| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0350938761186173, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "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": 5.1789, | |
| "eval_samples_per_second": 463.422, | |
| "eval_steps_per_second": 57.928, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002105632567117038, | |
| "grad_norm": 0.07256367057561874, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00350938761186173, | |
| "eval_loss": 10.377887725830078, | |
| "eval_runtime": 5.1938, | |
| "eval_samples_per_second": 462.089, | |
| "eval_steps_per_second": 57.761, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004211265134234076, | |
| "grad_norm": 0.06716205924749374, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3798, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0063168977013511145, | |
| "grad_norm": 0.07351335883140564, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3792, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00701877522372346, | |
| "eval_loss": 10.376435279846191, | |
| "eval_runtime": 5.235, | |
| "eval_samples_per_second": 458.451, | |
| "eval_steps_per_second": 57.306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008422530268468151, | |
| "grad_norm": 0.05700007453560829, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 10.3739, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01052816283558519, | |
| "grad_norm": 0.07175807654857635, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3717, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01052816283558519, | |
| "eval_loss": 10.374283790588379, | |
| "eval_runtime": 5.229, | |
| "eval_samples_per_second": 458.977, | |
| "eval_steps_per_second": 57.372, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012633795402702229, | |
| "grad_norm": 0.09788131713867188, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.375, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01403755044744692, | |
| "eval_loss": 10.371757507324219, | |
| "eval_runtime": 5.1826, | |
| "eval_samples_per_second": 463.084, | |
| "eval_steps_per_second": 57.886, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014739427969819266, | |
| "grad_norm": 0.08976900577545166, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 10.3723, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016845060536936303, | |
| "grad_norm": 0.10850024223327637, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 10.3716, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01754693805930865, | |
| "eval_loss": 10.368788719177246, | |
| "eval_runtime": 5.2374, | |
| "eval_samples_per_second": 458.24, | |
| "eval_steps_per_second": 57.28, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018950693104053343, | |
| "grad_norm": 0.12474418431520462, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 10.3719, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02105632567117038, | |
| "grad_norm": 0.1344069540500641, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02105632567117038, | |
| "eval_loss": 10.365849494934082, | |
| "eval_runtime": 5.3008, | |
| "eval_samples_per_second": 452.766, | |
| "eval_steps_per_second": 56.596, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023161958238287417, | |
| "grad_norm": 0.12643229961395264, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 10.3652, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02456571328303211, | |
| "eval_loss": 10.363306999206543, | |
| "eval_runtime": 5.2135, | |
| "eval_samples_per_second": 460.341, | |
| "eval_steps_per_second": 57.543, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.025267590805404458, | |
| "grad_norm": 0.12015967071056366, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 10.366, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.027373223372521495, | |
| "grad_norm": 0.1509571224451065, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 10.3625, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02807510089489384, | |
| "eval_loss": 10.361713409423828, | |
| "eval_runtime": 5.2202, | |
| "eval_samples_per_second": 459.755, | |
| "eval_steps_per_second": 57.469, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.029478855939638532, | |
| "grad_norm": 0.15704847872257233, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3618, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03158448850675557, | |
| "grad_norm": 0.1968822330236435, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3589, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03158448850675557, | |
| "eval_loss": 10.36101245880127, | |
| "eval_runtime": 5.1901, | |
| "eval_samples_per_second": 462.416, | |
| "eval_steps_per_second": 57.802, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.033690121073872606, | |
| "grad_norm": 0.18043430149555206, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 10.3625, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0350938761186173, | |
| "eval_loss": 10.3608980178833, | |
| "eval_runtime": 5.2384, | |
| "eval_samples_per_second": 458.151, | |
| "eval_steps_per_second": 57.269, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5828522016768.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |