| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 785, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 6.653893265217805, | |
| "learning_rate": 2.0253164556962026e-06, | |
| "loss": 0.7986, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.2182871699333191, | |
| "step": 5, | |
| "valid_targets_mean": 3853.9, | |
| "valid_targets_min": 485 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 4.269038223889598, | |
| "learning_rate": 4.556962025316456e-06, | |
| "loss": 0.788, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.16510218381881714, | |
| "step": 10, | |
| "valid_targets_mean": 3270.2, | |
| "valid_targets_min": 397 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 2.454564454487919, | |
| "learning_rate": 7.08860759493671e-06, | |
| "loss": 0.7233, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.15986603498458862, | |
| "step": 15, | |
| "valid_targets_mean": 4003.4, | |
| "valid_targets_min": 539 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.9816739115067487, | |
| "learning_rate": 9.620253164556963e-06, | |
| "loss": 0.6681, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1633913218975067, | |
| "step": 20, | |
| "valid_targets_mean": 4015.0, | |
| "valid_targets_min": 948 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.8392124404156497, | |
| "learning_rate": 1.2151898734177216e-05, | |
| "loss": 0.6424, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1591624915599823, | |
| "step": 25, | |
| "valid_targets_mean": 3975.4, | |
| "valid_targets_min": 437 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.6278174642292738, | |
| "learning_rate": 1.468354430379747e-05, | |
| "loss": 0.6069, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.14224126935005188, | |
| "step": 30, | |
| "valid_targets_mean": 4139.2, | |
| "valid_targets_min": 858 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.48936271109548074, | |
| "learning_rate": 1.7215189873417723e-05, | |
| "loss": 0.5879, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.14971768856048584, | |
| "step": 35, | |
| "valid_targets_mean": 4122.9, | |
| "valid_targets_min": 980 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.39715244899609475, | |
| "learning_rate": 1.974683544303798e-05, | |
| "loss": 0.5645, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.15213561058044434, | |
| "step": 40, | |
| "valid_targets_mean": 3704.0, | |
| "valid_targets_min": 559 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.481203351625684, | |
| "learning_rate": 2.2278481012658228e-05, | |
| "loss": 0.5371, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1108769029378891, | |
| "step": 45, | |
| "valid_targets_mean": 2972.7, | |
| "valid_targets_min": 499 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.321908100981505, | |
| "learning_rate": 2.481012658227848e-05, | |
| "loss": 0.5163, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12353712320327759, | |
| "step": 50, | |
| "valid_targets_mean": 3611.0, | |
| "valid_targets_min": 607 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 0.3120264870764351, | |
| "learning_rate": 2.7341772151898737e-05, | |
| "loss": 0.4924, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1275099366903305, | |
| "step": 55, | |
| "valid_targets_mean": 3764.9, | |
| "valid_targets_min": 615 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.3116456202990188, | |
| "learning_rate": 2.987341772151899e-05, | |
| "loss": 0.4905, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.13120296597480774, | |
| "step": 60, | |
| "valid_targets_mean": 3701.8, | |
| "valid_targets_min": 478 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 0.3042602953799047, | |
| "learning_rate": 3.240506329113924e-05, | |
| "loss": 0.4929, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10789033025503159, | |
| "step": 65, | |
| "valid_targets_mean": 3453.6, | |
| "valid_targets_min": 550 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 0.2990455658223868, | |
| "learning_rate": 3.49367088607595e-05, | |
| "loss": 0.4812, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11050158739089966, | |
| "step": 70, | |
| "valid_targets_mean": 3045.1, | |
| "valid_targets_min": 343 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.28570483366239047, | |
| "learning_rate": 3.746835443037975e-05, | |
| "loss": 0.4649, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12902486324310303, | |
| "step": 75, | |
| "valid_targets_mean": 4832.9, | |
| "valid_targets_min": 484 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.3078705603731694, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4685, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10504810512065887, | |
| "step": 80, | |
| "valid_targets_mean": 2656.4, | |
| "valid_targets_min": 472 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 0.29785746823270953, | |
| "learning_rate": 3.999504991751045e-05, | |
| "loss": 0.4703, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10425898432731628, | |
| "step": 85, | |
| "valid_targets_mean": 3285.2, | |
| "valid_targets_min": 522 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 0.3329140550575177, | |
| "learning_rate": 3.9980202120373464e-05, | |
| "loss": 0.4646, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11807519197463989, | |
| "step": 90, | |
| "valid_targets_mean": 3115.9, | |
| "valid_targets_min": 503 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 0.30756921786044894, | |
| "learning_rate": 3.995546395837111e-05, | |
| "loss": 0.4513, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12577059864997864, | |
| "step": 95, | |
| "valid_targets_mean": 3942.8, | |
| "valid_targets_min": 482 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.297419707761942, | |
| "learning_rate": 3.992084767709763e-05, | |
| "loss": 0.4629, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11425703018903732, | |
| "step": 100, | |
| "valid_targets_mean": 3709.5, | |
| "valid_targets_min": 529 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 0.30400225439206074, | |
| "learning_rate": 3.987637041189781e-05, | |
| "loss": 0.4518, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10863518714904785, | |
| "step": 105, | |
| "valid_targets_mean": 3144.2, | |
| "valid_targets_min": 646 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 0.3177865182010035, | |
| "learning_rate": 3.982205417938482e-05, | |
| "loss": 0.4418, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12408401072025299, | |
| "step": 110, | |
| "valid_targets_mean": 3891.9, | |
| "valid_targets_min": 553 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 0.3036067722625731, | |
| "learning_rate": 3.975792586654179e-05, | |
| "loss": 0.4464, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11416186392307281, | |
| "step": 115, | |
| "valid_targets_mean": 3774.4, | |
| "valid_targets_min": 460 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.34203845327928967, | |
| "learning_rate": 3.968401721741259e-05, | |
| "loss": 0.4462, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10648570954799652, | |
| "step": 120, | |
| "valid_targets_mean": 3662.1, | |
| "valid_targets_min": 421 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.2913361988490416, | |
| "learning_rate": 3.960036481738819e-05, | |
| "loss": 0.448, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10248115658760071, | |
| "step": 125, | |
| "valid_targets_mean": 3422.8, | |
| "valid_targets_min": 764 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 0.3432190627348251, | |
| "learning_rate": 3.950701007509667e-05, | |
| "loss": 0.4279, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10087063908576965, | |
| "step": 130, | |
| "valid_targets_mean": 3340.4, | |
| "valid_targets_min": 475 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.31391476251217776, | |
| "learning_rate": 3.940399920190552e-05, | |
| "loss": 0.4192, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10765115916728973, | |
| "step": 135, | |
| "valid_targets_mean": 3240.6, | |
| "valid_targets_min": 478 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 0.3126293882942313, | |
| "learning_rate": 3.92913831890467e-05, | |
| "loss": 0.4295, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1005314439535141, | |
| "step": 140, | |
| "valid_targets_mean": 3031.4, | |
| "valid_targets_min": 397 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 0.3292337991876051, | |
| "learning_rate": 3.916921778237556e-05, | |
| "loss": 0.4344, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0934506356716156, | |
| "step": 145, | |
| "valid_targets_mean": 3086.1, | |
| "valid_targets_min": 484 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3323908164835582, | |
| "learning_rate": 3.903756345477612e-05, | |
| "loss": 0.4183, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10864369571208954, | |
| "step": 150, | |
| "valid_targets_mean": 3421.8, | |
| "valid_targets_min": 638 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 0.318993666997237, | |
| "learning_rate": 3.889648537622657e-05, | |
| "loss": 0.4239, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10692336410284042, | |
| "step": 155, | |
| "valid_targets_mean": 3036.9, | |
| "valid_targets_min": 342 | |
| }, | |
| { | |
| "epoch": 1.0192, | |
| "grad_norm": 0.32983428761792527, | |
| "learning_rate": 3.874605338153952e-05, | |
| "loss": 0.4313, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10634830594062805, | |
| "step": 160, | |
| "valid_targets_mean": 3387.6, | |
| "valid_targets_min": 618 | |
| }, | |
| { | |
| "epoch": 1.0512, | |
| "grad_norm": 0.30908658201131584, | |
| "learning_rate": 3.8586341935793265e-05, | |
| "loss": 0.4192, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11579123139381409, | |
| "step": 165, | |
| "valid_targets_mean": 3286.0, | |
| "valid_targets_min": 493 | |
| }, | |
| { | |
| "epoch": 1.0832, | |
| "grad_norm": 0.29320932151007156, | |
| "learning_rate": 3.841743009747089e-05, | |
| "loss": 0.4191, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12825851142406464, | |
| "step": 170, | |
| "valid_targets_mean": 4071.0, | |
| "valid_targets_min": 833 | |
| }, | |
| { | |
| "epoch": 1.1152, | |
| "grad_norm": 0.3327558621495939, | |
| "learning_rate": 3.8239401479325714e-05, | |
| "loss": 0.4242, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11058387160301208, | |
| "step": 175, | |
| "valid_targets_mean": 3520.4, | |
| "valid_targets_min": 486 | |
| }, | |
| { | |
| "epoch": 1.1472, | |
| "grad_norm": 0.32685077032260906, | |
| "learning_rate": 3.8052344206992276e-05, | |
| "loss": 0.4195, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10514901578426361, | |
| "step": 180, | |
| "valid_targets_mean": 2730.8, | |
| "valid_targets_min": 541 | |
| }, | |
| { | |
| "epoch": 1.1792, | |
| "grad_norm": 0.30481242938403647, | |
| "learning_rate": 3.7856350875363396e-05, | |
| "loss": 0.4296, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10446308553218842, | |
| "step": 185, | |
| "valid_targets_mean": 3265.6, | |
| "valid_targets_min": 596 | |
| }, | |
| { | |
| "epoch": 1.2112, | |
| "grad_norm": 0.31129338950024904, | |
| "learning_rate": 3.765151850275497e-05, | |
| "loss": 0.4298, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11686381697654724, | |
| "step": 190, | |
| "valid_targets_mean": 3738.5, | |
| "valid_targets_min": 435 | |
| }, | |
| { | |
| "epoch": 1.2432, | |
| "grad_norm": 0.3040952622339095, | |
| "learning_rate": 3.7437948482881104e-05, | |
| "loss": 0.4198, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07344812154769897, | |
| "step": 195, | |
| "valid_targets_mean": 2414.3, | |
| "valid_targets_min": 360 | |
| }, | |
| { | |
| "epoch": 1.2752, | |
| "grad_norm": 0.29997753174494113, | |
| "learning_rate": 3.721574653466336e-05, | |
| "loss": 0.4204, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11752958595752716, | |
| "step": 200, | |
| "valid_targets_mean": 3929.6, | |
| "valid_targets_min": 546 | |
| }, | |
| { | |
| "epoch": 1.3072, | |
| "grad_norm": 0.28637187232858646, | |
| "learning_rate": 3.698502264989903e-05, | |
| "loss": 0.4054, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10360358655452728, | |
| "step": 205, | |
| "valid_targets_mean": 4811.8, | |
| "valid_targets_min": 489 | |
| }, | |
| { | |
| "epoch": 1.3392, | |
| "grad_norm": 0.3142554483872628, | |
| "learning_rate": 3.674589103881432e-05, | |
| "loss": 0.4215, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09267735481262207, | |
| "step": 210, | |
| "valid_targets_mean": 2937.2, | |
| "valid_targets_min": 411 | |
| }, | |
| { | |
| "epoch": 1.3712, | |
| "grad_norm": 0.30585074446413874, | |
| "learning_rate": 3.64984700735293e-05, | |
| "loss": 0.4096, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08472581952810287, | |
| "step": 215, | |
| "valid_targets_mean": 2885.4, | |
| "valid_targets_min": 377 | |
| }, | |
| { | |
| "epoch": 1.4032, | |
| "grad_norm": 0.27701675622672256, | |
| "learning_rate": 3.624288222946273e-05, | |
| "loss": 0.408, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08717796206474304, | |
| "step": 220, | |
| "valid_targets_mean": 4064.2, | |
| "valid_targets_min": 451 | |
| }, | |
| { | |
| "epoch": 1.4352, | |
| "grad_norm": 0.356773918451923, | |
| "learning_rate": 3.597925402470578e-05, | |
| "loss": 0.4208, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11334685981273651, | |
| "step": 225, | |
| "valid_targets_mean": 3693.6, | |
| "valid_targets_min": 418 | |
| }, | |
| { | |
| "epoch": 1.4672, | |
| "grad_norm": 0.3067967573468513, | |
| "learning_rate": 3.570771595739445e-05, | |
| "loss": 0.4129, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09118153154850006, | |
| "step": 230, | |
| "valid_targets_mean": 2948.8, | |
| "valid_targets_min": 397 | |
| }, | |
| { | |
| "epoch": 1.4992, | |
| "grad_norm": 0.30926384728160244, | |
| "learning_rate": 3.5428402441111964e-05, | |
| "loss": 0.4219, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10135011374950409, | |
| "step": 235, | |
| "valid_targets_mean": 2829.0, | |
| "valid_targets_min": 613 | |
| }, | |
| { | |
| "epoch": 1.5312000000000001, | |
| "grad_norm": 0.3408424443405089, | |
| "learning_rate": 3.5141451738352936e-05, | |
| "loss": 0.4145, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11236296594142914, | |
| "step": 240, | |
| "valid_targets_mean": 3582.9, | |
| "valid_targets_min": 500 | |
| }, | |
| { | |
| "epoch": 1.5632000000000001, | |
| "grad_norm": 0.331700526762141, | |
| "learning_rate": 3.4847005892082266e-05, | |
| "loss": 0.409, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1031736359000206, | |
| "step": 245, | |
| "valid_targets_mean": 3656.4, | |
| "valid_targets_min": 443 | |
| }, | |
| { | |
| "epoch": 1.5952, | |
| "grad_norm": 0.2816575202622663, | |
| "learning_rate": 3.454521065542273e-05, | |
| "loss": 0.4072, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08433468639850616, | |
| "step": 250, | |
| "valid_targets_mean": 3330.4, | |
| "valid_targets_min": 463 | |
| }, | |
| { | |
| "epoch": 1.6272, | |
| "grad_norm": 0.29328376186189875, | |
| "learning_rate": 3.423621541950597e-05, | |
| "loss": 0.4179, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08616122603416443, | |
| "step": 255, | |
| "valid_targets_mean": 3166.2, | |
| "valid_targets_min": 518 | |
| }, | |
| { | |
| "epoch": 1.6592, | |
| "grad_norm": 0.27906281295429675, | |
| "learning_rate": 3.3920173139522664e-05, | |
| "loss": 0.4132, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08289863914251328, | |
| "step": 260, | |
| "valid_targets_mean": 2922.2, | |
| "valid_targets_min": 431 | |
| }, | |
| { | |
| "epoch": 1.6912, | |
| "grad_norm": 0.303610299022672, | |
| "learning_rate": 3.35972402590084e-05, | |
| "loss": 0.3999, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0856861025094986, | |
| "step": 265, | |
| "valid_targets_mean": 2907.5, | |
| "valid_targets_min": 541 | |
| }, | |
| { | |
| "epoch": 1.7231999999999998, | |
| "grad_norm": 0.2797676689846236, | |
| "learning_rate": 3.326757663240291e-05, | |
| "loss": 0.4085, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09948824346065521, | |
| "step": 270, | |
| "valid_targets_mean": 3758.2, | |
| "valid_targets_min": 400 | |
| }, | |
| { | |
| "epoch": 1.7551999999999999, | |
| "grad_norm": 0.31870793987096163, | |
| "learning_rate": 3.293134544592073e-05, | |
| "loss": 0.4132, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09039462357759476, | |
| "step": 275, | |
| "valid_targets_mean": 3021.4, | |
| "valid_targets_min": 512 | |
| }, | |
| { | |
| "epoch": 1.7872, | |
| "grad_norm": 0.3056342361621842, | |
| "learning_rate": 3.258871313677274e-05, | |
| "loss": 0.3959, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12409260869026184, | |
| "step": 280, | |
| "valid_targets_mean": 5069.3, | |
| "valid_targets_min": 1505 | |
| }, | |
| { | |
| "epoch": 1.8192, | |
| "grad_norm": 0.31917984163018115, | |
| "learning_rate": 3.2239849310778316e-05, | |
| "loss": 0.4192, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11373455822467804, | |
| "step": 285, | |
| "valid_targets_mean": 3589.4, | |
| "valid_targets_min": 606 | |
| }, | |
| { | |
| "epoch": 1.8512, | |
| "grad_norm": 0.29976559155122484, | |
| "learning_rate": 3.188492665840909e-05, | |
| "loss": 0.4131, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10674092173576355, | |
| "step": 290, | |
| "valid_targets_mean": 3625.8, | |
| "valid_targets_min": 849 | |
| }, | |
| { | |
| "epoch": 1.8832, | |
| "grad_norm": 0.32783689424299467, | |
| "learning_rate": 3.1524120869305726e-05, | |
| "loss": 0.4133, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09319078177213669, | |
| "step": 295, | |
| "valid_targets_mean": 3229.2, | |
| "valid_targets_min": 434 | |
| }, | |
| { | |
| "epoch": 1.9152, | |
| "grad_norm": 0.33085638352381364, | |
| "learning_rate": 3.11576105453101e-05, | |
| "loss": 0.4122, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10556285083293915, | |
| "step": 300, | |
| "valid_targets_mean": 2998.1, | |
| "valid_targets_min": 453 | |
| }, | |
| { | |
| "epoch": 1.9472, | |
| "grad_norm": 0.3043466242056176, | |
| "learning_rate": 3.0785577112055916e-05, | |
| "loss": 0.3983, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.06790900975465775, | |
| "step": 305, | |
| "valid_targets_mean": 2348.4, | |
| "valid_targets_min": 390 | |
| }, | |
| { | |
| "epoch": 1.9792, | |
| "grad_norm": 0.29766877730815416, | |
| "learning_rate": 3.040820472916153e-05, | |
| "loss": 0.4105, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09513919055461884, | |
| "step": 310, | |
| "valid_targets_mean": 3049.9, | |
| "valid_targets_min": 505 | |
| }, | |
| { | |
| "epoch": 2.0064, | |
| "grad_norm": 0.35175183601655335, | |
| "learning_rate": 3.002568019906939e-05, | |
| "loss": 0.4038, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12016259133815765, | |
| "step": 315, | |
| "valid_targets_mean": 3695.6, | |
| "valid_targets_min": 643 | |
| }, | |
| { | |
| "epoch": 2.0384, | |
| "grad_norm": 0.32818982055787627, | |
| "learning_rate": 2.963819287457733e-05, | |
| "loss": 0.4006, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08270606398582458, | |
| "step": 320, | |
| "valid_targets_mean": 2680.0, | |
| "valid_targets_min": 492 | |
| }, | |
| { | |
| "epoch": 2.0704, | |
| "grad_norm": 0.32196700686995317, | |
| "learning_rate": 2.924593456510733e-05, | |
| "loss": 0.3985, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09519985318183899, | |
| "step": 325, | |
| "valid_targets_mean": 2763.8, | |
| "valid_targets_min": 363 | |
| }, | |
| { | |
| "epoch": 2.1024, | |
| "grad_norm": 0.308052217632256, | |
| "learning_rate": 2.8849099441758306e-05, | |
| "loss": 0.4036, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09480351209640503, | |
| "step": 330, | |
| "valid_targets_mean": 3369.1, | |
| "valid_targets_min": 548 | |
| }, | |
| { | |
| "epoch": 2.1344, | |
| "grad_norm": 0.3079270290154787, | |
| "learning_rate": 2.844788394118979e-05, | |
| "loss": 0.4028, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12439969182014465, | |
| "step": 335, | |
| "valid_targets_mean": 4398.2, | |
| "valid_targets_min": 363 | |
| }, | |
| { | |
| "epoch": 2.1664, | |
| "grad_norm": 0.3234918538636103, | |
| "learning_rate": 2.8042486668384164e-05, | |
| "loss": 0.404, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08282612264156342, | |
| "step": 340, | |
| "valid_targets_mean": 2829.8, | |
| "valid_targets_min": 365 | |
| }, | |
| { | |
| "epoch": 2.1984, | |
| "grad_norm": 0.29904525030296997, | |
| "learning_rate": 2.7633108298335582e-05, | |
| "loss": 0.4038, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10378585755825043, | |
| "step": 345, | |
| "valid_targets_mean": 3928.0, | |
| "valid_targets_min": 434 | |
| }, | |
| { | |
| "epoch": 2.2304, | |
| "grad_norm": 0.36061877038637963, | |
| "learning_rate": 2.721995147671416e-05, | |
| "loss": 0.3884, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09449270367622375, | |
| "step": 350, | |
| "valid_targets_mean": 2698.2, | |
| "valid_targets_min": 485 | |
| }, | |
| { | |
| "epoch": 2.2624, | |
| "grad_norm": 0.29172267982635475, | |
| "learning_rate": 2.68032207195547e-05, | |
| "loss": 0.3899, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09744615852832794, | |
| "step": 355, | |
| "valid_targets_mean": 3623.7, | |
| "valid_targets_min": 440 | |
| }, | |
| { | |
| "epoch": 2.2944, | |
| "grad_norm": 0.31227829595750434, | |
| "learning_rate": 2.6383122312019604e-05, | |
| "loss": 0.3967, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10573260486125946, | |
| "step": 360, | |
| "valid_targets_mean": 3432.0, | |
| "valid_targets_min": 858 | |
| }, | |
| { | |
| "epoch": 2.3264, | |
| "grad_norm": 0.2915425245682301, | |
| "learning_rate": 2.595986420628597e-05, | |
| "loss": 0.3862, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11143533885478973, | |
| "step": 365, | |
| "valid_targets_mean": 3948.1, | |
| "valid_targets_min": 563 | |
| }, | |
| { | |
| "epoch": 2.3584, | |
| "grad_norm": 0.2875718921580862, | |
| "learning_rate": 2.5533655918607573e-05, | |
| "loss": 0.4017, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11865570396184921, | |
| "step": 370, | |
| "valid_targets_mean": 4236.0, | |
| "valid_targets_min": 510 | |
| }, | |
| { | |
| "epoch": 2.3904, | |
| "grad_norm": 0.30131690343538353, | |
| "learning_rate": 2.510470842560259e-05, | |
| "loss": 0.4033, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11871572583913803, | |
| "step": 375, | |
| "valid_targets_mean": 3731.9, | |
| "valid_targets_min": 504 | |
| }, | |
| { | |
| "epoch": 2.4224, | |
| "grad_norm": 0.32506143019983696, | |
| "learning_rate": 2.467323405981841e-05, | |
| "loss": 0.4085, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11484360694885254, | |
| "step": 380, | |
| "valid_targets_mean": 3139.8, | |
| "valid_targets_min": 495 | |
| }, | |
| { | |
| "epoch": 2.4544, | |
| "grad_norm": 0.2960692684866897, | |
| "learning_rate": 2.423944640462533e-05, | |
| "loss": 0.3923, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09598161280155182, | |
| "step": 385, | |
| "valid_targets_mean": 3949.2, | |
| "valid_targets_min": 381 | |
| }, | |
| { | |
| "epoch": 2.4864, | |
| "grad_norm": 0.2863694508364452, | |
| "learning_rate": 2.3803560188490968e-05, | |
| "loss": 0.3893, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08352990448474884, | |
| "step": 390, | |
| "valid_targets_mean": 2739.9, | |
| "valid_targets_min": 362 | |
| }, | |
| { | |
| "epoch": 2.5183999999999997, | |
| "grad_norm": 0.2791576320364606, | |
| "learning_rate": 2.336579117868789e-05, | |
| "loss": 0.3956, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10237205028533936, | |
| "step": 395, | |
| "valid_targets_mean": 3759.4, | |
| "valid_targets_min": 300 | |
| }, | |
| { | |
| "epoch": 2.5504, | |
| "grad_norm": 0.31409378849802383, | |
| "learning_rate": 2.292635607448711e-05, | |
| "loss": 0.3948, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1151379868388176, | |
| "step": 400, | |
| "valid_targets_mean": 3616.1, | |
| "valid_targets_min": 555 | |
| }, | |
| { | |
| "epoch": 2.5824, | |
| "grad_norm": 0.32761196340498366, | |
| "learning_rate": 2.248547239989008e-05, | |
| "loss": 0.3976, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10201191902160645, | |
| "step": 405, | |
| "valid_targets_mean": 2985.4, | |
| "valid_targets_min": 447 | |
| }, | |
| { | |
| "epoch": 2.6144, | |
| "grad_norm": 0.3167676555579155, | |
| "learning_rate": 2.204335839595255e-05, | |
| "loss": 0.3939, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11454886198043823, | |
| "step": 410, | |
| "valid_targets_mean": 3582.5, | |
| "valid_targets_min": 420 | |
| }, | |
| { | |
| "epoch": 2.6464, | |
| "grad_norm": 0.27490076265711977, | |
| "learning_rate": 2.1600232912753452e-05, | |
| "loss": 0.3911, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08334609866142273, | |
| "step": 415, | |
| "valid_targets_mean": 3968.5, | |
| "valid_targets_min": 686 | |
| }, | |
| { | |
| "epoch": 2.6784, | |
| "grad_norm": 0.28820601662868195, | |
| "learning_rate": 2.1156315301062293e-05, | |
| "loss": 0.4017, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08992220461368561, | |
| "step": 420, | |
| "valid_targets_mean": 2925.8, | |
| "valid_targets_min": 391 | |
| }, | |
| { | |
| "epoch": 2.7104, | |
| "grad_norm": 0.3281495262447984, | |
| "learning_rate": 2.0711825303758712e-05, | |
| "loss": 0.3986, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1050509512424469, | |
| "step": 425, | |
| "valid_targets_mean": 2994.0, | |
| "valid_targets_min": 562 | |
| }, | |
| { | |
| "epoch": 2.7424, | |
| "grad_norm": 0.3228350127824187, | |
| "learning_rate": 2.0266982947057962e-05, | |
| "loss": 0.393, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10246922820806503, | |
| "step": 430, | |
| "valid_targets_mean": 3511.3, | |
| "valid_targets_min": 618 | |
| }, | |
| { | |
| "epoch": 2.7744, | |
| "grad_norm": 0.2869434244081683, | |
| "learning_rate": 1.9822008431596083e-05, | |
| "loss": 0.3891, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12022943794727325, | |
| "step": 435, | |
| "valid_targets_mean": 3858.6, | |
| "valid_targets_min": 603 | |
| }, | |
| { | |
| "epoch": 2.8064, | |
| "grad_norm": 0.300790879461136, | |
| "learning_rate": 1.937712202342881e-05, | |
| "loss": 0.4065, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11000954359769821, | |
| "step": 440, | |
| "valid_targets_mean": 3939.7, | |
| "valid_targets_min": 427 | |
| }, | |
| { | |
| "epoch": 2.8384, | |
| "grad_norm": 0.28711521054057904, | |
| "learning_rate": 1.8932543944998037e-05, | |
| "loss": 0.3884, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10628990828990936, | |
| "step": 445, | |
| "valid_targets_mean": 3955.8, | |
| "valid_targets_min": 407 | |
| }, | |
| { | |
| "epoch": 2.8704, | |
| "grad_norm": 0.27490225031276794, | |
| "learning_rate": 1.8488494266119877e-05, | |
| "loss": 0.3857, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09173107147216797, | |
| "step": 450, | |
| "valid_targets_mean": 3124.4, | |
| "valid_targets_min": 464 | |
| }, | |
| { | |
| "epoch": 2.9024, | |
| "grad_norm": 0.26973879900365233, | |
| "learning_rate": 1.804519279504834e-05, | |
| "loss": 0.3875, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11304472386837006, | |
| "step": 455, | |
| "valid_targets_mean": 4598.9, | |
| "valid_targets_min": 1131 | |
| }, | |
| { | |
| "epoch": 2.9344, | |
| "grad_norm": 0.3057439567770752, | |
| "learning_rate": 1.7602858969668365e-05, | |
| "loss": 0.4019, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11872843652963638, | |
| "step": 460, | |
| "valid_targets_mean": 3611.4, | |
| "valid_targets_min": 474 | |
| }, | |
| { | |
| "epoch": 2.9664, | |
| "grad_norm": 0.25695636015059875, | |
| "learning_rate": 1.716171174887231e-05, | |
| "loss": 0.3937, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10790961235761642, | |
| "step": 465, | |
| "valid_targets_mean": 4442.4, | |
| "valid_targets_min": 556 | |
| }, | |
| { | |
| "epoch": 2.9984, | |
| "grad_norm": 0.31522398996251605, | |
| "learning_rate": 1.6721969504173484e-05, | |
| "loss": 0.3995, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09481863677501678, | |
| "step": 470, | |
| "valid_targets_mean": 3173.0, | |
| "valid_targets_min": 400 | |
| }, | |
| { | |
| "epoch": 3.0256, | |
| "grad_norm": 0.2758446026102969, | |
| "learning_rate": 1.628384991161041e-05, | |
| "loss": 0.3778, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09901263564825058, | |
| "step": 475, | |
| "valid_targets_mean": 3940.1, | |
| "valid_targets_min": 1030 | |
| }, | |
| { | |
| "epoch": 3.0576, | |
| "grad_norm": 0.29085168398143973, | |
| "learning_rate": 1.5847569843995452e-05, | |
| "loss": 0.3942, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09330069273710251, | |
| "step": 480, | |
| "valid_targets_mean": 3361.1, | |
| "valid_targets_min": 363 | |
| }, | |
| { | |
| "epoch": 3.0896, | |
| "grad_norm": 0.2720296117070282, | |
| "learning_rate": 1.5413345263560922e-05, | |
| "loss": 0.3748, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09819469600915909, | |
| "step": 485, | |
| "valid_targets_mean": 3642.7, | |
| "valid_targets_min": 427 | |
| }, | |
| { | |
| "epoch": 3.1216, | |
| "grad_norm": 0.31649252944987283, | |
| "learning_rate": 1.4981391115056032e-05, | |
| "loss": 0.395, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09010912477970123, | |
| "step": 490, | |
| "valid_targets_mean": 2690.6, | |
| "valid_targets_min": 710 | |
| }, | |
| { | |
| "epoch": 3.1536, | |
| "grad_norm": 0.28403309639320534, | |
| "learning_rate": 1.455192121934748e-05, | |
| "loss": 0.3905, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08111590147018433, | |
| "step": 495, | |
| "valid_targets_mean": 2885.1, | |
| "valid_targets_min": 448 | |
| }, | |
| { | |
| "epoch": 3.1856, | |
| "grad_norm": 0.291991076529333, | |
| "learning_rate": 1.4125148167576303e-05, | |
| "loss": 0.3914, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0833030641078949, | |
| "step": 500, | |
| "valid_targets_mean": 3337.6, | |
| "valid_targets_min": 657 | |
| }, | |
| { | |
| "epoch": 3.2176, | |
| "grad_norm": 0.2907190434367134, | |
| "learning_rate": 1.3701283215923563e-05, | |
| "loss": 0.3911, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07886438816785812, | |
| "step": 505, | |
| "valid_targets_mean": 3121.6, | |
| "valid_targets_min": 580 | |
| }, | |
| { | |
| "epoch": 3.2496, | |
| "grad_norm": 0.3111497498450304, | |
| "learning_rate": 1.328053618103677e-05, | |
| "loss": 0.384, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10352186858654022, | |
| "step": 510, | |
| "valid_targets_mean": 3174.3, | |
| "valid_targets_min": 332 | |
| }, | |
| { | |
| "epoch": 3.2816, | |
| "grad_norm": 0.2851076378107036, | |
| "learning_rate": 1.2863115336168916e-05, | |
| "loss": 0.3927, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1003105416893959, | |
| "step": 515, | |
| "valid_targets_mean": 3972.4, | |
| "valid_targets_min": 878 | |
| }, | |
| { | |
| "epoch": 3.3136, | |
| "grad_norm": 0.2924211050016801, | |
| "learning_rate": 1.2449227308081509e-05, | |
| "loss": 0.3944, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09007060527801514, | |
| "step": 520, | |
| "valid_targets_mean": 2907.2, | |
| "valid_targets_min": 367 | |
| }, | |
| { | |
| "epoch": 3.3456, | |
| "grad_norm": 0.2942152490063321, | |
| "learning_rate": 1.2039076974762587e-05, | |
| "loss": 0.3817, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07443501055240631, | |
| "step": 525, | |
| "valid_targets_mean": 2579.8, | |
| "valid_targets_min": 525 | |
| }, | |
| { | |
| "epoch": 3.3776, | |
| "grad_norm": 0.2795457037362308, | |
| "learning_rate": 1.163286736401044e-05, | |
| "loss": 0.3801, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08758899569511414, | |
| "step": 530, | |
| "valid_targets_mean": 3070.0, | |
| "valid_targets_min": 596 | |
| }, | |
| { | |
| "epoch": 3.4096, | |
| "grad_norm": 0.2754932761787426, | |
| "learning_rate": 1.123079955293322e-05, | |
| "loss": 0.3714, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08010783791542053, | |
| "step": 535, | |
| "valid_targets_mean": 3035.8, | |
| "valid_targets_min": 458 | |
| }, | |
| { | |
| "epoch": 3.4416, | |
| "grad_norm": 0.278351719055505, | |
| "learning_rate": 1.0833072568414037e-05, | |
| "loss": 0.3847, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1174527108669281, | |
| "step": 540, | |
| "valid_targets_mean": 3627.0, | |
| "valid_targets_min": 263 | |
| }, | |
| { | |
| "epoch": 3.4736000000000002, | |
| "grad_norm": 0.35326534965127765, | |
| "learning_rate": 1.0439883288591057e-05, | |
| "loss": 0.3885, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0970514640212059, | |
| "step": 545, | |
| "valid_targets_mean": 4814.1, | |
| "valid_targets_min": 794 | |
| }, | |
| { | |
| "epoch": 3.5056000000000003, | |
| "grad_norm": 0.2367121659420493, | |
| "learning_rate": 1.0051426345401202e-05, | |
| "loss": 0.378, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09693192690610886, | |
| "step": 550, | |
| "valid_targets_mean": 4847.6, | |
| "valid_targets_min": 1636 | |
| }, | |
| { | |
| "epoch": 3.5376, | |
| "grad_norm": 0.24935272283077584, | |
| "learning_rate": 9.667894028235704e-06, | |
| "loss": 0.3786, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0942145437002182, | |
| "step": 555, | |
| "valid_targets_mean": 3423.2, | |
| "valid_targets_min": 455 | |
| }, | |
| { | |
| "epoch": 3.5696, | |
| "grad_norm": 0.27022355504307083, | |
| "learning_rate": 9.289476188755315e-06, | |
| "loss": 0.3925, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10093735158443451, | |
| "step": 560, | |
| "valid_targets_mean": 3986.3, | |
| "valid_targets_min": 640 | |
| }, | |
| { | |
| "epoch": 3.6016, | |
| "grad_norm": 0.26576428709157074, | |
| "learning_rate": 8.916360146912122e-06, | |
| "loss": 0.3873, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09885665774345398, | |
| "step": 565, | |
| "valid_targets_mean": 4024.7, | |
| "valid_targets_min": 568 | |
| }, | |
| { | |
| "epoch": 3.6336, | |
| "grad_norm": 0.3135727669575876, | |
| "learning_rate": 8.548730598224646e-06, | |
| "loss": 0.396, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11619214713573456, | |
| "step": 570, | |
| "valid_targets_mean": 3899.1, | |
| "valid_targets_min": 381 | |
| }, | |
| { | |
| "epoch": 3.6656, | |
| "grad_norm": 0.2791512424743348, | |
| "learning_rate": 8.186769522352053e-06, | |
| "loss": 0.3814, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08608850836753845, | |
| "step": 575, | |
| "valid_targets_mean": 2816.6, | |
| "valid_targets_min": 373 | |
| }, | |
| { | |
| "epoch": 3.6976, | |
| "grad_norm": 0.27385447865273665, | |
| "learning_rate": 7.830656093012714e-06, | |
| "loss": 0.3788, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12399238348007202, | |
| "step": 580, | |
| "valid_targets_mean": 4058.5, | |
| "valid_targets_min": 785 | |
| }, | |
| { | |
| "epoch": 3.7296, | |
| "grad_norm": 0.27618164218667346, | |
| "learning_rate": 7.480566589291696e-06, | |
| "loss": 0.3875, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10159634053707123, | |
| "step": 585, | |
| "valid_targets_mean": 3408.8, | |
| "valid_targets_min": 743 | |
| }, | |
| { | |
| "epoch": 3.7616, | |
| "grad_norm": 0.2841362214293442, | |
| "learning_rate": 7.1366743083812285e-06, | |
| "loss": 0.3897, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09839831292629242, | |
| "step": 590, | |
| "valid_targets_mean": 3104.8, | |
| "valid_targets_min": 471 | |
| }, | |
| { | |
| "epoch": 3.7936, | |
| "grad_norm": 0.28548790060974555, | |
| "learning_rate": 6.799149479797101e-06, | |
| "loss": 0.3809, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08586011826992035, | |
| "step": 595, | |
| "valid_targets_mean": 3246.6, | |
| "valid_targets_min": 525 | |
| }, | |
| { | |
| "epoch": 3.8256, | |
| "grad_norm": 0.27943035798215976, | |
| "learning_rate": 6.4681591811137e-06, | |
| "loss": 0.3818, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09518860280513763, | |
| "step": 600, | |
| "valid_targets_mean": 4215.2, | |
| "valid_targets_min": 490 | |
| }, | |
| { | |
| "epoch": 3.8576, | |
| "grad_norm": 0.2810036156630675, | |
| "learning_rate": 6.143867255259197e-06, | |
| "loss": 0.3897, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08238103985786438, | |
| "step": 605, | |
| "valid_targets_mean": 2850.9, | |
| "valid_targets_min": 568 | |
| }, | |
| { | |
| "epoch": 3.8895999999999997, | |
| "grad_norm": 0.29740130028269385, | |
| "learning_rate": 5.8264342294119504e-06, | |
| "loss": 0.3982, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09944004565477371, | |
| "step": 610, | |
| "valid_targets_mean": 2959.0, | |
| "valid_targets_min": 523 | |
| }, | |
| { | |
| "epoch": 3.9215999999999998, | |
| "grad_norm": 0.26619801805874743, | |
| "learning_rate": 5.516017235538258e-06, | |
| "loss": 0.3844, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09084463119506836, | |
| "step": 615, | |
| "valid_targets_mean": 3531.8, | |
| "valid_targets_min": 468 | |
| }, | |
| { | |
| "epoch": 3.9536, | |
| "grad_norm": 0.2876578187458763, | |
| "learning_rate": 5.212769932610695e-06, | |
| "loss": 0.3951, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09096888452768326, | |
| "step": 620, | |
| "valid_targets_mean": 3072.9, | |
| "valid_targets_min": 479 | |
| }, | |
| { | |
| "epoch": 3.9856, | |
| "grad_norm": 0.30583576856778977, | |
| "learning_rate": 4.916842430545681e-06, | |
| "loss": 0.3971, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1204671710729599, | |
| "step": 625, | |
| "valid_targets_mean": 4041.7, | |
| "valid_targets_min": 362 | |
| }, | |
| { | |
| "epoch": 4.0128, | |
| "grad_norm": 0.2674044027570556, | |
| "learning_rate": 4.628381215897837e-06, | |
| "loss": 0.3927, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08395358175039291, | |
| "step": 630, | |
| "valid_targets_mean": 2808.9, | |
| "valid_targets_min": 500 | |
| }, | |
| { | |
| "epoch": 4.0448, | |
| "grad_norm": 0.2553938956875972, | |
| "learning_rate": 4.347529079347914e-06, | |
| "loss": 0.376, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07460927963256836, | |
| "step": 635, | |
| "valid_targets_mean": 2424.4, | |
| "valid_targets_min": 558 | |
| }, | |
| { | |
| "epoch": 4.0768, | |
| "grad_norm": 0.2632386816144587, | |
| "learning_rate": 4.074425045020247e-06, | |
| "loss": 0.3813, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07464930415153503, | |
| "step": 640, | |
| "valid_targets_mean": 2766.4, | |
| "valid_targets_min": 321 | |
| }, | |
| { | |
| "epoch": 4.1088, | |
| "grad_norm": 0.2733790383704323, | |
| "learning_rate": 3.8092043016646487e-06, | |
| "loss": 0.383, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.11327754706144333, | |
| "step": 645, | |
| "valid_targets_mean": 4320.8, | |
| "valid_targets_min": 1049 | |
| }, | |
| { | |
| "epoch": 4.1408, | |
| "grad_norm": 0.27745450311166203, | |
| "learning_rate": 3.551998135736867e-06, | |
| "loss": 0.3823, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10820911824703217, | |
| "step": 650, | |
| "valid_targets_mean": 3525.9, | |
| "valid_targets_min": 503 | |
| }, | |
| { | |
| "epoch": 4.1728, | |
| "grad_norm": 0.23325649385080435, | |
| "learning_rate": 3.3029338664107267e-06, | |
| "loss": 0.3805, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0991358831524849, | |
| "step": 655, | |
| "valid_targets_mean": 4343.9, | |
| "valid_targets_min": 877 | |
| }, | |
| { | |
| "epoch": 4.2048, | |
| "grad_norm": 0.263943774734023, | |
| "learning_rate": 3.0621347825540625e-06, | |
| "loss": 0.3878, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09415062516927719, | |
| "step": 660, | |
| "valid_targets_mean": 2924.2, | |
| "valid_targets_min": 490 | |
| }, | |
| { | |
| "epoch": 4.2368, | |
| "grad_norm": 0.2646170332985445, | |
| "learning_rate": 2.8297200816997183e-06, | |
| "loss": 0.3791, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09657609462738037, | |
| "step": 665, | |
| "valid_targets_mean": 3533.6, | |
| "valid_targets_min": 522 | |
| }, | |
| { | |
| "epoch": 4.2688, | |
| "grad_norm": 0.2720210216781996, | |
| "learning_rate": 2.605804811041803e-06, | |
| "loss": 0.3834, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10745777934789658, | |
| "step": 670, | |
| "valid_targets_mean": 3359.8, | |
| "valid_targets_min": 431 | |
| }, | |
| { | |
| "epoch": 4.3008, | |
| "grad_norm": 0.28841127198811484, | |
| "learning_rate": 2.390499810486351e-06, | |
| "loss": 0.3844, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07852067798376083, | |
| "step": 675, | |
| "valid_targets_mean": 2390.2, | |
| "valid_targets_min": 456 | |
| }, | |
| { | |
| "epoch": 4.3328, | |
| "grad_norm": 0.2791923496468385, | |
| "learning_rate": 2.183911657784685e-06, | |
| "loss": 0.3892, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08093634247779846, | |
| "step": 680, | |
| "valid_targets_mean": 2649.8, | |
| "valid_targets_min": 549 | |
| }, | |
| { | |
| "epoch": 4.3648, | |
| "grad_norm": 0.267611073793364, | |
| "learning_rate": 1.986142615776532e-06, | |
| "loss": 0.37, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.1003832146525383, | |
| "step": 685, | |
| "valid_targets_mean": 3195.8, | |
| "valid_targets_min": 659 | |
| }, | |
| { | |
| "epoch": 4.3968, | |
| "grad_norm": 0.2751994662355363, | |
| "learning_rate": 1.7972905817690644e-06, | |
| "loss": 0.3847, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10562784969806671, | |
| "step": 690, | |
| "valid_targets_mean": 3961.6, | |
| "valid_targets_min": 604 | |
| }, | |
| { | |
| "epoch": 4.4288, | |
| "grad_norm": 0.24300228310709823, | |
| "learning_rate": 1.617449039076955e-06, | |
| "loss": 0.375, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.0899253860116005, | |
| "step": 695, | |
| "valid_targets_mean": 3598.1, | |
| "valid_targets_min": 504 | |
| }, | |
| { | |
| "epoch": 4.4608, | |
| "grad_norm": 0.2682274992222663, | |
| "learning_rate": 1.4467070107473413e-06, | |
| "loss": 0.3807, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08145391941070557, | |
| "step": 700, | |
| "valid_targets_mean": 3031.5, | |
| "valid_targets_min": 492 | |
| }, | |
| { | |
| "epoch": 4.4928, | |
| "grad_norm": 0.27154053518075244, | |
| "learning_rate": 1.2851490154926816e-06, | |
| "loss": 0.3853, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.07518133521080017, | |
| "step": 705, | |
| "valid_targets_mean": 3224.0, | |
| "valid_targets_min": 402 | |
| }, | |
| { | |
| "epoch": 4.5248, | |
| "grad_norm": 0.26946328842599987, | |
| "learning_rate": 1.1328550258533211e-06, | |
| "loss": 0.3846, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08350574970245361, | |
| "step": 710, | |
| "valid_targets_mean": 2933.0, | |
| "valid_targets_min": 552 | |
| }, | |
| { | |
| "epoch": 4.5568, | |
| "grad_norm": 0.2707252657667389, | |
| "learning_rate": 9.899004286103953e-07, | |
| "loss": 0.3808, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08704008162021637, | |
| "step": 715, | |
| "valid_targets_mean": 3129.4, | |
| "valid_targets_min": 661 | |
| }, | |
| { | |
| "epoch": 4.5888, | |
| "grad_norm": 0.2870915755454043, | |
| "learning_rate": 8.5635598746876e-07, | |
| "loss": 0.3791, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09163787961006165, | |
| "step": 720, | |
| "valid_targets_mean": 2906.2, | |
| "valid_targets_min": 351 | |
| }, | |
| { | |
| "epoch": 4.6208, | |
| "grad_norm": 0.2719189407636618, | |
| "learning_rate": 7.32287808028389e-07, | |
| "loss": 0.3894, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09621652960777283, | |
| "step": 725, | |
| "valid_targets_mean": 3840.2, | |
| "valid_targets_min": 414 | |
| }, | |
| { | |
| "epoch": 4.6528, | |
| "grad_norm": 0.2779956698416493, | |
| "learning_rate": 6.177573050615327e-07, | |
| "loss": 0.3838, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10833831131458282, | |
| "step": 730, | |
| "valid_targets_mean": 3572.7, | |
| "valid_targets_min": 685 | |
| }, | |
| { | |
| "epoch": 4.6848, | |
| "grad_norm": 0.23565669698199462, | |
| "learning_rate": 5.128211721119213e-07, | |
| "loss": 0.3708, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08886441588401794, | |
| "step": 735, | |
| "valid_targets_mean": 3671.9, | |
| "valid_targets_min": 614 | |
| }, | |
| { | |
| "epoch": 4.7168, | |
| "grad_norm": 0.2754757471772312, | |
| "learning_rate": 4.175313534309755e-07, | |
| "loss": 0.3881, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09923436492681503, | |
| "step": 740, | |
| "valid_targets_mean": 3188.0, | |
| "valid_targets_min": 437 | |
| }, | |
| { | |
| "epoch": 4.7488, | |
| "grad_norm": 0.26349202357701723, | |
| "learning_rate": 3.319350182649861e-07, | |
| "loss": 0.3969, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09422273188829422, | |
| "step": 745, | |
| "valid_targets_mean": 3051.8, | |
| "valid_targets_min": 512 | |
| }, | |
| { | |
| "epoch": 4.7808, | |
| "grad_norm": 0.2639224649966649, | |
| "learning_rate": 2.560745375059392e-07, | |
| "loss": 0.3888, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09115906059741974, | |
| "step": 750, | |
| "valid_targets_mean": 2980.6, | |
| "valid_targets_min": 451 | |
| }, | |
| { | |
| "epoch": 4.8128, | |
| "grad_norm": 0.25288566509269783, | |
| "learning_rate": 1.8998746271758016e-07, | |
| "loss": 0.3779, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.08009067177772522, | |
| "step": 755, | |
| "valid_targets_mean": 3168.9, | |
| "valid_targets_min": 580 | |
| }, | |
| { | |
| "epoch": 4.8448, | |
| "grad_norm": 0.2786989737626223, | |
| "learning_rate": 1.337065075470778e-07, | |
| "loss": 0.3827, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09392277896404266, | |
| "step": 760, | |
| "valid_targets_mean": 3298.1, | |
| "valid_targets_min": 341 | |
| }, | |
| { | |
| "epoch": 4.8768, | |
| "grad_norm": 0.2688509408355671, | |
| "learning_rate": 8.725953153150279e-08, | |
| "loss": 0.391, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.10245306044816971, | |
| "step": 765, | |
| "valid_targets_mean": 4131.7, | |
| "valid_targets_min": 332 | |
| }, | |
| { | |
| "epoch": 4.9088, | |
| "grad_norm": 0.2543446058848574, | |
| "learning_rate": 5.066952630711886e-08, | |
| "loss": 0.3871, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09322092682123184, | |
| "step": 770, | |
| "valid_targets_mean": 3542.6, | |
| "valid_targets_min": 344 | |
| }, | |
| { | |
| "epoch": 4.9408, | |
| "grad_norm": 0.3020874124682841, | |
| "learning_rate": 2.3954604228342283e-08, | |
| "loss": 0.3886, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.09930112957954407, | |
| "step": 775, | |
| "valid_targets_mean": 3566.8, | |
| "valid_targets_min": 440 | |
| }, | |
| { | |
| "epoch": 4.9728, | |
| "grad_norm": 0.28365305176007183, | |
| "learning_rate": 7.12798940197601e-09, | |
| "loss": 0.3746, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.12032979726791382, | |
| "step": 780, | |
| "valid_targets_mean": 3426.9, | |
| "valid_targets_min": 632 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.5194064450810855, | |
| "learning_rate": 1.9801114115480802e-10, | |
| "loss": 0.3662, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.37630948424339294, | |
| "step": 785, | |
| "valid_targets_mean": 3882.5, | |
| "valid_targets_min": 584 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "loss_nan_ranks": 0, | |
| "loss_rank_avg": 0.37630948424339294, | |
| "step": 785, | |
| "total_flos": 1.4884589961457172e+18, | |
| "train_loss": 0.41875876818492913, | |
| "train_runtime": 16491.6632, | |
| "train_samples_per_second": 3.031, | |
| "train_steps_per_second": 0.048, | |
| "valid_targets_mean": 3882.5, | |
| "valid_targets_min": 584 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 785, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4884589961457172e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |