| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03158448850675557, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007018775223723461, | |
| "eval_loss": 10.378314971923828, | |
| "eval_runtime": 5.2226, | |
| "eval_samples_per_second": 459.545, | |
| "eval_steps_per_second": 57.443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002105632567117038, | |
| "grad_norm": 0.07227218896150589, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00350938761186173, | |
| "eval_loss": 10.377897262573242, | |
| "eval_runtime": 5.2366, | |
| "eval_samples_per_second": 458.312, | |
| "eval_steps_per_second": 57.289, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004211265134234076, | |
| "grad_norm": 0.0682116374373436, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3798, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0063168977013511145, | |
| "grad_norm": 0.077728271484375, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3792, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00701877522372346, | |
| "eval_loss": 10.376399040222168, | |
| "eval_runtime": 5.2739, | |
| "eval_samples_per_second": 455.068, | |
| "eval_steps_per_second": 56.884, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008422530268468151, | |
| "grad_norm": 0.06318044662475586, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 10.3739, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01052816283558519, | |
| "grad_norm": 0.0808248370885849, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3715, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01052816283558519, | |
| "eval_loss": 10.37405014038086, | |
| "eval_runtime": 5.3022, | |
| "eval_samples_per_second": 452.642, | |
| "eval_steps_per_second": 56.58, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012633795402702229, | |
| "grad_norm": 0.11386722326278687, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3747, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01403755044744692, | |
| "eval_loss": 10.371191024780273, | |
| "eval_runtime": 5.2459, | |
| "eval_samples_per_second": 457.498, | |
| "eval_steps_per_second": 57.187, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014739427969819266, | |
| "grad_norm": 0.10688723623752594, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 10.3719, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016845060536936303, | |
| "grad_norm": 0.12940353155136108, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 10.3709, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01754693805930865, | |
| "eval_loss": 10.36774730682373, | |
| "eval_runtime": 5.2455, | |
| "eval_samples_per_second": 457.536, | |
| "eval_steps_per_second": 57.192, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018950693104053343, | |
| "grad_norm": 0.14812299609184265, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 10.371, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02105632567117038, | |
| "grad_norm": 0.16699759662151337, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02105632567117038, | |
| "eval_loss": 10.364386558532715, | |
| "eval_runtime": 5.2274, | |
| "eval_samples_per_second": 459.12, | |
| "eval_steps_per_second": 57.39, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023161958238287417, | |
| "grad_norm": 0.15282683074474335, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 10.3637, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02456571328303211, | |
| "eval_loss": 10.361509323120117, | |
| "eval_runtime": 5.2364, | |
| "eval_samples_per_second": 458.328, | |
| "eval_steps_per_second": 57.291, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.025267590805404458, | |
| "grad_norm": 0.14900287985801697, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 10.3643, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.027373223372521495, | |
| "grad_norm": 0.17812974750995636, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 10.3606, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02807510089489384, | |
| "eval_loss": 10.35970687866211, | |
| "eval_runtime": 5.2357, | |
| "eval_samples_per_second": 458.39, | |
| "eval_steps_per_second": 57.299, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.029478855939638532, | |
| "grad_norm": 0.18757128715515137, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3599, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03158448850675557, | |
| "grad_norm": 0.23149600625038147, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3569, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03158448850675557, | |
| "eval_loss": 10.358962059020996, | |
| "eval_runtime": 5.2602, | |
| "eval_samples_per_second": 456.26, | |
| "eval_steps_per_second": 57.033, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5270768713728.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |