Adding model, graphs and metadata.

Browse files

Files changed (14) hide show

README.md +11 -4
eval/eval_metrics.json +4 -0
eval/evaluate_timing.json +1 -0
eval/nbest_predictions.json.tgz +0 -0
eval/predictions.json +0 -0
eval/sparsity_report.json +1 -0
eval/speed_report.json +1 -0
model_card/density_info.js +4 -4
model_card/pruning_info.js +4 -4
model_info.json +295 -0
training/data_args.json +16 -0
training/model_args.json +6 -0
training/sparse_args.json +29 -0
training/training_args.bin +3 -0

README.md CHANGED Viewed

@@ -21,22 +21,24 @@ widget:
 This model was created using the [nn_pruning](https://github.com/huggingface/nn_pruning) python library: the **linear layers contains 26.0%** of the original weights.
 The model contains **42.0%** of the original weights **overall** (the embeddings account for a significant part of the model, and they are not pruned by this method).
 With a simple resizing of the linear matrices it ran **2.44x as fast as BERT-base** on the evaluation.
 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.
-<div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/density_info.js" id="97855ddc-561d-447e-b31f-ff2514f18cc2"></script></div>
-In terms of accuracy, its **F1 is 87.71**, compared with 88.5 for BERT-base, a **F1 drop of -0.79**.
 ## Fine-Pruning details
-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 equivalent model [csarron/bert-base-uncased-squad-v1](https://huggingface.co/csarron/bert-base-uncased-squad-v1).
 This model is case-insensitive: it does not make a difference between english and English.
 A side-effect of the block pruning is that some of the attention heads are completely removed: 80 heads were removed on a total of 144 (55.6%).
 Here is a detailed view on how the remaining heads are distributed in the network after pruning.
-<div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/pruning_info.js" id="22fe1a34-3ff7-4b5e-9fd8-5574ce7d15ac"></script></div>
 ## Details of the SQuAD1.1 dataset
@@ -66,6 +68,11 @@ GPU driver: 455.23.05, CUDA: 11.1
 | **F1** | **87.71** | **88.5** | **-0.79**|
 ## Example Usage
 ```python
 from transformers import pipeline

 This model was created using the [nn_pruning](https://github.com/huggingface/nn_pruning) python library: the **linear layers contains 26.0%** of the original weights.
 The model contains **42.0%** of the original weights **overall** (the embeddings account for a significant part of the model, and they are not pruned by this method).
 With a simple resizing of the linear matrices it ran **2.44x as fast as BERT-base** on the evaluation.
 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.
+<div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/density_info.js" id="5787ef08-ec97-4223-80fb-b7d410af7b37"></script></div>
+In terms of accuracy, its **F1 is 87.71**, compared with 88.5 for BERT-base, a **F1 drop of 0.79**.
 ## Fine-Pruning details
+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 [csarron/bert-base-uncased-squad-v1](https://huggingface.co/csarron/bert-base-uncased-squad-v1).
 This model is case-insensitive: it does not make a difference between english and English.
 A side-effect of the block pruning is that some of the attention heads are completely removed: 80 heads were removed on a total of 144 (55.6%).
 Here is a detailed view on how the remaining heads are distributed in the network after pruning.
+<div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/pruning_info.js" id="a936580a-5d72-4995-9a5a-86f6c50c2855"></script></div>
 ## Details of the SQuAD1.1 dataset
 | **F1** | **87.71** | **88.5** | **-0.79**|
 ## Example Usage
+Install nn_pruning: it contains the optimization script, which just pack the linear layers into smaller ones by removing empty rows/columns.
+`pip install nn_pruning`
+Then you can use the `transformers library` almost as usual: you just have to call `optimize_model` when the pipeline has loaded.
 ```python
 from transformers import pipeline

eval/eval_metrics.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+    "exact_match": 80.01892147587512,
+    "f1": 87.70534763770029
+}

eval/evaluate_timing.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"eval_elapsed_time": 22.60543141514063}

eval/nbest_predictions.json.tgz ADDED Viewed

Binary file (6.63 MB). View file

eval/predictions.json ADDED Viewed

The diff for this file is too large to render. See raw diff

eval/sparsity_report.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"total": 108877826, "nnz": 46161559, "linear_total": 84934656, "linear_nnz": 22248960, "layers": {"0": {"total": 7086336, "nnz": 1640232, "linear_total": 7077888, "linear_nnz": 1634304, "linear_attention_total": 2359296, "linear_attention_nnz": 786432, "linear_dense_total": 4718592, "linear_dense_nnz": 847872}, "1": {"total": 7086336, "nnz": 1893837, "linear_total": 7077888, "linear_nnz": 1887744, "linear_attention_total": 2359296, "linear_attention_nnz": 786432, "linear_dense_total": 4718592, "linear_dense_nnz": 1101312}, "2": {"total": 7086720, "nnz": 2407323, "linear_total": 7077888, "linear_nnz": 2400768, "linear_attention_total": 2359296, "linear_attention_nnz": 1179648, "linear_dense_total": 4718592, "linear_dense_nnz": 1221120}, "3": {"total": 7086912, "nnz": 2594901, "linear_total": 7077888, "linear_nnz": 2588160, "linear_attention_total": 2359296, "linear_attention_nnz": 1376256, "linear_dense_total": 4718592, "linear_dense_nnz": 1211904}, "4": {"total": 7086912, "nnz": 2662529, "linear_total": 7077888, "linear_nnz": 2655744, "linear_attention_total": 2359296, "linear_attention_nnz": 1376256, "linear_dense_total": 4718592, "linear_dense_nnz": 1279488}, "5": {"total": 7086528, "nnz": 2205912, "linear_total": 7077888, "linear_nnz": 2199552, "linear_attention_total": 2359296, "linear_attention_nnz": 983040, "linear_dense_total": 4718592, "linear_dense_nnz": 1216512}, "6": {"total": 7086720, "nnz": 2138348, "linear_total": 7077888, "linear_nnz": 2131968, "linear_attention_total": 2359296, "linear_attention_nnz": 1179648, "linear_dense_total": 4718592, "linear_dense_nnz": 952320}, "7": {"total": 7086912, "nnz": 2098450, "linear_total": 7077888, "linear_nnz": 2092032, "linear_attention_total": 2359296, "linear_attention_nnz": 1376256, "linear_dense_total": 4718592, "linear_dense_nnz": 715776}, "8": {"total": 7086528, "nnz": 1423579, "linear_total": 7077888, "linear_nnz": 1417728, "linear_attention_total": 2359296, "linear_attention_nnz": 983040, "linear_dense_total": 4718592, "linear_dense_nnz": 434688}, "9": {"total": 7086528, "nnz": 1160752, "linear_total": 7077888, "linear_nnz": 1155072, "linear_attention_total": 2359296, "linear_attention_nnz": 983040, "linear_dense_total": 4718592, "linear_dense_nnz": 172032}, "10": {"total": 7086528, "nnz": 1136160, "linear_total": 7077888, "linear_nnz": 1130496, "linear_attention_total": 2359296, "linear_attention_nnz": 983040, "linear_dense_total": 4718592, "linear_dense_nnz": 147456}, "11": {"total": 7086144, "nnz": 960814, "linear_total": 7077888, "linear_nnz": 955392, "linear_attention_total": 2359296, "linear_attention_nnz": 589824, "linear_dense_total": 4718592, "linear_dense_nnz": 365568}}, "total_sparsity": 57.602424023418685, "linear_sparsity": 73.80461516203704, "pruned_heads": {"0": [0, 2, 4, 5, 6, 7, 9, 11], "1": [0, 2, 3, 5, 6, 7, 8, 9], "2": [1, 2, 4, 7, 8, 11], "3": [2, 4, 6, 7, 10], "4": [0, 1, 2, 6, 11], "5": [0, 1, 2, 5, 6, 7, 11], "6": [0, 2, 3, 4, 7, 10], "7": [1, 3, 6, 7, 11], "8": [0, 1, 2, 3, 4, 6, 8], "9": [1, 3, 4, 5, 7, 9, 10], "10": [1, 4, 5, 6, 7, 8, 9], "11": [0, 2, 3, 5, 6, 7, 8, 10, 11]}}

eval/speed_report.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"timings": {"eval_elapsed_time": 22.999519595876336, "cuda_eval_elapsed_time": 15.838374267578125}, "metrics": {"exact_match": 80.02838221381268, "f1": 87.70940223967354}}

