foamMistral0.3-7B-Instruct / trainer_log.jsonl
finalform's picture
Upload folder using huggingface_hub
e90069c verified
{"current_steps": 10, "total_steps": 288, "loss": 1.0176, "lr": 0.0001, "epoch": 0.32, "percentage": 3.47, "elapsed_time": "0:01:07", "remaining_time": "0:31:04"}
{"current_steps": 20, "total_steps": 288, "loss": 0.5103, "lr": 9.968335515358916e-05, "epoch": 0.64, "percentage": 6.94, "elapsed_time": "0:02:12", "remaining_time": "0:29:38"}
{"current_steps": 30, "total_steps": 288, "loss": 0.3179, "lr": 9.873743117270691e-05, "epoch": 0.96, "percentage": 10.42, "elapsed_time": "0:03:18", "remaining_time": "0:28:24"}
{"current_steps": 32, "total_steps": 288, "eval_loss": 0.3320535123348236, "epoch": 1.0, "percentage": 11.11, "elapsed_time": "0:03:48", "remaining_time": "0:30:28"}
{"current_steps": 40, "total_steps": 288, "loss": 0.3371, "lr": 9.717420893549902e-05, "epoch": 1.256, "percentage": 13.89, "elapsed_time": "0:04:43", "remaining_time": "0:29:15"}
{"current_steps": 50, "total_steps": 288, "loss": 0.2708, "lr": 9.501348789257373e-05, "epoch": 1.576, "percentage": 17.36, "elapsed_time": "0:05:48", "remaining_time": "0:27:38"}
{"current_steps": 60, "total_steps": 288, "loss": 0.206, "lr": 9.2282635291242e-05, "epoch": 1.896, "percentage": 20.83, "elapsed_time": "0:06:54", "remaining_time": "0:26:15"}
{"current_steps": 64, "total_steps": 288, "eval_loss": 0.24253705143928528, "epoch": 2.0, "percentage": 22.22, "elapsed_time": "0:07:38", "remaining_time": "0:26:43"}
{"current_steps": 70, "total_steps": 288, "loss": 0.2057, "lr": 8.90162395476046e-05, "epoch": 2.192, "percentage": 24.31, "elapsed_time": "0:08:19", "remaining_time": "0:25:55"}
{"current_steps": 80, "total_steps": 288, "loss": 0.2043, "lr": 8.525567215680398e-05, "epoch": 2.512, "percentage": 27.78, "elapsed_time": "0:09:24", "remaining_time": "0:24:28"}
{"current_steps": 90, "total_steps": 288, "loss": 0.1447, "lr": 8.104856369019524e-05, "epoch": 2.832, "percentage": 31.25, "elapsed_time": "0:10:30", "remaining_time": "0:23:08"}
{"current_steps": 96, "total_steps": 288, "eval_loss": 0.21092161536216736, "epoch": 3.0, "percentage": 33.33, "elapsed_time": "0:11:27", "remaining_time": "0:22:55"}
{"current_steps": 100, "total_steps": 288, "loss": 0.1352, "lr": 7.644820051634812e-05, "epoch": 3.128, "percentage": 34.72, "elapsed_time": "0:11:54", "remaining_time": "0:22:23"}
{"current_steps": 110, "total_steps": 288, "loss": 0.1437, "lr": 7.15128498868873e-05, "epoch": 3.448, "percentage": 38.19, "elapsed_time": "0:13:00", "remaining_time": "0:21:03"}
{"current_steps": 120, "total_steps": 288, "loss": 0.1067, "lr": 6.630502193549474e-05, "epoch": 3.768, "percentage": 41.67, "elapsed_time": "0:14:07", "remaining_time": "0:19:46"}
{"current_steps": 128, "total_steps": 288, "eval_loss": 0.20618033409118652, "epoch": 4.0, "percentage": 44.44, "elapsed_time": "0:15:17", "remaining_time": "0:19:06"}
{"current_steps": 130, "total_steps": 288, "loss": 0.0916, "lr": 6.0890677937442574e-05, "epoch": 4.064, "percentage": 45.14, "elapsed_time": "0:15:31", "remaining_time": "0:18:52"}
{"current_steps": 140, "total_steps": 288, "loss": 0.1133, "lr": 5.5338394857677945e-05, "epoch": 4.384, "percentage": 48.61, "elapsed_time": "0:16:37", "remaining_time": "0:17:34"}
{"current_steps": 150, "total_steps": 288, "loss": 0.0792, "lr": 4.971849676912172e-05, "epoch": 4.704, "percentage": 52.08, "elapsed_time": "0:17:43", "remaining_time": "0:16:18"}
{"current_steps": 160, "total_steps": 288, "loss": 0.0612, "lr": 4.410216414245771e-05, "epoch": 5.0, "percentage": 55.56, "elapsed_time": "0:18:44", "remaining_time": "0:14:59"}
{"current_steps": 160, "total_steps": 288, "eval_loss": 0.2128402590751648, "epoch": 5.0, "percentage": 55.56, "elapsed_time": "0:19:06", "remaining_time": "0:15:17"}
{"current_steps": 170, "total_steps": 288, "loss": 0.091, "lr": 3.856053228896442e-05, "epoch": 5.32, "percentage": 59.03, "elapsed_time": "0:20:13", "remaining_time": "0:14:02"}
{"current_steps": 180, "total_steps": 288, "loss": 0.0605, "lr": 3.316379037532644e-05, "epoch": 5.64, "percentage": 62.5, "elapsed_time": "0:21:19", "remaining_time": "0:12:47"}
{"current_steps": 190, "total_steps": 288, "loss": 0.0491, "lr": 2.798029242211828e-05, "epoch": 5.96, "percentage": 65.97, "elapsed_time": "0:22:25", "remaining_time": "0:11:34"}
{"current_steps": 192, "total_steps": 288, "eval_loss": 0.2168993204832077, "epoch": 6.0, "percentage": 66.67, "elapsed_time": "0:22:55", "remaining_time": "0:11:27"}
{"current_steps": 200, "total_steps": 288, "loss": 0.0648, "lr": 2.3075691545870558e-05, "epoch": 6.256, "percentage": 69.44, "elapsed_time": "0:23:50", "remaining_time": "0:10:29"}
{"current_steps": 210, "total_steps": 288, "loss": 0.0431, "lr": 1.8512108410229878e-05, "epoch": 6.576, "percentage": 72.92, "elapsed_time": "0:24:55", "remaining_time": "0:09:15"}
{"current_steps": 220, "total_steps": 288, "loss": 0.0378, "lr": 1.434734441843899e-05, "epoch": 6.896, "percentage": 76.39, "elapsed_time": "0:26:01", "remaining_time": "0:08:02"}
{"current_steps": 224, "total_steps": 288, "eval_loss": 0.2166266143321991, "epoch": 7.0, "percentage": 77.78, "elapsed_time": "0:26:45", "remaining_time": "0:07:38"}
{"current_steps": 230, "total_steps": 288, "loss": 0.0383, "lr": 1.063414961267859e-05, "epoch": 7.192, "percentage": 79.86, "elapsed_time": "0:27:26", "remaining_time": "0:06:55"}
{"current_steps": 240, "total_steps": 288, "loss": 0.0415, "lr": 7.41955455290726e-06, "epoch": 7.5120000000000005, "percentage": 83.33, "elapsed_time": "0:28:31", "remaining_time": "0:05:42"}
{"current_steps": 250, "total_steps": 288, "loss": 0.0294, "lr": 4.744274637483936e-06, "epoch": 7.832, "percentage": 86.81, "elapsed_time": "0:29:37", "remaining_time": "0:04:30"}
{"current_steps": 256, "total_steps": 288, "eval_loss": 0.22243177890777588, "epoch": 8.0, "percentage": 88.89, "elapsed_time": "0:30:34", "remaining_time": "0:03:49"}
{"current_steps": 260, "total_steps": 288, "loss": 0.0265, "lr": 2.6421944103256657e-06, "epoch": 8.128, "percentage": 90.28, "elapsed_time": "0:31:01", "remaining_time": "0:03:20"}
{"current_steps": 270, "total_steps": 288, "loss": 0.0371, "lr": 1.1399383862592927e-06, "epoch": 8.448, "percentage": 93.75, "elapsed_time": "0:32:07", "remaining_time": "0:02:08"}
{"current_steps": 280, "total_steps": 288, "loss": 0.0215, "lr": 2.5653383040524227e-07, "epoch": 8.768, "percentage": 97.22, "elapsed_time": "0:33:13", "remaining_time": "0:00:56"}
{"current_steps": 288, "total_steps": 288, "eval_loss": 0.22601914405822754, "epoch": 9.0, "percentage": 100.0, "elapsed_time": "0:34:25", "remaining_time": "0:00:00"}
{"current_steps": 288, "total_steps": 288, "epoch": 9.0, "percentage": 100.0, "elapsed_time": "0:34:25", "remaining_time": "0:00:00"}
{"current_steps": 5, "total_steps": 49, "percentage": 10.2, "elapsed_time": "0:00:01", "remaining_time": "0:00:11"}
{"current_steps": 10, "total_steps": 49, "percentage": 20.41, "elapsed_time": "0:00:02", "remaining_time": "0:00:11"}
{"current_steps": 15, "total_steps": 49, "percentage": 30.61, "elapsed_time": "0:00:04", "remaining_time": "0:00:10"}
{"current_steps": 20, "total_steps": 49, "percentage": 40.82, "elapsed_time": "0:00:06", "remaining_time": "0:00:08"}
{"current_steps": 25, "total_steps": 49, "percentage": 51.02, "elapsed_time": "0:00:07", "remaining_time": "0:00:07"}
{"current_steps": 30, "total_steps": 49, "percentage": 61.22, "elapsed_time": "0:00:09", "remaining_time": "0:00:06"}
{"current_steps": 35, "total_steps": 49, "percentage": 71.43, "elapsed_time": "0:00:11", "remaining_time": "0:00:04"}
{"current_steps": 40, "total_steps": 49, "percentage": 81.63, "elapsed_time": "0:00:13", "remaining_time": "0:00:02"}
{"current_steps": 45, "total_steps": 49, "percentage": 91.84, "elapsed_time": "0:00:14", "remaining_time": "0:00:01"}
{"current_steps": 0, "total_steps": 49, "eval_loss": 1.411633849143982, "percentage": 0.0, "elapsed_time": "0:00:16", "remaining_time": "0:00:00"}