| { | |
| "best_metric": 2.1071135997772217, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03518648838845883, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007037297677691766, | |
| "grad_norm": 1.000688076019287, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007037297677691766, | |
| "eval_loss": 3.9164936542510986, | |
| "eval_runtime": 37.194, | |
| "eval_samples_per_second": 64.365, | |
| "eval_steps_per_second": 8.066, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014074595355383533, | |
| "grad_norm": 3.5250110626220703, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9462, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00211118930330753, | |
| "grad_norm": 2.5911612510681152, | |
| "learning_rate": 6e-05, | |
| "loss": 3.5786, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0028149190710767065, | |
| "grad_norm": 2.7744967937469482, | |
| "learning_rate": 8e-05, | |
| "loss": 3.6077, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003518648838845883, | |
| "grad_norm": 2.1832773685455322, | |
| "learning_rate": 0.0001, | |
| "loss": 3.277, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00422237860661506, | |
| "grad_norm": 2.0739316940307617, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 3.3723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0049261083743842365, | |
| "grad_norm": 1.2714459896087646, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.4562, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005629838142153413, | |
| "grad_norm": 1.2591367959976196, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 3.2138, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0063335679099225895, | |
| "grad_norm": 1.2095932960510254, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.078, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007037297677691766, | |
| "grad_norm": 0.9941366314888, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.9243, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007741027445460943, | |
| "grad_norm": 1.0468645095825195, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.9552, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00844475721323012, | |
| "grad_norm": 0.853911817073822, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.671, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009148486980999296, | |
| "grad_norm": 0.7470048069953918, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.7815, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 0.8711528778076172, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.2661, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01055594651653765, | |
| "grad_norm": 1.0046913623809814, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.5723, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011259676284306826, | |
| "grad_norm": 0.8753963708877563, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.5533, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011963406052076003, | |
| "grad_norm": 0.7471569776535034, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.6629, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012667135819845179, | |
| "grad_norm": 0.922391414642334, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.3434, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013370865587614356, | |
| "grad_norm": 0.8568523526191711, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.3051, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014074595355383532, | |
| "grad_norm": 0.716374933719635, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3548, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014778325123152709, | |
| "grad_norm": 0.8990435600280762, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.3813, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015482054890921885, | |
| "grad_norm": 1.5527658462524414, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.2674, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01618578465869106, | |
| "grad_norm": 0.8330752849578857, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.156, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01688951442646024, | |
| "grad_norm": 0.7202480435371399, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.1928, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017593244194229415, | |
| "grad_norm": 0.7861363291740417, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.2604, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017593244194229415, | |
| "eval_loss": 2.1998445987701416, | |
| "eval_runtime": 37.6878, | |
| "eval_samples_per_second": 63.522, | |
| "eval_steps_per_second": 7.96, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018296973961998593, | |
| "grad_norm": 0.8111019134521484, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.1868, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.019000703729767768, | |
| "grad_norm": 0.6819187998771667, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.1773, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 0.7138143181800842, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.2268, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 1.2253530025482178, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.4231, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0211118930330753, | |
| "grad_norm": 0.7903726100921631, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.0236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021815622800844477, | |
| "grad_norm": 0.6488191485404968, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.0918, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.022519352568613652, | |
| "grad_norm": 0.7203357219696045, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.1305, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02322308233638283, | |
| "grad_norm": 0.7722885608673096, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.2269, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023926812104152005, | |
| "grad_norm": 0.6173502802848816, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 2.0185, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.024630541871921183, | |
| "grad_norm": 0.8969466090202332, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4426, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.025334271639690358, | |
| "grad_norm": 0.7939102053642273, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.0875, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.026038001407459536, | |
| "grad_norm": 0.6162180304527283, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.9491, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02674173117522871, | |
| "grad_norm": 0.6837140321731567, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.8046, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02744546094299789, | |
| "grad_norm": 0.6838858127593994, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8489, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.028149190710767064, | |
| "grad_norm": 0.9752803444862366, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.9773, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028852920478536243, | |
| "grad_norm": 0.8087269067764282, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.7675, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": 0.8337047696113586, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7071, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.030260380014074596, | |
| "grad_norm": 1.047497272491455, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7507, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03096410978184377, | |
| "grad_norm": 1.00037682056427, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.84, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03166783954961295, | |
| "grad_norm": 1.0732063055038452, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.7851, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03237156931738212, | |
| "grad_norm": 1.073845386505127, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.0417, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.033075299085151305, | |
| "grad_norm": 1.1644452810287476, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.0671, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03377902885292048, | |
| "grad_norm": 1.675778865814209, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.2341, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 2.151191234588623, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.0903, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03518648838845883, | |
| "grad_norm": 3.5507590770721436, | |
| "learning_rate": 0.0, | |
| "loss": 2.834, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03518648838845883, | |
| "eval_loss": 2.1071135997772217, | |
| "eval_runtime": 37.6494, | |
| "eval_samples_per_second": 63.587, | |
| "eval_steps_per_second": 7.968, | |
| "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": 5, | |
| "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": 8520778270113792.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |