43 lines
1016 B
JSON
43 lines
1016 B
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.926829268292683,
|
|
"eval_steps": 50,
|
|
"global_step": 45,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 2.926829268292683,
|
|
"step": 45,
|
|
"total_flos": 2.2262743935483904e+16,
|
|
"train_loss": 1286.0677951388889,
|
|
"train_runtime": 57.7743,
|
|
"train_samples_per_second": 50.94,
|
|
"train_steps_per_second": 0.779
|
|
}
|
|
],
|
|
"logging_steps": 50,
|
|
"max_steps": 45,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 100,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2.2262743935483904e+16,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|