Hugging Face's logo

haizhongzheng
/
Llama-3.2-1B-dpo-lora

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
haizhongzheng commited on
Commit
a02ff0c
•
1 Parent(s): b96cab0

Model save

Browse files
Files changed (6) hide show
  1. adapter_config.json +4 -4
  2. all_results.json +4 -4
  3. runs/Nov21_11-21-27_novi/events.out.tfevents.1732206093.novi.844228.0 +3 -0
  4. train_results.json +4 -4
  5. trainer_state.json +4 -4
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "gate_proj",
 
24
  "k_proj",
25
  "o_proj",
26
- "q_proj",
27
- "v_proj",
28
  "up_proj",
29
- "down_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "down_proj",
24
+ "q_proj",
25
  "k_proj",
26
  "o_proj",
 
 
27
  "up_proj",
28
+ "gate_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.6070349644347967,
5
- "train_runtime": 21926.9285,
6
  "train_samples": 61134,
7
- "train_samples_per_second": 2.788,
8
- "train_steps_per_second": 0.174
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.0101,
6
  "train_samples": 61134,
7
+ "train_samples_per_second": 6068984.159,
8
+ "train_steps_per_second": 379323.919
9
  }
runs/Nov21_11-21-27_novi/events.out.tfevents.1732206093.novi.844228.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87dd36fa1206aec63ea92b18bde19e86d7994d8b3561cd45357564b696b84176
3
+ size 6737
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.6070349644347967,
5
- "train_runtime": 21926.9285,
6
  "train_samples": 61134,
7
- "train_samples_per_second": 2.788,
8
- "train_steps_per_second": 0.174
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.0101,
6
  "train_samples": 61134,
7
+ "train_samples_per_second": 6068984.159,
8
+ "train_steps_per_second": 379323.919
9
  }
trainer_state.json CHANGED
@@ -6365,10 +6365,10 @@
6365
  "epoch": 1.0,
6366
  "step": 3821,
6367
  "total_flos": 0.0,
6368
- "train_loss": 0.6070349644347967,
6369
- "train_runtime": 21926.9285,
6370
- "train_samples_per_second": 2.788,
6371
- "train_steps_per_second": 0.174
6372
  }
6373
  ],
6374
  "logging_steps": 10,
 
6365
  "epoch": 1.0,
6366
  "step": 3821,
6367
  "total_flos": 0.0,
6368
+ "train_loss": 0.0,
6369
+ "train_runtime": 0.0101,
6370
+ "train_samples_per_second": 6068984.159,
6371
+ "train_steps_per_second": 379323.919
6372
  }
6373
  ],
6374
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44207f4f7dc468c9e8df355fc3da2d243e7878b1538f08273e2272a9d1ba17e7
3
  size 6328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd7f1dfa59ed39bf5f60b5a68d7dd810dee35322e3b9080465ba967487ba2cd
3
  size 6328