| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 5178, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5793742757821553, |
| "grad_norm": 4.606655597686768, |
| "learning_rate": 1.8072614909231365e-05, |
| "loss": 0.3853, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9035830618892509, |
| "eval_f1": 0.7438579904034558, |
| "eval_loss": 0.26155194640159607, |
| "eval_model_preparation_time": 0.0033, |
| "eval_runtime": 4.4748, |
| "eval_samples_per_second": 343.035, |
| "eval_steps_per_second": 21.454, |
| "step": 863 |
| }, |
| { |
| "epoch": 1.1587485515643106, |
| "grad_norm": 4.532162666320801, |
| "learning_rate": 1.6141367323290847e-05, |
| "loss": 0.2576, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.7381228273464657, |
| "grad_norm": 5.762636184692383, |
| "learning_rate": 1.4210119737350329e-05, |
| "loss": 0.2283, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9198697068403909, |
| "eval_f1": 0.7780841955159529, |
| "eval_loss": 0.2665092945098877, |
| "eval_model_preparation_time": 0.0033, |
| "eval_runtime": 4.4634, |
| "eval_samples_per_second": 343.91, |
| "eval_steps_per_second": 21.508, |
| "step": 1726 |
| }, |
| { |
| "epoch": 2.317497103128621, |
| "grad_norm": 0.497444748878479, |
| "learning_rate": 1.2278872151409811e-05, |
| "loss": 0.1931, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.8968713789107765, |
| "grad_norm": 3.7842884063720703, |
| "learning_rate": 1.0347624565469293e-05, |
| "loss": 0.1834, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9146579804560261, |
| "eval_f1": 0.765570564927072, |
| "eval_loss": 0.2603704333305359, |
| "eval_model_preparation_time": 0.0033, |
| "eval_runtime": 4.4661, |
| "eval_samples_per_second": 343.702, |
| "eval_steps_per_second": 21.495, |
| "step": 2589 |
| }, |
| { |
| "epoch": 3.4762456546929315, |
| "grad_norm": 0.3960210680961609, |
| "learning_rate": 8.416376979528776e-06, |
| "loss": 0.1353, |
| "step": 3000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9218241042345277, |
| "eval_f1": 0.7780743111484496, |
| "eval_loss": 0.2716759443283081, |
| "eval_model_preparation_time": 0.0033, |
| "eval_runtime": 4.48, |
| "eval_samples_per_second": 342.633, |
| "eval_steps_per_second": 21.429, |
| "step": 3452 |
| }, |
| { |
| "epoch": 4.055619930475087, |
| "grad_norm": 5.781081199645996, |
| "learning_rate": 6.485129393588259e-06, |
| "loss": 0.1446, |
| "step": 3500 |
| }, |
| { |
| "epoch": 4.634994206257242, |
| "grad_norm": 9.73343563079834, |
| "learning_rate": 4.553881807647741e-06, |
| "loss": 0.1029, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9257328990228013, |
| "eval_f1": 0.7846248698845295, |
| "eval_loss": 0.3429003655910492, |
| "eval_model_preparation_time": 0.0033, |
| "eval_runtime": 4.4592, |
| "eval_samples_per_second": 344.234, |
| "eval_steps_per_second": 21.529, |
| "step": 4315 |
| }, |
| { |
| "epoch": 5.214368482039397, |
| "grad_norm": 0.018824853003025055, |
| "learning_rate": 2.622634221707223e-06, |
| "loss": 0.0826, |
| "step": 4500 |
| }, |
| { |
| "epoch": 5.793742757821553, |
| "grad_norm": 0.07604879140853882, |
| "learning_rate": 6.913866357667054e-07, |
| "loss": 0.0782, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9179153094462541, |
| "eval_f1": 0.7776778508930786, |
| "eval_loss": 0.3899814486503601, |
| "eval_model_preparation_time": 0.0033, |
| "eval_runtime": 4.4603, |
| "eval_samples_per_second": 344.145, |
| "eval_steps_per_second": 21.523, |
| "step": 5178 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5178, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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": 1.0898616579001344e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
