|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.995854444956241, |
|
"eval_steps": 500, |
|
"global_step": 1626, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.09212344541685859, |
|
"grad_norm": 0.12725915014743805, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7623, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.18424689083371718, |
|
"grad_norm": 0.08605462312698364, |
|
"learning_rate": 0.00019950370742676928, |
|
"loss": 0.5035, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.2763703362505758, |
|
"grad_norm": 0.0940171480178833, |
|
"learning_rate": 0.000198019755833442, |
|
"loss": 0.4819, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.36849378166743435, |
|
"grad_norm": 0.08826165646314621, |
|
"learning_rate": 0.00019556287470311418, |
|
"loss": 0.4714, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.460617227084293, |
|
"grad_norm": 0.09107191115617752, |
|
"learning_rate": 0.00019215745067295169, |
|
"loss": 0.4619, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.5527406725011516, |
|
"grad_norm": 0.08955097198486328, |
|
"learning_rate": 0.0001878372854760519, |
|
"loss": 0.4544, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.6448641179180101, |
|
"grad_norm": 0.08695589751005173, |
|
"learning_rate": 0.00018264526043046192, |
|
"loss": 0.4462, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.7369875633348687, |
|
"grad_norm": 0.0795988142490387, |
|
"learning_rate": 0.00017663291080558476, |
|
"loss": 0.4429, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.8291110087517273, |
|
"grad_norm": 0.08313881605863571, |
|
"learning_rate": 0.00016985991429075036, |
|
"loss": 0.4379, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.921234454168586, |
|
"grad_norm": 0.08691557496786118, |
|
"learning_rate": 0.00016239349864333527, |
|
"loss": 0.4373, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.0133578995854444, |
|
"grad_norm": 0.09147489815950394, |
|
"learning_rate": 0.00015430777439602876, |
|
"loss": 0.42, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 1.105481345002303, |
|
"grad_norm": 0.09083960950374603, |
|
"learning_rate": 0.0001456829992466935, |
|
"loss": 0.4143, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.1976047904191618, |
|
"grad_norm": 0.08557241410017014, |
|
"learning_rate": 0.00013660478143237746, |
|
"loss": 0.4146, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 1.2897282358360203, |
|
"grad_norm": 0.0918116420507431, |
|
"learning_rate": 0.000127163229994669, |
|
"loss": 0.4106, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 1.381851681252879, |
|
"grad_norm": 0.09400823712348938, |
|
"learning_rate": 0.00011745206037073426, |
|
"loss": 0.4109, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 1.4739751266697374, |
|
"grad_norm": 0.08512525260448456, |
|
"learning_rate": 0.0001075676641878081, |
|
"loss": 0.408, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.566098572086596, |
|
"grad_norm": 0.0889173299074173, |
|
"learning_rate": 9.760815249421973e-05, |
|
"loss": 0.4046, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 1.6582220175034545, |
|
"grad_norm": 0.08603310585021973, |
|
"learning_rate": 8.76723819236997e-05, |
|
"loss": 0.4044, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 1.7503454629203132, |
|
"grad_norm": 0.09495241940021515, |
|
"learning_rate": 7.785897345911754e-05, |
|
"loss": 0.4006, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 1.842468908337172, |
|
"grad_norm": 0.08712262660264969, |
|
"learning_rate": 6.826533353525428e-05, |
|
"loss": 0.4021, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.9345923537540304, |
|
"grad_norm": 0.09235688298940659, |
|
"learning_rate": 5.8986687196999135e-05, |
|
"loss": 0.4008, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 2.026715799170889, |
|
"grad_norm": 0.08817901462316513, |
|
"learning_rate": 5.0115132909698394e-05, |
|
"loss": 0.3932, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 2.1188392445877477, |
|
"grad_norm": 0.0930236354470253, |
|
"learning_rate": 4.1738728403467974e-05, |
|
"loss": 0.3811, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 2.210962690004606, |
|
"grad_norm": 0.09463441371917725, |
|
"learning_rate": 3.394061662524432e-05, |
|
"loss": 0.3788, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 2.3030861354214647, |
|
"grad_norm": 0.09606461971998215, |
|
"learning_rate": 2.679820047424253e-05, |
|
"loss": 0.3772, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 2.3952095808383236, |
|
"grad_norm": 0.09706277400255203, |
|
"learning_rate": 2.0382374512275893e-05, |
|
"loss": 0.3783, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 2.487333026255182, |
|
"grad_norm": 0.09914683550596237, |
|
"learning_rate": 1.4756821274865695e-05, |
|
"loss": 0.3775, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 2.5794564716720405, |
|
"grad_norm": 0.09216427803039551, |
|
"learning_rate": 9.977379167852763e-06, |
|
"loss": 0.378, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 2.671579917088899, |
|
"grad_norm": 0.09703709185123444, |
|
"learning_rate": 6.091488223675057e-06, |
|
"loss": 0.3779, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 2.763703362505758, |
|
"grad_norm": 0.09853541105985641, |
|
"learning_rate": 3.1377192186521354e-06, |
|
"loss": 0.379, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 2.8558268079226163, |
|
"grad_norm": 0.09633565694093704, |
|
"learning_rate": 1.1453908251886636e-06, |
|
"loss": 0.3777, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 2.947950253339475, |
|
"grad_norm": 0.09454528242349625, |
|
"learning_rate": 1.342785989868922e-07, |
|
"loss": 0.3777, |
|
"step": 1600 |
|
} |
|
], |
|
"logging_steps": 50, |
|
"max_steps": 1626, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.6228755379440845e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|