| { | |
| "best_metric": 0.48576095700263977, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.2032967032967035, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04395604395604396, | |
| "grad_norm": 1.6147027015686035, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9245, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04395604395604396, | |
| "eval_loss": 1.125306487083435, | |
| "eval_runtime": 1.5098, | |
| "eval_samples_per_second": 101.338, | |
| "eval_steps_per_second": 13.247, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08791208791208792, | |
| "grad_norm": 1.9983218908309937, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0253, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13186813186813187, | |
| "grad_norm": 1.9161258935928345, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.0749, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17582417582417584, | |
| "grad_norm": 1.3471875190734863, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9817, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "grad_norm": 1.3092931509017944, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9245, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26373626373626374, | |
| "grad_norm": 0.8603388071060181, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6806, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.7902740240097046, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.5908, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3516483516483517, | |
| "grad_norm": 0.7974825501441956, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6714, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3956043956043956, | |
| "grad_norm": 0.5884117484092712, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6504, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 0.7321068048477173, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6882, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4835164835164835, | |
| "grad_norm": 0.8219019174575806, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7878, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5274725274725275, | |
| "grad_norm": 0.7585610151290894, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.509, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.4833940267562866, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5126, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.5011129379272461, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5713, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 0.5959790945053101, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6383, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7032967032967034, | |
| "grad_norm": 0.45197582244873047, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6132, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7472527472527473, | |
| "grad_norm": 0.44793838262557983, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5253, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7912087912087912, | |
| "grad_norm": 0.47516193985939026, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8351648351648352, | |
| "grad_norm": 0.3715343177318573, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4779, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.3526500165462494, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5268, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.42601215839385986, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6127, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.967032967032967, | |
| "grad_norm": 0.5091745257377625, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6665, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0137362637362637, | |
| "grad_norm": 0.49048399925231934, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6154, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0576923076923077, | |
| "grad_norm": 0.3723498284816742, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4186, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1016483516483517, | |
| "grad_norm": 0.33258843421936035, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4749, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1016483516483517, | |
| "eval_loss": 0.506989598274231, | |
| "eval_runtime": 1.5047, | |
| "eval_samples_per_second": 101.683, | |
| "eval_steps_per_second": 13.292, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1456043956043955, | |
| "grad_norm": 0.36688488721847534, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5008, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1895604395604396, | |
| "grad_norm": 0.43694236874580383, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5812, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2335164835164836, | |
| "grad_norm": 0.3758331537246704, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5703, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2774725274725274, | |
| "grad_norm": 0.448770135641098, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4405, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3214285714285714, | |
| "grad_norm": 0.37327253818511963, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4513, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3653846153846154, | |
| "grad_norm": 0.43464577198028564, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4473, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4093406593406592, | |
| "grad_norm": 0.37203073501586914, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5111, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4532967032967032, | |
| "grad_norm": 0.43420180678367615, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.555, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.4972527472527473, | |
| "grad_norm": 0.35687336325645447, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5298, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.541208791208791, | |
| "grad_norm": 0.3457031548023224, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3852, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.5851648351648353, | |
| "grad_norm": 0.3911322057247162, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4185, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.629120879120879, | |
| "grad_norm": 0.36752089858055115, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4663, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6730769230769231, | |
| "grad_norm": 0.43490225076675415, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5413, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7170329670329672, | |
| "grad_norm": 0.3592076897621155, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5346, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.760989010989011, | |
| "grad_norm": 0.4103586673736572, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.443, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.804945054945055, | |
| "grad_norm": 0.4131491780281067, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4211, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.848901098901099, | |
| "grad_norm": 0.3365662693977356, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4593, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.8928571428571428, | |
| "grad_norm": 0.38286104798316956, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5117, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9368131868131868, | |
| "grad_norm": 0.4395010769367218, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5906, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.9807692307692308, | |
| "grad_norm": 0.46687841415405273, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5821, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0274725274725274, | |
| "grad_norm": 0.4192560613155365, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4939, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0714285714285716, | |
| "grad_norm": 0.39490610361099243, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4142, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1153846153846154, | |
| "grad_norm": 0.45630407333374023, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4404, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.159340659340659, | |
| "grad_norm": 0.46277567744255066, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4813, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2032967032967035, | |
| "grad_norm": 0.498955637216568, | |
| "learning_rate": 0.0, | |
| "loss": 0.5494, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2032967032967035, | |
| "eval_loss": 0.48576095700263977, | |
| "eval_runtime": 1.5069, | |
| "eval_samples_per_second": 101.531, | |
| "eval_steps_per_second": 13.272, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |