| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3989769820971867, |
| "eval_steps": 10, |
| "global_step": 39, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.010230179028132993, |
| "eval_loss": 2.483304738998413, |
| "eval_runtime": 5.4403, |
| "eval_samples_per_second": 7.72, |
| "eval_steps_per_second": 3.86, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.05115089514066496, |
| "grad_norm": 26.666269302368164, |
| "learning_rate": 5e-05, |
| "loss": 10.9039, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.10230179028132992, |
| "grad_norm": 15.509090423583984, |
| "learning_rate": 0.0001, |
| "loss": 10.4859, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10230179028132992, |
| "eval_loss": 2.162769079208374, |
| "eval_runtime": 5.6657, |
| "eval_samples_per_second": 7.413, |
| "eval_steps_per_second": 3.706, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1534526854219949, |
| "grad_norm": 10.331184387207031, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 9.3725, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.20460358056265984, |
| "grad_norm": 7.912665843963623, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 7.717, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.20460358056265984, |
| "eval_loss": 1.9835408926010132, |
| "eval_runtime": 5.7895, |
| "eval_samples_per_second": 7.254, |
| "eval_steps_per_second": 3.627, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2557544757033248, |
| "grad_norm": 4.825455665588379, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 7.8041, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.3069053708439898, |
| "grad_norm": 6.498897075653076, |
| "learning_rate": 5e-05, |
| "loss": 7.2391, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3069053708439898, |
| "eval_loss": 1.9637117385864258, |
| "eval_runtime": 5.8807, |
| "eval_samples_per_second": 7.142, |
| "eval_steps_per_second": 3.571, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.35805626598465473, |
| "grad_norm": 16.6773681640625, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 8.4421, |
| "step": 35 |
| } |
| ], |
| "logging_steps": 5, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1042022588678144e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
