manual upload from checkpoint
Browse files- dataset/adv_index_map_0.json +1 -0
- dataset/adv_index_map_1.json +1 -0
- dataset/adv_index_map_2.json +1 -0
- dataset/adv_index_map_3.json +1 -0
- dataset/adv_losses_0.json +1 -0
- dataset/adv_losses_1.json +1 -0
- dataset/adv_losses_2.json +1 -0
- dataset/adv_losses_3.json +1 -0
- dataset/clean_index_map_0.json +0 -0
- dataset/clean_index_map_1.json +0 -0
- dataset/clean_index_map_2.json +0 -0
- dataset/clean_index_map_3.json +0 -0
- lr_scheduler_0.pt +3 -0
- lr_scheduler_1.pt +3 -0
- lr_scheduler_2.pt +3 -0
- lr_scheduler_3.pt +3 -0
- model/.gitignore +2 -0
- model/commit.txt +1 -0
- model/config.json +32 -0
- model/disk-write-timestamp.txt +1 -0
- model/done-saving +0 -0
- model/pytorch_model.bin +3 -0
- model/pytorch_model.bin.index.json +1 -0
- model/special_tokens_map.json +24 -0
- model/tokenizer.json +0 -0
- model/tokenizer_config.json +215 -0
- optimizer_0.pt +3 -0
- optimizer_1.pt +3 -0
- optimizer_2.pt +3 -0
- optimizer_3.pt +3 -0
- rng/distributed_rng_state_0.pt +3 -0
- rng/distributed_rng_state_1.pt +3 -0
- rng/distributed_rng_state_2.pt +3 -0
- rng/distributed_rng_state_3.pt +3 -0
- rng/torch_rng_state_0.pt +3 -0
- rng/torch_rng_state_1.pt +3 -0
- rng/torch_rng_state_2.pt +3 -0
- rng/torch_rng_state_3.pt +3 -0
- save_complete +0 -0
- state.json +1 -0
dataset/adv_index_map_0.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
dataset/adv_index_map_1.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
dataset/adv_index_map_2.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
dataset/adv_index_map_3.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
dataset/adv_losses_0.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
dataset/adv_losses_1.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
dataset/adv_losses_2.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
dataset/adv_losses_3.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
dataset/clean_index_map_0.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
dataset/clean_index_map_1.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
dataset/clean_index_map_2.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
dataset/clean_index_map_3.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
lr_scheduler_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2792637a43ba566d12944320a7221c25544dfee3f3abb417eeed446c0922cc59
|
3 |
+
size 1084
|
lr_scheduler_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8c168848f3000928b6dc262e6e6f5cd4c63188020b259a0b5c68e989c55c2eb
|
3 |
+
size 1084
|
lr_scheduler_2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e632840b3c3439ae89d77999c8e08c409ea3f7b6a5e37d33d2aa79c460bf164
|
3 |
+
size 1084
|
lr_scheduler_3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83c8d5225a80ebca9a4a0493caa4cfeaff3da3da6dfb53c1fd15a1c83fbb3d2d
|
3 |
+
size 1084
|
model/.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
|
2 |
+
done-saving
|
model/commit.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
b9b32a2bd6f7250bf28ca73fbb5912b90342c84a
|
model/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-12b",
|
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": 5120,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 20480,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"model_type": "gpt_neox",
|
19 |
+
"num_attention_heads": 40,
|
20 |
+
"num_hidden_layers": 36,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rotary_emb_base": 10000,
|
25 |
+
"rotary_pct": 0.25,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.42.4",
|
29 |
+
"use_cache": false,
|
30 |
+
"use_parallel_residual": true,
|
31 |
+
"vocab_size": 50688
|
32 |
+
}
|
model/disk-write-timestamp.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
20241103-085550
|
model/done-saving
ADDED
File without changes
|
model/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0141f144cfade06979dc4a75fc76233ef68f2d39da2f5b210fd7029e29bd6167
|
3 |
+
size 46346449502
|
model/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"format": "pt"}, "weight_map": {"": "pytorch_model.bin"}}
|
model/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
model/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model/tokenizer_config.json
ADDED
@@ -0,0 +1,215 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
207 |
+
"bos_token": "<|endoftext|>",
|
208 |
+
"clean_up_tokenization_spaces": false,
|
209 |
+
"eos_token": "<|endoftext|>",
|
210 |
+
"model_max_length": 2048,
|
211 |
+
"pad_token": "<|endoftext|>",
|
212 |
+
"padding_side": "right",
|
213 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
214 |
+
"unk_token": "<|endoftext|>"
|
215 |
+
}
|
optimizer_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d69e76fed6e2f0a3ec7d44c10671d0f8cb7cf95ea3b39eb5a0378e03be4b7344
|
3 |
+
size 11586667274
|
optimizer_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b39304f73de6890fc30d39daf7f30c0cb55677aad2beb470844d3b3d5e0136c
|
3 |
+
size 11586667270
|
optimizer_2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b7bf7b907cae1ee34120f01a583ada55ff4bb064433b2edb92bcce8f46680dd
|
3 |
+
size 11586625218
|
optimizer_3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ecf2bb203fc2e35eacf7ffea5859f7cdbf0d91558bd4fc4540dc4e94cc6aa17
|
3 |
+
size 11586605978
|
rng/distributed_rng_state_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae994ec553d409bbad89373cbca07b36b3fd95fd08dd014f5b8a89566de98a9d
|
3 |
+
size 1120
|
rng/distributed_rng_state_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9faf2cef9da43fdbdbb7a74ced021e617fe767239ffde53bb26b1c27bc149924
|
3 |
+
size 1120
|
rng/distributed_rng_state_2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e724da8f2d1ea6f9b0fa1c4c0b6ed0864dc77328cddfda3d2f5bb79e87a5cc3
|
3 |
+
size 1120
|
rng/distributed_rng_state_3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d28ab8473f489f6bde5dd148fe1d95cab6b9a3308e64f4367bcd481d3c0cfd57
|
3 |
+
size 1120
|
rng/torch_rng_state_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d0072374ea5e72a08304099691b1241257b8919acd469ba7ae7903c55a5c52d
|
3 |
+
size 6286
|
rng/torch_rng_state_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6629fd06e55775df54974ff6cf030b5b8c01a720b9e49049720337e844f4c3d4
|
3 |
+
size 6286
|
rng/torch_rng_state_2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ccac21b3b4f8011d186a7897de4871f217308979e3ffe641fca144d87d3e785
|
3 |
+
size 6286
|
rng/torch_rng_state_3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94b12ca2b8358ae1016d4a93e94bdd3a3bd020249bbb61db5a96a426eb4c9b27
|
3 |
+
size 6286
|
save_complete
ADDED
File without changes
|
state.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"epoch": 3, "flops": 335093604065280000}
|