augustocsc commited on
Commit
871d2fa
·
1 Parent(s): 8abe706

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -33
README.md CHANGED
@@ -12,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # gpt-m-large
14
 
15
- This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0342
18
 
19
  ## Model description
20
 
@@ -45,37 +45,37 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:-----:|:---------------:|
48
- | 0.6102 | 0.03 | 1000 | 0.3834 |
49
- | 1.2492 | 0.06 | 2000 | 0.5341 |
50
- | 0.839 | 0.09 | 3000 | 0.5090 |
51
- | 1.8656 | 0.13 | 4000 | 1.4058 |
52
- | 0.0595 | 0.16 | 5000 | 0.0546 |
53
- | 0.0462 | 0.19 | 6000 | 0.0404 |
54
- | 0.0399 | 0.22 | 7000 | 0.0372 |
55
- | 0.0382 | 0.25 | 8000 | 0.0363 |
56
- | 0.037 | 0.28 | 9000 | 0.0361 |
57
- | 0.0365 | 0.31 | 10000 | 0.0352 |
58
- | 0.0362 | 0.35 | 11000 | 0.0349 |
59
- | 0.0357 | 0.38 | 12000 | 0.0347 |
60
- | 0.0356 | 0.41 | 13000 | 0.0345 |
61
- | 0.0349 | 0.44 | 14000 | 0.0344 |
62
- | 0.0352 | 0.47 | 15000 | 0.0343 |
63
- | 0.0355 | 0.5 | 16000 | 0.0342 |
64
- | 0.0354 | 0.53 | 17000 | 0.0342 |
65
- | 0.0352 | 0.57 | 18000 | 0.0342 |
66
- | 0.0352 | 0.6 | 19000 | 0.0342 |
67
- | 0.0352 | 0.63 | 20000 | 0.0342 |
68
- | 0.0351 | 0.66 | 21000 | 0.0342 |
69
- | 0.0348 | 0.69 | 22000 | 0.0342 |
70
- | 0.035 | 0.72 | 23000 | 0.0342 |
71
- | 0.0354 | 0.75 | 24000 | 0.0342 |
72
- | 0.0354 | 0.79 | 25000 | 0.0342 |
73
- | 0.0353 | 0.82 | 26000 | 0.0342 |
74
- | 0.0352 | 0.85 | 27000 | 0.0342 |
75
- | 0.035 | 0.88 | 28000 | 0.0342 |
76
- | 0.0349 | 0.91 | 29000 | 0.0342 |
77
- | 0.0351 | 0.94 | 30000 | 0.0342 |
78
- | 0.0355 | 0.97 | 31000 | 0.0342 |
79
 
80
 
81
  ### Framework versions
 
12
 
13
  # gpt-m-large
14
 
15
+ This model is a fine-tuned version of [augustocsc/gpt-m-large](https://huggingface.co/augustocsc/gpt-m-large) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0327
18
 
19
  ## Model description
20
 
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:-----:|:---------------:|
48
+ | 0.0343 | 0.03 | 1000 | 0.0343 |
49
+ | 0.0337 | 0.06 | 2000 | 0.0342 |
50
+ | 0.0338 | 0.09 | 3000 | 0.0338 |
51
+ | 0.0349 | 0.13 | 4000 | 0.0337 |
52
+ | 0.034 | 0.16 | 5000 | 0.0335 |
53
+ | 0.0342 | 0.19 | 6000 | 0.0334 |
54
+ | 0.0341 | 0.22 | 7000 | 0.0333 |
55
+ | 0.0339 | 0.25 | 8000 | 0.0333 |
56
+ | 0.0336 | 0.28 | 9000 | 0.0331 |
57
+ | 0.0335 | 0.31 | 10000 | 0.0330 |
58
+ | 0.0334 | 0.35 | 11000 | 0.0330 |
59
+ | 0.0331 | 0.38 | 12000 | 0.0328 |
60
+ | 0.0332 | 0.41 | 13000 | 0.0328 |
61
+ | 0.0327 | 0.44 | 14000 | 0.0327 |
62
+ | 0.0331 | 0.47 | 15000 | 0.0327 |
63
+ | 0.0335 | 0.5 | 16000 | 0.0327 |
64
+ | 0.0333 | 0.53 | 17000 | 0.0327 |
65
+ | 0.0333 | 0.57 | 18000 | 0.0327 |
66
+ | 0.0333 | 0.6 | 19000 | 0.0327 |
67
+ | 0.0332 | 0.63 | 20000 | 0.0327 |
68
+ | 0.0331 | 0.66 | 21000 | 0.0327 |
69
+ | 0.0328 | 0.69 | 22000 | 0.0327 |
70
+ | 0.033 | 0.72 | 23000 | 0.0327 |
71
+ | 0.0334 | 0.75 | 24000 | 0.0327 |
72
+ | 0.0334 | 0.79 | 25000 | 0.0327 |
73
+ | 0.0333 | 0.82 | 26000 | 0.0327 |
74
+ | 0.0332 | 0.85 | 27000 | 0.0327 |
75
+ | 0.033 | 0.88 | 28000 | 0.0327 |
76
+ | 0.033 | 0.91 | 29000 | 0.0327 |
77
+ | 0.0331 | 0.94 | 30000 | 0.0327 |
78
+ | 0.0335 | 0.97 | 31000 | 0.0327 |
79
 
80
 
81
  ### Framework versions