Hugging Face's logo

Kudod
/
hoa-1b4_model_nmt_test

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
Kudod commited on
Commit
4155ff6
·
verified ·
1 Parent(s): 7078a50

End of training

Browse files
Files changed (3) hide show
  1. README.md +158 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Mar08_14-42-07_ubuntu/events.out.tfevents.1709883731.ubuntu.9250.0 +2 -2
README.md ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigscience-bloom-rail-1.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: vlsp-2023-vllm/hoa-1b4
7
+ model-index:
8
+ - name: hoa-1b4_model_nmt_test
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # hoa-1b4_model_nmt_test
16
+
17
+ This model is a fine-tuned version of [vlsp-2023-vllm/hoa-1b4](https://huggingface.co/vlsp-2023-vllm/hoa-1b4) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0045
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 4e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 100
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 1.0 | 21 | 2.8255 |
51
+ | No log | 2.0 | 42 | 2.3028 |
52
+ | No log | 3.0 | 63 | 1.8727 |
53
+ | No log | 4.0 | 84 | 1.5161 |
54
+ | No log | 5.0 | 105 | 1.2181 |
55
+ | No log | 6.0 | 126 | 0.9991 |
56
+ | No log | 7.0 | 147 | 0.7980 |
57
+ | No log | 8.0 | 168 | 0.6372 |
58
+ | No log | 9.0 | 189 | 0.5075 |
59
+ | No log | 10.0 | 210 | 0.4042 |
60
+ | No log | 11.0 | 231 | 0.3321 |
61
+ | No log | 12.0 | 252 | 0.2716 |
62
+ | No log | 13.0 | 273 | 0.2143 |
63
+ | No log | 14.0 | 294 | 0.1740 |
64
+ | No log | 15.0 | 315 | 0.1397 |
65
+ | No log | 16.0 | 336 | 0.1263 |
66
+ | No log | 17.0 | 357 | 0.0990 |
67
+ | No log | 18.0 | 378 | 0.0853 |
68
+ | No log | 19.0 | 399 | 0.0678 |
69
+ | No log | 20.0 | 420 | 0.0546 |
70
+ | No log | 21.0 | 441 | 0.0476 |
71
+ | No log | 22.0 | 462 | 0.0441 |
72
+ | No log | 23.0 | 483 | 0.0367 |
73
+ | 0.7202 | 24.0 | 504 | 0.0292 |
74
+ | 0.7202 | 25.0 | 525 | 0.0241 |
75
+ | 0.7202 | 26.0 | 546 | 0.0227 |
76
+ | 0.7202 | 27.0 | 567 | 0.0207 |
77
+ | 0.7202 | 28.0 | 588 | 0.0186 |
78
+ | 0.7202 | 29.0 | 609 | 0.0168 |
79
+ | 0.7202 | 30.0 | 630 | 0.0139 |
80
+ | 0.7202 | 31.0 | 651 | 0.0126 |
81
+ | 0.7202 | 32.0 | 672 | 0.0113 |
82
+ | 0.7202 | 33.0 | 693 | 0.0113 |
83
+ | 0.7202 | 34.0 | 714 | 0.0107 |
84
+ | 0.7202 | 35.0 | 735 | 0.0099 |
85
+ | 0.7202 | 36.0 | 756 | 0.0087 |
86
+ | 0.7202 | 37.0 | 777 | 0.0085 |
87
+ | 0.7202 | 38.0 | 798 | 0.0080 |
88
+ | 0.7202 | 39.0 | 819 | 0.0077 |
89
+ | 0.7202 | 40.0 | 840 | 0.0072 |
90
+ | 0.7202 | 41.0 | 861 | 0.0071 |
91
+ | 0.7202 | 42.0 | 882 | 0.0070 |
92
+ | 0.7202 | 43.0 | 903 | 0.0068 |
93
+ | 0.7202 | 44.0 | 924 | 0.0064 |
94
+ | 0.7202 | 45.0 | 945 | 0.0063 |
95
+ | 0.7202 | 46.0 | 966 | 0.0061 |
96
+ | 0.7202 | 47.0 | 987 | 0.0061 |
97
+ | 0.0146 | 48.0 | 1008 | 0.0060 |
98
+ | 0.0146 | 49.0 | 1029 | 0.0058 |
99
+ | 0.0146 | 50.0 | 1050 | 0.0059 |
100
+ | 0.0146 | 51.0 | 1071 | 0.0067 |
101
+ | 0.0146 | 52.0 | 1092 | 0.0056 |
102
+ | 0.0146 | 53.0 | 1113 | 0.0055 |
103
+ | 0.0146 | 54.0 | 1134 | 0.0055 |
104
+ | 0.0146 | 55.0 | 1155 | 0.0053 |
105
+ | 0.0146 | 56.0 | 1176 | 0.0055 |
106
+ | 0.0146 | 57.0 | 1197 | 0.0055 |
107
+ | 0.0146 | 58.0 | 1218 | 0.0057 |
108
+ | 0.0146 | 59.0 | 1239 | 0.0053 |
109
+ | 0.0146 | 60.0 | 1260 | 0.0052 |
110
+ | 0.0146 | 61.0 | 1281 | 0.0052 |
111
+ | 0.0146 | 62.0 | 1302 | 0.0051 |
112
+ | 0.0146 | 63.0 | 1323 | 0.0050 |
113
+ | 0.0146 | 64.0 | 1344 | 0.0049 |
114
+ | 0.0146 | 65.0 | 1365 | 0.0050 |
115
+ | 0.0146 | 66.0 | 1386 | 0.0049 |
116
+ | 0.0146 | 67.0 | 1407 | 0.0049 |
117
+ | 0.0146 | 68.0 | 1428 | 0.0050 |
118
+ | 0.0146 | 69.0 | 1449 | 0.0049 |
119
+ | 0.0146 | 70.0 | 1470 | 0.0049 |
120
+ | 0.0146 | 71.0 | 1491 | 0.0048 |
121
+ | 0.0064 | 72.0 | 1512 | 0.0048 |
122
+ | 0.0064 | 73.0 | 1533 | 0.0047 |
123
+ | 0.0064 | 74.0 | 1554 | 0.0048 |
124
+ | 0.0064 | 75.0 | 1575 | 0.0048 |
125
+ | 0.0064 | 76.0 | 1596 | 0.0047 |
126
+ | 0.0064 | 77.0 | 1617 | 0.0047 |
127
+ | 0.0064 | 78.0 | 1638 | 0.0047 |
128
+ | 0.0064 | 79.0 | 1659 | 0.0047 |
129
+ | 0.0064 | 80.0 | 1680 | 0.0048 |
130
+ | 0.0064 | 81.0 | 1701 | 0.0046 |
131
+ | 0.0064 | 82.0 | 1722 | 0.0046 |
132
+ | 0.0064 | 83.0 | 1743 | 0.0046 |
133
+ | 0.0064 | 84.0 | 1764 | 0.0046 |
134
+ | 0.0064 | 85.0 | 1785 | 0.0046 |
135
+ | 0.0064 | 86.0 | 1806 | 0.0046 |
136
+ | 0.0064 | 87.0 | 1827 | 0.0046 |
137
+ | 0.0064 | 88.0 | 1848 | 0.0046 |
138
+ | 0.0064 | 89.0 | 1869 | 0.0046 |
139
+ | 0.0064 | 90.0 | 1890 | 0.0046 |
140
+ | 0.0064 | 91.0 | 1911 | 0.0045 |
141
+ | 0.0064 | 92.0 | 1932 | 0.0045 |
142
+ | 0.0064 | 93.0 | 1953 | 0.0045 |
143
+ | 0.0064 | 94.0 | 1974 | 0.0045 |
144
+ | 0.0064 | 95.0 | 1995 | 0.0045 |
145
+ | 0.0052 | 96.0 | 2016 | 0.0045 |
146
+ | 0.0052 | 97.0 | 2037 | 0.0045 |
147
+ | 0.0052 | 98.0 | 2058 | 0.0045 |
148
+ | 0.0052 | 99.0 | 2079 | 0.0045 |
149
+ | 0.0052 | 100.0 | 2100 | 0.0045 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - PEFT 0.8.2
155
+ - Transformers 4.37.2
156
+ - Pytorch 2.0.1+cu117
157
+ - Datasets 2.14.5
158
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed83d99486cc6e424f71f8b8e113bbc8916e0e7fb18baf929d385b9e32d7e359
3
  size 12590048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f0c4ff65b094be2384791eca87402f5408d11f15cc36d21c1d4d8093143ff3
3
  size 12590048
runs/Mar08_14-42-07_ubuntu/events.out.tfevents.1709883731.ubuntu.9250.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7270cb8b04f0d53ce344949ccbae56d0f8aa830f988ca9bef49dca1f78c77bfa
3
- size 30960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d31048dd7ce75ff2844f5151b32e1d567be62270cb053d0f3c34f5f4a36b85e
3
+ size 32669