deprem-ner-mdebertav3 / trainer_state.json
nlztrk's picture
Upload ./ with huggingface_hub (#1)
1535c93
{
"best_metric": 0.24886493384838104,
"best_model_checkpoint": "address_detection_model/checkpoint-480",
"epoch": 13.0,
"global_step": 1248,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.90849413168888,
"eval_f1": 0.59986366734833,
"eval_loss": 0.4046468734741211,
"eval_precision": 0.561941251596424,
"eval_recall": 0.6432748538011696,
"eval_runtime": 0.333,
"eval_samples_per_second": 576.556,
"eval_steps_per_second": 36.035,
"step": 96
},
{
"epoch": 2.0,
"eval_accuracy": 0.9192361249254029,
"eval_f1": 0.693135935397039,
"eval_loss": 0.305729478597641,
"eval_precision": 0.64214463840399,
"eval_recall": 0.7529239766081871,
"eval_runtime": 0.3645,
"eval_samples_per_second": 526.796,
"eval_steps_per_second": 32.925,
"step": 192
},
{
"epoch": 3.0,
"eval_accuracy": 0.9305748955639547,
"eval_f1": 0.7226428079834825,
"eval_loss": 0.25665250420570374,
"eval_precision": 0.682704811443433,
"eval_recall": 0.7675438596491229,
"eval_runtime": 0.3364,
"eval_samples_per_second": 570.696,
"eval_steps_per_second": 35.669,
"step": 288
},
{
"epoch": 4.0,
"eval_accuracy": 0.9289834891585439,
"eval_f1": 0.7248787248787248,
"eval_loss": 0.2604641616344452,
"eval_precision": 0.689064558629776,
"eval_recall": 0.7646198830409356,
"eval_runtime": 0.3089,
"eval_samples_per_second": 621.464,
"eval_steps_per_second": 38.842,
"step": 384
},
{
"epoch": 5.0,
"eval_accuracy": 0.9327630793713945,
"eval_f1": 0.7221067221067221,
"eval_loss": 0.24886493384838104,
"eval_precision": 0.686429512516469,
"eval_recall": 0.7616959064327485,
"eval_runtime": 0.3123,
"eval_samples_per_second": 614.738,
"eval_steps_per_second": 38.421,
"step": 480
},
{
"epoch": 5.21,
"learning_rate": 1.9583333333333333e-05,
"loss": 0.3477,
"step": 500
},
{
"epoch": 6.0,
"eval_accuracy": 0.9341555599761289,
"eval_f1": 0.7311679336558397,
"eval_loss": 0.2547823190689087,
"eval_precision": 0.6933158584534731,
"eval_recall": 0.7733918128654971,
"eval_runtime": 0.3117,
"eval_samples_per_second": 615.908,
"eval_steps_per_second": 38.494,
"step": 576
},
{
"epoch": 7.0,
"eval_accuracy": 0.9307738213646309,
"eval_f1": 0.7350069735006974,
"eval_loss": 0.26613351702690125,
"eval_precision": 0.7026666666666667,
"eval_recall": 0.77046783625731,
"eval_runtime": 0.3453,
"eval_samples_per_second": 555.983,
"eval_steps_per_second": 34.749,
"step": 672
},
{
"epoch": 8.0,
"eval_accuracy": 0.9345534115774816,
"eval_f1": 0.7416201117318436,
"eval_loss": 0.25599348545074463,
"eval_precision": 0.7098930481283422,
"eval_recall": 0.7763157894736842,
"eval_runtime": 0.313,
"eval_samples_per_second": 613.472,
"eval_steps_per_second": 38.342,
"step": 768
},
{
"epoch": 9.0,
"eval_accuracy": 0.9321663019693655,
"eval_f1": 0.7372764786795049,
"eval_loss": 0.27552878856658936,
"eval_precision": 0.6961038961038961,
"eval_recall": 0.783625730994152,
"eval_runtime": 0.3343,
"eval_samples_per_second": 574.283,
"eval_steps_per_second": 35.893,
"step": 864
},
{
"epoch": 10.0,
"eval_accuracy": 0.9299781181619255,
"eval_f1": 0.7323549965059398,
"eval_loss": 0.2917962074279785,
"eval_precision": 0.7014725568942436,
"eval_recall": 0.7660818713450293,
"eval_runtime": 0.329,
"eval_samples_per_second": 583.528,
"eval_steps_per_second": 36.47,
"step": 960
},
{
"epoch": 10.42,
"learning_rate": 9.166666666666668e-06,
"loss": 0.1205,
"step": 1000
},
{
"epoch": 11.0,
"eval_accuracy": 0.9315695245673364,
"eval_f1": 0.7329624478442281,
"eval_loss": 0.28479865193367004,
"eval_precision": 0.6989389920424404,
"eval_recall": 0.77046783625731,
"eval_runtime": 0.3325,
"eval_samples_per_second": 577.484,
"eval_steps_per_second": 36.093,
"step": 1056
},
{
"epoch": 12.0,
"eval_accuracy": 0.9299781181619255,
"eval_f1": 0.7342995169082126,
"eval_loss": 0.3070613443851471,
"eval_precision": 0.6954248366013072,
"eval_recall": 0.7777777777777778,
"eval_runtime": 0.3292,
"eval_samples_per_second": 583.292,
"eval_steps_per_second": 36.456,
"step": 1152
},
{
"epoch": 13.0,
"eval_accuracy": 0.9333598567734235,
"eval_f1": 0.745998608211552,
"eval_loss": 0.2998543679714203,
"eval_precision": 0.7118193891102258,
"eval_recall": 0.783625730994152,
"eval_runtime": 0.3372,
"eval_samples_per_second": 569.432,
"eval_steps_per_second": 35.589,
"step": 1248
}
],
"max_steps": 1440,
"num_train_epochs": 15,
"total_flos": 487199638963260.0,
"trial_name": null,
"trial_params": null
}