Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-test-iter-0

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
BraylonDash commited on
Commit
ca3bff4
•
1 Parent(s): eabbb0f

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -5
  2. adapter_config.json +3 -3
  3. all_results.json +3 -3
  4. runs/Mar20_14-41-56_Braylon/events.out.tfevents.1710906175.Braylon.13917.0 +3 -0
  5. train_results.json +3 -3
  6. trainer_state.json +3 -3
  7. 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-0
15
  results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  # phi-2-gpo-test-iter-0
22
 
23
- This model is a fine-tuned version of [lole25/phi-2-sft-ultrachat-lora](https://huggingface.co/lole25/phi-2-sft-ultrachat-lora) 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-0
11
  results: []
 
16
 
17
  # phi-2-gpo-test-iter-0
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
  "k_proj",
25
- "v_proj"
 
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "k_proj",
23
+ "v_proj",
24
+ "dense",
25
+ "q_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 0.00012263256940059364,
4
- "train_runtime": 3.7023,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 2.161,
7
- "train_steps_per_second": 0.54
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 0.00012263256940059364,
4
+ "train_runtime": 3.6855,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 2.171,
7
+ "train_steps_per_second": 0.543
8
  }
runs/Mar20_14-41-56_Braylon/events.out.tfevents.1710906175.Braylon.13917.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a429e2c0b8e4a7111bda054c71a61fb7004251eb8ca7bcd9f615bbd95f7d4a1
3
+ size 5781
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 0.00012263256940059364,
4
- "train_runtime": 3.7023,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 2.161,
7
- "train_steps_per_second": 0.54
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 0.00012263256940059364,
4
+ "train_runtime": 3.6855,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 2.171,
7
+ "train_steps_per_second": 0.543
8
  }
trainer_state.json CHANGED
@@ -27,9 +27,9 @@
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 0.00012263256940059364,
30
- "train_runtime": 3.7023,
31
- "train_samples_per_second": 2.161,
32
- "train_steps_per_second": 0.54
33
  }
34
  ],
35
  "logging_steps": 10,
 
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 0.00012263256940059364,
30
+ "train_runtime": 3.6855,
31
+ "train_samples_per_second": 2.171,
32
+ "train_steps_per_second": 0.543
33
  }
34
  ],
35
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32378785ad512c229817f552b2a3b8b8ae06d0cf23c1f6781bfb823757866d23
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b7cfc6de10dd065e750b9eeb306e378a137575418805710f063e8d52be2642
3
  size 5816