FinancialBERT / trainer_state.json
Ahmed HAZOURLI (BFR)
FinancialBERT model
5d43385
raw
history blame
7.68 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8670770831526923,
"global_step": 30000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.9277435764039425e-05,
"loss": 4.5138,
"step": 500
},
{
"epoch": 0.03,
"learning_rate": 4.855487152807885e-05,
"loss": 4.3608,
"step": 1000
},
{
"epoch": 0.04,
"learning_rate": 4.783230729211827e-05,
"loss": 4.031,
"step": 1500
},
{
"epoch": 0.06,
"learning_rate": 4.710974305615769e-05,
"loss": 3.3475,
"step": 2000
},
{
"epoch": 0.07,
"learning_rate": 4.638717882019712e-05,
"loss": 2.8365,
"step": 2500
},
{
"epoch": 0.09,
"learning_rate": 4.5664614584236545e-05,
"loss": 2.5081,
"step": 3000
},
{
"epoch": 0.1,
"learning_rate": 4.494205034827597e-05,
"loss": 2.2906,
"step": 3500
},
{
"epoch": 0.12,
"learning_rate": 4.421948611231539e-05,
"loss": 2.1787,
"step": 4000
},
{
"epoch": 0.13,
"learning_rate": 4.349692187635481e-05,
"loss": 2.1026,
"step": 4500
},
{
"epoch": 0.14,
"learning_rate": 4.277435764039423e-05,
"loss": 2.0387,
"step": 5000
},
{
"epoch": 0.16,
"learning_rate": 4.205179340443365e-05,
"loss": 2.0001,
"step": 5500
},
{
"epoch": 0.17,
"learning_rate": 4.1329229168473074e-05,
"loss": 1.9804,
"step": 6000
},
{
"epoch": 0.19,
"learning_rate": 4.06066649325125e-05,
"loss": 1.951,
"step": 6500
},
{
"epoch": 0.2,
"learning_rate": 3.9884100696551927e-05,
"loss": 1.9113,
"step": 7000
},
{
"epoch": 0.22,
"learning_rate": 3.916153646059135e-05,
"loss": 1.9078,
"step": 7500
},
{
"epoch": 0.23,
"learning_rate": 3.843897222463077e-05,
"loss": 1.8793,
"step": 8000
},
{
"epoch": 0.25,
"learning_rate": 3.7716407988670195e-05,
"loss": 1.8833,
"step": 8500
},
{
"epoch": 0.26,
"learning_rate": 3.699384375270962e-05,
"loss": 1.8618,
"step": 9000
},
{
"epoch": 0.27,
"learning_rate": 3.627127951674904e-05,
"loss": 1.835,
"step": 9500
},
{
"epoch": 0.29,
"learning_rate": 3.554871528078846e-05,
"loss": 1.8187,
"step": 10000
},
{
"epoch": 0.3,
"learning_rate": 3.4826151044827885e-05,
"loss": 1.8097,
"step": 10500
},
{
"epoch": 0.32,
"learning_rate": 3.410358680886731e-05,
"loss": 1.7973,
"step": 11000
},
{
"epoch": 0.33,
"learning_rate": 3.338102257290673e-05,
"loss": 1.8006,
"step": 11500
},
{
"epoch": 0.35,
"learning_rate": 3.265845833694616e-05,
"loss": 1.7698,
"step": 12000
},
{
"epoch": 0.36,
"learning_rate": 3.193589410098558e-05,
"loss": 1.7673,
"step": 12500
},
{
"epoch": 0.38,
"learning_rate": 3.1213329865025005e-05,
"loss": 1.7731,
"step": 13000
},
{
"epoch": 0.39,
"learning_rate": 3.0490765629064428e-05,
"loss": 1.7643,
"step": 13500
},
{
"epoch": 0.4,
"learning_rate": 2.976820139310385e-05,
"loss": 1.7534,
"step": 14000
},
{
"epoch": 0.42,
"learning_rate": 2.9045637157143273e-05,
"loss": 1.7307,
"step": 14500
},
{
"epoch": 0.43,
"learning_rate": 2.8323072921182693e-05,
