artelabsuper commited on
Commit
5b3e33d
1 Parent(s): 8667fb2

add trained model

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - rouge
6
+ model-index:
7
+ - name: summarization_mlsum
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # summarization_mlsum
15
+
16
+ This model is a fine-tuned version of [gsarti/it5-base](https://huggingface.co/gsarti/it5-base) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.0190
19
+ - Rouge1: 19.2854
20
+ - Rouge2: 6.0392
21
+ - Rougel: 16.4987
22
+ - Rougelsum: 16.616
23
+ - Gen Len: 32.7635
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 6
44
+ - eval_batch_size: 6
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 4.0
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.12.0.dev0
57
+ - Pytorch 1.9.1+cu102
58
+ - Datasets 1.12.1
59
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_gen_len": 32.7635,
4
+ "eval_loss": 2.0189740657806396,
5
+ "eval_rouge1": 19.2854,
6
+ "eval_rouge2": 6.0392,
7
+ "eval_rougeL": 16.4987,
8
+ "eval_rougeLsum": 16.616,
9
+ "eval_runtime": 647.9074,
10
+ "eval_samples": 4000,
11
+ "eval_samples_per_second": 6.174,
12
+ "eval_steps_per_second": 1.029,
13
+ "predict_gen_len": 32.5268,
14
+ "predict_loss": 1.9996718168258667,
15
+ "predict_rouge1": 19.3739,
16
+ "predict_rouge2": 5.9753,
17
+ "predict_rougeL": 16.691,
18
+ "predict_rougeLsum": 16.7862,
19
+ "predict_runtime": 650.8156,
20
+ "predict_samples": 4000,
21
+ "predict_samples_per_second": 6.146,
22
+ "predict_steps_per_second": 1.025,
23
+ "train_loss": 2.132151625336569,
24
+ "train_runtime": 19550.5305,
25
+ "train_samples": 31997,
26
+ "train_samples_per_second": 6.547,
27
+ "train_steps_per_second": 1.091
28
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gsarti/it5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "gradient_checkpointing": false,
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "model_type": "t5",
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.12.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 32103
29
+ }
eval_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_gen_len": 32.7635,
4
+ "eval_loss": 2.0189740657806396,
5
+ "eval_rouge1": 19.2854,
6
+ "eval_rouge2": 6.0392,
7
+ "eval_rougeL": 16.4987,
8
+ "eval_rougeLsum": 16.616,
9
+ "eval_runtime": 647.9074,
10
+ "eval_samples": 4000,
11
+ "eval_samples_per_second": 6.174,
12
+ "eval_steps_per_second": 1.029
13
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
predict_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_gen_len": 32.5268,
3
+ "predict_loss": 1.9996718168258667,
4
+ "predict_rouge1": 19.3739,
5
+ "predict_rouge2": 5.9753,
6
+ "predict_rougeL": 16.691,
7
+ "predict_rougeLsum": 16.7862,
8
+ "predict_runtime": 650.8156,
9
+ "predict_samples": 4000,
10
+ "predict_samples_per_second": 6.146,
11
+ "predict_steps_per_second": 1.025
12
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a2e861d40ecd3b41c78c6d58bb53271e4ee48a2db66998a4d975039b91eee4
3
+ size 990284749
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>"]}
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>"], "special_tokens_map_file": null, "name_or_path": "gsarti/it5-base", "tokenizer_class": "T5Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 2.132151625336569,
4
+ "train_runtime": 19550.5305,
5
+ "train_samples": 31997,
6
+ "train_samples_per_second": 6.547,
7
+ "train_steps_per_second": 1.091
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 21332,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 4.882805175323458e-05,
13
+ "loss": 2.894,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.19,
18
+ "learning_rate": 4.7656103506469155e-05,
19
+ "loss": 2.3094,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.28,
24
+ "learning_rate": 4.648415525970373e-05,
25
+ "loss": 2.256,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.38,
30
+ "learning_rate": 4.5312207012938315e-05,
31
+ "loss": 2.2547,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.47,
36
+ "learning_rate": 4.4140258766172885e-05,
37
+ "loss": 2.2201,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.56,
42
+ "learning_rate": 4.296831051940747e-05,
43
+ "loss": 2.1982,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.66,
48
+ "learning_rate": 4.1796362272642045e-05,
49
+ "loss": 2.2123,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.75,
54
+ "learning_rate": 4.0624414025876614e-05,
55
+ "loss": 2.178,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.84,
60
+ "learning_rate": 3.94524657791112e-05,
61
+ "loss": 2.1991,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.94,
66
+ "learning_rate": 3.8280517532345774e-05,
67
+ "loss": 2.1734,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.03,
72
+ "learning_rate": 3.710856928558035e-05,
73
+ "loss": 2.1487,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.13,
78
+ "learning_rate": 3.593662103881493e-05,
79
+ "loss": 2.1605,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.22,
84
+ "learning_rate": 3.476467279204951e-05,
85
+ "loss": 2.1316,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.31,
90
+ "learning_rate": 3.359272454528408e-05,
91
+ "loss": 2.1173,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.41,
96
+ "learning_rate": 3.242077629851866e-05,
97
+ "loss": 2.1218,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.5,
102
+ "learning_rate": 3.124882805175324e-05,
103
+ "loss": 2.1017,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.59,
108
+ "learning_rate": 3.0076879804987813e-05,
109
+ "loss": 2.1083,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.69,
114
+ "learning_rate": 2.8904931558222393e-05,
115
+ "loss": 2.1279,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.78,
120
+ "learning_rate": 2.7732983311456966e-05,
121
+ "loss": 2.1056,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.88,
126
+ "learning_rate": 2.6561035064691543e-05,
127
+ "loss": 2.1081,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.97,
132
+ "learning_rate": 2.5389086817926123e-05,
133
+ "loss": 2.1229,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 2.06,
138
+ "learning_rate": 2.42171385711607e-05,
139
+ "loss": 2.1051,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.16,
144
+ "learning_rate": 2.3045190324395276e-05,
145
+ "loss": 2.0861,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.25,
150
+ "learning_rate": 2.1873242077629852e-05,
151
+ "loss": 2.0813,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.34,
156
+ "learning_rate": 2.070129383086443e-05,
157
+ "loss": 2.0704,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.44,
162
+ "learning_rate": 1.952934558409901e-05,
163
+ "loss": 2.0753,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.53,
168
+ "learning_rate": 1.8357397337333585e-05,
169
+ "loss": 2.0803,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.63,
174
+ "learning_rate": 1.718544909056816e-05,
175
+ "loss": 2.0947,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.72,
180
+ "learning_rate": 1.6013500843802738e-05,
181
+ "loss": 2.0526,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.81,
186
+ "learning_rate": 1.4841552597037315e-05,
187
+ "loss": 2.0683,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.91,
192
+ "learning_rate": 1.3669604350271891e-05,
193
+ "loss": 2.0641,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 3.0,
198
+ "learning_rate": 1.249765610350647e-05,
199
+ "loss": 2.0679,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 3.09,
204
+ "learning_rate": 1.1325707856741047e-05,
205
+ "loss": 2.0329,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 3.19,
210
+ "learning_rate": 1.0153759609975624e-05,
211
+ "loss": 2.0512,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 3.28,
216
+ "learning_rate": 8.9818113632102e-06,
217
+ "loss": 2.0731,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 3.38,
222
+ "learning_rate": 7.809863116444779e-06,
223
+ "loss": 2.0693,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 3.47,
228
+ "learning_rate": 6.637914869679355e-06,
229
+ "loss": 2.0459,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 3.56,
234
+ "learning_rate": 5.4659666229139326e-06,
235
+ "loss": 2.0371,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 3.66,
240
+ "learning_rate": 4.294018376148509e-06,
241
+ "loss": 2.0285,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 3.75,
246
+ "learning_rate": 3.122070129383087e-06,
247
+ "loss": 2.0494,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 3.84,
252
+ "learning_rate": 1.9501218826176638e-06,
253
+ "loss": 2.0385,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 3.94,
258
+ "learning_rate": 7.781736358522408e-07,
259
+ "loss": 2.0785,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 4.0,
264
+ "step": 21332,
265
+ "total_flos": 7.623777879473818e+16,
266
+ "train_loss": 2.132151625336569,
267
+ "train_runtime": 19550.5305,
268
+ "train_samples_per_second": 6.547,
269
+ "train_steps_per_second": 1.091
270
+ }
271
+ ],
272
+ "max_steps": 21332,
273
+ "num_train_epochs": 4,
274
+ "total_flos": 7.623777879473818e+16,
275
+ "trial_name": null,
276
+ "trial_params": null
277
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beace91aac75f278e7cd5a31be3a2e2b092696778bc85a752abf34ab2d39a72c
3
+ size 2927