Hugging Face's logo

ahmedabdelwahed
/
test

PEFT
Safetensors
Generated from Trainer
Model card Files Community
ahmedabdelwahed commited on
Commit
7afad9d
•
1 Parent(s): f9e34ac

Mojiz-DPO

Browse files
Files changed (3) hide show
  1. README.md +49 -49
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,15 +16,15 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [ahmedabdelwahed/Mojiz-sft](https://huggingface.co/ahmedabdelwahed/Mojiz-sft) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0004
20
- - Rewards/chosen: 4.9321
21
- - Rewards/rejected: -3.1907
22
  - Rewards/accuracies: 1.0
23
- - Rewards/margins: 8.1228
24
- - Logps/rejected: -102.9468
25
- - Logps/chosen: -276.9925
26
- - Logits/rejected: -11.5352
27
- - Logits/chosen: -12.8189
28
 
29
  ## Model description
30
 
@@ -43,7 +43,7 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 1e-05
47
  - train_batch_size: 4
48
  - eval_batch_size: 8
49
  - seed: 42
@@ -56,46 +56,46 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
59
- | 0.59 | 0.41 | 100 | 0.5689 | 0.2142 | -0.0529 | 1.0 | 0.2670 | -71.5682 | -324.1714 | -11.7019 | -12.9321 |
60
- | 0.3343 | 0.82 | 200 | 0.2046 | 1.1503 | -0.4195 | 1.0 | 1.5698 | -75.2343 | -314.8096 | -11.5589 | -12.6981 |
61
- | 0.1352 | 1.22 | 300 | 0.0544 | 2.1788 | -0.9611 | 1.0 | 3.1399 | -80.6501 | -304.5251 | -11.3938 | -12.4321 |
62
- | 0.0394 | 1.63 | 400 | 0.0235 | 2.7263 | -1.2443 | 1.0 | 3.9706 | -83.4828 | -299.0500 | -11.3316 | -12.3395 |
63
- | 0.0406 | 2.04 | 500 | 0.0129 | 3.0958 | -1.4814 | 1.0 | 4.5771 | -85.8533 | -295.3555 | -11.2949 | -12.2909 |
64
- | 0.0288 | 2.45 | 600 | 0.0085 | 3.3507 | -1.6368 | 1.0 | 4.9875 | -87.4073 | -292.8057 | -11.2931 | -12.2987 |
65
- | 0.0168 | 2.86 | 700 | 0.0058 | 3.5726 | -1.7858 | 1.0 | 5.3584 | -88.8972 | -290.5872 | -11.2839 | -12.2960 |
66
- | 0.0124 | 3.27 | 800 | 0.0044 | 3.7498 | -1.8907 | 1.0 | 5.6405 | -89.9465 | -288.8147 | -11.2953 | -12.3275 |
67
- | 0.0087 | 3.67 | 900 | 0.0035 | 3.8535 | -2.0148 | 1.0 | 5.8684 | -91.1878 | -287.7778 | -11.2906 | -12.3302 |
68
- | 0.007 | 4.08 | 1000 | 0.0029 | 3.9744 | -2.0910 | 1.0 | 6.0654 | -91.9495 | -286.5689 | -11.3025 | -12.3602 |
69
- | 0.0122 | 4.49 | 1100 | 0.0023 | 4.0733 | -2.1965 | 1.0 | 6.2698 | -93.0046 | -285.5799 | -11.3092 | -12.3815 |
70
- | 0.0062 | 4.9 | 1200 | 0.0020 | 4.1431 | -2.2995 | 1.0 | 6.4426 | -94.0349 | -284.8822 | -11.3084 | -12.3870 |
71
- | 0.0113 | 5.31 | 1300 | 0.0017 | 4.2353 | -2.3425 | 1.0 | 6.5778 | -94.4643 | -283.9596 | -11.3304 | -12.4328 |
72
- | 0.0096 | 5.71 | 1400 | 0.0015 | 4.3008 | -2.4035 | 1.0 | 6.7044 | -95.0748 | -283.3046 | -11.3438 | -12.4598 |
73
- | 0.0054 | 6.12 | 1500 | 0.0013 | 4.3515 | -2.4735 | 1.0 | 6.8250 | -95.7742 | -282.7977 | -11.3476 | -12.4711 |
74
- | 0.0127 | 6.53 | 1600 | 0.0012 | 4.4101 | -2.5237 | 1.0 | 6.9338 | -96.2767 | -282.2122 | -11.3609 | -12.4973 |
75
- | 0.0046 | 6.94 | 1700 | 0.0011 | 4.4473 | -2.5927 | 1.0 | 7.0400 | -96.9663 | -281.8404 | -11.3694 | -12.5148 |
76
- | 0.0049 | 7.35 | 1800 | 0.0010 | 4.4882 | -2.6539 | 1.0 | 7.1421 | -97.5784 | -281.4307 | -11.3787 | -12.5361 |
77
- | 0.0039 | 7.76 | 1900 | 0.0009 | 4.5274 | -2.7045 | 1.0 | 7.2319 | -98.0843 | -281.0386 | -11.3905 | -12.5571 |
78
- | 0.0044 | 8.16 | 2000 | 0.0008 | 4.5889 | -2.7282 | 1.0 | 7.3171 | -98.3214 | -280.4241 | -11.4088 | -12.5904 |
79
- | 0.0065 | 8.57 | 2100 | 0.0008 | 4.6306 | -2.7613 | 1.0 | 7.3919 | -98.6527 | -280.0075 | -11.4171 | -12.6086 |
80
- | 0.0033 | 8.98 | 2200 | 0.0007 | 4.6508 | -2.8105 | 1.0 | 7.4613 | -99.1442 | -279.8048 | -11.4214 | -12.6158 |
81
- | 0.0041 | 9.39 | 2300 | 0.0007 | 4.6876 | -2.8441 | 1.0 | 7.5316 | -99.4804 | -279.4375 | -11.4311 | -12.6356 |
82
- | 0.0025 | 9.8 | 2400 | 0.0006 | 4.7079 | -2.8946 | 1.0 | 7.6026 | -99.9857 | -279.2337 | -11.4363 | -12.6466 |
83
- | 0.0113 | 10.2 | 2500 | 0.0006 | 4.7531 | -2.9135 | 1.0 | 7.6665 | -100.1742 | -278.7823 | -11.4524 | -12.6747 |
84
- | 0.004 | 10.61 | 2600 | 0.0006 | 4.7825 | -2.9382 | 1.0 | 7.7207 | -100.4218 | -278.4879 | -11.4644 | -12.6965 |
85
- | 0.0035 | 11.02 | 2700 | 0.0005 | 4.7952 | -2.9793 | 1.0 | 7.7745 | -100.8324 | -278.3613 | -11.4722 | -12.7103 |
86
- | 0.0018 | 11.43 | 2800 | 0.0005 | 4.8215 | -3.0007 | 1.0 | 7.8222 | -101.0460 | -278.0980 | -11.4836 | -12.7306 |
87
- | 0.0036 | 11.84 | 2900 | 0.0005 | 4.8430 | -3.0254 | 1.0 | 7.8684 | -101.2935 | -277.8831 | -11.4928 | -12.7447 |
88
- | 0.0015 | 12.24 | 3000 | 0.0005 | 4.8521 | -3.0583 | 1.0 | 7.9104 | -101.6220 | -277.7916 | -11.4961 | -12.7505 |
89
- | 0.0052 | 12.65 | 3100 | 0.0005 | 4.8654 | -3.0809 | 1.0 | 7.9463 | -101.8486 | -277.6590 | -11.5056 | -12.7670 |
90
- | 0.0022 | 13.06 | 3200 | 0.0005 | 4.8844 | -3.0964 | 1.0 | 7.9807 | -102.0031 | -277.4695 | -11.5118 | -12.7789 |
91
- | 0.002 | 13.47 | 3300 | 0.0004 | 4.8951 | -3.1182 | 1.0 | 8.0133 | -102.2215 | -277.3618 | -11.5162 | -12.7874 |
92
- | 0.0022 | 13.88 | 3400 | 0.0004 | 4.9070 | -3.1334 | 1.0 | 8.0404 | -102.3737 | -277.2430 | -11.5216 | -12.7971 |
93
- | 0.0021 | 14.29 | 3500 | 0.0004 | 4.9110 | -3.1522 | 1.0 | 8.0632 | -102.5618 | -277.2032 | -11.5242 | -12.8018 |
94
- | 0.0016 | 14.69 | 3600 | 0.0004 | 4.9225 | -3.1606 | 1.0 | 8.0831 | -102.6452 | -277.0878 | -11.5305 | -12.8112 |
95
- | 0.0038 | 15.1 | 3700 | 0.0004 | 4.9251 | -3.1769 | 1.0 | 8.1020 | -102.8086 | -277.0620 | -11.5312 | -12.8121 |
96
- | 0.0081 | 15.51 | 3800 | 0.0004 | 4.9290 | -3.1834 | 1.0 | 8.1124 | -102.8736 | -277.0229 | -11.5335 | -12.8159 |
97
- | 0.0021 | 15.92 | 3900 | 0.0004 | 4.9308 | -3.1902 | 1.0 | 8.1210 | -102.9418 | -277.0052 | -11.5346 | -12.8179 |
98
- | 0.0019 | 16.33 | 4000 | 0.0004 | 4.9321 | -3.1907 | 1.0 | 8.1228 | -102.9468 | -276.9925 | -11.5352 | -12.8189 |
99
 
100
 
101
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [ahmedabdelwahed/Mojiz-sft](https://huggingface.co/ahmedabdelwahed/Mojiz-sft) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0000
20
+ - Rewards/chosen: 18.1376
21
+ - Rewards/rejected: -8.6571
22
  - Rewards/accuracies: 1.0
23
+ - Rewards/margins: 26.7947
24
+ - Logps/rejected: -88.3536
25
+ - Logps/chosen: -290.0378
26
+ - Logits/rejected: -11.4716
27
+ - Logits/chosen: -12.5332
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 5e-05
47
  - train_batch_size: 4
48
  - eval_batch_size: 8
49
  - seed: 42
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
59
+ | 0.0793 | 0.41 | 100 | 0.0027 | 5.9377 | -1.9974 | 1.0 | 7.9351 | -75.0342 | -314.4376 | -11.5492 | -12.6810 |
60
+ | 0.0031 | 0.82 | 200 | 0.0000 | 12.4888 | -4.6855 | 1.0 | 17.1744 | -80.4105 | -301.3354 | -11.3597 | -12.3643 |
61
+ | 0.0066 | 1.22 | 300 | 0.0000 | 13.8033 | -5.7242 | 1.0 | 19.5275 | -82.4877 | -298.7064 | -11.3187 | -12.3016 |
62
+ | 0.0 | 1.63 | 400 | 0.0000 | 14.5933 | -6.1262 | 1.0 | 20.7195 | -83.2918 | -297.1264 | -11.3144 | -12.2958 |
63
+ | 0.0001 | 2.04 | 500 | 0.0000 | 15.3023 | -6.5782 | 1.0 | 21.8805 | -84.1958 | -295.7085 | -11.3077 | -12.2893 |
64
+ | 0.0 | 2.45 | 600 | 0.0000 | 15.4711 | -6.6092 | 1.0 | 22.0803 | -84.2578 | -295.3708 | -11.3213 | -12.3081 |
65
+ | 0.0002 | 2.86 | 700 | 0.0000 | 15.6218 | -7.1110 | 1.0 | 22.7329 | -85.2615 | -295.0694 | -11.2976 | -12.2623 |
66
+ | 0.0 | 3.27 | 800 | 0.0000 | 15.9433 | -6.9864 | 1.0 | 22.9296 | -85.0122 | -294.4265 | -11.3403 | -12.3306 |
67
+ | 0.0 | 3.67 | 900 | 0.0000 | 15.9641 | -7.0354 | 1.0 | 22.9995 | -85.1103 | -294.3849 | -11.3391 | -12.3288 |
68
+ | 0.0 | 4.08 | 1000 | 0.0000 | 16.2814 | -7.0358 | 1.0 | 23.3172 | -85.1110 | -293.7502 | -11.3672 | -12.3761 |
69
+ | 0.0 | 4.49 | 1100 | 0.0000 | 16.4334 | -8.0549 | 1.0 | 24.4882 | -87.1492 | -293.4463 | -11.3531 | -12.3479 |
70
