Hugging Face's logo

haurajahra
/
QA_using_DistilBERT_LORA_qv

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
haurajahra commited on
Commit
b981bf9
·
1 Parent(s): 0644136

Model save

Browse files
Files changed (3) hide show
  1. README.md +192 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Nov28_01-56-56_c481cd1ed10b/events.out.tfevents.1701136658.c481cd1ed10b.891.0 +2 -2
README.md ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: QA_using_DistilBERT_LORA_qv
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # QA_using_DistilBERT_LORA_qv
15
+
16
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.7782
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 64
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 2
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 4.7211 | 0.01 | 500 | 4.4152 |
50
+ | 4.3014 | 0.03 | 1000 | 4.3057 |
51
+ | 4.2235 | 0.04 | 1500 | 4.2254 |
52
+ | 4.1424 | 0.06 | 2000 | 4.1592 |
53
+ | 4.1312 | 0.07 | 2500 | 4.1091 |
54
+ | 4.033 | 0.09 | 3000 | 3.8720 |
55
+ | 3.739 | 0.1 | 3500 | 3.7028 |
56
+ | 3.6547 | 0.12 | 4000 | 3.5784 |
57
+ | 3.4915 | 0.13 | 4500 | 3.4967 |
58
+ | 3.5266 | 0.15 | 5000 | 3.4501 |
59
+ | 3.4602 | 0.16 | 5500 | 3.5048 |
60
+ | 3.4749 | 0.18 | 6000 | 3.3635 |
61
+ | 3.4088 | 0.19 | 6500 | 3.3465 |
62
+ | 3.3869 | 0.21 | 7000 | 3.3438 |
63
+ | 3.3835 | 0.22 | 7500 | 3.2838 |
64
+ | 3.2902 | 0.23 | 8000 | 3.3156 |
65
+ | 3.2747 | 0.25 | 8500 | 3.2770 |
66
+ | 3.2968 | 0.26 | 9000 | 3.2578 |
67
+ | 3.2305 | 0.28 | 9500 | 3.2645 |
68
+ | 3.2288 | 0.29 | 10000 | 3.1857 |
69
+ | 3.2717 | 0.31 | 10500 | 3.2326 |
70
+ | 3.1697 | 0.32 | 11000 | 3.2098 |
71
+ | 3.1786 | 0.34 | 11500 | 3.2656 |
72
+ | 3.2063 | 0.35 | 12000 | 3.1725 |
73
+ | 3.186 | 0.37 | 12500 | 3.1901 |
74
+ | 3.1389 | 0.38 | 13000 | 3.1706 |
75
+ | 3.234 | 0.4 | 13500 | 3.1553 |
76
+ | 3.1207 | 0.41 | 14000 | 3.1764 |
77
+ | 3.1764 | 0.42 | 14500 | 3.1441 |
78
+ | 3.1458 | 0.44 | 15000 | 3.1459 |
79
+ | 3.0631 | 0.45 | 15500 | 3.1461 |
80
+ | 3.1193 | 0.47 | 16000 | 3.1306 |
81
+ | 3.0437 | 0.48 | 16500 | 3.1775 |
82
+ | 3.1309 | 0.5 | 17000 | 3.0853 |
83
+ | 3.0448 | 0.51 | 17500 | 3.1136 |
84
+ | 3.0273 | 0.53 | 18000 | 3.0640 |
85
+ | 3.0826 | 0.54 | 18500 | 3.0786 |
86
+ | 3.0044 | 0.56 | 19000 | 3.0843 |
87
+ | 3.0672 | 0.57 | 19500 | 3.0516 |
88
+ | 3.0447 | 0.59 | 20000 | 3.0581 |
89
+ | 3.0168 | 0.6 | 20500 | 3.0369 |
90
+ | 2.9619 | 0.62 | 21000 | 3.0725 |
91
+ | 3.0981 | 0.63 | 21500 | 3.0389 |
92
+ | 3.0247 | 0.64 | 22000 | 3.0339 |
93
+ | 3.041 | 0.66 | 22500 | 3.0465 |
94
+ | 3.0286 | 0.67 | 23000 | 3.0806 |
95
+ | 3.0136 | 0.69 | 23500 | 3.0149 |
96
+ | 2.9814 | 0.7 | 24000 | 3.0128 |
97
+ | 3.0359 | 0.72 | 24500 | 3.0086 |
98
+ | 2.9939 | 0.73 | 25000 | 3.0216 |
99
+ | 2.996 | 0.75 | 25500 | 3.1415 |
100
+ | 2.9554 | 0.76 | 26000 | 3.0490 |
101
+ | 2.9773 | 0.78 | 26500 | 3.0457 |
102
+ | 2.9625 | 0.79 | 27000 | 2.9663 |
103
+ | 2.9184 | 0.81 | 27500 | 2.9981 |
104
+ | 2.9735 | 0.82 | 28000 | 3.0404 |
105
+ | 2.9567 | 0.84 | 28500 | 2.9621 |
106
+ | 2.9706 | 0.85 | 29000 | 3.0024 |
107
+ | 2.9436 | 0.86 | 29500 | 2.9535 |
108
+ | 2.9069 | 0.88 | 30000 | 2.9993 |
109
+ | 2.9652 | 0.89 | 30500 | 2.9393 |
110
+ | 2.9426 | 0.91 | 31000 | 2.9693 |
111
+ | 2.8936 | 0.92 | 31500 | 2.9111 |
112
+ | 2.9245 | 0.94 | 32000 | 2.9678 |
113
+ | 2.9054 | 0.95 | 32500 | 2.9263 |
114
+ | 2.8426 | 0.97 | 33000 | 2.9429 |
115
+ | 2.8782 | 0.98 | 33500 | 2.9232 |
116
+ | 2.8963 | 1.0 | 34000 | 2.9545 |
117
+ | 2.8757 | 1.01 | 34500 | 2.9181 |
118
+ | 2.853 | 1.03 | 35000 | 2.8925 |
119
+ | 2.8758 | 1.04 | 35500 | 2.9464 |
120
+ | 2.9179 | 1.06 | 36000 | 2.9076 |
121
+ | 2.8924 | 1.07 | 36500 | 2.8874 |
122
+ | 2.9488 | 1.08 | 37000 | 2.9284 |
123
+ | 2.8746 | 1.1 | 37500 | 2.9012 |
124
+ | 2.8026 | 1.11 | 38000 | 2.8679 |
125
+ | 2.8177 | 1.13 | 38500 | 2.9000 |
126
+ | 2.8113 | 1.14 | 39000 | 2.9069 |
127
+ | 2.8047 | 1.16 | 39500 | 2.8755 |
128
+ | 2.8437 | 1.17 | 40000 | 2.9043 |
129
+ | 2.8093 | 1.19 | 40500 | 2.8915 |
130
+ | 2.7881 | 1.2 | 41000 | 2.8665 |
131
+ | 2.8251 | 1.22 | 41500 | 2.8516 |
132
+ | 2.8356 | 1.23 | 42000 | 2.8927 |
133
+ | 2.7805 | 1.25 | 42500 | 2.8759 |
134
+ | 2.8944 | 1.26 | 43000 | 2.8491 |
135
+ | 2.88 | 1.27 | 43500 | 2.8458 |
136
+ | 2.8109 | 1.29 | 44000 | 2.8613 |
137
+ | 2.7595 | 1.3 | 44500 | 2.8734 |
138
+ | 2.8038 | 1.32 | 45000 | 2.8344 |
139
+ | 2.8113 | 1.33 | 45500 | 2.8448 |
140
+ | 2.8396 | 1.35 | 46000 | 2.8216 |
141
+ | 2.833 | 1.36 | 46500 | 2.8445 |
142
+ | 2.7711 | 1.38 | 47000 | 2.8499 |
143
+ | 2.7933 | 1.39 | 47500 | 2.8649 |
144
+ | 2.8079 | 1.41 | 48000 | 2.8390 |
145
+ | 2.781 | 1.42 | 48500 | 2.7999 |
146
+ | 2.8195 | 1.44 | 49000 | 2.8320 |
147
+ | 2.7553 | 1.45 | 49500 | 2.8500 |
148
+ | 2.7769 | 1.47 | 50000 | 2.8364 |
149
+ | 2.6745 | 1.48 | 50500 | 2.8392 |
150
+ | 2.7891 | 1.49 | 51000 | 2.8166 |
151
+ | 2.7691 | 1.51 | 51500 | 2.8195 |
152
+ | 2.7744 | 1.52 | 52000 | 2.8505 |
153
+ | 2.739 | 1.54 | 52500 | 2.8055 |
154
+ | 2.7843 | 1.55 | 53000 | 2.8633 |
155
+ | 2.7072 | 1.57 | 53500 | 2.8214 |
156
+ | 2.7658 | 1.58 | 54000 | 2.8178 |
157
+ | 2.7271 | 1.6 | 54500 | 2.8075 |
158
+ | 2.8387 | 1.61 | 55000 | 2.8025 |
159
+ | 2.7425 | 1.63 | 55500 | 2.8061 |
160
+ | 2.7464 | 1.64 | 56000 | 2.7882 |
161
+ | 2.7442 | 1.66 | 56500 | 2.8161 |
162
+ | 2.7398 | 1.67 | 57000 | 2.8091 |
163
+ | 2.7081 | 1.69 | 57500 | 2.8166 |
164
+ | 2.759 | 1.7 | 58000 | 2.8014 |
165
+ | 2.6873 | 1.71 | 58500 | 2.7949 |
166
+ | 2.8057 | 1.73 | 59000 | 2.8044 |
167
+ | 2.8156 | 1.74 | 59500 | 2.7860 |
168
+ | 2.6884 | 1.76 | 60000 | 2.7931 |
169
+ | 2.7627 | 1.77 | 60500 | 2.7931 |
170
+ | 2.6991 | 1.79 | 61000 | 2.7895 |
171
+ | 2.8059 | 1.8 | 61500 | 2.7981 |
172
+ | 2.7018 | 1.82 | 62000 | 2.7972 |
173
+ | 2.7027 | 1.83 | 62500 | 2.7956 |
174
+ | 2.7658 | 1.85 | 63000 | 2.7949 |
175
+ | 2.7735 | 1.86 | 63500 | 2.7803 |
176
+ | 2.6972 | 1.88 | 64000 | 2.7894 |
177
+ | 2.6512 | 1.89 | 64500 | 2.8087 |
178
+ | 2.6856 | 1.9 | 65000 | 2.7795 |
179
+ | 2.7292 | 1.92 | 65500 | 2.7772 |
180
+ | 2.7744 | 1.93 | 66000 | 2.7821 |
181
+ | 2.8022 | 1.95 | 66500 | 2.7858 |
182
+ | 2.7054 | 1.96 | 67000 | 2.7816 |
183
+ | 2.7255 | 1.98 | 67500 | 2.7740 |
184
+ | 2.6243 | 1.99 | 68000 | 2.7782 |
185
+
186
+
187
+ ### Framework versions
188
+
189
+ - Transformers 4.35.2
190
+ - Pytorch 2.1.0+cu118
191
+ - Datasets 2.15.0
192
+ - Tokenizers 0.15.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e377c579179de2600aa5efa38814a426bc13dde07d18bd74e2a0a5641423309a
3
  size 1189496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c561e6807dd849d6aa43904415d6c3055136cf7a3b1f0b69d2cbad886729275b
3
  size 1189496
runs/Nov28_01-56-56_c481cd1ed10b/events.out.tfevents.1701136658.c481cd1ed10b.891.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8259d2fefeab3df2f9de6b707ce54984f39d042e1d651992bb6fd56614080db9
3
- size 42168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788f2b76a00f39c9f3fe79a343f9ef806416ff11eb01a79f2c00e92a19100779
3
+ size 42528