das22-44-camembert_finetuned_pero / trainer_state.json
HueyNemud
model data
bdd207b
{
"best_metric": 0.9612490594431903,
"best_model_checkpoint": "/content/drive/MyDrive/SODUCO/article_das_2022/44-camembert_finetuned_pero/checkpoint-2000",
"epoch": 5.319148936170213,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.27,
"eval_accuracy": 0.9608945527236382,
"eval_f1": 0.9189897100093545,
"eval_loss": 0.24732524156570435,
"eval_precision": 0.912332838038633,
"eval_recall": 0.9257444402563136,
"eval_runtime": 2.7834,
"eval_samples_per_second": 239.997,
"eval_steps_per_second": 15.09,
"step": 100
},
{
"epoch": 0.53,
"eval_accuracy": 0.9631434282858571,
"eval_f1": 0.9296359177513677,
"eval_loss": 0.17169421911239624,
"eval_precision": 0.9305135951661632,
"eval_recall": 0.9287598944591029,
"eval_runtime": 2.6347,
"eval_samples_per_second": 253.541,
"eval_steps_per_second": 15.941,
"step": 200
},
{
"epoch": 0.8,
"eval_accuracy": 0.9705147426286856,
"eval_f1": 0.9395872420262664,
"eval_loss": 0.13204523921012878,
"eval_precision": 0.9353754202465446,
"eval_recall": 0.9438371654730494,
"eval_runtime": 2.6,
"eval_samples_per_second": 256.926,
"eval_steps_per_second": 16.154,
"step": 300
},
{
"epoch": 1.06,
"eval_accuracy": 0.9681409295352323,
"eval_f1": 0.9378998870907039,
"eval_loss": 0.1420740932226181,
"eval_precision": 0.936490041337843,
"eval_recall": 0.9393139841688655,
"eval_runtime": 2.565,
"eval_samples_per_second": 260.431,
"eval_steps_per_second": 16.374,
"step": 400
},
{
"epoch": 1.33,
"learning_rate": 9e-05,
"loss": 0.2455,
"step": 500
},
{
"epoch": 1.33,
"eval_accuracy": 0.9758870564717641,
"eval_f1": 0.9526493799323562,
"eval_loss": 0.1057828888297081,
"eval_precision": 0.9497939303109779,
"eval_recall": 0.9555220505088579,
"eval_runtime": 2.6085,
"eval_samples_per_second": 256.084,
"eval_steps_per_second": 16.101,
"step": 500
},
{
"epoch": 1.6,
"eval_accuracy": 0.9731384307846077,
"eval_f1": 0.9493694711086017,
"eval_loss": 0.10737968236207962,
"eval_precision": 0.9481203007518797,
"eval_recall": 0.9506219374293253,
"eval_runtime": 2.5863,
"eval_samples_per_second": 258.283,
"eval_steps_per_second": 16.239,
"step": 600
},
{
"epoch": 1.86,
"eval_accuracy": 0.972888555722139,
"eval_f1": 0.9527573875399962,
"eval_loss": 0.11101129651069641,
"eval_precision": 0.9515037593984963,
"eval_recall": 0.9540143234074633,
"eval_runtime": 2.5978,
"eval_samples_per_second": 257.138,
"eval_steps_per_second": 16.167,
"step": 700
},
{
"epoch": 2.13,
"eval_accuracy": 0.9753873063468266,
"eval_f1": 0.9515583927900865,
"eval_loss": 0.09300221502780914,
"eval_precision": 0.9479985035540591,
"eval_recall": 0.9551451187335093,
"eval_runtime": 2.6079,
"eval_samples_per_second": 256.141,
"eval_steps_per_second": 16.105,
"step": 800
},
{
"epoch": 2.39,
"eval_accuracy": 0.9762618690654673,
"eval_f1": 0.9552914544425579,
"eval_loss": 0.10092608630657196,
"eval_precision": 0.9561933534743202,
"eval_recall": 0.9543912551828119,
"eval_runtime": 2.604,
"eval_samples_per_second": 256.532,
"eval_steps_per_second": 16.129,
"step": 900
},
{
"epoch": 2.66,
"learning_rate": 8e-05,
"loss": 0.0868,
"step": 1000
},
{
"epoch": 2.66,
"eval_accuracy": 0.9766366816591704,
"eval_f1": 0.9565217391304348,
"eval_loss": 0.09077496081590652,
"eval_precision": 0.9552631578947368,
"eval_recall": 0.9577836411609498,
"eval_runtime": 2.6166,
"eval_samples_per_second": 255.294,
"eval_steps_per_second": 16.051,
"step": 1000
},
{
"epoch": 2.93,
"eval_accuracy": 0.9761369315342329,
"eval_f1": 0.9558021440662028,
"eval_loss": 0.09924957156181335,
"eval_precision": 0.9538288288288288,
"eval_recall": 0.9577836411609498,
"eval_runtime": 2.6844,
"eval_samples_per_second": 248.843,
"eval_steps_per_second": 15.646,
"step": 1100
},
{
"epoch": 3.19,
"eval_accuracy": 0.9767616191904048,
"eval_f1": 0.9542975362046267,
"eval_loss": 0.08850151300430298,
"eval_precision": 0.9523273273273273,
"eval_recall": 0.9562759140595553,
"eval_runtime": 2.8038,
"eval_samples_per_second": 238.25,
"eval_steps_per_second": 14.98,
"step": 1200
},
{
"epoch": 3.46,
"eval_accuracy": 0.9770114942528736,
"eval_f1": 0.9576191373139952,
"eval_loss": 0.09413458406925201,
"eval_precision": 0.9570783132530121,
"eval_recall": 0.9581605729362985,
"eval_runtime": 2.631,
"eval_samples_per_second": 253.897,
"eval_steps_per_second": 15.964,
"step": 1300
},
{
"epoch": 3.72,
"eval_accuracy": 0.9758870564717641,
"eval_f1": 0.9575871819038644,
"eval_loss": 0.09968729317188263,
"eval_precision": 0.9577677224736049,
"eval_recall": 0.9574067093856012,
"eval_runtime": 2.6616,
"eval_samples_per_second": 250.976,
"eval_steps_per_second": 15.78,
"step": 1400
},
{
"epoch": 3.99,
"learning_rate": 7e-05,
"loss": 0.056,
"step": 1500
},
{
"epoch": 3.99,
"eval_accuracy": 0.974887556221889,
"eval_f1": 0.9591106086301111,
"eval_loss": 0.10856281220912933,
"eval_precision": 0.9589299171062547,
"eval_recall": 0.9592913682623445,
"eval_runtime": 2.616,
"eval_samples_per_second": 255.356,
"eval_steps_per_second": 16.055,
"step": 1500
},
{
"epoch": 4.26,
"eval_accuracy": 0.9762618690654673,
"eval_f1": 0.9577836411609498,
"eval_loss": 0.10103093087673187,
"eval_precision": 0.9577836411609498,
"eval_recall": 0.9577836411609498,
"eval_runtime": 2.6677,
"eval_samples_per_second": 250.406,
"eval_steps_per_second": 15.744,
"step": 1600
},
{
"epoch": 4.52,
"eval_accuracy": 0.9783858070964517,
"eval_f1": 0.9612198795180723,
"eval_loss": 0.09965386986732483,
"eval_precision": 0.9601353892440767,
"eval_recall": 0.9623068224651338,
"eval_runtime": 2.9477,
"eval_samples_per_second": 226.62,
"eval_steps_per_second": 14.249,
"step": 1700
},
{
"epoch": 4.79,
"eval_accuracy": 0.975512243878061,
"eval_f1": 0.9551957831325302,
"eval_loss": 0.10638727992773056,
"eval_precision": 0.9541180895073336,
"eval_recall": 0.9562759140595553,
"eval_runtime": 2.6219,
"eval_samples_per_second": 254.779,
"eval_steps_per_second": 16.019,
"step": 1800
},
{
"epoch": 5.05,
"eval_accuracy": 0.9757621189405298,
"eval_f1": 0.9559984956750659,
"eval_loss": 0.09631699323654175,
"eval_precision": 0.9538461538461539,
"eval_recall": 0.9581605729362985,
"eval_runtime": 2.6401,
"eval_samples_per_second": 253.021,
"eval_steps_per_second": 15.908,
"step": 1900
},
{
"epoch": 5.32,
"learning_rate": 6e-05,
"loss": 0.04,
"step": 2000
},
{
"epoch": 5.32,
"eval_accuracy": 0.9777611194402799,
"eval_f1": 0.9612490594431903,
"eval_loss": 0.09422445297241211,
"eval_precision": 0.9594442358242583,
"eval_recall": 0.9630606860158312,
"eval_runtime": 2.6383,
"eval_samples_per_second": 253.191,
"eval_steps_per_second": 15.919,
"step": 2000
}
],
"max_steps": 5000,
"num_train_epochs": 14,
"total_flos": 790348180152456.0,
"trial_name": null,
"trial_params": null
}