Hugging Face's logo

Anhltq
/
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-soft_scavenging_clam

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
rl-swarm
grpo
gensyn
I am soft scavenging clam
trl
conversational
text-generation-inference
Model card Files
xet
Community
Anhltq commited on
Commit
a5032b8
·
verified ·
1 Parent(s): faadbd7

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +2 -2
  2. model.safetensors +1 -1
  3. train_results.json +2 -2
  4. trainer_state.json +3 -3
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": -2.7790665626525877e-07,
4
- "train_runtime": 3161.8325,
5
  "train_samples": 160,
6
- "train_samples_per_second": 0.101,
7
  "train_steps_per_second": 0.006
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": -2.7790665626525877e-07,
4
+ "train_runtime": 3143.7741,
5
  "train_samples": 160,
6
+ "train_samples_per_second": 0.102,
7
  "train_steps_per_second": 0.006
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f56802790fcca3fcc69f9c09fbd2d62c07fab6a15110cc0d094adc7c40872245
3
  size 1976163472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b114055c1a1b44b7027c19bc13db83e7d9e96f9ea30a41c21eded6b713c60d17
3
  size 1976163472
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": -2.7790665626525877e-07,
4
- "train_runtime": 3161.8325,
5
  "train_samples": 160,
6
- "train_samples_per_second": 0.101,
7
  "train_steps_per_second": 0.006
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": -2.7790665626525877e-07,
4
+ "train_runtime": 3143.7741,
5
  "train_samples": 160,
6
+ "train_samples_per_second": 0.102,
7
  "train_steps_per_second": 0.006
8
  }
trainer_state.json CHANGED
@@ -183,7 +183,7 @@
183
  {
184
  "completion_length": 89.625,
185
  "epoch": 1.0,
186
- "grad_norm": 3.1471806494209886e-08,
187
  "kl": 0.0,
188
  "learning_rate": 0.0,
189
  "loss": -0.0,
@@ -204,8 +204,8 @@
204
  "step": 20,
205
  "total_flos": 0.0,
206
  "train_loss": -2.7790665626525877e-07,
207
- "train_runtime": 3161.8325,
208
- "train_samples_per_second": 0.101,
209
  "train_steps_per_second": 0.006
210
  }
211
  ],
 
183
  {
184
  "completion_length": 89.625,
185
  "epoch": 1.0,
186
+ "grad_norm": 3.0665063377455226e-08,
187
  "kl": 0.0,
188
  "learning_rate": 0.0,
189
  "loss": -0.0,
 
204
  "step": 20,
205
  "total_flos": 0.0,
206
  "train_loss": -2.7790665626525877e-07,
207
+ "train_runtime": 3143.7741,
208
+ "train_samples_per_second": 0.102,
209
  "train_steps_per_second": 0.006
210
  }
211
  ],