Hugging Face's logo

paul-stansifer
/
gemma-qwantz-punchline

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
paul-stansifer commited on
Commit
701f71a
•
1 Parent(s): 5cf4fc8

End of training

Browse files
Files changed (6) hide show
  1. README.md +7 -4
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +1 -1
  4. runs/May08_18-14-14_79b7edacd770/events.out.tfevents.1715192057.79b7edacd770.232.1 +3 -0
  5. runs/May08_18-20-04_79b7edacd770/events.out.tfevents.1715192407.79b7edacd770.232.2 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [unsloth/gemma-2b-bnb-4bit](https://huggingface.co/unsloth/gemma-2b-bnb-4bit) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6906
22
- - Accuracy: 0.6118
23
 
24
  ## Model description
25
 
@@ -44,13 +44,16 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 1
 
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 0.6361 | 1.0 | 150 | 0.6906 | 0.6118 |
 
 
54
 
55
 
56
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [unsloth/gemma-2b-bnb-4bit](https://huggingface.co/unsloth/gemma-2b-bnb-4bit) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4710
22
+ - Accuracy: 0.7824
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 3
48
+ - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.6508 | 1.0 | 150 | 0.6241 | 0.6235 |
55
+ | 0.5972 | 2.0 | 300 | 0.5388 | 0.7353 |
56
+ | 0.4801 | 3.0 | 450 | 0.4710 | 0.7824 |
57
 
58
 
59
  ### Framework versions
adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
  "k_proj",
 
25
  "o_proj",
26
  "v_proj"
27
  ],
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "k_proj",
24
+ "q_proj",
25
  "o_proj",
26
  "v_proj"
27
  ],
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d600a7db9fe81c6a3ef927cda68486c85d054f16a963d3d079984be102bf9b0d
3
  size 14781232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:233bfa7c026cab4af10fd92827fdcefc95c24695cbb8a22cbd374379ca3cd86a
3
  size 14781232
runs/May08_18-14-14_79b7edacd770/events.out.tfevents.1715192057.79b7edacd770.232.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2faf78b2aef6b8d518b340e6d52736e71a69b06ee84b6e8621969ae16adb827f
3
+ size 5703
runs/May08_18-20-04_79b7edacd770/events.out.tfevents.1715192407.79b7edacd770.232.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cf1ee121d01f181be217cd4f0880102add809de14cc4dabf05279051c572d6
3
+ size 5526
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caef5edc50ff776601202d1a233c5eba267e1aef67b7ca76f2954290d51bb334
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57da339089aadf7c674fc43dbd0bf4da9275f453d96bdc930ea886eb8e8984c
3
  size 5048