Hugging Face's logo

Zacktree
/
code-bench-CodeGemma-7B-cg-nv9n

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
Zacktree commited on
Commit
f6c5302
·
verified ·
1 Parent(s): 9f1ffab

Model save

Browse files
Files changed (3) hide show
  1. README.md +140 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Sep19_11-47-10_m3h111/events.out.tfevents.1758246497.m3h111.612245.0 +2 -2
README.md ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-cg-nv9n
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-cg-nv9n
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: 0.0676
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: 4
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 0.623 | 0.0530 | 50 | 0.5961 |
58
+ | 0.473 | 0.1061 | 100 | 0.4669 |
59
+ | 0.4018 | 0.1591 | 150 | 0.3573 |
60
+ | 0.3249 | 0.2121 | 200 | 0.2696 |
61
+ | 0.2703 | 0.2652 | 250 | 0.2265 |
62
+ | 0.2066 | 0.3182 | 300 | 0.1859 |
63
+ | 0.1725 | 0.3713 | 350 | 0.1526 |
64
+ | 0.1588 | 0.4243 | 400 | 0.1341 |
65
+ | 0.1467 | 0.4773 | 450 | 0.1278 |
66
+ | 0.1349 | 0.5304 | 500 | 0.1229 |
67
+ | 0.1541 | 0.5834 | 550 | 0.1170 |
68
+ | 0.1262 | 0.6364 | 600 | 0.1137 |
69
+ | 0.1273 | 0.6895 | 650 | 0.1118 |
70
+ | 0.1322 | 0.7425 | 700 | 0.1091 |
71
+ | 0.1244 | 0.7955 | 750 | 0.1069 |
72
+ | 0.1134 | 0.8486 | 800 | 0.1043 |
73
+ | 0.1206 | 0.9016 | 850 | 0.1030 |
74
+ | 0.117 | 0.9547 | 900 | 0.1016 |
75
+ | 0.101 | 1.0077 | 950 | 0.1003 |
76
+ | 0.1095 | 1.0607 | 1000 | 0.0999 |
77
+ | 0.0989 | 1.1138 | 1050 | 0.0991 |
78
+ | 0.1054 | 1.1668 | 1100 | 0.0972 |
79
+ | 0.1073 | 1.2198 | 1150 | 0.0964 |
80
+ | 0.1057 | 1.2729 | 1200 | 0.0951 |
81
+ | 0.111 | 1.3259 | 1250 | 0.0953 |
82
+ | 0.0946 | 1.3789 | 1300 | 0.0935 |
83
+ | 0.0907 | 1.4320 | 1350 | 0.0926 |
84
+ | 0.0989 | 1.4850 | 1400 | 0.0919 |
85
+ | 0.1037 | 1.5381 | 1450 | 0.0905 |
86
+ | 0.0955 | 1.5911 | 1500 | 0.0899 |
87
+ | 0.0893 | 1.6441 | 1550 | 0.0887 |
88
+ | 0.1015 | 1.6972 | 1600 | 0.0881 |
89
+ | 0.0952 | 1.7502 | 1650 | 0.0874 |
90
+ | 0.0918 | 1.8032 | 1700 | 0.0868 |
91
+ | 0.0926 | 1.8563 | 1750 | 0.0860 |
92
+ | 0.0886 | 1.9093 | 1800 | 0.0852 |
93
+ | 0.0989 | 1.9623 | 1850 | 0.0841 |
94
+ | 0.0863 | 2.0154 | 1900 | 0.0839 |
95
+ | 0.0821 | 2.0684 | 1950 | 0.0836 |
96
+ | 0.0964 | 2.1215 | 2000 | 0.0830 |
97
+ | 0.0755 | 2.1745 | 2050 | 0.0824 |
98
+ | 0.0777 | 2.2275 | 2100 | 0.0817 |
99
+ | 0.0761 | 2.2806 | 2150 | 0.0807 |
100
+ | 0.0777 | 2.3336 | 2200 | 0.0802 |
101
+ | 0.0857 | 2.3866 | 2250 | 0.0795 |
102
+ | 0.0883 | 2.4397 | 2300 | 0.0793 |
103
+ | 0.0784 | 2.4927 | 2350 | 0.0785 |
104
+ | 0.0774 | 2.5457 | 2400 | 0.0779 |
105
+ | 0.0776 | 2.5988 | 2450 | 0.0772 |
106
+ | 0.0788 | 2.6518 | 2500 | 0.0770 |
107
+ | 0.0853 | 2.7064 | 2550 | 0.0768 |
108
+ | 0.0836 | 2.7595 | 2600 | 0.0764 |
109
+ | 0.0822 | 2.8125 | 2650 | 0.0758 |
110
+ | 0.0862 | 2.8656 | 2700 | 0.0755 |
111
+ | 0.0753 | 2.9186 | 2750 | 0.0750 |
112
+ | 0.0798 | 2.9716 | 2800 | 0.0744 |
113
+ | 0.0762 | 3.0247 | 2850 | 0.0741 |
114
+ | 0.0884 | 3.0777 | 2900 | 0.0736 |
115
+ | 0.0753 | 3.1307 | 2950 | 0.0731 |
116
+ | 0.0774 | 3.1838 | 3000 | 0.0727 |
117
+ | 0.0753 | 3.2368 | 3050 | 0.0725 |
118
+ | 0.0853 | 3.2898 | 3100 | 0.0723 |
119
+ | 0.0723 | 3.3429 | 3150 | 0.0718 |
120
+ | 0.0762 | 3.3959 | 3200 | 0.0713 |
121
+ | 0.0737 | 3.4490 | 3250 | 0.0712 |
122
+ | 0.0751 | 3.5020 | 3300 | 0.0705 |
123
+ | 0.0737 | 3.5550 | 3350 | 0.0700 |
124
+ | 0.069 | 3.6081 | 3400 | 0.0701 |
125
+ | 0.0696 | 3.6611 | 3450 | 0.0697 |
126
+ | 0.0725 | 3.7141 | 3500 | 0.0692 |
127
+ | 0.074 | 3.7672 | 3550 | 0.0686 |
128
+ | 0.0655 | 3.8202 | 3600 | 0.0684 |
129
+ | 0.0671 | 3.8732 | 3650 | 0.0679 |
130
+ | 0.0642 | 3.9263 | 3700 | 0.0676 |
131
+ | 0.07 | 3.9793 | 3750 | 0.0676 |
132
+
133
+
134
+ ### Framework versions
135
+
136
+ - PEFT 0.12.0
137
+ - Transformers 4.44.2
138
+ - Pytorch 2.5.1+cu121
139
+ - Datasets 2.21.0
140
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:400c482eaa5d83907ec0a9f25840b134040238915e29f13518dd66e3a03273ea
3
  size 1600180696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3ab8beda6a1b218a58e0c472258515b4627d9e68adaa52c01f9b2ffc6ff374
3
  size 1600180696
runs/Sep19_11-47-10_m3h111/events.out.tfevents.1758246497.m3h111.612245.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b3cdd5ee0f8203619906c5188cc9f324a1b0a63aa5d16a1683574110ec35593
3
- size 38784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7ccba80522d29fe7632fdfacd305c3444e3967301c64968073f56b63efe6a2
3
+ size 39138