HF中国镜像站's logo

TTTXXX01
/
Qwen2.5-1.5B-Open-R1-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
TTTXXX01 commited on
Commit
409cd31
·
verified ·
1 Parent(s): da74b0b

Model save

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. all_results.json +2 -2
  3. train_results.json +2 -2
  4. trainer_state.json +2 -2
  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/yuanyige/OpenR1/runs/uclfg0aq)
31
 
32
 
33
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 
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/yuanyige/OpenR1/runs/83pavv6e)
31
 
32
 
33
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
all_results.json CHANGED
@@ -7,8 +7,8 @@
7
  "eval_steps_per_second": 0.025,
8
  "total_flos": 0.0,
9
  "train_loss": 18.18843185901642,
10
- "train_runtime": 28.8641,
11
  "train_samples": 72441,
12
- "train_samples_per_second": 3.43,
13
  "train_steps_per_second": 0.035
14
  }
 
7
  "eval_steps_per_second": 0.025,
8
  "total_flos": 0.0,
9
  "train_loss": 18.18843185901642,
10
+ "train_runtime": 28.7694,
11
  "train_samples": 72441,
12
+ "train_samples_per_second": 3.441,
13
  "train_steps_per_second": 0.035
14
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 18.18843185901642,
4
- "train_runtime": 28.8641,
5
  "train_samples": 72441,
6
- "train_samples_per_second": 3.43,
7
  "train_steps_per_second": 0.035
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 18.18843185901642,
4
+ "train_runtime": 28.7694,
5
  "train_samples": 72441,
6
+ "train_samples_per_second": 3.441,
7
  "train_steps_per_second": 0.035
8
  }
trainer_state.json CHANGED
@@ -19,8 +19,8 @@
19
  "step": 0,
20
  "total_flos": 0.0,
21
  "train_loss": 18.18843185901642,
22
- "train_runtime": 28.8641,
23
- "train_samples_per_second": 3.43,
24
  "train_steps_per_second": 0.035
25
  }
26
  ],
 
19
  "step": 0,
20
  "total_flos": 0.0,
21
  "train_loss": 18.18843185901642,
22
+ "train_runtime": 28.7694,
23
+ "train_samples_per_second": 3.441,
24
  "train_steps_per_second": 0.035
25
  }
26
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4cb960ae5f3824a0620531afc22d0e5240365c7568a5b3c920037d0ad3450e7
3
  size 7608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b2b87d79dce701d2c1845ef7906b24c20a4c1316dc593d94aa32576dbe9276
3
  size 7608