| { | |
| "best_metric": 0.494415283203125, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2724795640326976, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010899182561307902, | |
| "grad_norm": 48.11774826049805, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010899182561307902, | |
| "eval_loss": 11.284085273742676, | |
| "eval_runtime": 66.2727, | |
| "eval_samples_per_second": 9.325, | |
| "eval_steps_per_second": 1.177, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021798365122615803, | |
| "grad_norm": 51.14781951904297, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0866, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0326975476839237, | |
| "grad_norm": 31.01067543029785, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.8468, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043596730245231606, | |
| "grad_norm": 10.979269027709961, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0698, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05449591280653951, | |
| "grad_norm": 7.363651275634766, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.949, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0653950953678474, | |
| "grad_norm": 3.0180106163024902, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5933, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07629427792915532, | |
| "grad_norm": 4.888218879699707, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.5683, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08719346049046321, | |
| "grad_norm": 2.343219041824341, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5197, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09809264305177112, | |
| "grad_norm": 1.9261095523834229, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5082, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10899182561307902, | |
| "grad_norm": 1.4614423513412476, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4522, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11989100817438691, | |
| "grad_norm": 5.520626544952393, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5888, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1307901907356948, | |
| "grad_norm": 3.687649726867676, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5874, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14168937329700274, | |
| "grad_norm": 2.2551167011260986, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5814, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15258855585831063, | |
| "grad_norm": 1.3158828020095825, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5455, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16348773841961853, | |
| "grad_norm": 0.9369361400604248, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5013, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17438692098092642, | |
| "grad_norm": 2.9609029293060303, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.508, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18528610354223432, | |
| "grad_norm": 2.630481719970703, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.479, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19618528610354224, | |
| "grad_norm": 1.4421982765197754, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4377, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20708446866485014, | |
| "grad_norm": 1.9808775186538696, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4395, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21798365122615804, | |
| "grad_norm": 2.5307984352111816, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4381, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22888283378746593, | |
| "grad_norm": 1.2831040620803833, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4428, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23978201634877383, | |
| "grad_norm": 0.9908807277679443, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4264, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2506811989100817, | |
| "grad_norm": 1.501499056816101, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3689, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2615803814713896, | |
| "grad_norm": 1.7701606750488281, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4138, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "grad_norm": 2.01239275932312, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.511, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "eval_loss": 0.494415283203125, | |
| "eval_runtime": 32.277, | |
| "eval_samples_per_second": 19.147, | |
| "eval_steps_per_second": 2.417, | |
| "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": 3.315690861756416e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |