Hugging Face's logo

rooftopcoder
/
distilt5-coqa

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
1
rooftopcoder commited on
Commit
6eee8a6
·
1 Parent(s): 82ce6e6

Training in progress, step 500

Browse files
Files changed (13) hide show
  1. .gitignore +1 -0
  2. added_tokens.json +4 -0
  3. config.json +57 -0
  4. pytorch_model.bin +3 -0
  5. runs/May16_08-01-01_17a942d449c2/1684224202.6148336/events.out.tfevents.1684224202.17a942d449c2.673.1 +3 -0
  6. runs/May16_08-01-01_17a942d449c2/1684224236.2348454/events.out.tfevents.1684224236.17a942d449c2.673.2 +3 -0
  7. runs/May16_08-01-01_17a942d449c2/1684224236.9770648/events.out.tfevents.1684224236.17a942d449c2.673.3 +3 -0
  8. runs/May16_08-01-01_17a942d449c2/events.out.tfevents.1684224202.17a942d449c2.673.0 +3 -0
  9. special_tokens_map.json +107 -0
  10. spiece.model +3 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +212 -0
  13. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<hl>": 32101,
3
+ "<sep>": 32100
4
+ }
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "valhalla/distilt5-qa-qg-hl-6-4",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "init_metadata": {
15
+ "copied_decoder_layers": [
16
+ 0,
17
+ 1,
18
+ 3,
19
+ 5
20
+ ],
21
+ "copied_encoder_layers": [
22
+ 0,
23
+ 1,
24
+ 2,
25
+ 3,
26
+ 4,
27
+ 5
28
+ ],
29
+ "teacher_type": "t5"
30
+ },
31
+ "initializer_factor": 1.0,
32
+ "is_encoder_decoder": true,
33
+ "is_gated_act": false,
34
+ "layer_norm_epsilon": 1e-06,
35
+ "model_type": "t5",
36
+ "n_positions": 512,
37
+ "num_decoder_layers": 4,
38
+ "num_heads": 8,
39
+ "num_layers": 6,
40
+ "output_past": true,
41
+ "pad_token_id": 0,
42
+ "relative_attention_max_distance": 128,
43
+ "relative_attention_num_buckets": 32,
44
+ "task_specific_params": {
45
+ "translation_en_to_fr": {
46
+ "early_stopping": true,
47
+ "length_penalty": 1.0,
48
+ "max_length": 32,
49
+ "num_beams": 4,
50
+ "prefix": ""
51
+ }
52
+ },
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.29.1",
55
+ "use_cache": true,
56
+ "vocab_size": 32102
57
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9dfcefe4c51eb6d7fb4a32263ba11526b9e074ac9ddd7b16ddc8258283da58
3
+ size 208442673
runs/May16_08-01-01_17a942d449c2/1684224202.6148336/events.out.tfevents.1684224202.17a942d449c2.673.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ddaaf7f0e5db37e45cd19f2afc731d3010754dc3feaafdc297b956c0dd9fa9
3
+ size 6152
runs/May16_08-01-01_17a942d449c2/1684224236.2348454/events.out.tfevents.1684224236.17a942d449c2.673.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6aef0e3a7809a51344562c563aaad3a02d9da14722e8a5b31cf53ae2d4dd73
3
+ size 6152
runs/May16_08-01-01_17a942d449c2/1684224236.9770648/events.out.tfevents.1684224236.17a942d449c2.673.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb47daac3e3d022cec7e4b5ab899d3c669b412ac7827c39742029a03a34b789
3
+ size 6152
runs/May16_08-01-01_17a942d449c2/events.out.tfevents.1684224202.17a942d449c2.673.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e35cb127ba73c6caa49159e80bad0231787cdd01c6f62c0a18de1496d0988e0
3
+ size 13901
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_0>",
104
+ "<extra_id_1>",
105
+ "<extra_id_2>",
106
+ "<extra_id_3>",
107
+ "<extra_id_4>",
108
+ "<extra_id_5>",
109
+ "<extra_id_6>",
110
+ "<extra_id_7>",
111
+ "<extra_id_8>",
112
+ "<extra_id_9>",
113
+ "<extra_id_10>",
114
+ "<extra_id_11>",
115
+ "<extra_id_12>",
116
+ "<extra_id_13>",
117
+ "<extra_id_14>",
118
+ "<extra_id_15>",
119
+ "<extra_id_16>",
120
+ "<extra_id_17>",
121
+ "<extra_id_18>",
122
+ "<extra_id_19>",
123
+ "<extra_id_20>",
124
+ "<extra_id_21>",
125
+ "<extra_id_22>",
126
+ "<extra_id_23>",
127
+ "<extra_id_24>",
128
+ "<extra_id_25>",
129
+ "<extra_id_26>",
130
+ "<extra_id_27>",
131
+ "<extra_id_28>",
132
+ "<extra_id_29>",
133
+ "<extra_id_30>",
134
+ "<extra_id_31>",
135
+ "<extra_id_32>",
136
+ "<extra_id_33>",
137
+ "<extra_id_34>",
138
+ "<extra_id_35>",
139
+ "<extra_id_36>",
140
+ "<extra_id_37>",
141
+ "<extra_id_38>",
142
+ "<extra_id_39>",
143
+ "<extra_id_40>",
144
+ "<extra_id_41>",
145
+ "<extra_id_42>",
146
+ "<extra_id_43>",
147
+ "<extra_id_44>",
148
+ "<extra_id_45>",
149
+ "<extra_id_46>",
150
+ "<extra_id_47>",
151
+ "<extra_id_48>",
152
+ "<extra_id_49>",
153
+ "<extra_id_50>",
154
+ "<extra_id_51>",
155
+ "<extra_id_52>",
156
+ "<extra_id_53>",
157
+ "<extra_id_54>",
158
+ "<extra_id_55>",
159
+ "<extra_id_56>",
160
+ "<extra_id_57>",
161
+ "<extra_id_58>",
162
+ "<extra_id_59>",
163
+ "<extra_id_60>",
164
+ "<extra_id_61>",
165
+ "<extra_id_62>",
166
+ "<extra_id_63>",
167
+ "<extra_id_64>",
168
+ "<extra_id_65>",
169
+ "<extra_id_66>",
170
+ "<extra_id_67>",
171
+ "<extra_id_68>",
172
+ "<extra_id_69>",
173
+ "<extra_id_70>",
174
+ "<extra_id_71>",
175
+ "<extra_id_72>",
176
+ "<extra_id_73>",
177
+ "<extra_id_74>",
178
+ "<extra_id_75>",
179
+ "<extra_id_76>",
180
+ "<extra_id_77>",
181
+ "<extra_id_78>",
182
+ "<extra_id_79>",
183
+ "<extra_id_80>",
184
+ "<extra_id_81>",
185
+ "<extra_id_82>",
186
+ "<extra_id_83>",
187
+ "<extra_id_84>",
188
+ "<extra_id_85>",
189
+ "<extra_id_86>",
190
+ "<extra_id_87>",
191
+ "<extra_id_88>",
192
+ "<extra_id_89>",
193
+ "<extra_id_90>",
194
+ "<extra_id_91>",
195
+ "<extra_id_92>",
196
+ "<extra_id_93>",
197
+ "<extra_id_94>",
198
+ "<extra_id_95>",
199
+ "<extra_id_96>",
200
+ "<extra_id_97>",
201
+ "<extra_id_98>",
202
+ "<extra_id_99>"
203
+ ],
204
+ "clean_up_tokenization_spaces": true,
205
+ "eos_token": "</s>",
206
+ "extra_ids": 100,
207
+ "model_max_length": 512,
208
+ "pad_token": "<pad>",
209
+ "sp_model_kwargs": {},
210
+ "tokenizer_class": "T5Tokenizer",
211
+ "unk_token": "<unk>"
212
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7baf056fef5a261e8aed7e326df230cb0f035686f25aac2d24e6218e1e5b61a2
3
+ size 4091