Hugging Face's logo

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

PEFT
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Community
BraylonDash commited on
Commit
dca548a
•
1 Parent(s): c4868ba

Model save

Browse files
Files changed (6) hide show
  1. README.md +1 -5
  2. adapter_config.json +3 -3
  3. all_results.json +3 -3
  4. train_results.json +3 -3
  5. trainer_state.json +3 -3
  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-longest-iter-0
15
  results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  # phi-2-gpo-test-longest-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-longest-iter-0
11
  results: []
 
16
 
17
  # phi-2-gpo-test-longest-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
- "v_proj",
23
- "dense",
24
  "q_proj",
25
- "k_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "k_proj",
 
23
  "q_proj",
24
+ "v_proj",
25
+ "dense"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.33,
3
  "train_loss": 0.0029907251009717584,
4
- "train_runtime": 7.9772,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 2.256,
7
- "train_steps_per_second": 0.251
8
  }
 
1
  {
2
  "epoch": 1.33,
3
  "train_loss": 0.0029907251009717584,
4
+ "train_runtime": 8.1822,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 2.2,
7
+ "train_steps_per_second": 0.244
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.33,
3
  "train_loss": 0.0029907251009717584,
4
- "train_runtime": 7.9772,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 2.256,
7
- "train_steps_per_second": 0.251
8
  }
 
1
  {
2
  "epoch": 1.33,
3
  "train_loss": 0.0029907251009717584,
4
+ "train_runtime": 8.1822,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 2.2,
7
+ "train_steps_per_second": 0.244
8
  }
trainer_state.json CHANGED
@@ -27,9 +27,9 @@
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 0.0029907251009717584,
30
- "train_runtime": 7.9772,
31
- "train_samples_per_second": 2.256,
32
- "train_steps_per_second": 0.251
33
  }
34
  ],
35
  "logging_steps": 10,
 
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 0.0029907251009717584,
30
+ "train_runtime": 8.1822,
31
+ "train_samples_per_second": 2.2,
32
+ "train_steps_per_second": 0.244
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:c9d5fba5aa2d52c5c13aca2a85588c7109f576c68ce8d7649266dff2bfdf5fbd
3
  size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b0c0e98c2107e656523ce58ba178549db02437fab37205bc665050802862a9
3
  size 5880