{ "best_metric": 0.09648923575878143, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.5639760310186817, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.011279520620373634, "grad_norm": 18.636917114257812, "learning_rate": 5e-05, "loss": 3.2422, "step": 1 }, { "epoch": 0.011279520620373634, "eval_loss": 5.690601348876953, "eval_runtime": 1.9296, "eval_samples_per_second": 25.912, "eval_steps_per_second": 6.737, "step": 1 }, { "epoch": 0.022559041240747268, "grad_norm": 28.302452087402344, "learning_rate": 0.0001, "loss": 3.5306, "step": 2 }, { "epoch": 0.0338385618611209, "grad_norm": 19.500347137451172, "learning_rate": 9.990365154573717e-05, "loss": 2.8159, "step": 3 }, { "epoch": 0.045118082481494536, "grad_norm": 11.530250549316406, "learning_rate": 9.961501876182148e-05, "loss": 1.1316, "step": 4 }, { "epoch": 0.05639760310186817, "grad_norm": 7.540546894073486, "learning_rate": 9.913533761814537e-05, "loss": 0.7297, "step": 5 }, { "epoch": 0.0676771237222418, "grad_norm": 3.1581292152404785, "learning_rate": 9.846666218300807e-05, "loss": 0.4268, "step": 6 }, { "epoch": 0.07895664434261544, "grad_norm": 4.705471515655518, "learning_rate": 9.761185582727977e-05, "loss": 0.3025, "step": 7 }, { "epoch": 0.09023616496298907, "grad_norm": 2.972853183746338, "learning_rate": 9.657457896300791e-05, "loss": 0.1283, "step": 8 }, { "epoch": 0.10151568558336271, "grad_norm": 0.3666192293167114, "learning_rate": 9.535927336897098e-05, "loss": 0.0174, "step": 9 }, { "epoch": 0.11279520620373634, "grad_norm": 0.18954011797904968, "learning_rate": 9.397114317029975e-05, "loss": 0.0071, "step": 10 }, { "epoch": 0.12407472682410997, "grad_norm": 0.048828527331352234, "learning_rate": 9.241613255361455e-05, "loss": 0.0017, "step": 11 }, { "epoch": 0.1353542474444836, "grad_norm": 0.2890184819698334, "learning_rate": 9.070090031310558e-05, "loss": 0.0052, "step": 12 }, { "epoch": 0.14663376806485726, "grad_norm": 2.866231679916382, "learning_rate": 8.883279133655399e-05, "loss": 1.4678, "step": 13 }, { "epoch": 0.15791328868523088, "grad_norm": 0.02171432040631771, "learning_rate": 8.681980515339464e-05, "loss": 0.0005, "step": 14 }, { "epoch": 0.1691928093056045, "grad_norm": 0.19137023389339447, "learning_rate": 8.467056167950311e-05, "loss": 0.0007, "step": 15 }, { "epoch": 0.18047232992597814, "grad_norm": 0.13450351357460022, "learning_rate": 8.239426430539243e-05, "loss": 0.0018, "step": 16 }, { "epoch": 0.19175185054635177, "grad_norm": 0.013826968148350716, "learning_rate": 8.000066048588211e-05, "loss": 0.0002, "step": 17 }, { "epoch": 0.20303137116672543, "grad_norm": 0.30814099311828613, "learning_rate": 7.75e-05, "loss": 0.0121, "step": 18 }, { "epoch": 0.21431089178709906, "grad_norm": 0.05152116343379021, "learning_rate": 7.490299105985507e-05, "loss": 0.0006, "step": 19 }, { "epoch": 0.22559041240747268, "grad_norm": 0.6050778031349182, "learning_rate": 7.222075445642904e-05, "loss": 0.0047, "step": 20 }, { "epoch": 0.2368699330278463, "grad_norm": 0.07030107080936432, "learning_rate": 6.946477593864228e-05, "loss": 0.0007, "step": 21 }, { "epoch": 0.24814945364821994, "grad_norm": 0.03173314034938812, "learning_rate": 6.664685702961344e-05, "loss": 0.0004, "step": 22 }, { "epoch": 0.25942897426859357, "grad_norm": 0.18959318101406097, "learning_rate": 6.377906449072578e-05, "loss": 0.0013, "step": 23 }, { "epoch": 0.2707084948889672, "grad_norm": 0.005595038179308176, "learning_rate": 6.087367864990233e-05, "loss": 0.0001, "step": 24 }, { "epoch": 0.28198801550934083, "grad_norm": 0.0017077671363949776, "learning_rate": 5.794314081535644e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.28198801550934083, "eval_loss": 0.19338418543338776, "eval_runtime": 1.9144, "eval_samples_per_second": 26.118, "eval_steps_per_second": 6.791, "step": 25 }, { "epoch": 0.2932675361297145, "grad_norm": 2.5036373138427734, "learning_rate": 5.500000000000001e-05, "loss": 0.7331, "step": 26 }, { "epoch": 0.30454705675008814, "grad_norm": 0.009689477272331715, "learning_rate": 5.205685918464356e-05, "loss": 0.0001, "step": 27 }, { "epoch": 0.31582657737046177, "grad_norm": 0.0014077340019866824, "learning_rate": 4.912632135009769e-05, "loss": 0.0, "step": 28 }, { "epoch": 0.3271060979908354, "grad_norm": 0.03966264799237251, "learning_rate": 4.6220935509274235e-05, "loss": 0.0002, "step": 29 }, { "epoch": 0.338385618611209, "grad_norm": 0.08873093873262405, "learning_rate": 4.3353142970386564e-05, "loss": 0.0007, "step": 30 }, { "epoch": 0.34966513923158266, "grad_norm": 0.09382674843072891, "learning_rate": 4.053522406135775e-05, "loss": 0.0009, "step": 31 }, { "epoch": 0.3609446598519563, "grad_norm": 0.04602659121155739, "learning_rate": 3.777924554357096e-05, "loss": 0.0003, "step": 32 }, { "epoch": 0.3722241804723299, "grad_norm": 0.29243648052215576, "learning_rate": 3.509700894014496e-05, "loss": 0.0044, "step": 33 }, { "epoch": 0.38350370109270354, "grad_norm": 0.16613152623176575, "learning_rate": 3.250000000000001e-05, "loss": 0.0022, "step": 34 }, { "epoch": 0.39478322171307717, "grad_norm": 0.043631184846162796, "learning_rate": 2.9999339514117912e-05, "loss": 0.0005, "step": 35 }, { "epoch": 0.40606274233345085, "grad_norm": 0.002960504963994026, "learning_rate": 2.760573569460757e-05, "loss": 0.0001, "step": 36 }, { "epoch": 0.4173422629538245, "grad_norm": 0.005832310300320387, "learning_rate": 2.53294383204969e-05, "loss": 0.0001, "step": 37 }, { "epoch": 0.4286217835741981, "grad_norm": 3.135204553604126, "learning_rate": 2.3180194846605367e-05, "loss": 0.8, "step": 38 }, { "epoch": 0.43990130419457174, "grad_norm": 0.005184840876609087, "learning_rate": 2.1167208663446025e-05, "loss": 0.0001, "step": 39 }, { "epoch": 0.45118082481494537, "grad_norm": 0.00458234827965498, "learning_rate": 1.9299099686894423e-05, "loss": 0.0001, "step": 40 }, { "epoch": 0.462460345435319, "grad_norm": 0.030586376786231995, "learning_rate": 1.758386744638546e-05, "loss": 0.0004, "step": 41 }, { "epoch": 0.4737398660556926, "grad_norm": 0.01800384186208248, "learning_rate": 1.602885682970026e-05, "loss": 0.0002, "step": 42 }, { "epoch": 0.48501938667606626, "grad_norm": 0.009339077398180962, "learning_rate": 1.464072663102903e-05, "loss": 0.0002, "step": 43 }, { "epoch": 0.4962989072964399, "grad_norm": 0.018710706382989883, "learning_rate": 1.3425421036992098e-05, "loss": 0.0003, "step": 44 }, { "epoch": 0.5075784279168135, "grad_norm": 0.008345427922904491, "learning_rate": 1.2388144172720251e-05, "loss": 0.0001, "step": 45 }, { "epoch": 0.5188579485371871, "grad_norm": 0.1667875349521637, "learning_rate": 1.1533337816991932e-05, "loss": 0.0116, "step": 46 }, { "epoch": 0.5301374691575608, "grad_norm": 0.031969476491212845, "learning_rate": 1.0864662381854632e-05, "loss": 0.0004, "step": 47 }, { "epoch": 0.5414169897779344, "grad_norm": 0.006944997701793909, "learning_rate": 1.0384981238178534e-05, "loss": 0.0001, "step": 48 }, { "epoch": 0.552696510398308, "grad_norm": 0.006165571045130491, "learning_rate": 1.0096348454262845e-05, "loss": 0.0001, "step": 49 }, { "epoch": 0.5639760310186817, "grad_norm": 0.005968439858406782, "learning_rate": 1e-05, "loss": 0.0001, "step": 50 }, { "epoch": 0.5639760310186817, "eval_loss": 0.09648923575878143, "eval_runtime": 1.9841, "eval_samples_per_second": 25.2, "eval_steps_per_second": 6.552, "step": 50 } ], "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": true }, "attributes": {} } }, "total_flos": 1.082548160519209e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }