| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 169, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029585798816568046, | |
| "grad_norm": 0.9565215877406359, | |
| "learning_rate": 1.940828402366864e-05, | |
| "loss": 1.1887, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05917159763313609, | |
| "grad_norm": 0.4750293559517379, | |
| "learning_rate": 1.881656804733728e-05, | |
| "loss": 1.0401, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08875739644970414, | |
| "grad_norm": 0.32953737249996196, | |
| "learning_rate": 1.822485207100592e-05, | |
| "loss": 0.968, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11834319526627218, | |
| "grad_norm": 0.318886344340766, | |
| "learning_rate": 1.7633136094674557e-05, | |
| "loss": 0.9185, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14792899408284024, | |
| "grad_norm": 0.2638389003046881, | |
| "learning_rate": 1.70414201183432e-05, | |
| "loss": 0.9058, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17751479289940827, | |
| "grad_norm": 0.32122906405989515, | |
| "learning_rate": 1.6449704142011837e-05, | |
| "loss": 0.9017, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20710059171597633, | |
| "grad_norm": 0.23483871965844322, | |
| "learning_rate": 1.5857988165680475e-05, | |
| "loss": 0.8819, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23668639053254437, | |
| "grad_norm": 0.20244306887706498, | |
| "learning_rate": 1.5266272189349113e-05, | |
| "loss": 0.8606, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26627218934911245, | |
| "grad_norm": 0.22372494047589192, | |
| "learning_rate": 1.4674556213017752e-05, | |
| "loss": 0.8706, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2958579881656805, | |
| "grad_norm": 0.21466269339189736, | |
| "learning_rate": 1.4082840236686392e-05, | |
| "loss": 0.8513, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3254437869822485, | |
| "grad_norm": 0.20954818106403592, | |
| "learning_rate": 1.349112426035503e-05, | |
| "loss": 0.8265, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35502958579881655, | |
| "grad_norm": 0.21146922721065695, | |
| "learning_rate": 1.2899408284023668e-05, | |
| "loss": 0.8576, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.19665190091249535, | |
| "learning_rate": 1.230769230769231e-05, | |
| "loss": 0.8218, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.41420118343195267, | |
| "grad_norm": 0.20585290386463395, | |
| "learning_rate": 1.1715976331360948e-05, | |
| "loss": 0.8216, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4437869822485207, | |
| "grad_norm": 0.18556862617304073, | |
| "learning_rate": 1.1124260355029586e-05, | |
| "loss": 0.8382, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47337278106508873, | |
| "grad_norm": 0.18750887001217453, | |
| "learning_rate": 1.0532544378698226e-05, | |
| "loss": 0.8172, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5029585798816568, | |
| "grad_norm": 0.19315058093994988, | |
| "learning_rate": 9.940828402366864e-06, | |
| "loss": 0.8314, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5325443786982249, | |
| "grad_norm": 0.2050825812729317, | |
| "learning_rate": 9.349112426035503e-06, | |
| "loss": 0.8135, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5621301775147929, | |
| "grad_norm": 0.2099801364496423, | |
| "learning_rate": 8.757396449704143e-06, | |
| "loss": 0.8203, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.591715976331361, | |
| "grad_norm": 0.19404392312346527, | |
| "learning_rate": 8.165680473372781e-06, | |
| "loss": 0.7997, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.591715976331361, | |
| "eval_loss": 0.8431870937347412, | |
| "eval_runtime": 1.6461, | |
| "eval_samples_per_second": 77.758, | |
| "eval_steps_per_second": 2.43, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.621301775147929, | |
| "grad_norm": 0.18171103310198067, | |
| "learning_rate": 7.573964497041421e-06, | |
| "loss": 0.8093, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.650887573964497, | |
| "grad_norm": 0.19297652713486121, | |
| "learning_rate": 6.98224852071006e-06, | |
| "loss": 0.8127, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6804733727810651, | |
| "grad_norm": 0.18560671609846813, | |
| "learning_rate": 6.3905325443786995e-06, | |
| "loss": 0.8045, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7100591715976331, | |
| "grad_norm": 0.1849552337643038, | |
| "learning_rate": 5.7988165680473375e-06, | |
| "loss": 0.7871, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7396449704142012, | |
| "grad_norm": 0.19462300584500286, | |
| "learning_rate": 5.207100591715976e-06, | |
| "loss": 0.7974, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.18273706345405402, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 0.809, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7988165680473372, | |
| "grad_norm": 0.1774041623216232, | |
| "learning_rate": 4.023668639053255e-06, | |
| "loss": 0.8001, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8284023668639053, | |
| "grad_norm": 0.1912069740049753, | |
| "learning_rate": 3.4319526627218935e-06, | |
| "loss": 0.8038, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8579881656804734, | |
| "grad_norm": 0.1757803683582901, | |
| "learning_rate": 2.840236686390533e-06, | |
| "loss": 0.799, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8875739644970414, | |
| "grad_norm": 0.1722960937134139, | |
| "learning_rate": 2.2485207100591717e-06, | |
| "loss": 0.7891, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9171597633136095, | |
| "grad_norm": 0.1845277131426741, | |
| "learning_rate": 1.656804733727811e-06, | |
| "loss": 0.8253, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9467455621301775, | |
| "grad_norm": 0.17325421407966338, | |
| "learning_rate": 1.06508875739645e-06, | |
| "loss": 0.792, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9763313609467456, | |
| "grad_norm": 0.17868163897456654, | |
| "learning_rate": 4.733727810650888e-07, | |
| "loss": 0.7757, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 169, | |
| "total_flos": 76916824473600.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 2.1926, | |
| "train_samples_per_second": 9855.825, | |
| "train_steps_per_second": 77.077 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 169, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 76916824473600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |