| { | |
| "best_metric": 0.7943152189254761, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.15521924718665114, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006208769887466045, | |
| "grad_norm": 20.6494083404541, | |
| "learning_rate": 5e-05, | |
| "loss": 10.9171, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006208769887466045, | |
| "eval_loss": 1.11298406124115, | |
| "eval_runtime": 30.4417, | |
| "eval_samples_per_second": 35.642, | |
| "eval_steps_per_second": 4.468, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01241753977493209, | |
| "grad_norm": 25.058574676513672, | |
| "learning_rate": 0.0001, | |
| "loss": 13.1041, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018626309662398137, | |
| "grad_norm": 13.562352180480957, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.7258, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02483507954986418, | |
| "grad_norm": 18.760438919067383, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 14.4185, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03104384943733023, | |
| "grad_norm": 16.084901809692383, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 14.4119, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.037252619324796274, | |
| "grad_norm": 11.85362720489502, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 13.9562, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04346138921226232, | |
| "grad_norm": 12.274022102355957, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 14.6683, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04967015909972836, | |
| "grad_norm": 13.757440567016602, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 14.6355, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05587892898719441, | |
| "grad_norm": 14.682954788208008, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 14.5799, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06208769887466046, | |
| "grad_norm": 13.583301544189453, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 14.1422, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0682964687621265, | |
| "grad_norm": 14.027863502502441, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 14.2622, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07450523864959255, | |
| "grad_norm": 14.751089096069336, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 15.3644, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0807140085370586, | |
| "grad_norm": 17.941997528076172, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 13.444, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08692277842452464, | |
| "grad_norm": 8.306686401367188, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.0147, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09313154831199069, | |
| "grad_norm": 8.1074800491333, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.5896, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09934031819945673, | |
| "grad_norm": 7.5470051765441895, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 12.5157, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10554908808692277, | |
| "grad_norm": 7.528012275695801, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 12.7302, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11175785797438882, | |
| "grad_norm": 7.592319488525391, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 12.8235, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11796662786185487, | |
| "grad_norm": 7.987727165222168, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 13.2507, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12417539774932092, | |
| "grad_norm": 8.953367233276367, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 13.5855, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13038416763678695, | |
| "grad_norm": 10.761629104614258, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 13.8462, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.136592937524253, | |
| "grad_norm": 10.666893005371094, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 13.2487, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14280170741171905, | |
| "grad_norm": 12.03550910949707, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 13.6735, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1490104772991851, | |
| "grad_norm": 12.296943664550781, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 14.1311, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15521924718665114, | |
| "grad_norm": 17.093778610229492, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 14.8873, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15521924718665114, | |
| "eval_loss": 0.7943152189254761, | |
| "eval_runtime": 28.9408, | |
| "eval_samples_per_second": 37.49, | |
| "eval_steps_per_second": 4.699, | |
| "step": 25 | |
| } | |
| ], | |
| "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": 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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8449238450962432e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |