|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.16059957173447537, |
|
"eval_steps": 5, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0032119914346895075, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0032119914346895075, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.9097, |
|
"eval_samples_per_second": 9.631, |
|
"eval_steps_per_second": 2.42, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.006423982869379015, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.009635974304068522, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.01284796573875803, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.016059957173447537, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.016059957173447537, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1506, |
|
"eval_samples_per_second": 9.813, |
|
"eval_steps_per_second": 2.466, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.019271948608137045, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.022483940042826552, |
|
"grad_norm": NaN, |
|
"learning_rate": 7e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.02569593147751606, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.028907922912205567, |
|
"grad_norm": NaN, |
|
"learning_rate": 9e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.032119914346895075, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.032119914346895075, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1974, |
|
"eval_samples_per_second": 9.802, |
|
"eval_steps_per_second": 2.463, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.035331905781584586, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.98458666866564e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.03854389721627409, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.938441702975689e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0417558886509636, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.861849601988383e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.044967880085653104, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.048179871520342615, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.048179871520342615, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1829, |
|
"eval_samples_per_second": 9.805, |
|
"eval_steps_per_second": 2.464, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.05139186295503212, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.45503262094184e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.05460385438972163, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.263200821770461e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.057815845824411134, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.061027837259100645, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.802029828000156e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.06423982869379015, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06423982869379015, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1855, |
|
"eval_samples_per_second": 9.805, |
|
"eval_steps_per_second": 2.464, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06745182012847965, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.247240241650918e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.07066381156316917, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.938926261462366e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.07387580299785867, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.612492823579745e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.07708779443254818, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.269952498697734e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.08029978586723768, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.08029978586723768, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.2145, |
|
"eval_samples_per_second": 9.797, |
|
"eval_steps_per_second": 2.462, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.0835117773019272, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.0867237687366167, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.167226819279528e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.08993576017130621, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.782172325201155e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.09314775160599571, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.392295478639225e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.09635974304068523, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.09635974304068523, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1401, |
|
"eval_samples_per_second": 9.816, |
|
"eval_steps_per_second": 2.466, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.09957173447537473, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.607704521360776e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.10278372591006424, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.2178276747988446e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.10599571734475374, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.832773180720475e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.10920770877944326, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.4549150281252636e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.11241970021413276, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.11241970021413276, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1385, |
|
"eval_samples_per_second": 9.816, |
|
"eval_steps_per_second": 2.466, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.11563169164882227, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7300475013022663e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.11884368308351177, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.3875071764202563e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.12205567451820129, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.1252676659528908, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.7527597583490822e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.1284796573875803, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.1284796573875803, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1276, |
|
"eval_samples_per_second": 9.819, |
|
"eval_steps_per_second": 2.467, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.1316916488222698, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1979701719998453e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.1349036402569593, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.1381156316916488, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.367991782295391e-06, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.14132762312633834, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.449673790581611e-06, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.14453961456102785, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.14453961456102785, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1383, |
|
"eval_samples_per_second": 9.816, |
|
"eval_steps_per_second": 2.466, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.14775160599571735, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.4471741852423237e-06, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.15096359743040685, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3815039801161721e-06, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.15417558886509636, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.15582970243117e-07, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.15738758029978586, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.5413331334360182e-07, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.16059957173447537, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.16059957173447537, |
|
"eval_loss": NaN, |
|
"eval_runtime": 40.1334, |
|
"eval_samples_per_second": 9.817, |
|
"eval_steps_per_second": 2.467, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.0644164762507674e+17, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|