model_card/density_info.js CHANGED Viewed

@@ -16,9 +16,9 @@
-      var element = document.getElementById("97855ddc-561d-447e-b31f-ff2514f18cc2");
         if (element == null) {
-          console.warn("Bokeh: autoload.js configured with elementid '97855ddc-561d-447e-b31f-ff2514f18cc2' but no matching script tag was found.")
         }
@@ -115,8 +115,8 @@
                 (function(root) {
                   function embed_document(root) {
-                  var docs_json = '{"42cc26ba-43eb-4190-9dae-f35f89db9fa6":{"roots":{"references":[{"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":{},"id":"1152","type":"UnionRenderers"},{"attributes":{},"id":"1153","type":"Selection"},{"attributes":{"data":{"density":["33.3%","18.0%","18.0%","33.3%","23.3%","23.3%","50.0%","25.9%","25.9%","58.3%","25.7%","25.7%","58.3%","27.1%","27.1%","41.7%","25.8%","25.8%","50.0%","20.2%","20.2%","58.3%","15.2%","15.2%","41.7%","9.2%","9.2%","41.7%","3.6%","3.6%","41.7%","3.1%","3.1%","25.0%","7.7%","7.7%"],"height":[0.196608,0.423936,0.423936,0.196608,0.550656,0.550656,0.294912,0.61056,0.61056,0.344064,0.605952,0.605952,0.344064,0.639744,0.639744,0.24576,0.608256,0.608256,0.294912,0.47616,0.47616,0.344064,0.357888,0.357888,0.24576,0.217344,0.217344,0.24576,0.086016,0.086016,0.24576,0.073728,0.073728,0.147456,0.182784,0.182784],"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":["0.20","0.42","0.42","0.20","0.55","0.55","0.29","0.61","0.61","0.34","0.61","0.61","0.34","0.64","0.64","0.25","0.61","0.61","0.29","0.48","0.48","0.34","0.36","0.36","0.25","0.22","0.22","0.25","0.09","0.09","0.25","0.07","0.07","0.15","0.18","0.18"],"url":["/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_11_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_11_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-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":{"fill_color":{"value":"#aa69f7"},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1136","type":"VBar"},{"attributes":{"items":[{"id":"1141"},{"id":"1142"},{"id":"1143"},{"id":"1144"}],"location":[10,0],"orientation":"horizontal"},"id":"1140","type":"Legend"},{"attributes":{},"id":"1151","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":{"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":"1134"}},"id":"1139","type":"CDSView"},{"attributes":{},"id":"1146","type":"BasicTickFormatter"},{"attributes":{"label":{"value":"query"},"renderers":[{"id":"1120"}]},"id":"1141","type":"LegendItem"},{"attributes":{"label":{"value":"key"},"renderers":[{"id":"1126"}]},"id":"1142","type":"LegendItem"},{"attributes":{},"id":"1157","type":"Selection"},{"attributes":{},"id":"1156","type":"UnionRenderers"},{"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":"#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":{"fill_color":{"value":"#ed5642"},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1124","type":"VBar"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto","tools":[{"id":"1094"}]},"id":"1114","type":"Toolbar"},{"attributes":{"data":{"density":["33.3%","33.3%","50.0%","58.3%","58.3%","41.7%","50.0%","58.3%","41.7%","41.7%","41.7%","25.0%"],"height":[0.196608,0.196608,0.294912,0.344064,0.344064,0.24576,0.294912,0.344064,0.24576,0.24576,0.24576,0.147456],"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":["0.20","0.20","0.29","0.34","0.34","0.25","0.29","0.34","0.25","0.25","0.25","0.15"],"url":["/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-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":{"source":{"id":"1128"}},"id":"1133","type":"CDSView"},{"attributes":{"label":{"value":"value"},"renderers":[{"id":"1132"}]},"id":"1143","type":"LegendItem"},{"attributes":{},"id":"1148","type":"BasicTickFormatter"},{"attributes":{},"id":"1111","type":"BasicTicker"},{"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":{"axis_label":"Parameters (M)","formatter":{"id":"1148"},"minor_tick_line_color":null,"ticker":{"id":"1111"}},"id":"1110","type":"LinearAxis"},{"attributes":{"label":{"value":"fully connected"},"renderers":[{"id":"1138"}]},"id":"1144","type":"LegendItem"},{"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":{"source":{"id":"1116"}},"id":"1121","type":"CDSView"},{"attributes":{"data":{"density":["33.3%","33.3%","50.0%","58.3%","58.3%","41.7%","50.0%","58.3%","41.7%","41.7%","41.7%","25.0%"],"height":[0.196608,0.196608,0.294912,0.344064,0.344064,0.24576,0.294912,0.344064,0.24576,0.24576,0.24576,0.147456],"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":["0.20","0.20","0.29","0.34","0.34","0.25","0.29","0.34","0.25","0.25","0.25","0.15"],"url":["/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-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":{"axis":{"id":"1110"},"dimension":1,"ticker":null},"id":"1113","type":"Grid"},{"attributes":{},"id":"1102","type":"LinearScale"},{"attributes":{"axis":{"id":"1106"},"grid_line_color":null,"ticker":null},"id":"1109","type":"Grid"},{"attributes":{},"id":"1150","type":"UnionRenderers"},{"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":{"data":{"density":["33.3%","33.3%","50.0%","58.3%","58.3%","41.7%","50.0%","58.3%","41.7%","41.7%","41.7%","25.0%"],"height":[0.196608,0.196608,0.294912,0.344064,0.344064,0.24576,0.294912,0.344064,0.24576,0.24576,0.24576,0.147456],"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":["0.20","0.20","0.29","0.34","0.34","0.25","0.29","0.34","0.25","0.25","0.25","0.15"],"url":["/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-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":{"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":{},"id":"1104","type":"LinearScale"},{"attributes":{"text":"Transformer Layers"},"id":"1096","type":"Title"},{"attributes":{"source":{"id":"1122"}},"id":"1127","type":"CDSView"},{"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":"1155","type":"Selection"},{"attributes":{},"id":"1154","type":"UnionRenderers"},{"attributes":{"fill_color":{"value":"#20cb97"},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1130","type":"VBar"},{"attributes":{"start":0},"id":"1100","type":"DataRange1d"},{"attributes":{},"id":"1098","type":"DataRange1d"},{"attributes":{"axis_label":"Layer","formatter":{"id":"1146"},"minor_tick_line_color":null,"ticker":{"id":"1107"}},"id":"1106","type":"LinearAxis"},{"attributes":{},"id":"1107","type":"BasicTicker"},{"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"}],"root_ids":["1095"]},"title":"Bokeh Application","version":"2.2.3"}}';
-                  var render_items = [{"docid":"42cc26ba-43eb-4190-9dae-f35f89db9fa6","root_ids":["1095"],"roots":{"1095":"97855ddc-561d-447e-b31f-ff2514f18cc2"}}];
                   root.Bokeh.embed.embed_items(docs_json, render_items);
                   }

+      var element = document.getElementById("5787ef08-ec97-4223-80fb-b7d410af7b37");
         if (element == null) {
+          console.warn("Bokeh: autoload.js configured with elementid '5787ef08-ec97-4223-80fb-b7d410af7b37' but no matching script tag was found.")
         }
                 (function(root) {
                   function embed_document(root) {
+                  var docs_json = '{"d0d1258c-6c90-4876-9671-bf4cf1f56b5b":{"roots":{"references":[{"attributes":{"source":{"id":"1116"}},"id":"1121","type":"CDSView"},{"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":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto","tools":[{"id":"1094"}]},"id":"1114","type":"Toolbar"},{"attributes":{"label":{"value":"key"},"renderers":[{"id":"1126"}]},"id":"1142","type":"LegendItem"},{"attributes":{},"id":"1148","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":{"label":{"value":"query"},"renderers":[{"id":"1120"}]},"id":"1141","type":"LegendItem"},{"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":{"label":{"value":"fully connected"},"renderers":[{"id":"1138"}]},"id":"1144","type":"LegendItem"},{"attributes":{"source":{"id":"1134"}},"id":"1139","type":"CDSView"},{"attributes":{"data":{"density":["33.3%","18.0%","18.0%","33.3%","23.3%","23.3%","50.0%","25.9%","25.9%","58.3%","25.7%","25.7%","58.3%","27.1%","27.1%","41.7%","25.8%","25.8%","50.0%","20.2%","20.2%","58.3%","15.2%","15.2%","41.7%","9.2%","9.2%","41.7%","3.6%","3.6%","41.7%","3.1%","3.1%","25.0%","7.7%","7.7%"],"height":[0.196608,0.423936,0.423936,0.196608,0.550656,0.550656,0.294912,0.61056,0.61056,0.344064,0.605952,0.605952,0.344064,0.639744,0.639744,0.24576,0.608256,0.608256,0.294912,0.47616,0.47616,0.344064,0.357888,0.357888,0.24576,0.217344,0.217344,0.24576,0.086016,0.086016,0.24576,0.073728,0.073728,0.147456,0.182784,0.182784],"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":["0.20","0.42","0.42","0.20","0.55","0.55","0.29","0.61","0.61","0.34","0.61","0.61","0.34","0.64","0.64","0.25","0.61","0.61","0.29","0.48","0.48","0.34","0.36","0.36","0.25","0.22","0.22","0.25","0.09","0.09","0.25","0.07","0.07","0.15","0.18","0.18"],"url":["/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_11_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_11_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-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":{"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":{"data":{"density":["33.3%","33.3%","50.0%","58.3%","58.3%","41.7%","50.0%","58.3%","41.7%","41.7%","41.7%","25.0%"],"height":[0.196608,0.196608,0.294912,0.344064,0.344064,0.24576,0.294912,0.344064,0.24576,0.24576,0.24576,0.147456],"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":["0.20","0.20","0.29","0.34","0.34","0.25","0.29","0.34","0.25","0.25","0.25","0.15"],"url":["/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-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":"#6573f7"},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1118","type":"VBar"},{"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":["33.3%","33.3%","50.0%","58.3%","58.3%","41.7%","50.0%","58.3%","41.7%","41.7%","41.7%","25.0%"],"height":[0.196608,0.196608,0.294912,0.344064,0.344064,0.24576,0.294912,0.344064,0.24576,0.24576,0.24576,0.147456],"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":["0.20","0.20","0.29","0.34","0.34","0.25","0.29","0.34","0.25","0.25","0.25","0.15"],"url":["/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-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":{"source":{"id":"1122"}},"id":"1127","type":"CDSView"},{"attributes":{},"id":"1154","type":"UnionRenderers"},{"attributes":{"data":{"density":["33.3%","33.3%","50.0%","58.3%","58.3%","41.7%","50.0%","58.3%","41.7%","41.7%","41.7%","25.0%"],"height":[0.196608,0.196608,0.294912,0.344064,0.344064,0.24576,0.294912,0.344064,0.24576,0.24576,0.24576,0.147456],"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":["0.20","0.20","0.29","0.34","0.34","0.25","0.29","0.34","0.25","0.25","0.25","0.15"],"url":["/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_0_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_1_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_2_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_3_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_4_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_5_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_6_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_7_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_8_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_9_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-v1/raw/main/model_card/images/layer_10_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.44-f87.7-d26-hybrid-filled-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":{},"id":"1111","type":"BasicTicker"},{"attributes":{},"id":"1150","type":"UnionRenderers"},{"attributes":{},"id":"1155","type":"Selection"},{"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":"1152","type":"UnionRenderers"},{"attributes":{},"id":"1107","type":"BasicTicker"},{"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":"value"},"renderers":[{"id":"1132"}]},"id":"1143","type":"LegendItem"},{"attributes":{"axis_label":"Layer","formatter":{"id":"1146"},"minor_tick_line_color":null,"ticker":{"id":"1107"}},"id":"1106","type":"LinearAxis"},{"attributes":{"source":{"id":"1128"}},"id":"1133","type":"CDSView"},{"attributes":{},"id":"1098","type":"DataRange1d"},{"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":{},"id":"1146","type":"BasicTickFormatter"},{"attributes":{"items":[{"id":"1141"},{"id":"1142"},{"id":"1143"},{"id":"1144"}],"location":[10,0],"orientation":"horizontal"},"id":"1140","type":"Legend"},{"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":{},"id":"1102","type":"LinearScale"},{"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":{},"id":"1156","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":{"axis":{"id":"1106"},"grid_line_color":null,"ticker":null},"id":"1109","type":"Grid"},{"attributes":{"start":0},"id":"1100","type":"DataRange1d"},{"attributes":{},"id":"1157","type":"Selection"},{"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":"1151","type":"Selection"},{"attributes":{"axis":{"id":"1110"},"dimension":1,"ticker":null},"id":"1113","type":"Grid"},{"attributes":{},"id":"1104","type":"LinearScale"},{"attributes":{"text":"Transformer Layers"},"id":"1096","type":"Title"},{"attributes":{},"id":"1153","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"}],"root_ids":["1095"]},"title":"Bokeh Application","version":"2.2.3"}}';
+                  var render_items = [{"docid":"d0d1258c-6c90-4876-9671-bf4cf1f56b5b","root_ids":["1095"],"roots":{"1095":"5787ef08-ec97-4223-80fb-b7d410af7b37"}}];
                   root.Bokeh.embed.embed_items(docs_json, render_items);
                   }

model_card/pruning_info.js CHANGED Viewed

@@ -16,9 +16,9 @@
-      var element = document.getElementById("22fe1a34-3ff7-4b5e-9fd8-5574ce7d15ac");
         if (element == null) {
-          console.warn("Bokeh: autoload.js configured with elementid '22fe1a34-3ff7-4b5e-9fd8-5574ce7d15ac' but no matching script tag was found.")
         }
@@ -115,8 +115,8 @@
                 (function(root) {
                   function embed_document(root) {
-                  var docs_json = '{"5312b8c7-33f3-4d8d-8865-4adc6426eddf":{"roots":{"references":[{"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":{"axis_label":"Layer index","formatter":{"id":"1031"},"minor_tick_line_color":null,"ticker":{"id":"1013"}},"id":"1012","type":"CategoricalAxis"},{"attributes":{},"id":"1033","type":"BasicTickFormatter"},{"attributes":{"source":{"id":"1024"}},"id":"1029","type":"CDSView"},{"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":{"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":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto"},"id":"1019","type":"Toolbar"},{"attributes":{},"id":"1035","type":"UnionRenderers"},{"attributes":{"text":"Pruned Transformer Heads"},"id":"1002","type":"Title"},{"attributes":{},"id":"1036","type":"Selection"},{"attributes":{"items":[{"id":"1038"},{"id":"1054"}],"location":null},"id":"1037","type":"Legend"},{"attributes":{"factors":["0","1","2","3","4","5","6","7","8","9","10","11"],"range_padding":0.1},"id":"1004","type":"FactorRange"},{"attributes":{"fields":[]},"id":"1020","type":"Stack"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1057","type":"LegendItem"},{"attributes":{"start":0},"id":"1006","type":"DataRange1d"},{"attributes":{},"id":"1013","type":"CategoricalTicker"},{"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":{"axis":{"id":"1015"},"dimension":1,"ticker":null},"id":"1018","type":"Grid"},{"attributes":{},"id":"1016","type":"BasicTicker"},{"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":{"data":{"active":[4,4,6,7,7,5,6,7,5,5,5,3],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[8,8,6,5,5,7,6,5,7,7,7,9]},"selected":{"id":"1053"},"selection_policy":{"id":"1052"}},"id":"1039","type":"ColumnDataSource"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1054","type":"LegendItem"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1038","type":"LegendItem"},{"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":{"source":{"id":"1039"}},"id":"1044","type":"CDSView"},{"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":{"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":{"axis":{"id":"1012"},"grid_line_color":null,"ticker":null},"id":"1014","type":"Grid"},{"attributes":{},"id":"1052","type":"UnionRenderers"},{"attributes":{},"id":"1008","type":"CategoricalScale"},{"attributes":{"data":{"active":[4,4,6,7,7,5,6,7,5,5,5,3],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[8,8,6,5,5,7,6,5,7,7,7,9]},"selected":{"id":"1036"},"selection_policy":{"id":"1035"}},"id":"1024","type":"ColumnDataSource"},{"attributes":{"axis_label":"Heads count","formatter":{"id":"1033"},"minor_tick_line_color":null,"ticker":{"id":"1016"}},"id":"1015","type":"LinearAxis"},{"attributes":{"fields":["active"]},"id":"1021","type":"Stack"},{"attributes":{},"id":"1053","type":"Selection"},{"attributes":{},"id":"1031","type":"CategoricalTickFormatter"},{"attributes":{"fields":["active","pruned"]},"id":"1023","type":"Stack"},{"attributes":{"fields":["active"]},"id":"1022","type":"Stack"}],"root_ids":["1001"]},"title":"Bokeh Application","version":"2.2.3"}}';
-                  var render_items = [{"docid":"5312b8c7-33f3-4d8d-8865-4adc6426eddf","root_ids":["1001"],"roots":{"1001":"22fe1a34-3ff7-4b5e-9fd8-5574ce7d15ac"}}];
                   root.Bokeh.embed.embed_items(docs_json, render_items);
                   }

+      var element = document.getElementById("a936580a-5d72-4995-9a5a-86f6c50c2855");
         if (element == null) {
+          console.warn("Bokeh: autoload.js configured with elementid 'a936580a-5d72-4995-9a5a-86f6c50c2855' but no matching script tag was found.")
         }
                 (function(root) {
                   function embed_document(root) {
+                  var docs_json = '{"98a0ba41-94b7-457f-821e-90a864891955":{"roots":{"references":[{"attributes":{"start":0},"id":"1006","type":"DataRange1d"},{"attributes":{},"id":"1035","type":"UnionRenderers"},{"attributes":{},"id":"1008","type":"CategoricalScale"},{"attributes":{"axis":{"id":"1012"},"grid_line_color":null,"ticker":null},"id":"1014","type":"Grid"},{"attributes":{},"id":"1036","type":"Selection"},{"attributes":{},"id":"1052","type":"UnionRenderers"},{"attributes":{"factors":["0","1","2","3","4","5","6","7","8","9","10","11"],"range_padding":0.1},"id":"1004","type":"FactorRange"},{"attributes":{},"id":"1013","type":"CategoricalTicker"},{"attributes":{"text":"Pruned Transformer Heads"},"id":"1002","type":"Title"},{"attributes":{},"id":"1053","type":"Selection"},{"attributes":{"fields":[]},"id":"1020","type":"Stack"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1038","type":"LegendItem"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1057","type":"LegendItem"},{"attributes":{},"id":"1010","type":"LinearScale"},{"attributes":{"items":[{"id":"1056"},{"id":"1057"}],"location":[10,0],"orientation":"horizontal"},"id":"1055","type":"Legend"},{"attributes":{},"id":"1031","type":"CategoricalTickFormatter"},{"attributes":{"data":{"active":[4,4,6,7,7,5,6,7,5,5,5,3],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[8,8,6,5,5,7,6,5,7,7,7,9]},"selected":{"id":"1053"},"selection_policy":{"id":"1052"}},"id":"1039","type":"ColumnDataSource"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1056","type":"LegendItem"},{"attributes":{"fields":["active"]},"id":"1021","type":"Stack"},{"attributes":{"source":{"id":"1039"}},"id":"1044","type":"CDSView"},{"attributes":{"axis":{"id":"1015"},"dimension":1,"ticker":null},"id":"1018","type":"Grid"},{"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":"1016","type":"BasicTicker"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1054","type":"LegendItem"},{"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":{},"id":"1033","type":"BasicTickFormatter"},{"attributes":{"data":{"active":[4,4,6,7,7,5,6,7,5,5,5,3],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[8,8,6,5,5,7,6,5,7,7,7,9]},"selected":{"id":"1036"},"selection_policy":{"id":"1035"}},"id":"1024","type":"ColumnDataSource"},{"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":{"axis_label":"Heads count","formatter":{"id":"1033"},"minor_tick_line_color":null,"ticker":{"id":"1016"}},"id":"1015","type":"LinearAxis"},{"attributes":{"fields":["active","pruned"]},"id":"1023","type":"Stack"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto"},"id":"1019","type":"Toolbar"},{"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":{"fields":["active"]},"id":"1022","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":{"items":[{"id":"1038"},{"id":"1054"}],"location":null},"id":"1037","type":"Legend"},{"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":{"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":{"axis_label":"Layer index","formatter":{"id":"1031"},"minor_tick_line_color":null,"ticker":{"id":"1013"}},"id":"1012","type":"CategoricalAxis"}],"root_ids":["1001"]},"title":"Bokeh Application","version":"2.2.3"}}';
+                  var render_items = [{"docid":"98a0ba41-94b7-457f-821e-90a864891955","root_ids":["1001"],"roots":{"1001":"a936580a-5d72-4995-9a5a-86f6c50c2855"}}];
                   root.Bokeh.embed.embed_items(docs_json, render_items);
                   }

model_info.json ADDED Viewed

	@@ -0,0 +1,295 @@

+{
+    "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squad_test_final_fine_tune/fine_tuned_hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1/checkpoint-22132",
+    "config": {
+        "_name_or_path": "/tmp/tmp61klxvbz",
+        "architectures": ["BertForQuestionAnswering"],
+        "attention_probs_dropout_prob": 0.1,
+        "gradient_checkpointing": false,
+        "hidden_act": "gelu",
+        "hidden_dropout_prob": 0.1,
+        "hidden_size": 768,
+        "initializer_range": 0.02,
+        "intermediate_size": 3072,
+        "layer_norm_eps": 1e-12,
+        "max_position_embeddings": 512,
+        "model_type": "bert",
+        "num_attention_heads": 12,
+        "num_hidden_layers": 12,
+        "pad_token_id": 0,
+        "position_embedding_type": "absolute",
+        "pruned_heads": {
+            "0": [0, 2, 4, 5, 6, 7, 9, 11],
+            "1": [0, 2, 3, 5, 6, 7, 8, 9],
+            "10": [1, 4, 5, 6, 7, 8, 9],
+            "11": [0, 2, 3, 5, 6, 7, 8, 10, 11],
+            "2": [1, 2, 4, 7, 8, 11],
+            "3": [2, 4, 6, 7, 10],
+            "4": [0, 1, 2, 6, 11],
+            "5": [0, 1, 2, 5, 6, 7, 11],
+            "6": [0, 2, 3, 4, 7, 10],
+            "7": [1, 3, 6, 7, 11],
+            "8": [0, 1, 2, 3, 4, 6, 8],
+            "9": [1, 3, 4, 5, 7, 9, 10]
+        },
+        "type_vocab_size": 2,
+        "vocab_size": 30522
+    },
+    "eval_metrics": {
+        "exact_match": 80.02838221381268,
+        "f1": 87.70940223967354,
+        "main_metric": 87.70940223967354
+    },
+    "model_args": {
+        "cache_dir": null,
+        "config_name": null,
+        "model_name_or_path": "/home/lagunas/devel/hf/nn_pruning/nn_pruning/analysis/tmp_finetune",
+        "tokenizer_name": null
+    },
+    "source_checkpoint": "/data_2to/devel_data/nn_pruning/output/squad_test3/hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1/checkpoint-90000",
+    "sparse_args": {
+        "ampere_pruning_method": "disabled",
+        "attention_block_cols": 1,
+        "attention_block_rows": 1,
+        "attention_lambda": 1.0,
+        "attention_output_with_dense": 0,
+        "attention_pruning_method": "topK",
+        "bias_mask": true,
+        "dense_block_cols": 1,
+        "dense_block_rows": 1,
+        "dense_lambda": 1.0,
+        "dense_pruning_method": "topK",
+        "distil_alpha_ce": 0.1,
+        "distil_alpha_teacher": 0.9,
+        "distil_teacher_name_or_path": "csarron/bert-base-uncased-squad-v1",
+        "distil_temperature": 2.0,
+        "final_ampere_temperature": 20.0,
+        "final_finetune": 1,
+        "final_threshold": 0.5,
+        "final_warmup": 0,
+        "initial_ampere_temperature": 0.0,
+        "initial_threshold": 1.0,
+        "initial_warmup": 0,
+        "mask_init": "constant",
+        "mask_scale": 0.0,
+        "mask_scores_learning_rate": 0.01,
+        "regularization": "",
+        "regularization_final_lambda": 0
+    },
+    "speed": {
+        "cuda_eval_elapsed_time": 15.838374267578125,
+        "eval_elapsed_time": 22.999519595876336
+    },
+    "speedup": 2.436764806371294,
+    "stats": {
+        "layers": {
+            "0": {
+                "linear_attention_nnz": 786432,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 847872,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 1634304,
+                "linear_total": 7077888,
+                "nnz": 1640232,
+                "total": 7086336
+            },
+            "1": {
+                "linear_attention_nnz": 786432,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 1101312,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 1887744,
+                "linear_total": 7077888,
+                "nnz": 1893837,
+                "total": 7086336
+            },
+            "10": {
+                "linear_attention_nnz": 983040,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 147456,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 1130496,
+                "linear_total": 7077888,
+                "nnz": 1136160,
+                "total": 7086528
+            },
+            "11": {
+                "linear_attention_nnz": 589824,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 365568,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 955392,
+                "linear_total": 7077888,
+                "nnz": 960814,
+                "total": 7086144
+            },
+            "2": {
+                "linear_attention_nnz": 1179648,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 1221120,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 2400768,
+                "linear_total": 7077888,
+                "nnz": 2407323,
+                "total": 7086720
+            },
+            "3": {
+                "linear_attention_nnz": 1376256,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 1211904,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 2588160,
+                "linear_total": 7077888,
+                "nnz": 2594901,
+                "total": 7086912
+            },
+            "4": {
+                "linear_attention_nnz": 1376256,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 1279488,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 2655744,
+                "linear_total": 7077888,
+                "nnz": 2662529,
+                "total": 7086912
+            },
+            "5": {
+                "linear_attention_nnz": 983040,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 1216512,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 2199552,
+                "linear_total": 7077888,
+                "nnz": 2205912,
+                "total": 7086528
+            },
+            "6": {
+                "linear_attention_nnz": 1179648,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 952320,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 2131968,
+                "linear_total": 7077888,
+                "nnz": 2138348,
+                "total": 7086720
+            },
+            "7": {
+                "linear_attention_nnz": 1376256,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 715776,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 2092032,
+                "linear_total": 7077888,
+                "nnz": 2098450,
+                "total": 7086912
+            },
+            "8": {
+                "linear_attention_nnz": 983040,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 434688,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 1417728,
+                "linear_total": 7077888,
+                "nnz": 1423579,
+                "total": 7086528
+            },
+            "9": {
+                "linear_attention_nnz": 983040,
+                "linear_attention_total": 2359296,
+                "linear_dense_nnz": 172032,
+                "linear_dense_total": 4718592,
+                "linear_nnz": 1155072,
+                "linear_total": 7077888,
+                "nnz": 1160752,
+                "total": 7086528
+            }
+        },
+        "linear_nnz": 22248960,
+        "linear_sparsity": 73.80461516203704,
+        "linear_total": 84934656,
+        "nnz": 46161559,
+        "pruned_heads": {
+            "0": [0, 2, 4, 5, 6, 7, 9, 11],
+            "1": [0, 2, 3, 5, 6, 7, 8, 9],
+            "10": [1, 4, 5, 6, 7, 8, 9],
+            "11": [0, 2, 3, 5, 6, 7, 8, 10, 11],
+            "2": [1, 2, 4, 7, 8, 11],
+            "3": [2, 4, 6, 7, 10],
+            "4": [0, 1, 2, 6, 11],
+            "5": [0, 1, 2, 5, 6, 7, 11],
+            "6": [0, 2, 3, 4, 7, 10],
+            "7": [1, 3, 6, 7, 11],
+            "8": [0, 1, 2, 3, 4, 6, 8],
+            "9": [1, 3, 4, 5, 7, 9, 10]
+        },
+        "total": 108877826,
+        "total_sparsity": 57.602424023418685
+    },
+    "training_args": {
+        "_n_gpu": -1,
+        "adafactor": false,
+        "adam_beta1": 0.9,
+        "adam_beta2": 0.999,
+        "adam_epsilon": 1e-08,
+        "dataloader_drop_last": false,
+        "dataloader_num_workers": 0,
+        "dataloader_pin_memory": true,
+        "ddp_find_unused_parameters": null,
+        "debug": false,
+        "deepspeed": null,
+        "disable_tqdm": false,
+        "do_eval": 1,
+        "do_predict": false,
+        "do_train": 1,
+        "eval_accumulation_steps": null,
+        "eval_steps": 2500,
+        "evaluation_strategy": "steps",
+        "fp16": false,
+        "fp16_backend": "auto",
+        "fp16_full_eval": false,
+        "fp16_opt_level": "O1",
+        "gradient_accumulation_steps": 1,
+        "greater_is_better": null,
+        "group_by_length": false,
+        "ignore_data_skip": false,
+        "label_names": null,
+        "label_smoothing_factor": 0.0,
+        "learning_rate": 3e-05,
+        "length_column_name": "length",
+        "load_best_model_at_end": false,
+        "local_rank": -1,
+        "logging_dir": "/data_2to/devel_data/nn_pruning/output/squad_test_final_fine_tune/fine_tuned_hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1",
+        "logging_first_step": false,
+        "logging_steps": 250,
+        "logging_strategy": "steps",
+        "lr_scheduler_type": "linear",
+        "max_grad_norm": 1.0,
+        "max_steps": -1,
+        "metric_for_best_model": null,
+        "mp_parameters": "",
+        "no_cuda": false,
+        "num_train_epochs": 4,
+        "optimize_model_before_eval": "disabled",
+        "output_dir": "/data_2to/devel_data/nn_pruning/output/squad_test_final_fine_tune/fine_tuned_hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1",
+        "overwrite_output_dir": 1,
+        "past_index": -1,
+        "per_device_eval_batch_size": 8,
+        "per_device_train_batch_size": 16,
+        "per_gpu_eval_batch_size": null,
+        "per_gpu_train_batch_size": null,
+        "prediction_loss_only": false,
+        "remove_unused_columns": true,
+        "report_to": null,
+        "run_name": "/data_2to/devel_data/nn_pruning/output/squad_test_final_fine_tune/fine_tuned_hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1",
+        "save_steps": 2500,
+        "save_strategy": "steps",
+        "save_total_limit": 50,
+        "seed": 17,
+        "sharded_ddp": "",
+        "skip_memory_metrics": false,
+        "tpu_metrics_debug": false,
+        "tpu_num_cores": null,
+        "warmup_ratio": 0.0,
+        "warmup_steps": 10,
+        "weight_decay": 0.0
+    }
+}

training/data_args.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "dataset_cache_dir": "dataset_cache",
+    "dataset_config_name": null,
+    "dataset_name": "squad",
+    "doc_stride": 128,
+    "max_answer_length": 30,
+    "max_seq_length": 384,
+    "n_best_size": 20,
+    "null_score_diff_threshold": 0.0,
+    "overwrite_cache": 0,
+    "pad_to_max_length": true,
+    "preprocessing_num_workers": null,
+    "train_file": null,
+    "validation_file": null,
+    "version_2_with_negative": false
+}

training/model_args.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+    "cache_dir": null,
+    "config_name": null,
+    "model_name_or_path": "/home/lagunas/devel/hf/nn_pruning/nn_pruning/analysis/tmp_finetune",
+    "tokenizer_name": null
+}

training/sparse_args.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+    "ampere_pruning_method": "disabled",
+    "attention_block_cols": 1,
+    "attention_block_rows": 1,
+    "attention_lambda": 1.0,
+    "attention_output_with_dense": 0,
+    "attention_pruning_method": "topK",
+    "bias_mask": true,
+    "dense_block_cols": 1,
+    "dense_block_rows": 1,
+    "dense_lambda": 1.0,
+    "dense_pruning_method": "topK",
+    "distil_alpha_ce": 0.1,
+    "distil_alpha_teacher": 0.9,
+    "distil_teacher_name_or_path": "csarron/bert-base-uncased-squad-v1",
+    "distil_temperature": 2.0,
+    "final_ampere_temperature": 20.0,
+    "final_finetune": 1,
+    "final_threshold": 0.5,
+    "final_warmup": 0,
+    "initial_ampere_temperature": 0.0,
+    "initial_threshold": 1.0,
+    "initial_warmup": 0,
+    "mask_init": "constant",
+    "mask_scale": 0.0,
+    "mask_scores_learning_rate": 0.01,
+    "regularization": "",
+    "regularization_final_lambda": 0
+}

training/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e45a99b61c7ce1b38799c6740eb361bc1debe3085179110bdb5277a23600be9d
+size 2095