Hugging Face's logo

Zacktree
/
code-bench-CodeGemma-7B-cg-nv9n_zs

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Zacktree commited on
Commit
80cf434
·
verified ·
1 Parent(s): 448dddc

Model save

Browse files
Files changed (3) hide show
  1. README.md +159 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Sep19_23-10-55_m3h111/events.out.tfevents.1758288046.m3h111.2330492.0 +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-cg-nv9n_zs
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_zs
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: 0.0352
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
+ | 0.6222 | 0.0530 | 50 | 0.5965 |
58
+ | 0.4468 | 0.1061 | 100 | 0.4544 |
59
+ | 0.3745 | 0.1591 | 150 | 0.3239 |
60
+ | 0.2795 | 0.2121 | 200 | 0.2315 |
61
+ | 0.1976 | 0.2652 | 250 | 0.1633 |
62
+ | 0.1415 | 0.3182 | 300 | 0.1274 |
63
+ | 0.1071 | 0.3713 | 350 | 0.0852 |
64
+ | 0.0845 | 0.4243 | 400 | 0.0698 |
65
+ | 0.0724 | 0.4773 | 450 | 0.0610 |
66
+ | 0.0716 | 0.5304 | 500 | 0.0574 |
67
+ | 0.0745 | 0.5834 | 550 | 0.0501 |
68
+ | 0.0618 | 0.6364 | 600 | 0.0507 |
69
+ | 0.0602 | 0.6895 | 650 | 0.0494 |
70
+ | 0.0646 | 0.7425 | 700 | 0.0480 |
71
+ | 0.0554 | 0.7955 | 750 | 0.0471 |
72
+ | 0.0506 | 0.8486 | 800 | 0.0450 |
73
+ | 0.0591 | 0.9016 | 850 | 0.0445 |
74
+ | 0.0498 | 0.9547 | 900 | 0.0440 |
75
+ | 0.0457 | 1.0077 | 950 | 0.0430 |
76
+ | 0.0484 | 1.0607 | 1000 | 0.0425 |
77
+ | 0.0434 | 1.1138 | 1050 | 0.0416 |
78
+ | 0.0473 | 1.1668 | 1100 | 0.0416 |
79
+ | 0.0512 | 1.2198 | 1150 | 0.0424 |
80
+ | 0.0521 | 1.2729 | 1200 | 0.0410 |
81
+ | 0.0526 | 1.3259 | 1250 | 0.0407 |
82
+ | 0.0393 | 1.3789 | 1300 | 0.0409 |
83
+ | 0.041 | 1.4320 | 1350 | 0.0399 |
84
+ | 0.0505 | 1.4850 | 1400 | 0.0405 |
85
+ | 0.0495 | 1.5381 | 1450 | 0.0399 |
86
+ | 0.0454 | 1.5911 | 1500 | 0.0392 |
87
+ | 0.0428 | 1.6441 | 1550 | 0.0393 |
88
+ | 0.045 | 1.6972 | 1600 | 0.0386 |
89
+ | 0.046 | 1.7502 | 1650 | 0.0383 |
90
+ | 0.0436 | 1.8032 | 1700 | 0.0383 |
91
+ | 0.0445 | 1.8563 | 1750 | 0.0386 |
92
+ | 0.0414 | 1.9093 | 1800 | 0.0382 |
93
+ | 0.05 | 1.9623 | 1850 | 0.0385 |
94
+ | 0.0444 | 2.0154 | 1900 | 0.0382 |
95
+ | 0.0422 | 2.0684 | 1950 | 0.0382 |
96
+ | 0.0494 | 2.1215 | 2000 | 0.0381 |
97
+ | 0.0408 | 2.1745 | 2050 | 0.0378 |
98
+ | 0.0394 | 2.2275 | 2100 | 0.0379 |
99
+ | 0.0392 | 2.2806 | 2150 | 0.0372 |
100
+ | 0.0356 | 2.3336 | 2200 | 0.0375 |
101
+ | 0.0448 | 2.3866 | 2250 | 0.0371 |
102
+ | 0.0477 | 2.4397 | 2300 | 0.0369 |
103
+ | 0.0404 | 2.4927 | 2350 | 0.0369 |
104
+ | 0.0378 | 2.5457 | 2400 | 0.0367 |
105
+ | 0.0448 | 2.5988 | 2450 | 0.0367 |
106
+ | 0.0408 | 2.6518 | 2500 | 0.0364 |
107
+ | 0.0419 | 2.7049 | 2550 | 0.0363 |
108
+ | 0.0431 | 2.7579 | 2600 | 0.0365 |
109
+ | 0.042 | 2.8109 | 2650 | 0.0363 |
110
+ | 0.0398 | 2.8640 | 2700 | 0.0362 |
111
+ | 0.033 | 2.9170 | 2750 | 0.0360 |
112
+ | 0.0447 | 2.9700 | 2800 | 0.0359 |
113
+ | 0.0402 | 3.0231 | 2850 | 0.0360 |
114
+ | 0.0433 | 3.0761 | 2900 | 0.0359 |
115
+ | 0.0342 | 3.1291 | 2950 | 0.0363 |
116
+ | 0.0404 | 3.1822 | 3000 | 0.0360 |
117
+ | 0.0365 | 3.2352 | 3050 | 0.0357 |
118
+ | 0.0374 | 3.2883 | 3100 | 0.0357 |
119
+ | 0.0363 | 3.3413 | 3150 | 0.0358 |
120
+ | 0.0378 | 3.3943 | 3200 | 0.0357 |
121
+ | 0.0376 | 3.4474 | 3250 | 0.0356 |
122
+ | 0.0347 | 3.5004 | 3300 | 0.0355 |
123
+ | 0.0391 | 3.5534 | 3350 | 0.0353 |
124
+ | 0.0306 | 3.6065 | 3400 | 0.0353 |
125
+ | 0.0351 | 3.6595 | 3450 | 0.0353 |
126
+ | 0.0349 | 3.7125 | 3500 | 0.0354 |
127
+ | 0.0399 | 3.7656 | 3550 | 0.0354 |
128
+ | 0.033 | 3.8186 | 3600 | 0.0352 |
129
+ | 0.0304 | 3.8717 | 3650 | 0.0352 |
130
+ | 0.0322 | 3.9247 | 3700 | 0.0354 |
131
+ | 0.0362 | 3.9777 | 3750 | 0.0350 |
132
+ | 0.0346 | 4.0308 | 3800 | 0.0352 |
133
+ | 0.0292 | 4.0838 | 3850 | 0.0353 |
134
+ | 0.0294 | 4.1368 | 3900 | 0.0354 |
135
+ | 0.0318 | 4.1899 | 3950 | 0.0354 |
136
+ | 0.0357 | 4.2429 | 4000 | 0.0351 |
137
+ | 0.0325 | 4.2959 | 4050 | 0.0352 |
138
+ | 0.0337 | 4.3490 | 4100 | 0.0352 |
139
+ | 0.0346 | 4.4020 | 4150 | 0.0353 |
140
+ | 0.0341 | 4.4551 | 4200 | 0.0352 |
141
+ | 0.0347 | 4.5081 | 4250 | 0.0353 |
142
+ | 0.0343 | 4.5611 | 4300 | 0.0352 |
143
+ | 0.0339 | 4.6142 | 4350 | 0.0352 |
144
+ | 0.0358 | 4.6672 | 4400 | 0.0352 |
145
+ | 0.0312 | 4.7234 | 4450 | 0.0352 |
146
+ | 0.0355 | 4.7765 | 4500 | 0.0351 |
147
+ | 0.0292 | 4.8295 | 4550 | 0.0351 |
148
+ | 0.0365 | 4.8825 | 4600 | 0.0352 |
149
+ | 0.036 | 4.9356 | 4650 | 0.0352 |
150
+ | 0.0319 | 4.9886 | 4700 | 0.0352 |
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:e0afb997cebfb3e1702b1602a203a12656418df32d960581bb9f18a8c87ca237
3
  size 1600180696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e5c841aaa57be614fc2f3be80758d34d3856713fd7dcf266e7e049c5839a4c
3
  size 1600180696
runs/Sep19_23-10-55_m3h111/events.out.tfevents.1758288046.m3h111.2330492.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1b181ef87ba6faa163f78d435eaca5e9b3d8f9af630086894c77c2cc60605c1
3
- size 13388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406e8c20405cba8a25b2ebb6a110f935685764cc936b738fa6e42658de39abf6
3
+ size 13953