|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.0, |
|
"eval_steps": 500, |
|
"global_step": 130, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 9.230769230769232e-06, |
|
"loss": 0.2471, |
|
"max_memory_allocated (GB)": 94.4, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 10, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 8.461538461538462e-06, |
|
"loss": 0.1034, |
|
"max_memory_allocated (GB)": 94.42, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 20, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 7.692307692307694e-06, |
|
"loss": 0.0834, |
|
"max_memory_allocated (GB)": 94.42, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 30, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 6.923076923076923e-06, |
|
"loss": 0.0813, |
|
"max_memory_allocated (GB)": 94.42, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 40, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 6.153846153846155e-06, |
|
"loss": 0.0771, |
|
"max_memory_allocated (GB)": 94.42, |
|
"memory_allocated (GB)": 17.83, |
|
"step": 50, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 5.384615384615385e-06, |
|
"loss": 0.0732, |
|
"max_memory_allocated (GB)": 94.42, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 60, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 4.615384615384616e-06, |
|
"loss": 0.0714, |
|
"max_memory_allocated (GB)": 94.43, |
|
"memory_allocated (GB)": 17.89, |
|
"step": 70, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 3.846153846153847e-06, |
|
"loss": 0.0715, |
|
"max_memory_allocated (GB)": 94.43, |
|
"memory_allocated (GB)": 17.89, |
|
"step": 80, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"learning_rate": 3.0769230769230774e-06, |
|
"loss": 0.0693, |
|
"max_memory_allocated (GB)": 94.43, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 90, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 2.307692307692308e-06, |
|
"loss": 0.0691, |
|
"max_memory_allocated (GB)": 94.43, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 100, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"learning_rate": 1.5384615384615387e-06, |
|
"loss": 0.0691, |
|
"max_memory_allocated (GB)": 94.43, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 110, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 7.692307692307694e-07, |
|
"loss": 0.0702, |
|
"max_memory_allocated (GB)": 94.43, |
|
"memory_allocated (GB)": 17.88, |
|
"step": 120, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.0698, |
|
"max_memory_allocated (GB)": 94.43, |
|
"memory_allocated (GB)": 17.74, |
|
"step": 130, |
|
"total_memory_available (GB)": 94.61 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"max_memory_allocated (GB)": 94.43, |
|
"memory_allocated (GB)": 17.74, |
|
"step": 130, |
|
"total_flos": 3.117345829342413e+16, |
|
"total_memory_available (GB)": 94.61, |
|
"train_loss": 0.08891021746855515, |
|
"train_runtime": 341.352, |
|
"train_samples_per_second": 429.544, |
|
"train_steps_per_second": 1.141 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 130, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"total_flos": 3.117345829342413e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|