| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9996261682242991, | |
| "eval_steps": 134, | |
| "global_step": 1337, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05009345794392523, | |
| "grad_norm": 2.942253589630127, | |
| "learning_rate": 5e-07, | |
| "loss": 0.4451, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.10018691588785046, | |
| "grad_norm": 6.863779067993164, | |
| "learning_rate": 1e-06, | |
| "loss": 0.427, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.1502803738317757, | |
| "grad_norm": 2.3883817195892334, | |
| "learning_rate": 9.443059019118869e-07, | |
| "loss": 0.3916, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.20037383177570092, | |
| "grad_norm": 4.304512977600098, | |
| "learning_rate": 8.886118038237738e-07, | |
| "loss": 0.3516, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.2504672897196262, | |
| "grad_norm": 2.8164753913879395, | |
| "learning_rate": 8.329177057356608e-07, | |
| "loss": 0.2772, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.3005607476635514, | |
| "grad_norm": 1.764276146888733, | |
| "learning_rate": 7.772236076475478e-07, | |
| "loss": 0.2265, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.3506542056074766, | |
| "grad_norm": 2.509056806564331, | |
| "learning_rate": 7.215295095594347e-07, | |
| "loss": 0.2223, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.40074766355140184, | |
| "grad_norm": 1.2209707498550415, | |
| "learning_rate": 6.658354114713217e-07, | |
| "loss": 0.1904, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.4508411214953271, | |
| "grad_norm": 1.6530442237854004, | |
| "learning_rate": 6.101413133832086e-07, | |
| "loss": 0.1972, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.5009345794392523, | |
| "grad_norm": 2.5448479652404785, | |
| "learning_rate": 5.544472152950955e-07, | |
| "loss": 0.1901, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5510280373831775, | |
| "grad_norm": 2.0424203872680664, | |
| "learning_rate": 4.987531172069825e-07, | |
| "loss": 0.1809, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.6011214953271028, | |
| "grad_norm": 2.789212226867676, | |
| "learning_rate": 4.4305901911886947e-07, | |
| "loss": 0.1667, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.6512149532710281, | |
| "grad_norm": 2.038717269897461, | |
| "learning_rate": 3.873649210307564e-07, | |
| "loss": 0.1713, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 0.7013084112149532, | |
| "grad_norm": 1.706325888633728, | |
| "learning_rate": 3.3167082294264335e-07, | |
| "loss": 0.1628, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.7514018691588785, | |
| "grad_norm": 1.2791858911514282, | |
| "learning_rate": 2.7597672485453034e-07, | |
| "loss": 0.1411, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.8014953271028037, | |
| "grad_norm": 2.504589557647705, | |
| "learning_rate": 2.2028262676641728e-07, | |
| "loss": 0.1502, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 0.851588785046729, | |
| "grad_norm": 2.502255439758301, | |
| "learning_rate": 1.6458852867830422e-07, | |
| "loss": 0.1568, | |
| "step": 1139 | |
| }, | |
| { | |
| "epoch": 0.9016822429906542, | |
| "grad_norm": 1.224613904953003, | |
| "learning_rate": 1.0889443059019118e-07, | |
| "loss": 0.134, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 0.9517757009345794, | |
| "grad_norm": 3.104508876800537, | |
| "learning_rate": 5.320033250207814e-08, | |
| "loss": 0.1404, | |
| "step": 1273 | |
| }, | |
| { | |
| "epoch": 0.9996261682242991, | |
| "step": 1337, | |
| "total_flos": 9.176656366338048e+16, | |
| "train_loss": 0.2238639939963684, | |
| "train_runtime": 1988.5984, | |
| "train_samples_per_second": 5.381, | |
| "train_steps_per_second": 0.672 | |
| } | |
| ], | |
| "logging_steps": 67, | |
| "max_steps": 1337, | |
| "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": 9.176656366338048e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |