Hugging Face's logo

irenewds
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
irenewds commited on
Commit
0f71292
·
verified ·
1 Parent(s): dd8f152

irenewds/shawgpt-ft

Browse files
Files changed (3) hide show
  1. README.md +16 -25
  2. runs/Oct24_20-34-40_1f4e1c060daf/events.out.tfevents.1729802081.1f4e1c060daf.28754.7 +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: 1.4966
20
 
21
  ## Model description
22
 
@@ -39,37 +39,28 @@ The following hyperparameters were used during training:
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
42
- - gradient_accumulation_steps: 4
43
- - total_train_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
- - num_epochs: 20
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:-------:|:----:|:---------------:|
54
- | 4.6204 | 0.9231 | 3 | 4.1048 |
55
- | 4.3258 | 1.8462 | 6 | 3.8169 |
56
- | 3.9783 | 2.7692 | 9 | 3.5341 |
57
- | 2.7261 | 4.0 | 13 | 3.1687 |
58
- | 3.3397 | 4.9231 | 16 | 2.9220 |
59
- | 3.0432 | 5.8462 | 19 | 2.7075 |
60
- | 2.7883 | 6.7692 | 22 | 2.5078 |
61
- | 1.9298 | 8.0 | 26 | 2.2852 |
62
- | 2.3461 | 8.9231 | 29 | 2.1040 |
63
- | 2.1186 | 9.8462 | 32 | 1.9649 |
64
- | 1.9918 | 10.7692 | 35 | 1.8571 |
65
- | 1.3817 | 12.0 | 39 | 1.7531 |
66
- | 1.7729 | 12.9231 | 42 | 1.6817 |
67
- | 1.6647 | 13.8462 | 45 | 1.6200 |
68
- | 1.6129 | 14.7692 | 48 | 1.5709 |
69
- | 1.1762 | 16.0 | 52 | 1.5287 |
70
- | 1.5169 | 16.9231 | 55 | 1.5096 |
71
- | 1.4859 | 17.8462 | 58 | 1.4992 |
72
- | 1.0397 | 18.4615 | 60 | 1.4966 |
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: 3.3903
20
 
21
  ## Model description
22
 
 
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 32
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
+ - num_epochs: 16
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 6.9703 | 0.6154 | 1 | 4.2307 |
55
+ | 3.4299 | 1.8462 | 3 | 4.0954 |
56
+ | 6.6315 | 2.4615 | 4 | 4.0002 |
57
+ | 3.1735 | 3.6923 | 6 | 3.8260 |
58
+ | 3.0824 | 4.9231 | 8 | 3.6824 |
59
+ | 5.9421 | 5.5385 | 9 | 3.6204 |
60
+ | 2.9008 | 6.7692 | 11 | 3.5164 |
61
+ | 2.8262 | 8.0 | 13 | 3.4415 |
62
+ | 5.5625 | 8.6154 | 14 | 3.4162 |
63
+ | 2.334 | 9.8462 | 16 | 3.3903 |
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
runs/Oct24_20-34-40_1f4e1c060daf/events.out.tfevents.1729802081.1f4e1c060daf.28754.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ccc4bcd3168a9a3101920db9672b671185a9c462111d15faf1ce8774c40d75
3
+ size 10660
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c96ca61cdd35f9cd64d101a9f251c09920cbb29127ce95ca255189bdeedfa31a
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df52654c2125c6cc3d3a176af21eb30f2ef1fc7e01e15ed33451cef4f6c43c0
3
  size 5176