|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 8.0, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.978494623655914e-05, |
|
"loss": 2.3806, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.956989247311828e-05, |
|
"loss": 2.2445, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.935483870967742e-05, |
|
"loss": 1.9394, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.9150537634408603e-05, |
|
"loss": 1.7953, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 1.8935483870967742e-05, |
|
"loss": 1.6449, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 1.8720430107526882e-05, |
|
"loss": 1.4618, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 1.8505376344086025e-05, |
|
"loss": 1.2538, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 1.8290322580645165e-05, |
|
"loss": 1.0844, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 1.8075268817204305e-05, |
|
"loss": 0.9909, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 1.7860215053763444e-05, |
|
"loss": 0.9419, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 1.764516129032258e-05, |
|
"loss": 0.8202, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 1.743010752688172e-05, |
|
"loss": 0.7706, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 1.721505376344086e-05, |
|
"loss": 0.7102, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 4.48, |
|
"learning_rate": 1.7e-05, |
|
"loss": 0.6723, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 1.678494623655914e-05, |
|
"loss": 0.6262, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 5.12, |
|
"learning_rate": 1.656989247311828e-05, |
|
"loss": 0.5895, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 5.44, |
|
"learning_rate": 1.6354838709677422e-05, |
|
"loss": 0.5636, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 5.76, |
|
"learning_rate": 1.6139784946236562e-05, |
|
"loss": 0.5095, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"learning_rate": 1.5924731182795702e-05, |
|
"loss": 0.5093, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 6.4, |
|
"learning_rate": 1.570967741935484e-05, |
|
"loss": 0.4729, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 6.72, |
|
"learning_rate": 1.549462365591398e-05, |
|
"loss": 0.4805, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 7.04, |
|
"learning_rate": 1.527956989247312e-05, |
|
"loss": 0.4508, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 7.36, |
|
"learning_rate": 1.5064516129032259e-05, |
|
"loss": 0.4254, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 7.68, |
|
"learning_rate": 1.4849462365591399e-05, |
|
"loss": 0.4104, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 1.4634408602150539e-05, |
|
"loss": 0.4135, |
|
"step": 500 |
|
} |
|
], |
|
"max_steps": 1860, |
|
"num_train_epochs": 30, |
|
"total_flos": 2.5991277871104e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|