|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 185, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05405405405405406, |
|
"grad_norm": 1.8533293008804321, |
|
"learning_rate": 0.0001, |
|
"loss": 0.7553, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.10810810810810811, |
|
"grad_norm": 1.8566731214523315, |
|
"learning_rate": 9.919647942993148e-05, |
|
"loss": 0.2456, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.16216216216216217, |
|
"grad_norm": 1.426089882850647, |
|
"learning_rate": 9.681174353198687e-05, |
|
"loss": 0.1699, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.21621621621621623, |
|
"grad_norm": 0.7362193465232849, |
|
"learning_rate": 9.292243968009331e-05, |
|
"loss": 0.1341, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.2702702702702703, |
|
"grad_norm": 1.2846084833145142, |
|
"learning_rate": 8.765357330018056e-05, |
|
"loss": 0.1093, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.32432432432432434, |
|
"grad_norm": 0.5028020739555359, |
|
"learning_rate": 8.117449009293668e-05, |
|
"loss": 0.106, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.3783783783783784, |
|
"grad_norm": 1.2113736867904663, |
|
"learning_rate": 7.369343312364993e-05, |
|
"loss": 0.0977, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.43243243243243246, |
|
"grad_norm": 0.6515302658081055, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 0.0861, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.4864864864864865, |
|
"grad_norm": 0.5156140923500061, |
|
"learning_rate": 5.6711663290882776e-05, |
|
"loss": 0.0856, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.5405405405405406, |
|
"grad_norm": 0.4655522108078003, |
|
"learning_rate": 4.775675848247427e-05, |
|
"loss": 0.065, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.5945945945945946, |
|
"grad_norm": 0.6544004678726196, |
|
"learning_rate": 3.887395330218429e-05, |
|
"loss": 0.0742, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.6486486486486487, |
|
"grad_norm": 0.5006158947944641, |
|
"learning_rate": 3.0348748417303823e-05, |
|
"loss": 0.0641, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.7027027027027027, |
|
"grad_norm": 0.4036032259464264, |
|
"learning_rate": 2.245515092739488e-05, |
|
"loss": 0.0562, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.7567567567567568, |
|
"grad_norm": 0.6734123229980469, |
|
"learning_rate": 1.544686755065677e-05, |
|
"loss": 0.0609, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.8108108108108109, |
|
"grad_norm": 0.7298457622528076, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 0.065, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.8648648648648649, |
|
"grad_norm": 0.47052305936813354, |
|
"learning_rate": 4.951556604879048e-06, |
|
"loss": 0.0577, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.918918918918919, |
|
"grad_norm": 0.46818605065345764, |
|
"learning_rate": 1.8018569652073381e-06, |
|
"loss": 0.0547, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.972972972972973, |
|
"grad_norm": 0.6747378706932068, |
|
"learning_rate": 2.012853002380466e-07, |
|
"loss": 0.0502, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 185, |
|
"total_flos": 2.671639181415504e+16, |
|
"train_loss": 0.12806547799625911, |
|
"train_runtime": 362.2784, |
|
"train_samples_per_second": 32.53, |
|
"train_steps_per_second": 0.511 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 185, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 10000, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.671639181415504e+16, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|