Training logs (best)
Browse files
training_logs/per_generator_auroc.tsv
CHANGED
|
@@ -1393,3 +1393,75 @@ step generator AUROC
|
|
| 1393 |
115 mpt 0.9803
|
| 1394 |
115 mpt-chat 0.9988
|
| 1395 |
115 MACRO_AVG 0.9936
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1393 |
115 mpt 0.9803
|
| 1394 |
115 mpt-chat 0.9988
|
| 1395 |
115 MACRO_AVG 0.9936
|
| 1396 |
+
120 chatgpt 0.9987
|
| 1397 |
+
120 cohere 0.9826
|
| 1398 |
+
120 cohere-chat 0.9898
|
| 1399 |
+
120 gpt2 0.9925
|
| 1400 |
+
120 gpt3 0.9976
|
| 1401 |
+
120 gpt4 0.9991
|
| 1402 |
+
120 llama-chat 0.9987
|
| 1403 |
+
120 mistral 0.9886
|
| 1404 |
+
120 mistral-chat 0.9988
|
| 1405 |
+
120 mpt 0.9822
|
| 1406 |
+
120 mpt-chat 0.9985
|
| 1407 |
+
120 MACRO_AVG 0.9934
|
| 1408 |
+
125 chatgpt 0.9974
|
| 1409 |
+
125 cohere 0.9808
|
| 1410 |
+
125 cohere-chat 0.9890
|
| 1411 |
+
125 gpt2 0.9925
|
| 1412 |
+
125 gpt3 0.9965
|
| 1413 |
+
125 gpt4 0.9981
|
| 1414 |
+
125 llama-chat 0.9970
|
| 1415 |
+
125 mistral 0.9881
|
| 1416 |
+
125 mistral-chat 0.9976
|
| 1417 |
+
125 mpt 0.9841
|
| 1418 |
+
125 mpt-chat 0.9976
|
| 1419 |
+
125 MACRO_AVG 0.9926
|
| 1420 |
+
130 chatgpt 0.9931
|
| 1421 |
+
130 cohere 0.9824
|
| 1422 |
+
130 cohere-chat 0.9892
|
| 1423 |
+
130 gpt2 0.9886
|
| 1424 |
+
130 gpt3 0.9932
|
| 1425 |
+
130 gpt4 0.9944
|
| 1426 |
+
130 llama-chat 0.9924
|
| 1427 |
+
130 mistral 0.9852
|
| 1428 |
+
130 mistral-chat 0.9935
|
| 1429 |
+
130 mpt 0.9768
|
| 1430 |
+
130 mpt-chat 0.9944
|
| 1431 |
+
130 MACRO_AVG 0.9894
|
| 1432 |
+
135 chatgpt 0.9945
|
| 1433 |
+
135 cohere 0.9849
|
| 1434 |
+
135 cohere-chat 0.9899
|
| 1435 |
+
135 gpt2 0.9896
|
| 1436 |
+
135 gpt3 0.9941
|
| 1437 |
+
135 gpt4 0.9955
|
| 1438 |
+
135 llama-chat 0.9937
|
| 1439 |
+
135 mistral 0.9865
|
| 1440 |
+
135 mistral-chat 0.9946
|
| 1441 |
+
135 mpt 0.9776
|
| 1442 |
+
135 mpt-chat 0.9955
|
| 1443 |
+
135 MACRO_AVG 0.9906
|
| 1444 |
+
140 chatgpt 0.9957
|
| 1445 |
+
140 cohere 0.9824
|
| 1446 |
+
140 cohere-chat 0.9901
|
| 1447 |
+
140 gpt2 0.9932
|
| 1448 |
+
140 gpt3 0.9954
|
| 1449 |
+
140 gpt4 0.9959
|
| 1450 |
+
140 llama-chat 0.9954
|
| 1451 |
+
140 mistral 0.9889
|
| 1452 |
+
140 mistral-chat 0.9962
|
| 1453 |
+
140 mpt 0.9845
|
| 1454 |
+
140 mpt-chat 0.9970
|
| 1455 |
+
140 MACRO_AVG 0.9922
|
| 1456 |
+
145 chatgpt 0.9989
|
| 1457 |
+
145 cohere 0.9798
|
| 1458 |
+
145 cohere-chat 0.9906
|
| 1459 |
+
145 gpt2 0.9947
|
| 1460 |
+
145 gpt3 0.9976
|
| 1461 |
+
145 gpt4 0.9993
|
| 1462 |
+
145 llama-chat 0.9994
|
| 1463 |
+
145 mistral 0.9905
|
| 1464 |
+
145 mistral-chat 0.9994
|
| 1465 |
+
145 mpt 0.9860
|
| 1466 |
+
145 mpt-chat 0.9992
|
| 1467 |
+
145 MACRO_AVG 0.9941
|