Hugging Face's logo

parkervg
/
destt5-schema-prediction

Text2Text Generation
Transformers
PyTorch
Safetensors
English
t5
text2sql
Inference Endpoints
text-generation-inference
Model card Files Community
2
Glenn, Parker commited on
Commit
25b2a12
•
1 Parent(s): 940a36a

initial commit

Browse files
Files changed (13) hide show
  1. .DS_Store +0 -0
  2. added_tokens.json +1 -0
  3. config.json +60 -0
  4. optimizer.pt +3 -0
  5. pytorch_model.bin +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +1 -0
  9. spiece.model +3 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +1 -0
  12. trainer_state.json +230 -0
  13. training_args.bin +3 -0
.DS_Store ADDED
Binary file (6.15 kB). View file
 
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {" <": 32101, " <=": 32100}
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./splash_train_concept_no_aliases/checkpoint-320",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 4096,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "diversity_penalty": null,
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "max_length": 512,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.18.0",
58
+ "use_cache": true,
59
+ "vocab_size": 32102
60
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5b9e0db6eea430e62a8fdd9f1d5f4101cec502229cd72e63b74c2301829dae
3
+ size 5383060
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afa79b7061c8846b4aa606d80ef06953ff60bf10d4c94b04ea23272f7a26e06
3
+ size 2950750420
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9eee7a11a0aae50e6b3dc1a9202841a9348eee13be9ecb26fce89406cd5ecc
3
+ size 15690
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c37c01577fff82c83af3895694c197cc30c027cff9e3a5ade410f9457e75f75c
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
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 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "./splash_train_concept_no_aliases/checkpoint-320", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8566413316413316,
3
+ "best_model_checkpoint": "./splash_train_concept_continued/checkpoint-128",
4
+ "epoch": 127.54739652870494,
5
+ "global_step": 128,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.55,
12
+ "learning_rate": 0.0001,
13
+ "loss": 0.0026,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 3.55,
18
+ "learning_rate": 0.0001,
19
+ "loss": 0.0011,
20
+ "step": 4
21
+ },
22
+ {
23
+ "epoch": 7.55,
24
+ "learning_rate": 0.0001,
25
+ "loss": 0.0022,
26
+ "step": 8
27
+ },
28
+ {
29
+ "epoch": 11.55,
30
+ "learning_rate": 0.0001,
31
+ "loss": 0.0018,
32
+ "step": 12
33
+ },
34
+ {
35
+ "epoch": 15.55,
36
+ "learning_rate": 0.0001,
37
+ "loss": 0.0003,
38
+ "step": 16
39
+ },
40
+ {
41
+ "epoch": 19.55,
42
+ "learning_rate": 0.0001,
43
+ "loss": 0.0002,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 23.55,
48
+ "learning_rate": 0.0001,
49
+ "loss": 0.0003,
50
+ "step": 24
51
+ },
52
+ {
53
+ "epoch": 27.55,
54
+ "learning_rate": 0.0001,
55
+ "loss": 0.0002,
56
+ "step": 28
57
+ },
58
+ {
59
+ "epoch": 31.55,
60
+ "learning_rate": 0.0001,
61
+ "loss": 0.0018,
62
+ "step": 32
63
+ },
64
+ {
65
+ "epoch": 35.55,
66
+ "learning_rate": 0.0001,
67
+ "loss": 0.0022,
68
+ "step": 36
69
+ },
70
+ {
71
+ "epoch": 39.55,
72
+ "learning_rate": 0.0001,
73
+ "loss": 0.0002,
74
+ "step": 40
75
+ },
76
+ {
77
+ "epoch": 43.55,
78
+ "learning_rate": 0.0001,
79
+ "loss": 0.0002,
80
+ "step": 44
81
+ },
82
+ {
83
+ "epoch": 47.55,
84
+ "learning_rate": 0.0001,
85
+ "loss": 0.0002,
86
+ "step": 48
87
+ },
88
+ {
89
+ "epoch": 51.55,
90
+ "learning_rate": 0.0001,
91
+ "loss": 0.0002,
92
+ "step": 52
93
+ },
94
+ {
95
+ "epoch": 55.55,
96
+ "learning_rate": 0.0001,
97
+ "loss": 0.0002,
98
+ "step": 56
99
+ },
100
+ {
101
+ "epoch": 59.55,
102
+ "learning_rate": 0.0001,
103
+ "loss": 0.0051,
104
+ "step": 60
105
+ },
106
+ {
107
+ "epoch": 63.55,
108
+ "learning_rate": 0.0001,
109
+ "loss": 0.0003,
110
+ "step": 64
111
+ },
112
+ {
113
+ "epoch": 63.55,
114
+ "eval_f1_score": 0.8557729057729058,
115
+ "eval_loss": 0.3384537696838379,
116
+ "eval_runtime": 287.8554,
117
+ "eval_samples_per_second": 3.342,
118
+ "step": 64
119
+ },
120
+ {
121
+ "epoch": 67.55,
122
+ "learning_rate": 0.0001,
123
+ "loss": 0.0001,
124
+ "step": 68
125
+ },
126
+ {
127
+ "epoch": 71.55,
128
+ "learning_rate": 0.0001,
129
+ "loss": 0.0002,
130
+ "step": 72
131
+ },
132
+ {
133
+ "epoch": 75.55,
134
+ "learning_rate": 0.0001,
135
+ "loss": 0.0002,
136
+ "step": 76
137
+ },
138
+ {
139
+ "epoch": 79.55,
140
+ "learning_rate": 0.0001,
141
+ "loss": 0.0046,
142
+ "step": 80
143
+ },
144
+ {
145
+ "epoch": 83.55,
146
+ "learning_rate": 0.0001,
147
+ "loss": 0.0007,
148
+ "step": 84
149
+ },
150
+ {
151
+ "epoch": 87.55,
152
+ "learning_rate": 0.0001,
153
+ "loss": 0.0001,
154
+ "step": 88
155
+ },
156
+ {
157
+ "epoch": 91.55,
158
+ "learning_rate": 0.0001,
159
+ "loss": 0.0001,
160
+ "step": 92
161
+ },
162
+ {
163
+ "epoch": 95.55,
164
+ "learning_rate": 0.0001,
165
+ "loss": 0.0001,
166
+ "step": 96
167
+ },
168
+ {
169
+ "epoch": 99.55,
170
+ "learning_rate": 0.0001,
171
+ "loss": 0.0001,
172
+ "step": 100
173
+ },
174
+ {
175
+ "epoch": 103.55,
176
+ "learning_rate": 0.0001,
177
+ "loss": 0.0001,
178
+ "step": 104
179
+ },
180
+ {
181
+ "epoch": 107.55,
182
+ "learning_rate": 0.0001,
183
+ "loss": 0.0001,
184
+ "step": 108
185
+ },
186
+ {
187
+ "epoch": 111.55,
188
+ "learning_rate": 0.0001,
189
+ "loss": 0.0006,
190
+ "step": 112
191
+ },
192
+ {
193
+ "epoch": 115.55,
194
+ "learning_rate": 0.0001,
195
+ "loss": 0.0001,
196
+ "step": 116
197
+ },
198
+ {
199
+ "epoch": 119.55,
200
+ "learning_rate": 0.0001,
201
+ "loss": 0.0001,
202
+ "step": 120
203
+ },
204
+ {
205
+ "epoch": 123.55,
206
+ "learning_rate": 0.0001,
207
+ "loss": 0.0001,
208
+ "step": 124
209
+ },
210
+ {
211
+ "epoch": 127.55,
212
+ "learning_rate": 0.0001,
213
+ "loss": 0.0001,
214
+ "step": 128
215
+ },
216
+ {
217
+ "epoch": 127.55,
218
+ "eval_f1_score": 0.8566413316413316,
219
+ "eval_loss": 0.35904133319854736,
220
+ "eval_runtime": 290.9961,
221
+ "eval_samples_per_second": 3.306,
222
+ "step": 128
223
+ }
224
+ ],
225
+ "max_steps": 3072,
226
+ "num_train_epochs": 3072,
227
+ "total_flos": 1.897685960620032e+18,
228
+ "trial_name": null,
229
+ "trial_params": null
230
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac862633dd50217b417b1702b6bab2210b5fec4ad55a176066d30afeddbbd2b0
3
+ size 3183