+ | 0.0 | 4.9 | 1200 | 0.0000 | 16.4611 | -8.1138 | 1.0 | 24.5749 | -87.2670 | -293.3908 | -11.3526 | -12.3460 |
71
+ | 0.0 | 5.31 | 1300 | 0.0000 | 16.5457 | -8.4467 | 1.0 | 24.9924 | -87.9329 | -293.2217 | -11.3564 | -12.3538 |
72
+ | 0.0 | 5.71 | 1400 | 0.0000 | 16.4919 | -8.8374 | 1.0 | 25.3293 | -88.7142 | -293.3293 | -11.3418 | -12.3282 |
73
+ | 0.0 | 6.12 | 1500 | 0.0000 | 16.5218 | -8.8510 | 1.0 | 25.3728 | -88.7414 | -293.2693 | -11.3406 | -12.3263 |
74
+ | 0.0009 | 6.53 | 1600 | 0.0000 | 16.7250 | -8.7002 | 1.0 | 25.4253 | -88.4399 | -292.8630 | -11.3674 | -12.3683 |
75
+ | 0.0 | 6.94 | 1700 | 0.0000 | 16.8143 | -8.6048 | 1.0 | 25.4192 | -88.2491 | -292.6844 | -11.3801 | -12.3887 |
76
+ | 0.0 | 7.35 | 1800 | 0.0000 | 16.8426 | -8.6228 | 1.0 | 25.4654 | -88.2850 | -292.6279 | -11.3809 | -12.3905 |
77
+ | 0.0 | 7.76 | 1900 | 0.0000 | 16.9276 | -8.6058 | 1.0 | 25.5334 | -88.2511 | -292.4578 | -11.3874 | -12.4012 |
78
+ | 0.0 | 8.16 | 2000 | 0.0000 | 17.0356 | -8.5350 | 1.0 | 25.5706 | -88.1095 | -292.2419 | -11.3966 | -12.4173 |
79
+ | 0.0 | 8.57 | 2100 | 0.0000 | 17.0415 | -8.5369 | 1.0 | 25.5785 | -88.1133 | -292.2300 | -11.3966 | -12.4174 |
80
+ | 0.0 | 8.98 | 2200 | 0.0000 | 17.0721 | -8.5671 | 1.0 | 25.6392 | -88.1736 | -292.1689 | -11.3993 | -12.4190 |
81
+ | 0.0 | 9.39 | 2300 | 0.0000 | 17.1929 | -8.5511 | 1.0 | 25.7440 | -88.1416 | -291.9272 | -11.4026 | -12.4260 |
82
+ | 0.0 | 9.8 | 2400 | 0.0000 | 17.2047 | -8.5698 | 1.0 | 25.7745 | -88.1790 | -291.9037 | -11.4023 | -12.4256 |
83
+ | 0.0001 | 10.2 | 2500 | 0.0000 | 17.2634 | -8.5804 | 1.0 | 25.8438 | -88.2003 | -291.7863 | -11.4056 | -12.4297 |
84
+ | 0.0 | 10.61 | 2600 | 0.0000 | 17.3959 | -8.6113 | 1.0 | 26.0073 | -88.2621 | -291.5212 | -11.4172 | -12.4483 |
85
+ | 0.0 | 11.02 | 2700 | 0.0000 | 17.4088 | -8.6090 | 1.0 | 26.0179 | -88.2575 | -291.4955 | -11.4184 | -12.4501 |
86
+ | 0.0 | 11.43 | 2800 | 0.0000 | 17.6812 | -8.5388 | 1.0 | 26.2200 | -88.1171 | -290.9506 | -11.4438 | -12.4857 |
87
+ | 0.0 | 11.84 | 2900 | 0.0000 | 17.7586 | -8.5575 | 1.0 | 26.3160 | -88.1544 | -290.7959 | -11.4495 | -12.4933 |
88
+ | 0.0 | 12.24 | 3000 | 0.0000 | 17.7675 | -8.5658 | 1.0 | 26.3332 | -88.1710 | -290.7781 | -11.4490 | -12.4925 |
89
+ | 0.0 | 12.65 | 3100 | 0.0000 | 17.7702 | -8.5654 | 1.0 | 26.3356 | -88.1702 | -290.7726 | -11.4495 | -12.4934 |
90
+ | 0.0 | 13.06 | 3200 | 0.0000 | 17.8009 | -8.5986 | 1.0 | 26.3995 | -88.2367 | -290.7113 | -11.4487 | -12.4922 |
91
+ | 0.0 | 13.47 | 3300 | 0.0000 | 17.8118 | -8.6182 | 1.0 | 26.4300 | -88.2759 | -290.6895 | -11.4489 | -12.4933 |
92
+ | 0.0 | 13.88 | 3400 | 0.0000 | 17.8154 | -8.6331 | 1.0 | 26.4485 | -88.3056 | -290.6822 | -11.4487 | -12.4930 |
93
+ | 0.0 | 14.29 | 3500 | 0.0000 | 17.8165 | -8.6345 | 1.0 | 26.4510 | -88.3085 | -290.6801 | -11.4488 | -12.4931 |
94
+ | 0.0 | 14.69 | 3600 | 0.0000 | 18.0311 | -8.5841 | 1.0 | 26.6152 | -88.2077 | -290.2509 | -11.4667 | -12.5224 |
95
+ | 0.0 | 15.1 | 3700 | 0.0000 | 18.0300 | -8.6313 | 1.0 | 26.6613 | -88.3020 | -290.2531 | -11.4650 | -12.5197 |
96
+ | 0.0 | 15.51 | 3800 | 0.0000 | 18.1087 | -8.6370 | 1.0 | 26.7457 | -88.3134 | -290.0956 | -11.4700 | -12.5305 |
97
+ | 0.0 | 15.92 | 3900 | 0.0000 | 18.1106 | -8.6368 | 1.0 | 26.7474 | -88.3131 | -290.0919 | -11.4703 | -12.5310 |
98
+ | 0.0 | 16.33 | 4000 | 0.0000 | 18.1376 | -8.6571 | 1.0 | 26.7947 | -88.3536 | -290.0378 | -11.4716 | -12.5332 |
99
 
100
 
101
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09c93cde8d603a402fda75b4363133ffe9e4c0f00a9551dc44e0b2122defc5e0
3
  size 7098016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9488d551fa99fb91dec195b1fb79c0a88b24857f90330aa4da281903928bf1
3
  size 7098016
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45e6cca049c1171e8b1d7d66a8d26679592eab903e1955b3bd2a4e366dc7e8ea
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f79a5065d57ef43787c2705bee7638f114c3433715cabbaed6077efb3d31a4
3
  size 4219