| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6974716652136007, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013949433304272014, | |
| "grad_norm": 7.010751247406006, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013949433304272014, | |
| "eval_loss": 9.326899528503418, | |
| "eval_runtime": 2.0555, | |
| "eval_samples_per_second": 24.325, | |
| "eval_steps_per_second": 6.325, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02789886660854403, | |
| "grad_norm": 9.376703262329102, | |
| "learning_rate": 0.0001, | |
| "loss": 6.5764, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.041848299912816043, | |
| "grad_norm": 7.487423419952393, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.34, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05579773321708806, | |
| "grad_norm": 3.2554428577423096, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.8028, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06974716652136007, | |
| "grad_norm": 3.363396167755127, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.5716, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08369659982563209, | |
| "grad_norm": 3.9122681617736816, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.3594, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0976460331299041, | |
| "grad_norm": 3.9620187282562256, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 5.1126, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11159546643417612, | |
| "grad_norm": 3.246738910675049, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.0225, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12554489973844812, | |
| "grad_norm": 5.447027683258057, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.8363, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13949433304272013, | |
| "grad_norm": 4.531150817871094, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.542, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15344376634699217, | |
| "grad_norm": 3.6110222339630127, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.5433, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16739319965126417, | |
| "grad_norm": 5.013479709625244, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.8052, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18134263295553618, | |
| "grad_norm": 5.054234504699707, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 4.5539, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1952920662598082, | |
| "grad_norm": 4.733574390411377, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.6474, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2092414995640802, | |
| "grad_norm": 3.496427536010742, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.5994, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22319093286835223, | |
| "grad_norm": 2.406287431716919, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.4711, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23714036617262424, | |
| "grad_norm": 1.5761107206344604, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.376, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.25108979947689625, | |
| "grad_norm": 1.8928381204605103, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.4662, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.26503923278116825, | |
| "grad_norm": 2.255488157272339, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.3946, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27898866608544026, | |
| "grad_norm": 2.6279284954071045, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.4128, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.29293809938971227, | |
| "grad_norm": 2.4174962043762207, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.4053, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.30688753269398433, | |
| "grad_norm": 2.133634567260742, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.338, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.32083696599825634, | |
| "grad_norm": 2.4884660243988037, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.0933, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.33478639930252835, | |
| "grad_norm": 2.57370662689209, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.8339, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.34873583260680036, | |
| "grad_norm": 3.5672824382781982, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.6497, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.34873583260680036, | |
| "eval_loss": 4.20637321472168, | |
| "eval_runtime": 2.0737, | |
| "eval_samples_per_second": 24.112, | |
| "eval_steps_per_second": 6.269, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.36268526591107236, | |
| "grad_norm": 3.976642370223999, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.4711, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.37663469921534437, | |
| "grad_norm": 4.475371360778809, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.4931, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3905841325196164, | |
| "grad_norm": 4.376916885375977, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 4.662, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4045335658238884, | |
| "grad_norm": 3.5628089904785156, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.5019, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4184829991281604, | |
| "grad_norm": 3.14534854888916, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.5237, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 2.6178762912750244, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 4.405, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.44638186573670446, | |
| "grad_norm": 2.1331136226654053, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 4.1528, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.46033129904097647, | |
| "grad_norm": 1.9061111211776733, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.347, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4742807323452485, | |
| "grad_norm": 1.8948556184768677, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.0309, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4882301656495205, | |
| "grad_norm": 2.3290843963623047, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.1429, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5021795989537925, | |
| "grad_norm": 3.0071651935577393, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.8502, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 3.767021656036377, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.8187, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5300784655623365, | |
| "grad_norm": 1.1453721523284912, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 4.0583, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5440278988666085, | |
| "grad_norm": 1.1263549327850342, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.1802, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5579773321708805, | |
| "grad_norm": 1.0567845106124878, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.1979, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5719267654751525, | |
| "grad_norm": 1.0829411745071411, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 4.2523, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5858761987794245, | |
| "grad_norm": 1.121140480041504, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.27, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5998256320836965, | |
| "grad_norm": 1.2229188680648804, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 4.193, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6137750653879687, | |
| "grad_norm": 1.2727962732315063, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.2052, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6277244986922407, | |
| "grad_norm": 1.4603536128997803, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.1933, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6416739319965127, | |
| "grad_norm": 1.4937858581542969, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.0251, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6556233653007847, | |
| "grad_norm": 1.6102039813995361, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.0256, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6695727986050567, | |
| "grad_norm": 1.9616433382034302, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.9568, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6835222319093287, | |
| "grad_norm": 2.3991916179656982, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.7399, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6974716652136007, | |
| "grad_norm": 4.19977331161499, | |
| "learning_rate": 1e-05, | |
| "loss": 3.6125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6974716652136007, | |
| "eval_loss": 4.018064022064209, | |
| "eval_runtime": 2.0767, | |
| "eval_samples_per_second": 24.076, | |
| "eval_steps_per_second": 6.26, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.62480894509056e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |