67 lines
1.6 KiB
JSON
67 lines
1.6 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.00042842606972634284,
|
||
|
|
"eval_steps": 99999999,
|
||
|
|
"global_step": 2,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.00021421303486317142,
|
||
|
|
"grad_norm": 174.29400634765625,
|
||
|
|
"learning_rate": 5e-05,
|
||
|
|
"loss": 175.3938,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.00021421303486317142,
|
||
|
|
"eval_accuracy": 0.024215843286987115,
|
||
|
|
"eval_loss": 10.354011535644531,
|
||
|
|
"eval_runtime": 152.0177,
|
||
|
|
"eval_samples_per_second": 52.06,
|
||
|
|
"eval_steps_per_second": 6.512,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.00042842606972634284,
|
||
|
|
"grad_norm": 83.63705444335938,
|
||
|
|
"learning_rate": 4.998929106875134e-05,
|
||
|
|
"loss": 164.501,
|
||
|
|
"step": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.00042842606972634284,
|
||
|
|
"eval_accuracy": 0.024217696048750854,
|
||
|
|
"eval_loss": 10.13454532623291,
|
||
|
|
"eval_runtime": 137.1006,
|
||
|
|
"eval_samples_per_second": 57.724,
|
||
|
|
"eval_steps_per_second": 7.221,
|
||
|
|
"step": 2
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 99999999,
|
||
|
|
"max_steps": 4669,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 99999999,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 133781520384000.0,
|
||
|
|
"train_batch_size": 8,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|