vwxyzjn commited on
Commit
ccc0a1e
·
verified ·
1 Parent(s): 7b12ead

Model save

Browse files
Files changed (25) hide show
  1. README.md +52 -0
  2. config.json +30 -0
  3. generation_config.json +5 -0
  4. model.safetensors +3 -0
  5. runs/Jul16_19-28-05_ip-26-0-160-192/events.out.tfevents.1721158090.ip-26-0-160-192.486807.0 +3 -0
  6. runs/Jul16_19-28-55_ip-26-0-160-192/events.out.tfevents.1721158138.ip-26-0-160-192.489756.0 +3 -0
  7. runs/Jul16_19-29-28_ip-26-0-160-192/events.out.tfevents.1721158172.ip-26-0-160-192.491088.0 +3 -0
  8. runs/Jul16_19-30-31_ip-26-0-160-100/events.out.tfevents.1721158236.ip-26-0-160-100.2233327.0 +3 -0
  9. runs/Jul16_19-33-40_ip-26-0-160-100/events.out.tfevents.1721158423.ip-26-0-160-100.3402169.0 +3 -0
  10. runs/Jul16_19-36-11_ip-26-0-160-100/events.out.tfevents.1721158574.ip-26-0-160-100.3889662.0 +3 -0
  11. runs/Jul16_19-38-13_ip-26-0-160-100/events.out.tfevents.1721158696.ip-26-0-160-100.82708.0 +3 -0
  12. runs/Jul16_19-42-12_ip-26-0-160-192/events.out.tfevents.1721158939.ip-26-0-160-192.496384.0 +3 -0
  13. runs/Jul16_19-51-28_ip-26-0-160-192/events.out.tfevents.1721159558.ip-26-0-160-192.501459.0 +3 -0
  14. runs/Jul16_19-58-21_ip-26-0-160-192/events.out.tfevents.1721159935.ip-26-0-160-192.503495.0 +3 -0
  15. runs/Jul16_20-03-09_ip-26-0-160-192/events.out.tfevents.1721160223.ip-26-0-160-192.505748.0 +3 -0
  16. runs/Jul16_20-25-10_ip-26-0-167-51/events.out.tfevents.1721161576.ip-26-0-167-51.2192748.0 +3 -0
  17. runs/Jul16_20-28-49_ip-26-0-167-51/events.out.tfevents.1721161782.ip-26-0-167-51.2195066.0 +3 -0
  18. runs/Jul16_20-35-23_ip-26-0-175-241/events.out.tfevents.1721162187.ip-26-0-175-241.1729472.0 +3 -0
  19. runs/Jul16_20-37-37_ip-26-0-175-241/events.out.tfevents.1721162313.ip-26-0-175-241.1731639.0 +3 -0
  20. runs/Jul16_20-40-54_ip-26-0-175-241/events.out.tfevents.1721162505.ip-26-0-175-241.1734374.0 +3 -0
  21. runs/Jul16_22-16-02_ip-26-0-171-168/events.out.tfevents.1721168229.ip-26-0-171-168.1704982.0 +3 -0
  22. special_tokens_map.json +30 -0
  23. tokenizer.json +0 -0
  24. tokenizer_config.json +224 -0
  25. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: online_dpo_llmjudge
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/costa-huang/huggingface/runs/e52d1ezu)
13
+ # online_dpo_llmjudge
14
+
15
+ This model was trained from scratch on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 3e-06
35
+ - train_batch_size: 16
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - distributed_type: multi-GPU
39
+ - num_devices: 8
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 512
42
+ - total_eval_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 3.0
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.42.3
50
+ - Pytorch 2.3.0+cu121
51
+ - Datasets 2.19.1
52
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 16,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.42.3",
27
+ "use_cache": true,
28
+ "use_parallel_residual": true,
29
+ "vocab_size": 50304
30
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "transformers_version": "4.42.3"
5
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce66e12687cf780b2e4178d85ee4a709512eb63206f442f8d1e466e8c4e6940
3
+ size 2023586384
runs/Jul16_19-28-05_ip-26-0-160-192/events.out.tfevents.1721158090.ip-26-0-160-192.486807.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea1a8854d668d03d3f135c2e13ce7a22378e85ea1cee36282f9d04551b15bad
3
+ size 6312
runs/Jul16_19-28-55_ip-26-0-160-192/events.out.tfevents.1721158138.ip-26-0-160-192.489756.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa4e6920560cad5eeed46b29b089e75172659f37dad6303b23f943ae3b58950e
3
+ size 6312
runs/Jul16_19-29-28_ip-26-0-160-192/events.out.tfevents.1721158172.ip-26-0-160-192.491088.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc56aac544deea4c2aeef37c23770bf2e5acd7ca114b0456b29972a0d0dc8eda
3
+ size 6312
runs/Jul16_19-30-31_ip-26-0-160-100/events.out.tfevents.1721158236.ip-26-0-160-100.2233327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa962531745f25707df83572eebf93fb85a8429deaf38335faf52d7506c3838
3
+ size 6312
runs/Jul16_19-33-40_ip-26-0-160-100/events.out.tfevents.1721158423.ip-26-0-160-100.3402169.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc5adc930f13cbc64d8d2fc63dbcc0e4af0d96a8899f97e14bfab8337369d39
3
+ size 6312
runs/Jul16_19-36-11_ip-26-0-160-100/events.out.tfevents.1721158574.ip-26-0-160-100.3889662.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f041c98914ea36a06b4eb448deb9119293891e5b7860b47fb8d5c0596096f3
3
+ size 6312
runs/Jul16_19-38-13_ip-26-0-160-100/events.out.tfevents.1721158696.ip-26-0-160-100.82708.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0fbc5ed9b50b3665df6e320213b14e9690e614465d81f7010a3131a4749c2fb
3
+ size 6312
runs/Jul16_19-42-12_ip-26-0-160-192/events.out.tfevents.1721158939.ip-26-0-160-192.496384.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd097d781e9863ffdee76ebdb4a0cfe536308aa49d687e802d8d4c76ceb28d0
3
+ size 6312
runs/Jul16_19-51-28_ip-26-0-160-192/events.out.tfevents.1721159558.ip-26-0-160-192.501459.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e838f0f284357f14d47e33a22335f806b8c3e42de7c2d5bb1a2357abe48527
3
+ size 7443
runs/Jul16_19-58-21_ip-26-0-160-192/events.out.tfevents.1721159935.ip-26-0-160-192.503495.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e016eb684dc75251ce329e68264b0fda964c4bde23d3f35b42ec0592f0c9c4
3
+ size 7443
runs/Jul16_20-03-09_ip-26-0-160-192/events.out.tfevents.1721160223.ip-26-0-160-192.505748.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de929c185dd28705f9e95f5b6cad189cc754641f362f1ee740c222feb1714370
3
+ size 12673
runs/Jul16_20-25-10_ip-26-0-167-51/events.out.tfevents.1721161576.ip-26-0-167-51.2192748.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953603241172c931c22496a0fd3c0347cbf91275876b09264300b417063aa677
3
+ size 6398
runs/Jul16_20-28-49_ip-26-0-167-51/events.out.tfevents.1721161782.ip-26-0-167-51.2195066.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f57e02279f95b2d20d983c84fa793bf0b6502ba8c8c2f3f32da7ab062eb033
3
+ size 6398
runs/Jul16_20-35-23_ip-26-0-175-241/events.out.tfevents.1721162187.ip-26-0-175-241.1729472.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfdb6bb8e0bb6c901b52e77c219c90817f9ee1675212f7e423b8b298381ba8ee
3
+ size 6399
runs/Jul16_20-37-37_ip-26-0-175-241/events.out.tfevents.1721162313.ip-26-0-175-241.1731639.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9140614c6832180bbead231a493e32b2b241557b86e1f99dafe345f3f25169b
3
+ size 6399
runs/Jul16_20-40-54_ip-26-0-175-241/events.out.tfevents.1721162505.ip-26-0-175-241.1734374.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6deca754b2120d828de19df2bd10645ca0a1a5269890fff073b2b92abbbd74
3
+ size 28365
runs/Jul16_22-16-02_ip-26-0-171-168/events.out.tfevents.1721168229.ip-26-0-171-168.1704982.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015fe15ea884f48d3f4016732450c5072a7a697bcf9be37b897c70d81a965de5
3
+ size 2082105
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": "[PAD]",
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "[PAD]",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ }
214
+ },
215
+ "bos_token": "<|endoftext|>",
216
+ "chat_template": "{% for message in messages %}{{' ' + message['content']}}{% endfor %}",
217
+ "clean_up_tokenization_spaces": true,
218
+ "eos_token": "<|endoftext|>",
219
+ "model_max_length": 1000000000000000019884624838656,
220
+ "pad_token": "[PAD]",
221
+ "padding_side": "left",
222
+ "tokenizer_class": "GPTNeoXTokenizer",
223
+ "unk_token": "<|endoftext|>"
224
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a577af5edc5f1f0519202485d410fcfb73210fc0b3b97f23cd93c31d2c67676
3
+ size 7480