afvanluenen commited on
Commit
47b70bf
·
verified ·
1 Parent(s): a0f2f20

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -4
README.md CHANGED
@@ -30,19 +30,61 @@ nor has it been tested on other downstream tasks.
30
 
31
  # Architecture description
32
  TODO: get model architecture like on the model card of the previous model
 
33
  Don't forget to describe that during pretraining, the --mlm-prob parameter has been set to 0.4, in accordance to [paper](INSERT LINK)
 
34
  Parameters used: epochs=19, eval_steps=10000, batch_size=512, gradient_accumulation_steps=1, mlm_prob=0.4, bf16=True, tf32=True
35
 
36
  add estimated time it has cost to train:
37
- pretraining:
38
  finetuning: 4 hours on 1 NVIDIA H200
39
 
40
  # Output
41
- The model outputs embeddings that can be compared using cosine similarity
42
 
43
  # Data
44
  TODO: how did we get the data?
45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  # Preprocessing
47
  Several preprocessing steps have been taken, that differ slightly between architectures.
48
  TODO: update to same as architecture.md in repo
@@ -50,6 +92,5 @@ TODO: update to same as architecture.md in repo
50
  # Performance
51
  Performance was measured in two ways: Mean Reciprocal Rank (MRR) and Accuracy@1
52
 
53
- -------------------------------------------------------------------------------------------------------------------------
54
  |model|ARM64 mrr|ARM64 acc|AMD64 mrr|AMD64 acc|RISC-V mrr|RISC-V acc|I386 mrr|I386 acc|crosslingual mrr|crosslingual acc|
55
- ---------------------------------------------------------------------------------------------------------------------------
 
30
 
31
  # Architecture description
32
  TODO: get model architecture like on the model card of the previous model
33
+
34
  Don't forget to describe that during pretraining, the --mlm-prob parameter has been set to 0.4, in accordance to [paper](INSERT LINK)
35
+
36
  Parameters used: epochs=19, eval_steps=10000, batch_size=512, gradient_accumulation_steps=1, mlm_prob=0.4, bf16=True, tf32=True
37
 
38
  add estimated time it has cost to train:
39
+ pretraining: 33 hours on TODO!
40
  finetuning: 4 hours on 1 NVIDIA H200
41
 
42
  # Output
43
+ The model outputs embeddings of size 768 that can be compared using cosine similarity
44
 
45
  # Data
46
  TODO: how did we get the data?
47
 
48
+ Total amount of functions per architecture
49
+
50
+ | Architecture | # functions|
51
+ |--------------|------------|
52
+ | amd64 |8 202 164|
53
+ | i386 |4 868 531|
54
+ | arm64 |4 421 768|
55
+ | riscv64 |3 791 434 |
56
+ -------------------------
57
+
58
+ Amount of functions per architecture per optimization
59
+
60
+ |Architecture | Optimization | # functions |
61
+ |-------------|--------------|-------------|
62
+ |amd64 | O0 | 1762442 |
63
+ |amd64 | O1 | 1448046 |
64
+ |amd64 | O2 | 1403180 |
65
+ |amd64 | O3 | 1308199 |
66
+ |amd64 | Oc | 899892 |
67
+ |amd64 | Os | 1380405 |
68
+ |arm64 | O0 | 918402 |
69
+ |arm64 | O1 | 824291 |
70
+ |arm64 | O2 | 790679 |
71
+ |arm64 | O3 | 741057 |
72
+ |arm64 | Oc | 331736 |
73
+ |arm64 | Os | 815603 |
74
+ |i386 | O0 | 1081475 |
75
+ |i386 | O1 | 873128 |
76
+ |i386 | O2 | 845943 |
77
+ |i386 | O3 | 816186 |
78
+ |i386 | Oc | 412503 |
79
+ |i386 | Os | 839296 |
80
+ |riscv64 | O0 | 845154 |
81
+ |riscv64 | O1 | 689670 |
82
+ |riscv64 | O2 | 670651 |
83
+ |riscv64 | O3 | 641428 |
84
+ |riscv64 | Oc | 259691 |
85
+ |riscv64 | Os | 684840 |
86
+ ----------------------------
87
+
88
  # Preprocessing
89
  Several preprocessing steps have been taken, that differ slightly between architectures.
90
  TODO: update to same as architecture.md in repo
 
92
  # Performance
93
  Performance was measured in two ways: Mean Reciprocal Rank (MRR) and Accuracy@1
94
 
 
95
  |model|ARM64 mrr|ARM64 acc|AMD64 mrr|AMD64 acc|RISC-V mrr|RISC-V acc|I386 mrr|I386 acc|crosslingual mrr|crosslingual acc|
96
+ |-----|---------|---------|---------|---------|----------|----------|--------|--------|----------------|----------------|