Hugging Face's logo

thashim
/
test_model

Text Generation
Transformers
TensorBoard
Safetensors
gpt_neox
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
thashim commited on
Commit
ae37e3b
•
1 Parent(s): b5c8e56

Training in progress, epoch 1

Browse files
Files changed (17) hide show
  1. config.json +5 -5
  2. logs/events.out.tfevents.1717595606.sphinx8.stanford.edu +3 -0
  3. logs/events.out.tfevents.1717596031.sphinx8.stanford.edu +3 -0
  4. logs/events.out.tfevents.1717597260.sphinx8.stanford.edu +3 -0
  5. logs/events.out.tfevents.1717597649.sphinx8.stanford.edu +3 -0
  6. logs/events.out.tfevents.1717597840.sphinx8.stanford.edu +3 -0
  7. logs/events.out.tfevents.1717598007.sphinx8.stanford.edu +3 -0
  8. logs/events.out.tfevents.1717598838.sphinx8.stanford.edu +3 -0
  9. logs/events.out.tfevents.1717600105.sphinx8.stanford.edu +3 -0
  10. logs/events.out.tfevents.1717600206.sphinx8.stanford.edu +3 -0
  11. logs/events.out.tfevents.1717605625.sphinx8.stanford.edu +3 -0
  12. logs/events.out.tfevents.1717606001.sphinx8.stanford.edu +3 -0
  13. model.safetensors +2 -2
  14. special_tokens_map.json +23 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +214 -0
  17. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "EleutherAI/pythia-70m",
3
  "architectures": [
4
  "GPTNeoXForCausalLM"
5
  ],
@@ -10,14 +10,14 @@
10
  "eos_token_id": 0,
11
  "hidden_act": "gelu",
12
  "hidden_dropout": 0.0,
13
- "hidden_size": 512,
14
  "initializer_range": 0.02,
15
- "intermediate_size": 2048,
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": 6,
21
  "rope_scaling": null,
22
  "rotary_emb_base": 10000,
23
  "rotary_pct": 0.25,
 
1
  {
2
+ "_name_or_path": "EleutherAI/pythia-160m",
3
  "architectures": [
4
  "GPTNeoXForCausalLM"
5
  ],
 
10
  "eos_token_id": 0,
11
  "hidden_act": "gelu",
12
  "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
  "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
  "layer_norm_eps": 1e-05,
17
  "max_position_embeddings": 2048,
18
  "model_type": "gpt_neox",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
  "rope_scaling": null,
22
  "rotary_emb_base": 10000,
23
  "rotary_pct": 0.25,
logs/events.out.tfevents.1717595606.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a1e4a981f95cd1d9b1621de6f9d6f48ed0b934c2c47382d755f0bc2d2d4edf
3
+ size 6468
logs/events.out.tfevents.1717596031.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38347e04f91e237920c2e757eb3291ace4a376bcef956ea81d5d6dd5515fddb
3
+ size 15119
logs/events.out.tfevents.1717597260.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2854a0291228dbbce9c9d4fc13f13818e093427bfc64869538d1f32729b84ab2
3
+ size 4801
logs/events.out.tfevents.1717597649.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7602f9bc108b7ea96f9219bec7f47ce675e6a0c04df59865e0590b49d826bb7
3
+ size 6257
logs/events.out.tfevents.1717597840.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93011d367263149432cc3b4bf257e7897c5a8b023a910b85bdc565d34ae0b19e
3
+ size 6257
logs/events.out.tfevents.1717598007.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243f94799857458c09bfe2f52ba67d9e79e1e6bb12b8cc42b1a5514eb02244f0
3
+ size 12165
logs/events.out.tfevents.1717598838.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd773a2e64f6405822389c11404645fa0c1da2decd3a1026a5c5301982f1740
3
+ size 6278
logs/events.out.tfevents.1717600105.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec1d476020cb5b333507529c69571262395bd12d4c8a9426e10e84ee09cb76e
3
+ size 4803
logs/events.out.tfevents.1717600206.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1471b3f410de39ec507eb8aa3724725926f88fca971b1a078ada35341b4dbb65
3
+ size 14863
logs/events.out.tfevents.1717605625.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb016554cbd4385c1b9975997c49137a6d8cf1163c9ac1c8ab30c73bfe0a8c9
3
+ size 5019
logs/events.out.tfevents.1717606001.sphinx8.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f35e25b78720078e24d3423eb3a6b38ca9d0fd8d0cb93bd5881ed5e95ec5cb
3
+ size 7772
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32480ebb74aef7716fb6d8013eadee68137de8ff6329297cd526c9c7b6468788
3
- size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:326e8db84f1dc3d5919dc5f0b3f7d68cbac030fef2b8642d8feb92e8accdcabb
3
+ size 649308728
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
209
+ "eos_token": "<|endoftext|>",
210
+ "model_max_length": 1000000000000000019884624838656,
211
+ "pad_token": null,
212
+ "tokenizer_class": "GPTNeoXTokenizer",
213
+ "unk_token": "<|endoftext|>"
214
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13e0bfd76591446f76582435702778ca13cd179b988dd8a946784a4880cc3ac6
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984ed7e5a68d49f15d666492599571bdc312f57955b323eec9cedb4619190d37
3
  size 5112