|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.39100684261974583, |
|
"eval_steps": 13, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.007820136852394917, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.007820136852394917, |
|
"eval_loss": NaN, |
|
"eval_runtime": 79.3335, |
|
"eval_samples_per_second": 2.723, |
|
"eval_steps_per_second": 1.361, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.015640273704789834, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.02346041055718475, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.03128054740957967, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.039100684261974585, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0469208211143695, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.05474095796676442, |
|
"grad_norm": NaN, |
|
"learning_rate": 7e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.06256109481915934, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.07038123167155426, |
|
"grad_norm": NaN, |
|
"learning_rate": 9e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.07820136852394917, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.08602150537634409, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.98458666866564e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.093841642228739, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.938441702975689e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.10166177908113393, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.861849601988383e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.10166177908113393, |
|
"eval_loss": NaN, |
|
"eval_runtime": 21.5779, |
|
"eval_samples_per_second": 10.01, |
|
"eval_steps_per_second": 5.005, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.10948191593352884, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.11730205278592376, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.12512218963831867, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.45503262094184e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.13294232649071358, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.263200821770461e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.14076246334310852, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.14858260019550343, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.802029828000156e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.15640273704789834, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.16422287390029325, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.247240241650918e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.17204301075268819, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.938926261462366e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.1798631476050831, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.612492823579745e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.187683284457478, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.269952498697734e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.19550342130987292, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.20332355816226785, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.20332355816226785, |
|
"eval_loss": NaN, |
|
"eval_runtime": 21.5848, |
|
"eval_samples_per_second": 10.007, |
|
"eval_steps_per_second": 5.004, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.21114369501466276, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.167226819279528e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.21896383186705767, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.782172325201155e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.22678396871945258, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.392295478639225e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.23460410557184752, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.24242424242424243, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.607704521360776e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.25024437927663734, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.2178276747988446e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.25806451612903225, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.832773180720475e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.26588465298142716, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.4549150281252636e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.27370478983382207, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.28152492668621704, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7300475013022663e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.28934506353861195, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.3875071764202563e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.29716520039100686, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.30498533724340177, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.7527597583490822e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.30498533724340177, |
|
"eval_loss": NaN, |
|
"eval_runtime": 21.6051, |
|
"eval_samples_per_second": 9.998, |
|
"eval_steps_per_second": 4.999, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.3128054740957967, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.3206256109481916, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1979701719998453e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.3284457478005865, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.3362658846529814, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.367991782295391e-06, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.34408602150537637, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.449673790581611e-06, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.3519061583577713, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.3597262952101662, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.4471741852423237e-06, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.3675464320625611, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3815039801161721e-06, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.375366568914956, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.15582970243117e-07, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.3831867057673509, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.5413331334360182e-07, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.39100684261974583, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"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": 1.102855796686848e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|