|
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.0,
|
|
"eval_steps": 100,
|
|
"global_step": 145,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.6896551724137931,
|
|
"eval_loss": 21.916179656982422,
|
|
"eval_runtime": 84.3206,
|
|
"eval_samples_per_second": 28.653,
|
|
"eval_steps_per_second": 3.582,
|
|
"eval_wer": 1.0002954209748893,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"step": 145,
|
|
"total_flos": 6.105598680744346e+17,
|
|
"train_loss": 18.507504377693966,
|
|
"train_runtime": 329.6848,
|
|
"train_samples_per_second": 14.044,
|
|
"train_steps_per_second": 0.44
|
|
}
|
|
],
|
|
"logging_steps": 500,
|
|
"max_steps": 145,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 400,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 6.105598680744346e+17,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|
|
|