Hugging Face's logo

Zacktree
/
code-bench-CodeGemma-7B-cgv1-ds_v3

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
Zacktree commited on
Commit
b5e8753
·
verified ·
1 Parent(s): ffc08d3

Model save

Browse files
Files changed (6) hide show
  1. README.md +179 -0
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. runs/Sep14_01-37-16_m3u004/events.out.tfevents.1757778313.m3u004.346234.0 +2 -2
  5. runs/Sep14_23-08-28_m3h110/events.out.tfevents.1757855892.m3h110.1149182.0 +3 -0
  6. training_args.bin +1 -1
README.md ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_v3
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_v3
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: 0.0663
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
+ | 0.7003 | 0.0530 | 50 | 0.6702 |
58
+ | 0.5467 | 0.1061 | 100 | 0.5399 |
59
+ | 0.4662 | 0.1591 | 150 | 0.4138 |
60
+ | 0.3608 | 0.2121 | 200 | 0.3042 |
61
+ | 0.3032 | 0.2652 | 250 | 0.2450 |
62
+ | 0.2313 | 0.3182 | 300 | 0.2067 |
63
+ | 0.1953 | 0.3713 | 350 | 0.1729 |
64
+ | 0.1701 | 0.4243 | 400 | 0.1495 |
65
+ | 0.1593 | 0.4773 | 450 | 0.1382 |
66
+ | 0.1491 | 0.5304 | 500 | 0.1334 |
67
+ | 0.1668 | 0.5834 | 550 | 0.1282 |
68
+ | 0.1433 | 0.6364 | 600 | 0.1259 |
69
+ | 0.1457 | 0.6895 | 650 | 0.1241 |
70
+ | 0.1476 | 0.7425 | 700 | 0.1215 |
71
+ | 0.139 | 0.7955 | 750 | 0.1176 |
72
+ | 0.1209 | 0.8486 | 800 | 0.1159 |
73
+ | 0.1365 | 0.9016 | 850 | 0.1148 |
74
+ | 0.1239 | 0.9547 | 900 | 0.1157 |
75
+ | 0.116 | 1.0077 | 950 | 0.1097 |
76
+ | 0.1145 | 1.0607 | 1000 | 0.1104 |
77
+ | 0.1187 | 1.1146 | 1050 | 0.1067 |
78
+ | 0.117 | 1.1676 | 1100 | 0.1069 |
79
+ | 0.1219 | 1.2206 | 1150 | 0.1059 |
80
+ | 0.1192 | 1.2737 | 1200 | 0.1052 |
81
+ | 0.1296 | 1.3267 | 1250 | 0.1023 |
82
+ | 0.1016 | 1.3797 | 1300 | 0.1016 |
83
+ | 0.1051 | 1.4328 | 1350 | 0.1011 |
84
+ | 0.1207 | 1.4858 | 1400 | 0.1016 |
85
+ | 0.1132 | 1.5388 | 1450 | 0.1031 |
86
+ | 0.1143 | 1.5919 | 1500 | 0.0997 |
87
+ | 0.1089 | 1.6449 | 1550 | 0.0988 |
88
+ | 0.1164 | 1.6980 | 1600 | 0.0966 |
89
+ | 0.1092 | 1.7510 | 1650 | 0.0961 |
90
+ | 0.1056 | 1.8040 | 1700 | 0.0957 |
91
+ | 0.1072 | 1.8571 | 1750 | 0.0948 |
92
+ | 0.1029 | 1.9101 | 1800 | 0.0942 |
93
+ | 0.1117 | 1.9631 | 1850 | 0.0931 |
94
+ | 0.1126 | 2.0162 | 1900 | 0.0931 |
95
+ | 0.104 | 2.0700 | 1950 | 0.0944 |
96
+ | 0.1094 | 2.1230 | 2000 | 0.0925 |
97
+ | 0.1044 | 2.1761 | 2050 | 0.0944 |
98
+ | 0.0981 | 2.2291 | 2100 | 0.0926 |
99
+ | 0.1031 | 2.2822 | 2150 | 0.0915 |
100
+ | 0.0933 | 2.3352 | 2200 | 0.0919 |
101
+ | 0.1085 | 2.3882 | 2250 | 0.0917 |
102
+ | 0.1106 | 2.4413 | 2300 | 0.0905 |
103
+ | 0.0988 | 2.4943 | 2350 | 0.0897 |
104
+ | 0.0909 | 2.5473 | 2400 | 0.0883 |
105
+ | 0.1025 | 2.6004 | 2450 | 0.0874 |
106
+ | 0.1016 | 2.6534 | 2500 | 0.0873 |
107
+ | 0.0927 | 2.7064 | 2550 | 0.0860 |
108
+ | 0.0942 | 2.7595 | 2600 | 0.0854 |
109
+ | 0.0888 | 2.8125 | 2650 | 0.0859 |
110
+ | 0.091 | 2.8656 | 2700 | 0.0851 |
111
+ | 0.0922 | 2.9186 | 2750 | 0.0855 |
112
+ | 0.0949 | 2.9716 | 2800 | 0.0839 |
113
+ | 0.0855 | 3.0247 | 2850 | 0.0841 |
114
+ | 0.0955 | 3.0777 | 2900 | 0.0831 |
115
+ | 0.0831 | 3.1307 | 2950 | 0.0817 |
116
+ | 0.0843 | 3.1838 | 3000 | 0.0814 |
117
+ | 0.0756 | 3.2368 | 3050 | 0.0812 |
118
+ | 0.0893 | 3.2898 | 3100 | 0.0806 |
119
+ | 0.0787 | 3.3429 | 3150 | 0.0827 |
120
+ | 0.0842 | 3.3959 | 3200 | 0.0790 |
121
+ | 0.079 | 3.4490 | 3250 | 0.0791 |
122
+ | 0.0797 | 3.5020 | 3300 | 0.0773 |
123
+ | 0.0774 | 3.5550 | 3350 | 0.0777 |
124
+ | 0.0751 | 3.6081 | 3400 | 0.0779 |
125
+ | 0.079 | 3.6611 | 3450 | 0.0781 |
126
+ | 0.0849 | 3.7141 | 3500 | 0.0762 |
127
+ | 0.0852 | 3.7672 | 3550 | 0.0759 |
128
+ | 0.0742 | 3.8202 | 3600 | 0.0770 |
129
+ | 0.0719 | 3.8732 | 3650 | 0.0755 |
130
+ | 0.07 | 3.9263 | 3700 | 0.0757 |
131
+ | 0.0778 | 3.9793 | 3750 | 0.0759 |
132
+ | 0.0792 | 4.0324 | 3800 | 0.0751 |
133
+ | 0.0705 | 4.0854 | 3850 | 0.0745 |
134
+ | 0.0679 | 4.1384 | 3900 | 0.0741 |
135
+ | 0.0619 | 4.1915 | 3950 | 0.0734 |
136
+ | 0.0689 | 4.2445 | 4000 | 0.0731 |
137
+ | 0.0653 | 4.2975 | 4050 | 0.0732 |
138
+ | 0.0678 | 4.3506 | 4100 | 0.0733 |
139
+ | 0.07 | 4.4036 | 4150 | 0.0719 |
140
+ | 0.0656 | 4.4566 | 4200 | 0.0739 |
141
+ | 0.062 | 4.5097 | 4250 | 0.0732 |
142
+ | 0.0676 | 4.5627 | 4300 | 0.0718 |
143
+ | 0.0668 | 4.6158 | 4350 | 0.0722 |
144
+ | 0.0701 | 4.6688 | 4400 | 0.0718 |
145
+ | 0.067 | 4.7218 | 4450 | 0.0709 |
146
+ | 0.0686 | 4.7749 | 4500 | 0.0722 |
147
+ | 0.0649 | 4.8279 | 4550 | 0.0751 |
148
+ | 0.0711 | 4.8809 | 4600 | 0.0708 |
149
+ | 0.0747 | 4.9340 | 4650 | 0.0711 |
150
+ | 0.0622 | 4.9870 | 4700 | 0.0700 |
151
+ | 0.0634 | 5.0400 | 4750 | 0.0695 |
152
+ | 0.0714 | 5.0931 | 4800 | 0.0756 |
153
+ | 0.0615 | 5.1461 | 4850 | 0.0732 |
154
+ | 0.0612 | 5.1992 | 4900 | 0.0704 |
155
+ | 0.0599 | 5.2522 | 4950 | 0.0686 |
156
+ | 0.0567 | 5.3052 | 5000 | 0.0679 |
157
+ | 0.0593 | 5.3583 | 5050 | 0.0673 |
158
+ | 0.0576 | 5.4113 | 5100 | 0.0675 |
159
+ | 0.0628 | 5.4643 | 5150 | 0.0664 |
160
+ | 0.0572 | 5.5174 | 5200 | 0.0660 |
161
+ | 0.06 | 5.5704 | 5250 | 0.0659 |
162
+ | 0.0568 | 5.6234 | 5300 | 0.0660 |
163
+ | 0.058 | 5.6765 | 5350 | 0.0656 |
164
+ | 0.0559 | 5.7295 | 5400 | 0.0650 |
165
+ | 0.0549 | 5.7826 | 5450 | 0.0652 |
166
+ | 0.0605 | 5.8356 | 5500 | 0.0649 |
167
+ | 0.0539 | 5.8886 | 5550 | 0.0641 |
168
+ | 0.0567 | 5.9417 | 5600 | 0.0637 |
169
+ | 0.057 | 5.9947 | 5650 | 0.0654 |
170
+ | 0.0482 | 6.0477 | 5700 | 0.0663 |
171
+
172
+
173
+ ### Framework versions
174
+
175
+ - PEFT 0.12.0
176
+ - Transformers 4.44.2
177
+ - Pytorch 2.5.1+cu121
178
+ - Datasets 2.21.0
179
+ - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "up_proj",
24
- "down_proj",
25
  "v_proj",
26
- "q_proj",
27
  "gate_proj",
28
- "k_proj",
29
- "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "k_proj",
24
  "up_proj",
 
25
  "v_proj",
26
+ "o_proj",
27
  "gate_proj",
28
+ "down_proj",
29
+ "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:396ed40a315ac49bf0589594156623ec2b1127e6a3ba4e96f07128ed0c35bb9b
3
  size 1600180696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9070aed38f1612d9138220168f91b351f4644fca45b3f0f2783fa64b5063f1d2
3
  size 1600180696
runs/Sep14_01-37-16_m3u004/events.out.tfevents.1757778313.m3u004.346234.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b82bacb778cac5eddbc402efb84c35828ab35a62250cfeb9b139c7e3365c3ce5
3
- size 106168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34d536e807aac3be8ff74782c35e603dc2bea38032ecf74feb645070c93eccd
3
+ size 106379
runs/Sep14_23-08-28_m3h110/events.out.tfevents.1757855892.m3h110.1149182.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d8d86d6527c4c38c73f6a9e79826d92bbc8e3e4ba261c5ec4868cbcb92aa98
3
+ size 5746
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3097d847240ef7e2acab915ba484c07d7caf75506260be3835e2822f1bb14f4
3
  size 6520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febb173af5ecfded702eef7abc30ac924686dd08f9fd0b333ea2ed89cb0a82eb
3
  size 6520