Hugging Face's logo

fpadovani
/
french_clm_wikipedia_30

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
fpadovani commited on
Commit
9715d9d
·
verified ·
1 Parent(s): 2d21de7

Model save

Browse files
Files changed (2) hide show
  1. README.md +53 -53
  2. model.safetensors +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 4.2325
18
 
19
  ## Model description
20
 
@@ -47,58 +47,58 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:-------:|:------:|:---------------:|
52
- | No log | 1.0518 | 2000 | 7.5189 |
53
- | 7.6141 | 2.1036 | 4000 | 6.5682 |
54
- | 7.6141 | 3.1554 | 6000 | 6.1693 |
55
- | 6.2396 | 4.2072 | 8000 | 5.9016 |
56
- | 6.2396 | 5.2590 | 10000 | 5.6737 |
57
- | 5.7217 | 6.3108 | 12000 | 5.4600 |
58
- | 5.7217 | 7.3626 | 14000 | 5.2725 |
59
- | 5.3064 | 8.4144 | 16000 | 5.1075 |
60
- | 5.3064 | 9.4662 | 18000 | 4.9717 |
61
- | 4.9744 | 10.5180 | 20000 | 4.8649 |
62
- | 4.9744 | 11.5698 | 22000 | 4.7635 |
63
- | 4.7273 | 12.6216 | 24000 | 4.6833 |
64
- | 4.7273 | 13.6734 | 26000 | 4.6216 |
65
- | 4.5397 | 14.7252 | 28000 | 4.5626 |
66
- | 4.5397 | 15.7770 | 30000 | 4.5062 |
67
- | 4.3839 | 16.8288 | 32000 | 4.4644 |
68
- | 4.3839 | 17.8806 | 34000 | 4.4263 |
69
- | 4.2529 | 18.9324 | 36000 | 4.3944 |
70
- | 4.2529 | 19.9842 | 38000 | 4.3651 |
71
- | 4.1409 | 21.0360 | 40000 | 4.3513 |
72
- | 4.1409 | 22.0878 | 42000 | 4.3216 |
73
- | 4.0334 | 23.1396 | 44000 | 4.3008 |
74
- | 4.0334 | 24.1914 | 46000 | 4.2791 |
75
- | 3.9378 | 25.2432 | 48000 | 4.2719 |
76
- | 3.9378 | 26.2950 | 50000 | 4.2624 |
77
- | 3.8595 | 27.3468 | 52000 | 4.2532 |
78
- | 3.8595 | 28.3986 | 54000 | 4.2432 |
79
- | 3.7927 | 29.4504 | 56000 | 4.2378 |
80
- | 3.7927 | 30.5022 | 58000 | 4.2377 |
81
- | 3.7367 | 31.5540 | 60000 | 4.2334 |
82
- | 3.7367 | 32.6058 | 62000 | 4.2300 |
83
- | 3.6869 | 33.6576 | 64000 | 4.2269 |
84
- | 3.6869 | 34.7094 | 66000 | 4.2245 |
85
- | 3.6416 | 35.7612 | 68000 | 4.2257 |
86
- | 3.6416 | 36.8130 | 70000 | 4.2206 |
87
- | 3.6032 | 37.8648 | 72000 | 4.2247 |
88
- | 3.6032 | 38.9166 | 74000 | 4.2272 |
89
- | 3.5669 | 39.9684 | 76000 | 4.2262 |
90
- | 3.5669 | 41.0202 | 78000 | 4.2309 |
91
- | 3.533 | 42.0720 | 80000 | 4.2304 |
92
- | 3.533 | 43.1238 | 82000 | 4.2290 |
93
- | 3.5033 | 44.1757 | 84000 | 4.2331 |
94
- | 3.5033 | 45.2275 | 86000 | 4.2322 |
95
- | 3.4759 | 46.2793 | 88000 | 4.2311 |
96
- | 3.4759 | 47.3311 | 90000 | 4.2341 |
97
- | 3.4528 | 48.3829 | 92000 | 4.2348 |
98
- | 3.4528 | 49.4347 | 94000 | 4.2326 |
99
- | 3.4319 | 50.4865 | 96000 | 4.2331 |
100
- | 3.4319 | 51.5383 | 98000 | 4.2326 |
101
- | 3.4136 | 52.5901 | 100000 | 4.2325 |
102
 
103
 
104
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 4.0459
18
 
19
  ## Model description
20
 
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:--------:|:------:|:---------------:|
52
+ | No log | 2.1471 | 2000 | 7.1380 |
53
+ | 7.213 | 4.2941 | 4000 | 5.8542 |
54
+ | 7.213 | 6.4412 | 6000 | 5.4036 |
55
+ | 5.4304 | 8.5883 | 8000 | 5.0499 |
56
+ | 5.4304 | 10.7354 | 10000 | 4.7606 |
57
+ | 4.771 | 12.8824 | 12000 | 4.5172 |
58
+ | 4.771 | 15.0295 | 14000 | 4.3206 |
59
+ | 4.2888 | 17.1766 | 16000 | 4.1530 |
60
+ | 4.2888 | 19.3237 | 18000 | 4.0155 |
61
+ | 3.9141 | 21.4707 | 20000 | 3.8966 |
62
+ | 3.9141 | 23.6178 | 22000 | 3.8047 |
63
+ | 3.6154 | 25.7649 | 24000 | 3.7359 |
64
+ | 3.6154 | 27.9120 | 26000 | 3.6784 |
65
+ | 3.3661 | 30.0590 | 28000 | 3.6360 |
66
+ | 3.3661 | 32.2061 | 30000 | 3.6019 |
67
+ | 3.1473 | 34.3532 | 32000 | 3.5816 |
68
+ | 3.1473 | 36.5003 | 34000 | 3.5699 |
69
+ | 2.9533 | 38.6473 | 36000 | 3.5650 |
70
+ | 2.9533 | 40.7944 | 38000 | 3.5667 |
71
+ | 2.777 | 42.9415 | 40000 | 3.5747 |
72
+ | 2.777 | 45.0886 | 42000 | 3.5878 |
73
+ | 2.6015 | 47.2356 | 44000 | 3.6107 |
74
+ | 2.6015 | 49.3827 | 46000 | 3.6261 |
75
+ | 2.4429 | 51.5298 | 48000 | 3.6414 |
76
+ | 2.4429 | 53.6769 | 50000 | 3.6637 |
77
+ | 2.3125 | 55.8239 | 52000 | 3.6778 |
78
+ | 2.3125 | 57.9710 | 54000 | 3.7033 |
79
+ | 2.1989 | 60.1181 | 56000 | 3.7410 |
80
+ | 2.1989 | 62.2652 | 58000 | 3.7755 |
81
+ | 2.1044 | 64.4122 | 60000 | 3.7876 |
82
+ | 2.1044 | 66.5593 | 62000 | 3.8081 |
83
+ | 2.0257 | 68.7064 | 64000 | 3.8222 |
84
+ | 2.0257 | 70.8535 | 66000 | 3.8411 |
85
+ | 1.9563 | 73.0005 | 68000 | 3.8488 |
86
+ | 1.9563 | 75.1476 | 70000 | 3.8915 |
87
+ | 1.8905 | 77.2947 | 72000 | 3.9079 |
88
+ | 1.8905 | 79.4418 | 74000 | 3.9169 |
89
+ | 1.836 | 81.5888 | 76000 | 3.9382 |
90
+ | 1.836 | 83.7359 | 78000 | 3.9430 |
91
+ | 1.7885 | 85.8830 | 80000 | 3.9471 |
92
+ | 1.7885 | 88.0301 | 82000 | 3.9668 |
93
+ | 1.7431 | 90.1771 | 84000 | 3.9860 |
94
+ | 1.7431 | 92.3242 | 86000 | 4.0088 |
95
+ | 1.7024 | 94.4713 | 88000 | 4.0132 |
96
+ | 1.7024 | 96.6184 | 90000 | 4.0260 |
97
+ | 1.6687 | 98.7654 | 92000 | 4.0358 |
98
+ | 1.6687 | 100.9125 | 94000 | 4.0290 |
99
+ | 1.6369 | 103.0596 | 96000 | 4.0422 |
100
+ | 1.6369 | 105.2067 | 98000 | 4.0445 |
101
+ | 1.6129 | 107.3537 | 100000 | 4.0459 |
102
 
103
 
104
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ed9362952b4fd87e379a57f57f1be931144492d1af09c3d76139f60bb946e69
3
  size 51007160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8b1563b095c6564a53ebf57a86c5fa081e4578472b661ade29b2847c968ea5
3
  size 51007160