Hugging Face's logo

mtc
/
google-mt5-large-absinth-span-3-epochs

Text2Text Generation
Transformers
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Community
mtc commited on
Commit
a03d4a9
Β·
verified Β·
1 Parent(s): 4635221

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. .gitattributes +2 -0
  2. README.md +78 -0
  3. checkpoint-1956/config.json +33 -0
  4. checkpoint-1956/generation_config.json +7 -0
  5. checkpoint-1956/model.safetensors +3 -0
  6. checkpoint-1956/optimizer.pt +3 -0
  7. checkpoint-1956/rng_state.pth +3 -0
  8. checkpoint-1956/scheduler.pt +3 -0
  9. checkpoint-1956/special_tokens_map.json +23 -0
  10. checkpoint-1956/spiece.model +3 -0
  11. checkpoint-1956/tokenizer.json +3 -0
  12. checkpoint-1956/tokenizer_config.json +839 -0
  13. checkpoint-1956/trainer_state.json +458 -0
  14. checkpoint-1956/training_args.bin +3 -0
  15. config.json +33 -0
  16. generation_config.json +7 -0
  17. model.safetensors +3 -0
  18. special_tokens_map.json +23 -0
  19. spiece.model +3 -0
  20. tokenizer.json +3 -0
  21. tokenizer_config.json +839 -0
  22. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-1956/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/mt5-large
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - mtc/span_absinth_with_articles_german_faithfulness_detection_dataset
8
+ model-index:
9
+ - name: google-mt5-large_MAX-CONTEXT-LEN-1024_MAX-GEN-LEN-256_span_absinth_faithfulness_multi_label_classification_bounded-quetzal-2024-07-15
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/background-tool/span_absinth_evaluation/runs/0mq2kpk8)
17
+ # google-mt5-large_MAX-CONTEXT-LEN-1024_MAX-GEN-LEN-256_span_absinth_faithfulness_multi_label_classification_bounded-quetzal-2024-07-15
18
+
19
+ This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on the mtc/span_absinth_with_articles_german_faithfulness_detection_dataset dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1459
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:----:|:---------------:|
52
+ | 5.7665 | 0.1534 | 100 | 2.7347 |
53
+ | 2.3656 | 0.3067 | 200 | 1.6610 |
54
+ | 1.1422 | 0.4601 | 300 | 0.5634 |
55
+ | 0.4894 | 0.6135 | 400 | 0.2760 |
56
+ | 0.3222 | 0.7669 | 500 | 0.2368 |
57
+ | 0.3563 | 0.9202 | 600 | 0.1922 |
58
+ | 0.2274 | 1.0736 | 700 | 0.1777 |
59
+ | 0.1465 | 1.2270 | 800 | 0.1763 |
60
+ | 0.1499 | 1.3804 | 900 | 0.1732 |
61
+ | 0.1379 | 1.5337 | 1000 | 0.1737 |
62
+ | 0.1311 | 1.6871 | 1100 | 0.1615 |
63
+ | 0.1535 | 1.8405 | 1200 | 0.1606 |
64
+ | 0.1303 | 1.9939 | 1300 | 0.1637 |
65
+ | 0.0981 | 2.1472 | 1400 | 0.1542 |
66
+ | 0.1385 | 2.3006 | 1500 | 0.1311 |
67
+ | 0.124 | 2.4540 | 1600 | 0.1427 |
68
+ | 0.1071 | 2.6074 | 1700 | 0.1430 |
69
+ | 0.1127 | 2.7607 | 1800 | 0.1476 |
70
+ | 0.1006 | 2.9141 | 1900 | 0.1459 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.42.2
76
+ - Pytorch 2.3.0+cu121
77
+ - Datasets 2.20.0
78
+ - Tokenizers 0.19.1
checkpoint-1956/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-large",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2816,
8
+ "d_kv": 64,
9
+ "d_model": 1024,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
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
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.42.2",
31
+ "use_cache": true,
32
+ "vocab_size": 250112
33
+ }
checkpoint-1956/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.42.2"
7
+ }
checkpoint-1956/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f5571db62745f0aa6bfb859c91b6da26dadbbea30437ad50f467099897d6c3
3
+ size 4918393736
checkpoint-1956/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3833d89ad87ac440486f8207f04dd736de57d1631f8e393b6a11301795a92748
3
+ size 9837133152
checkpoint-1956/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b0472f23f494395431683a9c0a0721c05d14ba197d43ee282efda4097dacc8
3
+ size 14244
checkpoint-1956/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03fe29262ceb7b327d00f4d13dded4bf22d4c5609193108748ea73aab5788d40
3
+ size 1064
checkpoint-1956/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-1956/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
checkpoint-1956/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10de43dbd3bc8019429080567fad7ba8b57f9fd1f7e8347e6235a98f60dd57c8
3
+ size 16350028
checkpoint-1956/tokenizer_config.json ADDED
@@ -0,0 +1,839 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "250000": {
29
+ "content": "▁<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "250001": {
37
+ "content": "▁<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "250002": {
45
+ "content": "▁<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "250003": {
53
+ "content": "▁<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "250004": {
61
+ "content": "▁<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "250005": {
69
+ "content": "▁<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "250006": {
77
+ "content": "▁<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "250007": {
85
+ "content": "▁<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "250008": {
93
+ "content": "▁<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "250009": {
101
+ "content": "▁<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "250010": {
109
+ "content": "▁<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "250011": {
117
+ "content": "▁<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "250012": {
125
+ "content": "▁<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "250013": {
133
+ "content": "▁<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "250014": {
141
+ "content": "▁<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "250015": {
149
+ "content": "▁<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "250016": {
157
+ "content": "▁<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "250017": {
165
+ "content": "▁<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "250018": {
173
+ "content": "▁<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "250019": {
181
+ "content": "▁<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "250020": {
189
+ "content": "▁<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "250021": {
197
+ "content": "▁<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "250022": {
205
+ "content": "▁<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "250023": {
213
+ "content": "▁<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "250024": {
221
+ "content": "▁<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "250025": {
229
+ "content": "▁<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "250026": {
237
+ "content": "▁<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "250027": {
245
+ "content": "▁<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "250028": {
253
+ "content": "▁<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "250029": {
261
+ "content": "▁<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "250030": {
269
+ "content": "▁<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "250031": {
277
+ "content": "▁<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "250032": {
285
+ "content": "▁<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "250033": {
293
+ "content": "▁<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "250034": {
301
+ "content": "▁<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "250035": {
309
+ "content": "▁<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "250036": {
317
+ "content": "▁<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "250037": {
325
+ "content": "▁<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "250038": {
333
+ "content": "▁<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "250039": {
341
+ "content": "▁<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "250040": {
349
+ "content": "▁<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "250041": {
357
+ "content": "▁<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "250042": {
365
+ "content": "▁<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "250043": {
373
+ "content": "▁<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "250044": {
381
+ "content": "▁<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "250045": {
389
+ "content": "▁<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "250046": {
397
+ "content": "▁<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "250047": {
405
+ "content": "▁<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "250048": {
413
+ "content": "▁<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "250049": {
421
+ "content": "▁<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "250050": {
429
+ "content": "οΏ½οΏ½οΏ½<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "250051": {
437
+ "content": "▁<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "250052": {
445
+ "content": "▁<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "250053": {
453
+ "content": "▁<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "250054": {
461
+ "content": "▁<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "250055": {
469
+ "content": "▁<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "250056": {
477
+ "content": "▁<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "250057": {
485
+ "content": "▁<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "250058": {
493
+ "content": "▁<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "250059": {
501
+ "content": "▁<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "250060": {
509
+ "content": "▁<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ },
516
+ "250061": {
517
+ "content": "▁<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": false
523
+ },
524
+ "250062": {
525
+ "content": "▁<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": false
531
+ },
532
+ "250063": {
533
+ "content": "▁<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": false
539
+ },
540
+ "250064": {
541
+ "content": "▁<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": false
547
+ },
548
+ "250065": {
549
+ "content": "▁<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": false
555
+ },
556
+ "250066": {
557
+ "content": "▁<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": false
563
+ },
564
+ "250067": {
565
+ "content": "▁<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": false
571
+ },
572
+ "250068": {
573
+ "content": "▁<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": false
579
+ },
580
+ "250069": {
581
+ "content": "▁<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": false
587
+ },
588
+ "250070": {
589
+ "content": "▁<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": false
595
+ },
596
+ "250071": {
597
+ "content": "▁<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": false
603
+ },
604
+ "250072": {
605
+ "content": "▁<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": false
611
+ },
612
+ "250073": {
613
+ "content": "▁<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": false
619
+ },
620
+ "250074": {
621
+ "content": "▁<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": false
627
+ },
628
+ "250075": {
629
+ "content": "▁<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": false
635
+ },
636
+ "250076": {
637
+ "content": "▁<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": false
643
+ },
644
+ "250077": {
645
+ "content": "▁<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": false
651
+ },
652
+ "250078": {
653
+ "content": "▁<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": false
659
+ },
660
+ "250079": {
661
+ "content": "▁<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": false
667
+ },
668
+ "250080": {
669
+ "content": "▁<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": false
675
+ },
676
+ "250081": {
677
+ "content": "▁<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": false
683
+ },
684
+ "250082": {
685
+ "content": "▁<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": false
691
+ },
692
+ "250083": {
693
+ "content": "▁<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": false
699
+ },
700
+ "250084": {
701
+ "content": "▁<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": false
707
+ },
708
+ "250085": {
709
+ "content": "▁<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": false
715
+ },
716
+ "250086": {
717
+ "content": "▁<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": false
723
+ },
724
+ "250087": {
725
+ "content": "▁<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": false
731
+ },
732
+ "250088": {
733
+ "content": "▁<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": false
739
+ },
740
+ "250089": {
741
+ "content": "▁<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": false
747
+ },
748
+ "250090": {
749
+ "content": "▁<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": false
755
+ },
756
+ "250091": {
757
+ "content": "▁<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": false
763
+ },
764
+ "250092": {
765
+ "content": "▁<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": false
771
+ },
772
+ "250093": {
773
+ "content": "▁<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": false
779
+ },
780
+ "250094": {
781
+ "content": "▁<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": false
787
+ },
788
+ "250095": {
789
+ "content": "▁<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": false
795
+ },
796
+ "250096": {
797
+ "content": "▁<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": false
803
+ },
804
+ "250097": {
805
+ "content": "▁<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": false
811
+ },
812
+ "250098": {
813
+ "content": "▁<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": false
819
+ },
820
+ "250099": {
821
+ "content": "▁<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": false
827
+ }
828
+ },
829
+ "additional_special_tokens": [],
830
+ "clean_up_tokenization_spaces": true,
831
+ "eos_token": "</s>",
832
+ "extra_ids": 0,
833
+ "legacy": true,
834
+ "model_max_length": 1024,
835
+ "pad_token": "<pad>",
836
+ "sp_model_kwargs": {},
837
+ "tokenizer_class": "T5Tokenizer",
838
+ "unk_token": "<unk>"
839
+ }
checkpoint-1956/trainer_state.json ADDED
@@ -0,0 +1,458 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 100,
6
+ "global_step": 1956,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07668711656441718,
13
+ "grad_norm": 39.43513107299805,
14
+ "learning_rate": 1.948875255623722e-05,
15
+ "loss": 10.9362,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.15337423312883436,
20
+ "grad_norm": 137.76531982421875,
21
+ "learning_rate": 1.8977505112474438e-05,
22
+ "loss": 5.7665,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.15337423312883436,
27
+ "eval_loss": 2.734666347503662,
28
+ "eval_runtime": 10.0858,
29
+ "eval_samples_per_second": 19.83,
30
+ "eval_steps_per_second": 4.957,
31
+ "step": 100
32
+ },
33
+ {
34
+ "epoch": 0.23006134969325154,
35
+ "grad_norm": 29.48383903503418,
36
+ "learning_rate": 1.8466257668711657e-05,
37
+ "loss": 3.0734,
38
+ "step": 150
39
+ },
40
+ {
41
+ "epoch": 0.3067484662576687,
42
+ "grad_norm": 10.881046295166016,
43
+ "learning_rate": 1.795501022494888e-05,
44
+ "loss": 2.3656,
45
+ "step": 200
46
+ },
47
+ {
48
+ "epoch": 0.3067484662576687,
49
+ "eval_loss": 1.6610013246536255,
50
+ "eval_runtime": 10.2143,
51
+ "eval_samples_per_second": 19.58,
52
+ "eval_steps_per_second": 4.895,
53
+ "step": 200
54
+ },
55
+ {
56
+ "epoch": 0.3834355828220859,
57
+ "grad_norm": 6.44171667098999,
58
+ "learning_rate": 1.7443762781186097e-05,
59
+ "loss": 1.5441,
60
+ "step": 250
61
+ },
62
+ {
63
+ "epoch": 0.4601226993865031,
64
+ "grad_norm": 6.2512431144714355,
65
+ "learning_rate": 1.6932515337423315e-05,
66
+ "loss": 1.1422,
67
+ "step": 300
68
+ },
69
+ {
70
+ "epoch": 0.4601226993865031,
71
+ "eval_loss": 0.5633783340454102,
72
+ "eval_runtime": 10.2837,
73
+ "eval_samples_per_second": 19.448,
74
+ "eval_steps_per_second": 4.862,
75
+ "step": 300
76
+ },
77
+ {
78
+ "epoch": 0.5368098159509203,
79
+ "grad_norm": 15.193826675415039,
80
+ "learning_rate": 1.6421267893660533e-05,
81
+ "loss": 0.6255,
82
+ "step": 350
83
+ },
84
+ {
85
+ "epoch": 0.6134969325153374,
86
+ "grad_norm": 8.66766357421875,
87
+ "learning_rate": 1.591002044989775e-05,
88
+ "loss": 0.4894,
89
+ "step": 400
90
+ },
91
+ {
92
+ "epoch": 0.6134969325153374,
93
+ "eval_loss": 0.2759694755077362,
94
+ "eval_runtime": 10.3266,
95
+ "eval_samples_per_second": 19.367,
96
+ "eval_steps_per_second": 4.842,
97
+ "step": 400
98
+ },
99
+ {
100
+ "epoch": 0.6901840490797546,
101
+ "grad_norm": 20.774620056152344,
102
+ "learning_rate": 1.539877300613497e-05,
103
+ "loss": 0.3649,
104
+ "step": 450
105
+ },
106
+ {
107
+ "epoch": 0.7668711656441718,
108
+ "grad_norm": 3.2865004539489746,
109
+ "learning_rate": 1.488752556237219e-05,
110
+ "loss": 0.3222,
111
+ "step": 500
112
+ },
113
+ {
114
+ "epoch": 0.7668711656441718,
115
+ "eval_loss": 0.23675286769866943,
116
+ "eval_runtime": 10.3368,
117
+ "eval_samples_per_second": 19.348,
118
+ "eval_steps_per_second": 4.837,
119
+ "step": 500
120
+ },
121
+ {
122
+ "epoch": 0.843558282208589,
123
+ "grad_norm": 6.2586188316345215,
124
+ "learning_rate": 1.4376278118609408e-05,
125
+ "loss": 0.3736,
126
+ "step": 550
127
+ },
128
+ {
129
+ "epoch": 0.9202453987730062,
130
+ "grad_norm": 15.381063461303711,
131
+ "learning_rate": 1.3865030674846627e-05,
132
+ "loss": 0.3563,
133
+ "step": 600
134
+ },
135
+ {
136
+ "epoch": 0.9202453987730062,
137
+ "eval_loss": 0.19222033023834229,
138
+ "eval_runtime": 10.2909,
139
+ "eval_samples_per_second": 19.435,
140
+ "eval_steps_per_second": 4.859,
141
+ "step": 600
142
+ },
143
+ {
144
+ "epoch": 0.9969325153374233,
145
+ "grad_norm": 8.114583969116211,
146
+ "learning_rate": 1.3353783231083845e-05,
147
+ "loss": 0.2088,
148
+ "step": 650
149
+ },
150
+ {
151
+ "epoch": 1.0736196319018405,
152
+ "grad_norm": 6.549014091491699,
153
+ "learning_rate": 1.2842535787321065e-05,
154
+ "loss": 0.2274,
155
+ "step": 700
156
+ },
157
+ {
158
+ "epoch": 1.0736196319018405,
159
+ "eval_loss": 0.17766746878623962,
160
+ "eval_runtime": 10.378,
161
+ "eval_samples_per_second": 19.271,
162
+ "eval_steps_per_second": 4.818,
163
+ "step": 700
164
+ },
165
+ {
166
+ "epoch": 1.1503067484662577,
167
+ "grad_norm": 11.181276321411133,
168
+ "learning_rate": 1.2331288343558283e-05,
169
+ "loss": 0.1874,
170
+ "step": 750
171
+ },
172
+ {
173
+ "epoch": 1.2269938650306749,
174
+ "grad_norm": 8.387093544006348,
175
+ "learning_rate": 1.1820040899795502e-05,
176
+ "loss": 0.1465,
177
+ "step": 800
178
+ },
179
+ {
180
+ "epoch": 1.2269938650306749,
181
+ "eval_loss": 0.1763072907924652,
182
+ "eval_runtime": 10.3846,
183
+ "eval_samples_per_second": 19.259,
184
+ "eval_steps_per_second": 4.815,
185
+ "step": 800
186
+ },
187
+ {
188
+ "epoch": 1.303680981595092,
189
+ "grad_norm": 2.6142139434814453,
190
+ "learning_rate": 1.130879345603272e-05,
191
+ "loss": 0.1416,
192
+ "step": 850
193
+ },
194
+ {
195
+ "epoch": 1.3803680981595092,
196
+ "grad_norm": 1.997550368309021,
197
+ "learning_rate": 1.079754601226994e-05,
198
+ "loss": 0.1499,
199
+ "step": 900
200
+ },
201
+ {
202
+ "epoch": 1.3803680981595092,
203
+ "eval_loss": 0.17320242524147034,
204
+ "eval_runtime": 10.3809,
205
+ "eval_samples_per_second": 19.266,
206
+ "eval_steps_per_second": 4.817,
207
+ "step": 900
208
+ },
209
+ {
210
+ "epoch": 1.4570552147239264,
211
+ "grad_norm": 0.2688699960708618,
212
+ "learning_rate": 1.0286298568507158e-05,
213
+ "loss": 0.1297,
214
+ "step": 950
215
+ },
216
+ {
217
+ "epoch": 1.5337423312883436,
218
+ "grad_norm": 0.8804627656936646,
219
+ "learning_rate": 9.775051124744377e-06,
220
+ "loss": 0.1379,
221
+ "step": 1000
222
+ },
223
+ {
224
+ "epoch": 1.5337423312883436,
225
+ "eval_loss": 0.17370212078094482,
226
+ "eval_runtime": 10.4224,
227
+ "eval_samples_per_second": 19.189,
228
+ "eval_steps_per_second": 4.797,
229
+ "step": 1000
230
+ },
231
+ {
232
+ "epoch": 1.6104294478527608,
233
+ "grad_norm": 8.888616561889648,
234
+ "learning_rate": 9.263803680981595e-06,
235
+ "loss": 0.1887,
236
+ "step": 1050
237
+ },
238
+ {
239
+ "epoch": 1.687116564417178,
240
+ "grad_norm": 9.447290420532227,
241
+ "learning_rate": 8.752556237218815e-06,
242
+ "loss": 0.1311,
243
+ "step": 1100
244
+ },
245
+ {
246
+ "epoch": 1.687116564417178,
247
+ "eval_loss": 0.16146855056285858,
248
+ "eval_runtime": 10.3797,
249
+ "eval_samples_per_second": 19.268,
250
+ "eval_steps_per_second": 4.817,
251
+ "step": 1100
252
+ },
253
+ {
254
+ "epoch": 1.7638036809815951,
255
+ "grad_norm": 0.26230740547180176,
256
+ "learning_rate": 8.241308793456033e-06,
257
+ "loss": 0.1068,
258
+ "step": 1150
259
+ },
260
+ {
261
+ "epoch": 1.8404907975460123,
262
+ "grad_norm": 4.092576503753662,
263
+ "learning_rate": 7.730061349693252e-06,
264
+ "loss": 0.1535,
265
+ "step": 1200
266
+ },
267
+ {
268
+ "epoch": 1.8404907975460123,
269
+ "eval_loss": 0.16064655780792236,
270
+ "eval_runtime": 10.3826,
271
+ "eval_samples_per_second": 19.263,
272
+ "eval_steps_per_second": 4.816,
273
+ "step": 1200
274
+ },
275
+ {
276
+ "epoch": 1.9171779141104295,
277
+ "grad_norm": 6.193262100219727,
278
+ "learning_rate": 7.218813905930471e-06,
279
+ "loss": 0.1168,
280
+ "step": 1250
281
+ },
282
+ {
283
+ "epoch": 1.9938650306748467,
284
+ "grad_norm": 0.05743325129151344,
285
+ "learning_rate": 6.707566462167689e-06,
286
+ "loss": 0.1303,
287
+ "step": 1300
288
+ },
289
+ {
290
+ "epoch": 1.9938650306748467,
291
+ "eval_loss": 0.1636618822813034,
292
+ "eval_runtime": 10.4022,
293
+ "eval_samples_per_second": 19.227,
294
+ "eval_steps_per_second": 4.807,
295
+ "step": 1300
296
+ },
297
+ {
298
+ "epoch": 2.0705521472392636,
299
+ "grad_norm": 4.37569522857666,
300
+ "learning_rate": 6.1963190184049085e-06,
301
+ "loss": 0.102,
302
+ "step": 1350
303
+ },
304
+ {
305
+ "epoch": 2.147239263803681,
306
+ "grad_norm": 6.298128128051758,
307
+ "learning_rate": 5.685071574642127e-06,
308
+ "loss": 0.0981,
309
+ "step": 1400
310
+ },
311
+ {
312
+ "epoch": 2.147239263803681,
313
+ "eval_loss": 0.15416213870048523,
314
+ "eval_runtime": 10.3803,
315
+ "eval_samples_per_second": 19.267,
316
+ "eval_steps_per_second": 4.817,
317
+ "step": 1400
318
+ },
319
+ {
320
+ "epoch": 2.223926380368098,
321
+ "grad_norm": 2.748354434967041,
322
+ "learning_rate": 5.173824130879346e-06,
323
+ "loss": 0.1061,
324
+ "step": 1450
325
+ },
326
+ {
327
+ "epoch": 2.3006134969325154,
328
+ "grad_norm": 4.336332321166992,
329
+ "learning_rate": 4.662576687116564e-06,
330
+ "loss": 0.1385,
331
+ "step": 1500
332
+ },
333
+ {
334
+ "epoch": 2.3006134969325154,
335
+ "eval_loss": 0.1310512125492096,
336
+ "eval_runtime": 10.3935,
337
+ "eval_samples_per_second": 19.243,
338
+ "eval_steps_per_second": 4.811,
339
+ "step": 1500
340
+ },
341
+ {
342
+ "epoch": 2.3773006134969323,
343
+ "grad_norm": 0.19903312623500824,
344
+ "learning_rate": 4.1513292433537835e-06,
345
+ "loss": 0.0877,
346
+ "step": 1550
347
+ },
348
+ {
349
+ "epoch": 2.4539877300613497,
350
+ "grad_norm": 1.4374008178710938,
351
+ "learning_rate": 3.6400817995910027e-06,
352
+ "loss": 0.124,
353
+ "step": 1600
354
+ },
355
+ {
356
+ "epoch": 2.4539877300613497,
357
+ "eval_loss": 0.14273065328598022,
358
+ "eval_runtime": 10.3898,
359
+ "eval_samples_per_second": 19.25,
360
+ "eval_steps_per_second": 4.812,
361
+ "step": 1600
362
+ },
363
+ {
364
+ "epoch": 2.530674846625767,
365
+ "grad_norm": 1.1356003284454346,
366
+ "learning_rate": 3.1288343558282214e-06,
367
+ "loss": 0.1099,
368
+ "step": 1650
369
+ },
370
+ {
371
+ "epoch": 2.607361963190184,
372
+ "grad_norm": 9.728405952453613,
373
+ "learning_rate": 2.61758691206544e-06,
374
+ "loss": 0.1071,
375
+ "step": 1700
376
+ },
377
+ {
378
+ "epoch": 2.607361963190184,
379
+ "eval_loss": 0.1429738849401474,
380
+ "eval_runtime": 10.4053,
381
+ "eval_samples_per_second": 19.221,
382
+ "eval_steps_per_second": 4.805,
383
+ "step": 1700
384
+ },
385
+ {
386
+ "epoch": 2.684049079754601,
387
+ "grad_norm": 0.05977565422654152,
388
+ "learning_rate": 2.1063394683026585e-06,
389
+ "loss": 0.0886,
390
+ "step": 1750
391
+ },
392
+ {
393
+ "epoch": 2.7607361963190185,
394
+ "grad_norm": 9.054681777954102,
395
+ "learning_rate": 1.5950920245398775e-06,
396
+ "loss": 0.1127,
397
+ "step": 1800
398
+ },
399
+ {
400
+ "epoch": 2.7607361963190185,
401
+ "eval_loss": 0.14762383699417114,
402
+ "eval_runtime": 10.3815,
403
+ "eval_samples_per_second": 19.265,
404
+ "eval_steps_per_second": 4.816,
405
+ "step": 1800
406
+ },
407
+ {
408
+ "epoch": 2.837423312883436,
409
+ "grad_norm": 4.280158996582031,
410
+ "learning_rate": 1.0838445807770962e-06,
411
+ "loss": 0.0958,
412
+ "step": 1850
413
+ },
414
+ {
415
+ "epoch": 2.914110429447853,
416
+ "grad_norm": 5.161213397979736,
417
+ "learning_rate": 5.72597137014315e-07,
418
+ "loss": 0.1006,
419
+ "step": 1900
420
+ },
421
+ {
422
+ "epoch": 2.914110429447853,
423
+ "eval_loss": 0.1459266096353531,
424
+ "eval_runtime": 10.3552,
425
+ "eval_samples_per_second": 19.314,
426
+ "eval_steps_per_second": 4.828,
427
+ "step": 1900
428
+ },
429
+ {
430
+ "epoch": 2.9907975460122698,
431
+ "grad_norm": 0.12986499071121216,
432
+ "learning_rate": 6.134969325153375e-08,
433
+ "loss": 0.126,
434
+ "step": 1950
435
+ }
436
+ ],
437
+ "logging_steps": 50,
438
+ "max_steps": 1956,
439
+ "num_input_tokens_seen": 0,
440
+ "num_train_epochs": 3,
441
+ "save_steps": -1956,
442
+ "stateful_callbacks": {
443
+ "TrainerControl": {
444
+ "args": {
445
+ "should_epoch_stop": false,
446
+ "should_evaluate": false,
447
+ "should_log": false,
448
+ "should_save": true,
449
+ "should_training_stop": true
450
+ },
451
+ "attributes": {}
452
+ }
453
+ },
454
+ "total_flos": 4.0587908358144e+16,
455
+ "train_batch_size": 4,
456
+ "trial_name": null,
457
+ "trial_params": null
458
+ }
checkpoint-1956/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d682c3b991f38a157d2f84de3d233022ea9eb195865dcb00007b89ebcd6066
3
+ size 5688
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-large",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2816,
8
+ "d_kv": 64,
9
+ "d_model": 1024,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
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
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.42.2",
31
+ "use_cache": true,
32
+ "vocab_size": 250112
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.42.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f5571db62745f0aa6bfb859c91b6da26dadbbea30437ad50f467099897d6c3
3
+ size 4918393736
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10de43dbd3bc8019429080567fad7ba8b57f9fd1f7e8347e6235a98f60dd57c8
3
+ size 16350028
tokenizer_config.json ADDED
@@ -0,0 +1,839 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "250000": {
29
+ "content": "▁<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "250001": {
37
+ "content": "▁<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "250002": {
45
+ "content": "▁<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "250003": {
53
+ "content": "▁<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "250004": {
61
+ "content": "▁<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "250005": {
69
+ "content": "▁<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "250006": {
77
+ "content": "▁<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "250007": {
85
+ "content": "▁<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "250008": {
93
+ "content": "▁<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "250009": {
101
+ "content": "▁<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "250010": {
109
+ "content": "▁<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "250011": {
117
+ "content": "▁<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "250012": {
125
+ "content": "▁<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "250013": {
133
+ "content": "▁<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "250014": {
141
+ "content": "▁<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "250015": {
149
+ "content": "▁<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "250016": {
157
+ "content": "▁<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "250017": {
165
+ "content": "▁<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "250018": {
173
+ "content": "▁<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "250019": {
181
+ "content": "▁<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "250020": {
189
+ "content": "▁<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "250021": {
197
+ "content": "▁<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "250022": {
205
+ "content": "▁<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "250023": {
213
+ "content": "▁<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "250024": {
221
+ "content": "▁<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "250025": {
229
+ "content": "▁<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "250026": {
237
+ "content": "▁<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "250027": {
245
+ "content": "▁<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "250028": {
253
+ "content": "▁<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "250029": {
261
+ "content": "▁<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "250030": {
269
+ "content": "▁<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "250031": {
277
+ "content": "▁<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "250032": {
285
+ "content": "▁<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "250033": {
293
+ "content": "▁<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "250034": {
301
+ "content": "▁<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "250035": {
309
+ "content": "▁<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "250036": {
317
+ "content": "▁<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "250037": {
325
+ "content": "▁<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "250038": {
333
+ "content": "▁<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "250039": {
341
+ "content": "▁<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "250040": {
349
+ "content": "▁<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "250041": {
357
+ "content": "▁<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "250042": {
365
+ "content": "▁<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "250043": {
373
+ "content": "▁<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "250044": {
381
+ "content": "▁<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "250045": {
389
+ "content": "▁<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "250046": {
397
+ "content": "▁<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "250047": {
405
+ "content": "▁<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "250048": {
413
+ "content": "▁<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "250049": {
421
+ "content": "▁<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "250050": {
429
+ "content": "οΏ½οΏ½οΏ½<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "250051": {
437
+ "content": "▁<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "250052": {
445
+ "content": "▁<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "250053": {
453
+ "content": "▁<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "250054": {
461
+ "content": "▁<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "250055": {
469
+ "content": "▁<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "250056": {
477
+ "content": "▁<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "250057": {
485
+ "content": "▁<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "250058": {
493
+ "content": "▁<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "250059": {
501
+ "content": "▁<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "250060": {
509
+ "content": "▁<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ },
516
+ "250061": {
517
+ "content": "▁<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": false
523
+ },
524
+ "250062": {
525
+ "content": "▁<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": false
531
+ },
532
+ "250063": {
533
+ "content": "▁<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": false
539
+ },
540
+ "250064": {
541
+ "content": "▁<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": false
547
+ },
548
+ "250065": {
549
+ "content": "▁<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": false
555
+ },
556
+ "250066": {
557
+ "content": "▁<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": false
563
+ },
564
+ "250067": {
565
+ "content": "▁<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": false
571
+ },
572
+ "250068": {
573
+ "content": "▁<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": false
579
+ },
580
+ "250069": {
581
+ "content": "▁<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": false
587
+ },
588
+ "250070": {
589
+ "content": "▁<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": false
595
+ },
596
+ "250071": {
597
+ "content": "▁<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": false
603
+ },
604
+ "250072": {
605
+ "content": "▁<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": false
611
+ },
612
+ "250073": {
613
+ "content": "▁<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": false
619
+ },
620
+ "250074": {
621
+ "content": "▁<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": false
627
+ },
628
+ "250075": {
629
+ "content": "▁<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": false
635
+ },
636
+ "250076": {
637
+ "content": "▁<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": false
643
+ },
644
+ "250077": {
645
+ "content": "▁<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": false
651
+ },
652
+ "250078": {
653
+ "content": "▁<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": false
659
+ },
660
+ "250079": {
661
+ "content": "▁<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": false
667
+ },
668
+ "250080": {
669
+ "content": "▁<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": false
675
+ },
676
+ "250081": {
677
+ "content": "▁<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": false
683
+ },
684
+ "250082": {
685
+ "content": "▁<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": false
691
+ },
692
+ "250083": {
693
+ "content": "▁<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": false
699
+ },
700
+ "250084": {
701
+ "content": "▁<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": false
707
+ },
708
+ "250085": {
709
+ "content": "▁<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": false
715
+ },
716
+ "250086": {
717
+ "content": "▁<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": false
723
+ },
724
+ "250087": {
725
+ "content": "▁<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": false
731
+ },
732
+ "250088": {
733
+ "content": "▁<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": false
739
+ },
740
+ "250089": {
741
+ "content": "▁<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": false
747
+ },
748
+ "250090": {
749
+ "content": "▁<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": false
755
+ },
756
+ "250091": {
757
+ "content": "▁<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": false
763
+ },
764
+ "250092": {
765
+ "content": "▁<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": false
771
+ },
772
+ "250093": {
773
+ "content": "▁<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": false
779
+ },
780
+ "250094": {
781
+ "content": "▁<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": false
787
+ },
788
+ "250095": {
789
+ "content": "▁<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": false
795
+ },
796
+ "250096": {
797
+ "content": "▁<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": false
803
+ },
804
+ "250097": {
805
+ "content": "▁<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": false
811
+ },
812
+ "250098": {
813
+ "content": "▁<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": false
819
+ },
820
+ "250099": {
821
+ "content": "▁<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": false
827
+ }
828
+ },
829
+ "additional_special_tokens": [],
830
+ "clean_up_tokenization_spaces": true,
831
+ "eos_token": "</s>",
832
+ "extra_ids": 0,
833
+ "legacy": true,
834
+ "model_max_length": 1024,
835
+ "pad_token": "<pad>",
836
+ "sp_model_kwargs": {},
837
+ "tokenizer_class": "T5Tokenizer",
838
+ "unk_token": "<unk>"
839
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d682c3b991f38a157d2f84de3d233022ea9eb195865dcb00007b89ebcd6066
3
+ size 5688