52 lines
1.2 KiB
JSON
52 lines
1.2 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.004651162790697674,
|
|
"eval_steps": 500,
|
|
"global_step": 1,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.004651162790697674,
|
|
"grad_norm": 20.563183171334625,
|
|
"learning_rate": 0.0,
|
|
"loss": 0.8406,
|
|
"mean_token_accuracy": 0.824097216129303,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.004651162790697674,
|
|
"step": 1,
|
|
"total_flos": 20312064000.0,
|
|
"train_loss": 0.8405675888061523,
|
|
"train_runtime": 27.3869,
|
|
"train_samples_per_second": 1.168,
|
|
"train_steps_per_second": 0.037
|
|
}
|
|
],
|
|
"logging_steps": 1,
|
|
"max_steps": 1,
|
|
"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": false,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 20312064000.0,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|