minhy112 commited on
Commit
c9d9086
·
verified ·
1 Parent(s): 5cd356f

Archive verified research artifact: summary.json

Browse files
artifacts/experiments/runs/test-qwen3-scienceqa-s17/summary.json ADDED
@@ -0,0 +1,417 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint": null,
3
+ "dataset": "scienceqa",
4
+ "method": "qwen3",
5
+ "scores": [
6
+ {
7
+ "complete": true,
8
+ "dataset": "scienceqa",
9
+ "evaluator_sha256": "1b95323ffdf36a0e8a8afef28c598e6fd560f6e63aa8d48709e51607e84d6100",
10
+ "groups": {
11
+ "context:image": {
12
+ "accuracy": 69.21241050119332,
13
+ "n": 419
14
+ },
15
+ "context:none": {
16
+ "accuracy": 75.61837455830388,
17
+ "n": 283
18
+ },
19
+ "context:text": {
20
+ "accuracy": 80.48780487804878,
21
+ "n": 410
22
+ },
23
+ "context:text_image": {
24
+ "accuracy": 74.24242424242425,
25
+ "n": 264
26
+ },
27
+ "grade:grade1": {
28
+ "accuracy": 80.0,
29
+ "n": 5
30
+ },
31
+ "grade:grade10": {
32
+ "accuracy": 75.0,
33
+ "n": 20
34
+ },
35
+ "grade:grade11": {
36
+ "accuracy": 78.94736842105263,
37
+ "n": 19
38
+ },
39
+ "grade:grade12": {
40
+ "accuracy": 83.33333333333333,
41
+ "n": 18
42
+ },
43
+ "grade:grade2": {
44
+ "accuracy": 87.87878787878788,
45
+ "n": 66
46
+ },
47
+ "grade:grade3": {
48
+ "accuracy": 80.32786885245902,
49
+ "n": 122
50
+ },
51
+ "grade:grade4": {
52
+ "accuracy": 78.37837837837837,
53
+ "n": 148
54
+ },
55
+ "grade:grade5": {
56
+ "accuracy": 78.04878048780488,
57
+ "n": 123
58
+ },
59
+ "grade:grade6": {
60
+ "accuracy": 69.0,
61
+ "n": 100
62
+ },
63
+ "grade:grade7": {
64
+ "accuracy": 72.22222222222223,
65
+ "n": 108
66
+ },
67
+ "grade:grade8": {
68
+ "accuracy": 59.40594059405941,
69
+ "n": 101
70
+ },
71
+ "grade:grade9": {
72
+ "accuracy": 77.77777777777777,
73
+ "n": 18
74
+ },
75
+ "grade_band:1-6": {
76
+ "accuracy": 78.19148936170212,
77
+ "n": 564
78
+ },
79
+ "grade_band:7-12": {
80
+ "accuracy": 69.36619718309859,
81
+ "n": 284
82
+ },
83
+ "subject:language science": {
84
+ "accuracy": 71.21951219512195,
85
+ "n": 205
86
+ },
87
+ "subject:natural science": {
88
+ "accuracy": 80.76109936575052,
89
+ "n": 473
90
+ },
91
+ "subject:social science": {
92
+ "accuracy": 64.70588235294117,
93
+ "n": 170
94
+ },
95
+ "topic:biology": {
96
+ "accuracy": 85.14285714285714,
97
+ "n": 175
98
+ },
99
+ "topic:capitalization": {
100
+ "accuracy": 100.0,
101
+ "n": 8
102
+ },
103
+ "topic:chemistry": {
104
+ "accuracy": 76.47058823529412,
105
+ "n": 51
106
+ },
107
+ "topic:civics": {
108
+ "accuracy": 100.0,
109
+ "n": 4
110
+ },
111
+ "topic:earth-science": {
112
+ "accuracy": 88.0952380952381,
113
+ "n": 42
114
+ },
115
+ "topic:economics": {
116
+ "accuracy": 88.46153846153847,
117
+ "n": 26
118
+ },
119
+ "topic:figurative-language": {
120
+ "accuracy": 77.58620689655173,
121
+ "n": 58
122
+ },
123
+ "topic:geography": {
124
+ "accuracy": 60.833333333333336,
125
+ "n": 120
126
+ },
127
+ "topic:grammar": {
128
+ "accuracy": 75.0,
129
+ "n": 12
130
+ },
131
+ "topic:phonological-awareness": {
132
+ "accuracy": 50.0,
133
+ "n": 6
134
+ },
135
+ "topic:physics": {
136
+ "accuracy": 67.91044776119404,
137
+ "n": 134
138
+ },
139
+ "topic:pronouns": {
140
+ "accuracy": 100.0,
141
+ "n": 1
142
+ },
143
+ "topic:punctuation": {
144
+ "accuracy": 70.0,
145
+ "n": 20
146
+ },
147
+ "topic:reading-comprehension": {
148
+ "accuracy": 50.0,
149
+ "n": 2
150
+ },
151
+ "topic:reference-skills": {
152
+ "accuracy": 40.0,
153
+ "n": 30
154
+ },
155
+ "topic:science-and-engineering-practices": {
156
+ "accuracy": 94.87179487179488,
157
+ "n": 39
158
+ },
159
+ "topic:units-and-measurement": {
160
+ "accuracy": 90.625,
161
+ "n": 32
162
+ },
163
+ "topic:us-history": {
164
+ "accuracy": 52.63157894736842,
165
+ "n": 19
166
+ },
167
+ "topic:verbs": {
168
+ "accuracy": 100.0,
169
+ "n": 4
170
+ },
171
+ "topic:vocabulary": {
172
+ "accuracy": 62.5,
173
+ "n": 8
174
+ },
175
+ "topic:word-study": {
176
+ "accuracy": 50.0,
177
+ "n": 2
178
+ },
179
+ "topic:world-history": {
180
+ "accuracy": 0.0,
181
+ "n": 1
182
+ },
183
+ "topic:writing-strategies": {
184
+ "accuracy": 79.62962962962963,
185
+ "n": 54
186
+ }
187
+ },
188
+ "input_sha256": "906ff9ed3e02c499fe1f0724b906d80e028c860d1e6827d24ebe6d15910ff554",
189
+ "metric_scale": "0-100",
190
+ "n_expected": 848,
191
+ "n_missing": 0,
192
+ "n_predictions": 848,
193
+ "parse_success_count": 848,
194
+ "prediction_sha256": "846bff60170e1010c252a797f7695d1c4cfd0cdec477419c544abff4225f1a66",
195
+ "protocol_sha256": "ca6b0397b6532489a12ad40a3a1d18408c0f52c45a20c15fae188d3a59eae462",
196
+ "scores": {
197
+ "accuracy": 75.23584905660377
198
+ },
199
+ "split": "val_calibration",
200
+ "status_counts": {
201
+ "ok": 848
202
+ },
203
+ "target_sha256": "a0c00e8c336814ef546a3f098aba5de64ae78aedb24f66571ad1b9a930c0e9b5"
204
+ },
205
+ {
206
+ "complete": true,
207
+ "dataset": "scienceqa",
208
+ "evaluator_sha256": "1b95323ffdf36a0e8a8afef28c598e6fd560f6e63aa8d48709e51607e84d6100",
209
+ "groups": {
210
+ "context:image": {
211
+ "accuracy": 70.25285076846802,
212
+ "n": 2017
213
+ },
214
+ "context:none": {
215
+ "accuracy": 73.86759581881533,
216
+ "n": 1435
217
+ },
218
+ "context:text": {
219
+ "accuracy": 79.66764418377322,
220
+ "n": 2046
221
+ },
222
+ "context:text_image": {
223
+ "accuracy": 73.1901352426412,
224
+ "n": 1257
225
+ },
226
+ "grade:grade1": {
227
+ "accuracy": 76.47058823529412,
228
+ "n": 17
229
+ },
230
+ "grade:grade10": {
231
+ "accuracy": 73.94957983193277,
232
+ "n": 119
233
+ },
234
+ "grade:grade11": {
235
+ "accuracy": 73.33333333333333,
236
+ "n": 105
237
+ },
238
+ "grade:grade12": {
239
+ "accuracy": 72.09302325581395,
240
+ "n": 86
241
+ },
242
+ "grade:grade2": {
243
+ "accuracy": 79.86348122866895,
244
+ "n": 293
245
+ },
246
+ "grade:grade3": {
247
+ "accuracy": 79.62382445141066,
248
+ "n": 638
249
+ },
250
+ "grade:grade4": {
251
+ "accuracy": 81.72362555720653,
252
+ "n": 673
253
+ },
254
+ "grade:grade5": {
255
+ "accuracy": 76.3975155279503,
256
+ "n": 644
257
+ },
258
+ "grade:grade6": {
259
+ "accuracy": 72.98474945533769,
260
+ "n": 459
261
+ },
262
+ "grade:grade7": {
263
+ "accuracy": 70.6713780918728,
264
+ "n": 566
265
+ },
266
+ "grade:grade8": {
267
+ "accuracy": 65.89595375722543,
268
+ "n": 519
269
+ },
270
+ "grade:grade9": {
271
+ "accuracy": 70.49180327868852,
272
+ "n": 122
273
+ },
274
+ "grade_band:1-6": {
275
+ "accuracy": 78.26725403817915,
276
+ "n": 2724
277
+ },
278
+ "grade_band:7-12": {
279
+ "accuracy": 69.54515491100857,
280
+ "n": 1517
281
+ },
282
+ "subject:language science": {
283
+ "accuracy": 72.18181818181819,
284
+ "n": 1100
285
+ },
286
+ "subject:natural science": {
287
+ "accuracy": 78.73001776198934,
288
+ "n": 2252
289
+ },
290
+ "subject:social science": {
291
+ "accuracy": 69.74128233970754,
292
+ "n": 889
293
+ },
294
+ "topic:biology": {
295
+ "accuracy": 84.125,
296
+ "n": 800
297
+ },
298
+ "topic:capitalization": {
299
+ "accuracy": 100.0,
300
+ "n": 33
301
+ },
302
+ "topic:chemistry": {
303
+ "accuracy": 72.30046948356808,
304
+ "n": 213
305
+ },
306
+ "topic:civics": {
307
+ "accuracy": 92.85714285714286,
308
+ "n": 28
309
+ },
310
+ "topic:culture": {
311
+ "accuracy": 50.0,
312
+ "n": 2
313
+ },
314
+ "topic:earth-science": {
315
+ "accuracy": 77.37556561085972,
316
+ "n": 221
317
+ },
318
+ "topic:economics": {
319
+ "accuracy": 93.54838709677419,
320
+ "n": 155
321
+ },
322
+ "topic:figurative-language": {
323
+ "accuracy": 73.03370786516854,
324
+ "n": 267
325
+ },
326
+ "topic:geography": {
327
+ "accuracy": 65.56291390728477,
328
+ "n": 604
329
+ },
330
+ "topic:grammar": {
331
+ "accuracy": 61.42857142857143,
332
+ "n": 70
333
+ },
334
+ "topic:literacy-in-science": {
335
+ "accuracy": 80.0,
336
+ "n": 5
337
+ },
338
+ "topic:phonological-awareness": {
339
+ "accuracy": 52.94117647058823,
340
+ "n": 17
341
+ },
342
+ "topic:physics": {
343
+ "accuracy": 65.31604538087521,
344
+ "n": 617
345
+ },
346
+ "topic:pronouns": {
347
+ "accuracy": 100.0,
348
+ "n": 2
349
+ },
350
+ "topic:punctuation": {
351
+ "accuracy": 75.0,
352
+ "n": 100
353
+ },
354
+ "topic:reading-comprehension": {
355
+ "accuracy": 95.0,
356
+ "n": 20
357
+ },
358
+ "topic:reference-skills": {
359
+ "accuracy": 47.916666666666664,
360
+ "n": 144
361
+ },
362
+ "topic:science-and-engineering-practices": {
363
+ "accuracy": 98.41269841269842,
364
+ "n": 189
365
+ },
366
+ "topic:units-and-measurement": {
367
+ "accuracy": 87.92270531400966,
368
+ "n": 207
369
+ },
370
+ "topic:us-history": {
371
+ "accuracy": 48.888888888888886,
372
+ "n": 90
373
+ },
374
+ "topic:verbs": {
375
+ "accuracy": 92.3076923076923,
376
+ "n": 52
377
+ },
378
+ "topic:vocabulary": {
379
+ "accuracy": 51.61290322580645,
380
+ "n": 31
381
+ },
382
+ "topic:word-study": {
383
+ "accuracy": 66.66666666666667,
384
+ "n": 9
385
+ },
386
+ "topic:world-history": {
387
+ "accuracy": 80.0,
388
+ "n": 10
389
+ },
390
+ "topic:writing-strategies": {
391
+ "accuracy": 78.59154929577464,
392
+ "n": 355
393
+ }
394
+ },
395
+ "input_sha256": "ca4a53185df6168e7b4802446ccc14e6bad7e8254b70808b32f46fc8af9334d7",
396
+ "metric_scale": "0-100",
397
+ "n_expected": 4241,
398
+ "n_missing": 0,
399
+ "n_predictions": 4241,
400
+ "parse_success_count": 4241,
401
+ "prediction_sha256": "ad7ebe7650a2549a878d240ad64ede7b97d77902121bf39eedd5ac3df0045e68",
402
+ "protocol_sha256": "ca6b0397b6532489a12ad40a3a1d18408c0f52c45a20c15fae188d3a59eae462",
403
+ "scores": {
404
+ "accuracy": 75.1473709030889
405
+ },
406
+ "split": "test",
407
+ "status_counts": {
408
+ "ok": 4241
409
+ },
410
+ "target_sha256": "f8ef56c273ad1ecbd7822d4b670663dfd3950f0df42a0c4d50a7c9c73d189f83"
411
+ }
412
+ ],
413
+ "seed": 17,
414
+ "test_feedback_for_training": false,
415
+ "test_used": true,
416
+ "validation_run": "experiments/runs/qwen3-scienceqa-s17"
417
+ }