nicholasKluge commited on
Commit
e2295f8
1 Parent(s): 9e3c264

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -12
README.md CHANGED
@@ -3,17 +3,26 @@ library_name: transformers
3
  tags: []
4
  ---
5
 
6
- # Model Card for Model ID
7
-
8
- | Step | Evaluation Loss | Perplexity | Total Energy Consumption |
9
- | ---- | --------------- | ---------- |------------------------- |
10
- | 50000 | 3.0317165851593018 | 20.732791663048406 | 0.04120226676343604 |
11
- | 100000 | 2.8416640758514404 | 17.144271180453458 | 0.04141422245773082 |
12
- | 150000 | 2.7315149307250977 | 15.356132885049972 | 0.0414626728018321 |
13
- | 200000 | 2.642719268798828 | 14.051361131845391 | 0.04142140609011406 |
14
- | 250000 | 2.5618579387664795 | 12.959873612653142 | 0.04138780675267453 |
15
- | 300000 | 2.4968385696411133 | 12.144040670176421 | 0.041324062100271744 |
16
- | 350000 | 2.4640052318573 | 11.75178603311608 | 0.041264254167392524 |
17
- | 400000 | 2.461648941040039 | 11.724128005574686 | 0.04069145953614345 |
 
 
 
 
 
 
 
 
 
18
 
19
 
 
3
  tags: []
4
  ---
5
 
6
+ # Mula 4x160m
7
+
8
+
9
+
10
+ | Step | Evaluation Loss | Perplexity | Total Energy Consumption |
11
+ |--------|-----------------|------------|--------------------------|
12
+ | 50000 | 3.03 | 20.73 | 0.041 |
13
+ | 100000 | 2.84 | 17.14 | 0.041 |
14
+ | 150000 | 2.73 | 15.35 | 0.041 |
15
+ | 200000 | 2.64 | 14.05 | 0.041 |
16
+ | 250000 | 2.56 | 12.95 | 0.041 |
17
+ | 300000 | 2.49 | 12.14 | 0.041 |
18
+ | 350000 | 2.46 | 11.75 | 0.041 |
19
+ | 400000 | 2.46 | 11.72 | 0.040 |
20
+
21
+
22
+ | | **ASSIN2 RTE** | **ASSIN2 STS** | **BLUEX** | **ENEM** | **FAQUAD NLI** | **HateBR** | **OAB Exams** | **Average** |
23
+ |-------------------|----------------|----------------|-----------|----------|----------------|------------|---------------|-------------|
24
+ | **TTL-460m** | 53.93 | 12.66 | 22.81 | 19.87 | 49.01 | 33.59 | 27.06 | 31.27 |
25
+ | **TTL-160m** | 53.36 | 2.58 | 21.84 | 18.75 | 43.97 | 36.88 | 22.60 | 28.56 |
26
+ | **Mula-4x160m** | 33.55 | 8.88 | 20.58 | 20.08 | 43.97 | 33.65 | 22.92 | 26.23 |
27
 
28