Hugging Face's logo

BraylonDash
/
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
a6341f3
•
1 Parent(s): 5092ad7

Model save

Browse files
Files changed (6) hide show
  1. README.md +1 -5
  2. all_results.json +3 -3
  3. runs/Mar19_14-05-25_Braylon/events.out.tfevents.1710817580.Braylon.22644.0 +3 -0
  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-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
 
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 2.5006682335515507e-05,
4
- "train_runtime": 3.6978,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 1.082,
7
- "train_steps_per_second": 0.541
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 2.5006682335515507e-05,
4
+ "train_runtime": 3.7148,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 1.077,
7
+ "train_steps_per_second": 0.538
8
  }
runs/Mar19_14-05-25_Braylon/events.out.tfevents.1710817580.Braylon.22644.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69095e625a72156ee14faad978fc92ae7f29e90ead36899d37511812019b1541
3
+ size 5793
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 2.5006682335515507e-05,
4
- "train_runtime": 3.6978,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 1.082,
7
- "train_steps_per_second": 0.541
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 2.5006682335515507e-05,
4
+ "train_runtime": 3.7148,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 1.077,
7
+ "train_steps_per_second": 0.538
8
  }
trainer_state.json CHANGED
@@ -27,9 +27,9 @@
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 2.5006682335515507e-05,
30
- "train_runtime": 3.6978,
31
- "train_samples_per_second": 1.082,
32
- "train_steps_per_second": 0.541
33
  }
34
  ],
35
  "logging_steps": 10,
 
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 2.5006682335515507e-05,
30
+ "train_runtime": 3.7148,
31
+ "train_samples_per_second": 1.077,
32
+ "train_steps_per_second": 0.538
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:b76b89590b4283663f6123b2fae64b633e0a190e3c061cbd5f383c145e8974e5
3
  size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26c28f8ab291e7da487914bf4afe4beb42cb69df5daa5a4d6f9e951b3c6f03f
3
  size 5880