Ca-Test
Collection
7 items
•
Updated
TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T trained for one epoch on Ca-lower_labels dataset with r100_O2_F100 WCE Trainer.
"eval_AVGf1": 0.9223289834840258,
"eval_accuracy": 0.9272914758360438,
"eval_diagnosis.avg_words_per_entity": 2.2245762711864407,
"eval_diagnosis.entity_count": 2360,
"eval_diagnosis.f1": 0.8788986878898688,
"eval_diagnosis.precision": 0.8925294888597641,
"eval_diagnosis.recall": 0.8656779661016949,
"eval_diagnosis.word_count": 5250,
"eval_diagnostic.avg_words_per_entity": 1.8057921635434413,
"eval_diagnostic.entity_count": 1761,
"eval_diagnostic.f1": 0.9564464955292761,
"eval_diagnostic.precision": 0.9718640093786636,
"eval_diagnostic.recall": 0.9415105053946621,
"eval_diagnostic.word_count": 3180,
"eval_drug.avg_words_per_entity": 1.0905096660808435,
"eval_drug.entity_count": 1138,
"eval_drug.f1": 0.957187922487607,
"eval_drug.precision": 0.9824236817761333,
"eval_drug.recall": 0.9332161687170475,
"eval_drug.word_count": 1241,
"eval_f1": 0.6559352257940142,
"eval_loss": 0.005444246344268322,
"eval_medical_finding.avg_words_per_entity": 4.152033985581874,
"eval_medical_finding.entity_count": 7768,
"eval_medical_finding.f1": 0.9184775620419185,
"eval_medical_finding.precision": 0.917415874646802,
"eval_medical_finding.recall": 0.9195417095777549,
"eval_medical_finding.word_count": 32253,
"eval_model_preparation_time": 0.0,
"eval_precision": 0.5121161950632149,
"eval_recall": 0.9120761292052004,
"eval_runtime": 311.6758,
"eval_samples_per_second": 26.252,
"eval_steps_per_second": 6.565,
"eval_therapy.avg_words_per_entity": 3.6986807387862797,
"eval_therapy.entity_count": 1895,
"eval_therapy.f1": 0.9006342494714588,
"eval_therapy.precision": 0.9020645844362096,
"eval_therapy.recall": 0.8992084432717679,
"eval_therapy.word_count": 7009,
"test_AVGf1": 0.8991844061835648,
"test_accuracy": 0.9393252816821795,
"test_diagnosis.avg_words_per_entity": 2.540414878397711,
"test_diagnosis.entity_count": 2796,
"test_diagnosis.f1": 0.7905454545454544,
"test_diagnosis.precision": 0.8039940828402367,
"test_diagnosis.recall": 0.7775393419170243,
"test_diagnosis.word_count": 7103,
"test_diagnostic.avg_words_per_entity": 1.9772727272727273,
"test_diagnostic.entity_count": 2156,
"test_diagnostic.f1": 0.9380572501173158,
"test_diagnostic.precision": 0.9491927825261158,
"test_diagnostic.recall": 0.9271799628942486,
"test_diagnostic.word_count": 4263,
"test_drug.avg_words_per_entity": 1.033793103448276,
"test_drug.entity_count": 1450,
"test_drug.f1": 0.9711267605633803,
"test_drug.precision": 0.9920863309352518,
"test_drug.recall": 0.9510344827586207,
"test_drug.word_count": 1499,
"test_f1": 0.6601992430504198,
"test_loss": 0.005932590924203396,
"test_medical_finding.avg_words_per_entity": 4.681758451797873,
"test_medical_finding.entity_count": 8371,
"test_medical_finding.f1": 0.900312076782665,
"test_medical_finding.precision": 0.8877148165350673,
"test_medical_finding.recall": 0.9132720105124835,
"test_medical_finding.word_count": 39191,
"test_model_preparation_time": 0.0,
"test_precision": 0.5235630994273097,
"test_recall": 0.8933364728043325,
"test_runtime": 357.9554,
"test_samples_per_second": 26.509,
"test_steps_per_second": 6.629,
"test_therapy.avg_words_per_entity": 3.9787810383747177,
"test_therapy.entity_count": 2215,
"test_therapy.f1": 0.8958804889090086,
"test_therapy.precision": 0.8983204720835225,
"test_therapy.recall": 0.8934537246049662,
"test_therapy.word_count": 8813