{ "best_metric": 2.5868492126464844, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.13065490772497143, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0026130981544994283, "grad_norm": 0.17355452477931976, "learning_rate": 5e-05, "loss": 2.5233, "step": 1 }, { "epoch": 0.0026130981544994283, "eval_loss": 3.012192726135254, "eval_runtime": 29.3618, "eval_samples_per_second": 87.801, "eval_steps_per_second": 11.001, "step": 1 }, { "epoch": 0.005226196308998857, "grad_norm": 0.18734553456306458, "learning_rate": 0.0001, "loss": 2.5518, "step": 2 }, { "epoch": 0.007839294463498285, "grad_norm": 0.18581555783748627, "learning_rate": 9.989294616193017e-05, "loss": 2.5721, "step": 3 }, { "epoch": 0.010452392617997713, "grad_norm": 0.19467462599277496, "learning_rate": 9.957224306869053e-05, "loss": 2.6214, "step": 4 }, { "epoch": 0.013065490772497142, "grad_norm": 0.19739745557308197, "learning_rate": 9.903926402016153e-05, "loss": 2.6669, "step": 5 }, { "epoch": 0.01567858892699657, "grad_norm": 0.20953311026096344, "learning_rate": 9.829629131445342e-05, "loss": 2.6156, "step": 6 }, { "epoch": 0.018291687081496, "grad_norm": 0.26149553060531616, "learning_rate": 9.73465064747553e-05, "loss": 2.5649, "step": 7 }, { "epoch": 0.020904785235995427, "grad_norm": 0.3346858620643616, "learning_rate": 9.619397662556435e-05, "loss": 2.6212, "step": 8 }, { "epoch": 0.023517883390494855, "grad_norm": 0.4584973156452179, "learning_rate": 9.484363707663442e-05, "loss": 3.0511, "step": 9 }, { "epoch": 0.026130981544994283, "grad_norm": 0.6182145476341248, "learning_rate": 9.330127018922194e-05, "loss": 2.9278, "step": 10 }, { "epoch": 0.02874407969949371, "grad_norm": 0.8655480146408081, "learning_rate": 9.157348061512727e-05, "loss": 3.2934, "step": 11 }, { "epoch": 0.03135717785399314, "grad_norm": 1.251930594444275, "learning_rate": 8.966766701456177e-05, "loss": 3.7197, "step": 12 }, { "epoch": 0.03397027600849257, "grad_norm": 0.329143762588501, "learning_rate": 8.759199037394887e-05, "loss": 2.4767, "step": 13 }, { "epoch": 0.036583374162992, "grad_norm": 0.35682442784309387, "learning_rate": 8.535533905932738e-05, "loss": 2.5104, "step": 14 }, { "epoch": 0.039196472317491425, "grad_norm": 0.30937492847442627, "learning_rate": 8.296729075500344e-05, "loss": 2.5524, "step": 15 }, { "epoch": 0.04180957047199085, "grad_norm": 0.2561572194099426, "learning_rate": 8.043807145043604e-05, "loss": 2.4258, "step": 16 }, { "epoch": 0.04442266862649028, "grad_norm": 0.25609326362609863, "learning_rate": 7.777851165098012e-05, "loss": 2.4862, "step": 17 }, { "epoch": 0.04703576678098971, "grad_norm": 0.25606176257133484, "learning_rate": 7.500000000000001e-05, "loss": 2.5181, "step": 18 }, { "epoch": 0.04964886493548914, "grad_norm": 0.3287118375301361, "learning_rate": 7.211443451095007e-05, "loss": 2.5548, "step": 19 }, { "epoch": 0.05226196308998857, "grad_norm": 0.362893670797348, "learning_rate": 6.91341716182545e-05, "loss": 2.5596, "step": 20 }, { "epoch": 0.054875061244487995, "grad_norm": 0.40215370059013367, "learning_rate": 6.607197326515808e-05, "loss": 2.5559, "step": 21 }, { "epoch": 0.05748815939898742, "grad_norm": 0.5295920372009277, "learning_rate": 6.294095225512603e-05, "loss": 2.9173, "step": 22 }, { "epoch": 0.06010125755348685, "grad_norm": 0.625182032585144, "learning_rate": 5.9754516100806423e-05, "loss": 2.8893, "step": 23 }, { "epoch": 0.06271435570798628, "grad_norm": 0.7390320301055908, "learning_rate": 5.6526309611002594e-05, "loss": 2.8407, "step": 24 }, { "epoch": 0.06532745386248572, "grad_norm": 1.2202332019805908, "learning_rate": 5.327015646150716e-05, "loss": 3.0844, "step": 25 }, { "epoch": 0.06532745386248572, "eval_loss": 2.626925230026245, "eval_runtime": 29.3632, "eval_samples_per_second": 87.797, "eval_steps_per_second": 11.0, "step": 25 }, { "epoch": 0.06794055201698514, "grad_norm": 0.2307354360818863, "learning_rate": 5e-05, "loss": 2.3779, "step": 26 }, { "epoch": 0.07055365017148457, "grad_norm": 0.233708456158638, "learning_rate": 4.6729843538492847e-05, "loss": 2.3673, "step": 27 }, { "epoch": 0.073166748325984, "grad_norm": 0.27781909704208374, "learning_rate": 4.347369038899744e-05, "loss": 2.4519, "step": 28 }, { "epoch": 0.07577984648048343, "grad_norm": 0.2605210840702057, "learning_rate": 4.0245483899193595e-05, "loss": 2.4452, "step": 29 }, { "epoch": 0.07839294463498285, "grad_norm": 0.2625426948070526, "learning_rate": 3.705904774487396e-05, "loss": 2.4593, "step": 30 }, { "epoch": 0.08100604278948229, "grad_norm": 0.28291064500808716, "learning_rate": 3.392802673484193e-05, "loss": 2.5734, "step": 31 }, { "epoch": 0.0836191409439817, "grad_norm": 0.3215564489364624, "learning_rate": 3.086582838174551e-05, "loss": 2.5779, "step": 32 }, { "epoch": 0.08623223909848114, "grad_norm": 0.40029940009117126, "learning_rate": 2.7885565489049946e-05, "loss": 2.7664, "step": 33 }, { "epoch": 0.08884533725298056, "grad_norm": 0.4789843261241913, "learning_rate": 2.500000000000001e-05, "loss": 2.6643, "step": 34 }, { "epoch": 0.09145843540748, "grad_norm": 0.5274697542190552, "learning_rate": 2.2221488349019903e-05, "loss": 2.7978, "step": 35 }, { "epoch": 0.09407153356197942, "grad_norm": 0.6247810125350952, "learning_rate": 1.9561928549563968e-05, "loss": 2.5879, "step": 36 }, { "epoch": 0.09668463171647886, "grad_norm": 0.8597372770309448, "learning_rate": 1.703270924499656e-05, "loss": 2.905, "step": 37 }, { "epoch": 0.09929772987097828, "grad_norm": 0.2140260934829712, "learning_rate": 1.4644660940672627e-05, "loss": 2.4018, "step": 38 }, { "epoch": 0.10191082802547771, "grad_norm": 0.19503909349441528, "learning_rate": 1.2408009626051137e-05, "loss": 2.4463, "step": 39 }, { "epoch": 0.10452392617997713, "grad_norm": 0.2137904167175293, "learning_rate": 1.0332332985438248e-05, "loss": 2.4112, "step": 40 }, { "epoch": 0.10713702433447657, "grad_norm": 0.22088205814361572, "learning_rate": 8.426519384872733e-06, "loss": 2.4364, "step": 41 }, { "epoch": 0.10975012248897599, "grad_norm": 0.21924644708633423, "learning_rate": 6.698729810778065e-06, "loss": 2.5638, "step": 42 }, { "epoch": 0.11236322064347543, "grad_norm": 0.2636262774467468, "learning_rate": 5.156362923365588e-06, "loss": 2.6048, "step": 43 }, { "epoch": 0.11497631879797485, "grad_norm": 0.2927165627479553, "learning_rate": 3.8060233744356633e-06, "loss": 2.5676, "step": 44 }, { "epoch": 0.11758941695247428, "grad_norm": 0.29179003834724426, "learning_rate": 2.653493525244721e-06, "loss": 2.427, "step": 45 }, { "epoch": 0.1202025151069737, "grad_norm": 0.3900332748889923, "learning_rate": 1.70370868554659e-06, "loss": 2.6848, "step": 46 }, { "epoch": 0.12281561326147314, "grad_norm": 0.5040877461433411, "learning_rate": 9.607359798384785e-07, "loss": 2.6233, "step": 47 }, { "epoch": 0.12542871141597256, "grad_norm": 0.581149697303772, "learning_rate": 4.277569313094809e-07, "loss": 2.5518, "step": 48 }, { "epoch": 0.12804180957047198, "grad_norm": 0.7256733775138855, "learning_rate": 1.0705383806982606e-07, "loss": 2.756, "step": 49 }, { "epoch": 0.13065490772497143, "grad_norm": 1.146926999092102, "learning_rate": 0.0, "loss": 3.0167, "step": 50 }, { "epoch": 0.13065490772497143, "eval_loss": 2.5868492126464844, "eval_runtime": 29.3665, "eval_samples_per_second": 87.787, "eval_steps_per_second": 10.999, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 1.059536353886208e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }