| { | |
| "best_metric": 0.7403023838996887, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-550", | |
| "epoch": 0.6472491909385113, | |
| "eval_steps": 50, | |
| "global_step": 550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011768167107972932, | |
| "eval_loss": 1.4336028099060059, | |
| "eval_runtime": 63.7044, | |
| "eval_samples_per_second": 22.479, | |
| "eval_steps_per_second": 5.62, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011768167107972934, | |
| "grad_norm": 1.2304390668869019, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4146, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023536334215945868, | |
| "grad_norm": 0.6472563743591309, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 6.0483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0353045013239188, | |
| "grad_norm": 0.7562745213508606, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 3.9027, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.047072668431891736, | |
| "grad_norm": 0.8033158779144287, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 1.8585, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05884083553986467, | |
| "grad_norm": 1.7948169708251953, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 1.7989, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05884083553986467, | |
| "eval_loss": 0.9343328475952148, | |
| "eval_runtime": 64.9646, | |
| "eval_samples_per_second": 22.043, | |
| "eval_steps_per_second": 5.511, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0706090026478376, | |
| "grad_norm": 0.8677065968513489, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 6.2807, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08237716975581054, | |
| "grad_norm": 0.7287414073944092, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 4.9082, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09414533686378347, | |
| "grad_norm": 1.209147572517395, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 3.0766, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1059135039717564, | |
| "grad_norm": 0.9230589866638184, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 1.5117, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11768167107972934, | |
| "grad_norm": 2.2932982444763184, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 1.5895, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11768167107972934, | |
| "eval_loss": 0.8446639180183411, | |
| "eval_runtime": 64.7346, | |
| "eval_samples_per_second": 22.121, | |
| "eval_steps_per_second": 5.53, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12944983818770225, | |
| "grad_norm": 0.867832362651825, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 6.0238, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1412180052956752, | |
| "grad_norm": 0.8156207203865051, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 4.7902, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15298617240364812, | |
| "grad_norm": 0.802191436290741, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 2.8416, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16475433951162108, | |
| "grad_norm": 1.274532675743103, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 1.3511, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.176522506619594, | |
| "grad_norm": 1.8214877843856812, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 1.4454, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.176522506619594, | |
| "eval_loss": 0.8176446557044983, | |
| "eval_runtime": 64.9157, | |
| "eval_samples_per_second": 22.059, | |
| "eval_steps_per_second": 5.515, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18829067372756694, | |
| "grad_norm": 0.7749770283699036, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 5.9457, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.20005884083553988, | |
| "grad_norm": 0.843367338180542, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 4.737, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2118270079435128, | |
| "grad_norm": 0.7175513505935669, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 2.8268, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.22359517505148574, | |
| "grad_norm": 0.8358870148658752, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 1.3233, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.23536334215945867, | |
| "grad_norm": 2.047827959060669, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 1.4239, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23536334215945867, | |
| "eval_loss": 0.7979318499565125, | |
| "eval_runtime": 64.8822, | |
| "eval_samples_per_second": 22.071, | |
| "eval_steps_per_second": 5.518, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2471315092674316, | |
| "grad_norm": 0.7978292107582092, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 5.7924, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2588996763754045, | |
| "grad_norm": 0.9069154858589172, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 4.7768, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.27066784348337747, | |
| "grad_norm": 0.7871260643005371, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 2.6733, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2824360105913504, | |
| "grad_norm": 0.7734578847885132, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 1.2857, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.29420417769932333, | |
| "grad_norm": 1.4109017848968506, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 1.3427, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.29420417769932333, | |
| "eval_loss": 0.7788119912147522, | |
| "eval_runtime": 65.0714, | |
| "eval_samples_per_second": 22.007, | |
| "eval_steps_per_second": 5.502, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.30597234480729624, | |
| "grad_norm": 0.7562018632888794, | |
| "learning_rate": 0.0001237326699871115, | |
| "loss": 5.6205, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3177405119152692, | |
| "grad_norm": 0.7738041281700134, | |
| "learning_rate": 0.00011852887240871145, | |
| "loss": 4.6291, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.32950867902324216, | |
| "grad_norm": 1.0495797395706177, | |
| "learning_rate": 0.00011327255272837221, | |
| "loss": 2.5666, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.34127684613121506, | |
| "grad_norm": 0.8168486952781677, | |
| "learning_rate": 0.00010797861055530831, | |
| "loss": 1.2404, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.353045013239188, | |
| "grad_norm": 1.7189139127731323, | |
| "learning_rate": 0.00010266205214377748, | |
| "loss": 1.3585, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.353045013239188, | |
| "eval_loss": 0.7667000889778137, | |
| "eval_runtime": 64.8942, | |
| "eval_samples_per_second": 22.067, | |
| "eval_steps_per_second": 5.517, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3648131803471609, | |
| "grad_norm": 0.7242693305015564, | |
| "learning_rate": 9.733794785622253e-05, | |
| "loss": 5.6994, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3765813474551339, | |
| "grad_norm": 0.810172438621521, | |
| "learning_rate": 9.202138944469168e-05, | |
| "loss": 4.7286, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3883495145631068, | |
| "grad_norm": 0.7765442728996277, | |
| "learning_rate": 8.672744727162781e-05, | |
| "loss": 2.8564, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.40011768167107975, | |
| "grad_norm": 0.7657132744789124, | |
| "learning_rate": 8.147112759128859e-05, | |
| "loss": 1.3036, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.41188584877905265, | |
| "grad_norm": 1.4623005390167236, | |
| "learning_rate": 7.626733001288851e-05, | |
| "loss": 1.3171, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.41188584877905265, | |
| "eval_loss": 0.7572553157806396, | |
| "eval_runtime": 64.9777, | |
| "eval_samples_per_second": 22.038, | |
| "eval_steps_per_second": 5.51, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.4236540158870256, | |
| "grad_norm": 0.696776270866394, | |
| "learning_rate": 7.113080526603792e-05, | |
| "loss": 5.7138, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4354221829949985, | |
| "grad_norm": 0.9223313331604004, | |
| "learning_rate": 6.607611338819697e-05, | |
| "loss": 4.5998, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.4471903501029715, | |
| "grad_norm": 0.7238697409629822, | |
| "learning_rate": 6.111758245266794e-05, | |
| "loss": 2.5621, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4589585172109444, | |
| "grad_norm": 0.9471986889839172, | |
| "learning_rate": 5.626926795411447e-05, | |
| "loss": 1.2488, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.47072668431891734, | |
| "grad_norm": 1.4697206020355225, | |
| "learning_rate": 5.1544912966734994e-05, | |
| "loss": 1.3135, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.47072668431891734, | |
| "eval_loss": 0.7500874400138855, | |
| "eval_runtime": 64.8413, | |
| "eval_samples_per_second": 22.085, | |
| "eval_steps_per_second": 5.521, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.48249485142689025, | |
| "grad_norm": 0.8447908759117126, | |
| "learning_rate": 4.695790918802576e-05, | |
| "loss": 5.6785, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.4942630185348632, | |
| "grad_norm": 0.8665351867675781, | |
| "learning_rate": 4.252125897855932e-05, | |
| "loss": 4.643, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5060311856428361, | |
| "grad_norm": 0.7426034808158875, | |
| "learning_rate": 3.824753850538082e-05, | |
| "loss": 2.7279, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.517799352750809, | |
| "grad_norm": 0.9415715932846069, | |
| "learning_rate": 3.414886209349615e-05, | |
| "loss": 1.2065, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.529567519858782, | |
| "grad_norm": 1.705180048942566, | |
| "learning_rate": 3.0236847886501542e-05, | |
| "loss": 1.3062, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.529567519858782, | |
| "eval_loss": 0.7452362179756165, | |
| "eval_runtime": 64.9352, | |
| "eval_samples_per_second": 22.053, | |
| "eval_steps_per_second": 5.513, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5413356869667549, | |
| "grad_norm": 0.7531328201293945, | |
| "learning_rate": 2.6522584913693294e-05, | |
| "loss": 5.4884, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5531038540747278, | |
| "grad_norm": 0.7240074872970581, | |
| "learning_rate": 2.301660165700936e-05, | |
| "loss": 4.6025, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5648720211827007, | |
| "grad_norm": 1.1110539436340332, | |
| "learning_rate": 1.9728836206903656e-05, | |
| "loss": 2.8274, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5766401882906738, | |
| "grad_norm": 1.0983327627182007, | |
| "learning_rate": 1.6668608091748495e-05, | |
| "loss": 1.2374, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5884083553986467, | |
| "grad_norm": 1.2942715883255005, | |
| "learning_rate": 1.3844591860619383e-05, | |
| "loss": 1.221, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5884083553986467, | |
| "eval_loss": 0.7421861290931702, | |
| "eval_runtime": 64.9523, | |
| "eval_samples_per_second": 22.047, | |
| "eval_steps_per_second": 5.512, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6001765225066196, | |
| "grad_norm": 0.7555685043334961, | |
| "learning_rate": 1.1264792494342857e-05, | |
| "loss": 5.5477, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6119446896145925, | |
| "grad_norm": 0.7698599696159363, | |
| "learning_rate": 8.936522714508678e-06, | |
| "loss": 4.6595, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6237128567225655, | |
| "grad_norm": 0.8012061715126038, | |
| "learning_rate": 6.866382254766157e-06, | |
| "loss": 2.9295, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6354810238305384, | |
| "grad_norm": 0.8370329737663269, | |
| "learning_rate": 5.060239153161872e-06, | |
| "loss": 1.2254, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6472491909385113, | |
| "grad_norm": 1.4551666975021362, | |
| "learning_rate": 3.5232131185484076e-06, | |
| "loss": 1.2469, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6472491909385113, | |
| "eval_loss": 0.7403023838996887, | |
| "eval_runtime": 65.1388, | |
| "eval_samples_per_second": 21.984, | |
| "eval_steps_per_second": 5.496, | |
| "step": 550 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.706288114835128e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |