| { | |
| "best_metric": 10.279115676879883, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.030716068343252065, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006143213668650413, | |
| "grad_norm": 0.7780297994613647, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3888, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006143213668650413, | |
| "eval_loss": 10.379473686218262, | |
| "eval_runtime": 10.2875, | |
| "eval_samples_per_second": 1066.055, | |
| "eval_steps_per_second": 133.269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012286427337300826, | |
| "grad_norm": 0.7444933652877808, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3902, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001842964100595124, | |
| "grad_norm": 0.6800626516342163, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3831, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024572854674601652, | |
| "grad_norm": 0.6638268828392029, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3727, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0030716068343252063, | |
| "grad_norm": 0.6447324752807617, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3679, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003685928201190248, | |
| "grad_norm": 0.5840840935707092, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3623, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004300249568055289, | |
| "grad_norm": 0.5894371271133423, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3615, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0049145709349203304, | |
| "grad_norm": 0.6044824123382568, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3607, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0055288923017853715, | |
| "grad_norm": 0.6095870733261108, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3605, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006143213668650413, | |
| "grad_norm": 0.6198980808258057, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3638, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006757535035515454, | |
| "grad_norm": 0.6176487803459167, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3653, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007371856402380496, | |
| "grad_norm": 0.6425470113754272, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.369, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007986177769245536, | |
| "grad_norm": 0.6421533226966858, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3601, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008600499136110579, | |
| "grad_norm": 0.7918420433998108, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3446, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00921482050297562, | |
| "grad_norm": 0.7731742858886719, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3286, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009829141869840661, | |
| "grad_norm": 0.708093523979187, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.346, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010443463236705702, | |
| "grad_norm": 0.7408599853515625, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3252, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011057784603570743, | |
| "grad_norm": 0.7132424712181091, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3184, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011672105970435784, | |
| "grad_norm": 0.6739526391029358, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3217, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012286427337300825, | |
| "grad_norm": 0.6705430150032043, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3243, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012900748704165866, | |
| "grad_norm": 0.6778592467308044, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3372, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013515070071030907, | |
| "grad_norm": 0.7233036756515503, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3294, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014129391437895948, | |
| "grad_norm": 0.7231239080429077, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3213, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014743712804760991, | |
| "grad_norm": 0.7424492835998535, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.334, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015358034171626032, | |
| "grad_norm": 0.7660529613494873, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3472, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015358034171626032, | |
| "eval_loss": 10.30517578125, | |
| "eval_runtime": 10.0941, | |
| "eval_samples_per_second": 1086.476, | |
| "eval_steps_per_second": 135.822, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015972355538491072, | |
| "grad_norm": 0.9604129195213318, | |
| "learning_rate": 5e-05, | |
| "loss": 10.2904, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.016586676905356115, | |
| "grad_norm": 0.9269930720329285, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.2859, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017200998272221157, | |
| "grad_norm": 0.8787549734115601, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.2847, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.017815319639086197, | |
| "grad_norm": 0.8421987295150757, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.2891, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01842964100595124, | |
| "grad_norm": 0.8014142513275146, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.2808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01904396237281628, | |
| "grad_norm": 0.8265954256057739, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.2778, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.019658283739681322, | |
| "grad_norm": 0.7673512697219849, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.2999, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02027260510654636, | |
| "grad_norm": 0.7799116373062134, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.295, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.020886926473411404, | |
| "grad_norm": 0.7570932507514954, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.311, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.021501247840276443, | |
| "grad_norm": 0.7700633406639099, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3018, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022115569207141486, | |
| "grad_norm": 0.7829461693763733, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.2994, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.022729890574006525, | |
| "grad_norm": 0.8024079203605652, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3168, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02334421194087157, | |
| "grad_norm": 0.764173150062561, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3122, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02395853330773661, | |
| "grad_norm": 0.9772190451622009, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.2755, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02457285467460165, | |
| "grad_norm": 0.9249041676521301, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.2693, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025187176041466693, | |
| "grad_norm": 0.8748021721839905, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.2821, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.025801497408331733, | |
| "grad_norm": 0.8471273183822632, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.2766, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.026415818775196775, | |
| "grad_norm": 0.8282643556594849, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.2786, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.027030140142061815, | |
| "grad_norm": 0.7962176203727722, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.2759, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.027644461508926858, | |
| "grad_norm": 0.7981472015380859, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.283, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028258782875791897, | |
| "grad_norm": 0.800590991973877, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.2844, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02887310424265694, | |
| "grad_norm": 0.7995105385780334, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.2902, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.029487425609521983, | |
| "grad_norm": 0.8139747381210327, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.299, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.030101746976387022, | |
| "grad_norm": 0.7791361808776855, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3037, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.030716068343252065, | |
| "grad_norm": 0.7885679602622986, | |
| "learning_rate": 0.0, | |
| "loss": 10.3219, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.030716068343252065, | |
| "eval_loss": 10.279115676879883, | |
| "eval_runtime": 10.1008, | |
| "eval_samples_per_second": 1085.753, | |
| "eval_steps_per_second": 135.732, | |
| "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": 84596179599360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |