Hugging Face's logo

jkazdan
/
gemma-2-2b_hs2_iter1_sftsd1

Safetensors
gemma2
trl
sft
Generated from Trainer
Model card Files Community
jkazdan commited on
Commit
7c2d65d
·
verified ·
1 Parent(s): 7d50402

End of training

Browse files
Files changed (4) hide show
  1. README.md +64 -33
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.4676
21
- - Num Input Tokens Seen: 8712000
22
 
23
  ## Model description
24
 
@@ -53,37 +53,68 @@ The following hyperparameters were used during training:
53
  | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
54
  |:-------------:|:------:|:----:|:---------------:|:-----------------:|
55
  | No log | 0 | 0 | 1.3956 | 0 |
56
- | 1.7677 | 0.0320 | 5 | 1.3656 | 271360 |
57
- | 1.5854 | 0.0639 | 10 | 1.2596 | 545792 |
58
- | 1.4739 | 0.0959 | 15 | 1.1954 | 825128 |
59
- | 1.2857 | 0.1279 | 20 | 1.1738 | 1108408 |
60
- | 1.184 | 0.1599 | 25 | 1.1751 | 1388256 |
61
- | 0.9207 | 0.1918 | 30 | 1.2445 | 1667528 |
62
- | 0.8665 | 0.2238 | 35 | 1.2921 | 1949712 |
63
- | 0.7163 | 0.2558 | 40 | 1.4105 | 2223872 |
64
- | 0.5853 | 0.2878 | 45 | 1.4211 | 2497184 |
65
- | 0.5139 | 0.3197 | 50 | 1.5440 | 2777320 |
66
- | 0.4299 | 0.3517 | 55 | 1.5069 | 3057528 |
67
- | 0.3458 | 0.3837 | 60 | 1.5679 | 3331488 |
68
- | 0.2913 | 0.4157 | 65 | 1.5084 | 3611304 |
69
- | 0.2654 | 0.4476 | 70 | 1.5051 | 3897800 |
70
- | 0.2249 | 0.4796 | 75 | 1.5396 | 4174176 |
71
- | 0.3085 | 0.5116 | 80 | 1.5069 | 4450528 |
72
- | 0.1601 | 0.5436 | 85 | 1.5507 | 4732680 |
73
- | 0.1126 | 0.5755 | 90 | 1.4520 | 5015288 |
74
- | 0.1922 | 0.6075 | 95 | 1.4548 | 5296336 |
75
- | 0.1709 | 0.6395 | 100 | 1.4422 | 5578672 |
76
- | 0.1558 | 0.6715 | 105 | 1.4477 | 5860328 |
77
- | 0.0981 | 0.7034 | 110 | 1.4791 | 6141568 |
78
- | 0.1635 | 0.7354 | 115 | 1.4351 | 6424480 |
79
- | 0.1061 | 0.7674 | 120 | 1.4498 | 6706048 |
80
- | 0.159 | 0.7994 | 125 | 1.4220 | 6990040 |
81
- | 0.0759 | 0.8313 | 130 | 1.4819 | 7264776 |
82
- | 0.0897 | 0.8633 | 135 | 1.4187 | 7543304 |
83
- | 0.1316 | 0.8953 | 140 | 1.4371 | 7823792 |
84
- | 0.1955 | 0.9273 | 145 | 1.4277 | 8101728 |
85
- | 0.1215 | 0.9592 | 150 | 1.4345 | 8378768 |
86
- | 0.1174 | 0.9912 | 155 | 1.4765 | 8659448 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
 
88
 
89
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.5298
21
+ - Num Input Tokens Seen: 17258584
22
 
23
  ## Model description
24
 
 
53
  | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
54
  |:-------------:|:------:|:----:|:---------------:|:-----------------:|
55
  | No log | 0 | 0 | 1.3956 | 0 |
56
+ | 1.7151 | 0.0160 | 5 | 1.3649 | 280984 |
57
+ | 1.5285 | 0.0320 | 10 | 1.2591 | 563568 |
58
+ | 1.4731 | 0.0480 | 15 | 1.1922 | 850472 |
59
+ | 1.3042 | 0.0640 | 20 | 1.1590 | 1126824 |
60
+ | 1.2126 | 0.0800 | 25 | 1.1400 | 1403000 |
61
+ | 1.1899 | 0.0960 | 30 | 1.1529 | 1677208 |
62
+ | 0.999 | 0.1120 | 35 | 1.1739 | 1947376 |
63
+ | 0.9221 | 0.1279 | 40 | 1.2091 | 2227616 |
64
+ | 0.9325 | 0.1439 | 45 | 1.2620 | 2499960 |
65
+ | 0.7948 | 0.1599 | 50 | 1.2823 | 2768464 |
66
+ | 0.7694 | 0.1759 | 55 | 1.3642 | 3043800 |
67
+ | 0.7514 | 0.1919 | 60 | 1.3647 | 3322280 |
68
+ | 0.65 | 0.2079 | 65 | 1.4181 | 3592344 |
69
+ | 0.6182 | 0.2239 | 70 | 1.4624 | 3874992 |
70
+ | 0.5163 | 0.2399 | 75 | 1.4747 | 4152464 |
71
+ | 0.5077 | 0.2559 | 80 | 1.4591 | 4425448 |
72
+ | 0.4374 | 0.2719 | 85 | 1.5298 | 4701152 |
73
+ | 0.3394 | 0.2879 | 90 | 1.5052 | 4979368 |
74
+ | 0.3141 | 0.3039 | 95 | 1.5624 | 5254560 |
75
+ | 0.3624 | 0.3199 | 100 | 1.5197 | 5532040 |
76
+ | 0.2848 | 0.3359 | 105 | 1.5283 | 5815048 |
77
+ | 0.3023 | 0.3519 | 110 | 1.4896 | 6090168 |
78
+ | 0.2951 | 0.3679 | 115 | 1.5557 | 6370688 |
79
+ | 0.2294 | 0.3838 | 120 | 1.5023 | 6644392 |
80
+ | 0.1664 | 0.3998 | 125 | 1.5413 | 6915576 |
81
+ | 0.1481 | 0.4158 | 130 | 1.5159 | 7189320 |
82
+ | 0.196 | 0.4318 | 135 | 1.5542 | 7463232 |
83
+ | 0.2218 | 0.4478 | 140 | 1.5711 | 7740456 |
84
+ | 0.2089 | 0.4638 | 145 | 1.4790 | 8014600 |
85
+ | 0.2167 | 0.4798 | 150 | 1.5068 | 8293824 |
86
+ | 0.2483 | 0.4958 | 155 | 1.4646 | 8564248 |
87
+ | 0.1578 | 0.5118 | 160 | 1.4834 | 8836952 |
88
+ | 0.1617 | 0.5278 | 165 | 1.4932 | 9115608 |
89
+ | 0.1366 | 0.5438 | 170 | 1.4936 | 9389168 |
90
+ | 0.1628 | 0.5598 | 175 | 1.5136 | 9669560 |
91
+ | 0.1186 | 0.5758 | 180 | 1.4843 | 9942856 |
92
+ | 0.1343 | 0.5918 | 185 | 1.5045 | 10216144 |
93
+ | 0.1022 | 0.6078 | 190 | 1.4646 | 10489128 |
94
+ | 0.0853 | 0.6238 | 195 | 1.4684 | 10769016 |
95
+ | 0.1577 | 0.6397 | 200 | 1.4865 | 11047400 |
96
+ | 0.1552 | 0.6557 | 205 | 1.4296 | 11328400 |
97
+ | 0.2221 | 0.6717 | 210 | 1.4768 | 11602552 |
98
+ | 0.1426 | 0.6877 | 215 | 1.4382 | 11881496 |
99
+ | 0.0724 | 0.7037 | 220 | 1.4639 | 12166392 |
100
+ | 0.1345 | 0.7197 | 225 | 1.4186 | 12443568 |
101
+ | 0.1385 | 0.7357 | 230 | 1.4526 | 12722400 |
102
+ | 0.0969 | 0.7517 | 235 | 1.4532 | 13005696 |
103
+ | 0.1123 | 0.7677 | 240 | 1.4317 | 13287632 |
104
+ | 0.0852 | 0.7837 | 245 | 1.4869 | 13566576 |
105
+ | 0.1228 | 0.7997 | 250 | 1.4233 | 13843336 |
106
+ | 0.0919 | 0.8157 | 255 | 1.4676 | 14123744 |
107
+ | 0.0924 | 0.8317 | 260 | 1.4920 | 14403528 |
108
+ | 0.1393 | 0.8477 | 265 | 1.4665 | 14681304 |
109
+ | 0.1063 | 0.8637 | 270 | 1.4547 | 14956896 |
110
+ | 0.1158 | 0.8796 | 275 | 1.5160 | 15230056 |
111
+ | 0.1062 | 0.8956 | 280 | 1.5117 | 15505704 |
112
+ | 0.1193 | 0.9116 | 285 | 1.4500 | 15776784 |
113
+ | 0.2646 | 0.9276 | 290 | 1.4688 | 16050272 |
114
+ | 0.166 | 0.9436 | 295 | 1.4617 | 16318920 |
115
+ | 0.1153 | 0.9596 | 300 | 1.4931 | 16598920 |
116
+ | 0.1233 | 0.9756 | 305 | 1.4729 | 16875936 |
117
+ | 0.0626 | 0.9916 | 310 | 1.4923 | 17148640 |
118
 
119
 
120
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e6c4d25bc4e37af3bae671f585b8dc8a4ff1f5d3a2bdea13fac8aeec9a3aba4
3
  size 4988025760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f83245880d14ffa7f136bb9fe3b8b2b81f7182e884b54d9a9612e6516ee30a
3
  size 4988025760
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b67992ea47fef38394cb295f440d4763ffdbcf74405e9b2ffbe52429c1fabc2
3
  size 240691728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d294fa537d47ad3f630845666fc620737737d0cdce9567dcace1f1650cc2fc8
3
  size 240691728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f41a663f3774ba9b39866fd95fbe45544b1c6dd175c57fd4e1620747b82b0e8
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114359845fd8eda0b7b26315431ddc5568a69a42f6272ab4bf6b47e0e115deec
3
  size 5560