| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11682242990654206, | |
| "eval_steps": 4, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004672897196261682, | |
| "grad_norm": 0.021811505779623985, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 10.3773, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004672897196261682, | |
| "eval_loss": 10.380165100097656, | |
| "eval_runtime": 0.4183, | |
| "eval_samples_per_second": 215.178, | |
| "eval_steps_per_second": 54.99, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 0.027132729068398476, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 10.3817, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014018691588785047, | |
| "grad_norm": 0.03020065277814865, | |
| "learning_rate": 3e-06, | |
| "loss": 10.3781, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 0.022099485620856285, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 10.3826, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "eval_loss": 10.380165100097656, | |
| "eval_runtime": 0.4296, | |
| "eval_samples_per_second": 209.519, | |
| "eval_steps_per_second": 53.544, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02336448598130841, | |
| "grad_norm": 0.025594104081392288, | |
| "learning_rate": 5e-06, | |
| "loss": 10.381, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 0.03467366844415665, | |
| "learning_rate": 6e-06, | |
| "loss": 10.3765, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03271028037383177, | |
| "grad_norm": 0.022812705487012863, | |
| "learning_rate": 7e-06, | |
| "loss": 10.3822, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 0.026599343866109848, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 10.3811, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "eval_loss": 10.380156517028809, | |
| "eval_runtime": 0.4169, | |
| "eval_samples_per_second": 215.905, | |
| "eval_steps_per_second": 55.176, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04205607476635514, | |
| "grad_norm": 0.023074598982930183, | |
| "learning_rate": 9e-06, | |
| "loss": 10.3728, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04672897196261682, | |
| "grad_norm": 0.032919738441705704, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3786, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0514018691588785, | |
| "grad_norm": 0.02511332742869854, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 10.3747, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 0.024660587310791016, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 10.3836, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "eval_loss": 10.38013744354248, | |
| "eval_runtime": 0.4437, | |
| "eval_samples_per_second": 202.859, | |
| "eval_steps_per_second": 51.842, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06074766355140187, | |
| "grad_norm": 0.023776650428771973, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 10.3729, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06542056074766354, | |
| "grad_norm": 0.02619120106101036, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 10.3764, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07009345794392523, | |
| "grad_norm": 0.022596610710024834, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 10.3796, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 0.02786189876496792, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 10.3807, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "eval_loss": 10.380114555358887, | |
| "eval_runtime": 0.4279, | |
| "eval_samples_per_second": 210.353, | |
| "eval_steps_per_second": 53.757, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0794392523364486, | |
| "grad_norm": 0.026685988530516624, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 10.3827, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08411214953271028, | |
| "grad_norm": 0.025408007204532623, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 10.3776, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08878504672897196, | |
| "grad_norm": 0.02390649914741516, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 10.3809, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 0.028136681765317917, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 10.3781, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "eval_loss": 10.380105018615723, | |
| "eval_runtime": 0.549, | |
| "eval_samples_per_second": 163.933, | |
| "eval_steps_per_second": 41.894, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09813084112149532, | |
| "grad_norm": 0.021048307418823242, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 10.376, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.102803738317757, | |
| "grad_norm": 0.021575015038251877, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 10.3777, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10747663551401869, | |
| "grad_norm": 0.02331606112420559, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 10.3831, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 0.02492584101855755, | |
| "learning_rate": 1.0926199633097156e-07, | |
| "loss": 10.3764, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "eval_loss": 10.380101203918457, | |
| "eval_runtime": 0.4245, | |
| "eval_samples_per_second": 212.025, | |
| "eval_steps_per_second": 54.184, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11682242990654206, | |
| "grad_norm": 0.028461946174502373, | |
| "learning_rate": 0.0, | |
| "loss": 10.3803, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": 653780582400.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |