| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.5978367748279254, | |
| "eval_steps": 35, | |
| "global_step": 3250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.4860678577282414e-05, | |
| "loss": 2.6111, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.0262463092803955, | |
| "eval_runtime": 11.4452, | |
| "eval_samples_per_second": 1.835, | |
| "eval_steps_per_second": 0.262, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.471725946566137e-05, | |
| "loss": 2.2099, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.8728946447372437, | |
| "eval_runtime": 11.4415, | |
| "eval_samples_per_second": 1.835, | |
| "eval_steps_per_second": 0.262, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.4573840354040322e-05, | |
| "loss": 2.1297, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8009727001190186, | |
| "eval_runtime": 11.4312, | |
| "eval_samples_per_second": 1.837, | |
| "eval_steps_per_second": 0.262, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.4430421242419278e-05, | |
| "loss": 2.0376, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.7509633302688599, | |
| "eval_runtime": 11.4441, | |
| "eval_samples_per_second": 1.835, | |
| "eval_steps_per_second": 0.262, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.428700213079823e-05, | |
| "loss": 2.0077, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.7361119985580444, | |
| "eval_runtime": 11.4061, | |
| "eval_samples_per_second": 1.841, | |
| "eval_steps_per_second": 0.263, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.4143583019177186e-05, | |
| "loss": 1.9427, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.7030919790267944, | |
| "eval_runtime": 11.3698, | |
| "eval_samples_per_second": 1.847, | |
| "eval_steps_per_second": 0.264, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.4000163907556138e-05, | |
| "loss": 1.9224, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.6869089603424072, | |
| "eval_runtime": 11.4842, | |
| "eval_samples_per_second": 1.829, | |
| "eval_steps_per_second": 0.261, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.3856744795935094e-05, | |
| "loss": 1.9088, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.6638721227645874, | |
| "eval_runtime": 11.4694, | |
| "eval_samples_per_second": 1.831, | |
| "eval_steps_per_second": 0.262, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.3713325684314046e-05, | |
| "loss": 1.9012, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.6475718021392822, | |
| "eval_runtime": 11.4639, | |
| "eval_samples_per_second": 1.832, | |
| "eval_steps_per_second": 0.262, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.3569906572693e-05, | |
| "loss": 1.8873, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.6309669017791748, | |
| "eval_runtime": 11.4991, | |
| "eval_samples_per_second": 1.826, | |
| "eval_steps_per_second": 0.261, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.3426487461071954e-05, | |
| "loss": 1.881, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.6221837997436523, | |
| "eval_runtime": 11.509, | |
| "eval_samples_per_second": 1.825, | |
| "eval_steps_per_second": 0.261, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.328306834945091e-05, | |
| "loss": 1.8931, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.6102544069290161, | |
| "eval_runtime": 11.52, | |
| "eval_samples_per_second": 1.823, | |
| "eval_steps_per_second": 0.26, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.3139649237829865e-05, | |
| "loss": 1.8524, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.607195496559143, | |
| "eval_runtime": 11.4864, | |
| "eval_samples_per_second": 1.828, | |
| "eval_steps_per_second": 0.261, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.299623012620882e-05, | |
| "loss": 1.8498, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.5910367965698242, | |
| "eval_runtime": 11.4927, | |
| "eval_samples_per_second": 1.827, | |
| "eval_steps_per_second": 0.261, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.2852811014587773e-05, | |
| "loss": 1.8194, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.5871880054473877, | |
| "eval_runtime": 11.4668, | |
| "eval_samples_per_second": 1.831, | |
| "eval_steps_per_second": 0.262, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.270939190296673e-05, | |
| "loss": 1.8619, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.577917218208313, | |
| "eval_runtime": 11.4911, | |
| "eval_samples_per_second": 1.828, | |
| "eval_steps_per_second": 0.261, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.256597279134568e-05, | |
| "loss": 1.8458, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.569788932800293, | |
| "eval_runtime": 11.4523, | |
| "eval_samples_per_second": 1.834, | |
| "eval_steps_per_second": 0.262, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.2422553679724637e-05, | |
| "loss": 1.7886, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.5579793453216553, | |
| "eval_runtime": 11.4733, | |
| "eval_samples_per_second": 1.83, | |
| "eval_steps_per_second": 0.261, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.227913456810359e-05, | |
| "loss": 1.8302, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.5591094493865967, | |
| "eval_runtime": 11.5195, | |
| "eval_samples_per_second": 1.823, | |
| "eval_steps_per_second": 0.26, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.2135715456482545e-05, | |
| "loss": 1.8173, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.5488135814666748, | |
| "eval_runtime": 11.5232, | |
| "eval_samples_per_second": 1.822, | |
| "eval_steps_per_second": 0.26, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.1992296344861498e-05, | |
| "loss": 1.822, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.5554958581924438, | |
| "eval_runtime": 11.4539, | |
| "eval_samples_per_second": 1.833, | |
| "eval_steps_per_second": 0.262, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.1848877233240453e-05, | |
| "loss": 1.7775, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.5420997142791748, | |
| "eval_runtime": 11.4375, | |
| "eval_samples_per_second": 1.836, | |
| "eval_steps_per_second": 0.262, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.1705458121619406e-05, | |
| "loss": 1.8007, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.530941367149353, | |
| "eval_runtime": 11.5016, | |
| "eval_samples_per_second": 1.826, | |
| "eval_steps_per_second": 0.261, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.156203900999836e-05, | |
| "loss": 1.802, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.5383422374725342, | |
| "eval_runtime": 11.502, | |
| "eval_samples_per_second": 1.826, | |
| "eval_steps_per_second": 0.261, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.1418619898377314e-05, | |
| "loss": 1.7921, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.5289701223373413, | |
| "eval_runtime": 11.4801, | |
| "eval_samples_per_second": 1.829, | |
| "eval_steps_per_second": 0.261, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.127520078675627e-05, | |
| "loss": 1.7741, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.5224323272705078, | |
| "eval_runtime": 11.4514, | |
| "eval_samples_per_second": 1.834, | |
| "eval_steps_per_second": 0.262, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.1131781675135225e-05, | |
| "loss": 1.7642, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.5138221979141235, | |
| "eval_runtime": 11.4557, | |
| "eval_samples_per_second": 1.833, | |
| "eval_steps_per_second": 0.262, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.098836256351418e-05, | |
| "loss": 1.7763, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.5038686990737915, | |
| "eval_runtime": 11.491, | |
| "eval_samples_per_second": 1.828, | |
| "eval_steps_per_second": 0.261, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.0844943451893133e-05, | |
| "loss": 1.744, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.5031676292419434, | |
| "eval_runtime": 11.541, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 0.26, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.070152434027209e-05, | |
| "loss": 1.7968, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.507965326309204, | |
| "eval_runtime": 11.5281, | |
| "eval_samples_per_second": 1.822, | |
| "eval_steps_per_second": 0.26, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.055810522865104e-05, | |
| "loss": 1.7192, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.4997100830078125, | |
| "eval_runtime": 11.4603, | |
| "eval_samples_per_second": 1.832, | |
| "eval_steps_per_second": 0.262, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.0414686117029997e-05, | |
| "loss": 1.7469, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.4938936233520508, | |
| "eval_runtime": 11.5073, | |
| "eval_samples_per_second": 1.825, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.027126700540895e-05, | |
| "loss": 1.7566, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.4912477731704712, | |
| "eval_runtime": 11.5141, | |
| "eval_samples_per_second": 1.824, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0127847893787905e-05, | |
| "loss": 1.7395, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.4848188161849976, | |
| "eval_runtime": 11.5052, | |
| "eval_samples_per_second": 1.825, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.9984428782166857e-05, | |
| "loss": 1.7555, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.4838807582855225, | |
| "eval_runtime": 11.4789, | |
| "eval_samples_per_second": 1.829, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9841009670545813e-05, | |
| "loss": 1.7447, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.4835803508758545, | |
| "eval_runtime": 11.5109, | |
| "eval_samples_per_second": 1.824, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.9697590558924765e-05, | |
| "loss": 1.7375, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.483397126197815, | |
| "eval_runtime": 11.4887, | |
| "eval_samples_per_second": 1.828, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.955417144730372e-05, | |
| "loss": 1.7565, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.480878233909607, | |
| "eval_runtime": 11.4732, | |
| "eval_samples_per_second": 1.83, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.9410752335682677e-05, | |
| "loss": 1.6992, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.471764087677002, | |
| "eval_runtime": 11.4976, | |
| "eval_samples_per_second": 1.826, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.926733322406163e-05, | |
| "loss": 1.7588, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.4718772172927856, | |
| "eval_runtime": 11.4494, | |
| "eval_samples_per_second": 1.834, | |
| "eval_steps_per_second": 0.262, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.9123914112440585e-05, | |
| "loss": 1.7459, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.4739229679107666, | |
| "eval_runtime": 11.4772, | |
| "eval_samples_per_second": 1.83, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.898049500081954e-05, | |
| "loss": 1.7496, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.4594241380691528, | |
| "eval_runtime": 11.4774, | |
| "eval_samples_per_second": 1.83, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.8837075889198493e-05, | |
| "loss": 1.7217, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.4519307613372803, | |
| "eval_runtime": 11.4991, | |
| "eval_samples_per_second": 1.826, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8693656777577448e-05, | |
| "loss": 1.7379, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.450444221496582, | |
| "eval_runtime": 11.4875, | |
| "eval_samples_per_second": 1.828, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.85502376659564e-05, | |
| "loss": 1.7178, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.4498975276947021, | |
| "eval_runtime": 11.4834, | |
| "eval_samples_per_second": 1.829, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.8406818554335356e-05, | |
| "loss": 1.726, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.4456058740615845, | |
| "eval_runtime": 11.4896, | |
| "eval_samples_per_second": 1.828, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.826339944271431e-05, | |
| "loss": 1.6916, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.4492512941360474, | |
| "eval_runtime": 11.4853, | |
| "eval_samples_per_second": 1.828, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.8119980331093264e-05, | |
| "loss": 1.7388, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.4481810331344604, | |
| "eval_runtime": 11.5015, | |
| "eval_samples_per_second": 1.826, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.7976561219472217e-05, | |
| "loss": 1.7026, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.4463753700256348, | |
| "eval_runtime": 11.4964, | |
| "eval_samples_per_second": 1.827, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.7833142107851172e-05, | |
| "loss": 1.7025, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.4447450637817383, | |
| "eval_runtime": 11.5592, | |
| "eval_samples_per_second": 1.817, | |
| "eval_steps_per_second": 0.26, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.7689722996230128e-05, | |
| "loss": 1.7497, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.442565679550171, | |
| "eval_runtime": 11.4749, | |
| "eval_samples_per_second": 1.83, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.754630388460908e-05, | |
| "loss": 1.7545, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.4413307905197144, | |
| "eval_runtime": 11.4848, | |
| "eval_samples_per_second": 1.829, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.7402884772988036e-05, | |
| "loss": 1.6951, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.440474033355713, | |
| "eval_runtime": 11.5878, | |
| "eval_samples_per_second": 1.812, | |
| "eval_steps_per_second": 0.259, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.725946566136699e-05, | |
| "loss": 1.7432, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.4366823434829712, | |
| "eval_runtime": 11.5531, | |
| "eval_samples_per_second": 1.818, | |
| "eval_steps_per_second": 0.26, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.7116046549745944e-05, | |
| "loss": 1.7153, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.4368674755096436, | |
| "eval_runtime": 11.4927, | |
| "eval_samples_per_second": 1.827, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.69726274381249e-05, | |
| "loss": 1.732, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.4359997510910034, | |
| "eval_runtime": 11.4761, | |
| "eval_samples_per_second": 1.83, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.6829208326503852e-05, | |
| "loss": 1.7143, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.437907338142395, | |
| "eval_runtime": 11.5143, | |
| "eval_samples_per_second": 1.824, | |
| "eval_steps_per_second": 0.261, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6685789214882808e-05, | |
| "loss": 1.7072, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.4374998807907104, | |
| "eval_runtime": 11.4633, | |
| "eval_samples_per_second": 1.832, | |
| "eval_steps_per_second": 0.262, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.654237010326176e-05, | |
| "loss": 1.591, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.4363301992416382, | |
| "eval_runtime": 11.4952, | |
| "eval_samples_per_second": 1.827, | |
| "eval_steps_per_second": 0.261, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.6398950991640716e-05, | |
| "loss": 1.549, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 1.4447616338729858, | |
| "eval_runtime": 11.4847, | |
| "eval_samples_per_second": 1.829, | |
| "eval_steps_per_second": 0.261, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.6255531880019668e-05, | |
| "loss": 1.5636, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 1.4376814365386963, | |
| "eval_runtime": 11.5477, | |
| "eval_samples_per_second": 1.819, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.6112112768398624e-05, | |
| "loss": 1.5629, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.4429987668991089, | |
| "eval_runtime": 11.5258, | |
| "eval_samples_per_second": 1.822, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.596869365677758e-05, | |
| "loss": 1.5539, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.4357415437698364, | |
| "eval_runtime": 11.5216, | |
| "eval_samples_per_second": 1.823, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.5825274545156532e-05, | |
| "loss": 1.574, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 1.4316208362579346, | |
| "eval_runtime": 11.5068, | |
| "eval_samples_per_second": 1.825, | |
| "eval_steps_per_second": 0.261, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.5681855433535488e-05, | |
| "loss": 1.5976, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.4350919723510742, | |
| "eval_runtime": 11.554, | |
| "eval_samples_per_second": 1.818, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.553843632191444e-05, | |
| "loss": 1.6087, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.4374239444732666, | |
| "eval_runtime": 11.5273, | |
| "eval_samples_per_second": 1.822, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.5395017210293396e-05, | |
| "loss": 1.5684, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 1.4325898885726929, | |
| "eval_runtime": 11.558, | |
| "eval_samples_per_second": 1.817, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.5251598098672348e-05, | |
| "loss": 1.5858, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 1.437401294708252, | |
| "eval_runtime": 11.542, | |
| "eval_samples_per_second": 1.819, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.5108178987051302e-05, | |
| "loss": 1.5768, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.437371015548706, | |
| "eval_runtime": 11.5127, | |
| "eval_samples_per_second": 1.824, | |
| "eval_steps_per_second": 0.261, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.496475987543026e-05, | |
| "loss": 1.5719, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.4342734813690186, | |
| "eval_runtime": 11.5878, | |
| "eval_samples_per_second": 1.812, | |
| "eval_steps_per_second": 0.259, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.4821340763809213e-05, | |
| "loss": 1.5661, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 1.4325451850891113, | |
| "eval_runtime": 11.5679, | |
| "eval_samples_per_second": 1.815, | |
| "eval_steps_per_second": 0.259, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.4677921652188167e-05, | |
| "loss": 1.571, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 1.4307782649993896, | |
| "eval_runtime": 11.5174, | |
| "eval_samples_per_second": 1.823, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.4534502540567121e-05, | |
| "loss": 1.54, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 1.4300092458724976, | |
| "eval_runtime": 11.5587, | |
| "eval_samples_per_second": 1.817, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.4391083428946075e-05, | |
| "loss": 1.5275, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.4285993576049805, | |
| "eval_runtime": 11.5338, | |
| "eval_samples_per_second": 1.821, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.424766431732503e-05, | |
| "loss": 1.5837, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 1.4346880912780762, | |
| "eval_runtime": 11.5585, | |
| "eval_samples_per_second": 1.817, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.4104245205703983e-05, | |
| "loss": 1.571, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 1.4264836311340332, | |
| "eval_runtime": 11.5547, | |
| "eval_samples_per_second": 1.817, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.3960826094082937e-05, | |
| "loss": 1.5538, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.424988865852356, | |
| "eval_runtime": 11.5078, | |
| "eval_samples_per_second": 1.825, | |
| "eval_steps_per_second": 0.261, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.3817406982461891e-05, | |
| "loss": 1.5634, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 1.4214783906936646, | |
| "eval_runtime": 11.5523, | |
| "eval_samples_per_second": 1.818, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.3673987870840845e-05, | |
| "loss": 1.5762, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.417558193206787, | |
| "eval_runtime": 11.5881, | |
| "eval_samples_per_second": 1.812, | |
| "eval_steps_per_second": 0.259, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.35305687592198e-05, | |
| "loss": 1.5574, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 1.4196423292160034, | |
| "eval_runtime": 11.5684, | |
| "eval_samples_per_second": 1.815, | |
| "eval_steps_per_second": 0.259, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.3387149647598754e-05, | |
| "loss": 1.5783, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 1.42311429977417, | |
| "eval_runtime": 11.5665, | |
| "eval_samples_per_second": 1.816, | |
| "eval_steps_per_second": 0.259, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.3243730535977708e-05, | |
| "loss": 1.576, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 1.4219133853912354, | |
| "eval_runtime": 11.5466, | |
| "eval_samples_per_second": 1.819, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.3100311424356662e-05, | |
| "loss": 1.6013, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 1.4164221286773682, | |
| "eval_runtime": 11.5232, | |
| "eval_samples_per_second": 1.822, | |
| "eval_steps_per_second": 0.26, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.2956892312735619e-05, | |
| "loss": 1.5824, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 1.4148584604263306, | |
| "eval_runtime": 11.494, | |
| "eval_samples_per_second": 1.827, | |
| "eval_steps_per_second": 0.261, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.2813473201114573e-05, | |
| "loss": 1.5954, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 1.4142621755599976, | |
| "eval_runtime": 11.564, | |
| "eval_samples_per_second": 1.816, | |
| "eval_steps_per_second": 0.259, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.2670054089493527e-05, | |
| "loss": 1.5621, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.4165393114089966, | |
| "eval_runtime": 11.5455, | |
| "eval_samples_per_second": 1.819, | |
| "eval_steps_per_second": 0.26, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.2526634977872481e-05, | |
| "loss": 1.5877, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.41389000415802, | |
| "eval_runtime": 11.5632, | |
| "eval_samples_per_second": 1.816, | |
| "eval_steps_per_second": 0.259, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.2383215866251435e-05, | |
| "loss": 1.5843, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 1.409727931022644, | |
| "eval_runtime": 11.5302, | |
| "eval_samples_per_second": 1.821, | |
| "eval_steps_per_second": 0.26, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.2239796754630389e-05, | |
| "loss": 1.5255, | |
| "step": 3115 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 1.419966697692871, | |
| "eval_runtime": 11.5457, | |
| "eval_samples_per_second": 1.819, | |
| "eval_steps_per_second": 0.26, | |
| "step": 3115 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.2096377643009343e-05, | |
| "loss": 1.55, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 1.4153906106948853, | |
| "eval_runtime": 11.5656, | |
| "eval_samples_per_second": 1.816, | |
| "eval_steps_per_second": 0.259, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.1952958531388297e-05, | |
| "loss": 1.5519, | |
| "step": 3185 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 1.4161474704742432, | |
| "eval_runtime": 11.5425, | |
| "eval_samples_per_second": 1.819, | |
| "eval_steps_per_second": 0.26, | |
| "step": 3185 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.1809539419767251e-05, | |
| "loss": 1.5273, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.416408658027649, | |
| "eval_runtime": 11.5376, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 0.26, | |
| "step": 3220 | |
| } | |
| ], | |
| "logging_steps": 35, | |
| "max_steps": 6102, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 250, | |
| "total_flos": 1.093574423789568e+18, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |