| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.34873583260680036, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013949433304272014, | |
| "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 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.1240447254528e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |