Hugging Face's logo

tsavage68
/
mpt_1000_STEPS_1e8_rate03_beta_DPO

Text Generation
Transformers
Safetensors
mpt
trl
dpo
Generated from Trainer
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
tsavage68 commited on
Commit
c9962e1
·
verified ·
1 Parent(s): 18c6cf6

End of training

Browse files
Files changed (8) hide show
  1. README.md +20 -20
  2. final_checkpoint/model-00001-of-00003.safetensors +1 -1
  3. final_checkpoint/model-00002-of-00003.safetensors +1 -1
  4. final_checkpoint/model-00003-of-00003.safetensors +1 -1
  5. model-00001-of-00003.safetensors +1 -1
  6. model-00002-of-00003.safetensors +1 -1
  7. model-00003-of-00003.safetensors +1 -1
  8. training_args.bin +1 -1
README.md CHANGED
@@ -17,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.5250
21
- - Rewards/chosen: -11.2880
22
- - Rewards/rejected: -11.0941
23
- - Rewards/accuracies: 0.4989
24
- - Rewards/margins: -0.1939
25
- - Logps/rejected: -58.5379
26
- - Logps/chosen: -58.4188
27
- - Logits/rejected: 8.0116
28
- - Logits/chosen: 8.0111
29
 
30
  ## Model description
31
 
@@ -44,7 +44,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 1e-05
48
  - train_batch_size: 2
49
  - eval_batch_size: 1
50
  - seed: 42
@@ -59,16 +59,16 @@ The following hyperparameters were used during training:
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
- | 2.9156 | 0.1 | 100 | 3.4899 | -15.5009 | -15.3977 | 0.4725 | -0.1031 | -72.8833 | -72.4618 | 42.9070 | 42.9069 |
63
- | 2.1578 | 0.2 | 200 | 2.2150 | -9.7540 | -9.4579 | 0.4549 | -0.2961 | -53.0838 | -53.3056 | 12.3838 | 12.3837 |
64
- | 2.8766 | 0.29 | 300 | 2.2464 | -12.1892 | -11.8037 | 0.4593 | -0.3856 | -60.9030 | -61.4230 | 14.3112 | 14.3107 |
65
- | 2.5297 | 0.39 | 400 | 1.8130 | -10.1066 | -9.8997 | 0.4879 | -0.2069 | -54.5563 | -54.4807 | 10.1726 | 10.1723 |
66
- | 2.2297 | 0.49 | 500 | 1.9150 | -10.8801 | -10.6958 | 0.4923 | -0.1843 | -57.2102 | -57.0592 | 9.5803 | 9.5795 |
67
- | 1.8734 | 0.59 | 600 | 1.6431 | -11.3789 | -11.2312 | 0.4835 | -0.1477 | -58.9947 | -58.7219 | 11.7059 | 11.7051 |
68
- | 1.7922 | 0.68 | 700 | 1.6689 | -12.0398 | -11.8183 | 0.4879 | -0.2215 | -60.9518 | -60.9247 | 8.8943 | 8.8938 |
69
- | 1.268 | 0.78 | 800 | 1.5363 | -11.2805 | -11.0909 | 0.5033 | -0.1895 | -58.5271 | -58.3937 | 8.4559 | 8.4554 |
70
- | 1.7688 | 0.88 | 900 | 1.5253 | -11.2773 | -11.0831 | 0.4945 | -0.1942 | -58.5010 | -58.3831 | 8.0320 | 8.0315 |
71
- | 1.0648 | 0.98 | 1000 | 1.5250 | -11.2880 | -11.0941 | 0.4989 | -0.1939 | -58.5379 | -58.4188 | 8.0116 | 8.0111 |
72
 
73
 
74
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6933
21
+ - Rewards/chosen: -0.0008
22
+ - Rewards/rejected: -0.0019
23
+ - Rewards/accuracies: 0.5187
24
+ - Rewards/margins: 0.0011
25
+ - Logps/rejected: -21.5638
26
+ - Logps/chosen: -20.7947
27
+ - Logits/rejected: 14.2524
28
+ - Logits/chosen: 14.2550
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 1e-08
48
  - train_batch_size: 2
49
  - eval_batch_size: 1
50
  - seed: 42
 
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
+ | 0.6965 | 0.1 | 100 | 0.6951 | -0.0017 | 0.0013 | 0.4681 | -0.0029 | -21.5532 | -20.7977 | 14.2557 | 14.2583 |
63
+ | 0.6918 | 0.2 | 200 | 0.6942 | -0.0054 | -0.0044 | 0.5011 | -0.0010 | -21.5722 | -20.8104 | 14.2575 | 14.2601 |
64
+ | 0.6965 | 0.29 | 300 | 0.6941 | -0.0016 | -0.0010 | 0.4945 | -0.0006 | -21.5608 | -20.7975 | 14.2549 | 14.2575 |
65
+ | 0.6906 | 0.39 | 400 | 0.6946 | 0.0001 | 0.0020 | 0.4747 | -0.0019 | -21.5507 | -20.7919 | 14.2494 | 14.2520 |
66
+ | 0.6883 | 0.49 | 500 | 0.6972 | -0.0019 | 0.0050 | 0.4484 | -0.0069 | -21.5408 | -20.7986 | 14.2521 | 14.2547 |
67
+ | 0.6867 | 0.59 | 600 | 0.6969 | -0.0054 | 0.0010 | 0.4418 | -0.0064 | -21.5541 | -20.8103 | 14.2502 | 14.2528 |
68
+ | 0.6937 | 0.68 | 700 | 0.6939 | 0.0015 | 0.0020 | 0.5275 | -0.0005 | -21.5508 | -20.7871 | 14.2547 | 14.2573 |
69
+ | 0.6855 | 0.78 | 800 | 0.6933 | -0.0008 | -0.0017 | 0.5099 | 0.0009 | -21.5631 | -20.7947 | 14.2522 | 14.2548 |
70
+ | 0.6918 | 0.88 | 900 | 0.6933 | -0.0008 | -0.0019 | 0.5187 | 0.0011 | -21.5638 | -20.7947 | 14.2524 | 14.2550 |
71
+ | 0.6957 | 0.98 | 1000 | 0.6933 | -0.0008 | -0.0019 | 0.5187 | 0.0011 | -21.5638 | -20.7947 | 14.2524 | 14.2550 |
72
 
73
 
74
  ### Framework versions
final_checkpoint/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f85dd251dd626fdb73ead11607afecd33b2eccbbd0188a354b7b72ebf539fd29
3
  size 4976746424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bd2f664b12d6db09cf833656ae9a726999112b6713494e5b0db5937bad20e3
3
  size 4976746424
final_checkpoint/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:680fc811f2d4e36b7ed53f83f83770b202ef7146af87f569f7c4d75f6b229d12
3
  size 4966260992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d35ccdd8c1b28bfbf54f541d22882e3ea454d4fe2aa26cf7b115d7b0fe1db8a
3
  size 4966260992
final_checkpoint/model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:675d04898fb6d1bf9f999b7566532ab87f31bb2411a1a0be6679bcba94b252e9
3
  size 3355588232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c75b35f7faa707a36c75a3226633f4a41ea0d492ddb5d897c3bbf74506dc0f
3
  size 3355588232
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f85dd251dd626fdb73ead11607afecd33b2eccbbd0188a354b7b72ebf539fd29
3
  size 4976746424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bd2f664b12d6db09cf833656ae9a726999112b6713494e5b0db5937bad20e3
3
  size 4976746424
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:680fc811f2d4e36b7ed53f83f83770b202ef7146af87f569f7c4d75f6b229d12
3
  size 4966260992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d35ccdd8c1b28bfbf54f541d22882e3ea454d4fe2aa26cf7b115d7b0fe1db8a
3
  size 4966260992
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:675d04898fb6d1bf9f999b7566532ab87f31bb2411a1a0be6679bcba94b252e9
3
  size 3355588232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c75b35f7faa707a36c75a3226633f4a41ea0d492ddb5d897c3bbf74506dc0f
3
  size 3355588232
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b6321d2a9e526777d6d183b79b35ef1b3d7a41179b3b7f9063c490d45fa8bae
3
  size 4475
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b91ebb5dc97f9d92c9f28965a02db4b8cbe8d571b55177f03beb2199631458
3
  size 4475