aiAI_coder_V1.4B / trainer_log.jsonl
wefamm's picture
Upload folder using huggingface_hub
57ded2c verified
Raw History Blame Contribute Delete
16.1 kB
{"current_steps": 5, "total_steps": 315, "loss": 0.722562837600708, "lr": 4.998010925565448e-05, "epoch": 0.01591723040191007, "percentage": 1.59, "elapsed_time": "0:00:39", "remaining_time": "0:41:12", "throughput": 471.39, "total_tokens": 18800}
{"current_steps": 10, "total_steps": 315, "loss": 0.2945201873779297, "lr": 4.989935734988098e-05, "epoch": 0.03183446080382014, "percentage": 3.17, "elapsed_time": "0:01:17", "remaining_time": "0:39:36", "throughput": 475.99, "total_tokens": 37088}
{"current_steps": 15, "total_steps": 315, "loss": 0.17604056596755982, "lr": 4.975670171853926e-05, "epoch": 0.0477516912057302, "percentage": 4.76, "elapsed_time": "0:01:55", "remaining_time": "0:38:30", "throughput": 476.68, "total_tokens": 55072}
{"current_steps": 20, "total_steps": 315, "loss": 0.11049227714538574, "lr": 4.9552497026005974e-05, "epoch": 0.06366892160764027, "percentage": 6.35, "elapsed_time": "0:02:33", "remaining_time": "0:37:49", "throughput": 478.48, "total_tokens": 73632}
{"current_steps": 25, "total_steps": 315, "loss": 0.09105676412582397, "lr": 4.928725095732169e-05, "epoch": 0.07958615200955034, "percentage": 7.94, "elapsed_time": "0:03:11", "remaining_time": "0:37:06", "throughput": 481.84, "total_tokens": 92480}
{"current_steps": 30, "total_steps": 315, "loss": 0.10165604352951049, "lr": 4.896162295600589e-05, "epoch": 0.0955033824114604, "percentage": 9.52, "elapsed_time": "0:03:50", "remaining_time": "0:36:26", "throughput": 488.74, "total_tokens": 112464}
{"current_steps": 35, "total_steps": 315, "loss": 0.06480070948600769, "lr": 4.8576422584576514e-05, "epoch": 0.11142061281337047, "percentage": 11.11, "elapsed_time": "0:04:27", "remaining_time": "0:35:42", "throughput": 486.94, "total_tokens": 130432}
{"current_steps": 40, "total_steps": 315, "loss": 0.0799346923828125, "lr": 4.813260751184992e-05, "epoch": 0.12733784321528055, "percentage": 12.7, "elapsed_time": "0:05:05", "remaining_time": "0:35:02", "throughput": 483.26, "total_tokens": 147776}
{"current_steps": 45, "total_steps": 315, "loss": 0.11464616060256957, "lr": 4.763128113202537e-05, "epoch": 0.14325507361719061, "percentage": 14.29, "elapsed_time": "0:05:43", "remaining_time": "0:34:22", "throughput": 485.66, "total_tokens": 166960}
{"current_steps": 50, "total_steps": 315, "loss": 0.036882424354553224, "lr": 4.707368982147318e-05, "epoch": 0.15917230401910068, "percentage": 15.87, "elapsed_time": "0:06:21", "remaining_time": "0:33:43", "throughput": 483.64, "total_tokens": 184656}
{"current_steps": 55, "total_steps": 315, "loss": 0.05201725363731384, "lr": 4.6461219840046654e-05, "epoch": 0.17508953442101075, "percentage": 17.46, "elapsed_time": "0:06:59", "remaining_time": "0:33:03", "throughput": 480.48, "total_tokens": 201600}
{"current_steps": 60, "total_steps": 315, "loss": 0.02669697403907776, "lr": 4.579539388462173e-05, "epoch": 0.1910067648229208, "percentage": 19.05, "elapsed_time": "0:07:37", "remaining_time": "0:32:23", "throughput": 479.78, "total_tokens": 219424}
{"current_steps": 65, "total_steps": 315, "loss": 0.04229282438755035, "lr": 4.5077867303432546e-05, "epoch": 0.20692399522483088, "percentage": 20.63, "elapsed_time": "0:08:15", "remaining_time": "0:31:44", "throughput": 479.25, "total_tokens": 237328}
{"current_steps": 70, "total_steps": 315, "loss": 0.07041661143302917, "lr": 4.431042398061499e-05, "epoch": 0.22284122562674094, "percentage": 22.22, "elapsed_time": "0:08:53", "remaining_time": "0:31:06", "throughput": 480.66, "total_tokens": 256384}
{"current_steps": 75, "total_steps": 315, "loss": 0.07058953046798706, "lr": 4.34949719011896e-05, "epoch": 0.238758456028651, "percentage": 23.81, "elapsed_time": "0:09:31", "remaining_time": "0:30:28", "throughput": 482.59, "total_tokens": 275760}
{"current_steps": 80, "total_steps": 315, "loss": 0.04999509751796723, "lr": 4.263353840751022e-05, "epoch": 0.2546756864305611, "percentage": 25.4, "elapsed_time": "0:10:09", "remaining_time": "0:29:51", "throughput": 483.51, "total_tokens": 294912}
{"current_steps": 85, "total_steps": 315, "loss": 0.023084172606468202, "lr": 4.172826515897146e-05, "epoch": 0.27059291683247116, "percentage": 26.98, "elapsed_time": "0:10:47", "remaining_time": "0:29:12", "throughput": 483.01, "total_tokens": 312864}
{"current_steps": 90, "total_steps": 315, "loss": 0.027250510454177857, "lr": 4.078140280750597e-05, "epoch": 0.28651014723438123, "percentage": 28.57, "elapsed_time": "0:11:25", "remaining_time": "0:28:33", "throughput": 484.05, "total_tokens": 331824}
{"current_steps": 95, "total_steps": 315, "loss": 0.021656049787998198, "lr": 3.9795305402109195e-05, "epoch": 0.3024273776362913, "percentage": 30.16, "elapsed_time": "0:12:03", "remaining_time": "0:27:55", "throughput": 482.85, "total_tokens": 349248}
{"current_steps": 100, "total_steps": 315, "loss": 0.01830628514289856, "lr": 3.8772424536302564e-05, "epoch": 0.31834460803820136, "percentage": 31.75, "elapsed_time": "0:12:41", "remaining_time": "0:27:17", "throughput": 484.58, "total_tokens": 368960}
{"current_steps": 105, "total_steps": 315, "loss": 0.02595718502998352, "lr": 3.771530325308579e-05, "epoch": 0.3342618384401114, "percentage": 33.33, "elapsed_time": "0:13:19", "remaining_time": "0:26:39", "throughput": 484.26, "total_tokens": 387312}
{"current_steps": 110, "total_steps": 315, "loss": 0.03506172299385071, "lr": 3.662656972253127e-05, "epoch": 0.3501790688420215, "percentage": 34.92, "elapsed_time": "0:13:57", "remaining_time": "0:26:01", "throughput": 483.83, "total_tokens": 405344}
{"current_steps": 115, "total_steps": 315, "loss": 0.02651476263999939, "lr": 3.550893070773914e-05, "epoch": 0.36609629924393156, "percentage": 36.51, "elapsed_time": "0:14:36", "remaining_time": "0:25:23", "throughput": 483.7, "total_tokens": 423760}
{"current_steps": 120, "total_steps": 315, "loss": 0.019444951415061952, "lr": 3.436516483539781e-05, "epoch": 0.3820135296458416, "percentage": 38.1, "elapsed_time": "0:15:14", "remaining_time": "0:24:45", "throughput": 484.23, "total_tokens": 442656}
{"current_steps": 125, "total_steps": 315, "loss": 0.03442502021789551, "lr": 3.3198115687680115e-05, "epoch": 0.3979307600477517, "percentage": 39.68, "elapsed_time": "0:15:52", "remaining_time": "0:24:07", "throughput": 483.71, "total_tokens": 460592}
{"current_steps": 130, "total_steps": 315, "loss": 0.01847824454307556, "lr": 3.201068473265007e-05, "epoch": 0.41384799044966175, "percentage": 41.27, "elapsed_time": "0:16:30", "remaining_time": "0:23:29", "throughput": 483.64, "total_tokens": 478992}
{"current_steps": 135, "total_steps": 315, "loss": 0.019786083698272706, "lr": 3.0805824110756064e-05, "epoch": 0.4297652208515718, "percentage": 42.86, "elapsed_time": "0:17:08", "remaining_time": "0:22:51", "throughput": 485.03, "total_tokens": 498912}
{"current_steps": 140, "total_steps": 315, "loss": 0.018977819383144377, "lr": 2.958652929534456e-05, "epoch": 0.4456824512534819, "percentage": 44.44, "elapsed_time": "0:17:47", "remaining_time": "0:22:14", "throughput": 486.54, "total_tokens": 519280}
{"current_steps": 145, "total_steps": 315, "loss": 0.013403435051441193, "lr": 2.8355831645441388e-05, "epoch": 0.46159968165539195, "percentage": 46.03, "elapsed_time": "0:18:25", "remaining_time": "0:21:35", "throughput": 486.42, "total_tokens": 537680}
{"current_steps": 150, "total_steps": 315, "loss": 0.016910630464553832, "lr": 2.7116790869315582e-05, "epoch": 0.477516912057302, "percentage": 47.62, "elapsed_time": "0:19:03", "remaining_time": "0:20:58", "throughput": 486.76, "total_tokens": 556736}
{"current_steps": 155, "total_steps": 315, "loss": 0.026160690188407897, "lr": 2.587248741756253e-05, "epoch": 0.4934341424592121, "percentage": 49.21, "elapsed_time": "0:19:41", "remaining_time": "0:20:19", "throughput": 486.49, "total_tokens": 574848}
{"current_steps": 160, "total_steps": 315, "loss": 0.014300110936164855, "lr": 2.4626014824618415e-05, "epoch": 0.5093513728611222, "percentage": 50.79, "elapsed_time": "0:20:20", "remaining_time": "0:19:42", "throughput": 487.79, "total_tokens": 595184}
{"current_steps": 165, "total_steps": 315, "loss": 0.01761966049671173, "lr": 2.3380472017746202e-05, "epoch": 0.5252686032630323, "percentage": 52.38, "elapsed_time": "0:20:58", "remaining_time": "0:19:04", "throughput": 488.11, "total_tokens": 614240}
{"current_steps": 170, "total_steps": 315, "loss": 0.02411275953054428, "lr": 2.2138955612614207e-05, "epoch": 0.5411858336649423, "percentage": 53.97, "elapsed_time": "0:21:37", "remaining_time": "0:18:26", "throughput": 489.44, "total_tokens": 634816}
{"current_steps": 175, "total_steps": 315, "loss": 0.02472930997610092, "lr": 2.090455221462156e-05, "epoch": 0.5571030640668524, "percentage": 55.56, "elapsed_time": "0:22:14", "remaining_time": "0:17:47", "throughput": 489.32, "total_tokens": 653200}
{"current_steps": 180, "total_steps": 315, "loss": 0.0432051956653595, "lr": 1.9680330745110954e-05, "epoch": 0.5730202944687625, "percentage": 57.14, "elapsed_time": "0:22:52", "remaining_time": "0:17:09", "throughput": 488.88, "total_tokens": 671184}
{"current_steps": 185, "total_steps": 315, "loss": 0.015968725085258484, "lr": 1.8469334811546542e-05, "epoch": 0.5889375248706725, "percentage": 58.73, "elapsed_time": "0:23:31", "remaining_time": "0:16:31", "throughput": 488.41, "total_tokens": 689328}
{"current_steps": 190, "total_steps": 315, "loss": 0.020535998046398163, "lr": 1.7274575140626318e-05, "epoch": 0.6048547552725826, "percentage": 60.32, "elapsed_time": "0:24:09", "remaining_time": "0:15:53", "throughput": 487.99, "total_tokens": 707312}
{"current_steps": 195, "total_steps": 315, "loss": 0.017926733195781707, "lr": 1.609902209314108e-05, "epoch": 0.6207719856744927, "percentage": 61.9, "elapsed_time": "0:24:47", "remaining_time": "0:15:15", "throughput": 488.51, "total_tokens": 726832}
{"current_steps": 200, "total_steps": 315, "loss": 0.020335957407951355, "lr": 1.4945598279189565e-05, "epoch": 0.6366892160764027, "percentage": 63.49, "elapsed_time": "0:25:26", "remaining_time": "0:14:37", "throughput": 488.21, "total_tokens": 745184}
{"current_steps": 205, "total_steps": 315, "loss": 0.012867054343223572, "lr": 1.3817171292109183e-05, "epoch": 0.6526064464783128, "percentage": 65.08, "elapsed_time": "0:26:05", "remaining_time": "0:13:59", "throughput": 488.12, "total_tokens": 764064}
{"current_steps": 210, "total_steps": 315, "loss": 0.012676186859607697, "lr": 1.271654657918722e-05, "epoch": 0.6685236768802229, "percentage": 66.67, "elapsed_time": "0:26:43", "remaining_time": "0:13:21", "throughput": 488.41, "total_tokens": 783216}
{"current_steps": 215, "total_steps": 315, "loss": 0.013275411725044251, "lr": 1.1646460466876783e-05, "epoch": 0.6844409072821329, "percentage": 68.25, "elapsed_time": "0:27:23", "remaining_time": "0:12:44", "throughput": 489.17, "total_tokens": 803760}
{"current_steps": 220, "total_steps": 315, "loss": 0.015906769037246703, "lr": 1.0609573357858166e-05, "epoch": 0.700358137684043, "percentage": 69.84, "elapsed_time": "0:28:01", "remaining_time": "0:12:06", "throughput": 489.07, "total_tokens": 822352}
{"current_steps": 225, "total_steps": 315, "loss": 0.06054983139038086, "lr": 9.608463116858542e-06, "epoch": 0.716275368085953, "percentage": 71.43, "elapsed_time": "0:28:39", "remaining_time": "0:11:27", "throughput": 488.36, "total_tokens": 839776}
{"current_steps": 230, "total_steps": 315, "loss": 0.0126905158162117, "lr": 8.645618661674142e-06, "epoch": 0.7321925984878631, "percentage": 73.02, "elapsed_time": "0:29:18", "remaining_time": "0:10:49", "throughput": 487.96, "total_tokens": 857904}
{"current_steps": 235, "total_steps": 315, "loss": 0.018532435595989227, "lr": 7.723433775328384e-06, "epoch": 0.7481098288897732, "percentage": 74.6, "elapsed_time": "0:29:56", "remaining_time": "0:10:11", "throughput": 487.47, "total_tokens": 875536}
{"current_steps": 240, "total_steps": 315, "loss": 0.017641636729240417, "lr": 6.844201154750177e-06, "epoch": 0.7640270592916832, "percentage": 76.19, "elapsed_time": "0:30:34", "remaining_time": "0:09:33", "throughput": 487.35, "total_tokens": 893952}
{"current_steps": 245, "total_steps": 315, "loss": 0.014852634072303772, "lr": 6.010106710768052e-06, "epoch": 0.7799442896935933, "percentage": 77.78, "elapsed_time": "0:31:12", "remaining_time": "0:08:55", "throughput": 486.95, "total_tokens": 911888}
{"current_steps": 250, "total_steps": 315, "loss": 0.013549965620040894, "lr": 5.223224133591476e-06, "epoch": 0.7958615200955034, "percentage": 79.37, "elapsed_time": "0:31:51", "remaining_time": "0:08:16", "throughput": 487.45, "total_tokens": 931552}
{"current_steps": 255, "total_steps": 315, "loss": 0.016868625581264497, "lr": 4.4855097372902135e-06, "epoch": 0.8117787504974134, "percentage": 80.95, "elapsed_time": "0:32:29", "remaining_time": "0:07:38", "throughput": 487.98, "total_tokens": 951232}
{"current_steps": 260, "total_steps": 315, "loss": 0.02409391403198242, "lr": 3.798797596089351e-06, "epoch": 0.8276959808993235, "percentage": 82.54, "elapsed_time": "0:33:08", "remaining_time": "0:07:00", "throughput": 488.49, "total_tokens": 971248}
{"current_steps": 265, "total_steps": 315, "loss": 0.014366105198860168, "lr": 3.164794984571759e-06, "epoch": 0.8436132113012336, "percentage": 84.13, "elapsed_time": "0:33:46", "remaining_time": "0:06:22", "throughput": 488.35, "total_tokens": 989568}
{"current_steps": 270, "total_steps": 315, "loss": 0.019769111275672914, "lr": 2.58507813312448e-06, "epoch": 0.8595304417031436, "percentage": 85.71, "elapsed_time": "0:34:24", "remaining_time": "0:05:44", "throughput": 488.39, "total_tokens": 1008400}
{"current_steps": 275, "total_steps": 315, "loss": 0.012975563108921052, "lr": 2.0610883091816525e-06, "epoch": 0.8754476721050537, "percentage": 87.3, "elapsed_time": "0:35:03", "remaining_time": "0:05:05", "throughput": 488.16, "total_tokens": 1026832}
{"current_steps": 280, "total_steps": 315, "loss": 0.02301923781633377, "lr": 1.59412823400657e-06, "epoch": 0.8913649025069638, "percentage": 88.89, "elapsed_time": "0:35:41", "remaining_time": "0:04:27", "throughput": 488.23, "total_tokens": 1045568}
{"current_steps": 285, "total_steps": 315, "loss": 0.013730129599571228, "lr": 1.1853588439213442e-06, "epoch": 0.9072821329088738, "percentage": 90.48, "elapsed_time": "0:36:20", "remaining_time": "0:03:49", "throughput": 488.27, "total_tokens": 1064448}
{"current_steps": 290, "total_steps": 315, "loss": 0.01429380029439926, "lr": 8.357964040363209e-07, "epoch": 0.9231993633107839, "percentage": 92.06, "elapsed_time": "0:36:58", "remaining_time": "0:03:11", "throughput": 487.89, "total_tokens": 1082240}
{"current_steps": 295, "total_steps": 315, "loss": 0.01451290100812912, "lr": 5.463099816548579e-07, "epoch": 0.939116593712694, "percentage": 93.65, "elapsed_time": "0:37:36", "remaining_time": "0:02:32", "throughput": 487.8, "total_tokens": 1100608}
{"current_steps": 300, "total_steps": 315, "loss": 0.015449412167072296, "lr": 3.1761928563510955e-07, "epoch": 0.955033824114604, "percentage": 95.24, "elapsed_time": "0:38:14", "remaining_time": "0:01:54", "throughput": 487.81, "total_tokens": 1119264}
{"current_steps": 305, "total_steps": 315, "loss": 0.01347261518239975, "lr": 1.5029287708036854e-07, "epoch": 0.9709510545165141, "percentage": 96.83, "elapsed_time": "0:38:53", "remaining_time": "0:01:16", "throughput": 487.41, "total_tokens": 1137216}
{"current_steps": 310, "total_steps": 315, "loss": 0.020735736191272735, "lr": 4.474675580662113e-08, "epoch": 0.9868682849184242, "percentage": 98.41, "elapsed_time": "0:39:31", "remaining_time": "0:00:38", "throughput": 487.35, "total_tokens": 1155552}
{"current_steps": 315, "total_steps": 315, "loss": 0.01795462816953659, "lr": 1.2433261014244136e-09, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:40:02", "remaining_time": "0:00:00", "throughput": 487.24, "total_tokens": 1170680}
{"current_steps": 315, "total_steps": 315, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:40:03", "remaining_time": "0:00:00", "throughput": 487.12, "total_tokens": 1170680}