Hugging Face's logo

devamanyu
/
zephyr-7b-dpo-full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
alignment-handbook
trl
dpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
devamanyu commited on
Commit
9e0c8a4
•
1 Parent(s): fcb7cc5

Model save

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. all_results.json +4 -4
  3. train_results.json +4 -4
  4. trainer_state.json +4 -4
  5. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/devamanyu/huggingface/runs/nqluxh9k)
31
 
32
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
33
 
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/devamanyu/huggingface/runs/8zifsris)
31
 
32
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
33
 
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
- "train_loss": 1.0759161147113625,
5
- "train_runtime": 3593.5482,
6
  "train_samples": 61134,
7
- "train_samples_per_second": 17.012,
8
- "train_steps_per_second": 0.133
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 1.4704,
6
  "train_samples": 61134,
7
+ "train_samples_per_second": 41576.783,
8
+ "train_steps_per_second": 325.084
9
  }
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
- "train_loss": 1.0759161147113625,
5
- "train_runtime": 3593.5482,
6
  "train_samples": 61134,
7
- "train_samples_per_second": 17.012,
8
- "train_steps_per_second": 0.133
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 1.4704,
6
  "train_samples": 61134,
7
+ "train_samples_per_second": 41576.783,
8
+ "train_steps_per_second": 325.084
9
  }
trainer_state.json CHANGED
@@ -796,10 +796,10 @@
796
  "epoch": 1.0,
797
  "step": 478,
798
  "total_flos": 0.0,
799
- "train_loss": 1.0759161147113625,
800
- "train_runtime": 3593.5482,
801
- "train_samples_per_second": 17.012,
802
- "train_steps_per_second": 0.133
803
  }
804
  ],
805
  "logging_steps": 10,
 
796
  "epoch": 1.0,
797
  "step": 478,
798
  "total_flos": 0.0,
799
+ "train_loss": 0.0,
800
+ "train_runtime": 1.4704,
801
+ "train_samples_per_second": 41576.783,
802
+ "train_steps_per_second": 325.084
803
  }
804
  ],
805
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:565101d277f06937b87e1d29aa0bb904c367cd4ffa94d9aa8883ed10001eea8c
3
  size 7736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d317bd7a67b058be89b40bf68458d212bd37d0a756a2e6939853c1c873c93cf
3
  size 7736