| { |
| "best_metric": 0.8346361517906189, |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", |
| "epoch": 0.19061234214915415, |
| "eval_steps": 25, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.003812246842983083, |
| "grad_norm": 0.2967394292354584, |
| "learning_rate": 5e-05, |
| "loss": 0.9351, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.003812246842983083, |
| "eval_loss": 0.934563934803009, |
| "eval_runtime": 12.3785, |
| "eval_samples_per_second": 142.828, |
| "eval_steps_per_second": 17.854, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.007624493685966166, |
| "grad_norm": 0.33949005603790283, |
| "learning_rate": 0.0001, |
| "loss": 0.9268, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01143674052894925, |
| "grad_norm": 0.29785802960395813, |
| "learning_rate": 9.989294616193017e-05, |
| "loss": 0.9, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.015248987371932332, |
| "grad_norm": 0.26380258798599243, |
| "learning_rate": 9.957224306869053e-05, |
| "loss": 0.922, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.019061234214915415, |
| "grad_norm": 0.313311368227005, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.9216, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0228734810578985, |
| "grad_norm": 0.3013531565666199, |
| "learning_rate": 9.829629131445342e-05, |
| "loss": 0.9275, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.02668572790088158, |
| "grad_norm": 0.29245325922966003, |
| "learning_rate": 9.73465064747553e-05, |
| "loss": 0.8662, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.030497974743864665, |
| "grad_norm": 0.26414409279823303, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.7958, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.034310221586847746, |
| "grad_norm": 0.2993530035018921, |
| "learning_rate": 9.484363707663442e-05, |
| "loss": 0.9113, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03812246842983083, |
| "grad_norm": 0.27474743127822876, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 0.8902, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.041934715272813915, |
| "grad_norm": 0.27231356501579285, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.8842, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.045746962115797, |
| "grad_norm": 0.2848631739616394, |
| "learning_rate": 8.966766701456177e-05, |
| "loss": 0.8936, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.049559208958780084, |
| "grad_norm": 0.21465671062469482, |
| "learning_rate": 8.759199037394887e-05, |
| "loss": 0.9129, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.05337145580176316, |
| "grad_norm": 0.1949559450149536, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.8329, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.057183702644746245, |
| "grad_norm": 0.2053157389163971, |
| "learning_rate": 8.296729075500344e-05, |
| "loss": 0.9376, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.06099594948772933, |
| "grad_norm": 0.19364218413829803, |
| "learning_rate": 8.043807145043604e-05, |
| "loss": 0.8001, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.06480819633071241, |
| "grad_norm": 0.1981198489665985, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.8569, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.06862044317369549, |
| "grad_norm": 0.2124132364988327, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.8461, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.07243269001667858, |
| "grad_norm": 0.21935242414474487, |
| "learning_rate": 7.211443451095007e-05, |
| "loss": 0.8403, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.07624493685966166, |
| "grad_norm": 0.22234244644641876, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.8335, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.08005718370264475, |
| "grad_norm": 0.22361911833286285, |
| "learning_rate": 6.607197326515808e-05, |
| "loss": 0.8508, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.08386943054562783, |
| "grad_norm": 0.2258802205324173, |
| "learning_rate": 6.294095225512603e-05, |
| "loss": 0.7993, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.0876816773886109, |
| "grad_norm": 0.24764667451381683, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.8078, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.091493924231594, |
| "grad_norm": 0.25130197405815125, |
| "learning_rate": 5.6526309611002594e-05, |
| "loss": 0.7911, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.09530617107457708, |
| "grad_norm": 0.2888367772102356, |
| "learning_rate": 5.327015646150716e-05, |
| "loss": 0.8293, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.09530617107457708, |
| "eval_loss": 0.8428515195846558, |
| "eval_runtime": 12.3144, |
| "eval_samples_per_second": 143.571, |
| "eval_steps_per_second": 17.946, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.09911841791756017, |
| "grad_norm": 0.1759335994720459, |
| "learning_rate": 5e-05, |
| "loss": 0.8758, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.10293066476054324, |
| "grad_norm": 0.19624562561511993, |
| "learning_rate": 4.6729843538492847e-05, |
| "loss": 0.9195, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.10674291160352632, |
| "grad_norm": 0.19254527986049652, |
| "learning_rate": 4.347369038899744e-05, |
| "loss": 0.8493, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.11055515844650941, |
| "grad_norm": 0.20061329007148743, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.908, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.11436740528949249, |
| "grad_norm": 0.19461949169635773, |
| "learning_rate": 3.705904774487396e-05, |
| "loss": 0.8234, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.11817965213247558, |
| "grad_norm": 0.1995747834444046, |
| "learning_rate": 3.392802673484193e-05, |
| "loss": 0.8731, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.12199189897545866, |
| "grad_norm": 0.20301039516925812, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.8031, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.12580414581844174, |
| "grad_norm": 0.20862935483455658, |
| "learning_rate": 2.7885565489049946e-05, |
| "loss": 0.838, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.12961639266142483, |
| "grad_norm": 0.22189174592494965, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 0.8665, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.13342863950440792, |
| "grad_norm": 0.23263895511627197, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.8503, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.13724088634739098, |
| "grad_norm": 0.23706233501434326, |
| "learning_rate": 1.9561928549563968e-05, |
| "loss": 0.7954, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.14105313319037407, |
| "grad_norm": 0.27249541878700256, |
| "learning_rate": 1.703270924499656e-05, |
| "loss": 0.8025, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.14486538003335717, |
| "grad_norm": 0.1823560893535614, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.9405, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.14867762687634023, |
| "grad_norm": 0.16355444490909576, |
| "learning_rate": 1.2408009626051137e-05, |
| "loss": 0.8379, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.15248987371932332, |
| "grad_norm": 0.16927115619182587, |
| "learning_rate": 1.0332332985438248e-05, |
| "loss": 0.8402, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1563021205623064, |
| "grad_norm": 0.18029265105724335, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.8458, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.1601143674052895, |
| "grad_norm": 0.18312260508537292, |
| "learning_rate": 6.698729810778065e-06, |
| "loss": 0.8675, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.16392661424827257, |
| "grad_norm": 0.19348792731761932, |
| "learning_rate": 5.156362923365588e-06, |
| "loss": 0.8466, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.16773886109125566, |
| "grad_norm": 0.1927310675382614, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.7973, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.17155110793423875, |
| "grad_norm": 0.20133088529109955, |
| "learning_rate": 2.653493525244721e-06, |
| "loss": 0.8522, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.1753633547772218, |
| "grad_norm": 0.20981720089912415, |
| "learning_rate": 1.70370868554659e-06, |
| "loss": 0.8388, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.1791756016202049, |
| "grad_norm": 0.21205788850784302, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.7974, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.182987848463188, |
| "grad_norm": 0.23205319046974182, |
| "learning_rate": 4.277569313094809e-07, |
| "loss": 0.7912, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.1868000953061711, |
| "grad_norm": 0.24879471957683563, |
| "learning_rate": 1.0705383806982606e-07, |
| "loss": 0.848, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.19061234214915415, |
| "grad_norm": 0.29144957661628723, |
| "learning_rate": 0.0, |
| "loss": 0.8512, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.19061234214915415, |
| "eval_loss": 0.8346361517906189, |
| "eval_runtime": 12.391, |
| "eval_samples_per_second": 142.684, |
| "eval_steps_per_second": 17.836, |
| "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": 2.9585460372176896e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
