Hugging Face's logo

flyyufelix
/
Qwen-2.5-7B-Simple-RL

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
flyyufelix commited on
Commit
191b655
·
verified ·
1 Parent(s): f479f7e

Model save

Browse files
Files changed (5) hide show
  1. adapter_config.json +4 -4
  2. all_results.json +2 -2
  3. train_results.json +2 -2
  4. trainer_state.json +2 -2
  5. training_args.bin +2 -2
adapter_config.json CHANGED
@@ -23,13 +23,13 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
 
26
  "q_proj",
27
- "o_proj",
28
  "down_proj",
29
  "k_proj",
30
- "up_proj",
31
- "v_proj",
32
- "gate_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "up_proj",
27
+ "v_proj",
28
+ "gate_proj",
29
  "q_proj",
 
30
  "down_proj",
31
  "k_proj",
32
+ "o_proj"
 
 
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 48.8842,
5
  "train_samples": 7500,
6
- "train_samples_per_second": 0.327,
7
  "train_steps_per_second": 0.02
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 49.2958,
5
  "train_samples": 7500,
6
+ "train_samples_per_second": 0.325,
7
  "train_steps_per_second": 0.02
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 48.8842,
5
  "train_samples": 7500,
6
- "train_samples_per_second": 0.327,
7
  "train_steps_per_second": 0.02
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 49.2958,
5
  "train_samples": 7500,
6
+ "train_samples_per_second": 0.325,
7
  "train_steps_per_second": 0.02
8
  }
trainer_state.json CHANGED
@@ -27,8 +27,8 @@
27
  "step": 1,
28
  "total_flos": 0.0,
29
  "train_loss": 0.0,
30
- "train_runtime": 48.8842,
31
- "train_samples_per_second": 0.327,
32
  "train_steps_per_second": 0.02
33
  }
34
  ],
 
27
  "step": 1,
28
  "total_flos": 0.0,
29
  "train_loss": 0.0,
30
+ "train_runtime": 49.2958,
31
+ "train_samples_per_second": 0.325,
32
  "train_steps_per_second": 0.02
33
  }
34
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5b194307e6c24945ff1ba49c49cffa44544d0fe79d6516f1c19296273677ed1
3
- size 6584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a583b94977bd994f0e18110bd26ee8dce871621ac897bf26644714c54342d23
3
+ size 6520