77 lines
1.6 KiB
JSON
77 lines
1.6 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 3.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 6,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.8,
|
||
|
|
"grad_norm": 6.437300682067871,
|
||
|
|
"learning_rate": 0.0,
|
||
|
|
"loss": 3.2065,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 8.122940063476562,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 3.4218,
|
||
|
|
"step": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.8,
|
||
|
|
"grad_norm": 6.379891872406006,
|
||
|
|
"learning_rate": 4e-05,
|
||
|
|
"loss": 3.1851,
|
||
|
|
"step": 3
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.0,
|
||
|
|
"grad_norm": 5.646491050720215,
|
||
|
|
"learning_rate": 6e-05,
|
||
|
|
"loss": 2.9141,
|
||
|
|
"step": 4
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.8,
|
||
|
|
"grad_norm": 3.6690704822540283,
|
||
|
|
"learning_rate": 8e-05,
|
||
|
|
"loss": 2.4389,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.0,
|
||
|
|
"grad_norm": 2.7444732189178467,
|
||
|
|
"learning_rate": 0.0001,
|
||
|
|
"loss": 2.4879,
|
||
|
|
"step": 6
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 1,
|
||
|
|
"max_steps": 6,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"save_steps": 5000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 325414372823040.0,
|
||
|
|
"train_batch_size": 2,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|