{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 5.0, | |
"global_step": 2950, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.85, | |
"learning_rate": 1.663050847457627e-05, | |
"loss": 0.7248, | |
"step": 500 | |
}, | |
{ | |
"epoch": 1.69, | |
"learning_rate": 1.3240677966101696e-05, | |
"loss": 0.5954, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 2.54, | |
"learning_rate": 9.85084745762712e-06, | |
"loss": 0.4047, | |
"step": 1500 | |
}, | |
{ | |
"epoch": 3.39, | |
"learning_rate": 6.461016949152543e-06, | |
"loss": 0.2393, | |
"step": 2000 | |
}, | |
{ | |
"epoch": 4.24, | |
"learning_rate": 3.0711864406779663e-06, | |
"loss": 0.1266, | |
"step": 2500 | |
}, | |
{ | |
"epoch": 5.0, | |
"step": 2950, | |
"total_flos": 1.098149785632768e+16, | |
"train_loss": 0.36301778308415816, | |
"train_runtime": 286.6652, | |
"train_samples_per_second": 164.425, | |
"train_steps_per_second": 10.291 | |
} | |
], | |
"max_steps": 2950, | |
"num_train_epochs": 5, | |
"total_flos": 1.098149785632768e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |