madlag commited on
Commit
86c732c
1 Parent(s): 395b875

Adding model, graphs and metadata.

Browse files
README.md CHANGED
@@ -4,8 +4,8 @@ thumbnail:
4
  license: mit
5
  tags:
6
  - question-answering
7
- - bert
8
- - bert-base
9
  datasets:
10
  - squad
11
  metrics:
@@ -19,26 +19,26 @@ widget:
19
 
20
  ## BERT-base uncased model fine-tuned on SQuAD v1
21
 
22
- This model was created using the [nn_pruning](https://github.com/huggingface/nn_pruning) python library: the **linear layers contains 8.0%** of the original weights.
23
 
24
 
25
 
26
  The model contains **28.0%** of the original weights **overall** (the embeddings account for a significant part of the model, and they are not pruned by this method).
27
 
28
- With a simple resizing of the linear matrices it ran **1.16x as fast as BERT-base** on the evaluation.
29
  This is possible because the pruning method lead to structured matrices: to visualize them, hover below on the plot to see the non-zero/zero parts of each matrix.
30
 
31
- <div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/density_info.js" id="14cf4013-d609-473e-a62b-6f7429a41f44"></script></div>
32
 
33
- In terms of accuracy, its **F1 is 88.11**, compared with 88.5 for BERT-base, a **F1 drop of 0.39**.
34
 
35
  ## Fine-Pruning details
36
- This model was fine-tuned from the HuggingFace [BERT](https://www.aclweb.org/anthology/N19-1423/) base uncased checkpoint on [SQuAD1.1](https://rajpurkar.github.io/SQuAD-explorer), and distilled from the model [bert-large-uncased-whole-word-masking-finetuned-squad](https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad).
37
  This model is case-insensitive: it does not make a difference between english and English.
38
 
39
  A side-effect of the block pruning is that some of the attention heads are completely removed: 22 heads were removed on a total of 144 (15.3%).
40
  Here is a detailed view on how the remaining heads are distributed in the network after pruning.
41
- <div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/pruning_info.js" id="22413187-104d-479c-9a91-8249ba12fe4e"></script></div>
42
 
43
  ## Details of the SQuAD1.1 dataset
44
 
@@ -60,7 +60,7 @@ GPU driver: 455.23.05, CUDA: 11.1
60
 
61
  ### Results
62
 
63
- **Pytorch model file size**: `398M` (original BERT: `438M`)
64
 
65
  | Metric | # Value | # Original ([Table 2](https://www.aclweb.org/anthology/N19-1423.pdf))| Variation |
66
  | ------ | --------- | --------- | --------- |
@@ -84,11 +84,11 @@ qa_pipeline = pipeline(
84
  tokenizer="madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1"
85
  )
86
 
87
- print("BERT-base parameters: 110M")
88
- print(f"Parameters count (includes head pruning)={int(qa_pipeline.model.num_parameters() / 1E6)}M")
89
  qa_pipeline.model = optimize_model(qa_pipeline.model, "dense")
90
 
91
- print(f"Parameters count after optimization={int(qa_pipeline.model.num_parameters() / 1E6)}M")
92
  predictions = qa_pipeline({
93
  'context': "Frédéric François Chopin, born Fryderyk Franciszek Chopin (1 March 1810 – 17 October 1849), was a Polish composer and virtuoso pianist of the Romantic era who wrote primarily for solo piano.",
94
  'question': "Who is Frederic Chopin?",
4
  license: mit
5
  tags:
6
  - question-answering
7
+ -
8
+ -
9
  datasets:
10
  - squad
11
  metrics:
19
 
20
  ## BERT-base uncased model fine-tuned on SQuAD v1
21
 
22
+ This model was created using the [nn_pruning](https://github.com/huggingface/nn_pruning) python library: the **linear layers contains 8.0%** of the original weights.
23
 
24
 
25
 
26
  The model contains **28.0%** of the original weights **overall** (the embeddings account for a significant part of the model, and they are not pruned by this method).
27
 
28
+ With a simple resizing of the linear matrices it ran **1.16x as fast as bert-base-uncased** on the evaluation.
29
  This is possible because the pruning method lead to structured matrices: to visualize them, hover below on the plot to see the non-zero/zero parts of each matrix.
30
 
31
+ <div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/density_info.js" id="c60d09ec-81ff-4d6f-b616-c3ef09b2175d"></script></div>
32
 
33
+ In terms of accuracy, its **F1 is 88.11**, compared with 88.5 for bert-base-uncased, a **F1 drop of 0.39**.
34
 
35
  ## Fine-Pruning details
36
+ This model was fine-tuned from the HuggingFace [model](https://huggingface.co/bert-base-uncased) checkpoint on [SQuAD1.1](https://rajpurkar.github.io/SQuAD-explorer), and distilled from the model [bert-large-uncased-whole-word-masking-finetuned-squad](https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad)
37
  This model is case-insensitive: it does not make a difference between english and English.
38
 
39
  A side-effect of the block pruning is that some of the attention heads are completely removed: 22 heads were removed on a total of 144 (15.3%).
40
  Here is a detailed view on how the remaining heads are distributed in the network after pruning.
41
+ <div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/pruning_info.js" id="55528c8b-d5f5-46a5-a35a-dad93725f7e5"></script></div>
42
 
43
  ## Details of the SQuAD1.1 dataset
44
 
60
 
61
  ### Results
62
 
63
+ **Pytorch model file size**: `398MB` (original BERT: `420MB`)
64
 
65
  | Metric | # Value | # Original ([Table 2](https://www.aclweb.org/anthology/N19-1423.pdf))| Variation |
66
  | ------ | --------- | --------- | --------- |
84
  tokenizer="madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1"
85
  )
86
 
87
+ print("bert-base-uncased parameters: 152.0M")
88
+ print(f"Parameters count (includes only head pruning, not feed forward pruning)={int(qa_pipeline.model.num_parameters() / 1E6)}M")
89
  qa_pipeline.model = optimize_model(qa_pipeline.model, "dense")
90
 
91
+ print(f"Parameters count after complete optimization={int(qa_pipeline.model.num_parameters() / 1E6)}M")
92
  predictions = qa_pipeline({
93
  'context': "Frédéric François Chopin, born Fryderyk Franciszek Chopin (1 March 1810 – 17 October 1849), was a Polish composer and virtuoso pianist of the Romantic era who wrote primarily for solo piano.",
94
  'question': "Who is Frederic Chopin?",
eval/eval_metrics.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
1
+ {
2
+ "exact_match": 80.89877010406812,
3
+ "f1": 88.09526643561759
4
+ }
eval/evaluate_timing.json ADDED
@@ -0,0 +1 @@
 
1
+ {"eval_elapsed_time": 94.33543854672462, "cuda_eval_elapsed_time": 86.41913686752319}
eval/nbest_predictions.json.tgz ADDED
Binary file (6.63 MB). View file
eval/predictions.json ADDED
The diff for this file is too large to render. See raw diff
eval/sparsity_report.json ADDED
@@ -0,0 +1 @@
 
1
+ {"total": 108893186, "nnz": 30895354, "linear_total": 84934656, "linear_nnz": 6956106, "layers": {"0": {"total": 7087872, "nnz": 860873, "linear_total": 7077888, "linear_nnz": 852146, "linear_attention_total": 2359296, "linear_attention_nnz": 108638, "linear_dense_total": 4718592, "linear_dense_nnz": 743508}, "1": {"total": 7087872, "nnz": 960245, "linear_total": 7077888, "linear_nnz": 951459, "linear_attention_total": 2359296, "linear_attention_nnz": 171340, "linear_dense_total": 4718592, "linear_dense_nnz": 780119}, "2": {"total": 7087872, "nnz": 986901, "linear_total": 7077888, "linear_nnz": 977699, "linear_attention_total": 2359296, "linear_attention_nnz": 221074, "linear_dense_total": 4718592, "linear_dense_nnz": 756625}, "3": {"total": 7087872, "nnz": 973427, "linear_total": 7077888, "linear_nnz": 964137, "linear_attention_total": 2359296, "linear_attention_nnz": 258229, "linear_dense_total": 4718592, "linear_dense_nnz": 705908}, "4": {"total": 7087872, "nnz": 858037, "linear_total": 7077888, "linear_nnz": 848474, "linear_attention_total": 2359296, "linear_attention_nnz": 255136, "linear_dense_total": 4718592, "linear_dense_nnz": 593338}, "5": {"total": 7087872, "nnz": 720395, "linear_total": 7077888, "linear_nnz": 711055, "linear_attention_total": 2359296, "linear_attention_nnz": 179994, "linear_dense_total": 4718592, "linear_dense_nnz": 531061}, "6": {"total": 7087872, "nnz": 580963, "linear_total": 7077888, "linear_nnz": 571558, "linear_attention_total": 2359296, "linear_attention_nnz": 165167, "linear_dense_total": 4718592, "linear_dense_nnz": 406391}, "7": {"total": 7087872, "nnz": 421032, "linear_total": 7077888, "linear_nnz": 412421, "linear_attention_total": 2359296, "linear_attention_nnz": 139907, "linear_dense_total": 4718592, "linear_dense_nnz": 272514}, "8": {"total": 7087872, "nnz": 285536, "linear_total": 7077888, "linear_nnz": 277031, "linear_attention_total": 2359296, "linear_attention_nnz": 113253, "linear_dense_total": 4718592, "linear_dense_nnz": 163778}, "9": {"total": 7087872, "nnz": 162775, "linear_total": 7077888, "linear_nnz": 156105, "linear_attention_total": 2359296, "linear_attention_nnz": 84915, "linear_dense_total": 4718592, "linear_dense_nnz": 71190}, "10": {"total": 7087872, "nnz": 143162, "linear_total": 7077888, "linear_nnz": 136669, "linear_attention_total": 2359296, "linear_attention_nnz": 67316, "linear_dense_total": 4718592, "linear_dense_nnz": 69353}, "11": {"total": 7087872, "nnz": 103286, "linear_total": 7077888, "linear_nnz": 97352, "linear_attention_total": 2359296, "linear_attention_nnz": 41497, "linear_dense_total": 4718592, "linear_dense_nnz": 55855}}, "total_sparsity": 71.62783537254572, "linear_sparsity": 91.81004983407479, "pruned_heads": {"0": [9], "1": [], "2": [8], "3": [2, 4], "4": [], "5": [1], "6": [2, 3], "7": [1, 7], "8": [0], "9": [1, 4, 5, 7, 10], "10": [1, 2, 4], "11": [8, 11, 5, 7]}}
eval/speed_report.json ADDED
@@ -0,0 +1 @@
 
1
+ {"timings": {"eval_elapsed_time": 40.18306041043252, "cuda_eval_elapsed_time": 33.17768461608887}, "metrics": {"exact_match": 80.93661305581836, "f1": 88.11360890595924}}
model_card/density_info.js CHANGED
@@ -16,9 +16,9 @@
16
 
17
 
18
 
19
- var element = document.getElementById("14cf4013-d609-473e-a62b-6f7429a41f44");
20
  if (element == null) {
21
- console.warn("Bokeh: autoload.js configured with elementid '14cf4013-d609-473e-a62b-6f7429a41f44' but no matching script tag was found.")
22
  }
23
 
24
 
@@ -115,8 +115,8 @@
115
  (function(root) {
116
  function embed_document(root) {
117
 
118
- var docs_json = '{"63c71560-6caa-4f60-b5e0-9a1be29aeb92":{"roots":{"references":[{"attributes":{"fill_color":{"value":"#6573f7"},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1118","type":"VBar"},{"attributes":{},"id":"1151","type":"Selection"},{"attributes":{"fill_color":{"value":"#20cb97"},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1130","type":"VBar"},{"attributes":{},"id":"1155","type":"Selection"},{"attributes":{"label":{"value":"fully connected"},"renderers":[{"id":"1138"}]},"id":"1144","type":"LegendItem"},{"attributes":{},"id":"1156","type":"UnionRenderers"},{"attributes":{"data_source":{"id":"1128"},"glyph":{"id":"1130"},"hover_glyph":null,"muted_glyph":null,"name":"value","nonselection_glyph":{"id":"1131"},"selection_glyph":null,"view":{"id":"1133"}},"id":"1132","type":"GlyphRenderer"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto","tools":[{"id":"1094"}]},"id":"1114","type":"Toolbar"},{"attributes":{},"id":"1157","type":"Selection"},{"attributes":{"callback":null,"tooltips":"\\n &lt;div&gt;\\n &lt;div style=\\"margin-bottom:10px\\"&gt;\\n &lt;span style=\\"font-size: 15px;\\"&gt;&lt;b&gt;@name&lt;/b&gt;&lt;br/&gt;density=@density&lt;/span&gt;\\n &lt;/div&gt;\\n &lt;div&gt; \\n &lt;img\\n src=\\"@url\\" height=\\"@img_height\\" width=\\"@img_width\\" alt=\\"@url\\"\\n style=\\"float: left; margin: 0px 15px 15px 0px;\\"\\n border=\\"0\\"\\n /&gt;\\n &lt;/div&gt;\\n &lt;/div&gt;\\n "},"id":"1094","type":"HoverTool"},{"attributes":{"data_source":{"id":"1116"},"glyph":{"id":"1118"},"hover_glyph":null,"muted_glyph":null,"name":"query","nonselection_glyph":{"id":"1119"},"selection_glyph":null,"view":{"id":"1121"}},"id":"1120","type":"GlyphRenderer"},{"attributes":{},"id":"1146","type":"BasicTickFormatter"},{"attributes":{"data_source":{"id":"1122"},"glyph":{"id":"1124"},"hover_glyph":null,"muted_glyph":null,"name":"key","nonselection_glyph":{"id":"1125"},"selection_glyph":null,"view":{"id":"1127"}},"id":"1126","type":"GlyphRenderer"},{"attributes":{"axis_label":"Parameters (M)","formatter":{"id":"1148"},"minor_tick_line_color":null,"ticker":{"id":"1111"}},"id":"1110","type":"LinearAxis"},{"attributes":{"label":{"value":"query"},"renderers":[{"id":"1120"}]},"id":"1141","type":"LegendItem"},{"attributes":{"source":{"id":"1128"}},"id":"1133","type":"CDSView"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#6573f7"},"line_alpha":{"value":0.1},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1119","type":"VBar"},{"attributes":{},"id":"1154","type":"UnionRenderers"},{"attributes":{"above":[{"id":"1140"}],"below":[{"id":"1106"}],"center":[{"id":"1109"},{"id":"1113"}],"left":[{"id":"1110"}],"outline_line_color":null,"plot_height":300,"plot_width":505,"renderers":[{"id":"1120"},{"id":"1126"},{"id":"1132"},{"id":"1138"}],"title":{"id":"1096"},"toolbar":{"id":"1114"},"x_range":{"id":"1098"},"x_scale":{"id":"1102"},"y_range":{"id":"1100"},"y_scale":{"id":"1104"}},"id":"1095","subtype":"Figure","type":"Plot"},{"attributes":{"axis":{"id":"1106"},"grid_line_color":null,"ticker":null},"id":"1109","type":"Grid"},{"attributes":{"text":"Transformer Layers"},"id":"1096","type":"Title"},{"attributes":{"axis":{"id":"1110"},"dimension":1,"ticker":null},"id":"1113","type":"Grid"},{"attributes":{},"id":"1153","type":"Selection"},{"attributes":{"fill_color":{"value":"#ed5642"},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1124","type":"VBar"},{"attributes":{"items":[{"id":"1141"},{"id":"1142"},{"id":"1143"},{"id":"1144"}],"location":[10,0],"orientation":"horizontal"},"id":"1140","type":"Legend"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#ed5642"},"line_alpha":{"value":0.1},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1125","type":"VBar"},{"attributes":{},"id":"1148","type":"BasicTickFormatter"},{"attributes":{"data":{"density":["3.2%","7.0%","10.6%","10.4%","10.5%","6.1%","6.3%","4.7%","4.7%","5.8%","4.0%","2.3%"],"height":[0.019014,0.041261,0.062407,0.061625,0.061859,0.035875,0.037202,0.027519,0.027589,0.034429,0.023645,0.01364],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.query","1.attention.query","2.attention.query","3.attention.query","4.attention.query","5.attention.query","6.attention.query","7.attention.query","8.attention.query","9.attention.query","10.attention.query","11.attention.query"],"parameters":["0.02","0.04","0.06","0.06","0.06","0.04","0.04","0.03","0.03","0.03","0.02","0.01"],"url":["/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_attention_self_query.png"],"x":[0.08333333333333333,1.0833333333333333,2.0833333333333335,3.0833333333333335,4.083333333333333,5.083333333333333,6.083333333333333,7.083333333333333,8.083333333333334,9.083333333333334,10.083333333333334,11.083333333333334]},"selected":{"id":"1151"},"selection_policy":{"id":"1150"}},"id":"1116","type":"ColumnDataSource"},{"attributes":{"data":{"density":["3.5%","7.2%","11.0%","11.3%","10.9%","7.0%","7.1%","5.5%","5.1%","5.5%","4.1%","2.6%"],"height":[0.020692,0.042589,0.064965,0.066671,0.064557,0.041484,0.041594,0.032501,0.030267,0.03254,0.02413,0.015345],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.key","1.attention.key","2.attention.key","3.attention.key","4.attention.key","5.attention.key","6.attention.key","7.attention.key","8.attention.key","9.attention.key","10.attention.key","11.attention.key"],"parameters":["0.02","0.04","0.06","0.07","0.06","0.04","0.04","0.03","0.03","0.03","0.02","0.02"],"url":["/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_attention_self_key.png"],"x":[0.25,1.25,2.25,3.25,4.25,5.25,6.25,7.25,8.25,9.25,10.25,11.25]},"selected":{"id":"1153"},"selection_policy":{"id":"1152"}},"id":"1122","type":"ColumnDataSource"},{"attributes":{},"id":"1150","type":"UnionRenderers"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#20cb97"},"line_alpha":{"value":0.1},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1131","type":"VBar"},{"attributes":{"label":{"value":"key"},"renderers":[{"id":"1126"}]},"id":"1142","type":"LegendItem"},{"attributes":{},"id":"1111","type":"BasicTicker"},{"attributes":{},"id":"1107","type":"BasicTicker"},{"attributes":{},"id":"1102","type":"LinearScale"},{"attributes":{"source":{"id":"1116"}},"id":"1121","type":"CDSView"},{"attributes":{},"id":"1104","type":"LinearScale"},{"attributes":{"data":{"density":["5.6%","6.9%","7.8%","10.9%","10.8%","8.7%","7.5%","7.2%","4.9%","1.6%","1.8%","1.2%"],"height":[0.032803,0.040951,0.045967,0.064154,0.063766,0.051269,0.044338,0.042572,0.028976,0.009652,0.010327,0.007072],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.value","1.attention.value","2.attention.value","3.attention.value","4.attention.value","5.attention.value","6.attention.value","7.attention.value","8.attention.value","9.attention.value","10.attention.value","11.attention.value"],"parameters":["0.03","0.04","0.05","0.06","0.06","0.05","0.04","0.04","0.03","0.01","0.01","0.01"],"url":["/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_attention_self_value.png"],"x":[0.41666666666666663,1.4166666666666665,2.416666666666667,3.416666666666667,4.416666666666666,5.416666666666666,6.416666666666666,7.416666666666666,8.416666666666668,9.416666666666668,10.416666666666668,11.416666666666668]},"selected":{"id":"1155"},"selection_policy":{"id":"1154"}},"id":"1128","type":"ColumnDataSource"},{"attributes":{"fill_color":{"value":"#aa69f7"},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1136","type":"VBar"},{"attributes":{},"id":"1098","type":"DataRange1d"},{"attributes":{"source":{"id":"1134"}},"id":"1139","type":"CDSView"},{"attributes":{},"id":"1152","type":"UnionRenderers"},{"attributes":{"data_source":{"id":"1134"},"glyph":{"id":"1136"},"hover_glyph":null,"muted_glyph":null,"name":"fully connected","nonselection_glyph":{"id":"1137"},"selection_glyph":null,"view":{"id":"1139"}},"id":"1138","type":"GlyphRenderer"},{"attributes":{"source":{"id":"1122"}},"id":"1127","type":"CDSView"},{"attributes":{"label":{"value":"value"},"renderers":[{"id":"1132"}]},"id":"1143","type":"LegendItem"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#aa69f7"},"line_alpha":{"value":0.1},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1137","type":"VBar"},{"attributes":{"data":{"density":["6.1%","18.2%","13.3%","7.9%","19.6%","13.5%","8.1%","19.1%","12.9%","11.1%","18.0%","11.9%","11.0%","15.5%","9.6%","8.7%","14.1%","8.4%","7.1%","10.8%","6.4%","6.3%","7.1%","4.4%","4.5%","4.3%","2.7%","1.4%","1.8%","1.2%","1.6%","1.9%","1.1%","0.9%","1.5%","0.9%"],"height":[0.035903,0.429516,0.313925,0.046539,0.462132,0.317865,0.047735,0.451602,0.304909,0.065762,0.425332,0.280451,0.064954,0.366346,0.226804,0.051357,0.332724,0.198119,0.041967,0.255434,0.150735,0.037276,0.167799,0.104488,0.026418,0.100461,0.06307,0.008293,0.043433,0.027579,0.009214,0.043885,0.025351,0.005428,0.034427,0.021379],"img_height":["96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px"],"img_width":["96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px"],"name":["0.attention.output","0.intermediate","0.output","1.attention.output","1.intermediate","1.output","2.attention.output","2.intermediate","2.output","3.attention.output","3.intermediate","3.output","4.attention.output","4.intermediate","4.output","5.attention.output","5.intermediate","5.output","6.attention.output","6.intermediate","6.output","7.attention.output","7.intermediate","7.output","8.attention.output","8.intermediate","8.output","9.attention.output","9.intermediate","9.output","10.attention.output","10.intermediate","10.output","11.attention.output","11.intermediate","11.output"],"parameters":["0.04","0.43","0.31","0.05","0.46","0.32","0.05","0.45","0.30","0.07","0.43","0.28","0.06","0.37","0.23","0.05","0.33","0.20","0.04","0.26","0.15","0.04","0.17","0.10","0.03","0.10","0.06","0.01","0.04","0.03","0.01","0.04","0.03","0.01","0.03","0.02"],"url":["/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_output_dense.png"],"x":[0.5833333333333334,0.75,0.9166666666666667,1.5833333333333333,1.75,1.9166666666666665,2.5833333333333335,2.75,2.916666666666667,3.5833333333333335,3.75,3.916666666666667,4.583333333333333,4.75,4.916666666666666,5.583333333333333,5.75,5.916666666666666,6.583333333333333,6.75,6.916666666666666,7.583333333333333,7.75,7.916666666666666,8.583333333333334,8.75,8.916666666666668,9.583333333333334,9.75,9.916666666666668,10.583333333333334,10.75,10.916666666666668,11.583333333333334,11.75,11.916666666666668]},"selected":{"id":"1157"},"selection_policy":{"id":"1156"}},"id":"1134","type":"ColumnDataSource"},{"attributes":{"axis_label":"Layer","formatter":{"id":"1146"},"minor_tick_line_color":null,"ticker":{"id":"1107"}},"id":"1106","type":"LinearAxis"},{"attributes":{"start":0},"id":"1100","type":"DataRange1d"}],"root_ids":["1095"]},"title":"Bokeh Application","version":"2.2.3"}}';
119
- var render_items = [{"docid":"63c71560-6caa-4f60-b5e0-9a1be29aeb92","root_ids":["1095"],"roots":{"1095":"14cf4013-d609-473e-a62b-6f7429a41f44"}}];
120
  root.Bokeh.embed.embed_items(docs_json, render_items);
121
 
122
  }
16
 
17
 
18
 
19
+ var element = document.getElementById("c60d09ec-81ff-4d6f-b616-c3ef09b2175d");
20
  if (element == null) {
21
+ console.warn("Bokeh: autoload.js configured with elementid 'c60d09ec-81ff-4d6f-b616-c3ef09b2175d' but no matching script tag was found.")
22
  }
23
 
24
 
115
  (function(root) {
116
  function embed_document(root) {
117
 
118
+ var docs_json = '{"810e2153-6557-4d0d-819b-353b9cba234e":{"roots":{"references":[{"attributes":{"axis":{"id":"1106"},"grid_line_color":null,"ticker":null},"id":"1109","type":"Grid"},{"attributes":{},"id":"1098","type":"DataRange1d"},{"attributes":{"axis":{"id":"1110"},"dimension":1,"ticker":null},"id":"1113","type":"Grid"},{"attributes":{"start":0},"id":"1100","type":"DataRange1d"},{"attributes":{"label":{"value":"query"},"renderers":[{"id":"1120"}]},"id":"1141","type":"LegendItem"},{"attributes":{},"id":"1153","type":"UnionRenderers"},{"attributes":{},"id":"1104","type":"LinearScale"},{"attributes":{},"id":"1156","type":"Selection"},{"attributes":{"data":{"density":["3.2%","7.0%","10.6%","10.4%","10.5%","6.1%","6.3%","4.7%","4.7%","5.8%","4.0%","2.3%"],"height":[0.019014,0.041261,0.062407,0.061625,0.061859,0.035875,0.037202,0.027519,0.027589,0.034429,0.023645,0.01364],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.query","1.attention.query","2.attention.query","3.attention.query","4.attention.query","5.attention.query","6.attention.query","7.attention.query","8.attention.query","9.attention.query","10.attention.query","11.attention.query"],"parameters":["0.02","0.04","0.06","0.06","0.06","0.04","0.04","0.03","0.03","0.03","0.02","0.01"],"url":["/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_attention_self_query.png"],"x":[0.08333333333333333,1.0833333333333333,2.0833333333333335,3.0833333333333335,4.083333333333333,5.083333333333333,6.083333333333333,7.083333333333333,8.083333333333334,9.083333333333334,10.083333333333334,11.083333333333334]},"selected":{"id":"1150"},"selection_policy":{"id":"1151"}},"id":"1116","type":"ColumnDataSource"},{"attributes":{},"id":"1157","type":"UnionRenderers"},{"attributes":{"label":{"value":"value"},"renderers":[{"id":"1132"}]},"id":"1143","type":"LegendItem"},{"attributes":{"items":[{"id":"1141"},{"id":"1142"},{"id":"1143"},{"id":"1144"}],"location":[10,0],"orientation":"horizontal"},"id":"1140","type":"Legend"},{"attributes":{"axis_label":"Parameters (M)","formatter":{"id":"1149"},"minor_tick_line_color":null,"ticker":{"id":"1111"}},"id":"1110","type":"LinearAxis"},{"attributes":{"data":{"density":["6.1%","18.2%","13.3%","7.9%","19.6%","13.5%","8.1%","19.1%","12.9%","11.1%","18.0%","11.9%","11.0%","15.5%","9.6%","8.7%","14.1%","8.4%","7.1%","10.8%","6.4%","6.3%","7.1%","4.4%","4.5%","4.3%","2.7%","1.4%","1.8%","1.2%","1.6%","1.9%","1.1%","0.9%","1.5%","0.9%"],"height":[0.035903,0.429516,0.313925,0.046539,0.462132,0.317865,0.047735,0.451602,0.304909,0.065762,0.425332,0.280451,0.064954,0.366346,0.226804,0.051357,0.332724,0.198119,0.041967,0.255434,0.150735,0.037276,0.167799,0.104488,0.026418,0.100461,0.06307,0.008293,0.043433,0.027579,0.009214,0.043885,0.025351,0.005428,0.034427,0.021379],"img_height":["96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px"],"img_width":["96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px"],"name":["0.attention.output","0.intermediate","0.output","1.attention.output","1.intermediate","1.output","2.attention.output","2.intermediate","2.output","3.attention.output","3.intermediate","3.output","4.attention.output","4.intermediate","4.output","5.attention.output","5.intermediate","5.output","6.attention.output","6.intermediate","6.output","7.attention.output","7.intermediate","7.output","8.attention.output","8.intermediate","8.output","9.attention.output","9.intermediate","9.output","10.attention.output","10.intermediate","10.output","11.attention.output","11.intermediate","11.output"],"parameters":["0.04","0.43","0.31","0.05","0.46","0.32","0.05","0.45","0.30","0.07","0.43","0.28","0.06","0.37","0.23","0.05","0.33","0.20","0.04","0.26","0.15","0.04","0.17","0.10","0.03","0.10","0.06","0.01","0.04","0.03","0.01","0.04","0.03","0.01","0.03","0.02"],"url":["/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_output_dense.png"],"x":[0.5833333333333334,0.75,0.9166666666666667,1.5833333333333333,1.75,1.9166666666666665,2.5833333333333335,2.75,2.916666666666667,3.5833333333333335,3.75,3.916666666666667,4.583333333333333,4.75,4.916666666666666,5.583333333333333,5.75,5.916666666666666,6.583333333333333,6.75,6.916666666666666,7.583333333333333,7.75,7.916666666666666,8.583333333333334,8.75,8.916666666666668,9.583333333333334,9.75,9.916666666666668,10.583333333333334,10.75,10.916666666666668,11.583333333333334,11.75,11.916666666666668]},"selected":{"id":"1156"},"selection_policy":{"id":"1157"}},"id":"1134","type":"ColumnDataSource"},{"attributes":{},"id":"1155","type":"UnionRenderers"},{"attributes":{"text":"Transformer Layers"},"id":"1096","type":"Title"},{"attributes":{"label":{"value":"key"},"renderers":[{"id":"1126"}]},"id":"1142","type":"LegendItem"},{"attributes":{"fill_color":{"value":"#aa69f7"},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1136","type":"VBar"},{"attributes":{},"id":"1152","type":"Selection"},{"attributes":{"axis_label":"Layer","formatter":{"id":"1147"},"minor_tick_line_color":null,"ticker":{"id":"1107"}},"id":"1106","type":"LinearAxis"},{"attributes":{"source":{"id":"1128"}},"id":"1133","type":"CDSView"},{"attributes":{},"id":"1147","type":"BasicTickFormatter"},{"attributes":{"fill_color":{"value":"#ed5642"},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1124","type":"VBar"},{"attributes":{},"id":"1149","type":"BasicTickFormatter"},{"attributes":{"data":{"density":["5.6%","6.9%","7.8%","10.9%","10.8%","8.7%","7.5%","7.2%","4.9%","1.6%","1.8%","1.2%"],"height":[0.032803,0.040951,0.045967,0.064154,0.063766,0.051269,0.044338,0.042572,0.028976,0.009652,0.010327,0.007072],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.value","1.attention.value","2.attention.value","3.attention.value","4.attention.value","5.attention.value","6.attention.value","7.attention.value","8.attention.value","9.attention.value","10.attention.value","11.attention.value"],"parameters":["0.03","0.04","0.05","0.06","0.06","0.05","0.04","0.04","0.03","0.01","0.01","0.01"],"url":["/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_attention_self_value.png"],"x":[0.41666666666666663,1.4166666666666665,2.416666666666667,3.416666666666667,4.416666666666666,5.416666666666666,6.416666666666666,7.416666666666666,8.416666666666668,9.416666666666668,10.416666666666668,11.416666666666668]},"selected":{"id":"1154"},"selection_policy":{"id":"1155"}},"id":"1128","type":"ColumnDataSource"},{"attributes":{},"id":"1150","type":"Selection"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#aa69f7"},"line_alpha":{"value":0.1},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1137","type":"VBar"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#ed5642"},"line_alpha":{"value":0.1},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1125","type":"VBar"},{"attributes":{"label":{"value":"fully connected"},"renderers":[{"id":"1138"}]},"id":"1144","type":"LegendItem"},{"attributes":{"data_source":{"id":"1128"},"glyph":{"id":"1130"},"hover_glyph":null,"muted_glyph":null,"name":"value","nonselection_glyph":{"id":"1131"},"selection_glyph":null,"view":{"id":"1133"}},"id":"1132","type":"GlyphRenderer"},{"attributes":{"fill_color":{"value":"#20cb97"},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1130","type":"VBar"},{"attributes":{"data_source":{"id":"1116"},"glyph":{"id":"1118"},"hover_glyph":null,"muted_glyph":null,"name":"query","nonselection_glyph":{"id":"1119"},"selection_glyph":null,"view":{"id":"1121"}},"id":"1120","type":"GlyphRenderer"},{"attributes":{"source":{"id":"1116"}},"id":"1121","type":"CDSView"},{"attributes":{"callback":null,"tooltips":"\\n &lt;div&gt;\\n &lt;div style=\\"margin-bottom:10px\\"&gt;\\n &lt;span style=\\"font-size: 15px;\\"&gt;&lt;b&gt;@name&lt;/b&gt;&lt;br/&gt;density=@density&lt;/span&gt;\\n &lt;/div&gt;\\n &lt;div&gt; \\n &lt;img\\n src=\\"@url\\" height=\\"@img_height\\" width=\\"@img_width\\" alt=\\"@url\\"\\n style=\\"float: left; margin: 0px 15px 15px 0px;\\"\\n border=\\"0\\"\\n /&gt;\\n &lt;/div&gt;\\n &lt;/div&gt;\\n "},"id":"1094","type":"HoverTool"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#20cb97"},"line_alpha":{"value":0.1},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1131","type":"VBar"},{"attributes":{},"id":"1151","type":"UnionRenderers"},{"attributes":{"source":{"id":"1122"}},"id":"1127","type":"CDSView"},{"attributes":{"data_source":{"id":"1122"},"glyph":{"id":"1124"},"hover_glyph":null,"muted_glyph":null,"name":"key","nonselection_glyph":{"id":"1125"},"selection_glyph":null,"view":{"id":"1127"}},"id":"1126","type":"GlyphRenderer"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto","tools":[{"id":"1094"}]},"id":"1114","type":"Toolbar"},{"attributes":{},"id":"1107","type":"BasicTicker"},{"attributes":{"source":{"id":"1134"}},"id":"1139","type":"CDSView"},{"attributes":{"data_source":{"id":"1134"},"glyph":{"id":"1136"},"hover_glyph":null,"muted_glyph":null,"name":"fully connected","nonselection_glyph":{"id":"1137"},"selection_glyph":null,"view":{"id":"1139"}},"id":"1138","type":"GlyphRenderer"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#6573f7"},"line_alpha":{"value":0.1},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1119","type":"VBar"},{"attributes":{"data":{"density":["3.5%","7.2%","11.0%","11.3%","10.9%","7.0%","7.1%","5.5%","5.1%","5.5%","4.1%","2.6%"],"height":[0.020692,0.042589,0.064965,0.066671,0.064557,0.041484,0.041594,0.032501,0.030267,0.03254,0.02413,0.015345],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.key","1.attention.key","2.attention.key","3.attention.key","4.attention.key","5.attention.key","6.attention.key","7.attention.key","8.attention.key","9.attention.key","10.attention.key","11.attention.key"],"parameters":["0.02","0.04","0.06","0.07","0.06","0.04","0.04","0.03","0.03","0.03","0.02","0.02"],"url":["/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_0_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_1_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_2_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_3_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_4_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_5_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_6_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_7_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_8_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_9_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_10_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1/raw/main/model_card/images/layer_11_attention_self_key.png"],"x":[0.25,1.25,2.25,3.25,4.25,5.25,6.25,7.25,8.25,9.25,10.25,11.25]},"selected":{"id":"1152"},"selection_policy":{"id":"1153"}},"id":"1122","type":"ColumnDataSource"},{"attributes":{},"id":"1111","type":"BasicTicker"},{"attributes":{},"id":"1102","type":"LinearScale"},{"attributes":{},"id":"1154","type":"Selection"},{"attributes":{"fill_color":{"value":"#6573f7"},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1118","type":"VBar"},{"attributes":{"above":[{"id":"1140"}],"below":[{"id":"1106"}],"center":[{"id":"1109"},{"id":"1113"}],"left":[{"id":"1110"}],"outline_line_color":null,"plot_height":300,"plot_width":505,"renderers":[{"id":"1120"},{"id":"1126"},{"id":"1132"},{"id":"1138"}],"title":{"id":"1096"},"toolbar":{"id":"1114"},"x_range":{"id":"1098"},"x_scale":{"id":"1102"},"y_range":{"id":"1100"},"y_scale":{"id":"1104"}},"id":"1095","subtype":"Figure","type":"Plot"}],"root_ids":["1095"]},"title":"Bokeh Application","version":"2.2.3"}}';
119
+ var render_items = [{"docid":"810e2153-6557-4d0d-819b-353b9cba234e","root_ids":["1095"],"roots":{"1095":"c60d09ec-81ff-4d6f-b616-c3ef09b2175d"}}];
120
  root.Bokeh.embed.embed_items(docs_json, render_items);
121
 
122
  }
model_card/pruning_info.js CHANGED
@@ -16,9 +16,9 @@
16
 
17
 
18
 
19
- var element = document.getElementById("22413187-104d-479c-9a91-8249ba12fe4e");
20
  if (element == null) {
21
- console.warn("Bokeh: autoload.js configured with elementid '22413187-104d-479c-9a91-8249ba12fe4e' but no matching script tag was found.")
22
  }
23
 
24
 
@@ -115,8 +115,8 @@
115
  (function(root) {
116
  function embed_document(root) {
117
 
118
- var docs_json = '{"e28b944a-16ba-49cc-a930-4adf014f113a":{"roots":{"references":[{"attributes":{"above":[{"id":"1055"}],"below":[{"id":"1012"}],"center":[{"id":"1014"},{"id":"1018"},{"id":"1037"}],"left":[{"id":"1015"}],"outline_line_color":null,"plot_height":400,"renderers":[{"id":"1028"},{"id":"1043"}],"title":{"id":"1002"},"toolbar":{"id":"1019"},"toolbar_location":null,"x_range":{"id":"1004"},"x_scale":{"id":"1008"},"y_range":{"id":"1006"},"y_scale":{"id":"1010"}},"id":"1001","subtype":"Figure","type":"Plot"},{"attributes":{"bottom":{"expr":{"id":"1022"}},"fill_color":{"value":"#ffcccc"},"line_color":{"value":"#ffcccc"},"top":{"expr":{"id":"1023"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1041","type":"VBar"},{"attributes":{"fields":["active"]},"id":"1022","type":"Stack"},{"attributes":{"axis":{"id":"1012"},"grid_line_color":null,"ticker":null},"id":"1014","type":"Grid"},{"attributes":{},"id":"1008","type":"CategoricalScale"},{"attributes":{"data":{"active":[11,12,11,10,12,11,10,10,11,7,9,8],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[1,0,1,2,0,1,2,2,1,5,3,4]},"selected":{"id":"1036"},"selection_policy":{"id":"1035"}},"id":"1024","type":"ColumnDataSource"},{"attributes":{"fields":["active","pruned"]},"id":"1023","type":"Stack"},{"attributes":{},"id":"1013","type":"CategoricalTicker"},{"attributes":{"factors":["0","1","2","3","4","5","6","7","8","9","10","11"],"range_padding":0.1},"id":"1004","type":"FactorRange"},{"attributes":{"source":{"id":"1024"}},"id":"1029","type":"CDSView"},{"attributes":{"bottom":{"expr":{"id":"1020"}},"fill_color":{"value":"#0000ff"},"line_color":{"value":"#0000ff"},"top":{"expr":{"id":"1021"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1026","type":"VBar"},{"attributes":{"start":0},"id":"1006","type":"DataRange1d"},{"attributes":{"text":"Pruned Transformer Heads"},"id":"1002","type":"Title"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1038","type":"LegendItem"},{"attributes":{"bottom":{"expr":{"id":"1020"}},"fill_alpha":{"value":0.1},"fill_color":{"value":"#0000ff"},"line_alpha":{"value":0.1},"line_color":{"value":"#0000ff"},"top":{"expr":{"id":"1021"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1027","type":"VBar"},{"attributes":{"axis_label":"Layer index","formatter":{"id":"1031"},"minor_tick_line_color":null,"ticker":{"id":"1013"}},"id":"1012","type":"CategoricalAxis"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto"},"id":"1019","type":"Toolbar"},{"attributes":{},"id":"1010","type":"LinearScale"},{"attributes":{"data_source":{"id":"1024"},"glyph":{"id":"1026"},"hover_glyph":null,"muted_glyph":null,"name":"active","nonselection_glyph":{"id":"1027"},"selection_glyph":null,"view":{"id":"1029"}},"id":"1028","type":"GlyphRenderer"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1057","type":"LegendItem"},{"attributes":{},"id":"1035","type":"UnionRenderers"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1056","type":"LegendItem"},{"attributes":{},"id":"1036","type":"Selection"},{"attributes":{},"id":"1033","type":"BasicTickFormatter"},{"attributes":{"fields":[]},"id":"1020","type":"Stack"},{"attributes":{"axis_label":"Heads count","formatter":{"id":"1033"},"minor_tick_line_color":null,"ticker":{"id":"1016"}},"id":"1015","type":"LinearAxis"},{"attributes":{"axis":{"id":"1015"},"dimension":1,"ticker":null},"id":"1018","type":"Grid"},{"attributes":{},"id":"1016","type":"BasicTicker"},{"attributes":{"items":[{"id":"1038"},{"id":"1054"}],"location":null},"id":"1037","type":"Legend"},{"attributes":{"fields":["active"]},"id":"1021","type":"Stack"},{"attributes":{"items":[{"id":"1056"},{"id":"1057"}],"location":[10,0],"orientation":"horizontal"},"id":"1055","type":"Legend"},{"attributes":{"data":{"active":[11,12,11,10,12,11,10,10,11,7,9,8],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[1,0,1,2,0,1,2,2,1,5,3,4]},"selected":{"id":"1053"},"selection_policy":{"id":"1052"}},"id":"1039","type":"ColumnDataSource"},{"attributes":{"bottom":{"expr":{"id":"1022"}},"fill_alpha":{"value":0.1},"fill_color":{"value":"#ffcccc"},"line_alpha":{"value":0.1},"line_color":{"value":"#ffcccc"},"top":{"expr":{"id":"1023"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1042","type":"VBar"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1054","type":"LegendItem"},{"attributes":{"data_source":{"id":"1039"},"glyph":{"id":"1041"},"hover_glyph":null,"muted_glyph":null,"name":"pruned","nonselection_glyph":{"id":"1042"},"selection_glyph":null,"view":{"id":"1044"}},"id":"1043","type":"GlyphRenderer"},{"attributes":{},"id":"1053","type":"Selection"},{"attributes":{"source":{"id":"1039"}},"id":"1044","type":"CDSView"},{"attributes":{},"id":"1031","type":"CategoricalTickFormatter"},{"attributes":{},"id":"1052","type":"UnionRenderers"}],"root_ids":["1001"]},"title":"Bokeh Application","version":"2.2.3"}}';
119
- var render_items = [{"docid":"e28b944a-16ba-49cc-a930-4adf014f113a","root_ids":["1001"],"roots":{"1001":"22413187-104d-479c-9a91-8249ba12fe4e"}}];
120
  root.Bokeh.embed.embed_items(docs_json, render_items);
121
 
122
  }
16
 
17
 
18
 
19
+ var element = document.getElementById("55528c8b-d5f5-46a5-a35a-dad93725f7e5");
20
  if (element == null) {
21
+ console.warn("Bokeh: autoload.js configured with elementid '55528c8b-d5f5-46a5-a35a-dad93725f7e5' but no matching script tag was found.")
22
  }
23
 
24
 
115
  (function(root) {
116
  function embed_document(root) {
117
 
118
+ var docs_json = '{"138af068-f77d-4c4f-971d-d66194a2fb97":{"roots":{"references":[{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1057","type":"LegendItem"},{"attributes":{"above":[{"id":"1055"}],"below":[{"id":"1012"}],"center":[{"id":"1014"},{"id":"1018"},{"id":"1037"}],"left":[{"id":"1015"}],"outline_line_color":null,"plot_height":400,"renderers":[{"id":"1028"},{"id":"1043"}],"title":{"id":"1002"},"toolbar":{"id":"1019"},"toolbar_location":null,"x_range":{"id":"1004"},"x_scale":{"id":"1008"},"y_range":{"id":"1006"},"y_scale":{"id":"1010"}},"id":"1001","subtype":"Figure","type":"Plot"},{"attributes":{"source":{"id":"1024"}},"id":"1029","type":"CDSView"},{"attributes":{"axis_label":"Layer index","formatter":{"id":"1032"},"minor_tick_line_color":null,"ticker":{"id":"1013"}},"id":"1012","type":"CategoricalAxis"},{"attributes":{},"id":"1035","type":"Selection"},{"attributes":{"data":{"active":[11,12,11,10,12,11,10,10,11,7,9,8],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[1,0,1,2,0,1,2,2,1,5,3,4]},"selected":{"id":"1052"},"selection_policy":{"id":"1053"}},"id":"1039","type":"ColumnDataSource"},{"attributes":{"start":0},"id":"1006","type":"DataRange1d"},{"attributes":{},"id":"1036","type":"UnionRenderers"},{"attributes":{"items":[{"id":"1038"},{"id":"1054"}],"location":null},"id":"1037","type":"Legend"},{"attributes":{},"id":"1008","type":"CategoricalScale"},{"attributes":{"axis":{"id":"1012"},"grid_line_color":null,"ticker":null},"id":"1014","type":"Grid"},{"attributes":{},"id":"1013","type":"CategoricalTicker"},{"attributes":{},"id":"1052","type":"Selection"},{"attributes":{},"id":"1053","type":"UnionRenderers"},{"attributes":{"fields":[]},"id":"1020","type":"Stack"},{"attributes":{"bottom":{"expr":{"id":"1020"}},"fill_alpha":{"value":0.1},"fill_color":{"value":"#0000ff"},"line_alpha":{"value":0.1},"line_color":{"value":"#0000ff"},"top":{"expr":{"id":"1021"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1027","type":"VBar"},{"attributes":{"data_source":{"id":"1024"},"glyph":{"id":"1026"},"hover_glyph":null,"muted_glyph":null,"name":"active","nonselection_glyph":{"id":"1027"},"selection_glyph":null,"view":{"id":"1029"}},"id":"1028","type":"GlyphRenderer"},{"attributes":{"fields":["active"]},"id":"1022","type":"Stack"},{"attributes":{"text":"Pruned Transformer Heads"},"id":"1002","type":"Title"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto"},"id":"1019","type":"Toolbar"},{"attributes":{"factors":["0","1","2","3","4","5","6","7","8","9","10","11"],"range_padding":0.1},"id":"1004","type":"FactorRange"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1056","type":"LegendItem"},{"attributes":{"items":[{"id":"1056"},{"id":"1057"}],"location":[10,0],"orientation":"horizontal"},"id":"1055","type":"Legend"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1038","type":"LegendItem"},{"attributes":{"source":{"id":"1039"}},"id":"1044","type":"CDSView"},{"attributes":{"bottom":{"expr":{"id":"1022"}},"fill_color":{"value":"#ffcccc"},"line_color":{"value":"#ffcccc"},"top":{"expr":{"id":"1023"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1041","type":"VBar"},{"attributes":{},"id":"1032","type":"CategoricalTickFormatter"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1054","type":"LegendItem"},{"attributes":{"fields":["active"]},"id":"1021","type":"Stack"},{"attributes":{"axis":{"id":"1015"},"dimension":1,"ticker":null},"id":"1018","type":"Grid"},{"attributes":{"bottom":{"expr":{"id":"1022"}},"fill_alpha":{"value":0.1},"fill_color":{"value":"#ffcccc"},"line_alpha":{"value":0.1},"line_color":{"value":"#ffcccc"},"top":{"expr":{"id":"1023"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1042","type":"VBar"},{"attributes":{"fields":["active","pruned"]},"id":"1023","type":"Stack"},{"attributes":{},"id":"1034","type":"BasicTickFormatter"},{"attributes":{"data_source":{"id":"1039"},"glyph":{"id":"1041"},"hover_glyph":null,"muted_glyph":null,"name":"pruned","nonselection_glyph":{"id":"1042"},"selection_glyph":null,"view":{"id":"1044"}},"id":"1043","type":"GlyphRenderer"},{"attributes":{},"id":"1010","type":"LinearScale"},{"attributes":{},"id":"1016","type":"BasicTicker"},{"attributes":{"axis_label":"Heads count","formatter":{"id":"1034"},"minor_tick_line_color":null,"ticker":{"id":"1016"}},"id":"1015","type":"LinearAxis"},{"attributes":{"bottom":{"expr":{"id":"1020"}},"fill_color":{"value":"#0000ff"},"line_color":{"value":"#0000ff"},"top":{"expr":{"id":"1021"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1026","type":"VBar"},{"attributes":{"data":{"active":[11,12,11,10,12,11,10,10,11,7,9,8],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[1,0,1,2,0,1,2,2,1,5,3,4]},"selected":{"id":"1035"},"selection_policy":{"id":"1036"}},"id":"1024","type":"ColumnDataSource"}],"root_ids":["1001"]},"title":"Bokeh Application","version":"2.2.3"}}';
119
+ var render_items = [{"docid":"138af068-f77d-4c4f-971d-d66194a2fb97","root_ids":["1001"],"roots":{"1001":"55528c8b-d5f5-46a5-a35a-dad93725f7e5"}}];
120
  root.Bokeh.embed.embed_items(docs_json, render_items);
121
 
122
  }
model_info.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squad_test_8_mvp_lt/hp_od-__data_2to__devel_data__nn_pruning__output__squad_test_8_mvp_lt___es-steps_nte20_ls250_stl50_est5000_rn-__data_2to__devel_data__nn_pruning__output__squad_test_8_mvp_lt___dpm-si--7fe43555f854fbb6/checkpoint-110000",
3
+ "config": {
4
+ "_name_or_path": "/tmp/tmpdczbpf2s",
5
+ "architectures": ["BertForQuestionAnswering"],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "pruned_heads": {
21
+ "0": [9],
22
+ "1": [],
23
+ "10": [1, 2, 4],
24
+ "11": [5, 7, 8, 11],
25
+ "2": [8],
26
+ "3": [2, 4],
27
+ "4": [],
28
+ "5": [1],
29
+ "6": [2, 3],
30
+ "7": [1, 7],
31
+ "8": [0],
32
+ "9": [1, 4, 5, 7, 10]
33
+ },
34
+ "transformers_version": "4.4.2",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ },
39
+ "eval_metrics": {
40
+ "exact_match": 80.93661305581836,
41
+ "f1": 88.11360890595924,
42
+ "main_metric": 88.11360890595924
43
+ },
44
+ "model_args": {
45
+ "cache_dir": null,
46
+ "config_name": null,
47
+ "model_name_or_path": "bert-base-uncased",
48
+ "tokenizer_name": null,
49
+ "use_fast_tokenizer": true
50
+ },
51
+ "sparse_args": {
52
+ "ampere_pruning_method": "disabled",
53
+ "attention_block_cols": 1,
54
+ "attention_block_rows": 1,
55
+ "attention_lambda": 1.0,
56
+ "attention_output_with_dense": 0,
57
+ "attention_pruning_method": "sigmoied_threshold",
58
+ "bias_mask": true,
59
+ "dense_block_cols": 1,
60
+ "dense_block_rows": 1,
61
+ "dense_lambda": 1.0,
62
+ "dense_pruning_method": "sigmoied_threshold",
63
+ "distil_alpha_ce": 0.1,
64
+ "distil_alpha_teacher": 0.9,
65
+ "distil_teacher_name_or_path": "bert-large-uncased-whole-word-masking-finetuned-squad",
66
+ "distil_temperature": 2.0,
67
+ "final_ampere_temperature": 20.0,
68
+ "final_finetune": false,
69
+ "final_threshold": 0.1,
70
+ "final_warmup": 10,
71
+ "gelu_patch": 0,
72
+ "initial_ampere_temperature": 0.0,
73
+ "initial_threshold": 0,
74
+ "initial_warmup": 1,
75
+ "layer_norm_patch": 0,
76
+ "mask_init": "constant",
77
+ "mask_scale": 0.0,
78
+ "mask_scores_learning_rate": 0.01,
79
+ "regularization": "l1",
80
+ "regularization_final_lambda": 120
81
+ },
82
+ "speed": {
83
+ "cuda_eval_elapsed_time": 33.17768461608887,
84
+ "eval_elapsed_time": 40.18306041043252
85
+ },
86
+ "speedup": 1.1632636047982534,
87
+ "stats": {
88
+ "layers": {
89
+ "0": {
90
+ "linear_attention_nnz": 108638,
91
+ "linear_attention_total": 2359296,
92
+ "linear_dense_nnz": 743508,
93
+ "linear_dense_total": 4718592,
94
+ "linear_nnz": 852146,
95
+ "linear_total": 7077888,
96
+ "nnz": 860873,
97
+ "total": 7087872
98
+ },
99
+ "1": {
100
+ "linear_attention_nnz": 171340,
101
+ "linear_attention_total": 2359296,
102
+ "linear_dense_nnz": 780119,
103
+ "linear_dense_total": 4718592,
104
+ "linear_nnz": 951459,
105
+ "linear_total": 7077888,
106
+ "nnz": 960245,
107
+ "total": 7087872
108
+ },
109
+ "10": {
110
+ "linear_attention_nnz": 67316,
111
+ "linear_attention_total": 2359296,
112
+ "linear_dense_nnz": 69353,
113
+ "linear_dense_total": 4718592,
114
+ "linear_nnz": 136669,
115
+ "linear_total": 7077888,
116
+ "nnz": 143162,
117
+ "total": 7087872
118
+ },
119
+ "11": {
120
+ "linear_attention_nnz": 41497,
121
+ "linear_attention_total": 2359296,
122
+ "linear_dense_nnz": 55855,
123
+ "linear_dense_total": 4718592,
124
+ "linear_nnz": 97352,
125
+ "linear_total": 7077888,
126
+ "nnz": 103286,
127
+ "total": 7087872
128
+ },
129
+ "2": {
130
+ "linear_attention_nnz": 221074,
131
+ "linear_attention_total": 2359296,
132
+ "linear_dense_nnz": 756625,
133
+ "linear_dense_total": 4718592,
134
+ "linear_nnz": 977699,
135
+ "linear_total": 7077888,
136
+ "nnz": 986901,
137
+ "total": 7087872
138
+ },
139
+ "3": {
140
+ "linear_attention_nnz": 258229,
141
+ "linear_attention_total": 2359296,
142
+ "linear_dense_nnz": 705908,
143
+ "linear_dense_total": 4718592,
144
+ "linear_nnz": 964137,
145
+ "linear_total": 7077888,
146
+ "nnz": 973427,
147
+ "total": 7087872
148
+ },
149
+ "4": {
150
+ "linear_attention_nnz": 255136,
151
+ "linear_attention_total": 2359296,
152
+ "linear_dense_nnz": 593338,
153
+ "linear_dense_total": 4718592,
154
+ "linear_nnz": 848474,
155
+ "linear_total": 7077888,
156
+ "nnz": 858037,
157
+ "total": 7087872
158
+ },
159
+ "5": {
160
+ "linear_attention_nnz": 179994,
161
+ "linear_attention_total": 2359296,
162
+ "linear_dense_nnz": 531061,
163
+ "linear_dense_total": 4718592,
164
+ "linear_nnz": 711055,
165
+ "linear_total": 7077888,
166
+ "nnz": 720395,
167
+ "total": 7087872
168
+ },
169
+ "6": {
170
+ "linear_attention_nnz": 165167,
171
+ "linear_attention_total": 2359296,
172
+ "linear_dense_nnz": 406391,
173
+ "linear_dense_total": 4718592,
174
+ "linear_nnz": 571558,
175
+ "linear_total": 7077888,
176
+ "nnz": 580963,
177
+ "total": 7087872
178
+ },
179
+ "7": {
180
+ "linear_attention_nnz": 139907,
181
+ "linear_attention_total": 2359296,
182
+ "linear_dense_nnz": 272514,
183
+ "linear_dense_total": 4718592,
184
+ "linear_nnz": 412421,
185
+ "linear_total": 7077888,
186
+ "nnz": 421032,
187
+ "total": 7087872
188
+ },
189
+ "8": {
190
+ "linear_attention_nnz": 113253,
191
+ "linear_attention_total": 2359296,
192
+ "linear_dense_nnz": 163778,
193
+ "linear_dense_total": 4718592,
194
+ "linear_nnz": 277031,
195
+ "linear_total": 7077888,
196
+ "nnz": 285536,
197
+ "total": 7087872
198
+ },
199
+ "9": {
200
+ "linear_attention_nnz": 84915,
201
+ "linear_attention_total": 2359296,
202
+ "linear_dense_nnz": 71190,
203
+ "linear_dense_total": 4718592,
204
+ "linear_nnz": 156105,
205
+ "linear_total": 7077888,
206
+ "nnz": 162775,
207
+ "total": 7087872
208
+ }
209
+ },
210
+ "linear_nnz": 6956106,
211
+ "linear_sparsity": 91.81004983407479,
212
+ "linear_total": 84934656,
213
+ "nnz": 30895354,
214
+ "pruned_heads": {
215
+ "0": [9],
216
+ "1": [],
217
+ "10": [1, 2, 4],
218
+ "11": [8, 11, 5, 7],
219
+ "2": [8],
220
+ "3": [2, 4],
221
+ "4": [],
222
+ "5": [1],
223
+ "6": [2, 3],
224
+ "7": [1, 7],
225
+ "8": [0],
226
+ "9": [1, 4, 5, 7, 10]
227
+ },
228
+ "total": 108893186,
229
+ "total_sparsity": 71.62783537254572
230
+ },
231
+ "training_args": {
232
+ "_n_gpu": -1,
233
+ "adafactor": false,
234
+ "adam_beta1": 0.9,
235
+ "adam_beta2": 0.999,
236
+ "adam_epsilon": 1e-08,
237
+ "dataloader_drop_last": false,
238
+ "dataloader_num_workers": 0,
239
+ "dataloader_pin_memory": true,
240
+ "ddp_find_unused_parameters": null,
241
+ "debug": false,
242
+ "deepspeed": null,
243
+ "disable_tqdm": false,
244
+ "do_eval": 1,
245
+ "do_predict": false,
246
+ "do_train": 1,
247
+ "eval_accumulation_steps": null,
248
+ "eval_steps": 5000,
249
+ "evaluation_strategy": "steps",
250
+ "fp16": false,
251
+ "fp16_backend": "auto",
252
+ "fp16_full_eval": false,
253
+ "fp16_opt_level": "O1",
254
+ "gradient_accumulation_steps": 1,
255
+ "greater_is_better": null,
256
+ "group_by_length": false,
257
+ "ignore_data_skip": false,
258
+ "label_names": null,
259
+ "label_smoothing_factor": 0.0,
260
+ "learning_rate": 3e-05,
261
+ "length_column_name": "length",
262
+ "load_best_model_at_end": false,
263
+ "local_rank": -1,
264
+ "logging_dir": "/data_2to/devel_data/nn_pruning/output/squad_test_8_mvp_lt/",
265
+ "logging_first_step": false,
266
+ "logging_steps": 250,
267
+ "logging_strategy": "steps",
268
+ "lr_scheduler_type": "linear",
269
+ "max_grad_norm": 1.0,
270
+ "max_steps": -1,
271
+ "metric_for_best_model": null,
272
+ "mp_parameters": "",
273
+ "no_cuda": false,
274
+ "num_train_epochs": 20,
275
+ "optimize_model_before_eval": "disabled",
276
+ "output_dir": "/data_2to/devel_data/nn_pruning/output/squad_test_8_mvp_lt/",
277
+ "overwrite_output_dir": 1,
278
+ "past_index": -1,
279
+ "per_device_eval_batch_size": 8,
280
+ "per_device_train_batch_size": 16,
281
+ "per_gpu_eval_batch_size": null,
282
+ "per_gpu_train_batch_size": null,
283
+ "prediction_loss_only": false,
284
+ "remove_unused_columns": true,
285
+ "report_to": null,
286
+ "run_name": "/data_2to/devel_data/nn_pruning/output/squad_test_8_mvp_lt/",
287
+ "save_steps": 5000,
288
+ "save_strategy": "steps",
289
+ "save_total_limit": 50,
290
+ "seed": 17,
291
+ "sharded_ddp": "",
292
+ "skip_memory_metrics": false,
293
+ "tpu_metrics_debug": false,
294
+ "tpu_num_cores": null,
295
+ "warmup_ratio": 0.0,
296
+ "warmup_steps": 5400,
297
+ "weight_decay": 0.0
298
+ }
299
+ }
training/data_args.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_cache_dir": "dataset_cache",
3
+ "dataset_config_name": null,
4
+ "dataset_name": "squad",
5
+ "doc_stride": 128,
6
+ "max_answer_length": 30,
7
+ "max_seq_length": 384,
8
+ "n_best_size": 20,
9
+ "null_score_diff_threshold": 0.0,
10
+ "overwrite_cache": 0,
11
+ "pad_to_max_length": true,
12
+ "preprocessing_num_workers": null,
13
+ "train_file": null,
14
+ "validation_file": null,
15
+ "version_2_with_negative": false
16
+ }
training/model_args.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cache_dir": null,
3
+ "config_name": null,
4
+ "model_name_or_path": "bert-base-uncased",
5
+ "tokenizer_name": null,
6
+ "use_fast_tokenizer": true
7
+ }
training/sparse_args.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ampere_pruning_method": "disabled",
3
+ "attention_block_cols": 1,
4
+ "attention_block_rows": 1,
5
+ "attention_lambda": 1.0,
6
+ "attention_output_with_dense": 0,
7
+ "attention_pruning_method": "sigmoied_threshold",
8
+ "bias_mask": true,
9
+ "dense_block_cols": 1,
10
+ "dense_block_rows": 1,
11
+ "dense_lambda": 1.0,
12
+ "dense_pruning_method": "sigmoied_threshold",
13
+ "distil_alpha_ce": 0.1,
14
+ "distil_alpha_teacher": 0.9,
15
+ "distil_teacher_name_or_path": "bert-large-uncased-whole-word-masking-finetuned-squad",
16
+ "distil_temperature": 2.0,
17
+ "final_ampere_temperature": 20.0,
18
+ "final_finetune": false,
19
+ "final_threshold": 0.1,
20
+ "final_warmup": 10,
21
+ "gelu_patch": 0,
22
+ "initial_ampere_temperature": 0.0,
23
+ "initial_threshold": 0,
24
+ "initial_warmup": 1,
25
+ "layer_norm_patch": 0,
26
+ "mask_init": "constant",
27
+ "mask_scale": 0.0,
28
+ "mask_scores_learning_rate": 0.01,
29
+ "regularization": "l1",
30
+ "regularization_final_lambda": 120
31
+ }
training/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1491e45d592bbfbd8af86cc5f4323b46c07a03e1a9fdb85da4041bb3e14f7e97
3
+ size 1967