|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 10050, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.19900497512437812, |
|
"grad_norm": 0.26937374472618103, |
|
"learning_rate": 4.738219895287958e-05, |
|
"loss": 2.1306, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.39800995024875624, |
|
"grad_norm": 0.1997993439435959, |
|
"learning_rate": 4.2146596858638745e-05, |
|
"loss": 0.3628, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.5970149253731343, |
|
"grad_norm": 0.2434607893228531, |
|
"learning_rate": 3.691099476439791e-05, |
|
"loss": 0.354, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.7960199004975125, |
|
"grad_norm": 0.1875876635313034, |
|
"learning_rate": 3.167539267015707e-05, |
|
"loss": 0.3529, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.9950248756218906, |
|
"grad_norm": 0.2847432792186737, |
|
"learning_rate": 2.643979057591623e-05, |
|
"loss": 0.3518, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.1940298507462686, |
|
"grad_norm": 0.21426910161972046, |
|
"learning_rate": 2.1204188481675396e-05, |
|
"loss": 0.3414, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.3930348258706466, |
|
"grad_norm": 0.24933403730392456, |
|
"learning_rate": 1.5968586387434557e-05, |
|
"loss": 0.3444, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.5920398009950247, |
|
"grad_norm": 0.2430945485830307, |
|
"learning_rate": 1.0732984293193717e-05, |
|
"loss": 0.3504, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.7910447761194028, |
|
"grad_norm": 0.2998332381248474, |
|
"learning_rate": 5.49738219895288e-06, |
|
"loss": 0.3344, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.9900497512437811, |
|
"grad_norm": 0.15377995371818542, |
|
"learning_rate": 2.617801047120419e-07, |
|
"loss": 0.3431, |
|
"step": 10000 |
|
} |
|
], |
|
"logging_steps": 1000, |
|
"max_steps": 10050, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 1000, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.88611238559744e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|