Hugging Face's logo

wyluilipe
/
deabuse

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
wyluilipe commited on
Commit
e5c0549
·
verified ·
1 Parent(s): 3d8d251

wyluilipe/deabuse

Browse files
Files changed (5) hide show
  1. .DS_Store +0 -0
  2. README.md +117 -0
  3. model.safetensors +1 -1
  4. runs/May28_11-15-41_deniss-MacBook-Pro.local/events.out.tfevents.1716884145.deniss-MacBook-Pro.local.19764.0 +3 -0
  5. training_args.bin +1 -1
.DS_Store ADDED
Binary file (6.15 kB). View file
 
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ai-forever/ruT5-base
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: deabuse
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # deabuse
14
+
15
+ This model is a fine-tuned version of [ai-forever/ruT5-base](https://huggingface.co/ai-forever/ruT5-base) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0760
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 1
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 4
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 1
45
+ - num_epochs: 3
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 5.7858 | 0.05 | 400 | 0.7427 |
52
+ | 4.3608 | 0.1 | 800 | 0.4047 |
53
+ | 3.2919 | 0.15 | 1200 | 0.2366 |
54
+ | 3.2244 | 0.2 | 1600 | 0.2164 |
55
+ | 3.2491 | 0.25 | 2000 | 0.1757 |
56
+ | 1.6803 | 0.3 | 2400 | 0.1494 |
57
+ | 3.2828 | 0.35 | 2800 | 0.1500 |
58
+ | 3.39 | 0.4 | 3200 | 0.1510 |
59
+ | 0.0933 | 0.45 | 3600 | 0.1524 |
60
+ | 3.4757 | 0.5 | 4000 | 0.1423 |
61
+ | 3.1424 | 0.55 | 4400 | 0.1460 |
62
+ | 0.9616 | 0.6 | 4800 | 0.1178 |
63
+ | 2.6271 | 0.65 | 5200 | 0.1178 |
64
+ | 1.1441 | 0.7 | 5600 | 0.1190 |
65
+ | 3.018 | 0.75 | 6000 | 0.1136 |
66
+ | 1.3421 | 0.8 | 6400 | 0.0936 |
67
+ | 2.3062 | 0.85 | 6800 | 0.0994 |
68
+ | 2.5594 | 0.9 | 7200 | 0.0945 |
69
+ | 2.1381 | 0.95 | 7600 | 0.1061 |
70
+ | 1.0893 | 1.0 | 8000 | 0.1029 |
71
+ | 0.7525 | 1.05 | 8400 | 0.0978 |
72
+ | 2.1886 | 1.1 | 8800 | 0.0840 |
73
+ | 1.9948 | 1.15 | 9200 | 0.0952 |
74
+ | 0.7933 | 1.2 | 9600 | 0.0871 |
75
+ | 2.0757 | 1.25 | 10000 | 0.0853 |
76
+ | 0.6129 | 1.31 | 10400 | 0.0857 |
77
+ | 0.1338 | 1.36 | 10800 | 0.0936 |
78
+ | 2.6454 | 1.41 | 11200 | 0.0834 |
79
+ | 0.4243 | 1.46 | 11600 | 0.0891 |
80
+ | 0.6615 | 1.51 | 12000 | 0.0885 |
81
+ | 0.6634 | 1.56 | 12400 | 0.0942 |
82
+ | 0.5665 | 1.61 | 12800 | 0.0808 |
83
+ | 0.6661 | 1.66 | 13200 | 0.1021 |
84
+ | 1.1028 | 1.71 | 13600 | 0.0820 |
85
+ | 1.5217 | 1.76 | 14000 | 0.0769 |
86
+ | 0.7644 | 1.81 | 14400 | 0.0771 |
87
+ | 1.3725 | 1.86 | 14800 | 0.0800 |
88
+ | 0.846 | 1.91 | 15200 | 0.0788 |
89
+ | 1.7207 | 1.96 | 15600 | 0.0806 |
90
+ | 0.9188 | 2.01 | 16000 | 0.0806 |
91
+ | 1.4303 | 2.06 | 16400 | 0.0814 |
92
+ | 0.1599 | 2.11 | 16800 | 0.1072 |
93
+ | 0.1976 | 2.16 | 17200 | 0.0823 |
94
+ | 0.7077 | 2.21 | 17600 | 0.0830 |
95
+ | 1.8896 | 2.26 | 18000 | 0.0768 |
96
+ | 0.6957 | 2.31 | 18400 | 0.0826 |
97
+ | 0.7827 | 2.36 | 18800 | 0.0802 |
98
+ | 1.3298 | 2.41 | 19200 | 0.0791 |
99
+ | 0.2254 | 2.46 | 19600 | 0.0871 |
100
+ | 1.041 | 2.51 | 20000 | 0.0809 |
101
+ | 1.5451 | 2.56 | 20400 | 0.0838 |
102
+ | 1.6318 | 2.61 | 20800 | 0.0801 |
103
+ | 1.8972 | 2.66 | 21200 | 0.0774 |
104
+ | 1.8895 | 2.71 | 21600 | 0.0762 |
105
+ | 0.7721 | 2.76 | 22000 | 0.0740 |
106
+ | 0.3528 | 2.81 | 22400 | 0.0781 |
107
+ | 1.325 | 2.86 | 22800 | 0.0770 |
108
+ | 0.0282 | 2.91 | 23200 | 0.0785 |
109
+ | 1.6303 | 2.96 | 23600 | 0.0760 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - Transformers 4.39.0.dev0
115
+ - Pytorch 2.2.1
116
+ - Datasets 2.16.1
117
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:664b5d0ca6f28a36714048a983d2d4ba496b93b49b3db6f2259356b496bd6ff3
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f3322c31d2f04904456133361c3379a87aac431c1786c0c38a3680bafdceb32
3
  size 891644712
runs/May28_11-15-41_deniss-MacBook-Pro.local/events.out.tfevents.1716884145.deniss-MacBook-Pro.local.19764.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3749a59247242b051bfca1cb0e12b4bbf78fe204e96cb606fede8f4964f4a0
3
+ size 5095209
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fff35c11553b7d4e400ea0b5ba091b1851daed149ab9a0ba64a37eaaad22eee
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9850d39492a5e3cd484157b6b5260fcf89db9f98530648f6b396468c90294f
3
  size 4856