|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0045103964638491725, |
|
"eval_steps": 10, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 9.020792927698345e-05, |
|
"eval_loss": NaN, |
|
"eval_runtime": 153.2984, |
|
"eval_samples_per_second": 30.45, |
|
"eval_steps_per_second": 15.225, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00045103964638491725, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0009020792927698345, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0009020792927698345, |
|
"eval_loss": NaN, |
|
"eval_runtime": 147.1075, |
|
"eval_samples_per_second": 31.732, |
|
"eval_steps_per_second": 15.866, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0013531189391547517, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.001804158585539669, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.001804158585539669, |
|
"eval_loss": NaN, |
|
"eval_runtime": 151.2482, |
|
"eval_samples_per_second": 30.863, |
|
"eval_steps_per_second": 15.432, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0022551982319245862, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.0027062378783095035, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0027062378783095035, |
|
"eval_loss": NaN, |
|
"eval_runtime": 149.8682, |
|
"eval_samples_per_second": 31.147, |
|
"eval_steps_per_second": 15.574, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0031572775246944207, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.003608317171079338, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.003608317171079338, |
|
"eval_loss": NaN, |
|
"eval_runtime": 151.0034, |
|
"eval_samples_per_second": 30.913, |
|
"eval_steps_per_second": 15.457, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.004059356817464255, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.0045103964638491725, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.0045103964638491725, |
|
"eval_loss": NaN, |
|
"eval_runtime": 148.9245, |
|
"eval_samples_per_second": 31.345, |
|
"eval_steps_per_second": 15.672, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"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": 445190819020800.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|