Hugging Face's logo

nblinh
/
fcd3320e-2511-4e7b-a81e-8b77b18ba2eb

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files
xet
 Community
nblinh commited on
Commit
cf6b79b
·
verified ·
1 Parent(s): eeac779

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -2
  2. adapter_config.json +4 -4
  3. adapter_model.bin +1 -1
  4. adapter_model.safetensors +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -103,7 +103,7 @@ xformers_attention: true
103
 
104
  This model is a fine-tuned version of [UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2) on the None dataset.
105
  It achieves the following results on the evaluation set:
106
- - Loss: 0.7235
107
 
108
  ## Model description
109
 
@@ -135,7 +135,7 @@ The following hyperparameters were used during training:
135
 
136
  | Training Loss | Epoch | Step | Validation Loss |
137
  |:-------------:|:------:|:----:|:---------------:|
138
- | 0.5281 | 0.0002 | 10 | 0.7235 |
139
 
140
 
141
  ### Framework versions
 
103
 
104
  This model is a fine-tuned version of [UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2) on the None dataset.
105
  It achieves the following results on the evaluation set:
106
+ - Loss: 0.7176
107
 
108
  ## Model description
109
 
 
135
 
136
  | Training Loss | Epoch | Step | Validation Loss |
137
  |:-------------:|:------:|:----:|:---------------:|
138
+ | 0.528 | 0.0002 | 10 | 0.7176 |
139
 
140
 
141
  ### Framework versions
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "down_proj",
24
  "up_proj",
 
 
25
  "k_proj",
26
- "q_proj",
27
  "v_proj",
28
- "gate_proj",
29
- "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "up_proj",
24
+ "down_proj",
25
+ "gate_proj",
26
  "k_proj",
27
+ "o_proj",
28
  "v_proj",
29
+ "q_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ac5b93a61d33d9e47c66fde3f492f4b7d9c189bcb2981bccceeb9f9a8322dbb
3
  size 216284090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4479f642fa2d8104ea0212bc5495378a7ed617b85e1a933ab69e622816117857
3
  size 216284090
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4b569559ed4be0892c235e9791476a541ba8627b097ec23aef14b6f52f972f3
3
  size 216151256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c56271fb1b2aedb9192349bd769da25e531e0e1b7bba9d27702d7704ca37d1c
3
  size 216151256
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d7a1ea565272c88a63086fe3898cbfb6f6f2710b65646ee539fb346c82da79b
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37503f281ce88f417c09a5c7e2d060f21c1647c1e90277b15fbbf3e5c97863ce
3
  size 6776