Hugging Face's logo

thorirhrafn
/
llama_DPO_model_e2

PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
Model card Files Metrics Community
thorirhrafn commited on
Commit
e2ce8fb
•
1 Parent(s): 27a95c7

End of training

Browse files
Files changed (1) hide show
  1. README.md +30 -40
README.md CHANGED
@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1001
22
- - Rewards/chosen: 0.4226
23
- - Rewards/rejected: -1.9804
24
  - Rewards/accuracies: 1.0
25
- - Rewards/margins: 2.4030
26
- - Logps/rejected: -204.6132
27
- - Logps/chosen: -156.4080
28
- - Logits/rejected: -1.0519
29
- - Logits/chosen: -0.8585
30
 
31
  ## Model description
32
 
@@ -45,7 +45,7 @@ More information needed
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
- - learning_rate: 6e-07
49
  - train_batch_size: 1
50
  - eval_batch_size: 1
51
  - seed: 42
@@ -53,42 +53,32 @@ The following hyperparameters were used during training:
53
  - total_train_batch_size: 8
54
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
  - lr_scheduler_type: linear
56
- - num_epochs: 3
57
 
58
  ### Training results
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
62
- | 0.6757 | 0.1 | 25 | 0.6650 | 0.0149 | -0.0435 | 0.7767 | 0.0584 | -185.2444 | -160.4850 | -1.0519 | -0.8543 |
63
- | 0.6136 | 0.2 | 50 | 0.5989 | 0.0552 | -0.1462 | 0.9567 | 0.2014 | -186.2718 | -160.0822 | -1.0523 | -0.8553 |
64
- | 0.5526 | 0.3 | 75 | 0.5225 | 0.1032 | -0.2804 | 1.0 | 0.3837 | -187.6138 | -159.6014 | -1.0520 | -0.8542 |
65
- | 0.4819 | 0.4 | 100 | 0.4502 | 0.1474 | -0.4325 | 0.9967 | 0.5798 | -189.1341 | -159.1602 | -1.0518 | -0.8548 |
66
- | 0.4253 | 0.5 | 125 | 0.3835 | 0.1905 | -0.5943 | 1.0 | 0.7848 | -190.7523 | -158.7284 | -1.0527 | -0.8564 |
67
- | 0.3448 | 0.6 | 150 | 0.3197 | 0.2328 | -0.7813 | 1.0 | 1.0141 | -192.6229 | -158.3063 | -1.0526 | -0.8559 |
68
- | 0.3007 | 0.7 | 175 | 0.2637 | 0.2788 | -0.9753 | 1.0 | 1.2542 | -194.5630 | -157.8456 | -1.0525 | -0.8586 |
69
- | 0.2369 | 0.79 | 200 | 0.2192 | 0.3135 | -1.1671 | 1.0 | 1.4807 | -196.4808 | -157.4985 | -1.0519 | -0.8604 |
70
- | 0.1987 | 0.89 | 225 | 0.1825 | 0.3436 | -1.3550 | 1.0 | 1.6986 | -198.3592 | -157.1976 | -1.0520 | -0.8594 |
71
- | 0.1616 | 0.99 | 250 | 0.1532 | 0.3687 | -1.5379 | 1.0 | 1.9066 | -200.1886 | -156.9470 | -1.0519 | -0.8604 |
72
- | 0.1525 | 1.09 | 275 | 0.1346 | 0.3861 | -1.6703 | 1.0 | 2.0564 | -201.5127 | -156.7730 | -1.0511 | -0.8582 |
73
- | 0.1194 | 1.19 | 300 | 0.1246 | 0.3970 | -1.7483 | 1.0 | 2.1453 | -202.2923 | -156.6637 | -1.0509 | -0.8584 |
74
- | 0.1128 | 1.29 | 325 | 0.1161 | 0.4062 | -1.8227 | 1.0 | 2.2289 | -203.0370 | -156.5718 | -1.0511 | -0.8577 |
75
- | 0.1194 | 1.39 | 350 | 0.1108 | 0.4127 | -1.8680 | 1.0 | 2.2807 | -203.4899 | -156.5069 | -1.0514 | -0.8602 |
76
- | 0.1123 | 1.49 | 375 | 0.1070 | 0.4151 | -1.9092 | 1.0 | 2.3243 | -203.9014 | -156.4828 | -1.0515 | -0.8584 |
77
- | 0.1008 | 1.59 | 400 | 0.1046 | 0.4209 | -1.9290 | 1.0 | 2.3499 | -204.0999 | -156.4248 | -1.0516 | -0.8618 |
78
- | 0.0971 | 1.69 | 425 | 0.1033 | 0.4208 | -1.9461 | 1.0 | 2.3669 | -204.2709 | -156.4260 | -1.0510 | -0.8586 |
79
- | 0.109 | 1.79 | 450 | 0.1019 | 0.4235 | -1.9597 | 1.0 | 2.3832 | -204.4061 | -156.3985 | -1.0510 | -0.8587 |
80
- | 0.1035 | 1.89 | 475 | 0.1009 | 0.4234 | -1.9700 | 1.0 | 2.3934 | -204.5094 | -156.4001 | -1.0517 | -0.8580 |
81
- | 0.1046 | 1.99 | 500 | 0.1004 | 0.4210 | -1.9772 | 1.0 | 2.3983 | -204.5820 | -156.4234 | -1.0511 | -0.8603 |
82
- | 0.0961 | 2.09 | 525 | 0.1002 | 0.4227 | -1.9798 | 1.0 | 2.4025 | -204.6080 | -156.4070 | -1.0518 | -0.8587 |
83
- | 0.0932 | 2.19 | 550 | 0.1000 | 0.4237 | -1.9796 | 1.0 | 2.4033 | -204.6052 | -156.3964 | -1.0518 | -0.8597 |
84
- | 0.0901 | 2.29 | 575 | 0.1002 | 0.4231 | -1.9785 | 1.0 | 2.4015 | -204.5942 | -156.4030 | -1.0514 | -0.8594 |
85
- | 0.1033 | 2.38 | 600 | 0.1003 | 0.4248 | -1.9780 | 1.0 | 2.4028 | -204.5901 | -156.3859 | -1.0517 | -0.8616 |
86
- | 0.1108 | 2.48 | 625 | 0.0999 | 0.4262 | -1.9796 | 1.0 | 2.4057 | -204.6053 | -156.3723 | -1.0517 | -0.8583 |
87
- | 0.1026 | 2.58 | 650 | 0.0998 | 0.4208 | -1.9879 | 1.0 | 2.4088 | -204.6889 | -156.4255 | -1.0522 | -0.8594 |
88
- | 0.0956 | 2.68 | 675 | 0.1001 | 0.4227 | -1.9818 | 1.0 | 2.4045 | -204.6279 | -156.4070 | -1.0517 | -0.8588 |
89
- | 0.1003 | 2.78 | 700 | 0.0996 | 0.4241 | -1.9817 | 1.0 | 2.4058 | -204.6262 | -156.3926 | -1.0516 | -0.8584 |
90
- | 0.0874 | 2.88 | 725 | 0.0997 | 0.4228 | -1.9835 | 1.0 | 2.4064 | -204.6450 | -156.4057 | -1.0519 | -0.8609 |
91
- | 0.1001 | 2.98 | 750 | 0.1001 | 0.4226 | -1.9804 | 1.0 | 2.4030 | -204.6132 | -156.4080 | -1.0519 | -0.8585 |
92
 
93
 
94
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0896
22
+ - Rewards/chosen: 0.4401
23
+ - Rewards/rejected: -2.0930
24
  - Rewards/accuracies: 1.0
25
+ - Rewards/margins: 2.5330
26
+ - Logps/rejected: -205.7391
27
+ - Logps/chosen: -156.2334
28
+ - Logits/rejected: -1.0514
29
+ - Logits/chosen: -0.8587
30
 
31
  ## Model description
32
 
 
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
+ - learning_rate: 8e-07
49
  - train_batch_size: 1
50
  - eval_batch_size: 1
51
  - seed: 42
 
53
  - total_train_batch_size: 8
54
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
  - lr_scheduler_type: linear
56
+ - num_epochs: 2
57
 
58
  ### Training results
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
62
+ | 0.6699 | 0.1 | 25 | 0.6428 | 0.0307 | -0.0744 | 0.9033 | 0.1051 | -185.5532 | -160.3267 | -1.0520 | -0.8550 |
63
+ | 0.5702 | 0.2 | 50 | 0.5471 | 0.0866 | -0.2359 | 0.9933 | 0.3225 | -187.1690 | -159.7680 | -1.0514 | -0.8544 |
64
+ | 0.488 | 0.3 | 75 | 0.4456 | 0.1502 | -0.4424 | 1.0 | 0.5926 | -189.2334 | -159.1314 | -1.0527 | -0.8555 |
65
+ | 0.3957 | 0.4 | 100 | 0.3600 | 0.2054 | -0.6615 | 1.0 | 0.8669 | -191.4245 | -158.5795 | -1.0530 | -0.8577 |
66
+ | 0.3338 | 0.5 | 125 | 0.2865 | 0.2569 | -0.8933 | 1.0 | 1.1502 | -193.7425 | -158.0646 | -1.0524 | -0.8564 |
67
+ | 0.253 | 0.6 | 150 | 0.2257 | 0.3043 | -1.1373 | 1.0 | 1.4416 | -196.1830 | -157.5914 | -1.0523 | -0.8570 |
68
+ | 0.2134 | 0.7 | 175 | 0.1819 | 0.3496 | -1.3537 | 1.0 | 1.7033 | -198.3466 | -157.1379 | -1.0530 | -0.8584 |
69
+ | 0.1613 | 0.79 | 200 | 0.1473 | 0.3842 | -1.5693 | 1.0 | 1.9535 | -200.5027 | -156.7917 | -1.0525 | -0.8591 |
70
+ | 0.1358 | 0.89 | 225 | 0.1231 | 0.4031 | -1.7582 | 1.0 | 2.1614 | -202.3919 | -156.6024 | -1.0523 | -0.8593 |
71
+ | 0.115 | 0.99 | 250 | 0.1076 | 0.4205 | -1.8980 | 1.0 | 2.3185 | -203.7897 | -156.4292 | -1.0521 | -0.8590 |
72
+ | 0.1111 | 1.09 | 275 | 0.0989 | 0.4291 | -1.9856 | 1.0 | 2.4148 | -204.6660 | -156.3426 | -1.0515 | -0.8591 |
73
+ | 0.0902 | 1.19 | 300 | 0.0949 | 0.4280 | -2.0337 | 1.0 | 2.4617 | -205.1465 | -156.3540 | -1.0507 | -0.8576 |
74
+ | 0.0867 | 1.29 | 325 | 0.0920 | 0.4325 | -2.0705 | 1.0 | 2.5030 | -205.5146 | -156.3087 | -1.0510 | -0.8576 |
75
+ | 0.0973 | 1.39 | 350 | 0.0905 | 0.4357 | -2.0839 | 1.0 | 2.5196 | -205.6485 | -156.2766 | -1.0506 | -0.8576 |
76
+ | 0.0942 | 1.49 | 375 | 0.0897 | 0.4422 | -2.0838 | 1.0 | 2.5260 | -205.6476 | -156.2122 | -1.0515 | -0.8578 |
77
+ | 0.0858 | 1.59 | 400 | 0.0897 | 0.4392 | -2.0903 | 1.0 | 2.5295 | -205.7121 | -156.2415 | -1.0515 | -0.8587 |
78
+ | 0.083 | 1.69 | 425 | 0.0893 | 0.4401 | -2.0972 | 1.0 | 2.5373 | -205.7811 | -156.2327 | -1.0511 | -0.8584 |
79
+ | 0.0964 | 1.79 | 450 | 0.0897 | 0.4368 | -2.0947 | 1.0 | 2.5315 | -205.7564 | -156.2662 | -1.0511 | -0.8577 |
80
+ | 0.0931 | 1.89 | 475 | 0.0890 | 0.4406 | -2.0970 | 1.0 | 2.5376 | -205.7794 | -156.2282 | -1.0512 | -0.8585 |
81
+ | 0.0915 | 1.99 | 500 | 0.0896 | 0.4401 | -2.0930 | 1.0 | 2.5330 | -205.7391 | -156.2334 | -1.0514 | -0.8587 |
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions