| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028494087476848555, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005698817495369711, | |
| "eval_loss": 0.391124427318573, | |
| "eval_runtime": 17.339, | |
| "eval_samples_per_second": 42.621, | |
| "eval_steps_per_second": 21.339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005698817495369711, | |
| "grad_norm": 0.27616366744041443, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.2667, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007408462743980624, | |
| "eval_loss": 0.1670263260602951, | |
| "eval_runtime": 15.5071, | |
| "eval_samples_per_second": 47.656, | |
| "eval_steps_per_second": 23.86, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011397634990739421, | |
| "grad_norm": 0.21656300127506256, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.1212, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014816925487961248, | |
| "eval_loss": 0.13085024058818817, | |
| "eval_runtime": 15.6024, | |
| "eval_samples_per_second": 47.365, | |
| "eval_steps_per_second": 23.714, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017096452486109134, | |
| "grad_norm": 0.19540159404277802, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.1147, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02222538823194187, | |
| "eval_loss": 0.12224484980106354, | |
| "eval_runtime": 15.5988, | |
| "eval_samples_per_second": 47.375, | |
| "eval_steps_per_second": 23.72, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022795269981478843, | |
| "grad_norm": 0.15403081476688385, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.0953, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028494087476848555, | |
| "grad_norm": 0.3279174864292145, | |
| "learning_rate": 0.0, | |
| "loss": 0.1058, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2261980353134592.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |