imdatta0 commited on
Commit
550fe9f
1 Parent(s): a54de25

qwen-rep-OpenAssistant/oasst_top1_2023-08-25

Browse files
Files changed (2) hide show
  1. README.md +57 -57
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [Qwen/Qwen-14B](https://huggingface.co/Qwen/Qwen-14B) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.7369
18
 
19
  ## Model description
20
 
@@ -33,11 +33,11 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 1e-05
37
- - train_batch_size: 2
38
- - eval_batch_size: 2
39
  - seed: 42
40
- - gradient_accumulation_steps: 8
41
  - total_train_batch_size: 16
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
@@ -48,59 +48,59 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 1.8582 | 0.02 | 16 | 1.9962 |
52
- | 1.8358 | 0.04 | 32 | 1.9933 |
53
- | 1.8497 | 0.06 | 48 | 1.9878 |
54
- | 1.8285 | 0.08 | 64 | 1.9800 |
55
- | 1.8822 | 0.1 | 80 | 1.9697 |
56
- | 1.8283 | 0.12 | 96 | 1.9583 |
57
- | 1.7563 | 0.14 | 112 | 1.9458 |
58
- | 1.8092 | 0.17 | 128 | 1.9340 |
59
- | 1.7614 | 0.19 | 144 | 1.9217 |
60
- | 1.7469 | 0.21 | 160 | 1.9087 |
61
- | 1.7174 | 0.23 | 176 | 1.8953 |
62
- | 1.7582 | 0.25 | 192 | 1.8816 |
63
- | 1.684 | 0.27 | 208 | 1.8665 |
64
- | 1.6512 | 0.29 | 224 | 1.8515 |
65
- | 1.6781 | 0.31 | 240 | 1.8373 |
66
- | 1.7099 | 0.33 | 256 | 1.8232 |
67
- | 1.7453 | 0.35 | 272 | 1.8097 |
68
- | 1.6575 | 0.37 | 288 | 1.8002 |
69
- | 1.6458 | 0.39 | 304 | 1.7921 |
70
- | 1.6748 | 0.41 | 320 | 1.7852 |
71
- | 1.7381 | 0.43 | 336 | 1.7795 |
72
- | 1.5981 | 0.45 | 352 | 1.7719 |
73
- | 1.6238 | 0.47 | 368 | 1.7640 |
74
- | 1.7185 | 0.5 | 384 | 1.7590 |
75
- | 1.6045 | 0.52 | 400 | 1.7560 |
76
- | 1.6041 | 0.54 | 416 | 1.7546 |
77
- | 1.6066 | 0.56 | 432 | 1.7527 |
78
- | 1.6903 | 0.58 | 448 | 1.7485 |
79
- | 1.6984 | 0.6 | 464 | 1.7456 |
80
- | 1.6869 | 0.62 | 480 | 1.7436 |
81
- | 1.5921 | 0.64 | 496 | 1.7423 |
82
- | 1.6384 | 0.66 | 512 | 1.7429 |
83
- | 1.6382 | 0.68 | 528 | 1.7419 |
84
- | 1.6426 | 0.7 | 544 | 1.7414 |
85
- | 1.5818 | 0.72 | 560 | 1.7411 |
86
- | 1.6477 | 0.74 | 576 | 1.7401 |
87
- | 1.6235 | 0.76 | 592 | 1.7391 |
88
- | 1.6594 | 0.78 | 608 | 1.7384 |
89
- | 1.7294 | 0.8 | 624 | 1.7378 |
90
- | 1.6503 | 0.83 | 640 | 1.7373 |
91
- | 1.6328 | 0.85 | 656 | 1.7371 |
92
- | 1.5852 | 0.87 | 672 | 1.7372 |
93
- | 1.6594 | 0.89 | 688 | 1.7373 |
94
- | 1.6369 | 0.91 | 704 | 1.7373 |
95
- | 1.6426 | 0.93 | 720 | 1.7371 |
96
- | 1.674 | 0.95 | 736 | 1.7369 |
97
- | 1.5694 | 0.97 | 752 | 1.7369 |
98
- | 1.6266 | 0.99 | 768 | 1.7369 |
99
 
100
 
101
  ### Framework versions
102
 
103
- - Transformers 4.35.0.dev0
104
- - Pytorch 2.1.0+cu121
105
- - Datasets 2.5.2
106
- - Tokenizers 0.14.0
 
14
 
15
  This model is a fine-tuned version of [Qwen/Qwen-14B](https://huggingface.co/Qwen/Qwen-14B) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.6501
18
 
19
  ## Model description
20
 
 
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
+ - learning_rate: 0.0001
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 1
39
  - seed: 42
40
+ - gradient_accumulation_steps: 16
41
  - total_train_batch_size: 16
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.163 | 0.02 | 16 | 1.9459 |
52
+ | 1.9498 | 0.04 | 32 | 1.8467 |
53
+ | 1.9578 | 0.06 | 48 | 1.7864 |
54
+ | 1.8398 | 0.08 | 64 | 1.7530 |
55
+ | 1.7696 | 0.1 | 80 | 1.7076 |
56
+ | 1.7744 | 0.12 | 96 | 1.7275 |
57
+ | 1.8108 | 0.14 | 112 | 1.6887 |
58
+ | 1.7707 | 0.17 | 128 | 1.6942 |
59
+ | 1.787 | 0.19 | 144 | 1.6894 |
60
+ | 1.7029 | 0.21 | 160 | 1.6760 |
61
+ | 1.6732 | 0.23 | 176 | 1.6838 |
62
+ | 1.6313 | 0.25 | 192 | 1.6754 |
63
+ | 1.7071 | 0.27 | 208 | 1.6752 |
64
+ | 1.6781 | 0.29 | 224 | 1.6741 |
65
+ | 1.7782 | 0.31 | 240 | 1.6698 |
66
+ | 1.6836 | 0.33 | 256 | 1.6592 |
67
+ | 1.7229 | 0.35 | 272 | 1.6633 |
68
+ | 1.7196 | 0.37 | 288 | 1.6638 |
69
+ | 1.6892 | 0.39 | 304 | 1.6627 |
70
+ | 1.6844 | 0.41 | 320 | 1.6557 |
71
+ | 1.8027 | 0.43 | 336 | 1.6540 |
72
+ | 1.692 | 0.45 | 352 | 1.6577 |
73
+ | 1.7088 | 0.47 | 368 | 1.6611 |
74
+ | 1.7987 | 0.5 | 384 | 1.6557 |
75
+ | 1.709 | 0.52 | 400 | 1.6600 |
76
+ | 1.701 | 0.54 | 416 | 1.6588 |
77
+ | 1.6784 | 0.56 | 432 | 1.6594 |
78
+ | 1.6997 | 0.58 | 448 | 1.6484 |
79
+ | 1.7811 | 0.6 | 464 | 1.6583 |
80
+ | 1.7628 | 0.62 | 480 | 1.6461 |
81
+ | 1.6254 | 0.64 | 496 | 1.6527 |
82
+ | 1.6684 | 0.66 | 512 | 1.6520 |
83
+ | 1.6837 | 0.68 | 528 | 1.6570 |
84
+ | 1.7209 | 0.7 | 544 | 1.6543 |
85
+ | 1.677 | 0.72 | 560 | 1.6562 |
86
+ | 1.6819 | 0.74 | 576 | 1.6517 |
87
+ | 1.7072 | 0.76 | 592 | 1.6551 |
88
+ | 1.6446 | 0.78 | 608 | 1.6562 |
89
+ | 1.6908 | 0.8 | 624 | 1.6528 |
90
+ | 1.7209 | 0.83 | 640 | 1.6518 |
91
+ | 1.6818 | 0.85 | 656 | 1.6517 |
92
+ | 1.7007 | 0.87 | 672 | 1.6525 |
93
+ | 1.8077 | 0.89 | 688 | 1.6522 |
94
+ | 1.6856 | 0.91 | 704 | 1.6516 |
95
+ | 1.7247 | 0.93 | 720 | 1.6509 |
96
+ | 1.6645 | 0.95 | 736 | 1.6500 |
97
+ | 1.6841 | 0.97 | 752 | 1.6499 |
98
+ | 1.7244 | 0.99 | 768 | 1.6501 |
99
 
100
 
101
  ### Framework versions
102
 
103
+ - Transformers 4.32.0
104
+ - Pytorch 2.1.0
105
+ - Datasets 2.14.7
106
+ - Tokenizers 0.13.3
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb741c88122a18fbe275527343d757d604ef68b3fa5ab438b9e1f911de014745
3
  size 9312358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2c67675298f4c45b4bc7df7dc927f8e57796428bd311446fe1ef1d61000597
3
  size 9312358