Hugging Face's logo

Zacktree
/
code-bench-CodeGemma-7B-cgv1-ds_v2

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
Zacktree commited on
Commit
e545f45
·
verified ·
1 Parent(s): 05fe08a

Model save

Browse files
Files changed (3) hide show
  1. README.md +159 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Sep12_14-37-39_m3h111/events.out.tfevents.1757652367.m3h111.3686641.0 +2 -2
README.md ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: gemma
4
+ base_model: google/codegemma-7b
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: code-bench-CodeGemma-7B-cgv1-ds_v2
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # code-bench-CodeGemma-7B-cgv1-ds_v2
18
+
19
+ This model is a fine-tuned version of [google/codegemma-7b](https://huggingface.co/google/codegemma-7b) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0762
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 3
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 8
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.03
50
+ - num_epochs: 5
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 1.5399 | 0.0530 | 50 | 1.1400 |
58
+ | 0.6618 | 0.1061 | 100 | 0.6524 |
59
+ | 0.5559 | 0.1591 | 150 | 0.5211 |
60
+ | 0.4396 | 0.2121 | 200 | 0.3873 |
61
+ | 0.3611 | 0.2652 | 250 | 0.3164 |
62
+ | 0.2679 | 0.3182 | 300 | 0.2416 |
63
+ | 0.2163 | 0.3713 | 350 | 0.1974 |
64
+ | 0.1916 | 0.4243 | 400 | 0.1638 |
65
+ | 0.1696 | 0.4773 | 450 | 0.1485 |
66
+ | 0.1601 | 0.5304 | 500 | 0.1416 |
67
+ | 0.1804 | 0.5834 | 550 | 0.1351 |
68
+ | 0.152 | 0.6364 | 600 | 0.1336 |
69
+ | 0.1532 | 0.6895 | 650 | 0.1317 |
70
+ | 0.1527 | 0.7425 | 700 | 0.1286 |
71
+ | 0.1446 | 0.7955 | 750 | 0.1250 |
72
+ | 0.1379 | 0.8486 | 800 | 0.1217 |
73
+ | 0.1451 | 0.9016 | 850 | 0.1227 |
74
+ | 0.1382 | 0.9547 | 900 | 0.1196 |
75
+ | 0.1218 | 1.0077 | 950 | 0.1170 |
76
+ | 0.1238 | 1.0607 | 1000 | 0.1174 |
77
+ | 0.1143 | 1.1138 | 1050 | 0.1171 |
78
+ | 0.1301 | 1.1668 | 1100 | 0.1136 |
79
+ | 0.1243 | 1.2198 | 1150 | 0.1123 |
80
+ | 0.1291 | 1.2729 | 1200 | 0.1119 |
81
+ | 0.1288 | 1.3259 | 1250 | 0.1104 |
82
+ | 0.1058 | 1.3789 | 1300 | 0.1082 |
83
+ | 0.1065 | 1.4320 | 1350 | 0.1059 |
84
+ | 0.1259 | 1.4850 | 1400 | 0.1068 |
85
+ | 0.1225 | 1.5381 | 1450 | 0.1051 |
86
+ | 0.1085 | 1.5911 | 1500 | 0.1035 |
87
+ | 0.1058 | 1.6441 | 1550 | 0.1031 |
88
+ | 0.1169 | 1.6972 | 1600 | 0.1022 |
89
+ | 0.1117 | 1.7502 | 1650 | 0.1010 |
90
+ | 0.1115 | 1.8032 | 1700 | 0.1008 |
91
+ | 0.1137 | 1.8563 | 1750 | 0.0995 |
92
+ | 0.1068 | 1.9093 | 1800 | 0.0990 |
93
+ | 0.1131 | 1.9623 | 1850 | 0.0979 |
94
+ | 0.1065 | 2.0154 | 1900 | 0.0974 |
95
+ | 0.0972 | 2.0684 | 1950 | 0.0966 |
96
+ | 0.1042 | 2.1215 | 2000 | 0.0955 |
97
+ | 0.0906 | 2.1745 | 2050 | 0.0948 |
98
+ | 0.0995 | 2.2275 | 2100 | 0.0949 |
99
+ | 0.0903 | 2.2806 | 2150 | 0.0939 |
100
+ | 0.0894 | 2.3336 | 2200 | 0.0938 |
101
+ | 0.0928 | 2.3866 | 2250 | 0.0925 |
102
+ | 0.1021 | 2.4397 | 2300 | 0.0922 |
103
+ | 0.0892 | 2.4927 | 2350 | 0.0911 |
104
+ | 0.0864 | 2.5457 | 2400 | 0.0901 |
105
+ | 0.0873 | 2.5988 | 2450 | 0.0895 |
106
+ | 0.0973 | 2.6518 | 2500 | 0.0887 |
107
+ | 0.0928 | 2.7049 | 2550 | 0.0883 |
108
+ | 0.0931 | 2.7579 | 2600 | 0.0883 |
109
+ | 0.0903 | 2.8109 | 2650 | 0.0871 |
110
+ | 0.0925 | 2.8640 | 2700 | 0.0867 |
111
+ | 0.0795 | 2.9170 | 2750 | 0.0854 |
112
+ | 0.0935 | 2.9700 | 2800 | 0.0851 |
113
+ | 0.0807 | 3.0231 | 2850 | 0.0860 |
114
+ | 0.0919 | 3.0761 | 2900 | 0.0846 |
115
+ | 0.0733 | 3.1291 | 2950 | 0.0840 |
116
+ | 0.0829 | 3.1822 | 3000 | 0.0840 |
117
+ | 0.0784 | 3.2352 | 3050 | 0.0833 |
118
+ | 0.0749 | 3.2883 | 3100 | 0.0827 |
119
+ | 0.0746 | 3.3413 | 3150 | 0.0828 |
120
+ | 0.0783 | 3.3943 | 3200 | 0.0824 |
121
+ | 0.0839 | 3.4474 | 3250 | 0.0815 |
122
+ | 0.0766 | 3.5004 | 3300 | 0.0810 |
123
+ | 0.0785 | 3.5534 | 3350 | 0.0804 |
124
+ | 0.0676 | 3.6065 | 3400 | 0.0800 |
125
+ | 0.0772 | 3.6595 | 3450 | 0.0796 |
126
+ | 0.0754 | 3.7125 | 3500 | 0.0794 |
127
+ | 0.0738 | 3.7656 | 3550 | 0.0790 |
128
+ | 0.0681 | 3.8186 | 3600 | 0.0788 |
129
+ | 0.0639 | 3.8717 | 3650 | 0.0788 |
130
+ | 0.069 | 3.9247 | 3700 | 0.0779 |
131
+ | 0.0725 | 3.9777 | 3750 | 0.0779 |
132
+ | 0.0692 | 4.0308 | 3800 | 0.0787 |
133
+ | 0.0597 | 4.0838 | 3850 | 0.0780 |
134
+ | 0.062 | 4.1368 | 3900 | 0.0775 |
135
+ | 0.0643 | 4.1899 | 3950 | 0.0774 |
136
+ | 0.0707 | 4.2429 | 4000 | 0.0766 |
137
+ | 0.0603 | 4.2959 | 4050 | 0.0771 |
138
+ | 0.0719 | 4.3490 | 4100 | 0.0767 |
139
+ | 0.0659 | 4.4020 | 4150 | 0.0769 |
140
+ | 0.0684 | 4.4551 | 4200 | 0.0764 |
141
+ | 0.0631 | 4.5081 | 4250 | 0.0768 |
142
+ | 0.0642 | 4.5611 | 4300 | 0.0766 |
143
+ | 0.0623 | 4.6142 | 4350 | 0.0766 |
144
+ | 0.0766 | 4.6672 | 4400 | 0.0765 |
145
+ | 0.0671 | 4.7202 | 4450 | 0.0764 |
146
+ | 0.0651 | 4.7733 | 4500 | 0.0762 |
147
+ | 0.0621 | 4.8263 | 4550 | 0.0762 |
148
+ | 0.0638 | 4.8793 | 4600 | 0.0762 |
149
+ | 0.0727 | 4.9324 | 4650 | 0.0762 |
150
+ | 0.059 | 4.9854 | 4700 | 0.0762 |
151
+
152
+
153
+ ### Framework versions
154
+
155
+ - PEFT 0.12.0
156
+ - Transformers 4.44.2
157
+ - Pytorch 2.5.1+cu121
158
+ - Datasets 2.21.0
159
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84fbcdf89bdce3c17000b24ed9abb2cca47432611f5beff87b950a965e6f0f53
3
  size 4745934024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252308b20bd46b6ad6f102aaa9177a71ed339511ad8bc96abb8ded44c9ca5721
3
  size 4745934024
runs/Sep12_14-37-39_m3h111/events.out.tfevents.1757652367.m3h111.3686641.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef9c875f6c47b7dae973cbad9aba17d786551cabfd46243ee2aa9dff7a86b5c8
3
- size 129993
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad79130013303d530128f2dd4f96092f154ee3c45d73186387327d2c6d08036
3
+ size 130558