58 lines
1.3 KiB
JSON
58 lines
1.3 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.0,
|
|
"eval_steps": 500,
|
|
"global_step": 125,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.4,
|
|
"grad_norm": 0.7066887319026077,
|
|
"learning_rate": 6.958301789735853e-06,
|
|
"loss": 0.369345588684082,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"grad_norm": 0.6385046705268815,
|
|
"learning_rate": 1.0966307441413598e-06,
|
|
"loss": 0.2866981887817383,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"step": 125,
|
|
"total_flos": 2603673845760.0,
|
|
"train_loss": 0.31614510726928713,
|
|
"train_runtime": 3914.9332,
|
|
"train_samples_per_second": 2.043,
|
|
"train_steps_per_second": 0.032
|
|
}
|
|
],
|
|
"logging_steps": 50,
|
|
"max_steps": 125,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2603673845760.0,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|