| { | |
| "best_metric": 0.1712397187948227, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.13983569306065374, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005593427722426149, | |
| "grad_norm": 0.671412467956543, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8558, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005593427722426149, | |
| "eval_loss": 0.7013859748840332, | |
| "eval_runtime": 2.0591, | |
| "eval_samples_per_second": 24.283, | |
| "eval_steps_per_second": 6.314, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011186855444852298, | |
| "grad_norm": 0.6349863409996033, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5661, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016780283167278448, | |
| "grad_norm": 0.7139654755592346, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.5692, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022373710889704596, | |
| "grad_norm": 0.612759530544281, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.4843, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027967138612130748, | |
| "grad_norm": 0.6861884593963623, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.4173, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.033560566334556896, | |
| "grad_norm": 0.719796359539032, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.3673, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03915399405698305, | |
| "grad_norm": 0.5057691931724548, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.3184, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04474742177940919, | |
| "grad_norm": 0.5362572073936462, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.2838, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.050340849501835344, | |
| "grad_norm": 0.5265982151031494, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.2496, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.055934277224261496, | |
| "grad_norm": 0.45920541882514954, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.2228, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06152770494668764, | |
| "grad_norm": 0.4604686200618744, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.1959, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06712113266911379, | |
| "grad_norm": 0.6348649859428406, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.1546, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07271456039153994, | |
| "grad_norm": 0.7286633849143982, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.5576, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0783079881139661, | |
| "grad_norm": 0.49175405502319336, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.2519, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08390141583639224, | |
| "grad_norm": 0.4149652123451233, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.2311, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08949484355881838, | |
| "grad_norm": 0.35654476284980774, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.2064, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09508827128124454, | |
| "grad_norm": 0.32645905017852783, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.2058, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10068169900367069, | |
| "grad_norm": 0.2955136001110077, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.1923, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10627512672609683, | |
| "grad_norm": 0.3166772127151489, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.1974, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11186855444852299, | |
| "grad_norm": 0.29928117990493774, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.1687, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11746198217094914, | |
| "grad_norm": 0.33202478289604187, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.1511, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12305540989337528, | |
| "grad_norm": 0.3457794785499573, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.1565, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12864883761580143, | |
| "grad_norm": 0.2978086471557617, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.1458, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13424226533822758, | |
| "grad_norm": 0.3322213292121887, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.1322, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13983569306065374, | |
| "grad_norm": 0.6888604760169983, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1034, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13983569306065374, | |
| "eval_loss": 0.1712397187948227, | |
| "eval_runtime": 2.1024, | |
| "eval_samples_per_second": 23.782, | |
| "eval_steps_per_second": 6.183, | |
| "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": 1.3366130478625587e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |