|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.06730607437321218, |
|
"eval_steps": 500, |
|
"global_step": 400, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0016826518593303045, |
|
"grad_norm": 5.367858933563703, |
|
"learning_rate": 4.9999999999999996e-06, |
|
"loss": 0.9537, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.003365303718660609, |
|
"grad_norm": 9.386746384686745, |
|
"learning_rate": 9.999999999999999e-06, |
|
"loss": 0.943, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.005047955577990914, |
|
"grad_norm": 7.387362447577942, |
|
"learning_rate": 1.5e-05, |
|
"loss": 0.934, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.006730607437321218, |
|
"grad_norm": 6.9256319824932655, |
|
"learning_rate": 1.9999999999999998e-05, |
|
"loss": 0.8376, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.008413259296651522, |
|
"grad_norm": 9.1148382590838, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.8484, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.010095911155981827, |
|
"grad_norm": 3.9989232759892426, |
|
"learning_rate": 3e-05, |
|
"loss": 0.8097, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.011778563015312132, |
|
"grad_norm": 3.892371218590039, |
|
"learning_rate": 2.9999786123888308e-05, |
|
"loss": 0.7811, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.013461214874642436, |
|
"grad_norm": 8.096662196282066, |
|
"learning_rate": 2.9999144501652298e-05, |
|
"loss": 0.7446, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.01514386673397274, |
|
"grad_norm": 1.5769306611206149, |
|
"learning_rate": 2.9998075151588992e-05, |
|
"loss": 0.7258, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.016826518593303044, |
|
"grad_norm": 8.47430485487969, |
|
"learning_rate": 2.999657810419285e-05, |
|
"loss": 0.7052, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.01850917045263335, |
|
"grad_norm": 2.363071299913598, |
|
"learning_rate": 2.999465340215489e-05, |
|
"loss": 0.7657, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.020191822311963654, |
|
"grad_norm": 1.9252385425154874, |
|
"learning_rate": 2.999230110036149e-05, |
|
"loss": 0.7329, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.02187447417129396, |
|
"grad_norm": 8.946028475031488, |
|
"learning_rate": 2.99895212658928e-05, |
|
"loss": 0.7304, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.023557126030624265, |
|
"grad_norm": 6.877609312630206, |
|
"learning_rate": 2.9986313978020846e-05, |
|
"loss": 0.7453, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.02523977788995457, |
|
"grad_norm": 2.5256324882367993, |
|
"learning_rate": 2.9982679328207262e-05, |
|
"loss": 0.7366, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.02692242974928487, |
|
"grad_norm": 2.709550398238738, |
|
"learning_rate": 2.9978617420100692e-05, |
|
"loss": 0.7258, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.028605081608615177, |
|
"grad_norm": 1.543550019689774, |
|
"learning_rate": 2.9974128369533805e-05, |
|
"loss": 0.7372, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.03028773346794548, |
|
"grad_norm": 3.3453966881155504, |
|
"learning_rate": 2.9969212304520034e-05, |
|
"loss": 0.743, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.03197038532727579, |
|
"grad_norm": 1.922001656181265, |
|
"learning_rate": 2.9963869365249895e-05, |
|
"loss": 0.7819, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.03365303718660609, |
|
"grad_norm": 2.0611188483400036, |
|
"learning_rate": 2.995809970408699e-05, |
|
"loss": 0.7155, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.0353356890459364, |
|
"grad_norm": 1.5313041833127259, |
|
"learning_rate": 2.9951903485563685e-05, |
|
"loss": 0.7322, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.0370183409052667, |
|
"grad_norm": 2.0124191694435085, |
|
"learning_rate": 2.99452808863764e-05, |
|
"loss": 0.6759, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.03870099276459701, |
|
"grad_norm": 3.182123324389477, |
|
"learning_rate": 2.993823209538056e-05, |
|
"loss": 0.6953, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.04038364462392731, |
|
"grad_norm": 1.6122782177661379, |
|
"learning_rate": 2.9930757313585238e-05, |
|
"loss": 0.6953, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.04206629648325761, |
|
"grad_norm": 2.2027482596695647, |
|
"learning_rate": 2.9922856754147406e-05, |
|
"loss": 0.7301, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.04374894834258792, |
|
"grad_norm": 2.6782477155989213, |
|
"learning_rate": 2.9914530642365852e-05, |
|
"loss": 0.6891, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.04543160020191822, |
|
"grad_norm": 1.9740401144541417, |
|
"learning_rate": 2.990577921567476e-05, |
|
"loss": 0.7231, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.04711425206124853, |
|
"grad_norm": 1.719874620968932, |
|
"learning_rate": 2.989660272363696e-05, |
|
"loss": 0.7505, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.04879690392057883, |
|
"grad_norm": 1.3138364164203409, |
|
"learning_rate": 2.988700142793676e-05, |
|
"loss": 0.7116, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.05047955577990914, |
|
"grad_norm": 5.853627389344256, |
|
"learning_rate": 2.9876975602372536e-05, |
|
"loss": 0.719, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.05216220763923944, |
|
"grad_norm": 2.347259437170711, |
|
"learning_rate": 2.9866525532848906e-05, |
|
"loss": 0.6803, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.05384485949856974, |
|
"grad_norm": 1.937679220955038, |
|
"learning_rate": 2.9855651517368567e-05, |
|
"loss": 0.7461, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.05552751135790005, |
|
"grad_norm": 1.6661300351569575, |
|
"learning_rate": 2.9844353866023802e-05, |
|
"loss": 0.7472, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.05721016321723035, |
|
"grad_norm": 2.357915869204484, |
|
"learning_rate": 2.9832632900987642e-05, |
|
"loss": 0.7148, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.05889281507656066, |
|
"grad_norm": 4.398815186243292, |
|
"learning_rate": 2.982048895650468e-05, |
|
"loss": 0.6992, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.06057546693589096, |
|
"grad_norm": 12.662682224480092, |
|
"learning_rate": 2.9807922378881537e-05, |
|
"loss": 0.7539, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.06225811879522127, |
|
"grad_norm": 0.8642696401357872, |
|
"learning_rate": 2.979493352647697e-05, |
|
"loss": 0.7212, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.06394077065455157, |
|
"grad_norm": 27.047937858232604, |
|
"learning_rate": 2.9781522769691686e-05, |
|
"loss": 0.722, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.06562342251388188, |
|
"grad_norm": 2.598805292448644, |
|
"learning_rate": 2.9767690490957758e-05, |
|
"loss": 0.7065, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.06730607437321218, |
|
"grad_norm": 1.2314762895092763, |
|
"learning_rate": 2.9753437084727713e-05, |
|
"loss": 0.7498, |
|
"step": 400 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 5943, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 400, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.822380393496576e+18, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|