Hugging Face's logo

itufilum
/
Qwen2.5-1.5B-Instruct-Gensyn-Swarm-invisible_domestic_impala

Transformers
Safetensors
Generated from Trainer
rl-swarm
grpo
gensyn
I am invisible domestic impala
unsloth
trl
Model card Files Community
itufilum commited on
Commit
a176874
·
verified ·
1 Parent(s): b98877d

End of training

Browse files
Files changed (6) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. all_results.json +5 -5
  4. train_results.json +5 -5
  5. trainer_state.json +0 -0
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -24,13 +24,13 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
 
 
27
  "down_proj",
28
  "v_proj",
29
  "o_proj",
30
- "gate_proj",
31
- "up_proj",
32
  "k_proj",
33
- "q_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "q_proj",
28
+ "gate_proj",
29
  "down_proj",
30
  "v_proj",
31
  "o_proj",
 
 
32
  "k_proj",
33
+ "up_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3883d1b1d65e27432c874bf4be8b540f775e76cd64ceca5976601226af13660
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f40c4f67e4a4e2d2f33813c4d23d8e9163f47b699e2692a589303ae9cf06de7
3
  size 73911112
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.5662221504601517,
4
- "train_runtime": 16616.0393,
5
- "train_samples": 465,
6
- "train_samples_per_second": 0.674,
7
- "train_steps_per_second": 0.042
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.018085778060549274,
4
+ "train_runtime": 4235.9857,
5
+ "train_samples": 284,
6
+ "train_samples_per_second": 1.511,
7
+ "train_steps_per_second": 0.094
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.5662221504601517,
4
- "train_runtime": 16616.0393,
5
- "train_samples": 465,
6
- "train_samples_per_second": 0.674,
7
- "train_steps_per_second": 0.042
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.018085778060549274,
4
+ "train_runtime": 4235.9857,
5
+ "train_samples": 284,
6
+ "train_samples_per_second": 1.511,
7
+ "train_steps_per_second": 0.094
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65478c3d6835104e11164c00916a38422b4fb5ac130ef99fa8547d06a33bffab
3
  size 6008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e394bc452d114023b97bd623ddd5de8155d6d5573daf31bbe20869631e1d42
3
  size 6008