98 lines
2.3 KiB
JSON
98 lines
2.3 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 2.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 46,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.2222222222222222,
|
||
|
|
"grad_norm": 1.815280795097351,
|
||
|
|
"learning_rate": 4e-05,
|
||
|
|
"loss": 1.8314319610595704,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4444444444444444,
|
||
|
|
"grad_norm": 0.8358477354049683,
|
||
|
|
"learning_rate": 9e-05,
|
||
|
|
"loss": 1.557858657836914,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6666666666666666,
|
||
|
|
"grad_norm": 0.36792853474617004,
|
||
|
|
"learning_rate": 8.888888888888889e-05,
|
||
|
|
"loss": 1.2523537635803224,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8888888888888888,
|
||
|
|
"grad_norm": 0.23963096737861633,
|
||
|
|
"learning_rate": 7.500000000000001e-05,
|
||
|
|
"loss": 1.1497629165649415,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0888888888888888,
|
||
|
|
"grad_norm": 0.21918611228466034,
|
||
|
|
"learning_rate": 6.111111111111112e-05,
|
||
|
|
"loss": 1.0989482879638672,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3111111111111111,
|
||
|
|
"grad_norm": 0.1978486329317093,
|
||
|
|
"learning_rate": 4.722222222222222e-05,
|
||
|
|
"loss": 1.0302928924560546,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.5333333333333332,
|
||
|
|
"grad_norm": 0.18371747434139252,
|
||
|
|
"learning_rate": 3.3333333333333335e-05,
|
||
|
|
"loss": 0.9991992950439453,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.7555555555555555,
|
||
|
|
"grad_norm": 0.20835615694522858,
|
||
|
|
"learning_rate": 1.9444444444444445e-05,
|
||
|
|
"loss": 0.9896576881408692,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.9777777777777779,
|
||
|
|
"grad_norm": 0.17088429629802704,
|
||
|
|
"learning_rate": 5.555555555555556e-06,
|
||
|
|
"loss": 0.9686853408813476,
|
||
|
|
"step": 45
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 46,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 2,
|
||
|
|
"save_steps": 50,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 6895348250001408.0,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|