Add files via upload

NisanthSimon · web-flow · commit a9b2cf92f6b2 · 2024-06-01T10:06:24.000+10:00
diff --git a/fmeval/output/Anthropic_Claude_3_Sonnet.json b/fmeval/output/Anthropic_Claude_3_Sonnet.json
@@ -1 +1 @@
-[{"eval_name": "qa_accuracy", "dataset_name": "Anthropic_Claude_3_Sonnet", "dataset_scores": [{"name": "f1_score", "value": 0.5174579733313033}, {"name": "exact_match_score", "value": 0.0}, {"name": "quasi_exact_match_score", "value": 0.0}, {"name": "precision_over_words", "value": 0.4696493506493506}, {"name": "recall_over_words", "value": 0.772}], "prompt_template": null, "category_scores": null, "output_path": "/tmp/eval_results/qa_accuracy_Anthropic_Claude_3_Sonnet.jsonl", "error": null}]
+[{"eval_name": "qa_accuracy", "dataset_name": "Anthropic_Claude_3_Sonnet", "dataset_scores": [{"name": "f1_score", "value": 0.39827261117235935}, {"name": "exact_match_score", "value": 0.0}, {"name": "quasi_exact_match_score", "value": 0.0}, {"name": "precision_over_words", "value": 0.33088046756667394}, {"name": "recall_over_words", "value": 0.6611187320067399}], "prompt_template": null, "category_scores": null, "output_path": "/tmp/eval_results/qa_accuracy_Anthropic_Claude_3_Sonnet.jsonl", "error": null}]
diff --git a/fmeval/output/Meta_Llama3_70b_Instruct.json b/fmeval/output/Meta_Llama3_70b_Instruct.json
@@ -1 +1 @@
-[{"eval_name": "qa_accuracy", "dataset_name": "Meta_Llama3_70b_Instruct", "dataset_scores": [{"name": "f1_score", "value": 0.4541941391941392}, {"name": "exact_match_score", "value": 0.0}, {"name": "quasi_exact_match_score", "value": 0.0}, {"name": "precision_over_words", "value": 0.5398858447488585}, {"name": "recall_over_words", "value": 0.616}], "prompt_template": null, "category_scores": null, "output_path": "/tmp/eval_results/qa_accuracy_Meta_Llama3_70b_Instruct.jsonl", "error": null}]
+[{"eval_name": "qa_accuracy", "dataset_name": "Meta_Llama3_70b_Instruct", "dataset_scores": [{"name": "f1_score", "value": 0.3812911418843109}, {"name": "exact_match_score", "value": 0.0}, {"name": "quasi_exact_match_score", "value": 0.0}, {"name": "precision_over_words", "value": 0.38638235483215594}, {"name": "recall_over_words", "value": 0.5130198855148375}], "prompt_template": null, "category_scores": null, "output_path": "/tmp/eval_results/qa_accuracy_Meta_Llama3_70b_Instruct.jsonl", "error": null}]
diff --git a/fmeval/output/modelEvaluvationPlot.pdf b/fmeval/output/modelEvaluvationPlot.pdf

Original file line number	Diff line number	Diff line change
`@@ -1 +1 @@`
`1`		`-[{"eval_name": "qa_accuracy", "dataset_name": "Anthropic_Claude_3_Sonnet", "dataset_scores": [{"name": "f1_score", "value": 0.5174579733313033}, {"name": "exact_match_score", "value": 0.0}, {"name": "quasi_exact_match_score", "value": 0.0}, {"name": "precision_over_words", "value": 0.4696493506493506}, {"name": "recall_over_words", "value": 0.772}], "prompt_template": null, "category_scores": null, "output_path": "/tmp/eval_results/qa_accuracy_Anthropic_Claude_3_Sonnet.jsonl", "error": null}]`
	`1`	+[{"eval_name": "qa_accuracy", "dataset_name": "Anthropic_Claude_3_Sonnet", "dataset_scores": [{"name": "f1_score", "value": 0.39827261117235935}, {"name": "exact_match_score", "value": 0.0}, {"name": "quasi_exact_match_score", "value": 0.0}, {"name": "precision_over_words", "value": 0.33088046756667394}, {"name": "recall_over_words", "value": 0.6611187320067399}], "prompt_template": null, "category_scores": null, "output_path": "/tmp/eval_results/qa_accuracy_Anthropic_Claude_3_Sonnet.jsonl", "error": null}]