Hugging Face's logo

dcaisc
/
qwen2-7b-instruct-trl-sft-ChartQA

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Community
dcaisc commited on
Commit
26ef55b
·
verified ·
1 Parent(s): 5e56a41

Model save

Browse files
Files changed (2) hide show
  1. README.md +89 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2-VL-2B-Instruct
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: qwen2-7b-instruct-trl-sft-ChartQA
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
+ # qwen2-7b-instruct-trl-sft-ChartQA
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2406
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: 0.0002
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 32
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: constant
48
+ - lr_scheduler_warmup_ratio: 0.03
49
+ - num_epochs: 3
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 2.8769 | 0.1130 | 10 | 2.3660 |
56
+ | 2.0843 | 0.2260 | 20 | 1.5363 |
57
+ | 1.1442 | 0.3390 | 30 | 0.6542 |
58
+ | 0.5756 | 0.4520 | 40 | 0.4312 |
59
+ | 0.4821 | 0.5650 | 50 | 0.4034 |
60
+ | 0.4743 | 0.6780 | 60 | 0.3902 |
61
+ | 0.4445 | 0.7910 | 70 | 0.3732 |
62
+ | 0.4353 | 0.9040 | 80 | 0.3488 |
63
+ | 0.3692 | 1.0113 | 90 | 0.2830 |
64
+ | 0.3362 | 1.1243 | 100 | 0.2695 |
65
+ | 0.3219 | 1.2373 | 110 | 0.2662 |
66
+ | 0.3257 | 1.3503 | 120 | 0.2613 |
67
+ | 0.3012 | 1.4633 | 130 | 0.2603 |
68
+ | 0.3132 | 1.5763 | 140 | 0.2568 |
69
+ | 0.3054 | 1.6893 | 150 | 0.2548 |
70
+ | 0.3119 | 1.8023 | 160 | 0.2528 |
71
+ | 0.2956 | 1.9153 | 170 | 0.2507 |
72
+ | 0.2989 | 2.0226 | 180 | 0.2500 |
73
+ | 0.3087 | 2.1356 | 190 | 0.2476 |
74
+ | 0.2943 | 2.2486 | 200 | 0.2481 |
75
+ | 0.3064 | 2.3616 | 210 | 0.2453 |
76
+ | 0.2896 | 2.4746 | 220 | 0.2438 |
77
+ | 0.2825 | 2.5876 | 230 | 0.2435 |
78
+ | 0.2817 | 2.7006 | 240 | 0.2400 |
79
+ | 0.2758 | 2.8136 | 250 | 0.2401 |
80
+ | 0.2775 | 2.9266 | 260 | 0.2406 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - PEFT 0.15.2
86
+ - Transformers 4.51.3
87
+ - Pytorch 2.6.0+cu124
88
+ - Datasets 3.2.0
89
+ - Tokenizers 0.21.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a463c60fd30c3dfe6841bff0d8e883bb3a479b3efb4f6f16df0e8adf6c76dd68
3
  size 4372840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7c54fe33b73519610c1143c0d4d4fdb4b0db211d0ee6f1f179801d0d933b88
3
  size 4372840