| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00336388865528551, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.72777731057102e-05, | |
| "eval_loss": 7.581191062927246, | |
| "eval_runtime": 709.9549, | |
| "eval_samples_per_second": 8.816, | |
| "eval_steps_per_second": 4.409, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033638886552855103, | |
| "grad_norm": 4.927368640899658, | |
| "learning_rate": 5e-05, | |
| "loss": 7.893, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006727777310571021, | |
| "grad_norm": 7.293655872344971, | |
| "learning_rate": 0.0001, | |
| "loss": 6.5889, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006727777310571021, | |
| "eval_loss": 5.774456024169922, | |
| "eval_runtime": 715.6571, | |
| "eval_samples_per_second": 8.746, | |
| "eval_steps_per_second": 4.374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001009166596585653, | |
| "grad_norm": 7.266585350036621, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.2995, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013455554621142041, | |
| "grad_norm": 6.145931243896484, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013455554621142041, | |
| "eval_loss": 1.6418002843856812, | |
| "eval_runtime": 712.4966, | |
| "eval_samples_per_second": 8.785, | |
| "eval_steps_per_second": 4.393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001681944327642755, | |
| "grad_norm": 4.824899673461914, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3378, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002018333193171306, | |
| "grad_norm": 5.066746234893799, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4699, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002018333193171306, | |
| "eval_loss": 1.2462519407272339, | |
| "eval_runtime": 712.1677, | |
| "eval_samples_per_second": 8.789, | |
| "eval_steps_per_second": 4.395, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002354722058699857, | |
| "grad_norm": 4.359163284301758, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2994, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0026911109242284082, | |
| "grad_norm": 4.64229154586792, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2359, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0026911109242284082, | |
| "eval_loss": 1.182938814163208, | |
| "eval_runtime": 718.2201, | |
| "eval_samples_per_second": 8.715, | |
| "eval_steps_per_second": 4.358, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003027499789756959, | |
| "grad_norm": 4.52047872543335, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1852, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00336388865528551, | |
| "grad_norm": 4.517399311065674, | |
| "learning_rate": 0.0, | |
| "loss": 1.124, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00336388865528551, | |
| "eval_loss": 1.1775221824645996, | |
| "eval_runtime": 713.6593, | |
| "eval_samples_per_second": 8.77, | |
| "eval_steps_per_second": 4.386, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8143746210201600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |