| { | |
| "best_metric": 1.2082175016403198, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.15114301908180616, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006045720763272247, | |
| "grad_norm": 0.08884909003973007, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006045720763272247, | |
| "eval_loss": 1.2961229085922241, | |
| "eval_runtime": 4.1661, | |
| "eval_samples_per_second": 12.002, | |
| "eval_steps_per_second": 3.12, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012091441526544493, | |
| "grad_norm": 0.10288404673337936, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1438, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01813716228981674, | |
| "grad_norm": 0.10552998632192612, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 1.1514, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024182883053088987, | |
| "grad_norm": 0.09851573407649994, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 1.133, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.030228603816361232, | |
| "grad_norm": 0.09214343130588531, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 1.0755, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03627432457963348, | |
| "grad_norm": 0.13269194960594177, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 1.1901, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.042320045342905725, | |
| "grad_norm": 0.12675197422504425, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 1.1703, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.048365766106177974, | |
| "grad_norm": 0.10226869583129883, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 1.1973, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.054411486869450215, | |
| "grad_norm": 0.09047923237085342, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 1.1111, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.060457207632722464, | |
| "grad_norm": 0.09085343778133392, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 1.101, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06650292839599471, | |
| "grad_norm": 0.08678877353668213, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 1.1121, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07254864915926695, | |
| "grad_norm": 0.08263799548149109, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 1.1357, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07859436992253921, | |
| "grad_norm": 0.0801074281334877, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 1.0712, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08464009068581145, | |
| "grad_norm": 0.07154852896928787, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 1.0904, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09068581144908369, | |
| "grad_norm": 0.06537115573883057, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 1.0641, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09673153221235595, | |
| "grad_norm": 0.06021496281027794, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 1.0498, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10277725297562819, | |
| "grad_norm": 0.05982998386025429, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 1.156, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10882297373890043, | |
| "grad_norm": 0.06260080635547638, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 1.1428, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11486869450217269, | |
| "grad_norm": 0.06050794571638107, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 1.0999, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12091441526544493, | |
| "grad_norm": 0.06284893304109573, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 1.1309, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12696013602871717, | |
| "grad_norm": 0.06542612612247467, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 1.1075, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13300585679198942, | |
| "grad_norm": 0.07112954556941986, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 1.1579, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13905157755526168, | |
| "grad_norm": 0.06897735595703125, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 1.0505, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1450972983185339, | |
| "grad_norm": 0.07904097437858582, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 1.17, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15114301908180616, | |
| "grad_norm": 0.10859081894159317, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1309, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15114301908180616, | |
| "eval_loss": 1.2082175016403198, | |
| "eval_runtime": 4.202, | |
| "eval_samples_per_second": 11.899, | |
| "eval_steps_per_second": 3.094, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": 3.211340840991457e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |