{ "best_metric": 10.360739707946777, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.8314350797266514, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03644646924829157, "grad_norm": 0.15206216275691986, "learning_rate": 5e-05, "loss": 10.3796, "step": 1 }, { "epoch": 0.03644646924829157, "eval_loss": 10.380887031555176, "eval_runtime": 0.1809, "eval_samples_per_second": 1022.859, "eval_steps_per_second": 132.695, "step": 1 }, { "epoch": 0.07289293849658314, "grad_norm": 0.1610165387392044, "learning_rate": 0.0001, "loss": 10.379, "step": 2 }, { "epoch": 0.10933940774487472, "grad_norm": 0.18909887969493866, "learning_rate": 9.989294616193017e-05, "loss": 10.3808, "step": 3 }, { "epoch": 0.14578587699316628, "grad_norm": 0.2205168455839157, "learning_rate": 9.957224306869053e-05, "loss": 10.3768, "step": 4 }, { "epoch": 0.18223234624145787, "grad_norm": 0.2703295648097992, "learning_rate": 9.903926402016153e-05, "loss": 10.3755, "step": 5 }, { "epoch": 0.21867881548974943, "grad_norm": 0.33437639474868774, "learning_rate": 9.829629131445342e-05, "loss": 10.3741, "step": 6 }, { "epoch": 0.255125284738041, "grad_norm": 0.2190495729446411, "learning_rate": 9.73465064747553e-05, "loss": 10.3759, "step": 7 }, { "epoch": 0.29157175398633256, "grad_norm": 0.15123555064201355, "learning_rate": 9.619397662556435e-05, "loss": 10.3765, "step": 8 }, { "epoch": 0.32801822323462415, "grad_norm": 0.1677154153585434, "learning_rate": 9.484363707663442e-05, "loss": 10.3756, "step": 9 }, { "epoch": 0.36446469248291574, "grad_norm": 0.18042495846748352, "learning_rate": 9.330127018922194e-05, "loss": 10.3742, "step": 10 }, { "epoch": 0.4009111617312073, "grad_norm": 0.22101934254169464, "learning_rate": 9.157348061512727e-05, "loss": 10.3725, "step": 11 }, { "epoch": 0.43735763097949887, "grad_norm": 0.2781515419483185, "learning_rate": 8.966766701456177e-05, "loss": 10.3691, "step": 12 }, { "epoch": 0.47380410022779046, "grad_norm": 0.33735859394073486, "learning_rate": 8.759199037394887e-05, "loss": 10.3659, "step": 13 }, { "epoch": 0.510250569476082, "grad_norm": 0.17510421574115753, "learning_rate": 8.535533905932738e-05, "loss": 10.3727, "step": 14 }, { "epoch": 0.5466970387243736, "grad_norm": 0.1429934948682785, "learning_rate": 8.296729075500344e-05, "loss": 10.3725, "step": 15 }, { "epoch": 0.5831435079726651, "grad_norm": 0.15244732797145844, "learning_rate": 8.043807145043604e-05, "loss": 10.3719, "step": 16 }, { "epoch": 0.6195899772209568, "grad_norm": 0.17936758697032928, "learning_rate": 7.777851165098012e-05, "loss": 10.3695, "step": 17 }, { "epoch": 0.6560364464692483, "grad_norm": 0.22151167690753937, "learning_rate": 7.500000000000001e-05, "loss": 10.3661, "step": 18 }, { "epoch": 0.6924829157175398, "grad_norm": 0.26017025113105774, "learning_rate": 7.211443451095007e-05, "loss": 10.3616, "step": 19 }, { "epoch": 0.7289293849658315, "grad_norm": 0.3470045328140259, "learning_rate": 6.91341716182545e-05, "loss": 10.355, "step": 20 }, { "epoch": 0.765375854214123, "grad_norm": 0.14400780200958252, "learning_rate": 6.607197326515808e-05, "loss": 10.37, "step": 21 }, { "epoch": 0.8018223234624146, "grad_norm": 0.15392181277275085, "learning_rate": 6.294095225512603e-05, "loss": 10.3677, "step": 22 }, { "epoch": 0.8382687927107062, "grad_norm": 0.16887319087982178, "learning_rate": 5.9754516100806423e-05, "loss": 10.3667, "step": 23 }, { "epoch": 0.8747152619589977, "grad_norm": 0.1790841966867447, "learning_rate": 5.6526309611002594e-05, "loss": 10.3659, "step": 24 }, { "epoch": 0.9111617312072893, "grad_norm": 0.2096974402666092, "learning_rate": 5.327015646150716e-05, "loss": 10.3644, "step": 25 }, { "epoch": 0.9111617312072893, "eval_loss": 10.36435317993164, "eval_runtime": 