Hugging Face's logo

Karzan
/
walamakan-t5-base

Text2Text Generation
Transformers
PyTorch
Safetensors
t5
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Community
1
Karzan commited on
Commit
4045208
•
1 Parent(s): fac8cd6

End of training

Browse files
Files changed (6) hide show
  1. README.md +6 -118
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. pytorch_model.bin +1 -1
  5. tokenizer.json +6 -1
  6. training_args.bin +1 -1
README.md CHANGED
@@ -2,8 +2,6 @@
2
  base_model: Karzan/walamakan-t5-base
3
  tags:
4
  - generated_from_trainer
5
- metrics:
6
- - bleu
7
  model-index:
8
  - name: walamakan-t5-base
9
  results: []
@@ -15,10 +13,6 @@ should probably proofread and complete it, then remove this comment. -->
15
  # walamakan-t5-base
16
 
17
  This model is a fine-tuned version of [Karzan/walamakan-t5-base](https://huggingface.co/Karzan/walamakan-t5-base) on an unknown dataset.
18
- It achieves the following results on the evaluation set:
19
- - Loss: 1.0693
20
- - Bleu: 0.0
21
- - Gen Len: 19.0
22
 
23
  ## Model description
24
 
@@ -38,124 +32,18 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
- - train_batch_size: 8
42
- - eval_batch_size: 8
43
  - seed: 42
44
  - gradient_accumulation_steps: 4
45
- - total_train_batch_size: 32
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 100
49
-
50
- ### Training results
51
-
52
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
- |:-------------:|:-----:|:----:|:---------------:|:----:|:-------:|
54
- | No log | 1.0 | 87 | 0.8774 | 0.0 | 19.0 |
55
- | No log | 1.99 | 174 | 0.8688 | 0.0 | 19.0 |
56
- | No log | 2.99 | 261 | 0.8646 | 0.0 | 19.0 |
57
- | No log | 4.0 | 349 | 0.8800 | 0.0 | 19.0 |
58
- | No log | 5.0 | 436 | 0.8954 | 0.0 | 19.0 |
59
- | 1.5379 | 5.99 | 523 | 0.8964 | 0.0 | 19.0 |
60
- | 1.5379 | 6.99 | 610 | 0.8949 | 0.0 | 19.0 |
61
- | 1.5379 | 8.0 | 698 | 0.9078 | 0.0 | 19.0 |
62
- | 1.5379 | 9.0 | 785 | 0.9080 | 0.0 | 19.0 |
63
- | 1.5379 | 9.99 | 872 | 0.9188 | 0.0 | 19.0 |
64
- | 1.5379 | 10.99 | 959 | 0.9262 | 0.0 | 19.0 |
65
- | 1.4663 | 12.0 | 1047 | 0.9254 | 0.0 | 19.0 |
66
- | 1.4663 | 13.0 | 1134 | 0.9270 | 0.0 | 19.0 |
67
- | 1.4663 | 13.99 | 1221 | 0.9348 | 0.0 | 19.0 |
68
- | 1.4663 | 14.99 | 1308 | 0.9354 | 0.0 | 19.0 |
69
- | 1.4663 | 16.0 | 1396 | 0.9399 | 0.0 | 19.0 |
70
- | 1.4663 | 17.0 | 1483 | 0.9453 | 0.0 | 19.0 |
71
- | 1.4062 | 17.99 | 1570 | 0.9441 | 0.0 | 19.0 |
72
- | 1.4062 | 18.99 | 1657 | 0.9510 | 0.0 | 19.0 |
73
- | 1.4062 | 20.0 | 1745 | 0.9555 | 0.0 | 19.0 |
74
- | 1.4062 | 21.0 | 1832 | 0.9549 | 0.0 | 19.0 |
75
- | 1.4062 | 21.99 | 1919 | 0.9629 | 0.0 | 19.0 |
76
- | 1.3566 | 22.99 | 2006 | 0.9607 | 0.0 | 19.0 |
77
- | 1.3566 | 24.0 | 2094 | 0.9686 | 0.0 | 19.0 |
78
- | 1.3566 | 25.0 | 2181 | 0.9687 | 0.0 | 19.0 |
79
- | 1.3566 | 25.99 | 2268 | 0.9741 | 0.0 | 19.0 |
80
- | 1.3566 | 26.99 | 2355 | 0.9719 | 0.0 | 19.0 |
81
- | 1.3566 | 28.0 | 2443 | 0.9711 | 0.0 | 19.0 |
82
- | 1.312 | 29.0 | 2530 | 0.9750 | 0.0 | 19.0 |
83
- | 1.312 | 29.99 | 2617 | 0.9815 | 0.0 | 19.0 |
84
- | 1.312 | 30.99 | 2704 | 0.9841 | 0.0 | 19.0 |
85
- | 1.312 | 32.0 | 2792 | 0.9865 | 0.0 | 19.0 |
86
- | 1.312 | 33.0 | 2879 | 0.9876 | 0.0 | 19.0 |
87
- | 1.312 | 33.99 | 2966 | 0.9914 | 0.0 | 19.0 |
88
- | 1.2731 | 34.99 | 3053 | 0.9942 | 0.0 | 19.0 |
89
- | 1.2731 | 36.0 | 3141 | 0.9938 | 0.0 | 19.0 |
90
- | 1.2731 | 37.0 | 3228 | 0.9994 | 0.0 | 19.0 |
91
- | 1.2731 | 37.99 | 3315 | 1.0028 | 0.0 | 19.0 |
92
- | 1.2731 | 38.99 | 3402 | 1.0039 | 0.0 | 19.0 |
93
- | 1.2731 | 40.0 | 3490 | 1.0050 | 0.0 | 19.0 |
94
- | 1.2366 | 41.0 | 3577 | 1.0093 | 0.0 | 19.0 |
95
- | 1.2366 | 41.99 | 3664 | 1.0072 | 0.0 | 19.0 |
96
- | 1.2366 | 42.99 | 3751 | 1.0118 | 0.0 | 19.0 |
97
- | 1.2366 | 44.0 | 3839 | 1.0137 | 0.0 | 19.0 |
98
- | 1.2366 | 45.0 | 3926 | 1.0156 | 0.0 | 19.0 |
99
- | 1.2054 | 45.99 | 4013 | 1.0157 | 0.0 | 19.0 |
100
- | 1.2054 | 46.99 | 4100 | 1.0179 | 0.0 | 19.0 |
101
- | 1.2054 | 48.0 | 4188 | 1.0212 | 0.0 | 19.0 |
102
- | 1.2054 | 49.0 | 4275 | 1.0237 | 0.0 | 19.0 |
103
- | 1.2054 | 49.99 | 4362 | 1.0230 | 0.0 | 19.0 |
104
- | 1.2054 | 50.99 | 4449 | 1.0262 | 0.0 | 19.0 |
105
- | 1.1797 | 52.0 | 4537 | 1.0269 | 0.0 | 19.0 |
106
- | 1.1797 | 53.0 | 4624 | 1.0293 | 0.0 | 19.0 |
107
- | 1.1797 | 53.99 | 4711 | 1.0311 | 0.0 | 19.0 |
108
- | 1.1797 | 54.99 | 4798 | 1.0323 | 0.0 | 19.0 |
109
- | 1.1797 | 56.0 | 4886 | 1.0342 | 0.0 | 19.0 |
110
- | 1.1797 | 57.0 | 4973 | 1.0371 | 0.0 | 19.0 |
111
- | 1.153 | 57.99 | 5060 | 1.0374 | 0.0 | 19.0 |
112
- | 1.153 | 58.99 | 5147 | 1.0397 | 0.0 | 19.0 |
113
- | 1.153 | 60.0 | 5235 | 1.0411 | 0.0 | 19.0 |
114
- | 1.153 | 61.0 | 5322 | 1.0410 | 0.0 | 19.0 |
115
- | 1.153 | 61.99 | 5409 | 1.0442 | 0.0 | 19.0 |
116
- | 1.153 | 62.99 | 5496 | 1.0438 | 0.0 | 19.0 |
117
- | 1.1322 | 64.0 | 5584 | 1.0466 | 0.0 | 19.0 |
118
- | 1.1322 | 65.0 | 5671 | 1.0471 | 0.0 | 19.0 |
119
- | 1.1322 | 65.99 | 5758 | 1.0501 | 0.0 | 19.0 |
120
- | 1.1322 | 66.99 | 5845 | 1.0501 | 0.0 | 19.0 |
121
- | 1.1322 | 68.0 | 5933 | 1.0505 | 0.0 | 19.0 |
122
- | 1.1102 | 69.0 | 6020 | 1.0519 | 0.0 | 19.0 |
123
- | 1.1102 | 69.99 | 6107 | 1.0535 | 0.0 | 19.0 |
124
- | 1.1102 | 70.99 | 6194 | 1.0548 | 0.0 | 19.0 |
125
- | 1.1102 | 72.0 | 6282 | 1.0546 | 0.0 | 19.0 |
126
- | 1.1102 | 73.0 | 6369 | 1.0558 | 0.0 | 19.0 |
127
- | 1.1102 | 73.99 | 6456 | 1.0569 | 0.0 | 19.0 |
128
- | 1.0962 | 74.99 | 6543 | 1.0590 | 0.0 | 19.0 |
129
- | 1.0962 | 76.0 | 6631 | 1.0585 | 0.0 | 19.0 |
130
- | 1.0962 | 77.0 | 6718 | 1.0598 | 0.0 | 19.0 |
131
- | 1.0962 | 77.99 | 6805 | 1.0605 | 0.0 | 19.0 |
132
- | 1.0962 | 78.99 | 6892 | 1.0616 | 0.0 | 19.0 |
133
- | 1.0962 | 80.0 | 6980 | 1.0627 | 0.0 | 19.0 |
134
- | 1.0821 | 81.0 | 7067 | 1.0633 | 0.0 | 19.0 |
135
- | 1.0821 | 81.99 | 7154 | 1.0633 | 0.0 | 19.0 |
136
- | 1.0821 | 82.99 | 7241 | 1.0634 | 0.0 | 19.0 |
137
- | 1.0821 | 84.0 | 7329 | 1.0648 | 0.0 | 19.0 |
138
- | 1.0821 | 85.0 | 7416 | 1.0651 | 0.0 | 19.0 |
139
- | 1.0739 | 85.99 | 7503 | 1.0657 | 0.0 | 19.0 |
140
- | 1.0739 | 86.99 | 7590 | 1.0657 | 0.0 | 19.0 |
141
- | 1.0739 | 88.0 | 7678 | 1.0671 | 0.0 | 19.0 |
142
- | 1.0739 | 89.0 | 7765 | 1.0680 | 0.0 | 19.0 |
143
- | 1.0739 | 89.99 | 7852 | 1.0680 | 0.0 | 19.0 |
144
- | 1.0739 | 90.99 | 7939 | 1.0684 | 0.0 | 19.0 |
145
- | 1.065 | 92.0 | 8027 | 1.0684 | 0.0 | 19.0 |
146
- | 1.065 | 93.0 | 8114 | 1.0687 | 0.0 | 19.0 |
147
- | 1.065 | 93.99 | 8201 | 1.0689 | 0.0 | 19.0 |
148
- | 1.065 | 94.99 | 8288 | 1.0690 | 0.0 | 19.0 |
149
- | 1.065 | 96.0 | 8376 | 1.0691 | 0.0 | 19.0 |
150
- | 1.065 | 97.0 | 8463 | 1.0692 | 0.0 | 19.0 |
151
- | 1.0606 | 97.99 | 8550 | 1.0692 | 0.0 | 19.0 |
152
- | 1.0606 | 98.99 | 8637 | 1.0692 | 0.0 | 19.0 |
153
- | 1.0606 | 99.71 | 8700 | 1.0693 | 0.0 | 19.0 |
154
-
155
 
156
  ### Framework versions
157
 
158
- - Transformers 4.33.0
159
  - Pytorch 2.0.1+cu118
160
- - Datasets 2.14.4
161
  - Tokenizers 0.13.3
 
2
  base_model: Karzan/walamakan-t5-base
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: walamakan-t5-base
7
  results: []
 
13
  # walamakan-t5-base
14
 
15
  This model is a fine-tuned version of [Karzan/walamakan-t5-base](https://huggingface.co/Karzan/walamakan-t5-base) on an unknown dataset.
 
 
 
 
16
 
17
  ## Model description
18
 
 
32
 
33
  The following hyperparameters were used during training:
34
  - learning_rate: 2e-05
35
+ - train_batch_size: 2
36
+ - eval_batch_size: 2
37
  - seed: 42
38
  - gradient_accumulation_steps: 4
39
+ - total_train_batch_size: 8
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
 
44
  ### Framework versions
45
 
46
+ - Transformers 4.33.1
47
  - Pytorch 2.0.1+cu118
48
+ - Datasets 2.14.5
49
  - Tokenizers 0.13.3
config.json CHANGED
@@ -26,7 +26,7 @@
26
  "relative_attention_num_buckets": 32,
27
  "tie_word_embeddings": false,
28
  "torch_dtype": "float32",
29
- "transformers_version": "4.33.0",
30
  "use_cache": true,
31
  "vocab_size": 32100
32
  }
 
26
  "relative_attention_num_buckets": 32,
27
  "tie_word_embeddings": false,
28
  "torch_dtype": "float32",
29
+ "transformers_version": "4.33.1",
30
  "use_cache": true,
31
  "vocab_size": 32100
32
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
  "pad_token_id": 0,
5
- "transformers_version": "4.33.0"
6
  }
 
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
  "pad_token_id": 0,
5
+ "transformers_version": "4.33.1"
6
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:661ce8d7e3f7fbfc148dc33d01cda7da7e68fc21c45aa9296586a105acdaee66
3
  size 990236853
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae546d64c0779edc7aa99c15ddad75a5ad9e9323bc641087bb7ea877262cd536
3
  size 990236853
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1024,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2d59fc19a19d45f93a7243dc7ad49d050b0688c848f355e76b32af879359836
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0167e949de2f51cece562fbcd38f14e93565a982d3bd0717d016d1edf5a79c1
3
  size 4155