| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.0, |
| "eval_steps": 500, |
| "global_step": 860, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5331510901451111, |
| "eval_runtime": 0.1576, |
| "eval_samples_per_second": 190.357, |
| "eval_steps_per_second": 12.69, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.585590124130249, |
| "eval_runtime": 0.1565, |
| "eval_samples_per_second": 191.643, |
| "eval_steps_per_second": 12.776, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.6818682551383972, |
| "eval_runtime": 0.1569, |
| "eval_samples_per_second": 191.208, |
| "eval_steps_per_second": 12.747, |
| "step": 129 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.851180911064148, |
| "eval_runtime": 0.1574, |
| "eval_samples_per_second": 190.657, |
| "eval_steps_per_second": 12.71, |
| "step": 172 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.9524082541465759, |
| "eval_runtime": 0.1564, |
| "eval_samples_per_second": 191.765, |
| "eval_steps_per_second": 12.784, |
| "step": 215 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.9880648255348206, |
| "eval_runtime": 0.1566, |
| "eval_samples_per_second": 191.586, |
| "eval_steps_per_second": 12.772, |
| "step": 258 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.9563289284706116, |
| "eval_runtime": 0.1563, |
| "eval_samples_per_second": 191.912, |
| "eval_steps_per_second": 12.794, |
| "step": 301 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 1.0520259141921997, |
| "eval_runtime": 0.1564, |
| "eval_samples_per_second": 191.835, |
| "eval_steps_per_second": 12.789, |
| "step": 344 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 1.055499792098999, |
| "eval_runtime": 0.1564, |
| "eval_samples_per_second": 191.848, |
| "eval_steps_per_second": 12.79, |
| "step": 387 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 1.0590765476226807, |
| "eval_runtime": 0.1566, |
| "eval_samples_per_second": 191.584, |
| "eval_steps_per_second": 12.772, |
| "step": 430 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 1.056971788406372, |
| "eval_runtime": 0.1565, |
| "eval_samples_per_second": 191.75, |
| "eval_steps_per_second": 12.783, |
| "step": 473 |
| }, |
| { |
| "epoch": 11.627906976744185, |
| "grad_norm": 0.0028922727797180414, |
| "learning_rate": 2.0930232558139536e-05, |
| "loss": 0.0228, |
| "step": 500 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 1.0457484722137451, |
| "eval_runtime": 0.1573, |
| "eval_samples_per_second": 190.707, |
| "eval_steps_per_second": 12.714, |
| "step": 516 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 1.104873538017273, |
| "eval_runtime": 0.157, |
| "eval_samples_per_second": 191.099, |
| "eval_steps_per_second": 12.74, |
| "step": 559 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 1.0965876579284668, |
| "eval_runtime": 0.1563, |
| "eval_samples_per_second": 191.96, |
| "eval_steps_per_second": 12.797, |
| "step": 602 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 1.0893380641937256, |
| "eval_runtime": 0.1564, |
| "eval_samples_per_second": 191.875, |
| "eval_steps_per_second": 12.792, |
| "step": 645 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 1.0894120931625366, |
| "eval_runtime": 0.1563, |
| "eval_samples_per_second": 191.989, |
| "eval_steps_per_second": 12.799, |
| "step": 688 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 1.0961824655532837, |
| "eval_runtime": 0.1564, |
| "eval_samples_per_second": 191.817, |
| "eval_steps_per_second": 12.788, |
| "step": 731 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 1.0985208749771118, |
| "eval_runtime": 0.1566, |
| "eval_samples_per_second": 191.532, |
| "eval_steps_per_second": 12.769, |
| "step": 774 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 1.1004067659378052, |
| "eval_runtime": 0.1564, |
| "eval_samples_per_second": 191.788, |
| "eval_steps_per_second": 12.786, |
| "step": 817 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 1.101043701171875, |
| "eval_runtime": 0.1565, |
| "eval_samples_per_second": 191.677, |
| "eval_steps_per_second": 12.778, |
| "step": 860 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 860, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2214650181888000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
