|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.0, |
|
"eval_steps": 500, |
|
"global_step": 25012, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.9018471133855755e-05, |
|
"loss": 1.9521, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.801895090356629e-05, |
|
"loss": 0.6834, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.701943067327683e-05, |
|
"loss": 0.55, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.6019910442987366e-05, |
|
"loss": 0.4952, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.502039021269791e-05, |
|
"loss": 0.4475, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.402086998240845e-05, |
|
"loss": 0.4157, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 4.3021349752118984e-05, |
|
"loss": 0.3926, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.2021829521829525e-05, |
|
"loss": 0.3788, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.102230929154006e-05, |
|
"loss": 0.4176, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.00227890612506e-05, |
|
"loss": 0.3467, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 3.902326883096114e-05, |
|
"loss": 0.3491, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 3.802374860067168e-05, |
|
"loss": 0.321, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 3.702422837038222e-05, |
|
"loss": 0.2809, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 3.6024708140092754e-05, |
|
"loss": 0.2329, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 3.5025187909803295e-05, |
|
"loss": 0.2385, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 3.402566767951384e-05, |
|
"loss": 0.2367, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 3.302614744922438e-05, |
|
"loss": 0.232, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 3.202662721893491e-05, |
|
"loss": 0.2325, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 3.102710698864545e-05, |
|
"loss": 0.229, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 3.0027586758355993e-05, |
|
"loss": 0.2213, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 2.9028066528066527e-05, |
|
"loss": 0.2153, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 2.802854629777707e-05, |
|
"loss": 0.2163, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 2.7029026067487607e-05, |
|
"loss": 0.2152, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 2.602950583719815e-05, |
|
"loss": 0.2061, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.5029985606908683e-05, |
|
"loss": 0.205, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 2.4030465376619225e-05, |
|
"loss": 0.1256, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 2.3030945146329763e-05, |
|
"loss": 0.1247, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 2.20314249160403e-05, |
|
"loss": 0.1249, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 2.1033903726211422e-05, |
|
"loss": 0.1263, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 2.0034383495921957e-05, |
|
"loss": 0.1283, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 1.9034863265632495e-05, |
|
"loss": 0.1279, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 1.8035343035343037e-05, |
|
"loss": 0.1247, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 1.7035822805053575e-05, |
|
"loss": 0.1205, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 1.6036302574764113e-05, |
|
"loss": 0.1227, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 1.5036782344474653e-05, |
|
"loss": 0.1173, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 1.4037262114185193e-05, |
|
"loss": 0.1211, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 1.3037741883895729e-05, |
|
"loss": 0.1209, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 1.203822165360627e-05, |
|
"loss": 0.0903, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 1.1038701423316809e-05, |
|
"loss": 0.0639, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 1.0039181193027347e-05, |
|
"loss": 0.0616, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 9.041660003198465e-06, |
|
"loss": 0.0578, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 8.042139772909003e-06, |
|
"loss": 0.0595, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 7.042619542619543e-06, |
|
"loss": 0.0564, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 6.043099312330082e-06, |
|
"loss": 0.0594, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 5.043579082040621e-06, |
|
"loss": 0.0566, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 4.04405885175116e-06, |
|
"loss": 0.0582, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 3.0445386214616987e-06, |
|
"loss": 0.0572, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 2.0450183911722376e-06, |
|
"loss": 0.0561, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 3.92, |
|
"learning_rate": 1.0454981608827763e-06, |
|
"loss": 0.0538, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.797697105389413e-08, |
|
"loss": 0.0546, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"step": 25012, |
|
"total_flos": 5.323473007568486e+16, |
|
"train_loss": 0.23955335338535488, |
|
"train_runtime": 7304.5803, |
|
"train_samples_per_second": 54.783, |
|
"train_steps_per_second": 3.424 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 25012, |
|
"num_train_epochs": 4, |
|
"save_steps": 500, |
|
"total_flos": 5.323473007568486e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|