| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01810774105930285, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036215482118605704, | |
| "grad_norm": 7.147806167602539, | |
| "learning_rate": 1e-05, | |
| "loss": 177.0625, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036215482118605704, | |
| "eval_loss": 11.066532135009766, | |
| "eval_runtime": 16.836, | |
| "eval_samples_per_second": 27.619, | |
| "eval_steps_per_second": 13.839, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007243096423721141, | |
| "grad_norm": 7.007154941558838, | |
| "learning_rate": 2e-05, | |
| "loss": 177.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007243096423721141, | |
| "eval_loss": 11.066532135009766, | |
| "eval_runtime": 0.8952, | |
| "eval_samples_per_second": 519.411, | |
| "eval_steps_per_second": 260.264, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010864644635581712, | |
| "grad_norm": 6.883810520172119, | |
| "learning_rate": 3e-05, | |
| "loss": 177.0625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014486192847442281, | |
| "grad_norm": 6.865726470947266, | |
| "learning_rate": 4e-05, | |
| "loss": 177.125, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014486192847442281, | |
| "eval_loss": 11.065726280212402, | |
| "eval_runtime": 0.9646, | |
| "eval_samples_per_second": 482.076, | |
| "eval_steps_per_second": 241.556, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01810774105930285, | |
| "grad_norm": 6.813530445098877, | |
| "learning_rate": 5e-05, | |
| "loss": 177.0625, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 28576972800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |