Hugging Face's logo

koshirowada
/
pythia_14m_sft

TensorBoard
Safetensors
gpt_neox
Generated from Trainer
Model card Files
xet
Metrics Community
koshirowada commited on
Commit
ddfd7fe
·
verified ·
1 Parent(s): 9f6c560

Training in progress, epoch 1

Browse files
Files changed (49) hide show
  1. config.json +2 -4
  2. dpo_160m_high_seed_1/checkpoint-2368/config.json +29 -0
  3. dpo_160m_high_seed_1/checkpoint-2368/generation_config.json +6 -0
  4. dpo_160m_high_seed_1/checkpoint-2368/model.safetensors +3 -0
  5. dpo_160m_high_seed_1/checkpoint-2368/optimizer.pt +3 -0
  6. dpo_160m_high_seed_1/checkpoint-2368/rng_state.pth +3 -0
  7. dpo_160m_high_seed_1/checkpoint-2368/scheduler.pt +3 -0
  8. dpo_160m_high_seed_1/checkpoint-2368/special_tokens_map.json +30 -0
  9. dpo_160m_high_seed_1/checkpoint-2368/tokenizer.json +0 -0
  10. dpo_160m_high_seed_1/checkpoint-2368/tokenizer_config.json +216 -0
  11. dpo_160m_high_seed_1/checkpoint-2368/trainer_state.json +0 -0
  12. dpo_160m_high_seed_1/checkpoint-2368/training_args.bin +3 -0
  13. dpo_160m_high_seed_1/runs/Nov28_06-08-31_365d8ce0a2ec/events.out.tfevents.1732774141.365d8ce0a2ec.1232.0 +3 -0
  14. fdpo_test_seed_1/checkpoint-384/config.json +29 -0
  15. fdpo_test_seed_1/checkpoint-384/generation_config.json +6 -0
  16. fdpo_test_seed_1/checkpoint-384/model.safetensors +3 -0
  17. fdpo_test_seed_1/checkpoint-384/optimizer.pt +3 -0
  18. fdpo_test_seed_1/checkpoint-384/rng_state.pth +3 -0
  19. fdpo_test_seed_1/checkpoint-384/scheduler.pt +3 -0
  20. fdpo_test_seed_1/checkpoint-384/special_tokens_map.json +30 -0
  21. fdpo_test_seed_1/checkpoint-384/tokenizer.json +0 -0
  22. fdpo_test_seed_1/checkpoint-384/tokenizer_config.json +216 -0
  23. fdpo_test_seed_1/checkpoint-384/trainer_state.json +0 -0
  24. fdpo_test_seed_1/checkpoint-384/training_args.bin +3 -0
  25. fdpo_test_seed_1/filtered_dataset_epoch_0/data-00000-of-00001.arrow +3 -0
  26. fdpo_test_seed_1/filtered_dataset_epoch_0/dataset_info.json +136 -0
  27. fdpo_test_seed_1/filtered_dataset_epoch_0/state.json +13 -0
  28. fdpo_test_seed_1/filtered_dataset_epoch_1/data-00000-of-00001.arrow +3 -0
  29. fdpo_test_seed_1/filtered_dataset_epoch_1/dataset_info.json +136 -0
  30. fdpo_test_seed_1/filtered_dataset_epoch_1/state.json +13 -0
  31. fdpo_test_seed_1/filtered_dataset_epoch_2/data-00000-of-00001.arrow +3 -0
  32. fdpo_test_seed_1/filtered_dataset_epoch_2/dataset_info.json +136 -0
  33. fdpo_test_seed_1/filtered_dataset_epoch_2/state.json +13 -0
  34. fdpo_test_seed_1/filtered_dataset_epoch_3/data-00000-of-00001.arrow +3 -0
  35. fdpo_test_seed_1/filtered_dataset_epoch_3/dataset_info.json +136 -0
  36. fdpo_test_seed_1/filtered_dataset_epoch_3/state.json +13 -0
  37. fdpo_test_seed_1/filtered_dataset_epoch_4/data-00000-of-00001.arrow +3 -0
  38. fdpo_test_seed_1/filtered_dataset_epoch_4/dataset_info.json +136 -0
  39. fdpo_test_seed_1/filtered_dataset_epoch_4/state.json +13 -0
  40. fdpo_test_seed_1/runs/Nov14_08-08-23_b95916d8235d/events.out.tfevents.1731571952.b95916d8235d.2278.0 +3 -0
  41. fdpo_test_seed_1/runs/Nov14_08-08-23_b95916d8235d/events.out.tfevents.1731572150.b95916d8235d.2278.1 +3 -0
  42. fdpo_test_seed_1/runs/Nov28_05-04-12_365d8ce0a2ec/events.out.tfevents.1732770473.365d8ce0a2ec.737.0 +3 -0
  43. fdpo_test_seed_1/runs/Nov28_05-04-12_365d8ce0a2ec/events.out.tfevents.1732770609.365d8ce0a2ec.737.1 +3 -0
  44. fdpo_test_seed_1/runs/Nov28_05-04-12_365d8ce0a2ec/events.out.tfevents.1732770717.365d8ce0a2ec.737.2 +3 -0
  45. fdpo_test_seed_1/runs/Nov28_05-04-12_365d8ce0a2ec/events.out.tfevents.1732770810.365d8ce0a2ec.737.3 +3 -0
  46. model.safetensors +1 -1
  47. tokenizer.json +0 -0
  48. tokenizer_config.json +0 -2
  49. training_args.bin +2 -2
config.json CHANGED
@@ -3,7 +3,6 @@
3
  "architectures": [
4
  "GPTNeoXForCausalLM"
5
  ],
6
- "attention_bias": true,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 0,
9
  "classifier_dropout": 0.1,
@@ -18,14 +17,13 @@
18
  "model_type": "gpt_neox",
19
  "num_attention_heads": 4,
20
  "num_hidden_layers": 6,
21
- "partial_rotary_factor": 0.25,
22
  "rope_scaling": null,
23
- "rope_theta": 10000,
24
  "rotary_emb_base": 10000,
25
  "rotary_pct": 0.25,
26
  "tie_word_embeddings": false,
27
  "torch_dtype": "float32",
28
- "transformers_version": "4.46.2",
29
  "use_cache": true,
30
  "use_parallel_residual": true,
31
  "vocab_size": 50304
 
3
  "architectures": [
4
  "GPTNeoXForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 0,
8
  "classifier_dropout": 0.1,
 
17
  "model_type": "gpt_neox",
18
  "num_attention_heads": 4,
19
  "num_hidden_layers": 6,
20
+ "pad_token_id": 0,
21
  "rope_scaling": null,
 
22
  "rotary_emb_base": 10000,
23
  "rotary_pct": 0.25,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "float32",
26
+ "transformers_version": "4.36.2",
27
  "use_cache": true,
28
  "use_parallel_residual": true,
29
  "vocab_size": 50304
dpo_160m_high_seed_1/checkpoint-2368/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Mitsuki-Sakamoto/fdpo-models",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 0.25,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
+ "use_parallel_residual": true,
28
+ "vocab_size": 50304
29
+ }
dpo_160m_high_seed_1/checkpoint-2368/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.36.2"
6
+ }
dpo_160m_high_seed_1/checkpoint-2368/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c5ff95662c80b7208bc6858d248619901b5bb3571c9127ec2596061d506ece6
3
+ size 649308728
dpo_160m_high_seed_1/checkpoint-2368/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2755c0171ed7cbd53cbf1e6e83ee68e67ea02ef0daa93939346d00b0443d7fe6
3
+ size 649336890
dpo_160m_high_seed_1/checkpoint-2368/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79b92909f10a72677d56cccf6dff983e61160eb868d4a68bb4e9c98b0ecb899
3
+ size 14244
dpo_160m_high_seed_1/checkpoint-2368/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec2b05ca1d782b757badb9e3024ab078cb152b6a9d4d4aaf5e353b543c7fb40
3
+ size 1064
dpo_160m_high_seed_1/checkpoint-2368/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
dpo_160m_high_seed_1/checkpoint-2368/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
dpo_160m_high_seed_1/checkpoint-2368/tokenizer_config.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "bos_token": "<|endoftext|>",
206
+ "clean_up_tokenization_spaces": true,
207
+ "eos_token": "<|endoftext|>",
208
+ "max_length": 512,
209
+ "model_max_length": 1000000000000000019884624838656,
210
+ "pad_token": "<|endoftext|>",
211
+ "stride": 0,
212
+ "tokenizer_class": "GPTNeoXTokenizer",
213
+ "truncation_side": "right",
214
+ "truncation_strategy": "longest_first",
215
+ "unk_token": "<|endoftext|>"
216
+ }
dpo_160m_high_seed_1/checkpoint-2368/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
dpo_160m_high_seed_1/checkpoint-2368/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e5276da256bf9bd20e2dd317ba203c5803527d494fb6d2c8caed949c688204
3
+ size 6328
dpo_160m_high_seed_1/runs/Nov28_06-08-31_365d8ce0a2ec/events.out.tfevents.1732774141.365d8ce0a2ec.1232.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df4213225ca32c44b7fe5caf0684cef4019b7843a469c50e3285b0dbe79e025c
3
+ size 1524536
fdpo_test_seed_1/checkpoint-384/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Mitsuki-Sakamoto/fdpo-models",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 0.25,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
+ "use_parallel_residual": true,
28
+ "vocab_size": 50304
29
+ }
fdpo_test_seed_1/checkpoint-384/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.36.2"
6
+ }
fdpo_test_seed_1/checkpoint-384/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0575dd7b2edd17821b91dd2310a0d72227949f10635aca5b53e1c632e575f42f
3
+ size 649308728
fdpo_test_seed_1/checkpoint-384/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa6c7161c951a63ab61fad68ea28ca7ca2f949b51812cae554d444f2c8fa9a2
3
+ size 649336890
fdpo_test_seed_1/checkpoint-384/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d4ae0e89764c07d2ca72e87bf22bd82a57c6ff62d9cdda6c91cd7845b97711
3
+ size 14244
fdpo_test_seed_1/checkpoint-384/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:294ce4e24062ce28826bf8e50d6794e978ef8b9fdcc8c8d7d849f3151dc0af28
3
+ size 1064
fdpo_test_seed_1/checkpoint-384/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
fdpo_test_seed_1/checkpoint-384/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
fdpo_test_seed_1/checkpoint-384/tokenizer_config.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "bos_token": "<|endoftext|>",
206
+ "clean_up_tokenization_spaces": true,
207
+ "eos_token": "<|endoftext|>",
208
+ "max_length": 512,
209
+ "model_max_length": 1000000000000000019884624838656,
210
+ "pad_token": "<|endoftext|>",
211
+ "stride": 0,
212
+ "tokenizer_class": "GPTNeoXTokenizer",
213
+ "truncation_side": "right",
214
+ "truncation_strategy": "longest_first",
215
+ "unk_token": "<|endoftext|>"
216
+ }
fdpo_test_seed_1/checkpoint-384/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
fdpo_test_seed_1/checkpoint-384/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b8267c7b58c7be7f624ad548f9550096aeeef75950441568335bb79aa038c8
3
+ size 6456
fdpo_test_seed_1/filtered_dataset_epoch_0/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f09e59acb73007844604ec9d2ac8100117609b56d78721ec6f14b28972e708e
3
+ size 459896
fdpo_test_seed_1/filtered_dataset_epoch_0/dataset_info.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "160m_mix_seed1",
5
+ "dataset_name": "fdpo-preference-dataset",
6
+ "dataset_size": 25923121,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/Mitsuki-Sakamoto/fdpo-preference-dataset@995aa681b78cf617f28540ea2708706872e26b8c/160m_mix_seed1/preference-00000-of-00001.parquet": {
10
+ "num_bytes": 12316110,
11
+ "checksum": null
12
+ }
13
+ },
14
+ "download_size": 12316110,
15
+ "features": {
16
+ "instruction": {
17
+ "dtype": "string",
18
+ "_type": "Value"
19
+ },
20
+ "input": {
21
+ "dtype": "string",
22
+ "_type": "Value"
23
+ },
24
+ "output": {
25
+ "dtype": "string",
26
+ "_type": "Value"
27
+ },
28
+ "preference": {
29
+ "dtype": "int64",
30
+ "_type": "Value"
31
+ },
32
+ "output_1": {
33
+ "dtype": "string",
34
+ "_type": "Value"
35
+ },
36
+ "output_2": {
37
+ "dtype": "string",
38
+ "_type": "Value"
39
+ },
40
+ "reward_model_prompt_format": {
41
+ "dtype": "string",
42
+ "_type": "Value"
43
+ },
44
+ "gen_prompt_format": {
45
+ "dtype": "string",
46
+ "_type": "Value"
47
+ },
48
+ "gen_kwargs": {
49
+ "do_sample": {
50
+ "dtype": "bool",
51
+ "_type": "Value"
52
+ },
53
+ "max_new_tokens": {
54
+ "dtype": "int64",
55
+ "_type": "Value"
56
+ },
57
+ "pad_token_id": {
58
+ "dtype": "int64",
59
+ "_type": "Value"
60
+ },
61
+ "top_k": {
62
+ "dtype": "int64",
63
+ "_type": "Value"
64
+ },
65
+ "top_p": {
66
+ "dtype": "float64",
67
+ "_type": "Value"
68
+ }
69
+ },
70
+ "reward_1": {
71
+ "dtype": "float64",
72
+ "_type": "Value"
73
+ },
74
+ "reward_2": {
75
+ "dtype": "float64",
76
+ "_type": "Value"
77
+ },
78
+ "n_samples": {
79
+ "dtype": "int64",
80
+ "_type": "Value"
81
+ },
82
+ "reject_select": {
83
+ "dtype": "string",
84
+ "_type": "Value"
85
+ },
86
+ "index": {
87
+ "dtype": "int64",
88
+ "_type": "Value"
89
+ },
90
+ "unformatted_prompt": {
91
+ "dtype": "string",
92
+ "_type": "Value"
93
+ },
94
+ "prompt": {
95
+ "dtype": "string",
96
+ "_type": "Value"
97
+ },
98
+ "chosen": {
99
+ "dtype": "string",
100
+ "_type": "Value"
101
+ },
102
+ "rejected": {
103
+ "dtype": "string",
104
+ "_type": "Value"
105
+ },
106
+ "filtered_epoch": {
107
+ "dtype": "int64",
108
+ "_type": "Value"
109
+ },
110
+ "gen_reward": {
111
+ "dtype": "float64",
112
+ "_type": "Value"
113
+ },
114
+ "gen_response": {
115
+ "dtype": "string",
116
+ "_type": "Value"
117
+ }
118
+ },
119
+ "homepage": "",
120
+ "license": "",
121
+ "size_in_bytes": 38239231,
122
+ "splits": {
123
+ "preference": {
124
+ "name": "preference",
125
+ "num_bytes": 25923121,
126
+ "num_examples": 20000,
127
+ "dataset_name": "fdpo-preference-dataset"
128
+ }
129
+ },
130
+ "version": {
131
+ "version_str": "0.0.0",
132
+ "major": 0,
133
+ "minor": 0,
134
+ "patch": 0
135
+ }
136
+ }
fdpo_test_seed_1/filtered_dataset_epoch_0/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "871c350fc37766e1",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "preference"
13
+ }
fdpo_test_seed_1/filtered_dataset_epoch_1/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f5570fc13544985028dc3045243ef950602fa9d37de009708b1e37791ca0ec
3
+ size 462744
fdpo_test_seed_1/filtered_dataset_epoch_1/dataset_info.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "160m_mix_seed1",
5
+ "dataset_name": "fdpo-preference-dataset",
6
+ "dataset_size": 25923121,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/Mitsuki-Sakamoto/fdpo-preference-dataset@995aa681b78cf617f28540ea2708706872e26b8c/160m_mix_seed1/preference-00000-of-00001.parquet": {
10
+ "num_bytes": 12316110,
11
+ "checksum": null
12
+ }
13
+ },
14
+ "download_size": 12316110,
15
+ "features": {
16
+ "instruction": {
17
+ "dtype": "string",
18
+ "_type": "Value"
19
+ },
20
+ "input": {
21
+ "dtype": "string",
22
+ "_type": "Value"
23
+ },
24
+ "output": {
25
+ "dtype": "string",
26
+ "_type": "Value"
27
+ },
28
+ "preference": {
29
+ "dtype": "int64",
30
+ "_type": "Value"
31
+ },
32
+ "output_1": {
33
+ "dtype": "string",
34
+ "_type": "Value"
35
+ },
36
+ "output_2": {
37
+ "dtype": "string",
38
+ "_type": "Value"
39
+ },
40
+ "reward_model_prompt_format": {
41
+ "dtype": "string",
42
+ "_type": "Value"
43
+ },
44
+ "gen_prompt_format": {
45
+ "dtype": "string",
46
+ "_type": "Value"
47
+ },
48
+ "gen_kwargs": {
49
+ "do_sample": {
50
+ "dtype": "bool",
51
+ "_type": "Value"
52
+ },
53
+ "max_new_tokens": {
54
+ "dtype": "int64",
55
+ "_type": "Value"
56
+ },
57
+ "pad_token_id": {
58
+ "dtype": "int64",
59
+ "_type": "Value"
60
+ },
61
+ "top_k": {
62
+ "dtype": "int64",
63
+ "_type": "Value"
64
+ },
65
+ "top_p": {
66
+ "dtype": "float64",
67
+ "_type": "Value"
68
+ }
69
+ },
70
+ "reward_1": {
71
+ "dtype": "float64",
72
+ "_type": "Value"
73
+ },
74
+ "reward_2": {
75
+ "dtype": "float64",
76
+ "_type": "Value"
77
+ },
78
+ "n_samples": {
79
+ "dtype": "int64",
80
+ "_type": "Value"
81
+ },
82
+ "reject_select": {
83
+ "dtype": "string",
84
+ "_type": "Value"
85
+ },
86
+ "index": {
87
+ "dtype": "int64",
88
+ "_type": "Value"
89
+ },
90
+ "unformatted_prompt": {
91
+ "dtype": "string",
92
+ "_type": "Value"
93
+ },
94
+ "prompt": {
95
+ "dtype": "string",
96
+ "_type": "Value"
97
+ },
98
+ "chosen": {
99
+ "dtype": "string",
100
+ "_type": "Value"
101
+ },
102
+ "rejected": {
103
+ "dtype": "string",
104
+ "_type": "Value"
105
+ },
106
+ "filtered_epoch": {
107
+ "dtype": "int64",
108
+ "_type": "Value"
109
+ },
110
+ "gen_reward": {
111
+ "dtype": "float64",
112
+ "_type": "Value"
113
+ },
114
+ "gen_response": {
115
+ "dtype": "string",
116
+ "_type": "Value"
117
+ }
118
+ },
119
+ "homepage": "",
120
+ "license": "",
121
+ "size_in_bytes": 38239231,
122
+ "splits": {
123
+ "preference": {
124
+ "name": "preference",
125
+ "num_bytes": 25923121,
126
+ "num_examples": 20000,
127
+ "dataset_name": "fdpo-preference-dataset"
128
+ }
129
+ },
130
+ "version": {
131
+ "version_str": "0.0.0",
132
+ "major": 0,
133
+ "minor": 0,
134
+ "patch": 0
135
+ }
136
+ }
fdpo_test_seed_1/filtered_dataset_epoch_1/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "0dfa170a7521c07b",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "preference"
13
+ }
fdpo_test_seed_1/filtered_dataset_epoch_2/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d16119086ca53f5c59d322488a1a6d27e597d8f02d8b77a4194669864d1f0f
3
+ size 462448
fdpo_test_seed_1/filtered_dataset_epoch_2/dataset_info.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "160m_mix_seed1",
5
+ "dataset_name": "fdpo-preference-dataset",
6
+ "dataset_size": 25923121,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/Mitsuki-Sakamoto/fdpo-preference-dataset@995aa681b78cf617f28540ea2708706872e26b8c/160m_mix_seed1/preference-00000-of-00001.parquet": {
10
+ "num_bytes": 12316110,
11
+ "checksum": null
12
+ }
13
+ },
14
+ "download_size": 12316110,
15
+ "features": {
16
+ "instruction": {
17
+ "dtype": "string",
18
+ "_type": "Value"
19
+ },
20
+ "input": {
21
+ "dtype": "string",
22
+ "_type": "Value"
23
+ },
24
+ "output": {
25
+ "dtype": "string",
26
+ "_type": "Value"
27
+ },
28
+ "preference": {
29
+ "dtype": "int64",
30
+ "_type": "Value"
31
+ },
32
+ "output_1": {
33
+ "dtype": "string",
34
+ "_type": "Value"
35
+ },
36
+ "output_2": {
37
+ "dtype": "string",
38
+ "_type": "Value"
39
+ },
40
+ "reward_model_prompt_format": {
41
+ "dtype": "string",
42
+ "_type": "Value"
43
+ },
44
+ "gen_prompt_format": {
45
+ "dtype": "string",
46
+ "_type": "Value"
47
+ },
48
+ "gen_kwargs": {
49
+ "do_sample": {
50
+ "dtype": "bool",
51
+ "_type": "Value"
52
+ },
53
+ "max_new_tokens": {
54
+ "dtype": "int64",
55
+ "_type": "Value"
56
+ },
57
+ "pad_token_id": {
58
+ "dtype": "int64",
59
+ "_type": "Value"
60
+ },
61
+ "top_k": {
62
+ "dtype": "int64",
63
+ "_type": "Value"
64
+ },
65
+ "top_p": {
66
+ "dtype": "float64",
67
+ "_type": "Value"
68
+ }
69
+ },
70
+ "reward_1": {
71
+ "dtype": "float64",
72
+ "_type": "Value"
73
+ },
74
+ "reward_2": {
75
+ "dtype": "float64",
76
+ "_type": "Value"
77
+ },
78
+ "n_samples": {
79
+ "dtype": "int64",
80
+ "_type": "Value"
81
+ },
82
+ "reject_select": {
83
+ "dtype": "string",
84
+ "_type": "Value"
85
+ },
86
+ "index": {
87
+ "dtype": "int64",
88
+ "_type": "Value"
89
+ },
90
+ "unformatted_prompt": {
91
+ "dtype": "string",
92
+ "_type": "Value"
93
+ },
94
+ "prompt": {
95
+ "dtype": "string",
96
+ "_type": "Value"
97
+ },
98
+ "chosen": {
99
+ "dtype": "string",
100
+ "_type": "Value"
101
+ },
102
+ "rejected": {
103
+ "dtype": "string",
104
+ "_type": "Value"
105
+ },
106
+ "filtered_epoch": {
107
+ "dtype": "int64",
108
+ "_type": "Value"
109
+ },
110
+ "gen_reward": {
111
+ "dtype": "float64",
112
+ "_type": "Value"
113
+ },
114
+ "gen_response": {
115
+ "dtype": "string",
116
+ "_type": "Value"
117
+ }
118
+ },
119
+ "homepage": "",
120
+ "license": "",
121
+ "size_in_bytes": 38239231,
122
+ "splits": {
123
+ "preference": {
124
+ "name": "preference",
125
+ "num_bytes": 25923121,
126
+ "num_examples": 20000,
127
+ "dataset_name": "fdpo-preference-dataset"
128
+ }
129
+ },
130
+ "version": {
131
+ "version_str": "0.0.0",
132
+ "major": 0,
133
+ "minor": 0,
134
+ "patch": 0
135
+ }
136
+ }
fdpo_test_seed_1/filtered_dataset_epoch_2/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "d779829225225c75",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "preference"
13
+ }
fdpo_test_seed_1/filtered_dataset_epoch_3/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c8bbe3c95680f7c76e3567bebe045d689ba84524a5d85b8fae2e84979cddaf
3
+ size 463184
fdpo_test_seed_1/filtered_dataset_epoch_3/dataset_info.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "160m_mix_seed1",
5
+ "dataset_name": "fdpo-preference-dataset",
6
+ "dataset_size": 25923121,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/Mitsuki-Sakamoto/fdpo-preference-dataset@995aa681b78cf617f28540ea2708706872e26b8c/160m_mix_seed1/preference-00000-of-00001.parquet": {
10
+ "num_bytes": 12316110,
11
+ "checksum": null
12
+ }
13
+ },
14
+ "download_size": 12316110,
15
+ "features": {
16
+ "instruction": {
17
+ "dtype": "string",
18
+ "_type": "Value"
19
+ },
20
+ "input": {
21
+ "dtype": "string",
22
+ "_type": "Value"
23
+ },
24
+ "output": {
25
+ "dtype": "string",
26
+ "_type": "Value"
27
+ },
28
+ "preference": {
29
+ "dtype": "int64",
30
+ "_type": "Value"
31
+ },
32
+ "output_1": {
33
+ "dtype": "string",
34
+ "_type": "Value"
35
+ },
36
+ "output_2": {
37
+ "dtype": "string",
38
+ "_type": "Value"
39
+ },
40
+ "reward_model_prompt_format": {
41
+ "dtype": "string",
42
+ "_type": "Value"
43
+ },
44
+ "gen_prompt_format": {
45
+ "dtype": "string",
46
+ "_type": "Value"
47
+ },
48
+ "gen_kwargs": {
49
+ "do_sample": {
50
+ "dtype": "bool",
51
+ "_type": "Value"
52
+ },
53
+ "max_new_tokens": {
54
+ "dtype": "int64",
55
+ "_type": "Value"
56
+ },
57
+ "pad_token_id": {
58
+ "dtype": "int64",
59
+ "_type": "Value"
60
+ },
61
+ "top_k": {
62
+ "dtype": "int64",
63
+ "_type": "Value"
64
+ },
65
+ "top_p": {
66
+ "dtype": "float64",
67
+ "_type": "Value"
68
+ }
69
+ },
70
+ "reward_1": {
71
+ "dtype": "float64",
72
+ "_type": "Value"
73
+ },
74
+ "reward_2": {
75
+ "dtype": "float64",
76
+ "_type": "Value"
77
+ },
78
+ "n_samples": {
79
+ "dtype": "int64",
80
+ "_type": "Value"
81
+ },
82
+ "reject_select": {
83
+ "dtype": "string",
84
+ "_type": "Value"
85
+ },
86
+ "index": {
87
+ "dtype": "int64",
88
+ "_type": "Value"
89
+ },
90
+ "unformatted_prompt": {
91
+ "dtype": "string",
92
+ "_type": "Value"
93
+ },
94
+ "prompt": {
95
+ "dtype": "string",
96
+ "_type": "Value"
97
+ },
98
+ "chosen": {
99
+ "dtype": "string",
100
+ "_type": "Value"
101
+ },
102
+ "rejected": {
103
+ "dtype": "string",
104
+ "_type": "Value"
105
+ },
106
+ "filtered_epoch": {
107
+ "dtype": "int64",
108
+ "_type": "Value"
109
+ },
110
+ "gen_reward": {
111
+ "dtype": "float64",
112
+ "_type": "Value"
113
+ },
114
+ "gen_response": {
115
+ "dtype": "string",
116
+ "_type": "Value"
117
+ }
118
+ },
119
+ "homepage": "",
120
+ "license": "",
121
+ "size_in_bytes": 38239231,
122
+ "splits": {
123
+ "preference": {
124
+ "name": "preference",
125
+ "num_bytes": 25923121,
126
+ "num_examples": 20000,
127
+ "dataset_name": "fdpo-preference-dataset"
128
+ }
129
+ },
130
+ "version": {
131
+ "version_str": "0.0.0",
132
+ "major": 0,
133
+ "minor": 0,
134
+ "patch": 0
135
+ }
136
+ }
fdpo_test_seed_1/filtered_dataset_epoch_3/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "46f5eb25a4d1cbf3",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "preference"
13
+ }
fdpo_test_seed_1/filtered_dataset_epoch_4/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703d5fb1c3cbf24df658a8db518f1222f119379f0eeb92e22806beab6e4e23d8
3
+ size 463632
fdpo_test_seed_1/filtered_dataset_epoch_4/dataset_info.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "160m_mix_seed1",
5
+ "dataset_name": "fdpo-preference-dataset",
6
+ "dataset_size": 25923121,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/Mitsuki-Sakamoto/fdpo-preference-dataset@995aa681b78cf617f28540ea2708706872e26b8c/160m_mix_seed1/preference-00000-of-00001.parquet": {
10
+ "num_bytes": 12316110,
11
+ "checksum": null
12
+ }
13
+ },
14
+ "download_size": 12316110,
15
+ "features": {
16
+ "instruction": {
17
+ "dtype": "string",
18
+ "_type": "Value"
19
+ },
20
+ "input": {
21
+ "dtype": "string",
22
+ "_type": "Value"
23
+ },
24
+ "output": {
25
+ "dtype": "string",
26
+ "_type": "Value"
27
+ },
28
+ "preference": {
29
+ "dtype": "int64",
30
+ "_type": "Value"
31
+ },
32
+ "output_1": {
33
+ "dtype": "string",
34
+ "_type": "Value"
35
+ },
36
+ "output_2": {
37
+ "dtype": "string",
38
+ "_type": "Value"
39
+ },
40
+ "reward_model_prompt_format": {
41
+ "dtype": "string",
42
+ "_type": "Value"
43
+ },
44
+ "gen_prompt_format": {
45
+ "dtype": "string",
46
+ "_type": "Value"
47
+ },
48
+ "gen_kwargs": {
49
+ "do_sample": {
50
+ "dtype": "bool",
51
+ "_type": "Value"
52
+ },
53
+ "max_new_tokens": {
54
+ "dtype": "int64",
55
+ "_type": "Value"
56
+ },
57
+ "pad_token_id": {
58
+ "dtype": "int64",
59
+ "_type": "Value"
60
+ },
61
+ "top_k": {
62
+ "dtype": "int64",
63
+ "_type": "Value"
64
+ },
65
+ "top_p": {
66
+ "dtype": "float64",
67
+ "_type": "Value"
68
+ }
69
+ },
70
+ "reward_1": {
71
+ "dtype": "float64",
72
+ "_type": "Value"
73
+ },
74
+ "reward_2": {
75
+ "dtype": "float64",
76
+ "_type": "Value"
77
+ },
78
+ "n_samples": {
79
+ "dtype": "int64",
