Hugging Face's logo

tsk-18
/
ft-google-gemma-2b-it-qlora

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Community
tsk-18 commited on
Commit
24b3b2f
·
verified ·
1 Parent(s): f2a10a7

End of training

Browse files
Files changed (4) hide show
  1. README.md +7 -5
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 3.2462
22
 
23
  ## Model description
24
 
@@ -45,16 +45,18 @@ The following hyperparameters were used during training:
45
  - total_train_batch_size: 128
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
- - num_epochs: 10
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 0.1109 | 3.0 | 3 | 2.8722 |
56
- | 0.0491 | 6.0 | 6 | 2.9571 |
57
- | 0.0153 | 9.0 | 9 | 3.2462 |
 
 
58
 
59
 
60
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.6079
22
 
23
  ## Model description
24
 
 
45
  - total_train_batch_size: 128
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
+ - num_epochs: 5
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
+ | 0.2365 | 1.0 | 1 | 2.6422 |
56
+ | 0.1717 | 2.0 | 2 | 2.2893 |
57
+ | 0.1298 | 3.0 | 3 | 1.9988 |
58
+ | 0.0971 | 4.0 | 4 | 1.7610 |
59
+ | 0.0673 | 5.0 | 5 | 1.6079 |
60
 
61
 
62
  ### Framework versions
adapter_config.json CHANGED
@@ -22,13 +22,13 @@
22
  "rank_pattern": {},
23
  "revision": null,
24
  "target_modules": [
25
- "o_proj",
26
- "v_proj",
27
- "up_proj",
28
  "down_proj",
29
- "q_proj",
30
  "k_proj",
31
- "gate_proj"
 
 
 
 
32
  ],
33
  "task_type": "CAUSAL_LM",
34
  "use_dora": false,
 
22
  "rank_pattern": {},
23
  "revision": null,
24
  "target_modules": [
 
 
 
25
  "down_proj",
 
26
  "k_proj",
27
+ "q_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "up_proj",
31
+ "v_proj"
32
  ],
33
  "task_type": "CAUSAL_LM",
34
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6562914367ab4d707f5fbaba0c442459945c284fafe0fe3489c411cc3be553d
3
  size 4272785368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb2289b4970f2987ee7d02c9217dcc1efcf6e9b408f11b17ce008fb8dfd147b
3
  size 4272785368
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a778874a950e756317234ae0ce3d7fa2d9b2e61330e8ab192d56bc97cf42659
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:034fb7a7a10feafe9976b983194d753fdb18014da327b2e717d5f9e840345887
3
  size 4920