| { | |
| "best_metric": 0.7168570756912231, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-300", | |
| "epoch": 0.6511123168746609, | |
| "eval_steps": 150, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002170374389582203, | |
| "eval_loss": 3.8393607139587402, | |
| "eval_runtime": 52.8023, | |
| "eval_samples_per_second": 14.715, | |
| "eval_steps_per_second": 1.856, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02170374389582203, | |
| "grad_norm": 26.712209701538086, | |
| "learning_rate": 6e-06, | |
| "loss": 10.3362, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04340748779164406, | |
| "grad_norm": 38.7980842590332, | |
| "learning_rate": 1.2e-05, | |
| "loss": 12.0151, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06511123168746609, | |
| "grad_norm": 29.304401397705078, | |
| "learning_rate": 1.8e-05, | |
| "loss": 11.2638, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08681497558328811, | |
| "grad_norm": 39.74540710449219, | |
| "learning_rate": 2.4e-05, | |
| "loss": 9.229, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10851871947911014, | |
| "grad_norm": 65.20191955566406, | |
| "learning_rate": 3e-05, | |
| "loss": 6.7067, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13022246337493218, | |
| "grad_norm": 15.829483985900879, | |
| "learning_rate": 2.9996479470277262e-05, | |
| "loss": 5.6606, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1519262072707542, | |
| "grad_norm": 16.72377586364746, | |
| "learning_rate": 2.9985919533659653e-05, | |
| "loss": 4.3456, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17362995116657623, | |
| "grad_norm": 17.048402786254883, | |
| "learning_rate": 2.9968325147023267e-05, | |
| "loss": 3.5431, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19533369506239825, | |
| "grad_norm": 23.174785614013672, | |
| "learning_rate": 2.994370456924292e-05, | |
| "loss": 3.5592, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21703743895822028, | |
| "grad_norm": 63.94609832763672, | |
| "learning_rate": 2.9912069357315394e-05, | |
| "loss": 3.5889, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23874118285404233, | |
| "grad_norm": 17.54082679748535, | |
| "learning_rate": 2.9873434360934543e-05, | |
| "loss": 4.0375, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.26044492674986436, | |
| "grad_norm": 13.922243118286133, | |
| "learning_rate": 2.9827817715520775e-05, | |
| "loss": 3.5151, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2821486706456864, | |
| "grad_norm": 18.978328704833984, | |
| "learning_rate": 2.977524083370823e-05, | |
| "loss": 3.1774, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3038524145415084, | |
| "grad_norm": 19.49057388305664, | |
| "learning_rate": 2.9715728395293587e-05, | |
| "loss": 3.2158, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.32555615843733043, | |
| "grad_norm": 36.420654296875, | |
| "learning_rate": 2.96493083356513e-05, | |
| "loss": 3.1129, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.32555615843733043, | |
| "eval_loss": 0.803920328617096, | |
| "eval_runtime": 53.8173, | |
| "eval_samples_per_second": 14.438, | |
| "eval_steps_per_second": 1.821, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.34725990233315246, | |
| "grad_norm": 15.815438270568848, | |
| "learning_rate": 2.9576011832620583e-05, | |
| "loss": 3.6763, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3689636462289745, | |
| "grad_norm": 17.322349548339844, | |
| "learning_rate": 2.9495873291870436e-05, | |
| "loss": 3.2852, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3906673901247965, | |
| "grad_norm": 16.479698181152344, | |
| "learning_rate": 2.940893033074948e-05, | |
| "loss": 3.0177, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 20.874675750732422, | |
| "learning_rate": 2.9315223760628224e-05, | |
| "loss": 2.676, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.43407487791644056, | |
| "grad_norm": 29.774669647216797, | |
| "learning_rate": 2.9214797567742036e-05, | |
| "loss": 3.227, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45577862181226264, | |
| "grad_norm": 14.984698295593262, | |
| "learning_rate": 2.9107698892543862e-05, | |
| "loss": 3.4, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.47748236570808467, | |
| "grad_norm": 18.93448829650879, | |
| "learning_rate": 2.8993978007576263e-05, | |
| "loss": 2.9846, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4991861096039067, | |
| "grad_norm": 17.96265411376953, | |
| "learning_rate": 2.8873688293873336e-05, | |
| "loss": 3.0037, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5208898534997287, | |
| "grad_norm": 23.578723907470703, | |
| "learning_rate": 2.874688621590339e-05, | |
| "loss": 2.7363, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5425935973955507, | |
| "grad_norm": 39.76424026489258, | |
| "learning_rate": 2.861363129506436e-05, | |
| "loss": 3.1817, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5642973412913728, | |
| "grad_norm": 20.42775535583496, | |
| "learning_rate": 2.847398608174417e-05, | |
| "loss": 3.2541, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5860010851871947, | |
| "grad_norm": 16.566482543945312, | |
| "learning_rate": 2.832801612595937e-05, | |
| "loss": 2.8651, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6077048290830168, | |
| "grad_norm": 16.73906707763672, | |
| "learning_rate": 2.8175789946585697e-05, | |
| "loss": 2.8237, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6294085729788389, | |
| "grad_norm": 23.292736053466797, | |
| "learning_rate": 2.801737899919502e-05, | |
| "loss": 3.0393, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6511123168746609, | |
| "grad_norm": 38.29425048828125, | |
| "learning_rate": 2.7852857642513838e-05, | |
| "loss": 2.7109, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6511123168746609, | |
| "eval_loss": 0.7168570756912231, | |
| "eval_runtime": 53.8613, | |
| "eval_samples_per_second": 14.426, | |
| "eval_steps_per_second": 1.819, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 4.206407486275584e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |