LLDDSS commited on
Commit
11b82ca
·
verified ·
1 Parent(s): d9fd354

Upload folder using huggingface_hub (part 6)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/metrics_shard3.json +26 -0
  2. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions.jsonl +0 -0
  3. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions_shard0.jsonl +0 -0
  4. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions_shard1.jsonl +0 -0
  5. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions_shard2.jsonl +0 -0
  6. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions_shard3.jsonl +0 -0
  7. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics.json +25 -0
  8. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics_shard0.json +26 -0
  9. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics_shard1.json +26 -0
  10. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics_shard2.json +26 -0
  11. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics_shard3.json +26 -0
  12. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions.jsonl +0 -0
  13. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions_shard0.jsonl +0 -0
  14. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions_shard1.jsonl +0 -0
  15. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions_shard2.jsonl +0 -0
  16. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions_shard3.jsonl +0 -0
  17. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics.json +25 -0
  18. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics_shard0.json +26 -0
  19. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics_shard1.json +26 -0
  20. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics_shard2.json +26 -0
  21. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics_shard3.json +26 -0
  22. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions.jsonl +0 -0
  23. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions_shard0.jsonl +0 -0
  24. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions_shard1.jsonl +0 -0
  25. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions_shard2.jsonl +0 -0
  26. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions_shard3.jsonl +0 -0
  27. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics.json +25 -0
  28. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics_shard0.json +26 -0
  29. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics_shard1.json +26 -0
  30. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics_shard2.json +26 -0
  31. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics_shard3.json +26 -0
  32. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions.jsonl +0 -0
  33. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions_shard0.jsonl +0 -0
  34. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions_shard1.jsonl +0 -0
  35. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions_shard2.jsonl +0 -0
  36. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions_shard3.jsonl +0 -0
  37. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics.json +25 -0
  38. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics_shard0.json +26 -0
  39. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics_shard1.json +26 -0
  40. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics_shard2.json +26 -0
  41. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics_shard3.json +26 -0
  42. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions.jsonl +0 -0
  43. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions_shard0.jsonl +0 -0
  44. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions_shard1.jsonl +0 -0
  45. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions_shard2.jsonl +0 -0
  46. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions_shard3.jsonl +0 -0
  47. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.15/metrics.json +25 -0
  48. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.15/metrics_shard0.json +26 -0
  49. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.15/metrics_shard1.json +26 -0
  50. result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.15/metrics_shard2.json +26 -0
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/metrics_shard3.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 1,
5
+ "task": "youtube_level1",
6
+ "baseline": "0.20",
7
+ "scoring": "generate",
8
+ "num_samples": 205,
9
+ "accuracy": 0.3121951219512195,
10
+ "num_correct": 64,
11
+ "num_unparsed": 105,
12
+ "unparsed_rate": 0.5121951219512195,
13
+ "answer_instruction": "Answer with a single letter: A, B, C, or D.",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 3,
24
+ "elapsed_seconds": 48.80776047706604,
25
+ "samples_per_second": 4.200151738089399
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions_shard0.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions_shard1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions_shard2.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.20/predictions_shard3.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 1,
5
+ "task": "youtube_level1",
6
+ "baseline": "0.25",
7
+ "scoring": "generate",
8
+ "num_samples": 821,
9
+ "accuracy": 0.2935444579780755,
10
+ "num_correct": 241,
11
+ "num_unparsed": 436,
12
+ "unparsed_rate": 0.5310596833130329,
13
+ "answer_instruction": "Answer with a single letter: A, B, C, or D.",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "elapsed_seconds": 50.188525676727295,
24
+ "samples_per_second": 16.35832073028402
25
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics_shard0.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 1,
5
+ "task": "youtube_level1",
6
+ "baseline": "0.25",
7
+ "scoring": "generate",
8
+ "num_samples": 206,
9
+ "accuracy": 0.2621359223300971,
10
+ "num_correct": 54,
11
+ "num_unparsed": 118,
12
+ "unparsed_rate": 0.5728155339805825,
13
+ "answer_instruction": "Answer with a single letter: A, B, C, or D.",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 0,
24
+ "elapsed_seconds": 49.063581466674805,
25
+ "samples_per_second": 4.19863356571147
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics_shard1.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 1,
5
+ "task": "youtube_level1",
6
+ "baseline": "0.25",
7
+ "scoring": "generate",
8
+ "num_samples": 205,
9
+ "accuracy": 0.2682926829268293,
10
+ "num_correct": 55,
11
+ "num_unparsed": 109,
12
+ "unparsed_rate": 0.5317073170731708,
13
+ "answer_instruction": "Answer with a single letter: A, B, C, or D.",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 1,
24
+ "elapsed_seconds": 48.47278904914856,
25
+ "samples_per_second": 4.229176905668499
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics_shard2.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 1,
5
+ "task": "youtube_level1",
6
+ "baseline": "0.25",
7
+ "scoring": "generate",
8
+ "num_samples": 205,
9
+ "accuracy": 0.2975609756097561,
10
+ "num_correct": 61,
11
+ "num_unparsed": 109,
12
+ "unparsed_rate": 0.5317073170731708,
13
+ "answer_instruction": "Answer with a single letter: A, B, C, or D.",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 2,
24
+ "elapsed_seconds": 50.188525676727295,
25
+ "samples_per_second": 4.084598964321833
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/metrics_shard3.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 1,
5
+ "task": "youtube_level1",
6
+ "baseline": "0.25",
7
+ "scoring": "generate",
8
+ "num_samples": 205,
9
+ "accuracy": 0.3463414634146341,
10
+ "num_correct": 71,
11
+ "num_unparsed": 100,
12
+ "unparsed_rate": 0.4878048780487805,
13
+ "answer_instruction": "Answer with a single letter: A, B, C, or D.",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 3,
24
+ "elapsed_seconds": 49.0367591381073,
25
+ "samples_per_second": 4.180537286785966
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions_shard0.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions_shard1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions_shard2.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level1/baseline_0.25/predictions_shard3.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.00",
7
+ "scoring": "generate",
8
+ "num_samples": 764,
9
+ "accuracy": 0.03795811518324607,
10
+ "num_correct": 29,
11
+ "num_unparsed": 672,
12
+ "unparsed_rate": 0.8795811518324608,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "elapsed_seconds": 49.23310446739197,
24
+ "samples_per_second": 15.518013910863814
25
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics_shard0.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.00",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.02617801047120419,
10
+ "num_correct": 5,
11
+ "num_unparsed": 167,
12
+ "unparsed_rate": 0.8743455497382199,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 0,
24
+ "elapsed_seconds": 47.68956732749939,
25
+ "samples_per_second": 4.005068837977547
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics_shard1.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.00",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.05235602094240838,
10
+ "num_correct": 10,
11
+ "num_unparsed": 166,
12
+ "unparsed_rate": 0.8691099476439791,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 1,
24
+ "elapsed_seconds": 47.42433047294617,
25
+ "samples_per_second": 4.027468560867896
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics_shard2.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.00",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.05235602094240838,
10
+ "num_correct": 10,
11
+ "num_unparsed": 168,
12
+ "unparsed_rate": 0.8795811518324608,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 2,
24
+ "elapsed_seconds": 49.23310446739197,
25
+ "samples_per_second": 3.8795034777159536
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/metrics_shard3.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.00",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.020942408376963352,
10
+ "num_correct": 4,
11
+ "num_unparsed": 171,
12
+ "unparsed_rate": 0.8952879581151832,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 3,
24
+ "elapsed_seconds": 47.84153366088867,
25
+ "samples_per_second": 3.992346929215315
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions_shard0.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions_shard1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions_shard2.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.00/predictions_shard3.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.05",
7
+ "scoring": "generate",
8
+ "num_samples": 764,
9
+ "accuracy": 0.03795811518324607,
10
+ "num_correct": 29,
11
+ "num_unparsed": 671,
12
+ "unparsed_rate": 0.8782722513089005,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "elapsed_seconds": 49.33743500709534,
24
+ "samples_per_second": 15.485199015516864
25
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics_shard0.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.05",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.015706806282722512,
10
+ "num_correct": 3,
11
+ "num_unparsed": 169,
12
+ "unparsed_rate": 0.8848167539267016,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 0,
24
+ "elapsed_seconds": 48.017895221710205,
25
+ "samples_per_second": 3.9776837180827465
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics_shard1.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.05",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.05235602094240838,
10
+ "num_correct": 10,
11
+ "num_unparsed": 167,
12
+ "unparsed_rate": 0.8743455497382199,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 1,
24
+ "elapsed_seconds": 47.40277671813965,
25
+ "samples_per_second": 4.029299826373038
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics_shard2.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.05",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.041884816753926704,
10
+ "num_correct": 8,
11
+ "num_unparsed": 170,
12
+ "unparsed_rate": 0.8900523560209425,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 2,
24
+ "elapsed_seconds": 49.33743500709534,
25
+ "samples_per_second": 3.871299753879216
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/metrics_shard3.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.05",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.041884816753926704,
10
+ "num_correct": 8,
11
+ "num_unparsed": 165,
12
+ "unparsed_rate": 0.8638743455497382,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 3,
24
+ "elapsed_seconds": 48.098326444625854,
25
+ "samples_per_second": 3.9710321360118948
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions_shard0.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions_shard1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions_shard2.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.05/predictions_shard3.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.10",
7
+ "scoring": "generate",
8
+ "num_samples": 764,
9
+ "accuracy": 0.030104712041884817,
10
+ "num_correct": 23,
11
+ "num_unparsed": 675,
12
+ "unparsed_rate": 0.8835078534031413,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "elapsed_seconds": 49.15604829788208,
24
+ "samples_per_second": 15.542339680566174
25
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics_shard0.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.10",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.020942408376963352,
10
+ "num_correct": 4,
11
+ "num_unparsed": 171,
12
+ "unparsed_rate": 0.8952879581151832,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 0,
24
+ "elapsed_seconds": 47.62239384651184,
25
+ "samples_per_second": 4.010718163719315
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics_shard1.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.10",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.04712041884816754,
10
+ "num_correct": 9,
11
+ "num_unparsed": 165,
12
+ "unparsed_rate": 0.8638743455497382,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 1,
24
+ "elapsed_seconds": 47.39005398750305,
25
+ "samples_per_second": 4.030381565937179
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics_shard2.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.10",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.02617801047120419,
10
+ "num_correct": 5,
11
+ "num_unparsed": 172,
12
+ "unparsed_rate": 0.900523560209424,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 2,
24
+ "elapsed_seconds": 49.15604829788208,
25
+ "samples_per_second": 3.8855849201415436
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/metrics_shard3.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.10",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.02617801047120419,
10
+ "num_correct": 5,
11
+ "num_unparsed": 167,
12
+ "unparsed_rate": 0.8743455497382199,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 3,
24
+ "elapsed_seconds": 47.86641883850098,
25
+ "samples_per_second": 3.9902713558836505
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions_shard0.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions_shard1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions_shard2.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.10/predictions_shard3.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.15/metrics.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.15",
7
+ "scoring": "generate",
8
+ "num_samples": 764,
9
+ "accuracy": 0.034031413612565446,
10
+ "num_correct": 26,
11
+ "num_unparsed": 669,
12
+ "unparsed_rate": 0.8756544502617801,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "elapsed_seconds": 49.25848054885864,
24
+ "samples_per_second": 15.51001962478728
25
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.15/metrics_shard0.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.15",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.02617801047120419,
10
+ "num_correct": 5,
11
+ "num_unparsed": 167,
12
+ "unparsed_rate": 0.8743455497382199,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 0,
24
+ "elapsed_seconds": 47.783774614334106,
25
+ "samples_per_second": 3.997172712737183
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.15/metrics_shard1.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.15",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.04712041884816754,
10
+ "num_correct": 9,
11
+ "num_unparsed": 166,
12
+ "unparsed_rate": 0.8691099476439791,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 1,
24
+ "elapsed_seconds": 47.50464963912964,
25
+ "samples_per_second": 4.020659060764298
26
+ }
result/_archive_narrated_prompt/Qwen_Qwen3.5-4B/youtube_level2/baseline_0.15/metrics_shard2.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "Qwen/Qwen3.5-4B",
3
+ "dataset": "youtube",
4
+ "level": 2,
5
+ "task": "youtube_level2",
6
+ "baseline": "0.15",
7
+ "scoring": "generate",
8
+ "num_samples": 191,
9
+ "accuracy": 0.031413612565445025,
10
+ "num_correct": 6,
11
+ "num_unparsed": 168,
12
+ "unparsed_rate": 0.8795811518324608,
13
+ "answer_instruction": "",
14
+ "num_choices": 4,
15
+ "has_chat_template": true,
16
+ "enable_thinking": false,
17
+ "batch_size": 8,
18
+ "max_new_tokens": 16,
19
+ "image_min_pixels": 401408,
20
+ "image_max_pixels": 1003520,
21
+ "dtype": "bf16",
22
+ "num_shards": 4,
23
+ "shard_id": 2,
24
+ "elapsed_seconds": 49.25848054885864,
25
+ "samples_per_second": 3.87750490619682
26
+ }