tarekziade HF Staff commited on
Commit
c71cecb
·
1 Parent(s): 0fdcc83

Review cloud MIC baselines 7d8449a176b7481f9cb779992b3f8cb3 (#1)

Browse files

- Review cloud MIC baselines 7d8449a176b7481f9cb779992b3f8cb3 (e9b81ee8ab7ca155701a630c8f57bbc856691bb3)

integrations/transformers/expectations/cpu-x86_64-bf16/llava-mic.bfloat16.json CHANGED
@@ -1,34 +1,44 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/mic-llava-integration",
4
- "contract_name": "llava",
5
- "contract_revision": "5003194065e7851b52df8c2b3c86d1ac2a527111",
6
  "framework": "transformers",
7
  "variant": "bfloat16",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
- "revision": "25b00bd747517cb5fa61b48ef9817fbbcfa42f46",
11
  "environment": {
12
  "python": "3.11.17",
13
- "transformers": "5.19.0.dev0",
14
- "torch": "2.11.0+cpu",
15
- "torchvision": "0.26.0+cpu",
16
  "torchaudio": "2.11.0+cpu",
17
- "tokenizers": "0.23.1",
18
- "numpy": "1.26.4",
19
- "pillow": "12.2.0",
20
- "accelerate": "1.13.0",
21
  "safetensors": "0.8.0",
22
- "huggingface-hub": "1.32.0",
23
- "sentencepiece": "0.2.1",
24
- "protobuf": "6.33.6",
25
  "librosa": "0.11.0",
26
- "soundfile": "0.13.1",
27
- "scipy": "1.15.3"
28
  },
29
- "seconds": 9.67,
30
  "environment_differs": {
31
- "python": "3.11.17 (pinned 3.10)"
 
 
 
 
 
 
 
 
 
 
32
  },
33
  "platform": "cpu-x86_64-bf16"
34
  },
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/llava-mic",
4
+ "contract_name": "mic-llava",
5
+ "contract_revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
6
  "framework": "transformers",
7
  "variant": "bfloat16",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
+ "revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
11
  "environment": {
12
  "python": "3.11.17",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cpu",
15
+ "torchvision": "0.29.1+cpu",
16
  "torchaudio": "2.11.0+cpu",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.3.5",
19
+ "pillow": "12.3.0",
20
+ "accelerate": "1.15.0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
  },
29
+ "seconds": 8.24,
30
  "environment_differs": {
31
+ "torch": "2.14.0+cpu (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cpu (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.3.5 (pinned 1.26.4)",
35
+ "pillow": "12.3.0 (pinned 12.2.0)",
36
+ "accelerate": "1.15.0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
43
  "platform": "cpu-x86_64-bf16"
44
  },
integrations/transformers/expectations/cpu-x86_64-fp16/llava-mic.eager.json CHANGED
@@ -1,34 +1,44 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/mic-llava-integration",
4
- "contract_name": "llava",
5
- "contract_revision": "5003194065e7851b52df8c2b3c86d1ac2a527111",
6
  "framework": "transformers",
7
  "variant": "eager",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
- "revision": "25b00bd747517cb5fa61b48ef9817fbbcfa42f46",
11
  "environment": {
12
  "python": "3.11.17",
13
- "transformers": "5.19.0.dev0",
14
- "torch": "2.11.0+cpu",
15
- "torchvision": "0.26.0+cpu",
16
  "torchaudio": "2.11.0+cpu",
17
- "tokenizers": "0.23.1",
18
- "numpy": "1.26.4",
19
- "pillow": "12.2.0",
20
- "accelerate": "1.13.0",
21
  "safetensors": "0.8.0",
22
- "huggingface-hub": "1.32.0",
23
- "sentencepiece": "0.2.1",
24
- "protobuf": "6.33.6",
25
  "librosa": "0.11.0",
26
- "soundfile": "0.13.1",
27
- "scipy": "1.15.3"
28
  },
29
- "seconds": 8.58,
30
  "environment_differs": {
31
- "python": "3.11.17 (pinned 3.10)"
 
 
 
 
 
 
 
 
 
 
32
  },
33
  "platform": "cpu-x86_64-fp16"
34
  },
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/llava-mic",
4
+ "contract_name": "mic-llava",
5
+ "contract_revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
6
  "framework": "transformers",
7
  "variant": "eager",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
+ "revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
11
  "environment": {
12
  "python": "3.11.17",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cpu",
15
+ "torchvision": "0.29.1+cpu",
16
  "torchaudio": "2.11.0+cpu",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.3.5",
19
+ "pillow": "12.3.0",
20
+ "accelerate": "1.15.0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
  },
29
+ "seconds": 8.17,
30
  "environment_differs": {
31
+ "torch": "2.14.0+cpu (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cpu (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.3.5 (pinned 1.26.4)",
35
+ "pillow": "12.3.0 (pinned 12.2.0)",
36
+ "accelerate": "1.15.0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
43
  "platform": "cpu-x86_64-fp16"
44
  },
integrations/transformers/expectations/cpu-x86_64-fp16/llava-mic.json CHANGED
@@ -1,34 +1,44 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/mic-llava-integration",
4
- "contract_name": "llava",
5
- "contract_revision": "5003194065e7851b52df8c2b3c86d1ac2a527111",
6
  "framework": "transformers",
7
  "variant": "default",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
- "revision": "25b00bd747517cb5fa61b48ef9817fbbcfa42f46",
11
  "environment": {
12
  "python": "3.11.17",
13
- "transformers": "5.19.0.dev0",
14
- "torch": "2.11.0+cpu",
15
- "torchvision": "0.26.0+cpu",
16
  "torchaudio": "2.11.0+cpu",
17
- "tokenizers": "0.23.1",
18
- "numpy": "1.26.4",
19
- "pillow": "12.2.0",
20
- "accelerate": "1.13.0",
21
  "safetensors": "0.8.0",
22
- "huggingface-hub": "1.32.0",
23
- "sentencepiece": "0.2.1",
24
- "protobuf": "6.33.6",
25
  "librosa": "0.11.0",
26
- "soundfile": "0.13.1",
27
- "scipy": "1.15.3"
28
  },
29
- "seconds": 8.24,
30
  "environment_differs": {
31
- "python": "3.11.17 (pinned 3.10)"
 
 
 
 
 
 
 
 
 
 
32
  },
33
  "platform": "cpu-x86_64-fp16"
34
  },
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/llava-mic",
4
+ "contract_name": "mic-llava",
5
+ "contract_revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
6
  "framework": "transformers",
7
  "variant": "default",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
+ "revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
11
  "environment": {
12
  "python": "3.11.17",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cpu",
15
+ "torchvision": "0.29.1+cpu",
16
  "torchaudio": "2.11.0+cpu",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.3.5",
19
+ "pillow": "12.3.0",
20
+ "accelerate": "1.15.0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
  },
29
+ "seconds": 8.48,
30
  "environment_differs": {
31
+ "torch": "2.14.0+cpu (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cpu (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.3.5 (pinned 1.26.4)",
35
+ "pillow": "12.3.0 (pinned 12.2.0)",
36
+ "accelerate": "1.15.0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
43
  "platform": "cpu-x86_64-fp16"
44
  },
integrations/transformers/expectations/cuda/llava-mic.bfloat16.json CHANGED
@@ -1,32 +1,45 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/mic-llava-integration",
4
- "contract_name": "llava",
5
- "contract_revision": "unpublished",
6
  "framework": "transformers",
7
  "variant": "bfloat16",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
- "revision": "unpublished",
11
  "environment": {
12
- "python": "3.10.12",
13
- "transformers": "5.19.0.dev0",
14
- "torch": "2.11.0+cu128",
15
- "torchvision": "0.26.0+cu128",
16
- "torchaudio": "2.11.0+cu128",
17
- "tokenizers": "0.23.1",
18
- "numpy": "1.26.4",
19
- "pillow": "12.2.0",
20
- "accelerate": "1.13.0",
21
  "safetensors": "0.8.0",
22
- "huggingface-hub": "1.32.0",
23
- "sentencepiece": "0.2.1",
24
- "protobuf": "6.33.6",
25
  "librosa": "0.11.0",
26
- "soundfile": "0.13.1",
27
- "scipy": "1.15.3"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  },
29
- "seconds": 4.75,
30
  "platform": "cuda"
31
  },
32
  "outputs": {
@@ -41,22 +54,22 @@
41
  ],
42
  "probe_logits": [
43
  [
44
- -0.302734375,
45
- -0.03125,
46
  0.15234375,
47
  -0.06298828125,
48
- 0.0712890625
49
  ],
50
  [
51
  -0.318359375,
52
- -0.028076171875,
53
  0.150390625,
54
  -0.06494140625,
55
- 0.06494140625
56
  ]
57
  ],
58
  "training": {
59
- "loss": 10.515297889709473,
60
  "gradients": {
61
  "model.vision_tower.embeddings.patch_embedding.weight": true,
62
  "model.vision_tower.embeddings.position_embedding.weight": true
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/llava-mic",
4
+ "contract_name": "mic-llava",
5
+ "contract_revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
6
  "framework": "transformers",
7
  "variant": "bfloat16",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
+ "revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
11
  "environment": {
12
+ "python": "3.11.18",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cu130",
15
+ "torchvision": "0.29.1+cu130",
16
+ "torchaudio": "2.11.0+cu130",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.4.6",
19
+ "pillow": "13.0.0",
20
+ "accelerate": "1.16.0.dev0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.03,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cu130 (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cu130 (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.4.6 (pinned 1.26.4)",
35
+ "pillow": "13.0.0 (pinned 12.2.0)",
36
+ "accelerate": "1.16.0.dev0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
 
43
  "platform": "cuda"
44
  },
45
  "outputs": {
 
54
  ],
55
  "probe_logits": [
56
  [
57
+ -0.3046875,
58
+ -0.031982421875,
59
  0.15234375,
60
  -0.06298828125,
61
+ 0.07080078125
62
  ],
63
  [
64
  -0.318359375,
65
+ -0.0274658203125,
66
  0.150390625,
67
  -0.06494140625,
68
+ 0.064453125
69
  ]
70
  ],
71
  "training": {
72
+ "loss": 10.515118598937988,
73
  "gradients": {
74
  "model.vision_tower.embeddings.patch_embedding.weight": true,
75
  "model.vision_tower.embeddings.position_embedding.weight": true
integrations/transformers/expectations/cuda/llava-mic.eager.json CHANGED
@@ -1,32 +1,45 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/mic-llava-integration",
4
- "contract_name": "llava",
5
- "contract_revision": "unpublished",
6
  "framework": "transformers",
7
  "variant": "eager",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
- "revision": "unpublished",
11
  "environment": {
12
- "python": "3.10.12",
13
- "transformers": "5.19.0.dev0",
14
- "torch": "2.11.0+cu128",
15
- "torchvision": "0.26.0+cu128",
16
- "torchaudio": "2.11.0+cu128",
17
- "tokenizers": "0.23.1",
18
- "numpy": "1.26.4",
19
- "pillow": "12.2.0",
20
- "accelerate": "1.13.0",
21
  "safetensors": "0.8.0",
22
- "huggingface-hub": "1.32.0",
23
- "sentencepiece": "0.2.1",
24
- "protobuf": "6.33.6",
25
  "librosa": "0.11.0",
26
- "soundfile": "0.13.1",
27
- "scipy": "1.15.3"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  },
29
- "seconds": 4.85,
30
  "platform": "cuda"
31
  },
32
  "outputs": {
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/llava-mic",
4
+ "contract_name": "mic-llava",
5
+ "contract_revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
6
  "framework": "transformers",
7
  "variant": "eager",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
+ "revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
11
  "environment": {
12
+ "python": "3.11.18",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cu130",
15
+ "torchvision": "0.29.1+cu130",
16
+ "torchaudio": "2.11.0+cu130",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.4.6",
19
+ "pillow": "13.0.0",
20
+ "accelerate": "1.16.0.dev0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.16,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cu130 (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cu130 (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.4.6 (pinned 1.26.4)",
35
+ "pillow": "13.0.0 (pinned 12.2.0)",
36
+ "accelerate": "1.16.0.dev0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
 
43
  "platform": "cuda"
44
  },
45
  "outputs": {
integrations/transformers/expectations/cuda/llava-mic.json CHANGED
@@ -1,32 +1,45 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/mic-llava-integration",
4
- "contract_name": "llava",
5
- "contract_revision": "unpublished",
6
  "framework": "transformers",
7
  "variant": "default",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
- "revision": "unpublished",
11
  "environment": {
12
- "python": "3.10.12",
13
- "transformers": "5.19.0.dev0",
14
- "torch": "2.11.0+cu128",
15
- "torchvision": "0.26.0+cu128",
16
- "torchaudio": "2.11.0+cu128",
17
- "tokenizers": "0.23.1",
18
- "numpy": "1.26.4",
19
- "pillow": "12.2.0",
20
- "accelerate": "1.13.0",
21
  "safetensors": "0.8.0",
22
- "huggingface-hub": "1.32.0",
23
- "sentencepiece": "0.2.1",
24
- "protobuf": "6.33.6",
25
  "librosa": "0.11.0",
26
- "soundfile": "0.13.1",
27
- "scipy": "1.15.3"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  },
29
- "seconds": 4.75,
30
  "platform": "cuda"
31
  },
32
  "outputs": {
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/llava-mic",
4
+ "contract_name": "mic-llava",
5
+ "contract_revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
6
  "framework": "transformers",
7
  "variant": "default",
8
  "target": "llava-mic",
9
  "kind": "fixture",
10
+ "revision": "0fdcc8328bb598bbd85a99daf632a2da299ebed1",
11
  "environment": {
12
+ "python": "3.11.18",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cu130",
15
+ "torchvision": "0.29.1+cu130",
16
+ "torchaudio": "2.11.0+cu130",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.4.6",
19
+ "pillow": "13.0.0",
20
+ "accelerate": "1.16.0.dev0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.08,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cu130 (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cu130 (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.4.6 (pinned 1.26.4)",
35
+ "pillow": "13.0.0 (pinned 12.2.0)",
36
+ "accelerate": "1.16.0.dev0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
 
43
  "platform": "cuda"
44
  },
45
  "outputs": {