|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.504424778761062, |
|
"eval_steps": 500, |
|
"global_step": 170, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08849557522123894, |
|
"grad_norm": 0.31797459721565247, |
|
"learning_rate": 9.91645696388268e-05, |
|
"loss": 0.8613, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.17699115044247787, |
|
"grad_norm": 0.7891760468482971, |
|
"learning_rate": 9.665301848904975e-05, |
|
"loss": 0.7427, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.26548672566371684, |
|
"grad_norm": 1.1392697095870972, |
|
"learning_rate": 9.255088935784784e-05, |
|
"loss": 0.7273, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.35398230088495575, |
|
"grad_norm": 0.6338401436805725, |
|
"learning_rate": 8.699803935381485e-05, |
|
"loss": 0.6516, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4424778761061947, |
|
"grad_norm": 1.0638246536254883, |
|
"learning_rate": 8.018378615106108e-05, |
|
"loss": 0.6676, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.5309734513274337, |
|
"grad_norm": 1.0774465799331665, |
|
"learning_rate": 7.23404534331376e-05, |
|
"loss": 0.6645, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.6194690265486725, |
|
"grad_norm": 0.48238104581832886, |
|
"learning_rate": 6.373545009932168e-05, |
|
"loss": 0.6528, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.7079646017699115, |
|
"grad_norm": 0.50417160987854, |
|
"learning_rate": 5.466215328310079e-05, |
|
"loss": 0.6333, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.7964601769911505, |
|
"grad_norm": 1.2405716180801392, |
|
"learning_rate": 4.542990601526297e-05, |
|
"loss": 0.6844, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.8849557522123894, |
|
"grad_norm": 0.8654212951660156, |
|
"learning_rate": 3.635347054911746e-05, |
|
"loss": 0.5696, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.9734513274336283, |
|
"grad_norm": 0.8581073880195618, |
|
"learning_rate": 2.774229692390805e-05, |
|
"loss": 0.5922, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.0619469026548674, |
|
"grad_norm": 0.6241644024848938, |
|
"learning_rate": 1.9889972641710248e-05, |
|
"loss": 0.5009, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.1504424778761062, |
|
"grad_norm": 0.6132310032844543, |
|
"learning_rate": 1.3064213158260386e-05, |
|
"loss": 0.5355, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.238938053097345, |
|
"grad_norm": 0.7218645215034485, |
|
"learning_rate": 7.497734449769639e-06, |
|
"loss": 0.5312, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.3274336283185841, |
|
"grad_norm": 0.5715582370758057, |
|
"learning_rate": 3.380318844467728e-06, |
|
"loss": 0.5281, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.415929203539823, |
|
"grad_norm": 0.8143259882926941, |
|
"learning_rate": 8.523446247096445e-07, |
|
"loss": 0.5436, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.504424778761062, |
|
"grad_norm": 0.8244267106056213, |
|
"learning_rate": 0.0, |
|
"loss": 0.4617, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.504424778761062, |
|
"step": 170, |
|
"total_flos": 3.3074842059669504e+16, |
|
"train_loss": 0.6204830337973202, |
|
"train_runtime": 372.3105, |
|
"train_samples_per_second": 3.626, |
|
"train_steps_per_second": 0.457 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 170, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 3.3074842059669504e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|