148 lines
3.3 KiB
JSON
148 lines
3.3 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.9952,
|
|
"eval_steps": 500,
|
|
"global_step": 468,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.192,
|
|
"grad_norm": 1.5544959976587758,
|
|
"learning_rate": 4.94947663010567e-06,
|
|
"loss": 1.2661,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.384,
|
|
"grad_norm": 1.58877277838815,
|
|
"learning_rate": 4.799948609147061e-06,
|
|
"loss": 1.1198,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.576,
|
|
"grad_norm": 1.4076735500904218,
|
|
"learning_rate": 4.5574596647341414e-06,
|
|
"loss": 1.1018,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.768,
|
|
"grad_norm": 1.4296012725480793,
|
|
"learning_rate": 4.231810883773999e-06,
|
|
"loss": 1.1007,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"grad_norm": 1.405680058916635,
|
|
"learning_rate": 3.836164565319503e-06,
|
|
"loss": 1.0833,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 1.152,
|
|
"grad_norm": 1.3339483109482262,
|
|
"learning_rate": 3.386512217606339e-06,
|
|
"loss": 0.9834,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 1.3439999999999999,
|
|
"grad_norm": 1.3288150935651342,
|
|
"learning_rate": 2.9010282021444008e-06,
|
|
"loss": 0.9506,
|
|
"step": 210
|
|
},
|
|
{
|
|
"epoch": 1.536,
|
|
"grad_norm": 1.356933287143514,
|
|
"learning_rate": 2.399335149726463e-06,
|
|
"loss": 0.9435,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 1.728,
|
|
"grad_norm": 1.3070430897157126,
|
|
"learning_rate": 1.9017108392811065e-06,
|
|
"loss": 0.9443,
|
|
"step": 270
|
|
},
|
|
{
|
|
"epoch": 1.92,
|
|
"grad_norm": 1.3825627014048851,
|
|
"learning_rate": 1.4282685964923643e-06,
|
|
"loss": 0.9447,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 2.112,
|
|
"grad_norm": 1.4058361561032482,
|
|
"learning_rate": 9.981443394050525e-07,
|
|
"loss": 0.8923,
|
|
"step": 330
|
|
},
|
|
{
|
|
"epoch": 2.304,
|
|
"grad_norm": 1.3575000714838341,
|
|
"learning_rate": 6.28723129572247e-07,
|
|
"loss": 0.8429,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 2.496,
|
|
"grad_norm": 1.3763689831257202,
|
|
"learning_rate": 3.3493649053890325e-07,
|
|
"loss": 0.8478,
|
|
"step": 390
|
|
},
|
|
{
|
|
"epoch": 2.6879999999999997,
|
|
"grad_norm": 1.4156917358264154,
|
|
"learning_rate": 1.286588951321363e-07,
|
|
"loss": 0.8463,
|
|
"step": 420
|
|
},
|
|
{
|
|
"epoch": 2.88,
|
|
"grad_norm": 1.3846493525562265,
|
|
"learning_rate": 1.822781475486507e-08,
|
|
"loss": 0.8508,
|
|
"step": 450
|
|
},
|
|
{
|
|
"epoch": 2.9952,
|
|
"step": 468,
|
|
"total_flos": 80495178678272.0,
|
|
"train_loss": 0.9764440487592648,
|
|
"train_runtime": 2345.6045,
|
|
"train_samples_per_second": 25.58,
|
|
"train_steps_per_second": 0.2
|
|
}
|
|
],
|
|
"logging_steps": 30,
|
|
"max_steps": 468,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 100,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 80495178678272.0,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|