"loss": 1.7279,
"step": 15000
},
{
"epoch": 0.45,
"learning_rate": 2.7600508685222115e-05,
"loss": 1.7162,
"step": 15500
},
{
"epoch": 0.46,
"learning_rate": 2.6877944449261538e-05,
"loss": 1.7006,
"step": 16000
},
{
"epoch": 0.48,
"learning_rate": 2.615538021330096e-05,
"loss": 1.7176,
"step": 16500
},
{
"epoch": 0.49,
"learning_rate": 2.5432815977340387e-05,
"loss": 1.6928,
"step": 17000
},
{
"epoch": 0.51,
"learning_rate": 2.471025174137981e-05,
"loss": 1.6819,
"step": 17500
},
{
"epoch": 0.52,
"learning_rate": 2.3987687505419232e-05,
"loss": 1.6864,
"step": 18000
},
{
"epoch": 0.53,
"learning_rate": 2.3265123269458655e-05,
"loss": 1.6813,
"step": 18500
},
{
"epoch": 0.55,
"learning_rate": 2.2542559033498077e-05,
"loss": 1.6785,
"step": 19000
},
{
"epoch": 0.56,
"learning_rate": 2.1819994797537503e-05,
"loss": 1.6734,
"step": 19500
},
{
"epoch": 0.58,
"learning_rate": 2.1097430561576926e-05,
"loss": 1.6543,
"step": 20000
},
{
"epoch": 0.59,
"learning_rate": 2.037486632561635e-05,
"loss": 1.6633,
"step": 20500
},
{
"epoch": 0.61,
"learning_rate": 1.965230208965577e-05,
"loss": 1.668,
"step": 21000
},
{
"epoch": 0.62,
"learning_rate": 1.8929737853695194e-05,
"loss": 1.6554,
"step": 21500
},
{
"epoch": 0.64,
"learning_rate": 1.820717361773462e-05,
"loss": 1.6451,
"step": 22000
},
{
"epoch": 0.65,
"learning_rate": 1.748460938177404e-05,
"loss": 1.6347,
"step": 22500
},
{
"epoch": 0.66,
"learning_rate": 1.6762045145813462e-05,
"loss": 1.6288,
"step": 23000
},
{
"epoch": 0.68,
"learning_rate": 1.6039480909852885e-05,
"loss": 1.6476,
"step": 23500
},
{
"epoch": 0.69,
"learning_rate": 1.531691667389231e-05,
"loss": 1.629,
"step": 24000
},
{
"epoch": 0.71,
"learning_rate": 1.4594352437931733e-05,
"loss": 1.6197,
"step": 24500
},
{
"epoch": 0.72,
"learning_rate": 1.3871788201971156e-05,
"loss": 1.6158,
"step": 25000
},
{
"epoch": 0.74,
"learning_rate": 1.3149223966010579e-05,
"loss": 1.6208,
"step": 25500
},
{
"epoch": 0.75,
"learning_rate": 1.2426659730050003e-05,
"loss": 1.6081,
"step": 26000
},
{
"epoch": 0.77,
"learning_rate": 1.1704095494089424e-05,
"loss": 1.6147,
"step": 26500
},
{
"epoch": 0.78,
"learning_rate": 1.0981531258128848e-05,
"loss": 1.6003,
"step": 27000
},
{
"epoch": 0.79,
"learning_rate": 1.0258967022168271e-05,
"loss": 1.5853,
"step": 27500
},
{
"epoch": 0.81,
"learning_rate": 9.536402786207694e-06,
"loss": 1.6039,
"step": 28000
},
{
"epoch": 0.82,
"learning_rate": 8.813838550247118e-06,
"loss": 1.594,
"step": 28500
},
{
"epoch": 0.84,
"learning_rate": 8.091274314286539e-06,
"loss": 1.5874,
"step": 29000
},
{
"epoch": 0.85,
"learning_rate": 7.3687100783259635e-06,
"loss": 1.5707,
"step": 29500
},
{
"epoch": 0.87,
"learning_rate": 6.646145842365387e-06,
"loss": 1.5902,
"step": 30000
}
],
"max_steps": 34599,
"num_train_epochs": 1,
"total_flos": 7.89617673216e+16,
"trial_name": null,
"trial_params": null
}