63 lines
1.4 KiB
Plaintext
63 lines
1.4 KiB
Plaintext
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.03187200203980813,
|
|
"eval_steps": 500,
|
|
"global_step": 2000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.007968000509952033,
|
|
"grad_norm": 118279.4375,
|
|
"learning_rate": 2.9936381561814055e-05,
|
|
"loss": 1.2421,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.015936001019904066,
|
|
"grad_norm": 93984.2109375,
|
|
"learning_rate": 2.9856659208197584e-05,
|
|
"loss": 0.7745,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.023904001529856098,
|
|
"grad_norm": 78285.7578125,
|
|
"learning_rate": 2.9776936854581113e-05,
|
|
"loss": 0.73,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 0.03187200203980813,
|
|
"grad_norm": 72728.3359375,
|
|
"learning_rate": 2.9697214500964642e-05,
|
|
"loss": 0.7087,
|
|
"step": 2000
|
|
}
|
|
],
|
|
"logging_steps": 500,
|
|
"max_steps": 188253,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"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": 4180672512000000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|