Hugging Face's logo

irenewds
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
irenewds commited on
Commit
7922166
·
verified ·
1 Parent(s): b0978f9

irenewds/shawgpt-ft

Browse files
Files changed (3) hide show
  1. README.md +16 -21
  2. runs/Oct24_19-48-07_1f4e1c060daf/events.out.tfevents.1729799300.1f4e1c060daf.20197.1 +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: 1.3316
20
 
21
  ## Model description
22
 
@@ -44,32 +44,27 @@ The following hyperparameters were used during training:
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
- | 4.6062 | 0.9231 | 3 | 4.0336 |
55
- | 4.1724 | 1.8462 | 6 | 3.6011 |
56
- | 3.669 | 2.7692 | 9 | 3.1876 |
57
- | 2.4069 | 4.0 | 13 | 2.7142 |
58
- | 2.8308 | 4.9231 | 16 | 2.4288 |
59
- | 2.4589 | 5.8462 | 19 | 2.1674 |
60
- | 2.1294 | 6.7692 | 22 | 1.9285 |
61
- | 1.4108 | 8.0 | 26 | 1.7008 |
62
- | 1.6925 | 8.9231 | 29 | 1.5824 |
63
- | 1.5326 | 9.8462 | 32 | 1.4923 |
64
- | 1.4721 | 10.7692 | 35 | 1.4347 |
65
- | 1.0272 | 12.0 | 39 | 1.3852 |
66
- | 1.3601 | 12.9231 | 42 | 1.3676 |
67
- | 1.3123 | 13.8462 | 45 | 1.3553 |
68
- | 1.3121 | 14.7692 | 48 | 1.3469 |
69
- | 0.9808 | 16.0 | 52 | 1.3382 |
70
- | 1.2776 | 16.9231 | 55 | 1.3343 |
71
- | 1.2614 | 17.8462 | 58 | 1.3322 |
72
- | 0.888 | 18.4615 | 60 | 1.3316 |
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: 1.4750
20
 
21
  ## Model description
22
 
 
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: 15
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.6053 | 0.9231 | 3 | 4.0290 |
55
+ | 4.1741 | 1.8462 | 6 | 3.6093 |
56
+ | 3.6913 | 2.7692 | 9 | 3.2120 |
57
+ | 2.4435 | 4.0 | 13 | 2.7681 |
58
+ | 2.9111 | 4.9231 | 16 | 2.5080 |
59
+ | 2.5883 | 5.8462 | 19 | 2.2860 |
60
+ | 2.3061 | 6.7692 | 22 | 2.0874 |
61
+ | 1.5537 | 8.0 | 26 | 1.8540 |
62
+ | 1.8704 | 8.9231 | 29 | 1.7352 |
63
+ | 1.7152 | 9.8462 | 32 | 1.6456 |
64
+ | 1.647 | 10.7692 | 35 | 1.5787 |
65
+ | 1.1487 | 12.0 | 39 | 1.5120 |
66
+ | 1.5072 | 12.9231 | 42 | 1.4856 |
67
+ | 1.2433 | 13.8462 | 45 | 1.4750 |
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
runs/Oct24_19-48-07_1f4e1c060daf/events.out.tfevents.1729799300.1f4e1c060daf.20197.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41b404acc35ce63e56698c03510ad7f516a90e9fff9bda1b6cebc3b2ec53ed0
3
+ size 12553
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a9e4f7d7f8a5b75519fafab0eb9b2fdd1d4572066c79fec4b297ee1e7af666d
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c76033ac543464722332330b433f8981f5b66935e895d6b2bbb6f492057adcb
3
  size 5176