Hugging Face's logo

bif02
/
mistral_instruct_generation2

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
bif02 commited on
Commit
a21f879
·
verified ·
1 Parent(s): 7e6e960

bif02/mistral_6epochs

Browse files
Files changed (5) hide show
  1. README.md +9 -6
  2. adapter_model.safetensors +1 -1
  3. runs/Jul22_08-17-54_5d65eceb102c/events.out.tfevents.1721636295.5d65eceb102c.221.0 +3 -0
  4. runs/Jul22_08-17-54_5d65eceb102c/events.out.tfevents.1721636923.5d65eceb102c.221.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1729
24
 
25
  ## Model description
26
 
@@ -45,16 +45,19 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
- - num_epochs: 4
 
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | 0.3143 | 1.0 | 61 | 0.3059 |
55
- | 0.2126 | 2.0 | 122 | 0.2171 |
56
- | 0.1752 | 3.0 | 183 | 0.1815 |
57
- | 0.1633 | 4.0 | 244 | 0.1729 |
 
 
58
 
59
 
60
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.1644
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
+ - lr_scheduler_warmup_steps: 10
49
+ - num_epochs: 6
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
+ | 0.2038 | 1.0 | 61 | 0.2067 |
56
+ | 0.1683 | 2.0 | 122 | 0.1759 |
57
+ | 0.1612 | 3.0 | 183 | 0.1706 |
58
+ | 0.158 | 4.0 | 244 | 0.1669 |
59
+ | 0.1565 | 5.0 | 305 | 0.1660 |
60
+ | 0.156 | 6.0 | 366 | 0.1644 |
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:b9b78dc6287a7d755be008c7f338eaf439737bbcc2af85222bc5dc1b86aa8f3a
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28872b811e1232a31edfa433f32ca907b507958cc861da28d98f5b3708dfcdaa
3
  size 109069176
runs/Jul22_08-17-54_5d65eceb102c/events.out.tfevents.1721636295.5d65eceb102c.221.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8521466964dd54780f6496612f9bf25de39a120f35bd9c829a3da9a03bf9ce
3
+ size 7150
runs/Jul22_08-17-54_5d65eceb102c/events.out.tfevents.1721636923.5d65eceb102c.221.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b64389ca303e91795c1eb5183eb4285f39f0281bbb2b03c9661010c24b1746
3
+ size 15160
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9c285369b1efc7784a59489ee693925bfb9c7d7a02a5b062a47fc442915813
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f33dbad024860b5bfc83c54564a9d1891fc7679a59a2b209595ece712cd8c7
3
  size 5368