Hugging Face's logo

marcus2000
/
Saiga_timelist_task20steps

PEFT
Safetensors
Generated from Trainer
Model card Files Community
marcus2000 commited on
Commit
4a3fbeb
•
1 Parent(s): 48066d0

End of training

Browse files
Files changed (3) hide show
  1. README.md +18 -6
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [TheBloke/Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.8695
19
 
20
  ## Model description
21
 
@@ -42,16 +42,28 @@ The following hyperparameters were used during training:
42
  - total_train_batch_size: 20
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - training_steps: 20
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 1.979 | 0.13 | 5 | 1.9787 |
52
- | 1.9004 | 0.26 | 10 | 1.9026 |
53
- | 1.7991 | 0.39 | 15 | 1.8761 |
54
- | 1.7837 | 0.52 | 20 | 1.8695 |
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [TheBloke/Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.7498
19
 
20
  ## Model description
21
 
 
42
  - total_train_batch_size: 20
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - training_steps: 80
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 1.9766 | 0.13 | 5 | 1.9730 |
52
+ | 1.8885 | 0.26 | 10 | 1.8875 |
53
+ | 1.7781 | 0.39 | 15 | 1.8522 |
54
+ | 1.7543 | 0.52 | 20 | 1.8314 |
55
+ | 1.716 | 0.64 | 25 | 1.8151 |
56
+ | 1.8085 | 0.77 | 30 | 1.8015 |
57
+ | 1.6707 | 0.9 | 35 | 1.7902 |
58
+ | 1.6972 | 1.03 | 40 | 1.7805 |
59
+ | 1.6439 | 1.16 | 45 | 1.7728 |
60
+ | 1.6487 | 1.29 | 50 | 1.7668 |
61
+ | 1.5462 | 1.42 | 55 | 1.7606 |
62
+ | 1.6728 | 1.55 | 60 | 1.7557 |
63
+ | 1.6285 | 1.68 | 65 | 1.7520 |
64
+ | 1.5609 | 1.8 | 70 | 1.7508 |
65
+ | 1.5975 | 1.93 | 75 | 1.7500 |
66
+ | 1.6035 | 2.06 | 80 | 1.7498 |
67
 
68
 
69
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33f95e11dbb74067e6f6df215c3e932bad47fe7c967fac707d22340c9c488498
3
  size 33589040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7d4cee3da167364c19e2438363e31e6dde39fd24e11d317511148cb3b92065
3
  size 33589040
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3d5941ad30c88aa7312cf65aa1fc174fc4fe2d2a1cf92ae007c09710b30baf6
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c632e1dcb43c6d589f5104dea52976de3830b6248b57286e3b64a3009dba283
3
  size 4920