Hugging Face's logo

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

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
Mobarakol commited on
Commit
dc039d7
·
verified ·
1 Parent(s): 74c479a

Model save

Browse files
Files changed (2) hide show
  1. README.md +168 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2-VL-7B-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-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2465
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: 1
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 8
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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
+ | 2.6558 | 0.0283 | 10 | 2.1357 |
56
+ | 1.6719 | 0.0565 | 20 | 1.0837 |
57
+ | 0.7281 | 0.0848 | 30 | 0.4616 |
58
+ | 0.4803 | 0.1131 | 40 | 0.4224 |
59
+ | 0.4368 | 0.1413 | 50 | 0.3542 |
60
+ | 0.3313 | 0.1696 | 60 | 0.3046 |
61
+ | 0.317 | 0.1979 | 70 | 0.2986 |
62
+ | 0.3106 | 0.2261 | 80 | 0.2907 |
63
+ | 0.3115 | 0.2544 | 90 | 0.2879 |
64
+ | 0.3236 | 0.2827 | 100 | 0.2806 |
65
+ | 0.2803 | 0.3110 | 110 | 0.2726 |
66
+ | 0.3057 | 0.3392 | 120 | 0.2768 |
67
+ | 0.2897 | 0.3675 | 130 | 0.2780 |
68
+ | 0.2772 | 0.3958 | 140 | 0.2755 |
69
+ | 0.312 | 0.4240 | 150 | 0.2696 |
70
+ | 0.2554 | 0.4523 | 160 | 0.2674 |
71
+ | 0.2885 | 0.4806 | 170 | 0.2714 |
72
+ | 0.2831 | 0.5088 | 180 | 0.2699 |
73
+ | 0.2689 | 0.5371 | 190 | 0.2616 |
74
+ | 0.2819 | 0.5654 | 200 | 0.2607 |
75
+ | 0.2818 | 0.5936 | 210 | 0.2673 |
76
+ | 0.2931 | 0.6219 | 220 | 0.2595 |
77
+ | 0.2604 | 0.6502 | 230 | 0.2594 |
78
+ | 0.3043 | 0.6784 | 240 | 0.2561 |
79
+ | 0.2815 | 0.7067 | 250 | 0.2547 |
80
+ | 0.2914 | 0.7350 | 260 | 0.2552 |
81
+ | 0.2523 | 0.7633 | 270 | 0.2534 |
82
+ | 0.2589 | 0.7915 | 280 | 0.2540 |
83
+ | 0.2654 | 0.8198 | 290 | 0.2519 |
84
+ | 0.2917 | 0.8481 | 300 | 0.2490 |
85
+ | 0.2759 | 0.8763 | 310 | 0.2498 |
86
+ | 0.2766 | 0.9046 | 320 | 0.2474 |
87
+ | 0.2502 | 0.9329 | 330 | 0.2476 |
88
+ | 0.2738 | 0.9611 | 340 | 0.2462 |
89
+ | 0.2806 | 0.9894 | 350 | 0.2453 |
90
+ | 0.2648 | 1.0177 | 360 | 0.2465 |
91
+ | 0.2659 | 1.0459 | 370 | 0.2448 |
92
+ | 0.247 | 1.0742 | 380 | 0.2450 |
93
+ | 0.2692 | 1.1025 | 390 | 0.2488 |
94
+ | 0.2565 | 1.1307 | 400 | 0.2483 |
95
+ | 0.2264 | 1.1590 | 410 | 0.2470 |
96
+ | 0.2647 | 1.1873 | 420 | 0.2461 |
97
+ | 0.2438 | 1.2155 | 430 | 0.2485 |
98
+ | 0.2421 | 1.2438 | 440 | 0.2448 |
99
+ | 0.2693 | 1.2721 | 450 | 0.2432 |
100
+ | 0.262 | 1.3004 | 460 | 0.2426 |
101
+ | 0.2659 | 1.3286 | 470 | 0.2437 |
102
+ | 0.2375 | 1.3569 | 480 | 0.2479 |
103
+ | 0.2312 | 1.3852 | 490 | 0.2523 |
104
+ | 0.2503 | 1.4134 | 500 | 0.2511 |
105
+ | 0.2377 | 1.4417 | 510 | 0.2464 |
106
+ | 0.2385 | 1.4700 | 520 | 0.2432 |
107
+ | 0.2462 | 1.4982 | 530 | 0.2436 |
108
+ | 0.2462 | 1.5265 | 540 | 0.2464 |
109
+ | 0.2766 | 1.5548 | 550 | 0.2488 |
110
+ | 0.2407 | 1.5830 | 560 | 0.2474 |
111
+ | 0.2505 | 1.6113 | 570 | 0.2442 |
112
+ | 0.2291 | 1.6396 | 580 | 0.2456 |
113
+ | 0.244 | 1.6678 | 590 | 0.2444 |
114
+ | 0.2355 | 1.6961 | 600 | 0.2446 |
115
+ | 0.2458 | 1.7244 | 610 | 0.2452 |
116
+ | 0.2478 | 1.7527 | 620 | 0.2451 |
117
+ | 0.2687 | 1.7809 | 630 | 0.2450 |
118
+ | 0.2397 | 1.8092 | 640 | 0.2478 |
119
+ | 0.2436 | 1.8375 | 650 | 0.2478 |
120
+ | 0.2293 | 1.8657 | 660 | 0.2489 |
121
+ | 0.2341 | 1.8940 | 670 | 0.2476 |
122
+ | 0.2252 | 1.9223 | 680 | 0.2476 |
123
+ | 0.2505 | 1.9505 | 690 | 0.2522 |
124
+ | 0.2647 | 1.9788 | 700 | 0.2517 |
125
+ | 0.2428 | 2.0071 | 710 | 0.2495 |
126
+ | 0.2261 | 2.0353 | 720 | 0.2476 |
127
+ | 0.2466 | 2.0636 | 730 | 0.2460 |
128
+ | 0.222 | 2.0919 | 740 | 0.2453 |
129
+ | 0.2382 | 2.1201 | 750 | 0.2460 |
130
+ | 0.2122 | 2.1484 | 760 | 0.2473 |
131
+ | 0.2202 | 2.1767 | 770 | 0.2517 |
132
+ | 0.2157 | 2.2049 | 780 | 0.2495 |
133
+ | 0.2425 | 2.2332 | 790 | 0.2474 |
134
+ | 0.2547 | 2.2615 | 800 | 0.2477 |
135
+ | 0.2425 | 2.2898 | 810 | 0.2488 |
136
+ | 0.2337 | 2.3180 | 820 | 0.2497 |
137
+ | 0.2201 | 2.3463 | 830 | 0.2487 |
138
+ | 0.2251 | 2.3746 | 840 | 0.2467 |
139
+ | 0.2028 | 2.4028 | 850 | 0.2463 |
140
+ | 0.2221 | 2.4311 | 860 | 0.2480 |
141
+ | 0.2193 | 2.4594 | 870 | 0.2517 |
142
+ | 0.2076 | 2.4876 | 880 | 0.2595 |
143
+ | 0.2201 | 2.5159 | 890 | 0.2552 |
144
+ | 0.2303 | 2.5442 | 900 | 0.2536 |
145
+ | 0.2156 | 2.5724 | 910 | 0.2509 |
146
+ | 0.216 | 2.6007 | 920 | 0.2501 |
147
+ | 0.2084 | 2.6290 | 930 | 0.2516 |
148
+ | 0.2157 | 2.6572 | 940 | 0.2448 |
149
+ | 0.2214 | 2.6855 | 950 | 0.2450 |
150
+ | 0.2237 | 2.7138 | 960 | 0.2456 |
151
+ | 0.2041 | 2.7420 | 970 | 0.2501 |
152
+ | 0.1986 | 2.7703 | 980 | 0.2537 |
153
+ | 0.2238 | 2.7986 | 990 | 0.2531 |
154
+ | 0.2178 | 2.8269 | 1000 | 0.2512 |
155
+ | 0.2172 | 2.8551 | 1010 | 0.2477 |
156
+ | 0.2221 | 2.8834 | 1020 | 0.2554 |
157
+ | 0.2212 | 2.9117 | 1030 | 0.2497 |
158
+ | 0.2039 | 2.9399 | 1040 | 0.2478 |
159
+ | 0.2266 | 2.9682 | 1050 | 0.2465 |
160
+
161
+
162
+ ### Framework versions
163
+
164
+ - PEFT 0.13.0
165
+ - Transformers 4.45.1
166
+ - Pytorch 2.4.0+cu121
167
+ - Datasets 3.0.1
168
+ - Tokenizers 0.20.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96c9a12de573053d4a1819d8129f697b70507949988339e902a821fbf5ddce6c
3
  size 10107280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f492faf98a4f737df0290914b0e8b4ddd2cbd83714c5a0c151586a7dda0e19ce
3
  size 10107280