| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.206896551724138, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0239880059970015, | |
| "grad_norm": 25.815780639648438, | |
| "learning_rate": 5e-05, | |
| "loss": 12.6296, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0239880059970015, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2868, | |
| "eval_samples_per_second": 38.563, | |
| "eval_steps_per_second": 4.94, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.047976011994003, | |
| "grad_norm": 26.31700897216797, | |
| "learning_rate": 0.0001, | |
| "loss": 12.742, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07196401799100449, | |
| "grad_norm": 26.64243507385254, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.3839, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.095952023988006, | |
| "grad_norm": 34.356658935546875, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.5182, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1199400299850075, | |
| "grad_norm": 20.215286254882812, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.5691, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14392803598200898, | |
| "grad_norm": 8.281304359436035, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4542, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1679160419790105, | |
| "grad_norm": 44.6995964050293, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6559, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.191904047976012, | |
| "grad_norm": 4.587508678436279, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2158920539730135, | |
| "grad_norm": 5.482951641082764, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8605, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.239880059970015, | |
| "grad_norm": 5.588258266448975, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2638680659670165, | |
| "grad_norm": 2.3857452869415283, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7302, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.28785607196401797, | |
| "grad_norm": 3.0859477519989014, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6727, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3118440779610195, | |
| "grad_norm": 2.9488019943237305, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7185, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.335832083958021, | |
| "grad_norm": 3.7752580642700195, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6647, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3598200899550225, | |
| "grad_norm": 2.847517967224121, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.383808095952024, | |
| "grad_norm": 2.5103867053985596, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.57, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4077961019490255, | |
| "grad_norm": 3.128657817840576, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5727, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.431784107946027, | |
| "grad_norm": 2.203118085861206, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5221, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.45577211394302847, | |
| "grad_norm": 3.978393077850342, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6599, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.47976011994003, | |
| "grad_norm": 3.0100159645080566, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5186, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5037481259370314, | |
| "grad_norm": 3.876760482788086, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5536, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.527736131934033, | |
| "grad_norm": 2.3143439292907715, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.427, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 3.4697108268737793, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5237, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5757121439280359, | |
| "grad_norm": 1.9571346044540405, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3886, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5997001499250375, | |
| "grad_norm": 2.0236098766326904, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3582, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5997001499250375, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.3045, | |
| "eval_samples_per_second": 38.469, | |
| "eval_steps_per_second": 4.928, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.623688155922039, | |
| "grad_norm": 2.2931978702545166, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4088, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6476761619190404, | |
| "grad_norm": 4.021605491638184, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4037, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.671664167916042, | |
| "grad_norm": 3.1461658477783203, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5003, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 3.1163697242736816, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5027, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.719640179910045, | |
| "grad_norm": 2.4896295070648193, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3963, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7436281859070465, | |
| "grad_norm": 2.6032440662384033, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3874, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.767616191904048, | |
| "grad_norm": 2.020462989807129, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3101, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7916041979010495, | |
| "grad_norm": 1.9592450857162476, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3533, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.815592203898051, | |
| "grad_norm": 2.000779151916504, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3312, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8395802098950524, | |
| "grad_norm": 2.860116958618164, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.863568215892054, | |
| "grad_norm": 3.1632578372955322, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3844, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8875562218890555, | |
| "grad_norm": 1.6567466259002686, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3445, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9115442278860569, | |
| "grad_norm": 3.800011396408081, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4563, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9355322338830585, | |
| "grad_norm": 4.2941741943359375, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3852, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.95952023988006, | |
| "grad_norm": 3.70890212059021, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4847, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9835082458770614, | |
| "grad_norm": 3.93947696685791, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5756, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.014992503748126, | |
| "grad_norm": 2.8971164226531982, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3497, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0389805097451275, | |
| "grad_norm": 3.1195619106292725, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2846, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.062968515742129, | |
| "grad_norm": 1.7674708366394043, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1979, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0869565217391304, | |
| "grad_norm": 2.618422269821167, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2861, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1109445277361318, | |
| "grad_norm": 2.5724215507507324, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2475, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1349325337331335, | |
| "grad_norm": 2.017848014831543, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3238, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.158920539730135, | |
| "grad_norm": 2.6160171031951904, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2674, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1829085457271364, | |
| "grad_norm": 1.9704896211624146, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2627, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 4.044738292694092, | |
| "learning_rate": 0.0, | |
| "loss": 0.375, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2862, | |
| "eval_samples_per_second": 38.566, | |
| "eval_steps_per_second": 4.941, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |