| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.8018018018018018, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.036036036036036036, | |
| "grad_norm": 0.9987035989761353, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.036036036036036036, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.0843, | |
| "eval_samples_per_second": 36.78, | |
| "eval_steps_per_second": 4.72, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "grad_norm": 0.971971333026886, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8095, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 1.0247091054916382, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.0093, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 1.0774474143981934, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.1557, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18018018018018017, | |
| "grad_norm": 1.101145625114441, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.0087, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 1.0605506896972656, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.9362, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25225225225225223, | |
| "grad_norm": 0.9831973314285278, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.2861, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 1.1115872859954834, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.0562, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 1.3432058095932007, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.1655, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.36036036036036034, | |
| "grad_norm": 1.3428442478179932, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.108, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3963963963963964, | |
| "grad_norm": 1.2244690656661987, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 5.1427, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 1.1294629573822021, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.0746, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46846846846846846, | |
| "grad_norm": 1.3526092767715454, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 5.231, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5045045045045045, | |
| "grad_norm": 1.020145297050476, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.7132, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 1.0296194553375244, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.6688, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 1.1286603212356567, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.5959, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6126126126126126, | |
| "grad_norm": 1.1740059852600098, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.887, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 1.2440125942230225, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.6247, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6846846846846847, | |
| "grad_norm": 1.2338988780975342, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.5548, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 1.399675965309143, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.7504, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7567567567567568, | |
| "grad_norm": 0.9647018909454346, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.4062, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7927927927927928, | |
| "grad_norm": 0.920181930065155, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.1608, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8288288288288288, | |
| "grad_norm": 1.0398772954940796, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 4.3302, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 1.0814138650894165, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 4.4058, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9009009009009009, | |
| "grad_norm": 1.162844181060791, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.5071, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9009009009009009, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.0767, | |
| "eval_samples_per_second": 36.835, | |
| "eval_steps_per_second": 4.728, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9369369369369369, | |
| "grad_norm": 1.3344053030014038, | |
| "learning_rate": 5e-05, | |
| "loss": 4.515, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.972972972972973, | |
| "grad_norm": 1.7347127199172974, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 4.757, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.009009009009009, | |
| "grad_norm": 1.270090103149414, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 5.3056, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.045045045045045, | |
| "grad_norm": 0.9538925290107727, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 4.028, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.9219748377799988, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.7613, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.117117117117117, | |
| "grad_norm": 1.083941102027893, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.2848, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1531531531531531, | |
| "grad_norm": 1.0106741189956665, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.9071, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1891891891891893, | |
| "grad_norm": 1.3047679662704468, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 4.2408, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2252252252252251, | |
| "grad_norm": 1.0641274452209473, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.3484, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2612612612612613, | |
| "grad_norm": 1.174180269241333, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.4811, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2972972972972974, | |
| "grad_norm": 0.8928071856498718, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.5643, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.018917202949524, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.9813, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3693693693693694, | |
| "grad_norm": 1.0619010925292969, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.1614, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4054054054054055, | |
| "grad_norm": 1.1027988195419312, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 4.0984, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "grad_norm": 1.2321841716766357, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.9475, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4774774774774775, | |
| "grad_norm": 1.2451386451721191, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.3466, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5135135135135136, | |
| "grad_norm": 1.1862729787826538, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.5245, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5495495495495497, | |
| "grad_norm": 1.0056686401367188, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.9216, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5855855855855856, | |
| "grad_norm": 1.0354795455932617, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.0247, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6216216216216215, | |
| "grad_norm": 1.0059832334518433, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.6011, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6576576576576576, | |
| "grad_norm": 1.219404935836792, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.9867, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6936936936936937, | |
| "grad_norm": 1.2384576797485352, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.8457, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7297297297297298, | |
| "grad_norm": 1.3424208164215088, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.3521, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7657657657657657, | |
| "grad_norm": 1.2357970476150513, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 4.6568, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "grad_norm": 0.9953389167785645, | |
| "learning_rate": 0.0, | |
| "loss": 3.814, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.0746, | |
| "eval_samples_per_second": 36.851, | |
| "eval_steps_per_second": 4.729, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |