| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00105999576001696, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021199915200339198, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021199915200339198, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.7903, | |
| "eval_samples_per_second": 111.69, | |
| "eval_steps_per_second": 55.873, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042399830400678397, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00042399830400678397, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.3023, | |
| "eval_samples_per_second": 121.884, | |
| "eval_steps_per_second": 60.973, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006359974560101759, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008479966080135679, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008479966080135679, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.3327, | |
| "eval_samples_per_second": 121.658, | |
| "eval_steps_per_second": 60.86, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00105999576001696, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 19885213089792.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |