Hugging Face's logo

jkazdan
/
gemma-2-2b_hs2_iter1_sftsd2

Safetensors
gemma2
trl
sft
Generated from Trainer
Model card Files Community
jkazdan commited on
Commit
1bdbeea
·
verified ·
1 Parent(s): d9fdc6e

End of training

Browse files
Files changed (4) hide show
  1. README.md +33 -20
  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: 1.4064
21
- - Num Input Tokens Seen: 5013120
22
 
23
  ## Model description
24
 
@@ -53,24 +53,37 @@ 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
- | 1.7605 | 0.0533 | 5 | 1.3646 | 271024 |
57
- | 1.6463 | 0.1065 | 10 | 1.2574 | 548112 |
58
- | 1.2612 | 0.1598 | 15 | 1.1932 | 815192 |
59
- | 1.1881 | 0.2130 | 20 | 1.2005 | 1086056 |
60
- | 0.8721 | 0.2663 | 25 | 1.2474 | 1355552 |
61
- | 0.7559 | 0.3196 | 30 | 1.3551 | 1624672 |
62
- | 0.547 | 0.3728 | 35 | 1.4708 | 1891616 |
63
- | 0.5535 | 0.4261 | 40 | 1.5088 | 2160264 |
64
- | 0.364 | 0.4794 | 45 | 1.5059 | 2422952 |
65
- | 0.2764 | 0.5326 | 50 | 1.5500 | 2687280 |
66
- | 0.2753 | 0.5859 | 55 | 1.4921 | 2963720 |
67
- | 0.2451 | 0.6391 | 60 | 1.4914 | 3232320 |
68
- | 0.171 | 0.6924 | 65 | 1.4621 | 3499536 |
69
- | 0.2112 | 0.7457 | 70 | 1.4431 | 3767480 |
70
- | 0.1409 | 0.7989 | 75 | 1.4324 | 4034024 |
71
- | 0.1234 | 0.8522 | 80 | 1.4287 | 4306120 |
72
- | 0.17 | 0.9055 | 85 | 1.4654 | 4574936 |
73
- | 0.187 | 0.9587 | 90 | 1.4095 | 4843040 |
 
 
 
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### 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: 1.5013
21
+ - Num Input Tokens Seen: 8534232
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
+ | 1.7736 | 0.0320 | 5 | 1.3653 | 275408 |
57
+ | 1.6337 | 0.0639 | 10 | 1.2568 | 553472 |
58
+ | 1.4116 | 0.0959 | 15 | 1.1899 | 826008 |
59
+ | 1.2166 | 0.1279 | 20 | 1.1757 | 1103104 |
60
+ | 1.0729 | 0.1599 | 25 | 1.1790 | 1373480 |
61
+ | 0.8893 | 0.1918 | 30 | 1.2432 | 1652728 |
62
+ | 0.7547 | 0.2238 | 35 | 1.3378 | 1922040 |
63
+ | 0.7355 | 0.2558 | 40 | 1.4150 | 2199704 |
64
+ | 0.5898 | 0.2878 | 45 | 1.4809 | 2466336 |
65
+ | 0.5135 | 0.3197 | 50 | 1.5266 | 2736736 |
66
+ | 0.3229 | 0.3517 | 55 | 1.5925 | 3013400 |
67
+ | 0.3465 | 0.3837 | 60 | 1.5686 | 3287688 |
68
+ | 0.2492 | 0.4157 | 65 | 1.5743 | 3563792 |
69
+ | 0.2927 | 0.4476 | 70 | 1.5284 | 3835816 |
70
+ | 0.1576 | 0.4796 | 75 | 1.5619 | 4101480 |
71
+ | 0.1489 | 0.5116 | 80 | 1.5506 | 4374744 |
72
+ | 0.1981 | 0.5436 | 85 | 1.4726 | 4648312 |
73
+ | 0.1814 | 0.5755 | 90 | 1.4712 | 4923392 |
74
+ | 0.1315 | 0.6075 | 95 | 1.4717 | 5194312 |
75
+ | 0.1366 | 0.6395 | 100 | 1.4953 | 5462264 |
76
+ | 0.1341 | 0.6715 | 105 | 1.4516 | 5735336 |
77
+ | 0.0875 | 0.7034 | 110 | 1.4808 | 6010376 |
78
+ | 0.2061 | 0.7354 | 115 | 1.4586 | 6282688 |
79
+ | 0.1429 | 0.7674 | 120 | 1.4499 | 6551944 |
80
+ | 0.1636 | 0.7994 | 125 | 1.4508 | 6830192 |
81
+ | 0.0944 | 0.8313 | 130 | 1.4615 | 7104592 |
82
+ | 0.1036 | 0.8633 | 135 | 1.4519 | 7376888 |
83
+ | 0.1495 | 0.8953 | 140 | 1.4785 | 7649992 |
84
+ | 0.1092 | 0.9273 | 145 | 1.4493 | 7925824 |
85
+ | 0.0795 | 0.9592 | 150 | 1.4897 | 8204488 |
86
+ | 0.1456 | 0.9912 | 155 | 1.5040 | 8481368 |
87
 
88
 
89
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ebf43eff61fd6161cb5bad5022187a7603a7874ed074b95152e4477d3db4d0d
3
  size 4988025760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c44978a07fa859d02985d190213da47d5ebdaae88c7386ea1530207a3a82862b
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:db47d6485d577190c31fe82f5438ab4a6419f1b274450a413ec07682fb949d5c
3
  size 240691728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30a9fe60953272846040812269a2afb6c9ae1eb2cf3d0e52549cb433048d5605
3
  size 240691728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53ffc50821412135e1bfab8ea1324238146bb5049ed0552ce6038760b9e350e7
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bee570f98391ba03df3c0a98563352949e91c76e98b4cbc36d40200275f34d7
3
  size 5560