Hugging Face's logo

Christine789
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Christine789 commited on
Commit
345613b
•
1 Parent(s): a90b2de

Christine789/qlora_v2

Browse files
Files changed (4) hide show
  1. README.md +12 -12
  2. adapter_model.safetensors +1 -1
  3. runs/Sep29_15-02-36_4cd08f998954/events.out.tfevents.1727622156.4cd08f998954.20051.1 +3 -0
  4. 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: 1.7486
20
 
21
  ## Model description
22
 
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
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: 10
48
  - mixed_precision_training: Native AMP
49
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 4.5903 | 0.9231 | 3 | 3.9569 |
55
- | 4.0337 | 1.8462 | 6 | 3.4324 |
56
- | 3.4578 | 2.7692 | 9 | 2.9754 |
57
- | 2.2395 | 4.0 | 13 | 2.5348 |
58
- | 2.6193 | 4.9231 | 16 | 2.2674 |
59
- | 2.2876 | 5.8462 | 19 | 2.0560 |
60
- | 2.039 | 6.7692 | 22 | 1.9094 |
61
- | 1.4379 | 8.0 | 26 | 1.7941 |
62
- | 1.829 | 8.9231 | 29 | 1.7533 |
63
- | 1.2737 | 9.2308 | 30 | 1.7486 |
64
 
65
 
66
  ### 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: 1.3236
20
 
21
  ## Model description
22
 
 
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: 10
47
  - num_epochs: 10
48
  - mixed_precision_training: Native AMP
49
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.7883 | 0.9231 | 3 | 1.7008 |
55
+ | 1.6639 | 1.8462 | 6 | 1.5617 |
56
+ | 1.4596 | 2.7692 | 9 | 1.4324 |
57
+ | 1.0009 | 4.0 | 13 | 1.3596 |
58
+ | 1.303 | 4.9231 | 16 | 1.3316 |
59
+ | 1.2254 | 5.8462 | 19 | 1.3258 |
60
+ | 1.1821 | 6.7692 | 22 | 1.3243 |
61
+ | 0.8973 | 8.0 | 26 | 1.3227 |
62
+ | 1.1805 | 8.9231 | 29 | 1.3236 |
63
+ | 0.8572 | 9.2308 | 30 | 1.3236 |
64
 
65
 
66
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eaa4b2b4296c49c2bf972e688de5c784bffe0a86a7869809aa4e02aa6908679
3
  size 8397056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b639d244cf1910d842966d9e72d8497291a20adc1d40fb90ffcbfdc16c08649
3
  size 8397056
runs/Sep29_15-02-36_4cd08f998954/events.out.tfevents.1727622156.4cd08f998954.20051.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef31d9922615375181fee63e2320fd55a3257a9e63ac1b477e6aae56135f580
3
+ size 10648
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:597b3d4e3273951727c629056c3d9fa9d7fa24efecd77e6521baa49f81189860
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abce6aa795f9a1f621f0e4f09882c31ee4201fafbf47f2c5de55db1ca9147261
3
  size 5176