104 lines
2.4 KiB
JSON
104 lines
2.4 KiB
JSON
|
{
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.29612081729345574,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 1000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.029612081729345572,
|
||
|
|
"grad_norm": 1.3230875730514526,
|
||
|
|
"learning_rate": 4.851939591353272e-05,
|
||
|
|
"loss": 0.7815,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.059224163458691144,
|
||
|
|
"grad_norm": 1.2026115655899048,
|
||
|
|
"learning_rate": 4.703879182706544e-05,
|
||
|
|
"loss": 0.7442,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08883624518803672,
|
||
|
|
"grad_norm": 1.3409602642059326,
|
||
|
|
"learning_rate": 4.5558187740598166e-05,
|
||
|
|
"loss": 0.7353,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.11844832691738229,
|
||
|
|
"grad_norm": 1.6831313371658325,
|
||
|
|
"learning_rate": 4.407758365413089e-05,
|
||
|
|
"loss": 0.697,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.14806040864672787,
|
||
|
|
"grad_norm": 1.5774145126342773,
|
||
|
|
"learning_rate": 4.259697956766361e-05,
|
||
|
|
"loss": 0.7392,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.17767249037607344,
|
||
|
|
"grad_norm": 1.1909443140029907,
|
||
|
|
"learning_rate": 4.1145987562925676e-05,
|
||
|
|
"loss": 0.7317,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.207284572105419,
|
||
|
|
"grad_norm": 1.3016351461410522,
|
||
|
|
"learning_rate": 3.968018951732307e-05,
|
||
|
|
"loss": 0.6802,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.23689665383476458,
|
||
|
|
"grad_norm": 0.9892593622207642,
|
||
|
|
"learning_rate": 3.819958543085579e-05,
|
||
|
|
"loss": 0.7211,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.26650873556411014,
|
||
|
|
"grad_norm": 1.4809260368347168,
|
||
|
|
"learning_rate": 3.671898134438851e-05,
|
||
|
|
"loss": 0.7031,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.29612081729345574,
|
||
|
|
"grad_norm": 0.9776161909103394,
|
||
|
|
"learning_rate": 3.5238377257921236e-05,
|
||
|
|
"loss": 0.7068,
|
||
|
|
"step": 1000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 100,
|
||
|
|
"max_steps": 3377,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 1000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 7.6272529047552e+16,
|
||
|
|
"train_batch_size": 6,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|