snizio commited on
Commit
b3445ba
·
verified ·
1 Parent(s): 7de7f2f

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gsarti/it5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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
+ "gradient_checkpointing": false,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 8,
22
+ "num_heads": 6,
23
+ "num_layers": 8,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.2",
31
+ "use_cache": true,
32
+ "vocab_size": 32103
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.40.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64ce058555f5528f17fbda729e7a604ab40a092f4499c4ae933892308a86e61
3
+ size 307764648
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d9679c0f975b8079dfce4ffcc741ee713c03e9601b2c8197a553d271a4046b
3
+ size 1135610
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ea444c03a579298404d945d8e7dc9219d4a67e92e64ef3e496f911edb47c23
3
+ size 14512
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1f6eb6de093d51308bb94aee1c3766ef244f63879f3699941c1224289f975f
3
+ size 14512
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36a352173d02a93102f6909db23199e71aaf1bbefc02e47331fa51328bc2e62
3
+ size 1000
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,937 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32003": {
28
+ "content": "<extra_id_0>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32004": {
36
+ "content": "<extra_id_1>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32005": {
44
+ "content": "<extra_id_2>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32006": {
52
+ "content": "<extra_id_3>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32007": {
60
+ "content": "<extra_id_4>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32008": {
68
+ "content": "<extra_id_5>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32009": {
76
+ "content": "<extra_id_6>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32010": {
84
+ "content": "<extra_id_7>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32011": {
92
+ "content": "<extra_id_8>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32012": {
100
+ "content": "<extra_id_9>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32013": {
108
+ "content": "<extra_id_10>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32014": {
116
+ "content": "<extra_id_11>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32015": {
124
+ "content": "<extra_id_12>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32016": {
132
+ "content": "<extra_id_13>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32017": {
140
+ "content": "<extra_id_14>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32018": {
148
+ "content": "<extra_id_15>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32019": {
156
+ "content": "<extra_id_16>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "32020": {
164
+ "content": "<extra_id_17>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "32021": {
172
+ "content": "<extra_id_18>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "32022": {
180
+ "content": "<extra_id_19>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "32023": {
188
+ "content": "<extra_id_20>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "32024": {
196
+ "content": "<extra_id_21>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "32025": {
204
+ "content": "<extra_id_22>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "32026": {
212
+ "content": "<extra_id_23>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "32027": {
220
+ "content": "<extra_id_24>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "32028": {
228
+ "content": "<extra_id_25>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "32029": {
236
+ "content": "<extra_id_26>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32030": {
244
+ "content": "<extra_id_27>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "32031": {
252
+ "content": "<extra_id_28>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32032": {
260
+ "content": "<extra_id_29>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "32033": {
268
+ "content": "<extra_id_30>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "32034": {
276
+ "content": "<extra_id_31>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "32035": {
284
+ "content": "<extra_id_32>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "32036": {
292
+ "content": "<extra_id_33>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "32037": {
300
+ "content": "<extra_id_34>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "32038": {
308
+ "content": "<extra_id_35>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "32039": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "32040": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "32041": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "32042": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "32043": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "32044": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "32045": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "32046": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "32047": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "32048": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "32049": {
396
+ "content": "<extra_id_46>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "32050": {
404
+ "content": "<extra_id_47>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "32051": {
412
+ "content": "<extra_id_48>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "32052": {
420
+ "content": "<extra_id_49>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "32053": {
428
+ "content": "<extra_id_50>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "32054": {
436
+ "content": "<extra_id_51>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "32055": {
444
+ "content": "<extra_id_52>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "32056": {
452
+ "content": "<extra_id_53>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "32057": {
460
+ "content": "<extra_id_54>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "32058": {
468
+ "content": "<extra_id_55>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "32059": {
476
+ "content": "<extra_id_56>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "32060": {
484
+ "content": "<extra_id_57>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "32061": {
492
+ "content": "<extra_id_58>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "32062": {
500
+ "content": "<extra_id_59>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "32063": {
508
+ "content": "<extra_id_60>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "32064": {
516
+ "content": "<extra_id_61>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "32065": {
524
+ "content": "<extra_id_62>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "32066": {
532
+ "content": "<extra_id_63>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "32067": {
540
+ "content": "<extra_id_64>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "32068": {
548
+ "content": "<extra_id_65>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "32069": {
556
+ "content": "<extra_id_66>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "32070": {
564
+ "content": "<extra_id_67>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "32071": {
572
+ "content": "<extra_id_68>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "32072": {
580
+ "content": "<extra_id_69>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "32073": {
588
+ "content": "<extra_id_70>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "32074": {
596
+ "content": "<extra_id_71>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "32075": {
604
+ "content": "<extra_id_72>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "32076": {
612
+ "content": "<extra_id_73>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "32077": {
620
+ "content": "<extra_id_74>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "32078": {
628
+ "content": "<extra_id_75>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "32079": {
636
+ "content": "<extra_id_76>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "32080": {
644
+ "content": "<extra_id_77>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "32081": {
652
+ "content": "<extra_id_78>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "32082": {
660
+ "content": "<extra_id_79>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "32083": {
668
+ "content": "<extra_id_80>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "32084": {
676
+ "content": "<extra_id_81>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "32085": {
684
+ "content": "<extra_id_82>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "32086": {
692
+ "content": "<extra_id_83>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "32087": {
700
+ "content": "<extra_id_84>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "32088": {
708
+ "content": "<extra_id_85>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "32089": {
716
+ "content": "<extra_id_86>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "32090": {
724
+ "content": "<extra_id_87>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "32091": {
732
+ "content": "<extra_id_88>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "32092": {
740
+ "content": "<extra_id_89>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "32093": {
748
+ "content": "<extra_id_90>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "32094": {
756
+ "content": "<extra_id_91>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "32095": {
764
+ "content": "<extra_id_92>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "32096": {
772
+ "content": "<extra_id_93>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "32097": {
780
+ "content": "<extra_id_94>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "32098": {
788
+ "content": "<extra_id_95>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "32099": {
796
+ "content": "<extra_id_96>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "32100": {
804
+ "content": "<extra_id_97>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "32101": {
812
+ "content": "<extra_id_98>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "32102": {
820
+ "content": "<extra_id_99>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ }
827
+ },
828
+ "additional_special_tokens": [
829
+ "<extra_id_0>",
830
+ "<extra_id_1>",
831
+ "<extra_id_2>",
832
+ "<extra_id_3>",
833
+ "<extra_id_4>",
834
+ "<extra_id_5>",
835
+ "<extra_id_6>",
836
+ "<extra_id_7>",
837
+ "<extra_id_8>",
838
+ "<extra_id_9>",
839
+ "<extra_id_10>",
840
+ "<extra_id_11>",
841
+ "<extra_id_12>",
842
+ "<extra_id_13>",
843
+ "<extra_id_14>",
844
+ "<extra_id_15>",
845
+ "<extra_id_16>",
846
+ "<extra_id_17>",
847
+ "<extra_id_18>",
848
+ "<extra_id_19>",
849
+ "<extra_id_20>",
850
+ "<extra_id_21>",
851
+ "<extra_id_22>",
852
+ "<extra_id_23>",
853
+ "<extra_id_24>",
854
+ "<extra_id_25>",
855
+ "<extra_id_26>",
856
+ "<extra_id_27>",
857
+ "<extra_id_28>",
858
+ "<extra_id_29>",
859
+ "<extra_id_30>",
860
+ "<extra_id_31>",
861
+ "<extra_id_32>",
862
+ "<extra_id_33>",
863
+ "<extra_id_34>",
864
+ "<extra_id_35>",
865
+ "<extra_id_36>",
866
+ "<extra_id_37>",
867
+ "<extra_id_38>",
868
+ "<extra_id_39>",
869
+ "<extra_id_40>",
870
+ "<extra_id_41>",
871
+ "<extra_id_42>",
872
+ "<extra_id_43>",
873
+ "<extra_id_44>",
874
+ "<extra_id_45>",
875
+ "<extra_id_46>",
876
+ "<extra_id_47>",
877
+ "<extra_id_48>",
878
+ "<extra_id_49>",
879
+ "<extra_id_50>",
880
+ "<extra_id_51>",
881
+ "<extra_id_52>",
882
+ "<extra_id_53>",
883
+ "<extra_id_54>",
884
+ "<extra_id_55>",
885
+ "<extra_id_56>",
886
+ "<extra_id_57>",
887
+ "<extra_id_58>",
888
+ "<extra_id_59>",
889
+ "<extra_id_60>",
890
+ "<extra_id_61>",
891
+ "<extra_id_62>",
892
+ "<extra_id_63>",
893
+ "<extra_id_64>",
894
+ "<extra_id_65>",
895
+ "<extra_id_66>",
896
+ "<extra_id_67>",
897
+ "<extra_id_68>",
898
+ "<extra_id_69>",
899
+ "<extra_id_70>",
900
+ "<extra_id_71>",
901
+ "<extra_id_72>",
902
+ "<extra_id_73>",
903
+ "<extra_id_74>",
904
+ "<extra_id_75>",
905
+ "<extra_id_76>",
906
+ "<extra_id_77>",
907
+ "<extra_id_78>",
908
+ "<extra_id_79>",
909
+ "<extra_id_80>",
910
+ "<extra_id_81>",
911
+ "<extra_id_82>",
912
+ "<extra_id_83>",
913
+ "<extra_id_84>",
914
+ "<extra_id_85>",
915
+ "<extra_id_86>",
916
+ "<extra_id_87>",
917
+ "<extra_id_88>",
918
+ "<extra_id_89>",
919
+ "<extra_id_90>",
920
+ "<extra_id_91>",
921
+ "<extra_id_92>",
922
+ "<extra_id_93>",
923
+ "<extra_id_94>",
924
+ "<extra_id_95>",
925
+ "<extra_id_96>",
926
+ "<extra_id_97>",
927
+ "<extra_id_98>",
928
+ "<extra_id_99>"
929
+ ],
930
+ "clean_up_tokenization_spaces": true,
931
+ "eos_token": "</s>",
932
+ "extra_ids": 100,
933
+ "model_max_length": 1000000000000000019884624838656,
934
+ "pad_token": "<pad>",
935
+ "tokenizer_class": "T5Tokenizer",
936
+ "unk_token": "<unk>"
937
+ }
trainer_state.json ADDED
@@ -0,0 +1,1077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.4478375911712646,
3
+ "best_model_checkpoint": "checkpoints/it5-small/checkpoint-17663",
4
+ "epoch": 12.753068592057762,
5
+ "eval_steps": 1039,
6
+ "global_step": 17663,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14945848375451262,
13
+ "eval_g2l_cer": 293.7627,
14
+ "eval_g2l_gen_len": 13.9075,
15
+ "eval_g2l_rouge1": 17.4489,
16
+ "eval_g2l_rouge2": 8.198,
17
+ "eval_g2l_rougeL": 17.2001,
18
+ "eval_g2l_rougeLsum": 17.1915,
19
+ "eval_l2ex_cer": 136.8329,
20
+ "eval_l2ex_gen_len": 54.1737,
21
+ "eval_l2ex_rouge1": 17.812,
22
+ "eval_l2ex_rouge2": 6.7548,
23
+ "eval_l2ex_rougeL": 16.7136,
24
+ "eval_l2ex_rougeLsum": 16.7013,
25
+ "eval_l2g_cer": 154.2791,
26
+ "eval_l2g_gen_len": 50.8855,
27
+ "eval_l2g_rouge1": 13.7399,
28
+ "eval_l2g_rouge2": 4.278,
29
+ "eval_l2g_rougeL": 13.0474,
30
+ "eval_l2g_rougeLsum": 13.0446,
31
+ "eval_loss": 4.6176557540893555,
32
+ "eval_runtime": 109.9862,
33
+ "eval_samples_per_second": 90.202,
34
+ "eval_steps_per_second": 0.709,
35
+ "step": 207
36
+ },
37
+ {
38
+ "epoch": 0.15018050541516245,
39
+ "grad_norm": 99.67880249023438,
40
+ "learning_rate": 0.0002003853564547206,
41
+ "loss": 5.9292,
42
+ "step": 208
43
+ },
44
+ {
45
+ "epoch": 0.3003610108303249,
46
+ "grad_norm": 195.41990661621094,
47
+ "learning_rate": 0.0004007707129094412,
48
+ "loss": 4.6698,
49
+ "step": 416
50
+ },
51
+ {
52
+ "epoch": 0.4505415162454874,
53
+ "grad_norm": 274.79534912109375,
54
+ "learning_rate": 0.0006011560693641619,
55
+ "loss": 4.515,
56
+ "step": 624
57
+ },
58
+ {
59
+ "epoch": 0.6007220216606498,
60
+ "grad_norm": 210.73873901367188,
61
+ "learning_rate": 0.0008015414258188824,
62
+ "loss": 4.4776,
63
+ "step": 832
64
+ },
65
+ {
66
+ "epoch": 0.7501805054151625,
67
+ "eval_g2l_cer": 61.7538,
68
+ "eval_g2l_gen_len": 3.2726,
69
+ "eval_g2l_rouge1": 27.6616,
70
+ "eval_g2l_rouge2": 19.0238,
71
+ "eval_g2l_rougeL": 27.5754,
72
+ "eval_g2l_rougeLsum": 27.5869,
73
+ "eval_l2ex_cer": 88.1951,
74
+ "eval_l2ex_gen_len": 16.4502,
75
+ "eval_l2ex_rouge1": 28.4409,
76
+ "eval_l2ex_rouge2": 14.714,
77
+ "eval_l2ex_rougeL": 26.3524,
78
+ "eval_l2ex_rougeLsum": 26.38,
79
+ "eval_l2g_cer": 81.2622,
80
+ "eval_l2g_gen_len": 12.7833,
81
+ "eval_l2g_rouge1": 28.7842,
82
+ "eval_l2g_rouge2": 15.662,
83
+ "eval_l2g_rougeL": 27.3798,
84
+ "eval_l2g_rougeLsum": 27.3872,
85
+ "eval_loss": 4.086117744445801,
86
+ "eval_runtime": 92.0779,
87
+ "eval_samples_per_second": 107.746,
88
+ "eval_steps_per_second": 0.847,
89
+ "step": 1039
90
+ },
91
+ {
92
+ "epoch": 0.7509025270758123,
93
+ "grad_norm": 280.9309387207031,
94
+ "learning_rate": 0.0009999999746484521,
95
+ "loss": 4.4853,
96
+ "step": 1040
97
+ },
98
+ {
99
+ "epoch": 0.9010830324909748,
100
+ "grad_norm": 278.86737060546875,
101
+ "learning_rate": 0.000999720525233547,
102
+ "loss": 4.4543,
103
+ "step": 1248
104
+ },
105
+ {
106
+ "epoch": 1.0512635379061372,
107
+ "grad_norm": 347.6966857910156,
108
+ "learning_rate": 0.0009988930279319957,
109
+ "loss": 4.4011,
110
+ "step": 1456
111
+ },
112
+ {
113
+ "epoch": 1.2014440433212996,
114
+ "grad_norm": 388.53009033203125,
115
+ "learning_rate": 0.0009975183907215961,
116
+ "loss": 4.3391,
117
+ "step": 1664
118
+ },
119
+ {
120
+ "epoch": 1.3516245487364622,
121
