gayanin commited on
Commit
b6a211c
1 Parent(s): c7cba22

End of training

Browse files
Files changed (1) hide show
  1. README.md +29 -29
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 [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.2459
19
 
20
  ## Model description
21
 
@@ -48,34 +48,34 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
- | 0.4899 | 0.11 | 500 | 0.3923 |
52
- | 0.4257 | 0.21 | 1000 | 0.3560 |
53
- | 0.3927 | 0.32 | 1500 | 0.3329 |
54
- | 0.4045 | 0.43 | 2000 | 0.3179 |
55
- | 0.2929 | 0.54 | 2500 | 0.3145 |
56
- | 0.35 | 0.64 | 3000 | 0.2964 |
57
- | 0.343 | 0.75 | 3500 | 0.2856 |
58
- | 0.3296 | 0.86 | 4000 | 0.2811 |
59
- | 0.3448 | 0.96 | 4500 | 0.2724 |
60
- | 0.2576 | 1.07 | 5000 | 0.2716 |
61
- | 0.2627 | 1.18 | 5500 | 0.2717 |
62
- | 0.2309 | 1.28 | 6000 | 0.2741 |
63
- | 0.2414 | 1.39 | 6500 | 0.2651 |
64
- | 0.2547 | 1.5 | 7000 | 0.2585 |
65
- | 0.2269 | 1.61 | 7500 | 0.2612 |
66
- | 0.2371 | 1.71 | 8000 | 0.2563 |
67
- | 0.2781 | 1.82 | 8500 | 0.2526 |
68
- | 0.213 | 1.93 | 9000 | 0.2499 |
69
- | 0.2026 | 2.03 | 9500 | 0.2564 |
70
- | 0.1683 | 2.14 | 10000 | 0.2551 |
71
- | 0.1924 | 2.25 | 10500 | 0.2545 |
72
- | 0.2086 | 2.35 | 11000 | 0.2520 |
73
- | 0.1774 | 2.46 | 11500 | 0.2507 |
74
- | 0.1907 | 2.57 | 12000 | 0.2471 |
75
- | 0.175 | 2.68 | 12500 | 0.2469 |
76
- | 0.2055 | 2.78 | 13000 | 0.2467 |
77
- | 0.169 | 2.89 | 13500 | 0.2470 |
78
- | 0.2106 | 3.0 | 14000 | 0.2459 |
79
 
80
 
81
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.2462
19
 
20
  ## Model description
21
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.543 | 0.11 | 500 | 0.3991 |
52
+ | 0.4213 | 0.21 | 1000 | 0.3544 |
53
+ | 0.3907 | 0.32 | 1500 | 0.3328 |
54
+ | 0.4101 | 0.43 | 2000 | 0.3178 |
55
+ | 0.2998 | 0.54 | 2500 | 0.3148 |
56
+ | 0.3549 | 0.64 | 3000 | 0.2948 |
57
+ | 0.3401 | 0.75 | 3500 | 0.2861 |
58
+ | 0.3304 | 0.86 | 4000 | 0.2802 |
59
+ | 0.3404 | 0.96 | 4500 | 0.2749 |
60
+ | 0.2548 | 1.07 | 5000 | 0.2730 |
61
+ | 0.2725 | 1.18 | 5500 | 0.2696 |
62
+ | 0.2305 | 1.28 | 6000 | 0.2755 |
63
+ | 0.2424 | 1.39 | 6500 | 0.2647 |
64
+ | 0.2638 | 1.5 | 7000 | 0.2601 |
65
+ | 0.2276 | 1.61 | 7500 | 0.2622 |
66
+ | 0.2299 | 1.71 | 8000 | 0.2587 |
67
+ | 0.2817 | 1.82 | 8500 | 0.2519 |
68
+ | 0.2252 | 1.93 | 9000 | 0.2505 |
69
+ | 0.2022 | 2.03 | 9500 | 0.2554 |
70
+ | 0.1722 | 2.14 | 10000 | 0.2558 |
71
+ | 0.1878 | 2.25 | 10500 | 0.2546 |
72
+ | 0.2093 | 2.35 | 11000 | 0.2521 |
73
+ | 0.1656 | 2.46 | 11500 | 0.2513 |
74
+ | 0.1921 | 2.57 | 12000 | 0.2478 |
75
+ | 0.1754 | 2.68 | 12500 | 0.2468 |
76
+ | 0.2081 | 2.78 | 13000 | 0.2469 |
77
+ | 0.1707 | 2.89 | 13500 | 0.2472 |
78
+ | 0.2068 | 3.0 | 14000 | 0.2462 |
79
 
80
 
81
  ### Framework versions