Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-test-iter-1

PEFT
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Community
BraylonDash commited on
Commit
c00337c
•
1 Parent(s): a9f05ee

Model save

Browse files
Files changed (6) hide show
  1. README.md +1 -5
  2. adapter_config.json +3 -3
  3. all_results.json +2 -2
  4. train_results.json +2 -2
  5. trainer_state.json +2 -2
  6. training_args.bin +1 -1
README.md CHANGED
@@ -2,14 +2,10 @@
2
  license: mit
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
- - generated_from_trainer
7
  - trl
8
  - dpo
9
  - generated_from_trainer
10
  base_model: microsoft/phi-2
11
- datasets:
12
- - HuggingFaceH4/ultrafeedback_binarized
13
  model-index:
14
  - name: phi-2-gpo-test-iter-1
15
  results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  # phi-2-gpo-test-iter-1
22
 
23
- This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-test-iter-0](https://huggingface.co/DUAL-GPO/phi-2-gpo-test-iter-0) on the HuggingFaceH4/ultrafeedback_binarized dataset.
24
 
25
  ## Model description
26
 
 
2
  license: mit
3
  library_name: peft
4
  tags:
 
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
8
  base_model: microsoft/phi-2
 
 
9
  model-index:
10
  - name: phi-2-gpo-test-iter-1
11
  results: []
 
16
 
17
  # phi-2-gpo-test-iter-1
18
 
19
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
20
 
21
  ## Model description
22
 
adapter_config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
  "dense",
24
- "v_proj",
25
- "k_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "dense",
23
+ "q_proj",
24
+ "k_proj",
25
+ "v_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.33,
3
  "train_loss": 0.0015329468587879092,
4
- "train_runtime": 7.2892,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 2.744,
7
  "train_steps_per_second": 0.274
8
  }
 
1
  {
2
  "epoch": 1.33,
3
  "train_loss": 0.0015329468587879092,
4
+ "train_runtime": 7.3105,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 2.736,
7
  "train_steps_per_second": 0.274
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.33,
3
  "train_loss": 0.0015329468587879092,
4
- "train_runtime": 7.2892,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 2.744,
7
  "train_steps_per_second": 0.274
8
  }
 
1
  {
2
  "epoch": 1.33,
3
  "train_loss": 0.0015329468587879092,
4
+ "train_runtime": 7.3105,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 2.736,
7
  "train_steps_per_second": 0.274
8
  }
trainer_state.json CHANGED
@@ -27,8 +27,8 @@
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 0.0015329468587879092,
30
- "train_runtime": 7.2892,
31
- "train_samples_per_second": 2.744,
32
  "train_steps_per_second": 0.274
33
  }
34
  ],
 
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 0.0015329468587879092,
30
+ "train_runtime": 7.3105,
31
+ "train_samples_per_second": 2.736,
32
  "train_steps_per_second": 0.274
33
  }
34
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1545e3e119ea55ccb2756568d3ff67054bce5657c30f0f821154534a85010e1c
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:280048fc6b103273f575a888966374fd89d87ed7626c9712144913cb62125459
3
  size 5816