Hugging Face's logo

Yan777
/
trained_weigths

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Metrics Community
Yan777 commited on
Commit
23b1c20
·
verified ·
1 Parent(s): b359992

End of training

Browse files
Files changed (4) hide show
  1. README.md +10 -6
  2. adapter_model.safetensors +1 -1
  3. runs/Apr09_20-50-53_DESKTOP-5GR7SN9/events.out.tfevents.1712667060.DESKTOP-5GR7SN9.21868.3 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6810
21
 
22
  ## Model description
23
 
@@ -43,17 +43,21 @@ The following hyperparameters were used during training:
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_ratio: 0.03
46
- - num_epochs: 4
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.5761 | 1.0 | 755 | 0.6937 |
54
- | 0.5945 | 2.0 | 1510 | 0.6818 |
55
- | 0.5896 | 3.0 | 2265 | 0.6801 |
56
- | 0.609 | 4.0 | 3020 | 0.6810 |
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7291
21
 
22
  ## Model description
23
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_ratio: 0.03
46
+ - num_epochs: 8
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.5764 | 1.0 | 755 | 0.6950 |
54
+ | 0.5964 | 2.0 | 1510 | 0.6837 |
55
+ | 0.5912 | 3.0 | 2265 | 0.6830 |
56
+ | 0.6013 | 4.0 | 3020 | 0.6878 |
57
+ | 0.5122 | 5.0 | 3775 | 0.6994 |
58
+ | 0.4787 | 6.0 | 4530 | 0.7133 |
59
+ | 0.4859 | 7.0 | 5285 | 0.7235 |
60
+ | 0.4924 | 8.0 | 6040 | 0.7291 |
61
 
62
 
63
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9a7e72fda1a5bdafb6f8695c59913d5b1cb540204c80a58f21d0af7d1deb0ad
3
  size 1182877280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9480a32629005365e8819af7727ad5a24576b7951d949e7aa5340e20bf9fa669
3
  size 1182877280
runs/Apr09_20-50-53_DESKTOP-5GR7SN9/events.out.tfevents.1712667060.DESKTOP-5GR7SN9.21868.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01cdfafc76df4196cc60bedeb4153d897a93240b22ed5d783be6fdbd39d2102
3
+ size 58409
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8e61d934677e049031839f2415d60bb8548c3c1e6a993a1be68d3c749c40721
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a7a7afc26749fc081aac48feb01b6764c990bb8e9b9aff9b77bda2d2a4826b
3
  size 4920