| { | |
| "best_metric": 0.937868058681488, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1890359168241966, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003780718336483932, | |
| "grad_norm": 25.868711471557617, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007561436672967864, | |
| "grad_norm": 26.996562957763672, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1712, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011342155009451797, | |
| "grad_norm": 26.536226272583008, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1189, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015122873345935728, | |
| "grad_norm": 22.53629493713379, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0266, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01890359168241966, | |
| "grad_norm": 21.505897521972656, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022684310018903593, | |
| "grad_norm": 14.928448677062988, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0265, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.026465028355387523, | |
| "grad_norm": 14.477608680725098, | |
| "learning_rate": 7e-05, | |
| "loss": 0.9681, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.030245746691871456, | |
| "grad_norm": 15.048117637634277, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9996, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.034026465028355386, | |
| "grad_norm": 12.123842239379883, | |
| "learning_rate": 9e-05, | |
| "loss": 0.9432, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03780718336483932, | |
| "grad_norm": 14.511091232299805, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9389, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04158790170132325, | |
| "grad_norm": 13.797380447387695, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.0154, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.045368620037807186, | |
| "grad_norm": 14.586050033569336, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.9381, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04914933837429111, | |
| "grad_norm": 13.497241973876953, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.9256, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.052930056710775046, | |
| "grad_norm": 14.387834548950195, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.8607, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05671077504725898, | |
| "grad_norm": 13.219511032104492, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.8533, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06049149338374291, | |
| "grad_norm": 14.26727294921875, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.9375, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06427221172022685, | |
| "grad_norm": 11.609099388122559, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.9001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06805293005671077, | |
| "grad_norm": 13.114840507507324, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.933, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07183364839319471, | |
| "grad_norm": 14.351373672485352, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.9689, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07561436672967864, | |
| "grad_norm": 12.573498725891113, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.8473, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07939508506616257, | |
| "grad_norm": 11.286185264587402, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.764, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0831758034026465, | |
| "grad_norm": 12.673500061035156, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.8825, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 11.740640640258789, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.9075, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09073724007561437, | |
| "grad_norm": 11.874197959899902, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.7685, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0945179584120983, | |
| "grad_norm": 11.308283805847168, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.8379, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09829867674858223, | |
| "grad_norm": 12.97791576385498, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.8118, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10207939508506617, | |
| "grad_norm": 12.41085147857666, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.8996, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10586011342155009, | |
| "grad_norm": 10.894973754882812, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.8036, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10964083175803403, | |
| "grad_norm": 22.103853225708008, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.9205, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11342155009451796, | |
| "grad_norm": 11.814549446105957, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.8935, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11720226843100189, | |
| "grad_norm": 12.61363410949707, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.9126, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12098298676748583, | |
| "grad_norm": 12.015908241271973, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.8745, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12476370510396975, | |
| "grad_norm": 11.367657661437988, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.8188, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1285444234404537, | |
| "grad_norm": 12.085219383239746, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.8813, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1323251417769376, | |
| "grad_norm": 10.321392059326172, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.8272, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13610586011342155, | |
| "grad_norm": 10.407423973083496, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.8204, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.13988657844990549, | |
| "grad_norm": 13.754597663879395, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.9912, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14366729678638943, | |
| "grad_norm": 12.137901306152344, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.8117, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14744801512287334, | |
| "grad_norm": 12.281770706176758, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.9461, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15122873345935728, | |
| "grad_norm": 11.265958786010742, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.8125, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15500945179584122, | |
| "grad_norm": 12.097908973693848, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.8829, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15879017013232513, | |
| "grad_norm": 11.462668418884277, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.8174, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16257088846880907, | |
| "grad_norm": 10.441878318786621, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.7266, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.166351606805293, | |
| "grad_norm": 11.729705810546875, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.8822, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17013232514177692, | |
| "grad_norm": 10.593080520629883, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.8647, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 12.002582550048828, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.7542, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1776937618147448, | |
| "grad_norm": 13.187206268310547, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.8168, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.18147448015122875, | |
| "grad_norm": 15.53892993927002, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.9638, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.18525519848771266, | |
| "grad_norm": 20.015409469604492, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.7975, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1890359168241966, | |
| "grad_norm": 14.737130165100098, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.7617, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1890359168241966, | |
| "eval_loss": 0.937868058681488, | |
| "eval_runtime": 23.8905, | |
| "eval_samples_per_second": 18.669, | |
| "eval_steps_per_second": 4.688, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.15499809800192e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |