LucasMagnana commited on
Commit
adc7681
1 Parent(s): f4f1941

LucasMagnana/Pictalk

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: bert-large-uncased-whole-word-masking
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # pictalk
15
 
16
- This model is a fine-tuned version of [bert-large-uncased-whole-word-masking](https://huggingface.co/bert-large-uncased-whole-word-masking) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.5286
19
 
20
  ## Model description
21
 
@@ -47,56 +47,56 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 3.2507 | 1.0 | 25 | 2.7433 |
51
- | 2.518 | 2.0 | 50 | 2.2772 |
52
- | 2.323 | 3.0 | 75 | 2.0185 |
53
- | 2.0883 | 4.0 | 100 | 1.9731 |
54
- | 1.8835 | 5.0 | 125 | 1.9086 |
55
- | 1.8641 | 6.0 | 150 | 1.7880 |
56
- | 1.7244 | 7.0 | 175 | 1.7763 |
57
- | 1.7395 | 8.0 | 200 | 1.7191 |
58
- | 1.6834 | 9.0 | 225 | 1.6734 |
59
- | 1.6631 | 10.0 | 250 | 1.6970 |
60
- | 1.5764 | 11.0 | 275 | 1.6939 |
61
- | 1.54 | 12.0 | 300 | 1.6576 |
62
- | 1.5205 | 13.0 | 325 | 1.5530 |
63
- | 1.4832 | 14.0 | 350 | 1.5448 |
64
- | 1.4582 | 15.0 | 375 | 1.6000 |
65
- | 1.418 | 16.0 | 400 | 1.5240 |
66
- | 1.4152 | 17.0 | 425 | 1.5330 |
67
- | 1.3529 | 18.0 | 450 | 1.5850 |
68
- | 1.3886 | 19.0 | 475 | 1.4814 |
69
- | 1.3268 | 20.0 | 500 | 1.6087 |
70
- | 1.2914 | 21.0 | 525 | 1.5714 |
71
- | 1.3431 | 22.0 | 550 | 1.4989 |
72
- | 1.2838 | 23.0 | 575 | 1.5934 |
73
- | 1.2943 | 24.0 | 600 | 1.4751 |
74
- | 1.2704 | 25.0 | 625 | 1.5158 |
75
- | 1.284 | 26.0 | 650 | 1.6148 |
76
- | 1.2148 | 27.0 | 675 | 1.4828 |
77
- | 1.2382 | 28.0 | 700 | 1.4890 |
78
- | 1.1684 | 29.0 | 725 | 1.5531 |
79
- | 1.2053 | 30.0 | 750 | 1.4755 |
80
- | 1.1973 | 31.0 | 775 | 1.4426 |
81
- | 1.2127 | 32.0 | 800 | 1.5464 |
82
- | 1.1802 | 33.0 | 825 | 1.4410 |
83
- | 1.1828 | 34.0 | 850 | 1.5026 |
84
- | 1.1338 | 35.0 | 875 | 1.5691 |
85
- | 1.11 | 36.0 | 900 | 1.5073 |
86
- | 1.1456 | 37.0 | 925 | 1.5055 |
87
- | 1.1253 | 38.0 | 950 | 1.5108 |
88
- | 1.1214 | 39.0 | 975 | 1.4563 |
89
- | 1.1654 | 40.0 | 1000 | 1.5881 |
90
- | 1.0921 | 41.0 | 1025 | 1.4060 |
91
- | 1.1087 | 42.0 | 1050 | 1.4952 |
92
- | 1.0824 | 43.0 | 1075 | 1.5512 |
93
- | 1.1127 | 44.0 | 1100 | 1.5481 |
94
- | 1.0994 | 45.0 | 1125 | 1.5692 |
95
- | 1.0579 | 46.0 | 1150 | 1.4802 |
96
- | 1.1006 | 47.0 | 1175 | 1.5585 |
97
- | 1.0692 | 48.0 | 1200 | 1.4303 |
98
- | 1.1131 | 49.0 | 1225 | 1.5129 |
99
- | 1.0943 | 50.0 | 1250 | 1.5286 |
100
 
101
 
102
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: bert-large-uncased
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # pictalk
15
 
16
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.3395
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 4.4213 | 1.0 | 25 | 3.2802 |
51
+ | 3.1204 | 2.0 | 50 | 2.8289 |
52
+ | 2.7337 | 3.0 | 75 | 2.5070 |
53
+ | 2.4701 | 4.0 | 100 | 2.1833 |
54
+ | 2.2536 | 5.0 | 125 | 2.0859 |
55
+ | 2.1284 | 6.0 | 150 | 2.0973 |
56
+ | 1.9703 | 7.0 | 175 | 1.8079 |
57
+ | 1.9372 | 8.0 | 200 | 1.8733 |
58
+ | 1.9115 | 9.0 | 225 | 1.7319 |
59
+ | 1.7705 | 10.0 | 250 | 1.8154 |
60
+ | 1.7454 | 11.0 | 275 | 1.6135 |
61
+ | 1.7338 | 12.0 | 300 | 1.6072 |
62
+ | 1.6741 | 13.0 | 325 | 1.4479 |
63
+ | 1.6552 | 14.0 | 350 | 1.6893 |
64
+ | 1.5546 | 15.0 | 375 | 1.5714 |
65
+ | 1.5905 | 16.0 | 400 | 1.6661 |
66
+ | 1.5136 | 17.0 | 425 | 1.6100 |
67
+ | 1.5403 | 18.0 | 450 | 1.5664 |
68
+ | 1.4947 | 19.0 | 475 | 1.4803 |
69
+ | 1.4654 | 20.0 | 500 | 1.6041 |
70
+ | 1.4449 | 21.0 | 525 | 1.4071 |
71
+ | 1.4817 | 22.0 | 550 | 1.5543 |
72
+ | 1.377 | 23.0 | 575 | 1.3897 |
73
+ | 1.4102 | 24.0 | 600 | 1.4572 |
74
+ | 1.3246 | 25.0 | 625 | 1.5699 |
75
+ | 1.3323 | 26.0 | 650 | 1.4316 |
76
+ | 1.2745 | 27.0 | 675 | 1.5004 |
77
+ | 1.2589 | 28.0 | 700 | 1.5209 |
78
+ | 1.3488 | 29.0 | 725 | 1.4734 |
79
+ | 1.301 | 30.0 | 750 | 1.5197 |
80
+ | 1.2824 | 31.0 | 775 | 1.5087 |
81
+ | 1.2771 | 32.0 | 800 | 1.4041 |
82
+ | 1.2794 | 33.0 | 825 | 1.5773 |
83
+ | 1.2343 | 34.0 | 850 | 1.3722 |
84
+ | 1.3235 | 35.0 | 875 | 1.5125 |
85
+ | 1.2567 | 36.0 | 900 | 1.3877 |
86
+ | 1.2682 | 37.0 | 925 | 1.5471 |
87
+ | 1.2028 | 38.0 | 950 | 1.3677 |
88
+ | 1.2059 | 39.0 | 975 | 1.4233 |
89
+ | 1.2103 | 40.0 | 1000 | 1.5361 |
90
+ | 1.1987 | 41.0 | 1025 | 1.5492 |
91
+ | 1.2853 | 42.0 | 1050 | 1.4274 |
92
+ | 1.2088 | 43.0 | 1075 | 1.5027 |
93
+ | 1.2573 | 44.0 | 1100 | 1.5138 |
94
+ | 1.2511 | 45.0 | 1125 | 1.4198 |
95
+ | 1.1932 | 46.0 | 1150 | 1.3065 |
96
+ | 1.1864 | 47.0 | 1175 | 1.4521 |
97
+ | 1.2362 | 48.0 | 1200 | 1.4576 |
98
+ | 1.215 | 49.0 | 1225 | 1.4246 |
99
+ | 1.2118 | 50.0 | 1250 | 1.3395 |
100
 
101
 
102
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5466e6b534ceacdb0a030ac6917716558d4eafc7f91a480a0244587151354e33
3
  size 1340745016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28960551c321018b269b914cb99ce54c4a35525e9b1d5d54c813374916aab433
3
  size 1340745016
runs/Jan24_09-09-54_7739ca2fa2c1/events.out.tfevents.1706087395.7739ca2fa2c1.737.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d88a604b6ab9738e1d247b52bff8f305ebdbe9bd1bbc69f3ca809af43e53d25
3
- size 21593
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc0a66b314182c498e49d8b62d7b9518889a21974d5f4d6ee718629eef0b227b
3
+ size 26227