| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 62, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_bleu": 7.201362761069648, |
| "eval_loss": 2.1986560821533203, |
| "eval_runtime": 346.3823, |
| "eval_samples_per_second": 0.716, |
| "eval_steps_per_second": 0.089, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.6129032258064515, |
| "grad_norm": 256526.515625, |
| "learning_rate": 9.46236559139785e-06, |
| "loss": 2.4542, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_bleu": 9.736843493912039, |
| "eval_loss": 2.0518763065338135, |
| "eval_runtime": 251.5342, |
| "eval_samples_per_second": 0.986, |
| "eval_steps_per_second": 0.123, |
| "step": 62 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 93, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1519927594549248.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
