madlag commited on
Commit
151170c
1 Parent(s): c9c96fe

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:
@@ -19,7 +19,7 @@ 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 30.0%** of the original weights.
23
 
24
  This model **CANNOT be used without using nn_pruning `optimize_model`** function, as it uses NoNorms instead of LayerNorms and this is not currently supported by the Transformers library.
25
 
@@ -30,20 +30,20 @@ This does not need special handling, as it is supported by the Transformers libr
30
 
31
  The model contains **45.0%** of the original weights **overall** (the embeddings account for a significant part of the model, and they are not pruned by this method).
32
 
33
- With a simple resizing of the linear matrices it ran **2.01x as fast as BERT-base** on the evaluation.
34
  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.
35
 
36
- <div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/density_info.js" id="cb19239a-7547-4049-88a2-ceaf6bd7ab24"></script></div>
37
 
38
- In terms of accuracy, its **F1 is 89.19**, compared with 88.5 for BERT-base, a **F1 gain of 0.69**.
39
 
40
  ## Fine-Pruning details
41
- 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).
42
  This model is case-insensitive: it does not make a difference between english and English.
43
 
44
  A side-effect of the block pruning is that some of the attention heads are completely removed: 55 heads were removed on a total of 144 (38.2%).
45
  Here is a detailed view on how the remaining heads are distributed in the network after pruning.
46
- <div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/pruning_info.js" id="5bcb346e-3b5a-484b-89c2-a504aeed0c7a"></script></div>
47
 
48
  ## Details of the SQuAD1.1 dataset
49
 
@@ -65,7 +65,7 @@ GPU driver: 455.23.05, CUDA: 11.1
65
 
66
  ### Results
67
 
68
- **Pytorch model file size**: `374M` (original BERT: `438M`)
69
 
70
  | Metric | # Value | # Original ([Table 2](https://www.aclweb.org/anthology/N19-1423.pdf))| Variation |
71
  | ------ | --------- | --------- | --------- |
@@ -89,11 +89,11 @@ qa_pipeline = pipeline(
89
  tokenizer="madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1"
90
  )
91
 
92
- print("BERT-base parameters: 110M")
93
- print(f"Parameters count (includes head pruning)={int(qa_pipeline.model.num_parameters() / 1E6)}M")
94
  qa_pipeline.model = optimize_model(qa_pipeline.model, "dense")
95
 
96
- print(f"Parameters count after optimization={int(qa_pipeline.model.num_parameters() / 1E6)}M")
97
  predictions = qa_pipeline({
98
  '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.",
99
  '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 30.0%** of the original weights.
23
 
24
  This model **CANNOT be used without using nn_pruning `optimize_model`** function, as it uses NoNorms instead of LayerNorms and this is not currently supported by the Transformers library.
25
 
 
30
 
31
  The model contains **45.0%** of the original weights **overall** (the embeddings account for a significant part of the model, and they are not pruned by this method).
32
 
33
+ With a simple resizing of the linear matrices it ran **2.01x as fast as bert-base-uncased** on the evaluation.
34
  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.
35
 
36
+ <div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/density_info.js" id="c3b978cc-6d18-4fd0-a24b-e4369569d64d"></script></div>
37
 
38
+ In terms of accuracy, its **F1 is 89.19**, compared with 88.5 for bert-base-uncased, a **F1 gain of 0.69**.
39
 
40
  ## Fine-Pruning details
41
+ 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)
42
  This model is case-insensitive: it does not make a difference between english and English.
43
 
44
  A side-effect of the block pruning is that some of the attention heads are completely removed: 55 heads were removed on a total of 144 (38.2%).
45
  Here is a detailed view on how the remaining heads are distributed in the network after pruning.
46
+ <div class="graph"><script src="/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/pruning_info.js" id="7de38b6d-774c-4313-a5a4-8e32f554d9ec"></script></div>
47
 
48
  ## Details of the SQuAD1.1 dataset
49
 
 
65
 
66
  ### Results
67
 
68
+ **Pytorch model file size**: `374MB` (original BERT: `420MB`)
69
 
70
  | Metric | # Value | # Original ([Table 2](https://www.aclweb.org/anthology/N19-1423.pdf))| Variation |
71
  | ------ | --------- | --------- | --------- |
 
89
  tokenizer="madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1"
90
  )
91
 
92
+ print("bert-base-uncased parameters: 200.0M")
93
+ print(f"Parameters count (includes only head pruning, not feed forward pruning)={int(qa_pipeline.model.num_parameters() / 1E6)}M")
94
  qa_pipeline.model = optimize_model(qa_pipeline.model, "dense")
95
 
96
+ print(f"Parameters count after complete optimization={int(qa_pipeline.model.num_parameters() / 1E6)}M")
97
  predictions = qa_pipeline({
98
  '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.",
99
  'question': "Who is Frederic Chopin?",
eval/eval_metrics.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "exact_match": 82.21381267738883,
3
+ "f1": 89.18801010717891
4
+ }
eval/evaluate_timing.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_elapsed_time": 98.45825179666281, "cuda_eval_elapsed_time": 90.40731259918213}
eval/nbest_predictions.json.tgz ADDED
Binary file (6.6 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": 108882626, "nnz": 49662908, "linear_total": 84934656, "linear_nnz": 25746432, "layers": {"0": {"total": 7086912, "nnz": 2116894, "linear_total": 7077888, "linear_nnz": 2110464, "linear_attention_total": 2359296, "linear_attention_nnz": 1376256, "linear_dense_total": 4718592, "linear_dense_nnz": 734208}, "1": {"total": 7086528, "nnz": 1803218, "linear_total": 7077888, "linear_nnz": 1797120, "linear_attention_total": 2359296, "linear_attention_nnz": 983040, "linear_dense_total": 4718592, "linear_dense_nnz": 814080}, "2": {"total": 7087296, "nnz": 2797913, "linear_total": 7077888, "linear_nnz": 2790912, "linear_attention_total": 2359296, "linear_attention_nnz": 1769472, "linear_dense_total": 4718592, "linear_dense_nnz": 1021440}, "3": {"total": 7087296, "nnz": 2741044, "linear_total": 7077888, "linear_nnz": 2734080, "linear_attention_total": 2359296, "linear_attention_nnz": 1769472, "linear_dense_total": 4718592, "linear_dense_nnz": 964608}, "4": {"total": 7087488, "nnz": 2808736, "linear_total": 7077888, "linear_nnz": 2801664, "linear_attention_total": 2359296, "linear_attention_nnz": 1966080, "linear_dense_total": 4718592, "linear_dense_nnz": 835584}, "5": {"total": 7086912, "nnz": 2239854, "linear_total": 7077888, "linear_nnz": 2233344, "linear_attention_total": 2359296, "linear_attention_nnz": 1376256, "linear_dense_total": 4718592, "linear_dense_nnz": 857088}, "6": {"total": 7087296, "nnz": 2516642, "linear_total": 7077888, "linear_nnz": 2509824, "linear_attention_total": 2359296, "linear_attention_nnz": 1769472, "linear_dense_total": 4718592, "linear_dense_nnz": 740352}, "7": {"total": 7086912, "nnz": 1946287, "linear_total": 7077888, "linear_nnz": 1939968, "linear_attention_total": 2359296, "linear_attention_nnz": 1376256, "linear_dense_total": 4718592, "linear_dense_nnz": 563712}, "8": {"total": 7087296, "nnz": 2058616, "linear_total": 7077888, "linear_nnz": 2052096, "linear_attention_total": 2359296, "linear_attention_nnz": 1769472, "linear_dense_total": 4718592, "linear_dense_nnz": 282624}, "9": {"total": 7086720, "nnz": 1386755, "linear_total": 7077888, "linear_nnz": 1380864, "linear_attention_total": 2359296, "linear_attention_nnz": 1179648, "linear_dense_total": 4718592, "linear_dense_nnz": 201216}, "10": {"total": 7086528, "nnz": 1494281, "linear_total": 7077888, "linear_nnz": 1488384, "linear_attention_total": 2359296, "linear_attention_nnz": 983040, "linear_dense_total": 4718592, "linear_dense_nnz": 505344}, "11": {"total": 7086720, "nnz": 1913946, "linear_total": 7077888, "linear_nnz": 1907712, "linear_attention_total": 2359296, "linear_attention_nnz": 1179648, "linear_dense_total": 4718592, "linear_dense_nnz": 728064}}, "total_sparsity": 54.38858353765275, "linear_sparsity": 69.68677662037037, "pruned_heads": {"0": [0, 2, 4, 5, 6], "1": [0, 2, 3, 5, 6, 7, 8], "2": [8, 4, 7], "3": [2, 4, 6], "4": [1, 2], "5": [1, 2, 6, 7, 11], "6": [3, 10, 2], "7": [1, 3, 6, 7, 11], "8": [0, 3, 4], "9": [1, 4, 5, 7, 9, 10], "10": [1, 2, 4, 5, 6, 7, 8], "11": [0, 5, 7, 8, 10, 11]}}
eval/speed_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"timings": {"eval_elapsed_time": 26.312922549434006, "cuda_eval_elapsed_time": 19.22297591018677}, "metrics": {"exact_match": 82.21381267738883, "f1": 89.18874369381042}}
model_card/density_info.js CHANGED
@@ -16,9 +16,9 @@
16
 
17
 
18
 
19
- var element = document.getElementById("cb19239a-7547-4049-88a2-ceaf6bd7ab24");
20
  if (element == null) {
21
- console.warn("Bokeh: autoload.js configured with elementid 'cb19239a-7547-4049-88a2-ceaf6bd7ab24' 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 = '{"bb99ed32-eb33-4d5e-b318-7d785b4d7302":{"roots":{"references":[{"attributes":{"data":{"density":["58.3%","41.7%","75.0%","75.0%","83.3%","58.3%","75.0%","58.3%","75.0%","50.0%","41.7%","50.0%"],"height":[0.344064,0.24576,0.442368,0.442368,0.49152,0.344064,0.442368,0.344064,0.442368,0.294912,0.24576,0.294912],"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":["0.34","0.25","0.44","0.44","0.49","0.34","0.44","0.34","0.44","0.29","0.25","0.29"],"url":["/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-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":"1111","type":"BasicTicker"},{"attributes":{"start":0},"id":"1100","type":"DataRange1d"},{"attributes":{"source":{"id":"1128"}},"id":"1133","type":"CDSView"},{"attributes":{"axis_label":"Layer","formatter":{"id":"1146"},"minor_tick_line_color":null,"ticker":{"id":"1107"}},"id":"1106","type":"LinearAxis"},{"attributes":{},"id":"1098","type":"DataRange1d"},{"attributes":{"text":"Transformer Layers"},"id":"1096","type":"Title"},{"attributes":{},"id":"1102","type":"LinearScale"},{"attributes":{"fill_color":{"value":"#6573f7"},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1118","type":"VBar"},{"attributes":{"label":{"value":"query"},"renderers":[{"id":"1120"}]},"id":"1141","type":"LegendItem"},{"attributes":{"source":{"id":"1134"}},"id":"1139","type":"CDSView"},{"attributes":{},"id":"1155","type":"Selection"},{"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":"1148"},"minor_tick_line_color":null,"ticker":{"id":"1111"}},"id":"1110","type":"LinearAxis"},{"attributes":{"label":{"value":"value"},"renderers":[{"id":"1132"}]},"id":"1143","type":"LegendItem"},{"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":"#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":"1151","type":"Selection"},{"attributes":{},"id":"1154","type":"UnionRenderers"},{"attributes":{"data":{"density":["58.3%","15.6%","15.6%","41.7%","17.3%","17.3%","75.0%","21.6%","21.6%","75.0%","20.4%","20.4%","83.3%","17.7%","17.7%","58.3%","18.2%","18.2%","75.0%","15.7%","15.7%","58.3%","11.9%","11.9%","75.0%","6.0%","6.0%","50.0%","4.3%","4.3%","41.7%","10.7%","10.7%","50.0%","15.4%","15.4%"],"height":[0.344064,0.367104,0.367104,0.24576,0.40704,0.40704,0.442368,0.51072,0.51072,0.442368,0.482304,0.482304,0.49152,0.417792,0.417792,0.344064,0.428544,0.428544,0.442368,0.370176,0.370176,0.344064,0.281856,0.281856,0.442368,0.141312,0.141312,0.294912,0.100608,0.100608,0.24576,0.252672,0.252672,0.294912,0.364032,0.364032],"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":["0.34","0.37","0.37","0.25","0.41","0.41","0.44","0.51","0.51","0.44","0.48","0.48","0.49","0.42","0.42","0.34","0.43","0.43","0.44","0.37","0.37","0.34","0.28","0.28","0.44","0.14","0.14","0.29","0.10","0.10","0.25","0.25","0.25","0.29","0.36","0.36"],"url":["/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_11_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_11_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-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_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":{"axis":{"id":"1110"},"dimension":1,"ticker":null},"id":"1113","type":"Grid"},{"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":"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":{"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":"1157","type":"Selection"},{"attributes":{},"id":"1152","type":"UnionRenderers"},{"attributes":{},"id":"1153","type":"Selection"},{"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":"1122"}},"id":"1127","type":"CDSView"},{"attributes":{},"id":"1104","type":"LinearScale"},{"attributes":{"fill_color":{"value":"#20cb97"},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1130","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_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":{"id":"1106"},"grid_line_color":null,"ticker":null},"id":"1109","type":"Grid"},{"attributes":{},"id":"1150","type":"UnionRenderers"},{"attributes":{"data":{"density":["58.3%","41.7%","75.0%","75.0%","83.3%","58.3%","75.0%","58.3%","75.0%","50.0%","41.7%","50.0%"],"height":[0.344064,0.24576,0.442368,0.442368,0.49152,0.344064,0.442368,0.344064,0.442368,0.294912,0.24576,0.294912],"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":["0.34","0.25","0.44","0.44","0.49","0.34","0.44","0.34","0.44","0.29","0.25","0.29"],"url":["/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-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":{"label":{"value":"fully connected"},"renderers":[{"id":"1138"}]},"id":"1144","type":"LegendItem"},{"attributes":{},"id":"1107","type":"BasicTicker"},{"attributes":{"fill_color":{"value":"#aa69f7"},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1136","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"},{"attributes":{"label":{"value":"key"},"renderers":[{"id":"1126"}]},"id":"1142","type":"LegendItem"},{"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":"#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":"1146","type":"BasicTickFormatter"},{"attributes":{"data":{"density":["58.3%","41.7%","75.0%","75.0%","83.3%","58.3%","75.0%","58.3%","75.0%","50.0%","41.7%","50.0%"],"height":[0.344064,0.24576,0.442368,0.442368,0.49152,0.344064,0.442368,0.344064,0.442368,0.294912,0.24576,0.294912],"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":["0.34","0.25","0.44","0.44","0.49","0.34","0.44","0.34","0.44","0.29","0.25","0.29"],"url":["/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-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":"1148","type":"BasicTickFormatter"}],"root_ids":["1095"]},"title":"Bokeh Application","version":"2.2.3"}}';
119
- var render_items = [{"docid":"bb99ed32-eb33-4d5e-b318-7d785b4d7302","root_ids":["1095"],"roots":{"1095":"cb19239a-7547-4049-88a2-ceaf6bd7ab24"}}];
120
  root.Bokeh.embed.embed_items(docs_json, render_items);
121
 
122
  }
 
16
 
17
 
18
 
19
+ var element = document.getElementById("c3b978cc-6d18-4fd0-a24b-e4369569d64d");
20
  if (element == null) {
21
+ console.warn("Bokeh: autoload.js configured with elementid 'c3b978cc-6d18-4fd0-a24b-e4369569d64d' but no matching script tag was found.")
22
  }
23
 
24
 
 
115
  (function(root) {
116
  function embed_document(root) {
117
 
118
+ var docs_json = '{"632a3500-8560-49a8-827c-31134be1ae4f":{"roots":{"references":[{"attributes":{},"id":"1153","type":"UnionRenderers"},{"attributes":{"axis_label":"Layer","formatter":{"id":"1147"},"minor_tick_line_color":null,"ticker":{"id":"1107"}},"id":"1106","type":"LinearAxis"},{"attributes":{"text":"Transformer Layers"},"id":"1096","type":"Title"},{"attributes":{"axis_label":"Parameters (M)","formatter":{"id":"1149"},"minor_tick_line_color":null,"ticker":{"id":"1111"}},"id":"1110","type":"LinearAxis"},{"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":["58.3%","41.7%","75.0%","75.0%","83.3%","58.3%","75.0%","58.3%","75.0%","50.0%","41.7%","50.0%"],"height":[0.344064,0.24576,0.442368,0.442368,0.49152,0.344064,0.442368,0.344064,0.442368,0.294912,0.24576,0.294912],"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":["0.34","0.25","0.44","0.44","0.49","0.34","0.44","0.34","0.44","0.29","0.25","0.29"],"url":["/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-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":{"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":"1098","type":"DataRange1d"},{"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":"1150","type":"Selection"},{"attributes":{"data":{"density":["58.3%","15.6%","15.6%","41.7%","17.3%","17.3%","75.0%","21.6%","21.6%","75.0%","20.4%","20.4%","83.3%","17.7%","17.7%","58.3%","18.2%","18.2%","75.0%","15.7%","15.7%","58.3%","11.9%","11.9%","75.0%","6.0%","6.0%","50.0%","4.3%","4.3%","41.7%","10.7%","10.7%","50.0%","15.4%","15.4%"],"height":[0.344064,0.367104,0.367104,0.24576,0.40704,0.40704,0.442368,0.51072,0.51072,0.442368,0.482304,0.482304,0.49152,0.417792,0.417792,0.344064,0.428544,0.428544,0.442368,0.370176,0.370176,0.344064,0.281856,0.281856,0.442368,0.141312,0.141312,0.294912,0.100608,0.100608,0.24576,0.252672,0.252672,0.294912,0.364032,0.364032],"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":["0.34","0.37","0.37","0.25","0.41","0.41","0.44","0.51","0.51","0.44","0.48","0.48","0.49","0.42","0.42","0.34","0.43","0.43","0.44","0.37","0.37","0.34","0.28","0.28","0.44","0.14","0.14","0.29","0.10","0.10","0.25","0.25","0.25","0.29","0.36","0.36"],"url":["/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_11_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_11_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-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":{"fill_color":{"value":"#20cb97"},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1130","type":"VBar"},{"attributes":{},"id":"1149","type":"BasicTickFormatter"},{"attributes":{"data":{"density":["58.3%","41.7%","75.0%","75.0%","83.3%","58.3%","75.0%","58.3%","75.0%","50.0%","41.7%","50.0%"],"height":[0.344064,0.24576,0.442368,0.442368,0.49152,0.344064,0.442368,0.344064,0.442368,0.294912,0.24576,0.294912],"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":["0.34","0.25","0.44","0.44","0.49","0.34","0.44","0.34","0.44","0.29","0.25","0.29"],"url":["/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-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":{"start":0},"id":"1100","type":"DataRange1d"},{"attributes":{"axis":{"id":"1110"},"dimension":1,"ticker":null},"id":"1113","type":"Grid"},{"attributes":{"source":{"id":"1134"}},"id":"1139","type":"CDSView"},{"attributes":{"source":{"id":"1128"}},"id":"1133","type":"CDSView"},{"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":"query"},"renderers":[{"id":"1120"}]},"id":"1141","type":"LegendItem"},{"attributes":{"axis":{"id":"1106"},"grid_line_color":null,"ticker":null},"id":"1109","type":"Grid"},{"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":"1122"}},"id":"1127","type":"CDSView"},{"attributes":{},"id":"1151","type":"UnionRenderers"},{"attributes":{"label":{"value":"key"},"renderers":[{"id":"1126"}]},"id":"1142","type":"LegendItem"},{"attributes":{},"id":"1107","type":"BasicTicker"},{"attributes":{},"id":"1154","type":"Selection"},{"attributes":{"label":{"value":"fully connected"},"renderers":[{"id":"1138"}]},"id":"1144","type":"LegendItem"},{"attributes":{},"id":"1111","type":"BasicTicker"},{"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":{},"id":"1155","type":"UnionRenderers"},{"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":{"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":{"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":"#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":["58.3%","41.7%","75.0%","75.0%","83.3%","58.3%","75.0%","58.3%","75.0%","50.0%","41.7%","50.0%"],"height":[0.344064,0.24576,0.442368,0.442368,0.49152,0.344064,0.442368,0.344064,0.442368,0.294912,0.24576,0.294912],"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":["0.34","0.25","0.44","0.44","0.49","0.34","0.44","0.34","0.44","0.29","0.25","0.29"],"url":["/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_0_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_1_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_2_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_3_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_4_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_5_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_6_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_7_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_8_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_9_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1/raw/main/model_card/images/layer_10_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-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":"1152","type":"Selection"},{"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":"1104","type":"LinearScale"},{"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_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":"1147","type":"BasicTickFormatter"},{"attributes":{"label":{"value":"value"},"renderers":[{"id":"1132"}]},"id":"1143","type":"LegendItem"},{"attributes":{},"id":"1156","type":"Selection"},{"attributes":{},"id":"1102","type":"LinearScale"},{"attributes":{"source":{"id":"1116"}},"id":"1121","type":"CDSView"},{"attributes":{},"id":"1157","type":"UnionRenderers"},{"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_color":{"value":"#ed5642"},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1124","type":"VBar"}],"root_ids":["1095"]},"title":"Bokeh Application","version":"2.2.3"}}';
119
+ var render_items = [{"docid":"632a3500-8560-49a8-827c-31134be1ae4f","root_ids":["1095"],"roots":{"1095":"c3b978cc-6d18-4fd0-a24b-e4369569d64d"}}];
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("5bcb346e-3b5a-484b-89c2-a504aeed0c7a");
20
  if (element == null) {
21
- console.warn("Bokeh: autoload.js configured with elementid '5bcb346e-3b5a-484b-89c2-a504aeed0c7a' 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 = '{"271b0ca2-fc0d-4825-8e06-f2666f6ae338":{"roots":{"references":[{"attributes":{"fields":["active"]},"id":"1021","type":"Stack"},{"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":{},"id":"1053","type":"Selection"},{"attributes":{"source":{"id":"1024"}},"id":"1029","type":"CDSView"},{"attributes":{"start":0},"id":"1006","type":"DataRange1d"},{"attributes":{},"id":"1035","type":"UnionRenderers"},{"attributes":{"data":{"active":[7,5,9,9,10,7,9,7,9,6,5,6],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[5,7,3,3,2,5,3,5,3,6,7,6]},"selected":{"id":"1053"},"selection_policy":{"id":"1052"}},"id":"1039","type":"ColumnDataSource"},{"attributes":{},"id":"1036","type":"Selection"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1057","type":"LegendItem"},{"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":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1056","type":"LegendItem"},{"attributes":{},"id":"1013","type":"CategoricalTicker"},{"attributes":{},"id":"1008","type":"CategoricalScale"},{"attributes":{"axis":{"id":"1012"},"grid_line_color":null,"ticker":null},"id":"1014","type":"Grid"},{"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":{"items":[{"id":"1056"},{"id":"1057"}],"location":[10,0],"orientation":"horizontal"},"id":"1055","type":"Legend"},{"attributes":{"text":"Pruned Transformer Heads"},"id":"1002","type":"Title"},{"attributes":{},"id":"1052","type":"UnionRenderers"},{"attributes":{"axis_label":"Heads count","formatter":{"id":"1033"},"minor_tick_line_color":null,"ticker":{"id":"1016"}},"id":"1015","type":"LinearAxis"},{"attributes":{},"id":"1031","type":"CategoricalTickFormatter"},{"attributes":{"axis":{"id":"1015"},"dimension":1,"ticker":null},"id":"1018","type":"Grid"},{"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":{"fields":[]},"id":"1020","type":"Stack"},{"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":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1038","type":"LegendItem"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1054","type":"LegendItem"},{"attributes":{},"id":"1033","type":"BasicTickFormatter"},{"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":"1010","type":"LinearScale"},{"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":{"data":{"active":[7,5,9,9,10,7,9,7,9,6,5,6],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[5,7,3,3,2,5,3,5,3,6,7,6]},"selected":{"id":"1036"},"selection_policy":{"id":"1035"}},"id":"1024","type":"ColumnDataSource"},{"attributes":{"fields":["active"]},"id":"1022","type":"Stack"},{"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":"1016","type":"BasicTicker"},{"attributes":{"axis_label":"Layer index","formatter":{"id":"1031"},"minor_tick_line_color":null,"ticker":{"id":"1013"}},"id":"1012","type":"CategoricalAxis"},{"attributes":{"fields":["active","pruned"]},"id":"1023","type":"Stack"}],"root_ids":["1001"]},"title":"Bokeh Application","version":"2.2.3"}}';
119
- var render_items = [{"docid":"271b0ca2-fc0d-4825-8e06-f2666f6ae338","root_ids":["1001"],"roots":{"1001":"5bcb346e-3b5a-484b-89c2-a504aeed0c7a"}}];
120
  root.Bokeh.embed.embed_items(docs_json, render_items);
121
 
122
  }
 
16
 
17
 
18
 
19
+ var element = document.getElementById("7de38b6d-774c-4313-a5a4-8e32f554d9ec");
20
  if (element == null) {
21
+ console.warn("Bokeh: autoload.js configured with elementid '7de38b6d-774c-4313-a5a4-8e32f554d9ec' but no matching script tag was found.")
22
  }
23
 
24
 
 
115
  (function(root) {
116
  function embed_document(root) {
117
 
118
+ var docs_json = '{"1042e3b9-9a00-47e5-8b3c-ffb68f29c13e":{"roots":{"references":[{"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":{"axis_label":"Layer index","formatter":{"id":"1032"},"minor_tick_line_color":null,"ticker":{"id":"1013"}},"id":"1012","type":"CategoricalAxis"},{"attributes":{"data":{"active":[7,5,9,9,10,7,9,7,9,6,5,6],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[5,7,3,3,2,5,3,5,3,6,7,6]},"selected":{"id":"1052"},"selection_policy":{"id":"1053"}},"id":"1039","type":"ColumnDataSource"},{"attributes":{"start":0},"id":"1006","type":"DataRange1d"},{"attributes":{"items":[{"id":"1038"},{"id":"1054"}],"location":null},"id":"1037","type":"Legend"},{"attributes":{},"id":"1008","type":"CategoricalScale"},{"attributes":{},"id":"1035","type":"Selection"},{"attributes":{"axis":{"id":"1012"},"grid_line_color":null,"ticker":null},"id":"1014","type":"Grid"},{"attributes":{},"id":"1036","type":"UnionRenderers"},{"attributes":{},"id":"1013","type":"CategoricalTicker"},{"attributes":{},"id":"1052","type":"Selection"},{"attributes":{"fields":[]},"id":"1020","type":"Stack"},{"attributes":{},"id":"1053","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":{"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":{"source":{"id":"1024"}},"id":"1029","type":"CDSView"},{"attributes":{"fields":["active"]},"id":"1022","type":"Stack"},{"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":{},"id":"1032","type":"CategoricalTickFormatter"},{"attributes":{"text":"Pruned Transformer Heads"},"id":"1002","type":"Title"},{"attributes":{},"id":"1010","type":"LinearScale"},{"attributes":{"items":[{"id":"1056"},{"id":"1057"}],"location":[10,0],"orientation":"horizontal"},"id":"1055","type":"Legend"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1056","type":"LegendItem"},{"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":{"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":{"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"]},"id":"1021","type":"Stack"},{"attributes":{"axis":{"id":"1015"},"dimension":1,"ticker":null},"id":"1018","type":"Grid"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1054","type":"LegendItem"},{"attributes":{"fields":["active","pruned"]},"id":"1023","type":"Stack"},{"attributes":{},"id":"1034","type":"BasicTickFormatter"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto"},"id":"1019","type":"Toolbar"},{"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":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1057","type":"LegendItem"},{"attributes":{"data":{"active":[7,5,9,9,10,7,9,7,9,6,5,6],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[5,7,3,3,2,5,3,5,3,6,7,6]},"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":"1042e3b9-9a00-47e5-8b3c-ffb68f29c13e","root_ids":["1001"],"roots":{"1001":"7de38b6d-774c-4313-a5a4-8e32f554d9ec"}}];
120
  root.Bokeh.embed.embed_items(docs_json, render_items);
121
 
122
  }
model_info.json ADDED
@@ -0,0 +1,303 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squad_test_9_fullpatch6/hp_od-__data_2to__devel_data__nn_pruning__output__squad_test_9_fullpatch6___es-steps_nte20_ls250_stl50_est5000_rn-__data_2to__devel_data__nn_pruning__output__squad_test_9_fullpatch6_--5f772c87c5edbc85/checkpoint-100000",
3
+ "config": {
4
+ "_name_or_path": "/tmp/tmpcklouvey",
5
+ "architectures": ["BertForQuestionAnswering"],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "relu",
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
+ "layer_norm_type": "no_norm",
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "pruned_heads": {
22
+ "0": [0, 2, 4, 5, 6],
23
+ "1": [0, 2, 3, 5, 6, 7, 8],
24
+ "10": [1, 2, 4, 5, 6, 7, 8],
25
+ "11": [0, 5, 7, 8, 10, 11],
26
+ "2": [4, 7, 8],
27
+ "3": [2, 4, 6],
28
+ "4": [1, 2],
29
+ "5": [1, 2, 6, 7, 11],
30
+ "6": [2, 3, 10],
31
+ "7": [1, 3, 6, 7, 11],
32
+ "8": [0, 3, 4],
33
+ "9": [1, 4, 5, 7, 9, 10]
34
+ },
35
+ "type_vocab_size": 2,
36
+ "vocab_size": 30522
37
+ },
38
+ "eval_metrics": {
39
+ "exact_match": 82.21381267738883,
40
+ "f1": 89.18874369381042,
41
+ "main_metric": 89.18874369381042
42
+ },
43
+ "model_args": {
44
+ "cache_dir": null,
45
+ "config_name": null,
46
+ "model_name_or_path": "bert-base-uncased",
47
+ "tokenizer_name": null,
48
+ "use_fast_tokenizer": true
49
+ },
50
+ "sparse_args": {
51
+ "ampere_pruning_method": "disabled",
52
+ "attention_block_cols": 32,
53
+ "attention_block_rows": 32,
54
+ "attention_lambda": 1.0,
55
+ "attention_output_with_dense": 0,
56
+ "attention_pruning_method": "sigmoied_threshold",
57
+ "bias_mask": true,
58
+ "dense_block_cols": 1,
59
+ "dense_block_rows": 1,
60
+ "dense_lambda": 1.0,
61
+ "dense_pruning_method": "sigmoied_threshold:1d_alt",
62
+ "distil_alpha_ce": 0.1,
63
+ "distil_alpha_teacher": 0.9,
64
+ "distil_teacher_name_or_path": "bert-large-uncased-whole-word-masking-finetuned-squad",
65
+ "distil_temperature": 2.0,
66
+ "final_ampere_temperature": 20.0,
67
+ "final_finetune": false,
68
+ "final_threshold": 0.1,
69
+ "final_warmup": 10,
70
+ "gelu_patch": 1,
71
+ "gelu_patch_steps": 50000,
72
+ "initial_ampere_temperature": 0.0,
73
+ "initial_threshold": 0,
74
+ "initial_warmup": 1,
75
+ "layer_norm_patch": 1,
76
+ "layer_norm_patch_start_delta": 0.99,
77
+ "layer_norm_patch_steps": 50000,
78
+ "linear_min_parameters": 0,
79
+ "mask_init": "constant",
80
+ "mask_scale": 0.0,
81
+ "mask_scores_learning_rate": 0.01,
82
+ "regularization": "l1",
83
+ "regularization_final_lambda": 10,
84
+ "rewind_model_name_or_path": "madlag/bert-base-uncased-squadv1-x1.96-f88.3-d27-hybrid-filled-opt-v1"
85
+ },
86
+ "speed": {
87
+ "cuda_eval_elapsed_time": 19.22297591018677,
88
+ "eval_elapsed_time": 26.312922549434006
89
+ },
90
+ "speedup": 2.00772207100977,
91
+ "stats": {
92
+ "layers": {
93
+ "0": {
94
+ "linear_attention_nnz": 1376256,
95
+ "linear_attention_total": 2359296,
96
+ "linear_dense_nnz": 734208,
97
+ "linear_dense_total": 4718592,
98
+ "linear_nnz": 2110464,
99
+ "linear_total": 7077888,
100
+ "nnz": 2116894,
101
+ "total": 7086912
102
+ },
103
+ "1": {
104
+ "linear_attention_nnz": 983040,
105
+ "linear_attention_total": 2359296,
106
+ "linear_dense_nnz": 814080,
107
+ "linear_dense_total": 4718592,
108
+ "linear_nnz": 1797120,
109
+ "linear_total": 7077888,
110
+ "nnz": 1803218,
111
+ "total": 7086528
112
+ },
113
+ "10": {
114
+ "linear_attention_nnz": 983040,
115
+ "linear_attention_total": 2359296,
116
+ "linear_dense_nnz": 505344,
117
+ "linear_dense_total": 4718592,
118
+ "linear_nnz": 1488384,
119
+ "linear_total": 7077888,
120
+ "nnz": 1494281,
121
+ "total": 7086528
122
+ },
123
+ "11": {
124
+ "linear_attention_nnz": 1179648,
125
+ "linear_attention_total": 2359296,
126
+ "linear_dense_nnz": 728064,
127
+ "linear_dense_total": 4718592,
128
+ "linear_nnz": 1907712,
129
+ "linear_total": 7077888,
130
+ "nnz": 1913946,
131
+ "total": 7086720
132
+ },
133
+ "2": {
134
+ "linear_attention_nnz": 1769472,
135
+ "linear_attention_total": 2359296,
136
+ "linear_dense_nnz": 1021440,
137
+ "linear_dense_total": 4718592,
138
+ "linear_nnz": 2790912,
139
+ "linear_total": 7077888,
140
+ "nnz": 2797913,
141
+ "total": 7087296
142
+ },
143
+ "3": {
144
+ "linear_attention_nnz": 1769472,
145
+ "linear_attention_total": 2359296,
146
+ "linear_dense_nnz": 964608,
147
+ "linear_dense_total": 4718592,
148
+ "linear_nnz": 2734080,
149
+ "linear_total": 7077888,
150
+ "nnz": 2741044,
151
+ "total": 7087296
152
+ },
153
+ "4": {
154
+ "linear_attention_nnz": 1966080,
155
+ "linear_attention_total": 2359296,
156
+ "linear_dense_nnz": 835584,
157
+ "linear_dense_total": 4718592,
158
+ "linear_nnz": 2801664,
159
+ "linear_total": 7077888,
160
+ "nnz": 2808736,
161
+ "total": 7087488
162
+ },
163
+ "5": {
164
+ "linear_attention_nnz": 1376256,
165
+ "linear_attention_total": 2359296,
166
+ "linear_dense_nnz": 857088,
167
+ "linear_dense_total": 4718592,
168
+ "linear_nnz": 2233344,
169
+ "linear_total": 7077888,
170
+ "nnz": 2239854,
171
+ "total": 7086912
172
+ },
173
+ "6": {
174
+ "linear_attention_nnz": 1769472,
175
+ "linear_attention_total": 2359296,
176
+ "linear_dense_nnz": 740352,
177
+ "linear_dense_total": 4718592,
178
+ "linear_nnz": 2509824,
179
+ "linear_total": 7077888,
180
+ "nnz": 2516642,
181
+ "total": 7087296
182
+ },
183
+ "7": {
184
+ "linear_attention_nnz": 1376256,
185
+ "linear_attention_total": 2359296,
186
+ "linear_dense_nnz": 563712,
187
+ "linear_dense_total": 4718592,
188
+ "linear_nnz": 1939968,
189
+ "linear_total": 7077888,
190
+ "nnz": 1946287,
191
+ "total": 7086912
192
+ },
193
+ "8": {
194
+ "linear_attention_nnz": 1769472,
195
+ "linear_attention_total": 2359296,
196
+ "linear_dense_nnz": 282624,
197
+ "linear_dense_total": 4718592,
198
+ "linear_nnz": 2052096,
199
+ "linear_total": 7077888,
200
+ "nnz": 2058616,
201
+ "total": 7087296
202
+ },
203
+ "9": {
204
+ "linear_attention_nnz": 1179648,
205
+ "linear_attention_total": 2359296,
206
+ "linear_dense_nnz": 201216,
207
+ "linear_dense_total": 4718592,
208
+ "linear_nnz": 1380864,
209
+ "linear_total": 7077888,
210
+ "nnz": 1386755,
211
+ "total": 7086720
212
+ }
213
+ },
214
+ "linear_nnz": 25746432,
215
+ "linear_sparsity": 69.68677662037037,
216
+ "linear_total": 84934656,
217
+ "nnz": 49662908,
218
+ "pruned_heads": {
219
+ "0": [0, 2, 4, 5, 6],
220
+ "1": [0, 2, 3, 5, 6, 7, 8],
221
+ "10": [1, 2, 4, 5, 6, 7, 8],
222
+ "11": [0, 5, 7, 8, 10, 11],
223
+ "2": [8, 4, 7],
224
+ "3": [2, 4, 6],
225
+ "4": [1, 2],
226
+ "5": [1, 2, 6, 7, 11],
227
+ "6": [3, 10, 2],
228
+ "7": [1, 3, 6, 7, 11],
229
+ "8": [0, 3, 4],
230
+ "9": [1, 4, 5, 7, 9, 10]
231
+ },
232
+ "total": 108882626,
233
+ "total_sparsity": 54.38858353765275
234
+ },
235
+ "training_args": {
236
+ "_n_gpu": -1,
237
+ "adafactor": false,
238
+ "adam_beta1": 0.9,
239
+ "adam_beta2": 0.999,
240
+ "adam_epsilon": 1e-08,
241
+ "dataloader_drop_last": false,
242
+ "dataloader_num_workers": 0,
243
+ "dataloader_pin_memory": true,
244
+ "ddp_find_unused_parameters": null,
245
+ "debug": false,
246
+ "deepspeed": null,
247
+ "disable_tqdm": false,
248
+ "do_eval": 1,
249
+ "do_predict": false,
250
+ "do_train": 1,
251
+ "eval_accumulation_steps": null,
252
+ "eval_steps": 5000,
253
+ "evaluation_strategy": "steps",
254
+ "fp16": false,
255
+ "fp16_backend": "auto",
256
+ "fp16_full_eval": false,
257
+ "fp16_opt_level": "O1",
258
+ "gradient_accumulation_steps": 1,
259
+ "greater_is_better": null,
260
+ "group_by_length": false,
261
+ "ignore_data_skip": false,
262
+ "label_names": null,
263
+ "label_smoothing_factor": 0.0,
264
+ "learning_rate": 3e-05,
265
+ "length_column_name": "length",
266
+ "load_best_model_at_end": false,
267
+ "local_rank": -1,
268
+ "logging_dir": "/data_2to/devel_data/nn_pruning/output/squad_test_9_fullpatch6/",
269
+ "logging_first_step": false,
270
+ "logging_steps": 250,
271
+ "logging_strategy": "steps",
272
+ "lr_scheduler_type": "linear",
273
+ "max_grad_norm": 1.0,
274
+ "max_steps": -1,
275
+ "metric_for_best_model": null,
276
+ "mp_parameters": "",
277
+ "no_cuda": false,
278
+ "num_train_epochs": 20,
279
+ "optimize_model_before_eval": "disabled",
280
+ "output_dir": "/data_2to/devel_data/nn_pruning/output/squad_test_9_fullpatch6/",
281
+ "overwrite_output_dir": 1,
282
+ "past_index": -1,
283
+ "per_device_eval_batch_size": 8,
284
+ "per_device_train_batch_size": 16,
285
+ "per_gpu_eval_batch_size": null,
286
+ "per_gpu_train_batch_size": null,
287
+ "prediction_loss_only": false,
288
+ "remove_unused_columns": true,
289
+ "report_to": null,
290
+ "run_name": "/data_2to/devel_data/nn_pruning/output/squad_test_9_fullpatch6/",
291
+ "save_steps": 5000,
292
+ "save_strategy": "steps",
293
+ "save_total_limit": 50,
294
+ "seed": 17,
295
+ "sharded_ddp": "",
296
+ "skip_memory_metrics": false,
297
+ "tpu_metrics_debug": false,
298
+ "tpu_num_cores": null,
299
+ "warmup_ratio": 0.0,
300
+ "warmup_steps": 5400,
301
+ "weight_decay": 0.0
302
+ }
303
+ }
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 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ampere_pruning_method": "disabled",
3
+ "attention_block_cols": 32,
4
+ "attention_block_rows": 32,
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:1d_alt",
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": 1,
22
+ "gelu_patch_steps": 50000,
23
+ "initial_ampere_temperature": 0.0,
24
+ "initial_threshold": 0,
25
+ "initial_warmup": 1,
26
+ "layer_norm_patch": 1,
27
+ "layer_norm_patch_start_delta": 0.99,
28
+ "layer_norm_patch_steps": 50000,
29
+ "linear_min_parameters": 0,
30
+ "mask_init": "constant",
31
+ "mask_scale": 0.0,
32
+ "mask_scores_learning_rate": 0.01,
33
+ "regularization": "l1",
34
+ "regularization_final_lambda": 10,
35
+ "rewind_model_name_or_path": "madlag/bert-base-uncased-squadv1-x1.96-f88.3-d27-hybrid-filled-opt-v1"
36
+ }
training/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb5a04ceb10745ffd9468f13ee72ea9540da473e8a7efa3bb1aaf19e8880b75
3
+ size 1967