|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.07883326763894363, |
|
"eval_steps": 500, |
|
"global_step": 200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.999997870262096e-05, |
|
"loss": 2.714, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.999991481057455e-05, |
|
"loss": 2.7679, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.9999808324132915e-05, |
|
"loss": 2.6887, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.999965924374964e-05, |
|
"loss": 2.6986, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.999946757005972e-05, |
|
"loss": 2.7536, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.9999233303879592e-05, |
|
"loss": 2.7516, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.99989564462071e-05, |
|
"loss": 2.6283, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.999863699822152e-05, |
|
"loss": 2.708, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.9998274961283523e-05, |
|
"loss": 2.6932, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.9997870336935207e-05, |
|
"loss": 2.6321, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.9997423126900056e-05, |
|
"loss": 2.7129, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.9996933333082945e-05, |
|
"loss": 2.6179, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.9996400957570148e-05, |
|
"loss": 2.6052, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.99958260026293e-05, |
|
"loss": 2.7054, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.9995208470709405e-05, |
|
"loss": 2.6568, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.9994548364440836e-05, |
|
"loss": 2.6436, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.999384568663529e-05, |
|
"loss": 2.7091, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.9993100440285805e-05, |
|
"loss": 2.5557, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.999231262856675e-05, |
|
"loss": 2.5945, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.999148225483378e-05, |
|
"loss": 2.4729, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.9990609322623854e-05, |
|
"loss": 2.6724, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.9989693835655205e-05, |
|
"loss": 2.5272, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.9988735797827336e-05, |
|
"loss": 2.6145, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.9987735213220975e-05, |
|
"loss": 2.6772, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.9986692086098095e-05, |
|
"loss": 2.6388, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.998560642090187e-05, |
|
"loss": 2.4973, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.998447822225666e-05, |
|
"loss": 2.5338, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.9983307494968e-05, |
|
"loss": 2.6469, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.9982094244022582e-05, |
|
"loss": 2.6008, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.9980838474588214e-05, |
|
"loss": 2.5936, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.9979540192013814e-05, |
|
"loss": 2.5862, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.997819940182939e-05, |
|
"loss": 2.568, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.9976816109746e-05, |
|
"loss": 2.5343, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.9975390321655745e-05, |
|
"loss": 2.5575, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.9973922043631737e-05, |
|
"loss": 2.5399, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.9972411281928068e-05, |
|
"loss": 2.6394, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.9970858042979794e-05, |
|
"loss": 2.5378, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.9969262333402893e-05, |
|
"loss": 2.5373, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.9967624159994262e-05, |
|
"loss": 2.5414, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.9965943529731646e-05, |
|
"loss": 2.5606, |
|
"step": 200 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 7611, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 2733452333875200.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|