| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 29, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 2.067223362182073, | |
| "learning_rate": 0.0, | |
| "loss": 0.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 2.2905484024803084, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 1.043, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 2.0823489332612506, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 0.9479, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 2.155054227940796, | |
| "learning_rate": 2.1428571428571427e-06, | |
| "loss": 1.0054, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 2.122195910115268, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.0227, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 2.0002296419363823, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 0.9994, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 1.7794168286652636, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 0.9833, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 1.608102047372758, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0059, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 1.5096684699130434, | |
| "learning_rate": 4.999302593030069e-06, | |
| "loss": 1.0199, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 1.2553700926461733, | |
| "learning_rate": 4.99721076122146e-06, | |
| "loss": 0.9945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 1.0588682250755448, | |
| "learning_rate": 4.99372567166064e-06, | |
| "loss": 0.8896, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 1.2403025527385267, | |
| "learning_rate": 4.98884926876821e-06, | |
| "loss": 0.9064, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.45614035087719296, | |
| "grad_norm": 1.3277416791779741, | |
| "learning_rate": 4.982584273214061e-06, | |
| "loss": 0.9728, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 1.200452342066303, | |
| "learning_rate": 4.974934180399447e-06, | |
| "loss": 0.8801, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 1.2276015693500428, | |
| "learning_rate": 4.965903258506806e-06, | |
| "loss": 0.9056, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.9588298096291193, | |
| "learning_rate": 4.955496546118439e-06, | |
| "loss": 0.851, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5964912280701754, | |
| "grad_norm": 0.8961934214540342, | |
| "learning_rate": 4.943719849405347e-06, | |
| "loss": 0.9588, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.7752982692883841, | |
| "learning_rate": 4.930579738887827e-06, | |
| "loss": 0.8592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.7598215199572412, | |
| "learning_rate": 4.9160835457696075e-06, | |
| "loss": 0.9224, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.7947043775095588, | |
| "learning_rate": 4.900239357847582e-06, | |
| "loss": 0.9183, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.8131278296751281, | |
| "learning_rate": 4.883056014999423e-06, | |
| "loss": 0.8854, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 0.720597258722373, | |
| "learning_rate": 4.864543104251587e-06, | |
| "loss": 0.837, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8070175438596491, | |
| "grad_norm": 0.698175660395316, | |
| "learning_rate": 4.844710954430464e-06, | |
| "loss": 0.9006, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.6061246443427316, | |
| "learning_rate": 4.823570630399665e-06, | |
| "loss": 0.8713, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.5800728862173004, | |
| "learning_rate": 4.8011339268866505e-06, | |
| "loss": 0.8572, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 0.6881850987832964, | |
| "learning_rate": 4.777413361902152e-06, | |
| "loss": 0.9243, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.6013453853835422, | |
| "learning_rate": 4.752422169756048e-06, | |
| "loss": 0.8215, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 0.5049917945559669, | |
| "learning_rate": 4.726174293673612e-06, | |
| "loss": 0.8498, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.5049917945559669, | |
| "learning_rate": 4.698684378016223e-06, | |
| "loss": 0.7765, | |
| "step": 29 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 12946871943168.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |