codellama_rq2_sft / trainer_log.jsonl
Easonnoway's picture
Upload folder using huggingface_hub
9f394d4 verified
{"current_steps": 10, "total_steps": 310, "loss": 0.6022, "lr": 5.806451612903226e-06, "epoch": 0.16112789526686808, "percentage": 3.23, "elapsed_time": "0:02:32", "remaining_time": "1:16:28"}
{"current_steps": 20, "total_steps": 310, "loss": 0.5086, "lr": 1.2258064516129034e-05, "epoch": 0.32225579053373615, "percentage": 6.45, "elapsed_time": "0:04:58", "remaining_time": "1:12:04"}
{"current_steps": 30, "total_steps": 310, "loss": 0.4313, "lr": 1.870967741935484e-05, "epoch": 0.48338368580060426, "percentage": 9.68, "elapsed_time": "0:07:42", "remaining_time": "1:11:59"}
{"current_steps": 40, "total_steps": 310, "loss": 0.3224, "lr": 1.9959454037227215e-05, "epoch": 0.6445115810674723, "percentage": 12.9, "elapsed_time": "0:10:30", "remaining_time": "1:10:52"}
{"current_steps": 50, "total_steps": 310, "loss": 0.2318, "lr": 1.9795299412524948e-05, "epoch": 0.8056394763343404, "percentage": 16.13, "elapsed_time": "0:13:28", "remaining_time": "1:10:04"}
{"current_steps": 60, "total_steps": 310, "loss": 0.1739, "lr": 1.9507079544701583e-05, "epoch": 0.9667673716012085, "percentage": 19.35, "elapsed_time": "0:16:30", "remaining_time": "1:08:48"}
{"current_steps": 70, "total_steps": 310, "loss": 0.1281, "lr": 1.9098444967188308e-05, "epoch": 1.1127895266868078, "percentage": 22.58, "elapsed_time": "0:19:04", "remaining_time": "1:05:22"}
{"current_steps": 80, "total_steps": 310, "loss": 0.0624, "lr": 1.857457136130651e-05, "epoch": 1.2739174219536757, "percentage": 25.81, "elapsed_time": "0:21:35", "remaining_time": "1:02:03"}
{"current_steps": 90, "total_steps": 310, "loss": 0.0469, "lr": 1.7942094002155122e-05, "epoch": 1.4350453172205437, "percentage": 29.03, "elapsed_time": "0:24:23", "remaining_time": "0:59:37"}
{"current_steps": 100, "total_steps": 310, "loss": 0.0449, "lr": 1.7209023717584013e-05, "epoch": 1.596173212487412, "percentage": 32.26, "elapsed_time": "0:26:57", "remaining_time": "0:56:35"}
{"current_steps": 110, "total_steps": 310, "loss": 0.0285, "lr": 1.6384645424699835e-05, "epoch": 1.75730110775428, "percentage": 35.48, "elapsed_time": "0:29:42", "remaining_time": "0:54:01"}
{"current_steps": 120, "total_steps": 310, "loss": 0.0243, "lr": 1.5479400529019987e-05, "epoch": 1.918429003021148, "percentage": 38.71, "elapsed_time": "0:32:32", "remaining_time": "0:51:30"}
{"current_steps": 130, "total_steps": 310, "loss": 0.0154, "lr": 1.4504754675782731e-05, "epoch": 2.0644511581067473, "percentage": 41.94, "elapsed_time": "0:34:50", "remaining_time": "0:48:14"}
{"current_steps": 140, "total_steps": 310, "loss": 0.0064, "lr": 1.3473052528448203e-05, "epoch": 2.2255790533736155, "percentage": 45.16, "elapsed_time": "0:37:42", "remaining_time": "0:45:47"}
{"current_steps": 150, "total_steps": 310, "loss": 0.0073, "lr": 1.2397361413735785e-05, "epoch": 2.3867069486404833, "percentage": 48.39, "elapsed_time": "0:40:38", "remaining_time": "0:43:21"}
{"current_steps": 160, "total_steps": 310, "loss": 0.0064, "lr": 1.1291305813557616e-05, "epoch": 2.5478348439073515, "percentage": 51.61, "elapsed_time": "0:43:20", "remaining_time": "0:40:38"}
{"current_steps": 170, "total_steps": 310, "loss": 0.0044, "lr": 1.0168894800139311e-05, "epoch": 2.7089627391742197, "percentage": 54.84, "elapsed_time": "0:46:06", "remaining_time": "0:37:58"}
{"current_steps": 180, "total_steps": 310, "loss": 0.0036, "lr": 9.04434459999902e-06, "epoch": 2.8700906344410875, "percentage": 58.06, "elapsed_time": "0:48:58", "remaining_time": "0:35:22"}
{"current_steps": 190, "total_steps": 310, "loss": 0.0034, "lr": 7.93189853415293e-06, "epoch": 3.016112789526687, "percentage": 61.29, "elapsed_time": "0:51:05", "remaining_time": "0:32:15"}
{"current_steps": 200, "total_steps": 310, "loss": 0.0013, "lr": 6.845646615147445e-06, "epoch": 3.177240684793555, "percentage": 64.52, "elapsed_time": "0:53:51", "remaining_time": "0:29:37"}
{"current_steps": 210, "total_steps": 310, "loss": 0.0011, "lr": 5.799347085864851e-06, "epoch": 3.338368580060423, "percentage": 67.74, "elapsed_time": "0:56:42", "remaining_time": "0:27:00"}
{"current_steps": 220, "total_steps": 310, "loss": 0.0012, "lr": 4.8062521604551245e-06, "epoch": 3.499496475327291, "percentage": 70.97, "elapsed_time": "0:59:19", "remaining_time": "0:24:16"}
{"current_steps": 230, "total_steps": 310, "loss": 0.001, "lr": 3.878940174523371e-06, "epoch": 3.6606243705941592, "percentage": 74.19, "elapsed_time": "1:01:57", "remaining_time": "0:21:32"}
{"current_steps": 240, "total_steps": 310, "loss": 0.001, "lr": 3.0291562705240107e-06, "epoch": 3.8217522658610275, "percentage": 77.42, "elapsed_time": "1:04:50", "remaining_time": "0:18:54"}
{"current_steps": 250, "total_steps": 310, "loss": 0.0019, "lr": 2.2676636362076075e-06, "epoch": 3.9828801611278952, "percentage": 80.65, "elapsed_time": "1:07:30", "remaining_time": "0:16:12"}
{"current_steps": 260, "total_steps": 310, "loss": 0.0006, "lr": 1.60410718030361e-06, "epoch": 4.128902316213495, "percentage": 83.87, "elapsed_time": "1:10:59", "remaining_time": "0:13:39"}
{"current_steps": 270, "total_steps": 310, "loss": 0.0006, "lr": 1.0468913720946084e-06, "epoch": 4.290030211480363, "percentage": 87.1, "elapsed_time": "1:13:32", "remaining_time": "0:10:53"}
{"current_steps": 280, "total_steps": 310, "loss": 0.0005, "lr": 6.030737921409169e-07, "epoch": 4.451158106747231, "percentage": 90.32, "elapsed_time": "1:16:15", "remaining_time": "0:08:10"}
{"current_steps": 290, "total_steps": 310, "loss": 0.0009, "lr": 2.7827574242009434e-07, "epoch": 4.612286002014098, "percentage": 93.55, "elapsed_time": "1:19:04", "remaining_time": "0:05:27"}
{"current_steps": 300, "total_steps": 310, "loss": 0.0006, "lr": 7.661104807487607e-08, "epoch": 4.7734138972809665, "percentage": 96.77, "elapsed_time": "1:21:38", "remaining_time": "0:02:43"}
{"current_steps": 310, "total_steps": 310, "loss": 0.0007, "lr": 6.339525519594159e-10, "epoch": 4.934541792547835, "percentage": 100.0, "elapsed_time": "1:24:30", "remaining_time": "0:00:00"}
{"current_steps": 310, "total_steps": 310, "epoch": 4.934541792547835, "percentage": 100.0, "elapsed_time": "1:25:28", "remaining_time": "0:00:00"}