Hugging Face's logo

kangdawei
/
DAPO-7B

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
dapo
trl
conversational
text-generation-inference
Model card Files
xet
Community
kangdawei commited on
Commit
5a06c04
·
verified ·
1 Parent(s): 6257ba2

Training in progress, step 110

Browse files
Files changed (10) hide show
  1. adapter_config.json +4 -4
  2. adapter_model.safetensors +2 -2
  3. config.json +2 -1
  4. dynamic_sampling_log.txt +80 -0
  5. generation_config.json +4 -1
  6. model-00001-of-00004.safetensors +1 -1
  7. model-00002-of-00004.safetensors +1 -1
  8. model-00003-of-00004.safetensors +1 -1
  9. tokenizer.json +2 -2
  10. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -29,13 +29,13 @@
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
- "q_proj",
33
- "gate_proj",
34
  "v_proj",
35
- "k_proj",
36
  "o_proj",
37
  "up_proj",
38
- "down_proj"
 
 
39
  ],
40
  "target_parameters": null,
41
  "task_type": "CAUSAL_LM",
 
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
 
 
32
  "v_proj",
33
+ "down_proj",
34
  "o_proj",
35
  "up_proj",
36
+ "q_proj",
37
+ "k_proj",
38
+ "gate_proj"
39
  ],
40
  "target_parameters": null,
41
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
- size 40
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e29f20fde548c0097042b6cdacfabace5e93fd257e1e6b96007e508248fc830a
3
+ size 323014560
config.json CHANGED
@@ -3,7 +3,7 @@
3
  "Qwen2ForCausalLM"
4
  ],
5
  "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
  "dtype": "bfloat16",
8
  "eos_token_id": 151643,
9
  "hidden_act": "silu",
@@ -46,6 +46,7 @@
46
  "num_attention_heads": 28,
47
  "num_hidden_layers": 28,
48
  "num_key_value_heads": 4,
 
49
  "rms_norm_eps": 1e-06,
50
  "rope_scaling": null,
51
  "rope_theta": 10000,
 
3
  "Qwen2ForCausalLM"
4
  ],
5
  "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
  "dtype": "bfloat16",
8
  "eos_token_id": 151643,
9
  "hidden_act": "silu",
 
46
  "num_attention_heads": 28,
47
  "num_hidden_layers": 28,
48
  "num_key_value_heads": 4,
49
+ "pad_token_id": 151643,
50
  "rms_norm_eps": 1e-06,
51
  "rope_scaling": null,
52
  "rope_theta": 10000,
dynamic_sampling_log.txt CHANGED
@@ -803,3 +803,83 @@ Step Attempts Total Prompts Valid Prompts Efficiency
803
  99 3 18 6 33.3 %
804
  99 2 12 6 50.0 %
805
  99 3 18 6 33.3 %
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
803
  99 3 18 6 33.3 %
804
  99 2 12 6 50.0 %
805
  99 3 18 6 33.3 %
806
+ 100 4 24 6 25.0 %
807
+ 100 3 18 6 33.3 %
808
+ 100 4 24 6 25.0 %
809
+ 100 2 12 6 50.0 %
810
+ 100 3 18 6 33.3 %
811
+ 100 7 42 6 14.3 %
812
+ 100 3 18 6 33.3 %
813
+ 100 3 18 6 33.3 %
814
+ 101 5 30 6 20.0 %
815
+ 101 2 12 6 50.0 %
816
+ 101 2 12 6 50.0 %
817
+ 101 3 18 6 33.3 %
818
+ 101 4 24 6 25.0 %
819
+ 101 4 24 6 25.0 %
820
+ 101 3 18 6 33.3 %
821
+ 101 8 48 6 12.5 %
822
+ 102 4 24 6 25.0 %
823
+ 102 5 30 6 20.0 %
824
+ 102 4 24 6 25.0 %
825
+ 102 3 18 6 33.3 %
826
+ 102 3 18 6 33.3 %
827
+ 102 2 12 6 50.0 %
828
+ 102 5 30 6 20.0 %
829
+ 102 4 24 6 25.0 %
830
+ 103 1 6 6 100.0 %
831
+ 103 4 24 6 25.0 %
832
+ 103 3 18 6 33.3 %
833
+ 103 2 12 6 50.0 %
834
+ 103 2 12 6 50.0 %
835
+ 103 9 54 6 11.1 %
836
+ 103 6 36 6 16.7 %
837
+ 103 2 12 6 50.0 %
838
+ 104 2 12 6 50.0 %
839
+ 104 1 6 6 100.0 %
840
+ 104 8 48 6 12.5 %
841
+ 104 4 24 6 25.0 %
842
+ 104 6 36 6 16.7 %
843
+ 104 2 12 6 50.0 %
844
+ 104 2 12 6 50.0 %
845
+ 104 8 48 6 12.5 %
846
+ 105 4 24 6 25.0 %
847
+ 105 3 18 6 33.3 %
848
+ 105 3 18 6 33.3 %
849
+ 105 7 42 6 14.3 %
850
+ 105 1 6 6 100.0 %
851
+ 105 2 12 6 50.0 %
852
+ 105 1 6 6 100.0 %
853
+ 105 8 48 6 12.5 %
854
+ 106 2 12 6 50.0 %
855
+ 106 3 18 6 33.3 %
856
+ 106 1 6 6 100.0 %
857
+ 106 2 12 6 50.0 %
858
+ 106 2 12 6 50.0 %
859
+ 106 3 18 6 33.3 %
860
+ 106 7 42 6 14.3 %
861
+ 106 3 18 6 33.3 %
862
+ 107 1 6 6 100.0 %
863
+ 107 2 12 6 50.0 %
864
+ 107 6 36 6 16.7 %
865
+ 107 2 12 6 50.0 %
866
+ 107 3 18 6 33.3 %
867
+ 107 2 12 6 50.0 %
868
+ 107 3 18 6 33.3 %
869
+ 107 2 12 6 50.0 %
870
+ 108 1 6 6 100.0 %
871
+ 108 5 30 6 20.0 %
872
+ 108 4 24 6 25.0 %
873
+ 108 2 12 6 50.0 %
874
+ 108 2 12 6 50.0 %
875
+ 108 8 48 6 12.5 %
876
+ 108 2 12 6 50.0 %
877
+ 108 2 12 6 50.0 %
878
+ 109 1 6 6 100.0 %
879
+ 109 3 18 6 33.3 %
880
+ 109 6 36 6 16.7 %
881
+ 109 4 24 6 25.0 %
882
+ 109 3 18 6 33.3 %
883
+ 109 3 18 6 33.3 %
884
+ 109 2 12 6 50.0 %
885
+ 109 6 36 6 16.7 %
generation_config.json CHANGED
@@ -2,7 +2,10 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 151646,
4
  "do_sample": true,
5
- "eos_token_id": 151643,
 
 
 
6
  "temperature": 0.6,
7
  "top_p": 0.95,
8
  "transformers_version": "4.57.1"
 
2
  "_from_model_config": true,
3
  "bos_token_id": 151646,
4
  "do_sample": true,
5
+ "eos_token_id": [
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
  "temperature": 0.6,
10
  "top_p": 0.95,
11
  "transformers_version": "4.57.1"
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2547acd2ed4221452815cc1e43cfe6d8fe5eb93d6b0a17746940f62042edb8fc
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7acf113b5afb31f6c395014a5891df9213109fa76ea978fd940f523c445b39c0
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e053f6e3d3b18529c8951cf7ec083ae92e37d8a9f6e7ec486c091092321d906
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e38c04cca6a418ed413c932e303eec1886922e960cd068410e821338ad7178
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09055605bc0ed847bfb863ab09528796f3a086ba145fb9d4f6d92ad8310d6646
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ac7350e0ef280872dc11072e1a5ab14b8123b0347c603b525523a92b2091be
3
  size 4330865200
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
- size 11422778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4256422650d141f228fe954acee98679da412984c29a569877eefd3af69315a
3
+ size 11422959
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92df2953de292a8a4d447867c90e350e8357338da5214d2a17070cb10ce845a7
3
  size 8760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d047cbc55cda44b752f416d36e3a69e56abc0bd3f8f2902b298452f531a4525
3
  size 8760