0.1772, "eval_samples_per_second": 1044.023, "eval_steps_per_second": 135.441, "step": 25 }, { "epoch": 0.9476082004555809, "grad_norm": 0.25196874141693115, "learning_rate": 5e-05, "loss": 10.3584, "step": 26 }, { "epoch": 0.9840546697038725, "grad_norm": 0.3380187153816223, "learning_rate": 4.6729843538492847e-05, "loss": 10.353, "step": 27 }, { "epoch": 1.029612756264237, "grad_norm": 0.30297839641571045, "learning_rate": 4.347369038899744e-05, "loss": 19.0658, "step": 28 }, { "epoch": 1.0660592255125285, "grad_norm": 0.14603254199028015, "learning_rate": 4.0245483899193595e-05, "loss": 10.264, "step": 29 }, { "epoch": 1.10250569476082, "grad_norm": 0.15991508960723877, "learning_rate": 3.705904774487396e-05, "loss": 10.3639, "step": 30 }, { "epoch": 1.1389521640091116, "grad_norm": 0.19101238250732422, "learning_rate": 3.392802673484193e-05, "loss": 10.3875, "step": 31 }, { "epoch": 1.1753986332574031, "grad_norm": 0.20625823736190796, "learning_rate": 3.086582838174551e-05, "loss": 10.3873, "step": 32 }, { "epoch": 1.2118451025056949, "grad_norm": 0.24794551730155945, "learning_rate": 2.7885565489049946e-05, "loss": 10.3639, "step": 33 }, { "epoch": 1.2482915717539864, "grad_norm": 0.15549078583717346, "learning_rate": 2.500000000000001e-05, "loss": 6.8354, "step": 34 }, { "epoch": 1.284738041002278, "grad_norm": 0.19828249514102936, "learning_rate": 2.2221488349019903e-05, "loss": 13.8538, "step": 35 }, { "epoch": 1.3211845102505695, "grad_norm": 0.15714150667190552, "learning_rate": 1.9561928549563968e-05, "loss": 10.345, "step": 36 }, { "epoch": 1.357630979498861, "grad_norm": 0.1823427975177765, "learning_rate": 1.703270924499656e-05, "loss": 10.4047, "step": 37 }, { "epoch": 1.3940774487471526, "grad_norm": 0.1794886589050293, "learning_rate": 1.4644660940672627e-05, "loss": 10.395, "step": 38 }, { "epoch": 1.430523917995444, "grad_norm": 0.22187049686908722, "learning_rate": 1.2408009626051137e-05, "loss": 10.3162, "step": 39 }, { "epoch": 1.4669703872437356, "grad_norm": 0.2668076157569885, "learning_rate": 1.0332332985438248e-05, "loss": 10.4429, "step": 40 }, { "epoch": 1.5034168564920274, "grad_norm": 0.15169256925582886, "learning_rate": 8.426519384872733e-06, "loss": 8.8337, "step": 41 }, { "epoch": 1.539863325740319, "grad_norm": 0.15748904645442963, "learning_rate": 6.698729810778065e-06, "loss": 11.7664, "step": 42 }, { "epoch": 1.5763097949886105, "grad_norm": 0.15284818410873413, "learning_rate": 5.156362923365588e-06, "loss": 10.4053, "step": 43 }, { "epoch": 1.6127562642369022, "grad_norm": 0.1644909381866455, "learning_rate": 3.8060233744356633e-06, "loss": 10.3361, "step": 44 }, { "epoch": 1.6492027334851938, "grad_norm": 0.18126553297042847, "learning_rate": 2.653493525244721e-06, "loss": 10.3664, "step": 45 }, { "epoch": 1.6856492027334853, "grad_norm": 0.23220454156398773, "learning_rate": 1.70370868554659e-06, "loss": 10.3932, "step": 46 }, { "epoch": 1.7220956719817768, "grad_norm": 0.2918383777141571, "learning_rate": 9.607359798384785e-07, "loss": 10.4925, "step": 47 }, { "epoch": 1.7585421412300684, "grad_norm": 0.18016327917575836, "learning_rate": 4.277569313094809e-07, "loss": 9.7463, "step": 48 }, { "epoch": 1.79498861047836, "grad_norm": 0.166108638048172, "learning_rate": 1.0705383806982606e-07, "loss": 10.7557, "step": 49 }, { "epoch": 1.8314350797266514, "grad_norm": 0.16405977308750153, "learning_rate": 0.0, "loss": 10.3726, "step": 50 }, { "epoch": 1.8314350797266514, "eval_loss": 10.360739707946777, "eval_runtime": 0.1753, "eval_samples_per_second": 1055.129, "eval_steps_per_second": 136.882, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 42768059596800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }