Hugging Face's logo

Litzy619
/
GOLM2

Safetensors
Generated from Trainer
Model card Files Community
Litzy619 commited on
Commit
06169bc
•
1 Parent(s): 000361b

End of training

Browse files
Files changed (3) hide show
  1. README.md +34 -34
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
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/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1016
19
 
20
  ## Model description
21
 
@@ -50,39 +50,39 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 1.7996 | 0.09 | 10 | 1.4084 |
54
- | 0.9949 | 0.18 | 20 | 0.5027 |
55
- | 0.3011 | 0.27 | 30 | 0.1578 |
56
- | 0.1527 | 0.36 | 40 | 0.1481 |
57
- | 0.1447 | 0.45 | 50 | 0.1469 |
58
- | 0.1451 | 0.54 | 60 | 0.1464 |
59
- | 0.142 | 0.63 | 70 | 0.1422 |
60
- | 0.1422 | 0.73 | 80 | 0.1372 |
61
- | 0.1304 | 0.82 | 90 | 0.1289 |
62
- | 0.1241 | 0.91 | 100 | 0.1269 |
63
- | 0.1263 | 1.0 | 110 | 0.1302 |
64
- | 0.1163 | 1.09 | 120 | 0.1185 |
65
- | 0.1091 | 1.18 | 130 | 0.1211 |
66
- | 0.1143 | 1.27 | 140 | 0.1143 |
67
- | 0.1131 | 1.36 | 150 | 0.1113 |
68
- | 0.1127 | 1.45 | 160 | 0.1115 |
69
- | 0.1087 | 1.54 | 170 | 0.1073 |
70
- | 0.1086 | 1.63 | 180 | 0.1064 |
71
- | 0.1069 | 1.72 | 190 | 0.1053 |
72
- | 0.1027 | 1.81 | 200 | 0.1047 |
73
- | 0.1037 | 1.9 | 210 | 0.1022 |
74
- | 0.1072 | 1.99 | 220 | 0.1029 |
75
- | 0.0896 | 2.08 | 230 | 0.1056 |
76
- | 0.0918 | 2.18 | 240 | 0.1024 |
77
- | 0.0828 | 2.27 | 250 | 0.1026 |
78
- | 0.0861 | 2.36 | 260 | 0.1022 |
79
- | 0.0853 | 2.45 | 270 | 0.1049 |
80
- | 0.0809 | 2.54 | 280 | 0.1028 |
81
- | 0.0782 | 2.63 | 290 | 0.1021 |
82
- | 0.0814 | 2.72 | 300 | 0.1021 |
83
- | 0.0849 | 2.81 | 310 | 0.1019 |
84
- | 0.0838 | 2.9 | 320 | 0.1016 |
85
- | 0.0864 | 2.99 | 330 | 0.1016 |
86
 
87
 
88
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1067
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.7996 | 0.09 | 10 | 1.4594 |
54
+ | 0.9949 | 0.18 | 20 | 0.5804 |
55
+ | 0.3011 | 0.27 | 30 | 0.1728 |
56
+ | 0.1527 | 0.36 | 40 | 0.1498 |
57
+ | 0.1447 | 0.45 | 50 | 0.1491 |
58
+ | 0.1451 | 0.54 | 60 | 0.1476 |
59
+ | 0.142 | 0.63 | 70 | 0.1447 |
60
+ | 0.1422 | 0.73 | 80 | 0.1415 |
61
+ | 0.1304 | 0.82 | 90 | 0.1346 |
62
+ | 0.1241 | 0.91 | 100 | 0.1294 |
63
+ | 0.1263 | 1.0 | 110 | 0.1294 |
64
+ | 0.1163 | 1.09 | 120 | 0.1235 |
65
+ | 0.1091 | 1.18 | 130 | 0.1217 |
66
+ | 0.1143 | 1.27 | 140 | 0.1201 |
67
+ | 0.1131 | 1.36 | 150 | 0.1149 |
68
+ | 0.1127 | 1.45 | 160 | 0.1158 |
69
+ | 0.1087 | 1.54 | 170 | 0.1139 |
70
+ | 0.1086 | 1.63 | 180 | 0.1125 |
71
+ | 0.1069 | 1.72 | 190 | 0.1120 |
72
+ | 0.1027 | 1.81 | 200 | 0.1119 |
73
+ | 0.1037 | 1.9 | 210 | 0.1109 |
74
+ | 0.1072 | 1.99 | 220 | 0.1116 |
75
+ | 0.0896 | 2.08 | 230 | 0.1104 |
76
+ | 0.0918 | 2.18 | 240 | 0.1096 |
77
+ | 0.0828 | 2.27 | 250 | 0.1071 |
78
+ | 0.0861 | 2.36 | 260 | 0.1080 |
79
+ | 0.0853 | 2.45 | 270 | 0.1093 |
80
+ | 0.0809 | 2.54 | 280 | 0.1084 |
81
+ | 0.0782 | 2.63 | 290 | 0.1076 |
82
+ | 0.0814 | 2.72 | 300 | 0.1072 |
83
+ | 0.0849 | 2.81 | 310 | 0.1074 |
84
+ | 0.0838 | 2.9 | 320 | 0.1070 |
85
+ | 0.0864 | 2.99 | 330 | 0.1067 |
86
 
87
 
88
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d427504e03533c554e11cddee265d5d83343d79b0017f2a5b16cad4d18273467
3
  size 10087984512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73bbed85ec624fa169b5d998a3a357075a76f8e168d0add6331308ad139cae26
3
  size 10087984512
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1aa7b0a11e60f70c95838af493432ebe0cedbf9a8ac131d2210566c90791de1
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef965a6558899d07ed069ce843b070e7830515d5f3d416b26b2b8d7cf16ec2de
3
  size 5112