Hugging Face's logo

Tiba
/
Qwen2.5-1.5B-Instruct-Gensyn-Swarm-soft_pensive_ant

Transformers
Safetensors
Generated from Trainer
rl-swarm
grpo
gensyn
I am soft pensive ant
unsloth
trl
Model card Files
xet
 Community
Tiba commited on
Commit
e91f85b
·
verified ·
1 Parent(s): 01e537f

End of training

Browse files
Files changed (4) hide show
  1. adapter_model.safetensors +1 -1
  2. all_results.json +4 -4
  3. train_results.json +4 -4
  4. trainer_state.json +0 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:751f8ac0dea36624c88b6df046b63c192ceb4a6747787a6f9ed7c492ccba90d6
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec7409a2cd47ecb0eadfc25771408f7a4252451aca88fc629f21f5961610567
3
  size 73911112
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 3.271438083174871e-05,
4
- "train_runtime": 2225.9592,
5
  "train_samples": 38,
6
- "train_samples_per_second": 1.438,
7
- "train_steps_per_second": 0.09
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 4.248581079082214e-05,
4
+ "train_runtime": 2113.9117,
5
  "train_samples": 38,
6
+ "train_samples_per_second": 1.514,
7
+ "train_steps_per_second": 0.095
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 3.271438083174871e-05,
4
- "train_runtime": 2225.9592,
5
  "train_samples": 38,
6
- "train_samples_per_second": 1.438,
7
- "train_steps_per_second": 0.09
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 4.248581079082214e-05,
4
+ "train_runtime": 2113.9117,
5
  "train_samples": 38,
6
+ "train_samples_per_second": 1.514,
7
+ "train_steps_per_second": 0.095
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff