Hugging Face's logo

flyingbugs
/
Qwen2.5-Math-7B-math220k-pruned-correctness-ratio

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
Model card Files
xet
 Community
flyingbugs commited on
Commit
8e08ac4
·
verified ·
1 Parent(s): 099cff9

Model save

Browse files
Files changed (4) hide show
  1. README.md +2 -4
  2. all_results.json +3 -3
  3. train_results.json +3 -3
  4. trainer_state.json +0 -0
README.md CHANGED
@@ -1,11 +1,9 @@
1
  ---
2
  base_model: Qwen/Qwen2.5-Math-7B-Instruct
3
- datasets: flyingbugs/OpenR1-Math-220k-pruned-keep-0.5-end-start-0.5-correctness
4
  library_name: transformers
5
  model_name: Qwen2.5-Math-7B-math220k-pruned-correctness-ratio
6
  tags:
7
  - generated_from_trainer
8
- - open-r1
9
  - trl
10
  - sft
11
  licence: license
@@ -13,7 +11,7 @@ licence: license
13
 
14
  # Model Card for Qwen2.5-Math-7B-math220k-pruned-correctness-ratio
15
 
16
- This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) on the [flyingbugs/OpenR1-Math-220k-pruned-keep-0.5-end-start-0.5-correctness](https://huggingface.co/datasets/flyingbugs/OpenR1-Math-220k-pruned-keep-0.5-end-start-0.5-correctness) dataset.
17
  It has been trained using [TRL](https://github.com/huggingface/trl).
18
 
19
  ## Quick start
@@ -29,7 +27,7 @@ print(output["generated_text"])
29
 
30
  ## Training procedure
31
 
32
- [<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/jjh233/huggingface/runs/ncfncrt9)
33
 
34
 
35
  This model was trained with SFT.
 
1
  ---
2
  base_model: Qwen/Qwen2.5-Math-7B-Instruct
 
3
  library_name: transformers
4
  model_name: Qwen2.5-Math-7B-math220k-pruned-correctness-ratio
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
  - sft
9
  licence: license
 
11
 
12
  # Model Card for Qwen2.5-Math-7B-math220k-pruned-correctness-ratio
13
 
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
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/jjh233/huggingface/runs/eq48z0zn)
31
 
32
 
33
  This model was trained with SFT.
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "total_flos": 1.729506077931733e+18,
3
- "train_loss": 0.3741078261166443,
4
- "train_runtime": 117297.1766,
5
  "train_samples": 93733,
6
  "train_samples_per_second": 0.276,
7
  "train_steps_per_second": 0.017
 
1
  {
2
+ "total_flos": 1.421068017420206e+18,
3
+ "train_loss": 0.4403897248857372,
4
+ "train_runtime": 96505.9294,
5
  "train_samples": 93733,
6
  "train_samples_per_second": 0.276,
7
  "train_steps_per_second": 0.017
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "total_flos": 1.729506077931733e+18,
3
- "train_loss": 0.3741078261166443,
4
- "train_runtime": 117297.1766,
5
  "train_samples": 93733,
6
  "train_samples_per_second": 0.276,
7
  "train_steps_per_second": 0.017
 
1
  {
2
+ "total_flos": 1.421068017420206e+18,
3
+ "train_loss": 0.4403897248857372,
4
+ "train_runtime": 96505.9294,
5
  "train_samples": 93733,
6
  "train_samples_per_second": 0.276,
7
  "train_steps_per_second": 0.017
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff