v07_final_only_lr2e5 / trainer_log.jsonl
lldois's picture
Upload v07_final_only_lr2e5 model without checkpoints
dab8405 verified
Raw
History Blame Contribute Delete
12.3 kB
{"current_steps": 5, "total_steps": 297, "loss": 2.3417264938354494, "lr": 8.888888888888888e-06, "epoch": 0.016863406408094434, "percentage": 1.68, "elapsed_time": "0:00:38", "remaining_time": "0:37:34"}
{"current_steps": 10, "total_steps": 297, "loss": 1.7059539794921874, "lr": 2e-05, "epoch": 0.03372681281618887, "percentage": 3.37, "elapsed_time": "0:01:18", "remaining_time": "0:37:19"}
{"current_steps": 15, "total_steps": 297, "loss": 1.7476335525512696, "lr": 1.9985129789397633e-05, "epoch": 0.050590219224283306, "percentage": 5.05, "elapsed_time": "0:01:54", "remaining_time": "0:35:56"}
{"current_steps": 20, "total_steps": 297, "loss": 1.5680081367492675, "lr": 1.9940563382223196e-05, "epoch": 0.06745362563237774, "percentage": 6.73, "elapsed_time": "0:02:33", "remaining_time": "0:35:20"}
{"current_steps": 25, "total_steps": 297, "loss": 1.347496223449707, "lr": 1.9866433320848793e-05, "epoch": 0.08431703204047218, "percentage": 8.42, "elapsed_time": "0:03:13", "remaining_time": "0:35:03"}
{"current_steps": 30, "total_steps": 297, "loss": 1.2069475173950195, "lr": 1.9762960071199334e-05, "epoch": 0.10118043844856661, "percentage": 10.1, "elapsed_time": "0:03:52", "remaining_time": "0:34:33"}
{"current_steps": 35, "total_steps": 297, "loss": 1.324411678314209, "lr": 1.963045136707763e-05, "epoch": 0.11804384485666104, "percentage": 11.78, "elapsed_time": "0:04:33", "remaining_time": "0:34:05"}
{"current_steps": 40, "total_steps": 297, "loss": 1.165403175354004, "lr": 1.946930129495106e-05, "epoch": 0.13490725126475547, "percentage": 13.47, "elapsed_time": "0:05:13", "remaining_time": "0:33:36"}
{"current_steps": 45, "total_steps": 297, "loss": 1.2257371902465821, "lr": 1.9279989121921846e-05, "epoch": 0.15177065767284992, "percentage": 15.15, "elapsed_time": "0:05:55", "remaining_time": "0:33:08"}
{"current_steps": 50, "total_steps": 297, "loss": 1.234571933746338, "lr": 1.9063077870366504e-05, "epoch": 0.16863406408094436, "percentage": 16.84, "elapsed_time": "0:06:36", "remaining_time": "0:32:39"}
{"current_steps": 55, "total_steps": 297, "loss": 1.3958836555480958, "lr": 1.881921264348355e-05, "epoch": 0.18549747048903878, "percentage": 18.52, "elapsed_time": "0:07:15", "remaining_time": "0:31:56"}
{"current_steps": 60, "total_steps": 297, "loss": 1.0263965606689454, "lr": 1.854911870672947e-05, "epoch": 0.20236087689713322, "percentage": 20.2, "elapsed_time": "0:07:56", "remaining_time": "0:31:21"}
{"current_steps": 65, "total_steps": 297, "loss": 1.228264617919922, "lr": 1.8253599330848638e-05, "epoch": 0.21922428330522767, "percentage": 21.89, "elapsed_time": "0:08:36", "remaining_time": "0:30:44"}
{"current_steps": 70, "total_steps": 297, "loss": 1.250452423095703, "lr": 1.7933533402912354e-05, "epoch": 0.23608768971332209, "percentage": 23.57, "elapsed_time": "0:09:16", "remaining_time": "0:30:05"}
{"current_steps": 75, "total_steps": 297, "loss": 1.2329339027404784, "lr": 1.758987281247162e-05, "epoch": 0.25295109612141653, "percentage": 25.25, "elapsed_time": "0:09:56", "remaining_time": "0:29:25"}
{"current_steps": 80, "total_steps": 297, "loss": 1.2469540596008302, "lr": 1.7223639620597556e-05, "epoch": 0.26981450252951095, "percentage": 26.94, "elapsed_time": "0:10:33", "remaining_time": "0:28:39"}
{"current_steps": 85, "total_steps": 297, "loss": 1.0711227416992188, "lr": 1.6835923020228714e-05, "epoch": 0.2866779089376054, "percentage": 28.62, "elapsed_time": "0:11:16", "remaining_time": "0:28:06"}
{"current_steps": 90, "total_steps": 297, "loss": 1.6063650131225586, "lr": 1.6427876096865394e-05, "epoch": 0.30354131534569984, "percentage": 30.3, "elapsed_time": "0:11:52", "remaining_time": "0:27:18"}
{"current_steps": 95, "total_steps": 297, "loss": 1.1470824241638184, "lr": 1.6000712399244813e-05, "epoch": 0.32040472175379425, "percentage": 31.99, "elapsed_time": "0:12:33", "remaining_time": "0:26:42"}
{"current_steps": 100, "total_steps": 297, "loss": 1.255699348449707, "lr": 1.5555702330196024e-05, "epoch": 0.3372681281618887, "percentage": 33.67, "elapsed_time": "0:13:11", "remaining_time": "0:25:58"}
{"current_steps": 105, "total_steps": 297, "loss": 1.0055023193359376, "lr": 1.509416936840842e-05, "epoch": 0.35413153456998314, "percentage": 35.35, "elapsed_time": "0:13:51", "remaining_time": "0:25:19"}
{"current_steps": 110, "total_steps": 297, "loss": 1.4475191116333008, "lr": 1.4617486132350343e-05, "epoch": 0.37099494097807756, "percentage": 37.04, "elapsed_time": "0:14:30", "remaining_time": "0:24:39"}
{"current_steps": 115, "total_steps": 297, "loss": 1.1591588973999023, "lr": 1.4127070298043949e-05, "epoch": 0.38785834738617203, "percentage": 38.72, "elapsed_time": "0:15:11", "remaining_time": "0:24:02"}
{"current_steps": 120, "total_steps": 297, "loss": 1.1827627182006837, "lr": 1.3624380382837017e-05, "epoch": 0.40472175379426645, "percentage": 40.4, "elapsed_time": "0:15:52", "remaining_time": "0:23:25"}
{"current_steps": 125, "total_steps": 297, "loss": 1.4125149726867676, "lr": 1.3110911407710909e-05, "epoch": 0.42158516020236086, "percentage": 42.09, "elapsed_time": "0:16:30", "remaining_time": "0:22:42"}
{"current_steps": 130, "total_steps": 297, "loss": 1.1916536331176757, "lr": 1.2588190451025209e-05, "epoch": 0.43844856661045534, "percentage": 43.77, "elapsed_time": "0:17:11", "remaining_time": "0:22:05"}
{"current_steps": 135, "total_steps": 297, "loss": 1.049894142150879, "lr": 1.205777210692235e-05, "epoch": 0.45531197301854975, "percentage": 45.45, "elapsed_time": "0:17:51", "remaining_time": "0:21:26"}
{"current_steps": 140, "total_steps": 297, "loss": 1.4272873878479004, "lr": 1.1521233861899168e-05, "epoch": 0.47217537942664417, "percentage": 47.14, "elapsed_time": "0:18:32", "remaining_time": "0:20:47"}
{"current_steps": 145, "total_steps": 297, "loss": 1.1360230445861816, "lr": 1.098017140329561e-05, "epoch": 0.48903878583473864, "percentage": 48.82, "elapsed_time": "0:19:12", "remaining_time": "0:20:07"}
{"current_steps": 150, "total_steps": 297, "loss": 1.2251985549926758, "lr": 1.0436193873653362e-05, "epoch": 0.5059021922428331, "percentage": 50.51, "elapsed_time": "0:19:50", "remaining_time": "0:19:26"}
{"current_steps": 155, "total_steps": 297, "loss": 1.2744477272033692, "lr": 9.890919085058179e-06, "epoch": 0.5227655986509275, "percentage": 52.19, "elapsed_time": "0:20:29", "remaining_time": "0:18:46"}
{"current_steps": 160, "total_steps": 297, "loss": 1.2714393615722657, "lr": 9.34596870769857e-06, "epoch": 0.5396290050590219, "percentage": 53.87, "elapsed_time": "0:21:08", "remaining_time": "0:18:05"}
{"current_steps": 165, "total_steps": 297, "loss": 1.019619846343994, "lr": 8.802963446950378e-06, "epoch": 0.5564924114671164, "percentage": 55.56, "elapsed_time": "0:21:47", "remaining_time": "0:17:25"}
{"current_steps": 170, "total_steps": 297, "loss": 0.9829767227172852, "lr": 8.263518223330698e-06, "epoch": 0.5733558178752108, "percentage": 57.24, "elapsed_time": "0:22:28", "remaining_time": "0:16:47"}
{"current_steps": 175, "total_steps": 297, "loss": 1.5283356666564942, "lr": 7.72923736965627e-06, "epoch": 0.5902192242833052, "percentage": 58.92, "elapsed_time": "0:23:08", "remaining_time": "0:16:07"}
{"current_steps": 180, "total_steps": 297, "loss": 1.0275829315185547, "lr": 7.201709859690081e-06, "epoch": 0.6070826306913997, "percentage": 60.61, "elapsed_time": "0:23:49", "remaining_time": "0:15:29"}
{"current_steps": 185, "total_steps": 297, "loss": 1.1475248336791992, "lr": 6.682504582466482e-06, "epoch": 0.6239460370994941, "percentage": 62.29, "elapsed_time": "0:24:28", "remaining_time": "0:14:48"}
{"current_steps": 190, "total_steps": 297, "loss": 1.0172494888305663, "lr": 6.173165676349103e-06, "epoch": 0.6408094435075885, "percentage": 63.97, "elapsed_time": "0:25:06", "remaining_time": "0:14:08"}
{"current_steps": 195, "total_steps": 297, "loss": 1.176294994354248, "lr": 5.675207936698337e-06, "epoch": 0.657672849915683, "percentage": 65.66, "elapsed_time": "0:25:47", "remaining_time": "0:13:29"}
{"current_steps": 200, "total_steps": 297, "loss": 1.2884156227111816, "lr": 5.190112310806126e-06, "epoch": 0.6745362563237775, "percentage": 67.34, "elapsed_time": "0:26:25", "remaining_time": "0:12:48"}
{"current_steps": 205, "total_steps": 297, "loss": 1.2367602348327638, "lr": 4.7193214934963204e-06, "epoch": 0.6913996627318718, "percentage": 69.02, "elapsed_time": "0:27:03", "remaining_time": "0:12:08"}
{"current_steps": 210, "total_steps": 297, "loss": 1.2425697326660157, "lr": 4.264235636489542e-06, "epoch": 0.7082630691399663, "percentage": 70.71, "elapsed_time": "0:27:44", "remaining_time": "0:11:29"}
{"current_steps": 215, "total_steps": 297, "loss": 1.0178656578063965, "lr": 3.826208184292952e-06, "epoch": 0.7251264755480608, "percentage": 72.39, "elapsed_time": "0:28:24", "remaining_time": "0:10:50"}
{"current_steps": 220, "total_steps": 297, "loss": 1.4105095863342285, "lr": 3.4065418489993118e-06, "epoch": 0.7419898819561551, "percentage": 74.07, "elapsed_time": "0:29:05", "remaining_time": "0:10:10"}
{"current_steps": 225, "total_steps": 297, "loss": 1.2955214500427246, "lr": 3.0064847359663284e-06, "epoch": 0.7588532883642496, "percentage": 75.76, "elapsed_time": "0:29:42", "remaining_time": "0:09:30"}
{"current_steps": 230, "total_steps": 297, "loss": 1.0158836364746093, "lr": 2.6272266318987606e-06, "epoch": 0.7757166947723441, "percentage": 77.44, "elapsed_time": "0:30:21", "remaining_time": "0:08:50"}
{"current_steps": 235, "total_steps": 297, "loss": 1.2233789443969727, "lr": 2.26989546637263e-06, "epoch": 0.7925801011804384, "percentage": 79.12, "elapsed_time": "0:31:03", "remaining_time": "0:08:11"}
{"current_steps": 240, "total_steps": 297, "loss": 1.1834559440612793, "lr": 1.9355539573251737e-06, "epoch": 0.8094435075885329, "percentage": 80.81, "elapsed_time": "0:31:42", "remaining_time": "0:07:31"}
{"current_steps": 245, "total_steps": 297, "loss": 1.0230623245239259, "lr": 1.6251964504869221e-06, "epoch": 0.8263069139966274, "percentage": 82.49, "elapsed_time": "0:32:22", "remaining_time": "0:06:52"}
{"current_steps": 250, "total_steps": 297, "loss": 1.103525447845459, "lr": 1.339745962155613e-06, "epoch": 0.8431703204047217, "percentage": 84.18, "elapsed_time": "0:33:04", "remaining_time": "0:06:13"}
{"current_steps": 255, "total_steps": 297, "loss": 0.9862545013427735, "lr": 1.0800514341068592e-06, "epoch": 0.8600337268128162, "percentage": 85.86, "elapsed_time": "0:33:44", "remaining_time": "0:05:33"}
{"current_steps": 260, "total_steps": 297, "loss": 1.7211034774780274, "lr": 8.468852088055291e-07, "epoch": 0.8768971332209107, "percentage": 87.54, "elapsed_time": "0:34:19", "remaining_time": "0:04:53"}
{"current_steps": 265, "total_steps": 297, "loss": 1.0896631240844727, "lr": 6.409407324267448e-07, "epoch": 0.893760539629005, "percentage": 89.23, "elapsed_time": "0:34:59", "remaining_time": "0:04:13"}
{"current_steps": 270, "total_steps": 297, "loss": 1.114693832397461, "lr": 4.628304925177318e-07, "epoch": 0.9106239460370995, "percentage": 90.91, "elapsed_time": "0:35:38", "remaining_time": "0:03:33"}
{"current_steps": 275, "total_steps": 297, "loss": 1.1860212326049804, "lr": 3.1308419643406915e-07, "epoch": 0.927487352445194, "percentage": 92.59, "elapsed_time": "0:36:18", "remaining_time": "0:02:54"}
{"current_steps": 280, "total_steps": 297, "loss": 1.1702337265014648, "lr": 1.921471959676957e-07, "epoch": 0.9443507588532883, "percentage": 94.28, "elapsed_time": "0:36:55", "remaining_time": "0:02:14"}
{"current_steps": 285, "total_steps": 297, "loss": 1.0407076835632325, "lr": 1.0037916285192129e-07, "epoch": 0.9612141652613828, "percentage": 95.96, "elapsed_time": "0:37:34", "remaining_time": "0:01:34"}
{"current_steps": 290, "total_steps": 297, "loss": 1.326705265045166, "lr": 3.805301908254455e-08, "epoch": 0.9780775716694773, "percentage": 97.64, "elapsed_time": "0:38:14", "remaining_time": "0:00:55"}
{"current_steps": 295, "total_steps": 297, "loss": 1.308372402191162, "lr": 5.354125236343155e-09, "epoch": 0.9949409780775716, "percentage": 99.33, "elapsed_time": "0:38:52", "remaining_time": "0:00:15"}
{"current_steps": 297, "total_steps": 297, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:39:06", "remaining_time": "0:00:00"}