+ "grad_norm": 374.0000915527344,
122
+ "learning_rate": 0.0009955981219336306,
123
+ "loss": 4.2954,
124
+ "step": 1872
125
+ },
126
+ {
127
+ "epoch": 1.500361010830325,
128
+ "eval_g2l_cer": 60.8741,
129
+ "eval_g2l_gen_len": 5.7528,
130
+ "eval_g2l_rouge1": 34.1975,
131
+ "eval_g2l_rouge2": 23.0519,
132
+ "eval_g2l_rougeL": 33.7746,
133
+ "eval_g2l_rougeLsum": 33.7503,
134
+ "eval_l2ex_cer": 90.0364,
135
+ "eval_l2ex_gen_len": 38.0339,
136
+ "eval_l2ex_rouge1": 27.7928,
137
+ "eval_l2ex_rouge2": 12.8688,
138
+ "eval_l2ex_rougeL": 25.3603,
139
+ "eval_l2ex_rougeLsum": 25.3866,
140
+ "eval_l2g_cer": 95.9503,
141
+ "eval_l2g_gen_len": 38.6107,
142
+ "eval_l2g_rouge1": 31.3843,
143
+ "eval_l2g_rouge2": 20.1215,
144
+ "eval_l2g_rougeL": 30.0596,
145
+ "eval_l2g_rougeLsum": 30.1295,
146
+ "eval_loss": 4.214888095855713,
147
+ "eval_runtime": 102.9376,
148
+ "eval_samples_per_second": 96.379,
149
+ "eval_steps_per_second": 0.758,
150
+ "step": 2078
151
+ },
152
+ {
153
+ "epoch": 1.5018050541516246,
154
+ "grad_norm": 282.3067932128906,
155
+ "learning_rate": 0.0009931343285978396,
156
+ "loss": 4.2676,
157
+ "step": 2080
158
+ },
159
+ {
160
+ "epoch": 1.651985559566787,
161
+ "grad_norm": 429.1705017089844,
162
+ "learning_rate": 0.000990129714130466,
163
+ "loss": 4.2425,
164
+ "step": 2288
165
+ },
166
+ {
167
+ "epoch": 1.8021660649819493,
168
+ "grad_norm": 342.697509765625,
169
+ "learning_rate": 0.0009865875753679114,
170
+ "loss": 4.2198,
171
+ "step": 2496
172
+ },
173
+ {
174
+ "epoch": 1.952346570397112,
175
+ "grad_norm": 287.99896240234375,
176
+ "learning_rate": 0.0009825117989492565,
177
+ "loss": 4.1951,
178
+ "step": 2704
179
+ },
180
+ {
181
+ "epoch": 2.1025270758122745,
182
+ "grad_norm": 329.3447570800781,
183
+ "learning_rate": 0.0009779068570516165,
184
+ "loss": 4.137,
185
+ "step": 2912
186
+ },
187
+ {
188
+ "epoch": 2.2505415162454874,
189
+ "eval_g2l_cer": 57.0175,
190
+ "eval_g2l_gen_len": 3.4026,
191
+ "eval_g2l_rouge1": 33.2248,
192
+ "eval_g2l_rouge2": 24.7912,
193
+ "eval_g2l_rougeL": 33.1481,
194
+ "eval_g2l_rougeLsum": 33.1288,
195
+ "eval_l2ex_cer": 83.9364,
196
+ "eval_l2ex_gen_len": 17.4142,
197
+ "eval_l2ex_rouge1": 30.4747,
198
+ "eval_l2ex_rouge2": 15.2972,
199
+ "eval_l2ex_rougeL": 27.443,
200
+ "eval_l2ex_rougeLsum": 27.5452,
201
+ "eval_l2g_cer": 80.6606,
202
+ "eval_l2g_gen_len": 14.6152,
203
+ "eval_l2g_rouge1": 34.2385,
204
+ "eval_l2g_rouge2": 22.2422,
205
+ "eval_l2g_rougeL": 32.5658,
206
+ "eval_l2g_rougeLsum": 32.6354,
207
+ "eval_loss": 3.8766722679138184,
208
+ "eval_runtime": 93.2118,
209
+ "eval_samples_per_second": 106.435,
210
+ "eval_steps_per_second": 0.837,
211
+ "step": 3117
212
+ },
213
+ {
214
+ "epoch": 2.252707581227437,
215
+ "grad_norm": 373.11468505859375,
216
+ "learning_rate": 0.00097277780248301,
217
+ "loss": 4.1204,
218
+ "step": 3120
219
+ },
220
+ {
221
+ "epoch": 2.4028880866425992,
222
+ "grad_norm": 332.1923522949219,
223
+ "learning_rate": 0.0009671302631381275,
224
+ "loss": 4.1156,
225
+ "step": 3328
226
+ },
227
+ {
228
+ "epoch": 2.5530685920577616,
229
+ "grad_norm": 439.4508361816406,
230
+ "learning_rate": 0.0009609704358230791,
231
+ "loss": 4.0976,
232
+ "step": 3536
233
+ },
234
+ {
235
+ "epoch": 2.7032490974729244,
236
+ "grad_norm": 283.86175537109375,
237
+ "learning_rate": 0.0009543050794559023,
238
+ "loss": 4.0829,
239
+ "step": 3744
240
+ },
241
+ {
242
+ "epoch": 2.853429602888087,
243
+ "grad_norm": 373.6076965332031,
244
+ "learning_rate": 0.0009471415076502864,
245
+ "loss": 4.0567,
246
+ "step": 3952
247
+ },
248
+ {
249
+ "epoch": 3.00072202166065,
250
+ "eval_g2l_cer": 54.3375,
251
+ "eval_g2l_gen_len": 5.1478,
252
+ "eval_g2l_rouge1": 37.1423,
253
+ "eval_g2l_rouge2": 25.8415,
254
+ "eval_g2l_rougeL": 36.8263,
255
+ "eval_g2l_rougeLsum": 36.799,
256
+ "eval_l2ex_cer": 88.2942,
257
+ "eval_l2ex_gen_len": 35.3597,
258
+ "eval_l2ex_rouge1": 28.7362,
259
+ "eval_l2ex_rouge2": 13.0176,
260
+ "eval_l2ex_rougeL": 26.1133,
261
+ "eval_l2ex_rougeLsum": 26.1476,
262
+ "eval_l2g_cer": 85.0531,
263
+ "eval_l2g_gen_len": 29.6997,
264
+ "eval_l2g_rouge1": 35.6931,
265
+ "eval_l2g_rouge2": 23.4243,
266
+ "eval_l2g_rougeL": 34.012,
267
+ "eval_l2g_rougeLsum": 34.0684,
268
+ "eval_loss": 3.9321906566619873,
269
+ "eval_runtime": 100.3303,
270
+ "eval_samples_per_second": 98.883,
271
+ "eval_steps_per_second": 0.777,
272
+ "step": 4156
273
+ },
274
+ {
275
+ "epoch": 3.003610108303249,
276
+ "grad_norm": 456.342529296875,
277
+ "learning_rate": 0.0009394875806906537,
278
+ "loss": 4.045,
279
+ "step": 4160
280
+ },
281
+ {
282
+ "epoch": 3.1537906137184115,
283
+ "grad_norm": 336.9688720703125,
284
+ "learning_rate": 0.0009313516969074018,
285
+ "loss": 4.0002,
286
+ "step": 4368
287
+ },
288
+ {
289
+ "epoch": 3.303971119133574,
290
+ "grad_norm": 354.8324890136719,
291
+ "learning_rate": 0.0009227427834617708,
292
+ "loss": 3.9884,
293
+ "step": 4576
294
+ },
295
+ {
296
+ "epoch": 3.4541516245487367,
297
+ "grad_norm": 341.2556457519531,
298
+ "learning_rate": 0.0009136702865504465,
299
+ "loss": 3.9819,
300
+ "step": 4784
301
+ },
302
+ {
303
+ "epoch": 3.604332129963899,
304
+ "grad_norm": 348.25225830078125,
305
+ "learning_rate": 0.0009041441610406489,
306
+ "loss": 3.9644,
307
+ "step": 4992
308
+ },
309
+ {
310
+ "epoch": 3.7509025270758123,
311
+ "eval_g2l_cer": 54.7671,
312
+ "eval_g2l_gen_len": 3.3446,
313
+ "eval_g2l_rouge1": 34.9931,
314
+ "eval_g2l_rouge2": 26.209,
315
+ "eval_g2l_rougeL": 34.9234,
316
+ "eval_g2l_rougeLsum": 34.913,
317
+ "eval_l2ex_cer": 85.5203,
318
+ "eval_l2ex_gen_len": 20.1264,
319
+ "eval_l2ex_rouge1": 30.9385,
320
+ "eval_l2ex_rouge2": 15.6373,
321
+ "eval_l2ex_rougeL": 28.096,
322
+ "eval_l2ex_rougeLsum": 28.1379,
323
+ "eval_l2g_cer": 77.9784,
324
+ "eval_l2g_gen_len": 14.0847,
325
+ "eval_l2g_rouge1": 35.0014,
326
+ "eval_l2g_rouge2": 23.2642,
327
+ "eval_l2g_rougeL": 33.3426,
328
+ "eval_l2g_rougeLsum": 33.385,
329
+ "eval_loss": 3.767300844192505,
330
+ "eval_runtime": 93.092,
331
+ "eval_samples_per_second": 106.572,
332
+ "eval_steps_per_second": 0.838,
333
+ "step": 5195
334
+ },
335
+ {
336
+ "epoch": 3.7545126353790614,
337
+ "grad_norm": 282.4262390136719,
338
+ "learning_rate": 0.0008941748595470763,
339
+ "loss": 3.9561,
340
+ "step": 5200
341
+ },
342
+ {
343
+ "epoch": 3.904693140794224,
344
+ "grad_norm": 309.5865783691406,
345
+ "learning_rate": 0.0008837733209626942,
346
+ "loss": 3.9365,
347
+ "step": 5408
348
+ },
349
+ {
350
+ "epoch": 4.054873646209386,
351
+ "grad_norm": 314.7027893066406,
352
+ "learning_rate": 0.0008729509584559499,
353
+ "loss": 3.9144,
354
+ "step": 5616
355
+ },
356
+ {
357
+ "epoch": 4.205054151624549,
358
+ "grad_norm": 354.8764953613281,
359
+ "learning_rate": 0.0008617196469475859,
360
+ "loss": 3.871,
361
+ "step": 5824
362
+ },
363
+ {
364
+ "epoch": 4.355234657039711,
365
+ "grad_norm": 318.5345458984375,
366
+ "learning_rate": 0.0008500917100807916,
367
+ "loss": 3.8729,
368
+ "step": 6032
369
+ },
370
+ {
371
+ "epoch": 4.501083032490975,
372
+ "eval_g2l_cer": 54.0839,
373
+ "eval_g2l_gen_len": 5.259,
374
+ "eval_g2l_rouge1": 37.7304,
375
+ "eval_g2l_rouge2": 26.5008,
376
+ "eval_g2l_rougeL": 37.4145,
377
+ "eval_g2l_rougeLsum": 37.389,
378
+ "eval_l2ex_cer": 87.7795,
379
+ "eval_l2ex_gen_len": 34.444,
380
+ "eval_l2ex_rouge1": 29.4565,
381
+ "eval_l2ex_rouge2": 13.4704,
382
+ "eval_l2ex_rougeL": 26.584,
383
+ "eval_l2ex_rougeLsum": 26.6084,
384
+ "eval_l2g_cer": 84.0775,
385
+ "eval_l2g_gen_len": 27.3501,
386
+ "eval_l2g_rouge1": 36.4264,
387
+ "eval_l2g_rouge2": 23.9948,
388
+ "eval_l2g_rougeL": 34.6234,
389
+ "eval_l2g_rougeLsum": 34.6872,
390
+ "eval_loss": 3.814581871032715,
391
+ "eval_runtime": 99.5293,
392
+ "eval_samples_per_second": 99.679,
393
+ "eval_steps_per_second": 0.784,
394
+ "step": 6234
395
+ },
396
+ {
397
+ "epoch": 4.505415162454874,
398
+ "grad_norm": 302.9512634277344,
399
+ "learning_rate": 0.0008380799066989898,
400
+ "loss": 3.8677,
401
+ "step": 6240
402
+ },
403
+ {
404
+ "epoch": 4.6555956678700365,
405
+ "grad_norm": 250.16696166992188,
406
+ "learning_rate": 0.0008256974168460981,
407
+ "loss": 3.8378,
408
+ "step": 6448
409
+ },
410
+ {
411
+ "epoch": 4.8057761732851985,
412
+ "grad_norm": 348.5408935546875,
413
+ "learning_rate": 0.0008129578273046243,
414
+ "loss": 3.852,
415
+ "step": 6656
416
+ },
417
+ {
418
+ "epoch": 4.955956678700361,
419
+ "grad_norm": 355.0418701171875,
420
+ "learning_rate": 0.0007998751166874639,
421
+ "loss": 3.845,
422
+ "step": 6864
423
+ },
424
+ {
425
+ "epoch": 5.106137184115523,
426
+ "grad_norm": 349.153564453125,
427
+ "learning_rate": 0.0007864636400997593,
428
+ "loss": 3.799,
429
+ "step": 7072
430
+ },
431
+ {
432
+ "epoch": 5.251263537906137,
433
+ "eval_g2l_cer": 52.3635,
434
+ "eval_g2l_gen_len": 3.512,
435
+ "eval_g2l_rouge1": 37.4372,
436
+ "eval_g2l_rouge2": 27.515,
437
+ "eval_g2l_rougeL": 37.3252,
438
+ "eval_g2l_rougeLsum": 37.3643,
439
+ "eval_l2ex_cer": 81.2205,
440
+ "eval_l2ex_gen_len": 18.2107,
441
+ "eval_l2ex_rouge1": 32.8709,
442
+ "eval_l2ex_rouge2": 16.7456,
443
+ "eval_l2ex_rougeL": 29.6388,
444
+ "eval_l2ex_rougeLsum": 29.717,
445
+ "eval_l2g_cer": 73.2203,
446
+ "eval_l2g_gen_len": 13.7837,
447
+ "eval_l2g_rouge1": 37.1711,
448
+ "eval_l2g_rouge2": 24.5593,
449
+ "eval_l2g_rougeL": 35.3326,
450
+ "eval_l2g_rougeLsum": 35.3608,
451
+ "eval_loss": 3.6153602600097656,
452
+ "eval_runtime": 92.481,
453
+ "eval_samples_per_second": 107.276,
454
+ "eval_steps_per_second": 0.843,
455
+ "step": 7273
456
+ },
457
+ {
458
+ "epoch": 5.256317689530686,
459
+ "grad_norm": 313.629638671875,
460
+ "learning_rate": 0.0007727381133876502,
461
+ "loss": 3.7717,
462
+ "step": 7280
463
+ },
464
+ {
465
+ "epoch": 5.406498194945849,
466
+ "grad_norm": 366.9100036621094,
467
+ "learning_rate": 0.0007587135969911982,
468
+ "loss": 3.7698,
469
+ "step": 7488
470
+ },
471
+ {
472
+ "epoch": 5.556678700361011,
473
+ "grad_norm": 405.91522216796875,
474
+ "learning_rate": 0.000744405479419202,
475
+ "loss": 3.7686,
476
+ "step": 7696
477
+ },
478
+ {
479
+ "epoch": 5.706859205776174,
480
+ "grad_norm": 323.0384521484375,
481
+ "learning_rate": 0.000729829460364038,
482
+ "loss": 3.7567,
483
+ "step": 7904
484
+ },
485
+ {
486
+ "epoch": 5.8570397111913355,
487
+ "grad_norm": 236.5808563232422,
488
+ "learning_rate": 0.0007150015334750512,
489
+ "loss": 3.7504,
490
+ "step": 8112
491
+ },
492
+ {
493
+ "epoch": 6.0014440433213,
494
+ "eval_g2l_cer": 52.8799,
495
+ "eval_g2l_gen_len": 4.9953,
496
+ "eval_g2l_rouge1": 38.9469,
497
+ "eval_g2l_rouge2": 27.4705,
498
+ "eval_g2l_rougeL": 38.7013,
499
+ "eval_g2l_rougeLsum": 38.6638,
500
+ "eval_l2ex_cer": 83.8059,
501
+ "eval_l2ex_gen_len": 29.591,
502
+ "eval_l2ex_rouge1": 31.5224,
503
+ "eval_l2ex_rouge2": 15.0063,
504
+ "eval_l2ex_rougeL": 28.1947,
505
+ "eval_l2ex_rougeLsum": 28.2288,
506
+ "eval_l2g_cer": 80.9099,
507
+ "eval_l2g_gen_len": 24.6797,
508
+ "eval_l2g_rouge1": 37.5363,
509
+ "eval_l2g_rouge2": 24.8417,
510
+ "eval_l2g_rougeL": 35.6194,
511
+ "eval_l2g_rougeLsum": 35.6546,
512
+ "eval_loss": 3.7020649909973145,
513
+ "eval_runtime": 98.5066,
514
+ "eval_samples_per_second": 100.714,
515
+ "eval_steps_per_second": 0.792,
516
+ "step": 8312
517
+ },
518
+ {
519
+ "epoch": 6.007220216606498,
520
+ "grad_norm": 265.8843994140625,
521
+ "learning_rate": 0.000699937968809401,
522
+ "loss": 3.7525,
523
+ "step": 8320
524
+ },
525
+ {
526
+ "epoch": 6.15740072202166,
527
+ "grad_norm": 291.2859802246094,
528
+ "learning_rate": 0.0006846552949796146,
529
+ "loss": 3.6905,
530
+ "step": 8528
531
+ },
532
+ {
533
+ "epoch": 6.307581227436823,
534
+ "grad_norm": 268.9134826660156,
535
+ "learning_rate": 0.0006691702810174398,
536
+ "loss": 3.6939,
537
+ "step": 8736
538
+ },
539
+ {
540
+ "epoch": 6.457761732851986,
541
+ "grad_norm": 292.39154052734375,
542
+ "learning_rate": 0.0006534999179738952,
543
+ "loss": 3.7019,
544
+ "step": 8944
545
+ },
546
+ {
547
+ "epoch": 6.607942238267148,
548
+ "grad_norm": 298.4355773925781,
549
+ "learning_rate": 0.0006376614002757093,
550
+ "loss": 3.6892,
551
+ "step": 9152
552
+ },
553
+ {
554
+ "epoch": 6.751624548736462,
555
+ "eval_g2l_cer": 51.8358,
556
+ "eval_g2l_gen_len": 3.5613,
557
+ "eval_g2l_rouge1": 37.7745,
558
+ "eval_g2l_rouge2": 27.9843,
559
+ "eval_g2l_rougeL": 37.6788,
560
+ "eval_g2l_rougeLsum": 37.6728,
561
+ "eval_l2ex_cer": 84.3919,
562
+ "eval_l2ex_gen_len": 20.5961,
563
+ "eval_l2ex_rouge1": 32.2651,
564
+ "eval_l2ex_rouge2": 16.2957,
565
+ "eval_l2ex_rougeL": 28.9932,
566
+ "eval_l2ex_rougeLsum": 29.0868,
567
+ "eval_l2g_cer": 75.9064,
568
+ "eval_l2g_gen_len": 14.9821,
569
+ "eval_l2g_rouge1": 37.3147,
570
+ "eval_l2g_rouge2": 24.7819,
571
+ "eval_l2g_rougeL": 35.4462,
572
+ "eval_l2g_rougeLsum": 35.4671,
573
+ "eval_loss": 3.5767345428466797,
574
+ "eval_runtime": 93.796,
575
+ "eval_samples_per_second": 105.772,
576
+ "eval_steps_per_second": 0.832,
577
+ "step": 9351
578
+ },
579
+ {
580
+ "epoch": 6.758122743682311,
581
+ "grad_norm": 257.7994689941406,
582
+ "learning_rate": 0.0006216721068586019,
583
+ "loss": 3.6827,
584
+ "step": 9360
585
+ },
586
+ {
587
+ "epoch": 6.908303249097473,
588
+ "grad_norm": 264.89263916015625,
589
+ "learning_rate": 0.0006055495820981136,
590
+ "loss": 3.6662,
591
+ "step": 9568
592
+ },
593
+ {
594
+ "epoch": 7.058483754512635,
595
+ "grad_norm": 289.5307312011719,
596
+ "learning_rate": 0.0005893115165589047,
597
+ "loss": 3.6482,
598
+ "step": 9776
599
+ },
600
+ {
601
+ "epoch": 7.208664259927798,
602
+ "grad_norm": 254.08291625976562,
603
+ "learning_rate": 0.0005729757275836455,
604
+ "loss": 3.6198,
605
+ "step": 9984
606
+ },
607
+ {
608
+ "epoch": 7.35884476534296,
609
+ "grad_norm": 181.30072021484375,
610
+ "learning_rate": 0.0005565601397428012,
611
+ "loss": 3.6104,
612
+ "step": 10192
613
+ },
614
+ {
615
+ "epoch": 7.501805054151625,
616
+ "eval_g2l_cer": 52.672,
617
+ "eval_g2l_gen_len": 4.8856,
618
+ "eval_g2l_rouge1": 39.792,
619
+ "eval_g2l_rouge2": 28.4504,
620
+ "eval_g2l_rougeL": 39.5411,
621
+ "eval_g2l_rougeLsum": 39.532,
622
+ "eval_l2ex_cer": 87.7735,
623
+ "eval_l2ex_gen_len": 32.8952,
624
+ "eval_l2ex_rouge1": 30.3306,
625
+ "eval_l2ex_rouge2": 14.2701,
626
+ "eval_l2ex_rougeL": 27.0806,
627
+ "eval_l2ex_rougeLsum": 27.0923,
628
+ "eval_l2g_cer": 83.3818,
629
+ "eval_l2g_gen_len": 25.6912,
630
+ "eval_l2g_rouge1": 37.5685,
631
+ "eval_l2g_rouge2": 25.026,
632
+ "eval_l2g_rougeL": 35.6593,
633
+ "eval_l2g_rougeLsum": 35.7335,
634
+ "eval_loss": 3.6247808933258057,
635
+ "eval_runtime": 97.6949,
636
+ "eval_samples_per_second": 101.551,
637
+ "eval_steps_per_second": 0.798,
638
+ "step": 10390
639
+ },
640
+ {
641
+ "epoch": 7.509025270758123,
642
+ "grad_norm": 213.4962158203125,
643
+ "learning_rate": 0.0005400827651667568,
644
+ "loss": 3.6116,
645
+ "step": 10400
646
+ },
647
+ {
648
+ "epoch": 7.659205776173286,
649
+ "grad_norm": 200.51080322265625,
650
+ "learning_rate": 0.0005235616837818695,
651
+ "loss": 3.613,
652
+ "step": 10608
653
+ },
654
+ {
655
+ "epoch": 7.809386281588448,
656
+ "grad_norm": 210.73484802246094,
657
+ "learning_rate": 0.0005070150234721305,
658
+ "loss": 3.5998,
659
+ "step": 10816
660
+ },
661
+ {
662
+ "epoch": 7.95956678700361,
663
+ "grad_norm": 245.5376434326172,
664
+ "learning_rate": 0.0004904609401882021,
665
+ "loss": 3.6003,
666
+ "step": 11024
667
+ },
668
+ {
669
+ "epoch": 8.109747292418772,
670
+ "grad_norm": 234.57310485839844,
671
+ "learning_rate": 0.00047391759802566346,
672
+ "loss": 3.5769,
673
+ "step": 11232
674
+ },
675
+ {
676
+ "epoch": 8.251985559566787,
677
+ "eval_g2l_cer": 51.2806,
678
+ "eval_g2l_gen_len": 4.0062,
679
+ "eval_g2l_rouge1": 39.5838,
680
+ "eval_g2l_rouge2": 28.8731,
681
+ "eval_g2l_rougeL": 39.3964,
682
+ "eval_g2l_rougeLsum": 39.3929,
683
+ "eval_l2ex_cer": 81.177,
684
+ "eval_l2ex_gen_len": 21.2641,
685
+ "eval_l2ex_rouge1": 33.1446,
686
+ "eval_l2ex_rouge2": 16.6249,
687
+ "eval_l2ex_rougeL": 29.723,
688
+ "eval_l2ex_rougeLsum": 29.7703,
689
+ "eval_l2g_cer": 73.5184,
690
+ "eval_l2g_gen_len": 15.4612,
691
+ "eval_l2g_rouge1": 38.7817,
692
+ "eval_l2g_rouge2": 25.5669,
693
+ "eval_l2g_rougeL": 36.728,
694
+ "eval_l2g_rougeLsum": 36.7794,
695
+ "eval_loss": 3.502086639404297,
696
+ "eval_runtime": 94.3872,
697
+ "eval_samples_per_second": 105.11,
698
+ "eval_steps_per_second": 0.826,
699
+ "step": 11429
700
+ },
701
+ {
702
+ "epoch": 8.259927797833935,
703
+ "grad_norm": 212.4471435546875,
704
+ "learning_rate": 0.00045740314929431514,
705
+ "loss": 3.5588,
706
+ "step": 11440
707
+ },
708
+ {
709
+ "epoch": 8.410108303249098,
710
+ "grad_norm": 227.54701232910156,
711
+ "learning_rate": 0.000440935714600417,
712
+ "loss": 3.5575,
713
+ "step": 11648
714
+ },
715
+ {
716
+ "epoch": 8.56028880866426,
717
+ "grad_norm": 175.19906616210938,
718
+ "learning_rate": 0.00042453336296371426,
719
+ "loss": 3.5425,
720
+ "step": 11856
721
+ },
722
+ {
723
+ "epoch": 8.710469314079422,
724
+ "grad_norm": 197.85183715820312,
725
+ "learning_rate": 0.0004082140919910653,
726
+ "loss": 3.5516,
727
+ "step": 12064
728
+ },
729
+ {
730
+ "epoch": 8.860649819494585,
731
+ "grad_norm": 174.2976531982422,
732
+ "learning_rate": 0.00039199580812842894,
733
+ "loss": 3.5262,
734
+ "step": 12272
735
+ },
736
+ {
737
+ "epoch": 9.00216606498195,
738
+ "eval_g2l_cer": 52.3453,
739
+ "eval_g2l_gen_len": 4.6585,
740
+ "eval_g2l_rouge1": 39.8411,
741
+ "eval_g2l_rouge2": 28.7875,
742
+ "eval_g2l_rougeL": 39.7115,
743
+ "eval_g2l_rougeLsum": 39.6779,
744
+ "eval_l2ex_cer": 84.2856,
745
+ "eval_l2ex_gen_len": 28.0884,
746
+ "eval_l2ex_rouge1": 31.9562,
747
+ "eval_l2ex_rouge2": 15.2366,
748
+ "eval_l2ex_rougeL": 28.4418,
749
+ "eval_l2ex_rougeLsum": 28.4937,
750
+ "eval_l2g_cer": 82.0714,
751
+ "eval_l2g_gen_len": 22.9518,
752
+ "eval_l2g_rouge1": 38.3811,
753
+ "eval_l2g_rouge2": 25.3667,
754
+ "eval_l2g_rougeL": 36.2921,
755
+ "eval_l2g_rougeLsum": 36.3599,
756
+ "eval_loss": 3.542821168899536,
757
+ "eval_runtime": 97.8166,
758
+ "eval_samples_per_second": 101.424,
759
+ "eval_steps_per_second": 0.797,
760
+ "step": 12468
761
+ },
762
+ {
763
+ "epoch": 9.010830324909747,
764
+ "grad_norm": 148.35972595214844,
765
+ "learning_rate": 0.00037589630701287847,
766
+ "loss": 3.5412,
767
+ "step": 12480
768
+ },
769
+ {
770
+ "epoch": 9.16101083032491,
771
+ "grad_norm": 181.6919708251953,
772
+ "learning_rate": 0.00035993325394620217,
773
+ "loss": 3.4914,
774
+ "step": 12688
775
+ },
776
+ {
777
+ "epoch": 9.311191335740073,
778
+ "grad_norm": 218.32742309570312,
779
+ "learning_rate": 0.00034412416451151385,
780
+ "loss": 3.5073,
781
+ "step": 12896
782
+ },
783
+ {
784
+ "epoch": 9.461371841155234,
785
+ "grad_norm": 144.4810791015625,
786
+ "learning_rate": 0.0003284863853541441,
787
+ "loss": 3.5023,
788
+ "step": 13104
789
+ },
790
+ {
791
+ "epoch": 9.611552346570397,
792
+ "grad_norm": 204.1243896484375,
793
+ "learning_rate": 0.00031303707514790077,
794
+ "loss": 3.4959,
795
+ "step": 13312
796
+ },
797
+ {
798
+ "epoch": 9.752346570397112,
799
+ "eval_g2l_cer": 50.963,
800
+ "eval_g2l_gen_len": 3.9938,
801
+ "eval_g2l_rouge1": 39.9737,
802
+ "eval_g2l_rouge2": 29.4419,
803
+ "eval_g2l_rougeL": 39.8196,
804
+ "eval_g2l_rougeLsum": 39.8028,
805
+ "eval_l2ex_cer": 81.2748,
806
+ "eval_l2ex_gen_len": 22.4378,
807
+ "eval_l2ex_rouge1": 33.2444,
808
+ "eval_l2ex_rouge2": 16.7607,
809
+ "eval_l2ex_rougeL": 29.9288,
810
+ "eval_l2ex_rougeLsum": 29.9861,
811
+ "eval_l2g_cer": 74.1059,
812
+ "eval_l2g_gen_len": 15.8848,
813
+ "eval_l2g_rouge1": 38.9415,
814
+ "eval_l2g_rouge2": 25.7151,
815
+ "eval_l2g_rougeL": 36.9163,
816
+ "eval_l2g_rougeLsum": 36.9791,
817
+ "eval_loss": 3.475815534591675,
818
+ "eval_runtime": 94.3857,
819
+ "eval_samples_per_second": 105.111,
820
+ "eval_steps_per_second": 0.826,
821
+ "step": 13507
822
+ },
823
+ {
824
+ "epoch": 9.76173285198556,
825
+ "grad_norm": 156.18637084960938,
826
+ "learning_rate": 0.0002977931857675812,
827
+ "loss": 3.4928,
828
+ "step": 13520
829
+ },
830
+ {
831
+ "epoch": 9.911913357400723,
832
+ "grad_norm": 116.77749633789062,
833
+ "learning_rate": 0.00028277144368839654,
834
+ "loss": 3.4805,
835
+ "step": 13728
836
+ },
837
+ {
838
+ "epoch": 10.062093862815885,
839
+ "grad_norm": 147.93405151367188,
840
+ "learning_rate": 0.00026798833163271856,
841
+ "loss": 3.4859,
842
+ "step": 13936
843
+ },
844
+ {
845
+ "epoch": 10.212274368231046,
846
+ "grad_norm": 129.8922882080078,
847
+ "learning_rate": 0.0002534600704842848,
848
+ "loss": 3.4512,
849
+ "step": 14144
850
+ },
851
+ {
852
+ "epoch": 10.36245487364621,
853
+ "grad_norm": 129.17861938476562,
854
+ "learning_rate": 0.00023920260148970935,
855
+ "loss": 3.4679,
856
+ "step": 14352
857
+ },
858
+ {
859
+ "epoch": 10.502527075812274,
860
+ "eval_g2l_cer": 51.589,
861
+ "eval_g2l_gen_len": 4.615,
862
+ "eval_g2l_rouge1": 40.3572,
863
+ "eval_g2l_rouge2": 29.0165,
864
+ "eval_g2l_rougeL": 40.1696,
865
+ "eval_g2l_rougeLsum": 40.127,
866
+ "eval_l2ex_cer": 83.3939,
867
+ "eval_l2ex_gen_len": 27.2939,
868
+ "eval_l2ex_rouge1": 32.0,
869
+ "eval_l2ex_rouge2": 15.2047,
870
+ "eval_l2ex_rougeL": 28.4221,
871
+ "eval_l2ex_rougeLsum": 28.4944,
872
+ "eval_l2g_cer": 78.1523,
873
+ "eval_l2g_gen_len": 21.5805,
874
+ "eval_l2g_rouge1": 38.8011,
875
+ "eval_l2g_rouge2": 25.5645,
876
+ "eval_l2g_rougeL": 36.5851,
877
+ "eval_l2g_rougeLsum": 36.6686,
878
+ "eval_loss": 3.490727663040161,
879
+ "eval_runtime": 97.0968,
880
+ "eval_samples_per_second": 102.176,
881
+ "eval_steps_per_second": 0.803,
882
+ "step": 14546
883
+ },
884
+ {
885
+ "epoch": 10.512635379061372,
886
+ "grad_norm": 120.92171478271484,
887
+ "learning_rate": 0.00022523156876682566,
888
+ "loss": 3.4559,
889
+ "step": 14560
890
+ },
891
+ {
892
+ "epoch": 10.662815884476535,
893
+ "grad_norm": 72.50321960449219,
894
+ "learning_rate": 0.00021156230213905934,
895
+ "loss": 3.4527,
896
+ "step": 14768
897
+ },
898
+ {
899
+ "epoch": 10.812996389891698,
900
+ "grad_norm": 29.285614013671875,
901
+ "learning_rate": 0.0001982098003146605,
902
+ "loss": 3.445,
903
+ "step": 14976
904
+ },
905
+ {
906
+ "epoch": 10.963176895306859,
907
+ "grad_norm": 139.87692260742188,
908
+ "learning_rate": 0.00018518871442925475,
909
+ "loss": 3.4474,
910
+ "step": 15184
911
+ },
912
+ {
913
+ "epoch": 11.113357400722021,
914
+ "grad_norm": 115.22322845458984,
915
+ "learning_rate": 0.0001725133319697725,
916
+ "loss": 3.444,
917
+ "step": 15392
918
+ },
919
+ {
920
+ "epoch": 11.252707581227437,
921
+ "eval_g2l_cer": 50.9127,
922
+ "eval_g2l_gen_len": 4.3921,
923
+ "eval_g2l_rouge1": 41.0139,
924
+ "eval_g2l_rouge2": 29.6136,
925
+ "eval_g2l_rougeL": 40.8151,
926
+ "eval_g2l_rougeLsum": 40.8006,
927
+ "eval_l2ex_cer": 85.5529,
928
+ "eval_l2ex_gen_len": 28.0987,
929
+ "eval_l2ex_rouge1": 31.8781,
930
+ "eval_l2ex_rouge2": 15.2454,
931
+ "eval_l2ex_rougeL": 28.3874,
932
+ "eval_l2ex_rougeLsum": 28.4594,
933
+ "eval_l2g_cer": 79.5578,
934
+ "eval_l2g_gen_len": 20.9953,
935
+ "eval_l2g_rouge1": 38.8463,
936
+ "eval_l2g_rouge2": 25.6991,
937
+ "eval_l2g_rougeL": 36.7062,
938
+ "eval_l2g_rougeLsum": 36.784,
939
+ "eval_loss": 3.4728221893310547,
940
+ "eval_runtime": 95.7364,
941
+ "eval_samples_per_second": 103.628,
942
+ "eval_steps_per_second": 0.815,
943
+ "step": 15585
944
+ },
945
+ {
946
+ "epoch": 11.263537906137184,
947
+ "grad_norm": 90.60981750488281,
948
+ "learning_rate": 0.000160197561097393,
949
+ "loss": 3.4291,
950
+ "step": 15600
951
+ },
952
+ {
953
+ "epoch": 11.413718411552347,
954
+ "grad_norm": 84.94570922851562,
955
+ "learning_rate": 0.00014825491538670787,
956
+ "loss": 3.4392,
957
+ "step": 15808
958
+ },
959
+ {
960
+ "epoch": 11.56389891696751,
961
+ "grad_norm": 74.72296142578125,
962
+ "learning_rate": 0.00013669849899784683,
963
+ "loss": 3.4338,
964
+ "step": 16016
965
+ },
966
+ {
967
+ "epoch": 11.714079422382671,
968
+ "grad_norm": 73.01377868652344,
969
+ "learning_rate": 0.0001255409922978368,
970
+ "loss": 3.4147,
971
+ "step": 16224
972
+ },
973
+ {
974
+ "epoch": 11.864259927797834,
975
+ "grad_norm": 29.206298828125,
976
+ "learning_rate": 0.00011479463794697153,
977
+ "loss": 3.4327,
978
+ "step": 16432
979
+ },
980
+ {
981
+ "epoch": 12.0028880866426,
982
+ "eval_g2l_cer": 51.0704,
983
+ "eval_g2l_gen_len": 4.428,
984
+ "eval_g2l_rouge1": 40.8383,
985
+ "eval_g2l_rouge2": 29.5544,
986
+ "eval_g2l_rougeL": 40.6824,
987
+ "eval_g2l_rougeLsum": 40.648,
988
+ "eval_l2ex_cer": 85.2521,
989
+ "eval_l2ex_gen_len": 27.6208,
990
+ "eval_l2ex_rouge1": 31.8072,
991
+ "eval_l2ex_rouge2": 15.1802,
992
+ "eval_l2ex_rougeL": 28.2533,
993
+ "eval_l2ex_rougeLsum": 28.3249,
994
+ "eval_l2g_cer": 78.2445,
995
+ "eval_l2g_gen_len": 20.4718,
996
+ "eval_l2g_rouge1": 38.9972,
997
+ "eval_l2g_rouge2": 25.8126,
998
+ "eval_l2g_rougeL": 36.8133,
999
+ "eval_l2g_rougeLsum": 36.8913,
1000
+ "eval_loss": 3.460233211517334,
1001
+ "eval_runtime": 96.6773,
1002
+ "eval_samples_per_second": 102.62,
1003
+ "eval_steps_per_second": 0.807,
1004
+ "step": 16624
1005
+ },
1006
+ {
1007
+ "epoch": 12.014440433212997,
1008
+ "grad_norm": 75.82231140136719,
1009
+ "learning_rate": 0.00010447122746545834,
1010
+ "loss": 3.4103,
1011
+ "step": 16640
1012
+ },
1013
+ {
1014
+ "epoch": 12.16462093862816,
1015
+ "grad_norm": 68.91098022460938,
1016
+ "learning_rate": 9.458208829508076e-05,
1017
+ "loss": 3.4193,
1018
+ "step": 16848
1019
+ },
1020
+ {
1021
+ "epoch": 12.31480144404332,
1022
+ "grad_norm": 53.81922149658203,
1023
+ "learning_rate": 8.513807137007677e-05,
1024
+ "loss": 3.3993,
1025
+ "step": 17056
1026
+ },
1027
+ {
1028
+ "epoch": 12.464981949458483,
1029
+ "grad_norm": 9.850875854492188,
1030
+ "learning_rate": 7.61495392108672e-05,
1031
+ "loss": 3.401,
1032
+ "step": 17264
1033
+ },
1034
+ {
1035
+ "epoch": 12.615162454873646,
1036
+ "grad_norm": 36.068912506103516,
1037
+ "learning_rate": 6.762635455369967e-05,
1038
+ "loss": 3.4024,
1039
+ "step": 17472
1040
+ },
1041
+ {
1042
+ "epoch": 12.753068592057762,
1043
+ "eval_g2l_cer": 50.4581,
1044
+ "eval_g2l_gen_len": 4.2626,
1045
+ "eval_g2l_rouge1": 40.828,
1046
+ "eval_g2l_rouge2": 29.681,
1047
+ "eval_g2l_rougeL": 40.7031,
1048
+ "eval_g2l_rougeLsum": 40.6328,
1049
+ "eval_l2ex_cer": 83.6513,
1050
+ "eval_l2ex_gen_len": 25.1151,
1051
+ "eval_l2ex_rouge1": 32.7247,
1052
+ "eval_l2ex_rouge2": 15.913,
1053
+ "eval_l2ex_rougeL": 29.2133,
1054
+ "eval_l2ex_rougeLsum": 29.2625,
1055
+ "eval_l2g_cer": 76.3987,
1056
+ "eval_l2g_gen_len": 18.6672,
1057
+ "eval_l2g_rouge1": 39.0308,
1058
+ "eval_l2g_rouge2": 25.8759,
1059
+ "eval_l2g_rougeL": 36.9076,
1060
+ "eval_l2g_rougeLsum": 36.965,
1061
+ "eval_loss": 3.4478375911712646,
1062
+ "eval_runtime": 94.7036,
1063
+ "eval_samples_per_second": 104.758,
1064
+ "eval_steps_per_second": 0.824,
1065
+ "step": 17663
1066
+ }
1067
+ ],
1068
+ "logging_steps": 208,
1069
+ "max_steps": 20775,
1070
+ "num_input_tokens_seen": 0,
1071
+ "num_train_epochs": 15,
1072
+ "save_steps": 1039,
1073
+ "total_flos": 1.0504606235964211e+17,
1074
+ "train_batch_size": 64,
1075
+ "trial_name": null,
1076
+ "trial_params": null
1077
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888249d5ab0942a44644bfe9bccad874bd102c3431bd18c1f8182e381a5f0379
3
+ size 5176