| { | |
| "best_metric": 0.426371693611145, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5449591280653951, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010899182561307902, | |
| "grad_norm": 48.74156951904297, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010899182561307902, | |
| "eval_loss": 11.284085273742676, | |
| "eval_runtime": 71.4001, | |
| "eval_samples_per_second": 8.655, | |
| "eval_steps_per_second": 1.092, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021798365122615803, | |
| "grad_norm": 51.60028076171875, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0866, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0326975476839237, | |
| "grad_norm": 30.692434310913086, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.8167, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043596730245231606, | |
| "grad_norm": 11.017006874084473, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0877, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05449591280653951, | |
| "grad_norm": 7.536700248718262, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9595, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0653950953678474, | |
| "grad_norm": 3.1112093925476074, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5986, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07629427792915532, | |
| "grad_norm": 5.047523498535156, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.5773, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08719346049046321, | |
| "grad_norm": 1.6923166513442993, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5126, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09809264305177112, | |
| "grad_norm": 1.8672845363616943, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4981, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10899182561307902, | |
| "grad_norm": 1.621414065361023, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4449, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11989100817438691, | |
| "grad_norm": 6.684902667999268, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6032, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1307901907356948, | |
| "grad_norm": 3.221933603286743, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5688, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14168937329700274, | |
| "grad_norm": 3.1402652263641357, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5886, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15258855585831063, | |
| "grad_norm": 1.592869520187378, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5615, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16348773841961853, | |
| "grad_norm": 0.9822923541069031, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5196, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17438692098092642, | |
| "grad_norm": 1.522122859954834, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4893, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18528610354223432, | |
| "grad_norm": 1.7049654722213745, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4667, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19618528610354224, | |
| "grad_norm": 1.6317267417907715, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4413, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20708446866485014, | |
| "grad_norm": 3.2682507038116455, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4638, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21798365122615804, | |
| "grad_norm": 2.56499981880188, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4441, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22888283378746593, | |
| "grad_norm": 1.327353835105896, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4347, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23978201634877383, | |
| "grad_norm": 0.8864551782608032, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4295, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2506811989100817, | |
| "grad_norm": 1.4399280548095703, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3869, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2615803814713896, | |
| "grad_norm": 1.9145146608352661, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4312, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "grad_norm": 1.3893917798995972, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4949, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "eval_loss": 0.48585328459739685, | |
| "eval_runtime": 71.3281, | |
| "eval_samples_per_second": 8.664, | |
| "eval_steps_per_second": 1.094, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28337874659400547, | |
| "grad_norm": 4.9771599769592285, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4956, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29427792915531337, | |
| "grad_norm": 2.9701240062713623, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4031, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.30517711171662126, | |
| "grad_norm": 2.225861072540283, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4281, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31607629427792916, | |
| "grad_norm": 2.348742723464966, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4113, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32697547683923706, | |
| "grad_norm": 1.2155747413635254, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4347, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33787465940054495, | |
| "grad_norm": 1.0497678518295288, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4339, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34877384196185285, | |
| "grad_norm": 1.0491323471069336, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4078, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.35967302452316074, | |
| "grad_norm": 1.1474112272262573, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3978, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.37057220708446864, | |
| "grad_norm": 1.2539511919021606, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3917, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3814713896457766, | |
| "grad_norm": 1.2589647769927979, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4163, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3923705722070845, | |
| "grad_norm": 0.964292049407959, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3963, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4032697547683924, | |
| "grad_norm": 1.3542845249176025, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4011, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4141689373297003, | |
| "grad_norm": 1.3884631395339966, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4138, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4250681198910082, | |
| "grad_norm": 1.8797101974487305, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4123, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4359673024523161, | |
| "grad_norm": 1.6470329761505127, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4265, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44686648501362397, | |
| "grad_norm": 0.8266764879226685, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3881, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45776566757493187, | |
| "grad_norm": 1.2431610822677612, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.377, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.46866485013623976, | |
| "grad_norm": 1.4794811010360718, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4095, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.47956403269754766, | |
| "grad_norm": 1.0381994247436523, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3172, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4904632152588556, | |
| "grad_norm": 2.3326640129089355, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4444, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5013623978201635, | |
| "grad_norm": 1.3586293458938599, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3635, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5122615803814714, | |
| "grad_norm": 1.9634039402008057, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4188, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5231607629427792, | |
| "grad_norm": 1.3625668287277222, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3871, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5340599455040872, | |
| "grad_norm": 1.6320065259933472, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4262, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5449591280653951, | |
| "grad_norm": 1.5434727668762207, | |
| "learning_rate": 0.0, | |
| "loss": 0.4318, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5449591280653951, | |
| "eval_loss": 0.426371693611145, | |
| "eval_runtime": 39.1916, | |
| "eval_samples_per_second": 15.769, | |
| "eval_steps_per_second": 1.99, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |