Hugging Face's logo

irenewds
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
irenewds commited on
Commit
6bc9807
·
verified ·
1 Parent(s): 40fdb0d

irenewds/shawgpt-ft

Browse files
Files changed (3) hide show
  1. README.md +21 -21
  2. runs/Oct24_01-36-53_89957c487371/events.out.tfevents.1729733818.89957c487371.1061.1 +3 -0
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.4926
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0001
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
@@ -51,25 +51,25 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 4.6196 | 0.9231 | 3 | 4.0996 |
55
- | 4.3186 | 1.8462 | 6 | 3.8038 |
56
- | 3.9621 | 2.7692 | 9 | 3.5173 |
57
- | 2.7151 | 4.0 | 13 | 3.1519 |
58
- | 3.3264 | 4.9231 | 16 | 2.9077 |
59
- | 3.0314 | 5.8462 | 19 | 2.6983 |
60
- | 2.7911 | 6.7692 | 22 | 2.5124 |
61
- | 1.9218 | 8.0 | 26 | 2.2823 |
62
- | 2.3602 | 8.9231 | 29 | 2.1229 |
63
- | 2.1297 | 9.8462 | 32 | 1.9649 |
64
- | 1.9877 | 10.7692 | 35 | 1.8543 |
65
- | 1.3751 | 12.0 | 39 | 1.7460 |
66
- | 1.7619 | 12.9231 | 42 | 1.6779 |
67
- | 1.6587 | 13.8462 | 45 | 1.6203 |
68
- | 1.6074 | 14.7692 | 48 | 1.5695 |
69
- | 1.1674 | 16.0 | 52 | 1.5241 |
70
- | 1.503 | 16.9231 | 55 | 1.5053 |
71
- | 1.4711 | 17.8462 | 58 | 1.4951 |
72
- | 1.0311 | 18.4615 | 60 | 1.4926 |
73
 
74
 
75
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.3489
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.00015
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.6062 | 0.9231 | 3 | 4.0362 |
55
+ | 4.1781 | 1.8462 | 6 | 3.6161 |
56
+ | 3.6808 | 2.7692 | 9 | 3.2051 |
57
+ | 2.4181 | 4.0 | 13 | 2.7329 |
58
+ | 2.845 | 4.9231 | 16 | 2.4553 |
59
+ | 2.4808 | 5.8462 | 19 | 2.1947 |
60
+ | 2.1606 | 6.7692 | 22 | 1.9599 |
61
+ | 1.425 | 8.0 | 26 | 1.7251 |
62
+ | 1.7116 | 8.9231 | 29 | 1.6083 |
63
+ | 1.5518 | 9.8462 | 32 | 1.5094 |
64
+ | 1.4834 | 10.7692 | 35 | 1.4522 |
65
+ | 1.0371 | 12.0 | 39 | 1.3994 |
66
+ | 1.3682 | 12.9231 | 42 | 1.3823 |
67
+ | 1.3207 | 13.8462 | 45 | 1.3714 |
68
+ | 1.3218 | 14.7692 | 48 | 1.3640 |
69
+ | 0.9873 | 16.0 | 52 | 1.3561 |
70
+ | 1.2872 | 16.9231 | 55 | 1.3521 |
71
+ | 1.2689 | 17.8462 | 58 | 1.3495 |
72
+ | 0.8971 | 18.4615 | 60 | 1.3489 |
73
 
74
 
75
  ### Framework versions
runs/Oct24_01-36-53_89957c487371/events.out.tfevents.1729733818.89957c487371.1061.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca492e035774fdc9433dd1041a741e8ac513f785942f21a4c1edf49992a6c021
3
+ size 14918
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d24572c9554940e1f92edd78e10243cb6873325ac8bd219df60a27e7683379a
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f503e49e741f1ddad3d08ba2dd98cfccccd8d44fbe62354a8313f41c36708e
3
  size 5176