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
8fb3da0
·
verified ·
1 Parent(s): f1f3409

End of training

Browse files
Files changed (11) hide show
  1. README.md +6 -5
  2. adapter_model.safetensors +1 -1
  3. runs/Apr26_13-19-31_DESKTOP-5GR7SN9/events.out.tfevents.1714108772.DESKTOP-5GR7SN9.39000.0 +3 -0
  4. runs/Apr26_13-21-35_DESKTOP-5GR7SN9/events.out.tfevents.1714108902.DESKTOP-5GR7SN9.19944.0 +3 -0
  5. runs/Apr26_13-23-36_DESKTOP-5GR7SN9/events.out.tfevents.1714109024.DESKTOP-5GR7SN9.19944.1 +3 -0
  6. runs/Apr26_14-19-34_DESKTOP-5GR7SN9/events.out.tfevents.1714112386.DESKTOP-5GR7SN9.37664.0 +3 -0
  7. runs/Apr26_14-30-51_DESKTOP-5GR7SN9/events.out.tfevents.1714113061.DESKTOP-5GR7SN9.4328.0 +3 -0
  8. runs/Apr26_14-36-44_DESKTOP-5GR7SN9/events.out.tfevents.1714113411.DESKTOP-5GR7SN9.21524.0 +3 -0
  9. runs/Apr26_19-52-44_DESKTOP-5GR7SN9/events.out.tfevents.1714132371.DESKTOP-5GR7SN9.5720.0 +3 -0
  10. runs/Apr27_01-40-56_DESKTOP-5GR7SN9/events.out.tfevents.1714153263.DESKTOP-5GR7SN9.15560.0 +3 -0
  11. training_args.bin +1 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  library_name: peft
3
  tags:
4
  - trl
@@ -17,7 +18,7 @@ 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: 0.3999
21
 
22
  ## Model description
23
 
@@ -50,10 +51,10 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:-----:|:---------------:|
53
- | 0.8184 | 1.0 | 5194 | 0.4070 |
54
- | 0.842 | 2.0 | 10388 | 0.3978 |
55
- | 0.695 | 3.0 | 15582 | 0.3964 |
56
- | 0.7187 | 4.0 | 20776 | 0.3999 |
57
 
58
 
59
  ### Framework versions
 
1
  ---
2
+ license: llama2
3
  library_name: peft
4
  tags:
5
  - trl
 
18
 
19
  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.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7235
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:-----:|:---------------:|
54
+ | 0.7193 | 1.0 | 6036 | 0.6783 |
55
+ | 0.6395 | 2.0 | 12072 | 0.6763 |
56
+ | 0.5361 | 3.0 | 18108 | 0.6947 |
57
+ | 0.5402 | 4.0 | 24144 | 0.7235 |
58
 
59
 
60
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bbb497bb11df28b00ed0af9315e4f529522b7bd4d9c3c3b7ec5fe51b6aa0cd1
3
  size 1182877280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb453be819bdba93e47cae6a193477081568c1810e8cb3ad2c7e29eaefce49ad
3
  size 1182877280
runs/Apr26_13-19-31_DESKTOP-5GR7SN9/events.out.tfevents.1714108772.DESKTOP-5GR7SN9.39000.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a9240501d4216066bfbfe8dc2162f8da14d05f54af93c70e2eb3f1b800ed41
3
+ size 4789
runs/Apr26_13-21-35_DESKTOP-5GR7SN9/events.out.tfevents.1714108902.DESKTOP-5GR7SN9.19944.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e434fbbbe9462951a5eaedf6f9066dd50fa3a3cd372734b97db8cb7de1da00a4
3
+ size 5502
runs/Apr26_13-23-36_DESKTOP-5GR7SN9/events.out.tfevents.1714109024.DESKTOP-5GR7SN9.19944.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4aa7803fec380b455202a8338a12bbe8cbd1d76bd14c29093e3cd92126d44d
3
+ size 159068
runs/Apr26_14-19-34_DESKTOP-5GR7SN9/events.out.tfevents.1714112386.DESKTOP-5GR7SN9.37664.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe38ee2942cefc4bf6c48f3ac3d9bf445fa38874a87e001b15b68412e1e92692
3
+ size 4789
runs/Apr26_14-30-51_DESKTOP-5GR7SN9/events.out.tfevents.1714113061.DESKTOP-5GR7SN9.4328.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420b372123f3608bcddc022ae3618b5aff4037f5272eab239c0c105357b37412
3
+ size 4943
runs/Apr26_14-36-44_DESKTOP-5GR7SN9/events.out.tfevents.1714113411.DESKTOP-5GR7SN9.21524.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987f459d3855a43334a71f4f3e479c7138d679a4a8ce371ffcef26cfaa6699a2
3
+ size 158663
runs/Apr26_19-52-44_DESKTOP-5GR7SN9/events.out.tfevents.1714132371.DESKTOP-5GR7SN9.5720.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9c280c4116f65ad9abd41ca07130efb55d48e557bdab66413092e51b73a798
3
+ size 158663
runs/Apr27_01-40-56_DESKTOP-5GR7SN9/events.out.tfevents.1714153263.DESKTOP-5GR7SN9.15560.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae5a74efcfe0f4be5829768128ff6bff4437e35ba18e5df39a749d219592c879
3
+ size 158663
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13386342a61744b9c99fc799ab81c1095f816ff2298af5ffdeca832137c6a8e4
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee2ba3a80330bf310419e1b30549bf51d1f87b0222948d171a47694326aff88e
3
  size 4728