NasimB commited on
Commit
d24887b
·
1 Parent(s): 09734b6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -2
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 3.5640
19
 
20
  ## Model description
21
 
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 1000
44
- - num_epochs: 10
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
@@ -90,6 +90,45 @@ The following hyperparameters were used during training:
90
  | 3.4877 | 9.33 | 20000 | 3.5692 |
91
  | 3.4818 | 9.57 | 20500 | 3.5641 |
92
  | 3.4844 | 9.8 | 21000 | 3.5640 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93
 
94
 
95
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3.2321
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 19
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
 
90
  | 3.4877 | 9.33 | 20000 | 3.5692 |
91
  | 3.4818 | 9.57 | 20500 | 3.5641 |
92
  | 3.4844 | 9.8 | 21000 | 3.5640 |
93
+ | 3.5323 | 10.03 | 21500 | 3.6026 |
94
+ | 3.5123 | 10.27 | 22000 | 3.5877 |
95
+ | 3.5046 | 10.5 | 22500 | 3.5595 |
96
+ | 3.4787 | 10.73 | 23000 | 3.5403 |
97
+ | 3.4568 | 10.97 | 23500 | 3.5125 |
98
+ | 3.4154 | 11.2 | 24000 | 3.4916 |
99
+ | 3.3998 | 11.43 | 24500 | 3.4749 |
100
+ | 3.3986 | 11.67 | 25000 | 3.4578 |
101
+ | 3.372 | 11.9 | 25500 | 3.4405 |
102
+ | 3.3402 | 12.13 | 26000 | 3.4317 |
103
+ | 3.3281 | 12.37 | 26500 | 3.4215 |
104
+ | 3.322 | 12.6 | 27000 | 3.4093 |
105
+ | 3.3198 | 12.83 | 27500 | 3.4026 |
106
+ | 3.3039 | 13.07 | 28000 | 3.3971 |
107
+ | 3.296 | 13.3 | 28500 | 3.3954 |
108
+ | 3.3015 | 13.53 | 29000 | 3.3954 |
109
+ | 3.2939 | 13.77 | 29500 | 3.3927 |
110
+ | 3.3013 | 14.0 | 30000 | 3.3918 |
111
+ | 3.343 | 14.23 | 30500 | 3.4265 |
112
+ | 3.3438 | 14.47 | 31000 | 3.4133 |
113
+ | 3.3397 | 14.7 | 31500 | 3.3951 |
114
+ | 3.3156 | 14.93 | 32000 | 3.3681 |
115
+ | 3.2815 | 15.17 | 32500 | 3.3503 |
116
+ | 3.2654 | 15.4 | 33000 | 3.3313 |
117
+ | 3.2492 | 15.63 | 33500 | 3.3184 |
118
+ | 3.2399 | 15.87 | 34000 | 3.2995 |
119
+ | 3.2222 | 16.1 | 34500 | 3.2922 |
120
+ | 3.2026 | 16.33 | 35000 | 3.2818 |
121
+ | 3.191 | 16.57 | 35500 | 3.2723 |
122
+ | 3.1825 | 16.8 | 36000 | 3.2640 |
123
+ | 3.1691 | 17.03 | 36500 | 3.2530 |
124
+ | 3.1656 | 17.27 | 37000 | 3.2487 |
125
+ | 3.1487 | 17.5 | 37500 | 3.2419 |
126
+ | 3.1635 | 17.73 | 38000 | 3.2411 |
127
+ | 3.1675 | 17.97 | 38500 | 3.2330 |
128
+ | 3.1422 | 18.2 | 39000 | 3.2344 |
129
+ | 3.1443 | 18.43 | 39500 | 3.2331 |
130
+ | 3.1425 | 18.67 | 40000 | 3.2348 |
131
+ | 3.139 | 18.9 | 40500 | 3.2321 |
132
 
133
 
134
  ### Framework versions