"current_steps": 603, "total_steps": 1337, "loss": 0.148, "lr": 6.109725685785536e-07, "epoch": 0.4508411214953271, "percentage": 45.1, "elapsed_time": "0:15:36", "remaining_time": "0:19:00"}
{"current_steps": 670, "total_steps": 1337, "loss": 0.1521, "lr": 5.552784704904405e-07, "epoch": 0.5009345794392523, "percentage": 50.11, "elapsed_time": "0:17:13", "remaining_time": "0:17:09"}
{"current_steps": 737, "total_steps": 1337, "loss": 0.1475, "lr": 4.995843724023275e-07, "epoch": 0.5510280373831775, "percentage": 55.12, "elapsed_time": "0:18:51", "remaining_time": "0:15:21"}
{"current_steps": 750, "total_steps": 1337, "eval_loss": 0.14567767083644867, "epoch": 0.5607476635514018, "percentage": 56.1, "elapsed_time": "0:19:40", "remaining_time": "0:15:23"}
{"current_steps": 804, "total_steps": 1337, "loss": 0.1327, "lr": 4.438902743142144e-07, "epoch": 0.6011214953271028, "percentage": 60.13, "elapsed_time": "0:20:58", "remaining_time": "0:13:54"}
{"current_steps": 871, "total_steps": 1337, "loss": 0.1394, "lr": 3.881961762261014e-07, "epoch": 0.6512149532710281, "percentage": 65.15, "elapsed_time": "0:22:37", "remaining_time": "0:12:06"}
{"current_steps": 938, "total_steps": 1337, "loss": 0.1284, "lr": 3.3250207813798835e-07, "epoch": 0.7013084112149532, "percentage": 70.16, "elapsed_time": "0:24:14", "remaining_time": "0:10:18"}
{"current_steps": 1000, "total_steps": 1337, "eval_loss": 0.13731907308101654, "epoch": 0.7476635514018691, "percentage": 74.79, "elapsed_time": "0:26:15", "remaining_time": "0:08:50"}
{"current_steps": 1005, "total_steps": 1337, "loss": 0.1065, "lr": 2.7680798004987534e-07, "epoch": 0.7514018691588785, "percentage": 75.17, "elapsed_time": "0:26:21", "remaining_time": "0:08:42"}
{"current_steps": 1072, "total_steps": 1337, "loss": 0.1167, "lr": 2.2111388196176226e-07, "epoch": 0.8014953271028037, "percentage": 80.18, "elapsed_time": "0:27:58", "remaining_time": "0:06:54"}
{"current_steps": 1139, "total_steps": 1337, "loss": 0.1278, "lr": 1.6541978387364923e-07, "epoch": 0.851588785046729, "percentage": 85.19, "elapsed_time": "0:29:35", "remaining_time": "0:05:08"}
{"current_steps": 1206, "total_steps": 1337, "loss": 0.1066, "lr": 1.0972568578553615e-07, "epoch": 0.9016822429906542, "percentage": 90.2, "elapsed_time": "0:31:11", "remaining_time": "0:03:23"}
{"current_steps": 1250, "total_steps": 1337, "eval_loss": 0.13475529849529266, "epoch": 0.9345794392523364, "percentage": 93.49, "elapsed_time": "0:32:45", "remaining_time": "0:02:16"}
{"current_steps": 1273, "total_steps": 1337, "loss": 0.108, "lr": 5.403158769742311e-08, "epoch": 0.9517757009345794, "percentage": 95.21, "elapsed_time": "0:33:19", "remaining_time": "0:01:40"}
{"current_steps": 1337, "total_steps": 1337, "epoch": 0.9996261682242991, "percentage": 100.0, "elapsed_time": "0:34:54", "remaining_time": "0:00:00"}