| { | |
| "best_metric": 2.105609655380249, | |
| "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": 1.0071040391921997, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007037297677691766, | |
| "eval_loss": 3.9164936542510986, | |
| "eval_runtime": 37.1771, | |
| "eval_samples_per_second": 64.395, | |
| "eval_steps_per_second": 8.069, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014074595355383533, | |
| "grad_norm": 3.563297986984253, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9462, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00211118930330753, | |
| "grad_norm": 2.609055995941162, | |
| "learning_rate": 6e-05, | |
| "loss": 3.5791, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0028149190710767065, | |
| "grad_norm": 2.7890801429748535, | |
| "learning_rate": 8e-05, | |
| "loss": 3.6066, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003518648838845883, | |
| "grad_norm": 2.17081618309021, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2756, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00422237860661506, | |
| "grad_norm": 2.0635955333709717, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 3.3667, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0049261083743842365, | |
| "grad_norm": 1.2714797258377075, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.4584, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005629838142153413, | |
| "grad_norm": 1.267520785331726, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 3.2128, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0063335679099225895, | |
| "grad_norm": 1.241979956626892, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.0694, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007037297677691766, | |
| "grad_norm": 0.9922565221786499, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.9214, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007741027445460943, | |
| "grad_norm": 1.0429308414459229, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.9467, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00844475721323012, | |
| "grad_norm": 0.8632774353027344, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.6701, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009148486980999296, | |
| "grad_norm": 0.7449060678482056, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.7808, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 0.8643702268600464, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.2636, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01055594651653765, | |
| "grad_norm": 1.01483154296875, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.5699, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011259676284306826, | |
| "grad_norm": 0.8728858828544617, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.5537, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011963406052076003, | |
| "grad_norm": 0.7444866895675659, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.662, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012667135819845179, | |
| "grad_norm": 0.8878504633903503, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.3478, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013370865587614356, | |
| "grad_norm": 0.8550518751144409, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.31, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014074595355383532, | |
| "grad_norm": 0.7037220001220703, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3616, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014778325123152709, | |
| "grad_norm": 0.8830162882804871, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.3858, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015482054890921885, | |
| "grad_norm": 1.61112642288208, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.2735, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01618578465869106, | |
| "grad_norm": 0.8486283421516418, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.1605, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01688951442646024, | |
| "grad_norm": 0.7341535687446594, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.2015, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017593244194229415, | |
| "grad_norm": 0.8018566370010376, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.2605, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017593244194229415, | |
| "eval_loss": 2.200383424758911, | |
| "eval_runtime": 37.7147, | |
| "eval_samples_per_second": 63.476, | |
| "eval_steps_per_second": 7.954, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018296973961998593, | |
| "grad_norm": 0.8232203722000122, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.1872, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.019000703729767768, | |
| "grad_norm": 0.6864263415336609, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.1791, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 0.7136126160621643, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.2234, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 1.1825441122055054, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.4192, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0211118930330753, | |
| "grad_norm": 0.7965120077133179, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.0211, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021815622800844477, | |
| "grad_norm": 0.6437466740608215, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.0912, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.022519352568613652, | |
| "grad_norm": 0.7274101376533508, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.1358, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02322308233638283, | |
| "grad_norm": 0.7753286361694336, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.2257, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023926812104152005, | |
| "grad_norm": 0.6189289689064026, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 2.0214, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.024630541871921183, | |
| "grad_norm": 0.909999430179596, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4424, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.025334271639690358, | |
| "grad_norm": 0.7896960377693176, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.0872, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.026038001407459536, | |
| "grad_norm": 0.6156556010246277, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.9546, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02674173117522871, | |
| "grad_norm": 0.6940821409225464, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.8075, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02744546094299789, | |
| "grad_norm": 0.6875196695327759, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8502, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.028149190710767064, | |
| "grad_norm": 0.9812740087509155, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.9774, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028852920478536243, | |
| "grad_norm": 0.8174262642860413, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.7649, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": 0.8707631826400757, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7106, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.030260380014074596, | |
| "grad_norm": 1.0497000217437744, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.75, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03096410978184377, | |
| "grad_norm": 0.9923905730247498, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.8375, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03166783954961295, | |
| "grad_norm": 1.0750401020050049, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.7751, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03237156931738212, | |
| "grad_norm": 1.0641475915908813, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.0445, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.033075299085151305, | |
| "grad_norm": 1.1732888221740723, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.0729, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03377902885292048, | |
| "grad_norm": 1.6676044464111328, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.2338, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 2.1533820629119873, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.0833, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03518648838845883, | |
| "grad_norm": 3.547422170639038, | |
| "learning_rate": 0.0, | |
| "loss": 2.8245, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03518648838845883, | |
| "eval_loss": 2.105609655380249, | |
| "eval_runtime": 37.6568, | |
| "eval_samples_per_second": 63.574, | |
| "eval_steps_per_second": 7.967, | |
| "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 | |
| } | |