Hugging Face's logo

yueliu1999
/
GuardReasoner-3B

Text Classification
Transformers
Safetensors
llama-factory
full
Generated from Trainer
Inference Endpoints
Model card Files Community
3
yueliu1999 commited on
Commit
6de1f09
·
1 Parent(s): e821fae

update

Browse files
Files changed (17) hide show
  1. .gitattributes +12 -0
  2. README.md +19 -3
  3. all_results.json +3 -0
  4. config.json +3 -0
  5. generation_config.json +3 -0
  6. model-00001-of-00002.safetensors +3 -0
  7. model-00002-of-00002.safetensors +3 -0
  8. model.safetensors.index.json +3 -0
  9. special_tokens_map.json +3 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +3 -0
  12. train_results.json +3 -0
  13. trainer_log.jsonl +22 -0
  14. trainer_state.json +3 -0
  15. training_args.bin +3 -0
  16. training_loss.png +0 -0
  17. training_rewards_accuracies.png +0 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
37
+ special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
38
+ trainer_state.json filter=lfs diff=lfs merge=lfs -text
39
+ train_results.json filter=lfs diff=lfs merge=lfs -text
40
+ config.json filter=lfs diff=lfs merge=lfs -text
41
+ generation_config.json filter=lfs diff=lfs merge=lfs -text
42
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
43
+ tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
44
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ all_results.json filter=lfs diff=lfs merge=lfs -text
46
+ model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
47
+ model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,19 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: meta-llama/Llama-3.2-3B
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: GuardReasoner 3B
11
+ results: []
12
+ ---
13
+
14
+
15
+ # GuardReasoner 3B
16
+
17
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) via R-SFT and HS-DPO.
18
+
19
+
all_results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5a9f3ac8e30da5889e9761c7899a51933369a3e350cfea17d9e3cd69265572
3
+ size 255
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409d0ee9eec524929b50cdb6a3999e32dbd76faa82ed169490daea918eb02b20
3
+ size 906
generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6bd0b30e743618c41de600b71fe491ba7060cd6f728d737371e55c6cd544352
3
+ size 180
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7587cf5bd5e7d4a789d447bc101cd88a3a74893fbbedf47a0a55b809bb3c6f6
3
+ size 4965799096
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bdeae4874d9796fd250c0690548ae9f559265aac1e16db8245f8e610a8857b6
3
+ size 1459729952
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a57c30afc07c81610ae7fe013bea3b9d50365f9a8145ae98e8714220f3d7c7c
3
+ size 20919
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208d307467cabecb563e033fdb478b7c11a1bc6eca9a9c761bf6a303ccfce4c1
3
+ size 439
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd2ab776c0ad7171e4ba6ed31aba7c04843bc531da2875d91f49b35db660f4a
3
+ size 51269
train_results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5a9f3ac8e30da5889e9761c7899a51933369a3e350cfea17d9e3cd69265572
3
+ size 255
trainer_log.jsonl ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 108, "loss": 0.9057, "accuracy": 0.4039062559604645, "lr": 4.973604096452361e-06, "epoch": 0.0912981455064194, "percentage": 4.63, "elapsed_time": "0:03:13", "remaining_time": "1:06:23", "throughput": 8456.15, "total_tokens": 1635024}
2
+ {"current_steps": 10, "total_steps": 108, "loss": 0.9105, "accuracy": 0.5335937738418579, "lr": 4.894973780788722e-06, "epoch": 0.1825962910128388, "percentage": 9.26, "elapsed_time": "0:06:02", "remaining_time": "0:59:11", "throughput": 8960.73, "total_tokens": 3247056}
3
+ {"current_steps": 15, "total_steps": 108, "loss": 0.9091, "accuracy": 0.55078125, "lr": 4.765769467591626e-06, "epoch": 0.2738944365192582, "percentage": 13.89, "elapsed_time": "0:08:49", "remaining_time": "0:54:45", "throughput": 9210.88, "total_tokens": 4880736}
4
+ {"current_steps": 20, "total_steps": 108, "loss": 0.9107, "accuracy": 0.5515625476837158, "lr": 4.588719528532342e-06, "epoch": 0.3651925820256776, "percentage": 18.52, "elapsed_time": "0:11:39", "remaining_time": "0:51:16", "throughput": 9303.67, "total_tokens": 6504992}
5
+ {"current_steps": 25, "total_steps": 108, "loss": 0.9122, "accuracy": 0.5421874523162842, "lr": 4.367562678102491e-06, "epoch": 0.456490727532097, "percentage": 23.15, "elapsed_time": "0:14:26", "remaining_time": "0:47:57", "throughput": 9408.9, "total_tokens": 8154176}
6
+ {"current_steps": 30, "total_steps": 108, "loss": 0.9074, "accuracy": 0.5546875, "lr": 4.106969024216348e-06, "epoch": 0.5477888730385164, "percentage": 27.78, "elapsed_time": "0:17:16", "remaining_time": "0:44:54", "throughput": 9468.53, "total_tokens": 9810992}
7
+ {"current_steps": 35, "total_steps": 108, "loss": 0.9083, "accuracy": 0.5367187261581421, "lr": 3.8124414508364005e-06, "epoch": 0.6390870185449358, "percentage": 32.41, "elapsed_time": "0:20:02", "remaining_time": "0:41:48", "throughput": 9540.69, "total_tokens": 11475520}
8
+ {"current_steps": 40, "total_steps": 108, "loss": 0.9083, "accuracy": 0.5789062976837158, "lr": 3.4901994150978926e-06, "epoch": 0.7303851640513552, "percentage": 37.04, "elapsed_time": "0:22:50", "remaining_time": "0:38:49", "throughput": 9562.92, "total_tokens": 13103344}
9
+ {"current_steps": 45, "total_steps": 108, "loss": 0.9058, "accuracy": 0.5804687738418579, "lr": 3.147047612756302e-06, "epoch": 0.8216833095577746, "percentage": 41.67, "elapsed_time": "0:25:36", "remaining_time": "0:35:51", "throughput": 9610.35, "total_tokens": 14770400}
10
+ {"current_steps": 50, "total_steps": 108, "loss": 0.906, "accuracy": 0.5687500238418579, "lr": 2.7902322853130758e-06, "epoch": 0.912981455064194, "percentage": 46.3, "elapsed_time": "0:28:24", "remaining_time": "0:32:57", "throughput": 9625.44, "total_tokens": 16407968}
11
+ {"current_steps": 55, "total_steps": 108, "loss": 0.8844, "accuracy": 0.6742187738418579, "lr": 2.4272882031422216e-06, "epoch": 1.0171184022824535, "percentage": 50.93, "elapsed_time": "0:31:11", "remaining_time": "0:30:03", "throughput": 9636.87, "total_tokens": 18033440}
12
+ {"current_steps": 60, "total_steps": 108, "loss": 0.7792, "accuracy": 0.9820312857627869, "lr": 2.0658795558326745e-06, "epoch": 1.108416547788873, "percentage": 55.56, "elapsed_time": "0:33:56", "remaining_time": "0:27:09", "throughput": 9653.47, "total_tokens": 19663456}
13
+ {"current_steps": 65, "total_steps": 108, "loss": 0.7655, "accuracy": 0.971875011920929, "lr": 1.7136381096209665e-06, "epoch": 1.1997146932952925, "percentage": 60.19, "elapsed_time": "0:36:45", "remaining_time": "0:24:18", "throughput": 9667.4, "total_tokens": 21320512}
14
+ {"current_steps": 70, "total_steps": 108, "loss": 0.7554, "accuracy": 0.9710937738418579, "lr": 1.3780020494988447e-06, "epoch": 1.291012838801712, "percentage": 64.81, "elapsed_time": "0:39:32", "remaining_time": "0:21:27", "throughput": 9665.04, "total_tokens": 22925920}
15
+ {"current_steps": 75, "total_steps": 108, "loss": 0.7501, "accuracy": 0.9742187857627869, "lr": 1.0660589091223854e-06, "epoch": 1.3823109843081314, "percentage": 69.44, "elapsed_time": "0:42:18", "remaining_time": "0:18:36", "throughput": 9671.43, "total_tokens": 24546784}
16
+ {"current_steps": 80, "total_steps": 108, "loss": 0.745, "accuracy": 0.973437488079071, "lr": 7.843959053281663e-07, "epoch": 1.4736091298145506, "percentage": 74.07, "elapsed_time": "0:45:03", "remaining_time": "0:15:46", "throughput": 9688.45, "total_tokens": 26195552}
17
+ {"current_steps": 85, "total_steps": 108, "loss": 0.7364, "accuracy": 0.9749999642372131, "lr": 5.389608377010608e-07, "epoch": 1.56490727532097, "percentage": 78.7, "elapsed_time": "0:47:48", "remaining_time": "0:12:56", "throughput": 9703.97, "total_tokens": 27834928}
18
+ {"current_steps": 90, "total_steps": 108, "loss": 0.7328, "accuracy": 0.9820312261581421, "lr": 3.3493649053890325e-07, "epoch": 1.6562054208273893, "percentage": 83.33, "elapsed_time": "0:50:35", "remaining_time": "0:10:07", "throughput": 9710.41, "total_tokens": 29475168}
19
+ {"current_steps": 95, "total_steps": 108, "loss": 0.7339, "accuracy": 0.977343738079071, "lr": 1.7663118943294367e-07, "epoch": 1.7475035663338088, "percentage": 87.96, "elapsed_time": "0:53:22", "remaining_time": "0:07:18", "throughput": 9724.65, "total_tokens": 31144800}
20
+ {"current_steps": 100, "total_steps": 108, "loss": 0.739, "accuracy": 0.977343738079071, "lr": 6.738782355044048e-08, "epoch": 1.8388017118402282, "percentage": 92.59, "elapsed_time": "0:56:11", "remaining_time": "0:04:29", "throughput": 9727.16, "total_tokens": 32791472}
21
+ {"current_steps": 105, "total_steps": 108, "loss": 0.739, "accuracy": 0.975781261920929, "lr": 9.513254770636138e-09, "epoch": 1.9300998573466477, "percentage": 97.22, "elapsed_time": "0:58:56", "remaining_time": "0:01:41", "throughput": 9738.31, "total_tokens": 34444000}
22
+ {"current_steps": 108, "total_steps": 108, "epoch": 1.9848787446504992, "percentage": 100.0, "elapsed_time": "1:00:48", "remaining_time": "0:00:00", "throughput": 9710.57, "total_tokens": 35430880}
trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8743d39fee190372b72c4899bacd55262c2e6d578a956184a18d5fe14229c998
3
+ size 13152
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afdfd97a49d9747d3f6396d87310483deac0c776d9e28032924c0feb4c2f76c
3
+ size 7288
training_loss.png ADDED
training_rewards_accuracies.png ADDED