| { | |
| "best_metric": 1.4757866859436035, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.9327633113097551, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012436844150796735, | |
| "grad_norm": 4.334837913513184, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.2908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012436844150796735, | |
| "eval_loss": 6.697080135345459, | |
| "eval_runtime": 4.4995, | |
| "eval_samples_per_second": 11.112, | |
| "eval_steps_per_second": 2.889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02487368830159347, | |
| "grad_norm": 4.578608512878418, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.86, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03731053245239021, | |
| "grad_norm": 4.818152904510498, | |
| "learning_rate": 0.0001, | |
| "loss": 4.925, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04974737660318694, | |
| "grad_norm": 5.355129241943359, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 4.5105, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06218422075398368, | |
| "grad_norm": 5.519801616668701, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 3.597, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07462106490478042, | |
| "grad_norm": 4.105515480041504, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.9274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08705790905557714, | |
| "grad_norm": 3.8129172325134277, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 2.7116, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09949475320637388, | |
| "grad_norm": 3.111717939376831, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 2.4759, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11193159735717062, | |
| "grad_norm": 3.8541200160980225, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2602, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12436844150796736, | |
| "grad_norm": 3.1858394145965576, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 2.1403, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1368052856587641, | |
| "grad_norm": 2.9167511463165283, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 1.8919, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14924212980956084, | |
| "grad_norm": 6.798462390899658, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.6077, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16167897396035755, | |
| "grad_norm": 11.831518173217773, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 3.0053, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17411581811115429, | |
| "grad_norm": 9.798856735229492, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 2.8547, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18655266226195102, | |
| "grad_norm": 4.359902858734131, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.5411, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19898950641274776, | |
| "grad_norm": 2.2944040298461914, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 2.3035, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2114263505635445, | |
| "grad_norm": 2.36320424079895, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 2.1875, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22386319471434124, | |
| "grad_norm": 2.428184986114502, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.1433, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23630003886513798, | |
| "grad_norm": 2.2989890575408936, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 2.1427, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24873688301593472, | |
| "grad_norm": 2.1419265270233154, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 1.9281, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26117372716673143, | |
| "grad_norm": 1.9683345556259155, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.7075, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2736105713175282, | |
| "grad_norm": 1.7316274642944336, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 1.7915, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2860474154683249, | |
| "grad_norm": 1.917214035987854, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 1.6485, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2984842596191217, | |
| "grad_norm": 1.8824145793914795, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.3475, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "grad_norm": 8.887231826782227, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.772, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "eval_loss": 1.8483147621154785, | |
| "eval_runtime": 4.4758, | |
| "eval_samples_per_second": 11.171, | |
| "eval_steps_per_second": 2.905, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3233579479207151, | |
| "grad_norm": 3.4082753658294678, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 2.41, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.33579479207151186, | |
| "grad_norm": 3.109001874923706, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.3198, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.34823163622230857, | |
| "grad_norm": 2.304497718811035, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 2.0177, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.36066848037310534, | |
| "grad_norm": 1.9224731922149658, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 2.0373, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.37310532452390205, | |
| "grad_norm": 1.6497129201889038, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.807, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 1.6339839696884155, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 1.8076, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3979790128254955, | |
| "grad_norm": 1.8460805416107178, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 1.907, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4104158569762923, | |
| "grad_norm": 1.7650914192199707, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.8927, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.422852701127089, | |
| "grad_norm": 1.8454054594039917, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 1.5441, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4352895452778857, | |
| "grad_norm": 1.8942859172821045, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 1.5689, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4477263894286825, | |
| "grad_norm": 2.334362268447876, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2838, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4601632335794792, | |
| "grad_norm": 2.4197657108306885, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.9639, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.47260007773027596, | |
| "grad_norm": 1.9846646785736084, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 1.8122, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.48503692188107267, | |
| "grad_norm": 1.9487015008926392, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.0742, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.49747376603186944, | |
| "grad_norm": 2.0693061351776123, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 1.9641, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5099106101826661, | |
| "grad_norm": 1.666406273841858, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 1.7359, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5223474543334629, | |
| "grad_norm": 1.9289875030517578, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.887, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5347842984842596, | |
| "grad_norm": 1.6595007181167603, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 1.7954, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5472211426350564, | |
| "grad_norm": 1.7720122337341309, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 1.7259, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5596579867858531, | |
| "grad_norm": 1.9382787942886353, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.7288, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5720948309366498, | |
| "grad_norm": 1.5037600994110107, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 1.5281, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5845316750874465, | |
| "grad_norm": 1.6816551685333252, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 1.5025, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5969685192382433, | |
| "grad_norm": 1.8008204698562622, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3675, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6094053633890401, | |
| "grad_norm": 1.7607805728912354, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.9439, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6218422075398368, | |
| "grad_norm": 8.726191520690918, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.7328, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6218422075398368, | |
| "eval_loss": 1.5857478380203247, | |
| "eval_runtime": 4.4715, | |
| "eval_samples_per_second": 11.182, | |
| "eval_steps_per_second": 2.907, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6342790516906335, | |
| "grad_norm": 1.9586689472198486, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.9342, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6467158958414302, | |
| "grad_norm": 1.7377395629882812, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 1.9846, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.659152739992227, | |
| "grad_norm": 1.4514222145080566, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 1.6922, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6715895841430237, | |
| "grad_norm": 1.5051312446594238, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.872, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6840264282938204, | |
| "grad_norm": 1.3607957363128662, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 1.563, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6964632724446171, | |
| "grad_norm": 1.4457933902740479, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 1.5738, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.708900116595414, | |
| "grad_norm": 1.5340603590011597, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.4182, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7213369607462107, | |
| "grad_norm": 1.8126493692398071, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 1.4997, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7337738048970074, | |
| "grad_norm": 1.8174535036087036, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 1.4925, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7462106490478041, | |
| "grad_norm": 1.6950277090072632, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.3651, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7586474931986008, | |
| "grad_norm": 1.7184079885482788, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 1.258, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.7710843373493976, | |
| "grad_norm": 2.286306142807007, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 0.9343, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.7835211815001943, | |
| "grad_norm": 1.4997891187667847, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.5661, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.795958025650991, | |
| "grad_norm": 1.3938400745391846, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 1.7878, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8083948698017878, | |
| "grad_norm": 1.4616719484329224, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 1.7966, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8208317139525846, | |
| "grad_norm": 1.3521653413772583, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.7621, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.8332685581033813, | |
| "grad_norm": 1.436239242553711, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 1.4504, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.845705402254178, | |
| "grad_norm": 1.5169296264648438, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 1.5677, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8581422464049747, | |
| "grad_norm": 1.4382579326629639, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.5528, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.8705790905557714, | |
| "grad_norm": 1.535103440284729, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 1.5379, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8830159347065683, | |
| "grad_norm": 1.5666173696517944, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 1.4208, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.895452778857365, | |
| "grad_norm": 1.581671953201294, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.3917, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9078896230081617, | |
| "grad_norm": 1.4792799949645996, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 1.1024, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9203264671589584, | |
| "grad_norm": 1.4445815086364746, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 0.9231, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.9327633113097551, | |
| "grad_norm": 1.419348120689392, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3999, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.9327633113097551, | |
| "eval_loss": 1.4757866859436035, | |
| "eval_runtime": 4.3684, | |
| "eval_samples_per_second": 11.446, | |
| "eval_steps_per_second": 2.976, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 8.952125425975296e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |