OH_original_wo_camel_ai_math / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 0
8df1dde verified
{"current_steps": 10, "total_steps": 942, "loss": 0.8269, "learning_rate": 5e-06, "epoch": 0.03177124702144559, "percentage": 1.06, "elapsed_time": "0:04:56", "remaining_time": "7:39:54"}
{"current_steps": 20, "total_steps": 942, "loss": 0.7492, "learning_rate": 5e-06, "epoch": 0.06354249404289118, "percentage": 2.12, "elapsed_time": "0:09:48", "remaining_time": "7:31:50"}
{"current_steps": 30, "total_steps": 942, "loss": 0.7286, "learning_rate": 5e-06, "epoch": 0.09531374106433678, "percentage": 3.18, "elapsed_time": "0:14:40", "remaining_time": "7:25:52"}
{"current_steps": 40, "total_steps": 942, "loss": 0.7128, "learning_rate": 5e-06, "epoch": 0.12708498808578236, "percentage": 4.25, "elapsed_time": "0:19:31", "remaining_time": "7:20:26"}
{"current_steps": 50, "total_steps": 942, "loss": 0.696, "learning_rate": 5e-06, "epoch": 0.15885623510722796, "percentage": 5.31, "elapsed_time": "0:24:23", "remaining_time": "7:15:17"}
{"current_steps": 60, "total_steps": 942, "loss": 0.6873, "learning_rate": 5e-06, "epoch": 0.19062748212867356, "percentage": 6.37, "elapsed_time": "0:29:15", "remaining_time": "7:10:12"}
{"current_steps": 70, "total_steps": 942, "loss": 0.6917, "learning_rate": 5e-06, "epoch": 0.22239872915011913, "percentage": 7.43, "elapsed_time": "0:34:07", "remaining_time": "7:05:12"}
{"current_steps": 80, "total_steps": 942, "loss": 0.6812, "learning_rate": 5e-06, "epoch": 0.2541699761715647, "percentage": 8.49, "elapsed_time": "0:38:59", "remaining_time": "7:00:09"}
{"current_steps": 90, "total_steps": 942, "loss": 0.6755, "learning_rate": 5e-06, "epoch": 0.28594122319301035, "percentage": 9.55, "elapsed_time": "0:43:51", "remaining_time": "6:55:09"}
{"current_steps": 100, "total_steps": 942, "loss": 0.6712, "learning_rate": 5e-06, "epoch": 0.3177124702144559, "percentage": 10.62, "elapsed_time": "0:48:42", "remaining_time": "6:50:04"}
{"current_steps": 110, "total_steps": 942, "loss": 0.6712, "learning_rate": 5e-06, "epoch": 0.3494837172359015, "percentage": 11.68, "elapsed_time": "0:53:33", "remaining_time": "6:45:06"}
{"current_steps": 120, "total_steps": 942, "loss": 0.6702, "learning_rate": 5e-06, "epoch": 0.3812549642573471, "percentage": 12.74, "elapsed_time": "0:58:25", "remaining_time": "6:40:12"}
{"current_steps": 130, "total_steps": 942, "loss": 0.6639, "learning_rate": 5e-06, "epoch": 0.4130262112787927, "percentage": 13.8, "elapsed_time": "1:03:17", "remaining_time": "6:35:19"}
{"current_steps": 140, "total_steps": 942, "loss": 0.6664, "learning_rate": 5e-06, "epoch": 0.44479745830023826, "percentage": 14.86, "elapsed_time": "1:08:09", "remaining_time": "6:30:25"}
{"current_steps": 150, "total_steps": 942, "loss": 0.6601, "learning_rate": 5e-06, "epoch": 0.4765687053216839, "percentage": 15.92, "elapsed_time": "1:13:01", "remaining_time": "6:25:32"}
{"current_steps": 160, "total_steps": 942, "loss": 0.6579, "learning_rate": 5e-06, "epoch": 0.5083399523431295, "percentage": 16.99, "elapsed_time": "1:17:52", "remaining_time": "6:20:38"}
{"current_steps": 170, "total_steps": 942, "loss": 0.6574, "learning_rate": 5e-06, "epoch": 0.5401111993645751, "percentage": 18.05, "elapsed_time": "1:22:44", "remaining_time": "6:15:45"}
{"current_steps": 180, "total_steps": 942, "loss": 0.6611, "learning_rate": 5e-06, "epoch": 0.5718824463860207, "percentage": 19.11, "elapsed_time": "1:27:36", "remaining_time": "6:10:52"}
{"current_steps": 190, "total_steps": 942, "loss": 0.6593, "learning_rate": 5e-06, "epoch": 0.6036536934074662, "percentage": 20.17, "elapsed_time": "1:32:28", "remaining_time": "6:06:00"}
{"current_steps": 200, "total_steps": 942, "loss": 0.653, "learning_rate": 5e-06, "epoch": 0.6354249404289118, "percentage": 21.23, "elapsed_time": "1:37:19", "remaining_time": "6:01:05"}
{"current_steps": 210, "total_steps": 942, "loss": 0.6465, "learning_rate": 5e-06, "epoch": 0.6671961874503575, "percentage": 22.29, "elapsed_time": "1:42:10", "remaining_time": "5:56:10"}
{"current_steps": 220, "total_steps": 942, "loss": 0.6513, "learning_rate": 5e-06, "epoch": 0.698967434471803, "percentage": 23.35, "elapsed_time": "1:47:02", "remaining_time": "5:51:17"}
{"current_steps": 230, "total_steps": 942, "loss": 0.6552, "learning_rate": 5e-06, "epoch": 0.7307386814932486, "percentage": 24.42, "elapsed_time": "1:51:53", "remaining_time": "5:46:23"}
{"current_steps": 240, "total_steps": 942, "loss": 0.6476, "learning_rate": 5e-06, "epoch": 0.7625099285146942, "percentage": 25.48, "elapsed_time": "1:56:45", "remaining_time": "5:41:30"}
{"current_steps": 250, "total_steps": 942, "loss": 0.6515, "learning_rate": 5e-06, "epoch": 0.7942811755361397, "percentage": 26.54, "elapsed_time": "2:01:37", "remaining_time": "5:36:38"}
{"current_steps": 260, "total_steps": 942, "loss": 0.6391, "learning_rate": 5e-06, "epoch": 0.8260524225575854, "percentage": 27.6, "elapsed_time": "2:06:28", "remaining_time": "5:31:46"}
{"current_steps": 270, "total_steps": 942, "loss": 0.6488, "learning_rate": 5e-06, "epoch": 0.857823669579031, "percentage": 28.66, "elapsed_time": "2:11:19", "remaining_time": "5:26:52"}
{"current_steps": 280, "total_steps": 942, "loss": 0.644, "learning_rate": 5e-06, "epoch": 0.8895949166004765, "percentage": 29.72, "elapsed_time": "2:16:10", "remaining_time": "5:21:58"}
{"current_steps": 290, "total_steps": 942, "loss": 0.6533, "learning_rate": 5e-06, "epoch": 0.9213661636219221, "percentage": 30.79, "elapsed_time": "2:21:02", "remaining_time": "5:17:05"}
{"current_steps": 300, "total_steps": 942, "loss": 0.6458, "learning_rate": 5e-06, "epoch": 0.9531374106433678, "percentage": 31.85, "elapsed_time": "2:25:53", "remaining_time": "5:12:13"}
{"current_steps": 310, "total_steps": 942, "loss": 0.6416, "learning_rate": 5e-06, "epoch": 0.9849086576648134, "percentage": 32.91, "elapsed_time": "2:30:45", "remaining_time": "5:07:20"}
{"current_steps": 314, "total_steps": 942, "eval_loss": 0.6390731930732727, "epoch": 0.9976171564733916, "percentage": 33.33, "elapsed_time": "2:35:52", "remaining_time": "5:11:44"}
{"current_steps": 320, "total_steps": 942, "loss": 0.6169, "learning_rate": 5e-06, "epoch": 1.016679904686259, "percentage": 33.97, "elapsed_time": "2:39:22", "remaining_time": "5:09:47"}