| { | |
| "best_metric": 0.44474974274635315, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02250098441806829, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004500196883613658, | |
| "grad_norm": 14.470405578613281, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4203, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004500196883613658, | |
| "eval_loss": 0.5684293508529663, | |
| "eval_runtime": 452.6459, | |
| "eval_samples_per_second": 33.072, | |
| "eval_steps_per_second": 4.136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009000393767227316, | |
| "grad_norm": 19.14165687561035, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013500590650840974, | |
| "grad_norm": 7.805152416229248, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.5321, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018000787534454632, | |
| "grad_norm": 8.711684226989746, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.508, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0022500984418068293, | |
| "grad_norm": 9.045823097229004, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.5231, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002700118130168195, | |
| "grad_norm": 7.023049354553223, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5126, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003150137818529561, | |
| "grad_norm": 7.273670673370361, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.4839, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0036001575068909265, | |
| "grad_norm": 7.670405864715576, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4644, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004050177195252292, | |
| "grad_norm": 7.142709255218506, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.485, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0045001968836136585, | |
| "grad_norm": 10.405477523803711, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4792, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004950216571975024, | |
| "grad_norm": 6.8295488357543945, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4574, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00540023626033639, | |
| "grad_norm": 9.01709270477295, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5589, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005850255948697755, | |
| "grad_norm": 7.213496208190918, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5097, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006300275637059122, | |
| "grad_norm": 4.949221611022949, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4468, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006750295325420487, | |
| "grad_norm": 4.6725897789001465, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4699, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007200315013781853, | |
| "grad_norm": 4.634977340698242, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4386, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0076503347021432185, | |
| "grad_norm": 4.886142253875732, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4563, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008100354390504584, | |
| "grad_norm": 5.206636428833008, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4715, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00855037407886595, | |
| "grad_norm": 5.231688499450684, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4375, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009000393767227317, | |
| "grad_norm": 5.446512699127197, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009450413455588683, | |
| "grad_norm": 5.378635883331299, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4393, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009900433143950048, | |
| "grad_norm": 5.624276161193848, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4593, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010350452832311414, | |
| "grad_norm": 5.555810928344727, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4336, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01080047252067278, | |
| "grad_norm": 5.919965744018555, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011250492209034145, | |
| "grad_norm": 7.292273044586182, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5362, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011250492209034145, | |
| "eval_loss": 0.4537418782711029, | |
| "eval_runtime": 453.3835, | |
| "eval_samples_per_second": 33.018, | |
| "eval_steps_per_second": 4.129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01170051189739551, | |
| "grad_norm": 3.6232125759124756, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3568, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012150531585756876, | |
| "grad_norm": 4.612757205963135, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4476, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012600551274118243, | |
| "grad_norm": 4.424397945404053, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4496, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013050570962479609, | |
| "grad_norm": 4.639833450317383, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4594, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.013500590650840975, | |
| "grad_norm": 4.268221855163574, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4328, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01395061033920234, | |
| "grad_norm": 4.489709377288818, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4389, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.014400630027563706, | |
| "grad_norm": 4.984375476837158, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4716, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014850649715925071, | |
| "grad_norm": 5.402334690093994, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4697, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015300669404286437, | |
| "grad_norm": 6.122222423553467, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.443, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.015750689092647804, | |
| "grad_norm": 5.864333152770996, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4321, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016200708781009168, | |
| "grad_norm": 6.539216041564941, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4305, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.016650728469370536, | |
| "grad_norm": 7.409786224365234, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.467, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0171007481577319, | |
| "grad_norm": 7.067270278930664, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4947, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.017550767846093267, | |
| "grad_norm": 3.5447089672088623, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4212, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018000787534454634, | |
| "grad_norm": 4.050203323364258, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4935, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018450807222815998, | |
| "grad_norm": 4.0633625984191895, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4547, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.018900826911177365, | |
| "grad_norm": 4.116041660308838, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4385, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01935084659953873, | |
| "grad_norm": 4.439619541168213, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4512, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.019800866287900096, | |
| "grad_norm": 4.4050984382629395, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4405, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02025088597626146, | |
| "grad_norm": 4.711236000061035, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4533, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.020700905664622828, | |
| "grad_norm": 4.956698894500732, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4822, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02115092535298419, | |
| "grad_norm": 5.101325035095215, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4301, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02160094504134556, | |
| "grad_norm": 5.300014972686768, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4474, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.022050964729706926, | |
| "grad_norm": 6.052067756652832, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4681, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02250098441806829, | |
| "grad_norm": 7.596202373504639, | |
| "learning_rate": 0.0, | |
| "loss": 0.5284, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02250098441806829, | |
| "eval_loss": 0.44474974274635315, | |
| "eval_runtime": 455.7441, | |
| "eval_samples_per_second": 32.847, | |
| "eval_steps_per_second": 4.108, | |
| "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": 5.6941044108047155e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |