Hugging Face's logo

Salesforce
/
qaconv-unifiedqa-t5-large

Text2Text Generation
Transformers
PyTorch
TensorFlow
JAX
t5
text-generation-inference
Model card Files Community
2
Jason Wu commited on
Commit
b65623e
·
1 Parent(s): 290b16b

init

Browse files
Files changed (6) hide show
  1. config.json +63 -0
  2. special_tokens_map.json +1 -0
  3. spiece.model +3 -0
  4. tokenizer_config.json +1 -0
  5. trainer_state.json +257 -0
  6. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/unifiedqa-t5-large",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 4096,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "early_stopping": true,
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
+ "length_penalty": 2.0,
18
+ "max_length": 200,
19
+ "min_length": 30,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "no_repeat_ngram_size": 3,
23
+ "num_beams": 4,
24
+ "num_decoder_layers": 24,
25
+ "num_heads": 16,
26
+ "num_layers": 24,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "prefix": "summarize: ",
30
+ "relative_attention_num_buckets": 32,
31
+ "task_specific_params": {
32
+ "summarization": {
33
+ "early_stopping": true,
34
+ "length_penalty": 2.0,
35
+ "max_length": 200,
36
+ "min_length": 30,
37
+ "no_repeat_ngram_size": 3,
38
+ "num_beams": 4,
39
+ "prefix": "summarize: "
40
+ },
41
+ "translation_en_to_de": {
42
+ "early_stopping": true,
43
+ "max_length": 300,
44
+ "num_beams": 4,
45
+ "prefix": "translate English to German: "
46
+ },
47
+ "translation_en_to_fr": {
48
+ "early_stopping": true,
49
+ "max_length": 300,
50
+ "num_beams": 4,
51
+ "prefix": "translate English to French: "
52
+ },
53
+ "translation_en_to_ro": {
54
+ "early_stopping": true,
55
+ "max_length": 300,
56
+ "num_beams": 4,
57
+ "prefix": "translate English to Romanian: "
58
+ }
59
+ },
60
+ "transformers_version": "4.5.1",
61
+ "use_cache": true,
62
+ "vocab_size": 32128
63
+ }
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_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": "/root/.cache/huggingface/transformers/fe7918a6d07661cb20a4043d92715df8c8d9ebb3e48fb4f828b116d5ca17020c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "name_or_path": "allenai/unifiedqa-t5-large"}
trainer_state.json ADDED
@@ -0,0 +1,257 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 68220,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.73,
12
+ "learning_rate": 2.780123131046614e-05,
13
+ "loss": 0.635,
14
+ "step": 5000
15
+ },
16
+ {
17
+ "epoch": 0.73,
18
+ "eval_gen_len": 34.1,
19
+ "eval_loss": 0.5430836081504822,
20
+ "eval_rouge1": 19.0735,
21
+ "eval_rouge2": 11.8399,
22
+ "eval_rougeL": 18.8386,
23
+ "eval_rougeLsum": 18.9348,
24
+ "eval_runtime": 3057.941,
25
+ "eval_samples_per_second": 1.116,
26
+ "step": 5000
27
+ },
28
+ {
29
+ "epoch": 1.47,
30
+ "learning_rate": 2.5602462620932278e-05,
31
+ "loss": 0.4721,
32
+ "step": 10000
33
+ },
34
+ {
35
+ "epoch": 1.47,
36
+ "eval_gen_len": 34.1,
37
+ "eval_loss": 0.5901889204978943,
38
+ "eval_rouge1": 18.6178,
39
+ "eval_rouge2": 11.5042,
40
+ "eval_rougeL": 18.3666,
41
+ "eval_rougeLsum": 18.4882,
42
+ "eval_runtime": 3066.7913,
43
+ "eval_samples_per_second": 1.113,
44
+ "step": 10000
45
+ },
46
+ {
47
+ "epoch": 2.2,
48
+ "learning_rate": 2.3403693931398417e-05,
49
+ "loss": 0.3803,
50
+ "step": 15000
51
+ },
52
+ {
53
+ "epoch": 2.2,
54
+ "eval_gen_len": 33.1,
55
+ "eval_loss": 0.6489335298538208,
56
+ "eval_rouge1": 20.6093,
57
+ "eval_rouge2": 12.6294,
58
+ "eval_rougeL": 20.2763,
59
+ "eval_rougeLsum": 20.3561,
60
+ "eval_runtime": 2950.4654,
61
+ "eval_samples_per_second": 1.157,
62
+ "step": 15000
63
+ },
64
+ {
65
+ "epoch": 2.93,
66
+ "learning_rate": 2.120492524186456e-05,
67
+ "loss": 0.3072,
68
+ "step": 20000
69
+ },
70
+ {
71
+ "epoch": 2.93,
72
+ "eval_gen_len": 33.0,
73
+ "eval_loss": 0.6617271304130554,
74
+ "eval_rouge1": 21.175,
75
+ "eval_rouge2": 12.9525,
76
+ "eval_rougeL": 20.85,
77
+ "eval_rougeLsum": 20.9327,
78
+ "eval_runtime": 2933.4173,
79
+ "eval_samples_per_second": 1.163,
80
+ "step": 20000
81
+ },
82
+ {
83
+ "epoch": 3.66,
84
+ "learning_rate": 1.9006156552330694e-05,
85
+ "loss": 0.225,
86
+ "step": 25000
87
+ },
88
+ {
89
+ "epoch": 3.66,
90
+ "eval_gen_len": 33.7,
91
+ "eval_loss": 0.7911365628242493,
92
+ "eval_rouge1": 20.0159,
93
+ "eval_rouge2": 12.3403,
94
+ "eval_rougeL": 19.7354,
95
+ "eval_rougeLsum": 19.831,
96
+ "eval_runtime": 3007.359,
97
+ "eval_samples_per_second": 1.135,
98
+ "step": 25000
99
+ },
100
+ {
101
+ "epoch": 4.4,
102
+ "learning_rate": 1.6807387862796836e-05,
103
+ "loss": 0.1862,
104
+ "step": 30000
105
+ },
106
+ {
107
+ "epoch": 4.4,
108
+ "eval_gen_len": 33.5,
109
+ "eval_loss": 0.9180275201797485,
110
+ "eval_rouge1": 20.6775,
111
+ "eval_rouge2": 12.58,
112
+ "eval_rougeL": 20.3712,
113
+ "eval_rougeLsum": 20.4162,
114
+ "eval_runtime": 2990.0617,
115
+ "eval_samples_per_second": 1.141,
116
+ "step": 30000
117
+ },
118
+ {
119
+ "epoch": 5.13,
120
+ "learning_rate": 1.4608619173262973e-05,
121
+ "loss": 0.1559,
122
+ "step": 35000
123
+ },
124
+ {
125
+ "epoch": 5.13,
126
+ "eval_gen_len": 33.2,
127
+ "eval_loss": 1.0511494874954224,
128
+ "eval_rouge1": 20.3652,
129
+ "eval_rouge2": 12.4459,
130
+ "eval_rougeL": 20.0386,
131
+ "eval_rougeLsum": 20.1371,
132
+ "eval_runtime": 2942.5442,
133
+ "eval_samples_per_second": 1.16,
134
+ "step": 35000
135
+ },
136
+ {
137
+ "epoch": 5.86,
138
+ "learning_rate": 1.2409850483729111e-05,
139
+ "loss": 0.1256,
140
+ "step": 40000
141
+ },
142
+ {
143
+ "epoch": 5.86,
144
+ "eval_gen_len": 33.2,
145
+ "eval_loss": 1.1184989213943481,
146
+ "eval_rouge1": 20.6117,
147
+ "eval_rouge2": 12.6157,
148
+ "eval_rougeL": 20.3466,
149
+ "eval_rougeLsum": 20.4447,
150
+ "eval_runtime": 2945.923,
151
+ "eval_samples_per_second": 1.159,
152
+ "step": 40000
153
+ },
154
+ {
155
+ "epoch": 6.6,
156
+ "learning_rate": 1.0211081794195251e-05,
157
+ "loss": 0.1044,
158
+ "step": 45000
159
+ },
160
+ {
161
+ "epoch": 6.6,
162
+ "eval_gen_len": 33.5,
163
+ "eval_loss": 1.262742280960083,
164
+ "eval_rouge1": 20.4935,
165
+ "eval_rouge2": 12.393,
166
+ "eval_rougeL": 20.1894,
167
+ "eval_rougeLsum": 20.2828,
168
+ "eval_runtime": 2982.3339,
169
+ "eval_samples_per_second": 1.144,
170
+ "step": 45000
171
+ },
172
+ {
173
+ "epoch": 7.33,
174
+ "learning_rate": 8.01231310466139e-06,
175
+ "loss": 0.0844,
176
+ "step": 50000
177
+ },
178
+ {
179
+ "epoch": 7.33,
180
+ "eval_gen_len": 33.3,
181
+ "eval_loss": 1.5101187229156494,
182
+ "eval_rouge1": 21.5004,
183
+ "eval_rouge2": 12.9803,
184
+ "eval_rougeL": 21.2348,
185
+ "eval_rougeLsum": 21.3046,
186
+ "eval_runtime": 2964.055,
187
+ "eval_samples_per_second": 1.151,
188
+ "step": 50000
189
+ },
190
+ {
191
+ "epoch": 8.06,
192
+ "learning_rate": 5.813544415127529e-06,
193
+ "loss": 0.075,
194
+ "step": 55000
195
+ },
196
+ {
197
+ "epoch": 8.06,
198
+ "eval_gen_len": 33.1,
199
+ "eval_loss": 1.5069748163223267,
200
+ "eval_rouge1": 20.8058,
201
+ "eval_rouge2": 12.4951,
202
+ "eval_rougeL": 20.5311,
203
+ "eval_rougeLsum": 20.6195,
204
+ "eval_runtime": 2941.4323,
205
+ "eval_samples_per_second": 1.16,
206
+ "step": 55000
207
+ },
208
+ {
209
+ "epoch": 8.8,
210
+ "learning_rate": 3.6147757255936676e-06,
211
+ "loss": 0.0612,
212
+ "step": 60000
213
+ },
214
+ {
215
+ "epoch": 8.8,
216
+ "eval_gen_len": 33.2,
217
+ "eval_loss": 1.579475998878479,
218
+ "eval_rouge1": 20.9465,
219
+ "eval_rouge2": 12.6351,
220
+ "eval_rougeL": 20.6478,
221
+ "eval_rougeLsum": 20.7292,
222
+ "eval_runtime": 2955.2469,
223
+ "eval_samples_per_second": 1.155,
224
+ "step": 60000
225
+ },
226
+ {
227
+ "epoch": 9.53,
228
+ "learning_rate": 1.4160070360598064e-06,
229
+ "loss": 0.0519,
230
+ "step": 65000
231
+ },
232
+ {
233
+ "epoch": 9.53,
234
+ "eval_gen_len": 33.2,
235
+ "eval_loss": 1.6573169231414795,
236
+ "eval_rouge1": 20.9384,
237
+ "eval_rouge2": 12.6776,
238
+ "eval_rougeL": 20.6249,
239
+ "eval_rougeLsum": 20.7352,
240
+ "eval_runtime": 2938.7831,
241
+ "eval_samples_per_second": 1.161,
242
+ "step": 65000
243
+ },
244
+ {
245
+ "epoch": 10.0,
246
+ "step": 68220,
247
+ "total_flos": 5.6695121367374234e+17,
248
+ "train_runtime": 78827.7854,
249
+ "train_samples_per_second": 0.865
250
+ }
251
+ ],
252
+ "max_steps": 68220,
253
+ "num_train_epochs": 10,
254
+ "total_flos": 5.6695121367374234e+17,
255
+ "trial_name": null,
256
+ "trial_params": null
257
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0fc02be3e4e38486be474a203f689db7256b9316749b38e22671949a8fa499
3
+ size 2607