cmcmaster commited on
Commit
64da2d8
1 Parent(s): a2c0609

End of training

Browse files
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1133
19
 
20
  ## Model description
21
 
@@ -47,49 +47,71 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 1.6316 | 0.46 | 50 | 0.6287 |
51
- | 0.6403 | 0.93 | 100 | 0.3378 |
52
- | 0.4213 | 1.39 | 150 | 0.2460 |
53
- | 0.3452 | 1.85 | 200 | 0.2184 |
54
- | 0.306 | 2.31 | 250 | 0.1903 |
55
- | 0.2634 | 2.78 | 300 | 0.1807 |
56
- | 0.2423 | 3.24 | 350 | 0.1630 |
57
- | 0.2224 | 3.7 | 400 | 0.1599 |
58
- | 0.2107 | 4.17 | 450 | 0.1522 |
59
- | 0.1922 | 4.63 | 500 | 0.1515 |
60
- | 0.1887 | 5.09 | 550 | 0.1394 |
61
- | 0.1821 | 5.56 | 600 | 0.1414 |
62
- | 0.1705 | 6.02 | 650 | 0.1378 |
63
- | 0.1602 | 6.48 | 700 | 0.1330 |
64
- | 0.1579 | 6.94 | 750 | 0.1300 |
65
- | 0.1497 | 7.41 | 800 | 0.1282 |
66
- | 0.1534 | 7.87 | 850 | 0.1277 |
67
- | 0.147 | 8.33 | 900 | 0.1274 |
68
- | 0.1395 | 8.8 | 950 | 0.1204 |
69
- | 0.1361 | 9.26 | 1000 | 0.1235 |
70
- | 0.1353 | 9.72 | 1050 | 0.1210 |
71
- | 0.1303 | 10.19 | 1100 | 0.1220 |
72
- | 0.132 | 10.65 | 1150 | 0.1232 |
73
- | 0.1262 | 11.11 | 1200 | 0.1193 |
74
- | 0.1228 | 11.57 | 1250 | 0.1229 |
75
- | 0.1261 | 12.04 | 1300 | 0.1215 |
76
- | 0.1204 | 12.5 | 1350 | 0.1163 |
77
- | 0.12 | 12.96 | 1400 | 0.1189 |
78
- | 0.11 | 13.43 | 1450 | 0.1173 |
79
- | 0.1183 | 13.89 | 1500 | 0.1149 |
80
- | 0.108 | 14.35 | 1550 | 0.1178 |
81
- | 0.1122 | 14.81 | 1600 | 0.1150 |
82
- | 0.1126 | 15.28 | 1650 | 0.1157 |
83
- | 0.112 | 15.74 | 1700 | 0.1152 |
84
- | 0.1046 | 16.2 | 1750 | 0.1156 |
85
- | 0.1057 | 16.67 | 1800 | 0.1138 |
86
- | 0.1067 | 17.13 | 1850 | 0.1129 |
87
- | 0.1078 | 17.59 | 1900 | 0.1140 |
88
- | 0.1043 | 18.06 | 1950 | 0.1135 |
89
- | 0.1033 | 18.52 | 2000 | 0.1138 |
90
- | 0.1017 | 18.98 | 2050 | 0.1140 |
91
- | 0.102 | 19.44 | 2100 | 0.1125 |
92
- | 0.1012 | 19.91 | 2150 | 0.1133 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93
 
94
 
95
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1027
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 1.7961 | 0.3 | 50 | 0.7538 |
51
+ | 0.7207 | 0.61 | 100 | 0.3876 |
52
+ | 0.4596 | 0.91 | 150 | 0.2763 |
53
+ | 0.3536 | 1.22 | 200 | 0.2265 |
54
+ | 0.3089 | 1.52 | 250 | 0.1937 |
55
+ | 0.2736 | 1.83 | 300 | 0.1842 |
56
+ | 0.2415 | 2.13 | 350 | 0.1713 |
57
+ | 0.2309 | 2.44 | 400 | 0.1601 |
58
+ | 0.2011 | 2.74 | 450 | 0.1533 |
59
+ | 0.198 | 3.05 | 500 | 0.1464 |
60
+ | 0.1816 | 3.35 | 550 | 0.1418 |
61
+ | 0.1887 | 3.66 | 600 | 0.1354 |
62
+ | 0.1717 | 3.96 | 650 | 0.1295 |
63
+ | 0.1589 | 4.27 | 700 | 0.1320 |
64
+ | 0.1606 | 4.57 | 750 | 0.1230 |
65
+ | 0.1545 | 4.88 | 800 | 0.1255 |
66
+ | 0.1502 | 5.18 | 850 | 0.1247 |
67
+ | 0.1438 | 5.49 | 900 | 0.1251 |
68
+ | 0.1395 | 5.79 | 950 | 0.1222 |
69
+ | 0.1414 | 6.1 | 1000 | 0.1173 |
70
+ | 0.133 | 6.4 | 1050 | 0.1149 |
71
+ | 0.1338 | 6.71 | 1100 | 0.1124 |
72
+ | 0.1361 | 7.01 | 1150 | 0.1148 |
73
+ | 0.1269 | 7.32 | 1200 | 0.1137 |
74
+ | 0.123 | 7.62 | 1250 | 0.1145 |
75
+ | 0.1203 | 7.93 | 1300 | 0.1129 |
76
+ | 0.1194 | 8.23 | 1350 | 0.1081 |
77
+ | 0.1177 | 8.54 | 1400 | 0.1099 |
78
+ | 0.1173 | 8.84 | 1450 | 0.1109 |
79
+ | 0.113 | 9.15 | 1500 | 0.1107 |
80
+ | 0.1122 | 9.45 | 1550 | 0.1068 |
81
+ | 0.11 | 9.76 | 1600 | 0.1072 |
82
+ | 0.1078 | 10.06 | 1650 | 0.1086 |
83
+ | 0.101 | 10.37 | 1700 | 0.1088 |
84
+ | 0.1106 | 10.67 | 1750 | 0.1079 |
85
+ | 0.1094 | 10.98 | 1800 | 0.1109 |
86
+ | 0.1072 | 11.28 | 1850 | 0.1054 |
87
+ | 0.103 | 11.59 | 1900 | 0.1062 |
88
+ | 0.1009 | 11.89 | 1950 | 0.1051 |
89
+ | 0.1005 | 12.2 | 2000 | 0.1049 |
90
+ | 0.0985 | 12.5 | 2050 | 0.1059 |
91
+ | 0.0983 | 12.8 | 2100 | 0.1063 |
92
+ | 0.0953 | 13.11 | 2150 | 0.1062 |
93
+ | 0.0935 | 13.41 | 2200 | 0.1044 |
94
+ | 0.1003 | 13.72 | 2250 | 0.1034 |
95
+ | 0.0935 | 14.02 | 2300 | 0.1049 |
96
+ | 0.0935 | 14.33 | 2350 | 0.1038 |
97
+ | 0.096 | 14.63 | 2400 | 0.1020 |
98
+ | 0.0894 | 14.94 | 2450 | 0.1048 |
99
+ | 0.0931 | 15.24 | 2500 | 0.1034 |
100
+ | 0.0888 | 15.55 | 2550 | 0.1030 |
101
+ | 0.0904 | 15.85 | 2600 | 0.1038 |
102
+ | 0.0885 | 16.16 | 2650 | 0.1046 |
103
+ | 0.088 | 16.46 | 2700 | 0.1041 |
104
+ | 0.0925 | 16.77 | 2750 | 0.1027 |
105
+ | 0.0835 | 17.07 | 2800 | 0.1034 |
106
+ | 0.089 | 17.38 | 2850 | 0.1036 |
107
+ | 0.0844 | 17.68 | 2900 | 0.1043 |
108
+ | 0.0866 | 17.99 | 2950 | 0.1031 |
109
+ | 0.0835 | 18.29 | 3000 | 0.1030 |
110
+ | 0.0826 | 18.6 | 3050 | 0.1028 |
111
+ | 0.0874 | 18.9 | 3100 | 0.1018 |
112
+ | 0.0846 | 19.21 | 3150 | 0.1030 |
113
+ | 0.0852 | 19.51 | 3200 | 0.1026 |
114
+ | 0.0835 | 19.82 | 3250 | 0.1027 |
115
 
116
 
117
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:277450e6e2c32486280a66c0b9ab63250650b85cca9d9746a145c0ecb4d001a0
3
  size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6fa312c0462dad2cef000dae1feadd95c8999644309948dfd9f2c794e141225
3
  size 307867048
runs/Nov10_17-33-18_christopher-System-Product-Name/events.out.tfevents.1699597998.christopher-System-Product-Name.30388.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b37193c65be21980ec38823076173b098f099925b49453e710323736c804dff
3
+ size 33464
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cce8e4d2c3994de90beaf7187c95c1c845d1b3b40d1f2bf070c0183d2da8ae7
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b905a3df27a9d55cacafa59f3b6d59fcbcdb4816ce375f5a526c4e0a1f0cd09
3
  size 4792