152 lines
2.6 KiB
JSON
152 lines
2.6 KiB
JSON
|
{
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 8.963414634146341,
|
||
|
|
"eval_steps": 100,
|
||
|
|
"global_step": 2205,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.41,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.3987,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.81,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 1.1878,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.22,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.7575,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.63,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.7709,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.03,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.3723,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.44,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.3363,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.85,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.3537,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.25,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.1487,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.66,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.1769,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 4.07,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.112,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 4.47,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.1087,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 4.88,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.134,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 5.28,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.0765,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 5.69,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.1008,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 6.1,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.1036,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 6.5,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.0787,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 6.91,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.0881,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 7.32,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.0721,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 7.72,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.0671,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 8.13,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.0551,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 8.54,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.0654,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 8.94,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.0747,
|
||
|
|
"step": 2200
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 100,
|
||
|
|
"max_steps": 2205,
|
||
|
|
"num_train_epochs": 9,
|
||
|
|
"save_steps": 245,
|
||
|
|
"total_flos": 0.0,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|