{ "best_metric": 1.3975412845611572, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.0665889795238888, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001331779590477776, "grad_norm": 1.7705880403518677, "learning_rate": 5e-05, "loss": 2.2224, "step": 1 }, { "epoch": 0.001331779590477776, "eval_loss": 2.8852221965789795, "eval_runtime": 132.5537, "eval_samples_per_second": 38.166, "eval_steps_per_second": 4.775, "step": 1 }, { "epoch": 0.002663559180955552, "grad_norm": 1.9668562412261963, "learning_rate": 0.0001, "loss": 2.3534, "step": 2 }, { "epoch": 0.003995338771433328, "grad_norm": 1.9368491172790527, "learning_rate": 9.989294616193017e-05, "loss": 2.3148, "step": 3 }, { "epoch": 0.005327118361911104, "grad_norm": 1.7968571186065674, "learning_rate": 9.957224306869053e-05, "loss": 2.2266, "step": 4 }, { "epoch": 0.00665889795238888, "grad_norm": 1.8224536180496216, "learning_rate": 9.903926402016153e-05, "loss": 2.0955, "step": 5 }, { "epoch": 0.007990677542866656, "grad_norm": 1.6938631534576416, "learning_rate": 9.829629131445342e-05, "loss": 1.9078, "step": 6 }, { "epoch": 0.009322457133344432, "grad_norm": 1.8391814231872559, "learning_rate": 9.73465064747553e-05, "loss": 1.7316, "step": 7 }, { "epoch": 0.010654236723822208, "grad_norm": 1.6968375444412231, "learning_rate": 9.619397662556435e-05, "loss": 1.7418, "step": 8 }, { "epoch": 0.011986016314299984, "grad_norm": 1.964697241783142, "learning_rate": 9.484363707663442e-05, "loss": 1.6802, "step": 9 }, { "epoch": 0.01331779590477776, "grad_norm": 1.7452012300491333, "learning_rate": 9.330127018922194e-05, "loss": 1.5496, "step": 10 }, { "epoch": 0.014649575495255536, "grad_norm": 1.5461745262145996, "learning_rate": 9.157348061512727e-05, "loss": 1.4847, "step": 11 }, { "epoch": 0.015981355085733312, "grad_norm": 1.8924380540847778, "learning_rate": 8.966766701456177e-05, "loss": 1.5694, "step": 12 }, { "epoch": 0.017313134676211088, "grad_norm": 1.3992854356765747, "learning_rate": 8.759199037394887e-05, "loss": 1.8179, "step": 13 }, { "epoch": 0.018644914266688864, "grad_norm": 0.9770612120628357, "learning_rate": 8.535533905932738e-05, "loss": 1.656, "step": 14 }, { "epoch": 0.01997669385716664, "grad_norm": 0.8005850315093994, "learning_rate": 8.296729075500344e-05, "loss": 1.5767, "step": 15 }, { "epoch": 0.021308473447644416, "grad_norm": 0.7786310315132141, "learning_rate": 8.043807145043604e-05, "loss": 1.6064, "step": 16 }, { "epoch": 0.022640253038122192, "grad_norm": 0.794090986251831, "learning_rate": 7.777851165098012e-05, "loss": 1.3034, "step": 17 }, { "epoch": 0.023972032628599968, "grad_norm": 0.856802761554718, "learning_rate": 7.500000000000001e-05, "loss": 1.3084, "step": 18 }, { "epoch": 0.025303812219077744, "grad_norm": 0.9487705826759338, "learning_rate": 7.211443451095007e-05, "loss": 1.4072, "step": 19 }, { "epoch": 0.02663559180955552, "grad_norm": 1.0493732690811157, "learning_rate": 6.91341716182545e-05, "loss": 1.3545, "step": 20 }, { "epoch": 0.027967371400033296, "grad_norm": 1.1461377143859863, "learning_rate": 6.607197326515808e-05, "loss": 1.4088, "step": 21 }, { "epoch": 0.029299150990511072, "grad_norm": 1.1133924722671509, "learning_rate": 6.294095225512603e-05, "loss": 1.3857, "step": 22 }, { "epoch": 0.030630930580988848, "grad_norm": 1.176496148109436, "learning_rate": 5.9754516100806423e-05, "loss": 1.3288, "step": 23 }, { "epoch": 0.031962710171466624, "grad_norm": 1.212140440940857, "learning_rate": 5.6526309611002594e-05, "loss": 1.1867, "step": 24 }, { "epoch": 0.0332944897619444, "grad_norm": 1.6188991069793701, "learning_rate": 5.327015646150716e-05, "loss": 1.5372, "step": 25 }, { "epoch": 0.0332944897619444, "eval_loss": 1.4368922710418701, "eval_runtime": 