Hugging Face's logo

RedMist137
/
DPO-Zephyr-7B

Safetensors
mistral
trl
dpo
Generated from Trainer
Model card Files
xet
 Community
RedMist137 commited on
Commit
950fb4a
·
verified ·
1 Parent(s): a2cc2d6

Model save

Browse files
Files changed (6) hide show
  1. README.md +1 -7
  2. all_results.json +5 -5
  3. model-00001-of-00002.safetensors +1 -1
  4. model-00002-of-00002.safetensors +1 -1
  5. train_results.json +5 -5
  6. trainer_state.json +0 -0
README.md CHANGED
@@ -2,15 +2,9 @@
2
  license: other
3
  base_model: facebook/opt-2.7b
4
  tags:
5
- - alignment-handbook
6
  - trl
7
  - dpo
8
  - generated_from_trainer
9
- - trl
10
- - dpo
11
- - generated_from_trainer
12
- datasets:
13
- - RedMist137/AIHF_DPO_iter0
14
  model-index:
15
  - name: DPO-Zephyr-7B
16
  results: []
@@ -21,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  # DPO-Zephyr-7B
23
 
24
- This model is a fine-tuned version of [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b) on the RedMist137/AIHF_DPO_iter0 dataset.
25
 
26
  ## Model description
27
 
 
2
  license: other
3
  base_model: facebook/opt-2.7b
4
  tags:
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
 
 
 
 
 
8
  model-index:
9
  - name: DPO-Zephyr-7B
10
  results: []
 
15
 
16
  # DPO-Zephyr-7B
17
 
18
+ This model is a fine-tuned version of [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b) on the None dataset.
19
 
20
  ## Model description
21
 
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 0.5192557334487234,
3
  "total_flos": 0.0,
4
- "train_loss": 0.0,
5
- "train_runtime": 1.1312,
6
  "train_samples": 40000,
7
- "train_samples_per_second": 35360.967,
8
- "train_steps_per_second": 1105.03
9
  }
 
1
  {
2
+ "epoch": 1.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.69168408203125,
5
+ "train_runtime": 25620.0654,
6
  "train_samples": 40000,
7
+ "train_samples_per_second": 1.561,
8
+ "train_steps_per_second": 0.049
9
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd418fdddd3a80cfefe85a8306f00c640965e6dff3cc61d47601d265c4706f42
3
  size 4988545248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926d6a1076c6673f80db2020356316e274a18393f7a0675e59c9f9efef0747d6
3
  size 4988545248
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76f398442390d7b851d5567b3e136eb1aaccc772060868b996180ddb996b89d1
3
  size 314709704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4108a4b572d5ea6d9fa334a21e1660fa9d57bf5cb2d8688c19cc15f35a8f9b
3
  size 314709704
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 0.5192557334487234,
3
  "total_flos": 0.0,
4
- "train_loss": 0.0,
5
- "train_runtime": 1.1312,
6
  "train_samples": 40000,
7
- "train_samples_per_second": 35360.967,
8
- "train_steps_per_second": 1105.03
9
  }
 
1
  {
2
+ "epoch": 1.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.69168408203125,
5
+ "train_runtime": 25620.0654,
6
  "train_samples": 40000,
7
+ "train_samples_per_second": 1.561,
8
+ "train_steps_per_second": 0.049
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff