Hugging Face's logo

nlparabic
/
results_fixed

Safetensors
gpt2
Generated from Trainer
Model card Files Community
nlparabic commited on
Commit
aa08640
•
1 Parent(s): fd8b661

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.9793
22
- - Bleu: 0.3130
23
- - Rouge1: 0.5832
24
- - Rouge2: 0.3461
25
- - Rougel: 0.5454
26
 
27
  ## Model description
28
 
@@ -55,23 +55,25 @@ The following hyperparameters were used during training:
55
  | Training Loss | Epoch | Step | Bleu | Validation Loss | Rouge1 | Rouge2 | Rougel |
56
  |:-------------:|:------:|:----:|:------:|:---------------:|:------:|:------:|:------:|
57
  | 3.9816 | 1.0846 | 500 | 0.2270 | 2.8213 | 0.3851 | 0.1625 | 0.3198 |
58
- | 3.9816 | 2.0 | 922 | 2.4793 | 0.2481 | 0.4405 | 0.2030 | 0.3844 |
59
- | 2.6514 | 3.0 | 1383 | 2.2931 | 0.2658 | 0.4828 | 0.2385 | 0.4327 |
60
- | 2.3308 | 4.0 | 1844 | 2.1801 | 0.2797 | 0.5114 | 0.2679 | 0.4659 |
61
- | 2.1322 | 5.0 | 2305 | 2.1133 | 0.2886 | 0.5264 | 0.2867 | 0.4852 |
62
- | 1.9942 | 6.0 | 2766 | 2.0649 | 0.2926 | 0.5417 | 0.2993 | 0.5003 |
63
- | 1.8884 | 7.0 | 3227 | 2.0354 | 0.2967 | 0.5529 | 0.3108 | 0.5117 |
64
- | 1.8003 | 8.0 | 3688 | 2.0164 | 0.2973 | 0.5597 | 0.3199 | 0.5204 |
65
- | 1.7305 | 9.0 | 4149 | 2.0036 | 0.3053 | 0.5660 | 0.3262 | 0.5266 |
66
- | 1.6672 | 10.0 | 4610 | 1.9933 | 0.3072 | 0.5704 | 0.3319 | 0.5325 |
67
- | 1.6132 | 11.0 | 5071 | 1.9886 | 0.3093 | 0.5737 | 0.3366 | 0.5363 |
68
- | 1.5659 | 12.0 | 5532 | 1.9834 | 0.3099 | 0.5777 | 0.3397 | 0.5396 |
69
- | 1.5659 | 13.0 | 5993 | 1.9819 | 0.3117 | 0.5796 | 0.3423 | 0.5418 |
70
- | 1.5244 | 14.0 | 6454 | 1.9798 | 0.3126 | 0.5833 | 0.3452 | 0.5451 |
71
- | 1.4884 | 15.0 | 6915 | 1.9793 | 0.3130 | 0.5832 | 0.3461 | 0.5454 |
72
- | 1.4594 | 16.0 | 7376 | 1.9800 | 0.3133 | 0.5846 | 0.3469 | 0.5466 |
73
- | 1.4361 | 17.0 | 7837 | 1.9799 | 0.3151 | 0.5865 | 0.3493 | 0.5485 |
74
- | 1.4159 | 18.0 | 8298 | 1.9809 | 0.3149 | 0.5865 | 0.3495 | 0.5486 |
 
 
75
 
76
 
77
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.0654
22
+ - Bleu: 0.3119
23
+ - Rouge1: 0.5862
24
+ - Rouge2: 0.3489
25
+ - Rougel: 0.5479
26
 
27
  ## Model description
28
 
 
55
  | Training Loss | Epoch | Step | Bleu | Validation Loss | Rouge1 | Rouge2 | Rougel |
56
  |:-------------:|:------:|:----:|:------:|:---------------:|:------:|:------:|:------:|
57
  | 3.9816 | 1.0846 | 500 | 0.2270 | 2.8213 | 0.3851 | 0.1625 | 0.3198 |
58
+ | 3.9816 | 2.0 | 922 | 0.2481 | 2.4793 | 0.4405 | 0.2030 | 0.3844 |
59
+ | 2.6514 | 3.0 | 1383 | 0.2658 | 2.2931 | 0.4828 | 0.2385 | 0.4327 |
60
+ | 2.3308 | 4.0 | 1844 | 0.2797 | 2.1801 | 0.5114 | 0.2679 | 0.4659 |
61
+ | 2.1322 | 5.0 | 2305 | 0.2886 | 2.1133 | 0.5264 | 0.2867 | 0.4852 |
62
+ | 1.9942 | 6.0 | 2766 | 0.2926 | 2.0649 | 0.5417 | 0.2993 | 0.5003 |
63
+ | 1.8884 | 7.0 | 3227 | 0.2967 | 2.0354 | 0.5529 | 0.3108 | 0.5117 |
64
+ | 1.8003 | 8.0 | 3688 | 0.2973 | 2.0164 | 0.5597 | 0.3199 | 0.5204 |
65
+ | 1.7305 | 9.0 | 4149 | 0.3053 | 2.0036 | 0.5660 | 0.3262 | 0.5266 |
66
+ | 1.6672 | 10.0 | 4610 | 0.3072 | 1.9933 | 0.5704 | 0.3319 | 0.5325 |
67
+ | 1.6132 | 11.0 | 5071 | 0.3093 | 1.9886 | 0.5737 | 0.3366 | 0.5363 |
68
+ | 1.5659 | 12.0 | 5532 | 0.3099 | 1.9834 | 0.5777 | 0.3397 | 0.5396 |
69
+ | 1.5659 | 13.0 | 5993 | 0.3117 | 1.9819 | 0.5796 | 0.3423 | 0.5418 |
70
+ | 1.5244 | 14.0 | 6454 | 0.3126 | 1.9798 | 0.5833 | 0.3452 | 0.5451 |
71
+ | 1.4884 | 15.0 | 6915 | 0.3130 | 1.9793 | 0.5832 | 0.3461 | 0.5454 |
72
+ | 1.4594 | 16.0 | 7376 | 0.3133 | 1.9800 | 0.5846 | 0.3469 | 0.5466 |
73
+ | 1.4361 | 17.0 | 7837 | 0.3151 | 1.9799 | 0.5865 | 0.3493 | 0.5485 |
74
+ | 1.4159 | 18.0 | 8298 | 0.3149 | 1.9809 | 0.5865 | 0.3495 | 0.5486 |
75
+ | 1.4159 | 19.0 | 8398 | 2.0767 | 0.3099 | 0.5858 | 0.3476 | 0.5471 |
76
+ | 1.6189 | 20.0 | 8840 | 2.0654 | 0.3119 | 0.5862 | 0.3489 | 0.5479 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f8f07fa3f54a2b7688f51c9687635358dc942deacbfa22b3c60d7bc0f5987ff
3
  size 539221632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eebba2f2ff833170f3124d5c7a39e6a8e26d5c480423329231080b523195e5df
3
  size 539221632