155.5934, "eval_samples_per_second": 32.514, "eval_steps_per_second": 4.068, "step": 25 }, { "epoch": 0.034626269352422176, "grad_norm": 0.7546113729476929, "learning_rate": 5e-05, "loss": 1.6641, "step": 26 }, { "epoch": 0.03595804894289995, "grad_norm": 0.7036129832267761, "learning_rate": 4.6729843538492847e-05, "loss": 1.5849, "step": 27 }, { "epoch": 0.03728982853337773, "grad_norm": 0.7657355666160583, "learning_rate": 4.347369038899744e-05, "loss": 1.4307, "step": 28 }, { "epoch": 0.038621608123855504, "grad_norm": 0.7765692472457886, "learning_rate": 4.0245483899193595e-05, "loss": 1.4377, "step": 29 }, { "epoch": 0.03995338771433328, "grad_norm": 0.8169478178024292, "learning_rate": 3.705904774487396e-05, "loss": 1.3892, "step": 30 }, { "epoch": 0.041285167304811056, "grad_norm": 0.8468606472015381, "learning_rate": 3.392802673484193e-05, "loss": 1.2886, "step": 31 }, { "epoch": 0.04261694689528883, "grad_norm": 0.842719554901123, "learning_rate": 3.086582838174551e-05, "loss": 1.1519, "step": 32 }, { "epoch": 0.04394872648576661, "grad_norm": 0.8773880004882812, "learning_rate": 2.7885565489049946e-05, "loss": 1.4317, "step": 33 }, { "epoch": 0.045280506076244384, "grad_norm": 1.0714538097381592, "learning_rate": 2.500000000000001e-05, "loss": 1.4496, "step": 34 }, { "epoch": 0.04661228566672216, "grad_norm": 1.0184491872787476, "learning_rate": 2.2221488349019903e-05, "loss": 1.4086, "step": 35 }, { "epoch": 0.047944065257199936, "grad_norm": 1.0979220867156982, "learning_rate": 1.9561928549563968e-05, "loss": 1.2355, "step": 36 }, { "epoch": 0.04927584484767771, "grad_norm": 1.6338611841201782, "learning_rate": 1.703270924499656e-05, "loss": 1.4841, "step": 37 }, { "epoch": 0.05060762443815549, "grad_norm": 0.7203386425971985, "learning_rate": 1.4644660940672627e-05, "loss": 1.7433, "step": 38 }, { "epoch": 0.051939404028633264, "grad_norm": 0.6181879043579102, "learning_rate": 1.2408009626051137e-05, "loss": 1.5915, "step": 39 }, { "epoch": 0.05327118361911104, "grad_norm": 0.6601304411888123, "learning_rate": 1.0332332985438248e-05, "loss": 1.5255, "step": 40 }, { "epoch": 0.054602963209588816, "grad_norm": 0.7737628817558289, "learning_rate": 8.426519384872733e-06, "loss": 1.4904, "step": 41 }, { "epoch": 0.05593474280006659, "grad_norm": 0.6829192638397217, "learning_rate": 6.698729810778065e-06, "loss": 1.3329, "step": 42 }, { "epoch": 0.05726652239054437, "grad_norm": 0.7644971609115601, "learning_rate": 5.156362923365588e-06, "loss": 1.3325, "step": 43 }, { "epoch": 0.058598301981022144, "grad_norm": 0.7881768941879272, "learning_rate": 3.8060233744356633e-06, "loss": 1.2382, "step": 44 }, { "epoch": 0.05993008157149992, "grad_norm": 0.9224614500999451, "learning_rate": 2.653493525244721e-06, "loss": 1.3537, "step": 45 }, { "epoch": 0.061261861161977696, "grad_norm": 0.8903812170028687, "learning_rate": 1.70370868554659e-06, "loss": 1.2534, "step": 46 }, { "epoch": 0.06259364075245546, "grad_norm": 0.9834040403366089, "learning_rate": 9.607359798384785e-07, "loss": 1.3721, "step": 47 }, { "epoch": 0.06392542034293325, "grad_norm": 1.1316769123077393, "learning_rate": 4.277569313094809e-07, "loss": 1.1691, "step": 48 }, { "epoch": 0.06525719993341102, "grad_norm": 1.144602656364441, "learning_rate": 1.0705383806982606e-07, "loss": 1.2945, "step": 49 }, { "epoch": 0.0665889795238888, "grad_norm": 1.6286240816116333, "learning_rate": 0.0, "loss": 1.5057, "step": 50 }, { "epoch": 0.0665889795238888, "eval_loss": 1.3975412845611572, "eval_runtime": 132.4989, "eval_samples_per_second": 38.181, "eval_steps_per_second": 4.777, "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": 5.968083617316864e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }