|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9939527212754261, |
|
"eval_steps": 500, |
|
"global_step": 113, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 2.2167, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 6.666666666666667e-05, |
|
"loss": 2.2388, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001, |
|
"loss": 2.0807, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00013333333333333334, |
|
"loss": 2.0822, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0001666666666666667, |
|
"loss": 1.9579, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0002, |
|
"loss": 1.959, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019603960396039606, |
|
"loss": 1.9575, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019207920792079208, |
|
"loss": 1.8013, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00018811881188118812, |
|
"loss": 1.8639, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00018415841584158417, |
|
"loss": 1.9356, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00018019801980198022, |
|
"loss": 1.7797, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00017623762376237624, |
|
"loss": 1.8457, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00017227722772277228, |
|
"loss": 1.8558, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00016831683168316833, |
|
"loss": 1.774, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00016435643564356435, |
|
"loss": 1.784, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00016039603960396042, |
|
"loss": 1.7394, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00015643564356435644, |
|
"loss": 1.7558, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001524752475247525, |
|
"loss": 1.7461, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0001485148514851485, |
|
"loss": 1.7995, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00014455445544554456, |
|
"loss": 1.7515, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0001405940594059406, |
|
"loss": 1.8347, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.00013663366336633665, |
|
"loss": 1.8173, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0001326732673267327, |
|
"loss": 1.593, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.00012871287128712872, |
|
"loss": 1.667, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.00012475247524752477, |
|
"loss": 1.8398, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0001207920792079208, |
|
"loss": 1.7201, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.00011683168316831683, |
|
"loss": 1.7293, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.00011287128712871287, |
|
"loss": 1.7615, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00010891089108910893, |
|
"loss": 1.7714, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.00010495049504950496, |
|
"loss": 1.7434, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.00010099009900990099, |
|
"loss": 1.7252, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 9.702970297029703e-05, |
|
"loss": 1.7319, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 9.306930693069307e-05, |
|
"loss": 1.7242, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 8.910891089108912e-05, |
|
"loss": 1.7719, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 8.514851485148515e-05, |
|
"loss": 1.7428, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 8.11881188118812e-05, |
|
"loss": 1.7447, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 7.722772277227723e-05, |
|
"loss": 1.7924, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 7.326732673267327e-05, |
|
"loss": 1.7244, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 6.93069306930693e-05, |
|
"loss": 1.7086, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 6.534653465346535e-05, |
|
"loss": 1.693, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 6.13861386138614e-05, |
|
"loss": 1.7037, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 5.742574257425742e-05, |
|
"loss": 1.7431, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 5.346534653465347e-05, |
|
"loss": 1.8218, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 4.950495049504951e-05, |
|
"loss": 1.7956, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 4.554455445544555e-05, |
|
"loss": 1.7614, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 4.158415841584158e-05, |
|
"loss": 1.7205, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 3.762376237623763e-05, |
|
"loss": 1.753, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 3.366336633663367e-05, |
|
"loss": 1.6786, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 2.9702970297029702e-05, |
|
"loss": 1.849, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 2.5742574257425746e-05, |
|
"loss": 1.7078, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 2.1782178217821783e-05, |
|
"loss": 1.6983, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.7821782178217823e-05, |
|
"loss": 1.729, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.3861386138613863e-05, |
|
"loss": 1.6216, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 9.900990099009901e-06, |
|
"loss": 1.6221, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 5.940594059405941e-06, |
|
"loss": 1.7756, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.9801980198019803e-06, |
|
"loss": 1.679, |
|
"step": 112 |
|
} |
|
], |
|
"logging_steps": 2, |
|
"max_steps": 113, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"total_flos": 2.9899580069904384e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|