80
+ "_type": "Value"
81
+ },
82
+ "reject_select": {
83
+ "dtype": "string",
84
+ "_type": "Value"
85
+ },
86
+ "index": {
87
+ "dtype": "int64",
88
+ "_type": "Value"
89
+ },
90
+ "unformatted_prompt": {
91
+ "dtype": "string",
92
+ "_type": "Value"
93
+ },
94
+ "prompt": {
95
+ "dtype": "string",
96
+ "_type": "Value"
97
+ },
98
+ "chosen": {
99
+ "dtype": "string",
100
+ "_type": "Value"
101
+ },
102
+ "rejected": {
103
+ "dtype": "string",
104
+ "_type": "Value"
105
+ },
106
+ "filtered_epoch": {
107
+ "dtype": "int64",
108
+ "_type": "Value"
109
+ },
110
+ "gen_reward": {
111
+ "dtype": "float64",
112
+ "_type": "Value"
113
+ },
114
+ "gen_response": {
115
+ "dtype": "string",
116
+ "_type": "Value"
117
+ }
118
+ },
119
+ "homepage": "",
120
+ "license": "",
121
+ "size_in_bytes": 38239231,
122
+ "splits": {
123
+ "preference": {
124
+ "name": "preference",
125
+ "num_bytes": 25923121,
126
+ "num_examples": 20000,
127
+ "dataset_name": "fdpo-preference-dataset"
128
+ }
129
+ },
130
+ "version": {
131
+ "version_str": "0.0.0",
132
+ "major": 0,
133
+ "minor": 0,
134
+ "patch": 0
135
+ }
136
+ }
fdpo_test_seed_1/filtered_dataset_epoch_4/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "51184628b356c635",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "preference"
13
+ }
fdpo_test_seed_1/runs/Nov14_08-08-23_b95916d8235d/events.out.tfevents.1731571952.b95916d8235d.2278.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556ba222b857aa31afcbf3c65f64b49c10d07f9dadc38cf5bb0d9697635fb0ba
3
+ size 54027
fdpo_test_seed_1/runs/Nov14_08-08-23_b95916d8235d/events.out.tfevents.1731572150.b95916d8235d.2278.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:784d5a21165640ea43f7f61426978fff63f95bdd8fa34a29dc432f8bce5cc8ed
3
+ size 37853
fdpo_test_seed_1/runs/Nov28_05-04-12_365d8ce0a2ec/events.out.tfevents.1732770473.365d8ce0a2ec.737.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c21a310443d9f9f43ae059f51c8507c57a69eb7e7cd493fa4f9e8c8f0d78c62
3
+ size 98466
fdpo_test_seed_1/runs/Nov28_05-04-12_365d8ce0a2ec/events.out.tfevents.1732770609.365d8ce0a2ec.737.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e90c52a8a62ac838b6b946850a9272fa7aabaf61c8e362bd1c84fdae5ff4ba
3
+ size 71327
fdpo_test_seed_1/runs/Nov28_05-04-12_365d8ce0a2ec/events.out.tfevents.1732770717.365d8ce0a2ec.737.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfdc9e4d3559e78f1bae5ea564c93fd78af9c6f4f9e4c0827e43d60659831235
3
+ size 57379
fdpo_test_seed_1/runs/Nov28_05-04-12_365d8ce0a2ec/events.out.tfevents.1732770810.365d8ce0a2ec.737.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7d98e44cdddd0e6b855612a73d3f08f3d169603b452691438f96d4cf9da87e
3
+ size 50405
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6c006b230f4d2ae1b443996d156a1520d15aa629bad116b975f29b6852989d
3
  size 56279344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509744123e5eee3a77a5c081655a2b377921c1687c08517cee6f0c2fbc1b18bf
3
  size 56279344
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "add_bos_token": false,
3
- "add_eos_token": false,
4
  "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
  "0": {
 
1
  {
 
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:755279fa1478573d459744e52de23b9bdaf3d7e93858c76f8c98ebdf38f4bfa2
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece911babbf9bd0c5e4830fdc25f0a811d8509ddb32d353e66eab3c98e564249
3
+ size 4664