Hugging Face's logo

farid1088
/
GQA_BERT_legal_SQuAD_complete_augmented_100

Question Answering
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
farid1088 commited on
Commit
efd885c
•
1 Parent(s): f888af9

Model save

Browse files
Files changed (5) hide show
  1. README.md +103 -103
  2. emissions.csv +1 -1
  3. model.safetensors +1 -1
  4. runs/Mar07_20-21-37_hcdsgpu1/events.out.tfevents.1709842902.hcdsgpu1.1566498.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 1.2100
17
 
18
  ## Model description
19
 
@@ -33,8 +33,8 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 2e-05
36
- - train_batch_size: 128
37
- - eval_batch_size: 32
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
@@ -44,106 +44,106 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | No log | 1.0 | 4 | 4.8682 |
48
- | No log | 2.0 | 8 | 4.2730 |
49
- | No log | 3.0 | 12 | 3.6398 |
50
- | No log | 4.0 | 16 | 3.1455 |
51
- | No log | 5.0 | 20 | 2.7297 |
52
- | No log | 6.0 | 24 | 2.3844 |
53
- | No log | 7.0 | 28 | 2.0725 |
54
- | No log | 8.0 | 32 | 1.8236 |
55
- | No log | 9.0 | 36 | 1.6463 |
56
- | No log | 10.0 | 40 | 1.4038 |
57
- | No log | 11.0 | 44 | 1.3019 |
58
- | No log | 12.0 | 48 | 1.2451 |
59
- | No log | 13.0 | 52 | 1.1405 |
60
- | No log | 14.0 | 56 | 1.0619 |
61
- | No log | 15.0 | 60 | 1.0517 |
62
- | No log | 16.0 | 64 | 1.0360 |
63
- | No log | 17.0 | 68 | 1.0107 |
64
- | No log | 18.0 | 72 | 0.9929 |
65
- | No log | 19.0 | 76 | 1.0244 |
66
- | No log | 20.0 | 80 | 1.0331 |
67
- | No log | 21.0 | 84 | 1.0257 |
68
- | No log | 22.0 | 88 | 1.0301 |
69
- | No log | 23.0 | 92 | 1.0251 |
70
- | No log | 24.0 | 96 | 1.0220 |
71
- | No log | 25.0 | 100 | 1.0126 |
72
- | No log | 26.0 | 104 | 1.0261 |
73
- | No log | 27.0 | 108 | 1.0237 |
74
- | No log | 28.0 | 112 | 1.0297 |
75
- | No log | 29.0 | 116 | 1.0327 |
76
- | No log | 30.0 | 120 | 1.0501 |
77
- | No log | 31.0 | 124 | 1.0614 |
78
- | No log | 32.0 | 128 | 1.0668 |
79
- | No log | 33.0 | 132 | 1.0503 |
80
- | No log | 34.0 | 136 | 1.0463 |
81
- | No log | 35.0 | 140 | 1.0490 |
82
- | No log | 36.0 | 144 | 1.0738 |
83
- | No log | 37.0 | 148 | 1.0968 |
84
- | No log | 38.0 | 152 | 1.1256 |
85
- | No log | 39.0 | 156 | 1.1218 |
86
- | No log | 40.0 | 160 | 1.1161 |
87
- | No log | 41.0 | 164 | 1.1145 |
88
- | No log | 42.0 | 168 | 1.1072 |
89
- | No log | 43.0 | 172 | 1.0991 |
90
- | No log | 44.0 | 176 | 1.1346 |
91
- | No log | 45.0 | 180 | 1.1308 |
92
- | No log | 46.0 | 184 | 1.1307 |
93
- | No log | 47.0 | 188 | 1.1457 |
94
- | No log | 48.0 | 192 | 1.1671 |
95
- | No log | 49.0 | 196 | 1.1499 |
96
- | No log | 50.0 | 200 | 1.1410 |
97
- | No log | 51.0 | 204 | 1.1357 |
98
- | No log | 52.0 | 208 | 1.1664 |
99
- | No log | 53.0 | 212 | 1.1656 |
100
- | No log | 54.0 | 216 | 1.1656 |
101
- | No log | 55.0 | 220 | 1.1729 |
102
- | No log | 56.0 | 224 | 1.1928 |
103
- | No log | 57.0 | 228 | 1.1795 |
104
- | No log | 58.0 | 232 | 1.1924 |
105
- | No log | 59.0 | 236 | 1.1687 |
106
- | No log | 60.0 | 240 | 1.1868 |
107
- | No log | 61.0 | 244 | 1.1977 |
108
- | No log | 62.0 | 248 | 1.1880 |
109
- | No log | 63.0 | 252 | 1.1950 |
110
- | No log | 64.0 | 256 | 1.2011 |
111
- | No log | 65.0 | 260 | 1.1962 |
112
- | No log | 66.0 | 264 | 1.1938 |
113
- | No log | 67.0 | 268 | 1.2008 |
114
- | No log | 68.0 | 272 | 1.2157 |
115
- | No log | 69.0 | 276 | 1.2155 |
116
- | No log | 70.0 | 280 | 1.2192 |
117
- | No log | 71.0 | 284 | 1.2031 |
118
- | No log | 72.0 | 288 | 1.2139 |
119
- | No log | 73.0 | 292 | 1.2196 |
120
- | No log | 74.0 | 296 | 1.2374 |
121
- | No log | 75.0 | 300 | 1.2325 |
122
- | No log | 76.0 | 304 | 1.2169 |
123
- | No log | 77.0 | 308 | 1.2152 |
124
- | No log | 78.0 | 312 | 1.2238 |
125
- | No log | 79.0 | 316 | 1.2258 |
126
- | No log | 80.0 | 320 | 1.2208 |
127
- | No log | 81.0 | 324 | 1.2250 |
128
- | No log | 82.0 | 328 | 1.2251 |
129
- | No log | 83.0 | 332 | 1.2254 |
130
- | No log | 84.0 | 336 | 1.2104 |
131
- | No log | 85.0 | 340 | 1.2003 |
132
- | No log | 86.0 | 344 | 1.2023 |
133
- | No log | 87.0 | 348 | 1.2176 |
134
- | No log | 88.0 | 352 | 1.2245 |
135
- | No log | 89.0 | 356 | 1.2248 |
136
- | No log | 90.0 | 360 | 1.2203 |
137
- | No log | 91.0 | 364 | 1.2138 |
138
- | No log | 92.0 | 368 | 1.2116 |
139
- | No log | 93.0 | 372 | 1.2097 |
140
- | No log | 94.0 | 376 | 1.2159 |
141
- | No log | 95.0 | 380 | 1.2224 |
142
- | No log | 96.0 | 384 | 1.2220 |
143
- | No log | 97.0 | 388 | 1.2182 |
144
- | No log | 98.0 | 392 | 1.2128 |
145
- | No log | 99.0 | 396 | 1.2107 |
146
- | No log | 100.0 | 400 | 1.2100 |
147
 
148
 
149
  ### Framework versions
 
13
 
14
  This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 1.0964
17
 
18
  ## Model description
19
 
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 2e-05
36
+ - train_batch_size: 160
37
+ - eval_batch_size: 40
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | No log | 1.0 | 3 | 5.1190 |
48
+ | No log | 2.0 | 6 | 4.5892 |
49
+ | No log | 3.0 | 9 | 3.9684 |
50
+ | No log | 4.0 | 12 | 3.6427 |
51
+ | No log | 5.0 | 15 | 3.2081 |
52
+ | No log | 6.0 | 18 | 2.8413 |
53
+ | No log | 7.0 | 21 | 2.5487 |
54
+ | No log | 8.0 | 24 | 2.2830 |
55
+ | No log | 9.0 | 27 | 2.0807 |
56
+ | No log | 10.0 | 30 | 1.8644 |
57
+ | No log | 11.0 | 33 | 1.7166 |
58
+ | No log | 12.0 | 36 | 1.5672 |
59
+ | No log | 13.0 | 39 | 1.3949 |
60
+ | No log | 14.0 | 42 | 1.3109 |
61
+ | No log | 15.0 | 45 | 1.2622 |
62
+ | No log | 16.0 | 48 | 1.1875 |
63
+ | No log | 17.0 | 51 | 1.1579 |
64
+ | No log | 18.0 | 54 | 1.1329 |
65
+ | No log | 19.0 | 57 | 1.1090 |
66
+ | No log | 20.0 | 60 | 1.0811 |
67
+ | No log | 21.0 | 63 | 1.0542 |
68
+ | No log | 22.0 | 66 | 1.0481 |
69
+ | No log | 23.0 | 69 | 1.0355 |
70
+ | No log | 24.0 | 72 | 1.0304 |
71
+ | No log | 25.0 | 75 | 1.0276 |
72
+ | No log | 26.0 | 78 | 1.0277 |
73
+ | No log | 27.0 | 81 | 1.0329 |
74
+ | No log | 28.0 | 84 | 1.0356 |
75
+ | No log | 29.0 | 87 | 1.0410 |
76
+ | No log | 30.0 | 90 | 1.0267 |
77
+ | No log | 31.0 | 93 | 1.0280 |
78
+ | No log | 32.0 | 96 | 1.0453 |
79
+ | No log | 33.0 | 99 | 1.0520 |
80
+ | No log | 34.0 | 102 | 1.0430 |
81
+ | No log | 35.0 | 105 | 1.0393 |
82
+ | No log | 36.0 | 108 | 1.0370 |
83
+ | No log | 37.0 | 111 | 1.0284 |
84
+ | No log | 38.0 | 114 | 1.0313 |
85
+ | No log | 39.0 | 117 | 1.0376 |
86
+ | No log | 40.0 | 120 | 1.0312 |
87
+ | No log | 41.0 | 123 | 1.0218 |
88
+ | No log | 42.0 | 126 | 1.0348 |
89
+ | No log | 43.0 | 129 | 1.0426 |
90
+ | No log | 44.0 | 132 | 1.0411 |
91
+ | No log | 45.0 | 135 | 1.0463 |
92
+ | No log | 46.0 | 138 | 1.0661 |
93
+ | No log | 47.0 | 141 | 1.0733 |
94
+ | No log | 48.0 | 144 | 1.0609 |
95
+ | No log | 49.0 | 147 | 1.0578 |
96
+ | No log | 50.0 | 150 | 1.0639 |
97
+ | No log | 51.0 | 153 | 1.0490 |
98
+ | No log | 52.0 | 156 | 1.0507 |
99
+ | No log | 53.0 | 159 | 1.0460 |
100
+ | No log | 54.0 | 162 | 1.0534 |
101
+ | No log | 55.0 | 165 | 1.0530 |
102
+ | No log | 56.0 | 168 | 1.0521 |
103
+ | No log | 57.0 | 171 | 1.0470 |
104
+ | No log | 58.0 | 174 | 1.0462 |
105
+ | No log | 59.0 | 177 | 1.0547 |
106
+ | No log | 60.0 | 180 | 1.0628 |
107
+ | No log | 61.0 | 183 | 1.0550 |
108
+ | No log | 62.0 | 186 | 1.0474 |
109
+ | No log | 63.0 | 189 | 1.0536 |
110
+ | No log | 64.0 | 192 | 1.0711 |
111
+ | No log | 65.0 | 195 | 1.0832 |
112
+ | No log | 66.0 | 198 | 1.0855 |
113
+ | No log | 67.0 | 201 | 1.0901 |
114
+ | No log | 68.0 | 204 | 1.0912 |
115
+ | No log | 69.0 | 207 | 1.0888 |
116
+ | No log | 70.0 | 210 | 1.0882 |
117
+ | No log | 71.0 | 213 | 1.0985 |
118
+ | No log | 72.0 | 216 | 1.1056 |
119
+ | No log | 73.0 | 219 | 1.0876 |
120
+ | No log | 74.0 | 222 | 1.0781 |
121
+ | No log | 75.0 | 225 | 1.0894 |
122
+ | No log | 76.0 | 228 | 1.0906 |
123
+ | No log | 77.0 | 231 | 1.0848 |
124
+ | No log | 78.0 | 234 | 1.0851 |
125
+ | No log | 79.0 | 237 | 1.0949 |
126
+ | No log | 80.0 | 240 | 1.0982 |
127
+ | No log | 81.0 | 243 | 1.0932 |
128
+ | No log | 82.0 | 246 | 1.0825 |
129
+ | No log | 83.0 | 249 | 1.0791 |
130
+ | No log | 84.0 | 252 | 1.0821 |
131
+ | No log | 85.0 | 255 | 1.0819 |
132
+ | No log | 86.0 | 258 | 1.0808 |
133
+ | No log | 87.0 | 261 | 1.0794 |
134
+ | No log | 88.0 | 264 | 1.0815 |
135
+ | No log | 89.0 | 267 | 1.0859 |
136
+ | No log | 90.0 | 270 | 1.0883 |
137
+ | No log | 91.0 | 273 | 1.0890 |
138
+ | No log | 92.0 | 276 | 1.0935 |
139
+ | No log | 93.0 | 279 | 1.0982 |
140
+ | No log | 94.0 | 282 | 1.1007 |
141
+ | No log | 95.0 | 285 | 1.0994 |
142
+ | No log | 96.0 | 288 | 1.0997 |
143
+ | No log | 97.0 | 291 | 1.0998 |
144
+ | No log | 98.0 | 294 | 1.0978 |
145
+ | No log | 99.0 | 297 | 1.0970 |
146
+ | No log | 100.0 | 300 | 1.0964 |
147
 
148
 
149
  ### Framework versions
emissions.csv CHANGED
@@ -1,2 +1,2 @@
1
  timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
- 2024-03-06T13:39:15,codecarbon,e7ce0efc-76fc-4437-ac5e-e6a73e29f25b,366.31281542778015,0.054828438666223354,0.00014967655063390206,112.5,1072.152,377.88994789123535,0.011447098836302757,0.10490885600820554,0.03838807004344049,0.1547440248879488,Germany,DEU,free and hanseatic city of hamburg,,,Linux-6.5.0-21-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7065277099609,machine,N,1.0
 
1
  timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
+ 2024-03-07T20:29:36,codecarbon,c09023d6-60da-4be1-8653-2cd45c550949,473.682341337204,0.06677983072751029,0.00014098019896412225,112.5,759.169,377.8920922279358,0.01480230539292097,0.12408065898181493,0.049591849781825355,0.1884748141565612,Germany,DEU,free and hanseatic city of hamburg,,,Linux-5.15.0-97-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,5,4 x NVIDIA A401 x NVIDIA A100 80GB PCIe,9.9683,53.5649,1007.7122459411621,machine,N,1.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fc12ff35826a4f286663fc0f6f9522b0c98b518cdff57e00cfe969020845176
3
  size 433992496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad6d7ab0de07a155602d0ce58127cc95104615463958b5623eb1ba343ff6f1b
3
  size 433992496
runs/Mar07_20-21-37_hcdsgpu1/events.out.tfevents.1709842902.hcdsgpu1.1566498.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da86e2ef8f94db8e60a4dd53368b4fa390ed39ed6826d0338f4e21f6f0b3e126
3
+ size 31888
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bbd2cd65b5982e96be4b4096be78896cc37888fa1e837b1ef585853f5de81da
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0621a20d269a552d7bae8ea8ad5ae3f97a4688976cb644c440376241df7a6e58
3
  size 4920