Hugging Face's logo

Kudod
/
hoa-1b4_model_kaggle_test

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
Kudod commited on
Commit
3bbf3a5
·
verified ·
1 Parent(s): 9cb811f

End of training

Browse files
Files changed (3) hide show
  1. README.md +158 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Mar07_10-02-32_cb74e324675c/events.out.tfevents.1709805756.cb74e324675c.34.0 +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_kaggle_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_kaggle_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: 0.0088
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 | 7 | 3.2766 |
51
+ | No log | 2.0 | 14 | 2.8527 |
52
+ | No log | 3.0 | 21 | 2.6111 |
53
+ | No log | 4.0 | 28 | 2.3834 |
54
+ | No log | 5.0 | 35 | 2.1930 |
55
+ | No log | 6.0 | 42 | 2.0336 |
56
+ | No log | 7.0 | 49 | 1.8676 |
57
+ | No log | 8.0 | 56 | 1.7066 |
58
+ | No log | 9.0 | 63 | 1.5550 |
59
+ | No log | 10.0 | 70 | 1.4148 |
60
+ | No log | 11.0 | 77 | 1.2909 |
61
+ | No log | 12.0 | 84 | 1.1698 |
62
+ | No log | 13.0 | 91 | 1.0494 |
63
+ | No log | 14.0 | 98 | 0.9417 |
64
+ | No log | 15.0 | 105 | 0.8308 |
65
+ | No log | 16.0 | 112 | 0.7236 |
66
+ | No log | 17.0 | 119 | 0.6239 |
67
+ | No log | 18.0 | 126 | 0.5360 |
68
+ | No log | 19.0 | 133 | 0.4547 |
69
+ | No log | 20.0 | 140 | 0.3911 |
70
+ | No log | 21.0 | 147 | 0.3288 |
71
+ | No log | 22.0 | 154 | 0.2807 |
72
+ | No log | 23.0 | 161 | 0.2396 |
73
+ | No log | 24.0 | 168 | 0.2013 |
74
+ | No log | 25.0 | 175 | 0.1764 |
75
+ | No log | 26.0 | 182 | 0.1483 |
76
+ | No log | 27.0 | 189 | 0.1240 |
77
+ | No log | 28.0 | 196 | 0.1128 |
78
+ | No log | 29.0 | 203 | 0.0983 |
79
+ | No log | 30.0 | 210 | 0.0868 |
80
+ | No log | 31.0 | 217 | 0.0775 |
81
+ | No log | 32.0 | 224 | 0.0722 |
82
+ | No log | 33.0 | 231 | 0.0613 |
83
+ | No log | 34.0 | 238 | 0.0570 |
84
+ | No log | 35.0 | 245 | 0.0495 |
85
+ | No log | 36.0 | 252 | 0.0441 |
86
+ | No log | 37.0 | 259 | 0.0409 |
87
+ | No log | 38.0 | 266 | 0.0360 |
88
+ | No log | 39.0 | 273 | 0.0314 |
89
+ | No log | 40.0 | 280 | 0.0296 |
90
+ | No log | 41.0 | 287 | 0.0250 |
91
+ | No log | 42.0 | 294 | 0.0231 |
92
+ | No log | 43.0 | 301 | 0.0241 |
93
+ | No log | 44.0 | 308 | 0.0196 |
94
+ | No log | 45.0 | 315 | 0.0183 |
95
+ | No log | 46.0 | 322 | 0.0176 |
96
+ | No log | 47.0 | 329 | 0.0173 |
97
+ | No log | 48.0 | 336 | 0.0143 |
98
+ | No log | 49.0 | 343 | 0.0145 |
99
+ | No log | 50.0 | 350 | 0.0138 |
100
+ | No log | 51.0 | 357 | 0.0131 |
101
+ | No log | 52.0 | 364 | 0.0138 |
102
+ | No log | 53.0 | 371 | 0.0142 |
103
+ | No log | 54.0 | 378 | 0.0137 |
104
+ | No log | 55.0 | 385 | 0.0119 |
105
+ | No log | 56.0 | 392 | 0.0123 |
106
+ | No log | 57.0 | 399 | 0.0122 |
107
+ | No log | 58.0 | 406 | 0.0112 |
108
+ | No log | 59.0 | 413 | 0.0114 |
109
+ | No log | 60.0 | 420 | 0.0112 |
110
+ | No log | 61.0 | 427 | 0.0108 |
111
+ | No log | 62.0 | 434 | 0.0105 |
112
+ | No log | 63.0 | 441 | 0.0120 |
113
+ | No log | 64.0 | 448 | 0.0110 |
114
+ | No log | 65.0 | 455 | 0.0115 |
115
+ | No log | 66.0 | 462 | 0.0102 |
116
+ | No log | 67.0 | 469 | 0.0104 |
117
+ | No log | 68.0 | 476 | 0.0113 |
118
+ | No log | 69.0 | 483 | 0.0098 |
119
+ | No log | 70.0 | 490 | 0.0101 |
120
+ | No log | 71.0 | 497 | 0.0101 |
121
+ | 0.4941 | 72.0 | 504 | 0.0094 |
122
+ | 0.4941 | 73.0 | 511 | 0.0097 |
123
+ | 0.4941 | 74.0 | 518 | 0.0095 |
124
+ | 0.4941 | 75.0 | 525 | 0.0101 |
125
+ | 0.4941 | 76.0 | 532 | 0.0095 |
126
+ | 0.4941 | 77.0 | 539 | 0.0100 |
127
+ | 0.4941 | 78.0 | 546 | 0.0092 |
128
+ | 0.4941 | 79.0 | 553 | 0.0094 |
129
+ | 0.4941 | 80.0 | 560 | 0.0095 |
130
+ | 0.4941 | 81.0 | 567 | 0.0094 |
131
+ | 0.4941 | 82.0 | 574 | 0.0093 |
132
+ | 0.4941 | 83.0 | 581 | 0.0093 |
133
+ | 0.4941 | 84.0 | 588 | 0.0094 |
134
+ | 0.4941 | 85.0 | 595 | 0.0092 |
135
+ | 0.4941 | 86.0 | 602 | 0.0089 |
136
+ | 0.4941 | 87.0 | 609 | 0.0090 |
137
+ | 0.4941 | 88.0 | 616 | 0.0090 |
138
+ | 0.4941 | 89.0 | 623 | 0.0089 |
139
+ | 0.4941 | 90.0 | 630 | 0.0088 |
140
+ | 0.4941 | 91.0 | 637 | 0.0089 |
141
+ | 0.4941 | 92.0 | 644 | 0.0088 |
142
+ | 0.4941 | 93.0 | 651 | 0.0088 |
143
+ | 0.4941 | 94.0 | 658 | 0.0088 |
144
+ | 0.4941 | 95.0 | 665 | 0.0088 |
145
+ | 0.4941 | 96.0 | 672 | 0.0088 |
146
+ | 0.4941 | 97.0 | 679 | 0.0088 |
147
+ | 0.4941 | 98.0 | 686 | 0.0088 |
148
+ | 0.4941 | 99.0 | 693 | 0.0088 |
149
+ | 0.4941 | 100.0 | 700 | 0.0088 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - PEFT 0.9.0
155
+ - Transformers 4.38.1
156
+ - Pytorch 2.1.2
157
+ - Datasets 2.1.0
158
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b70f2d6adfb04d4f5422090cd86d9f4a55002b7615704a8ed626ce8d31fb836
3
  size 6298512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11925018db8b722524a51b039a67ac2da2795280c62fd8ef11333cfabbeaeec
3
  size 6298512
runs/Mar07_10-02-32_cb74e324675c/events.out.tfevents.1709805756.cb74e324675c.34.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45fa82d2905f559c41a21b3660182ff6a217a719a57e4f214eaca0027d9bd535
3
- size 24218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae7bd6cd05481dddf8afbd24c8ec1e9e64a29dacbbdceada33a63f89b359952
3
+ size 32431