| { | |
| "best_metric": 0.03395751491189003, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9093078758949882, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03818615751789976, | |
| "grad_norm": 18.12874984741211, | |
| "learning_rate": 5e-05, | |
| "loss": 10.1005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03818615751789976, | |
| "eval_loss": 10.637901306152344, | |
| "eval_runtime": 1.6122, | |
| "eval_samples_per_second": 109.79, | |
| "eval_steps_per_second": 14.267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07637231503579953, | |
| "grad_norm": 17.808269500732422, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2512, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11455847255369929, | |
| "grad_norm": 17.40803337097168, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.7879, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15274463007159905, | |
| "grad_norm": 19.329248428344727, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.0792, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1909307875894988, | |
| "grad_norm": 15.396371841430664, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.7587, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22911694510739858, | |
| "grad_norm": 14.42490005493164, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9182, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26730310262529833, | |
| "grad_norm": 14.44908332824707, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0481, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3054892601431981, | |
| "grad_norm": 10.369587898254395, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9454, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3436754176610978, | |
| "grad_norm": 7.190210342407227, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6841, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3818615751789976, | |
| "grad_norm": 4.101467609405518, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3795, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4200477326968974, | |
| "grad_norm": 19.52859115600586, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5522, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45823389021479716, | |
| "grad_norm": 11.562103271484375, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3438, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4964200477326969, | |
| "grad_norm": 4.227174282073975, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1642, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5346062052505967, | |
| "grad_norm": 7.807999134063721, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2666, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5727923627684964, | |
| "grad_norm": 3.6502740383148193, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2388, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6109785202863962, | |
| "grad_norm": 1.8619111776351929, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1697, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.649164677804296, | |
| "grad_norm": 4.5715651512146, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.185, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6873508353221957, | |
| "grad_norm": 2.615884304046631, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.102, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7255369928400954, | |
| "grad_norm": 2.4749627113342285, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1035, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7637231503579952, | |
| "grad_norm": 3.77799916267395, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1407, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.801909307875895, | |
| "grad_norm": 3.718111038208008, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1659, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8400954653937948, | |
| "grad_norm": 2.852799654006958, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0952, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8782816229116945, | |
| "grad_norm": 2.887477397918701, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1014, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9164677804295943, | |
| "grad_norm": 2.7658371925354004, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0995, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.954653937947494, | |
| "grad_norm": 1.2041877508163452, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0591, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.954653937947494, | |
| "eval_loss": 0.08095717430114746, | |
| "eval_runtime": 1.6085, | |
| "eval_samples_per_second": 110.039, | |
| "eval_steps_per_second": 14.299, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9928400954653938, | |
| "grad_norm": 1.2284048795700073, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1004, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0310262529832936, | |
| "grad_norm": 13.045022010803223, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.241, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0692124105011933, | |
| "grad_norm": 4.96898078918457, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1144, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.107398568019093, | |
| "grad_norm": 4.250532150268555, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0746, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1455847255369929, | |
| "grad_norm": 1.4110356569290161, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0325, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1837708830548925, | |
| "grad_norm": 1.8565313816070557, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.063, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2219570405727924, | |
| "grad_norm": 1.7540152072906494, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0558, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.260143198090692, | |
| "grad_norm": 5.772634029388428, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1493, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2983293556085918, | |
| "grad_norm": 1.3496861457824707, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1377, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3365155131264916, | |
| "grad_norm": 2.5683510303497314, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1028, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3747016706443915, | |
| "grad_norm": 5.049073696136475, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0636, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4128878281622912, | |
| "grad_norm": 4.343881130218506, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0452, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4510739856801909, | |
| "grad_norm": 1.931282639503479, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0356, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4892601431980907, | |
| "grad_norm": 1.8026151657104492, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0255, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5274463007159904, | |
| "grad_norm": 1.7957236766815186, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0455, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5656324582338903, | |
| "grad_norm": 1.2301855087280273, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0647, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.60381861575179, | |
| "grad_norm": 1.4172601699829102, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0399, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6420047732696896, | |
| "grad_norm": 0.4407726228237152, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0203, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6801909307875895, | |
| "grad_norm": 0.4551279544830322, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0218, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7183770883054894, | |
| "grad_norm": 0.5890151262283325, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.031, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.756563245823389, | |
| "grad_norm": 3.00361967086792, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.039, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7947494033412887, | |
| "grad_norm": 3.0584700107574463, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0615, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8329355608591884, | |
| "grad_norm": 1.4933966398239136, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0582, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8711217183770883, | |
| "grad_norm": 1.9643332958221436, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0364, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9093078758949882, | |
| "grad_norm": 0.3190707564353943, | |
| "learning_rate": 0.0, | |
| "loss": 0.0157, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9093078758949882, | |
| "eval_loss": 0.03395751491189003, | |
| "eval_runtime": 1.6062, | |
| "eval_samples_per_second": 110.2, | |
| "eval_steps_per_second": 14.32, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |