sheepy928 commited on
Commit
afad424
1 Parent(s): 19ab00a

Training in progress, step 16000, checkpoint

Browse files
checkpoint-16000/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.42.4",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-16000/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": "4.42.4"
6
+ }
checkpoint-16000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e724719905cd0e560b4dd5aa3fe79228b05507520c145f5c096453af79138378
3
+ size 891644712
checkpoint-16000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:912d98d5371156a307affb0a4ef2803469fb63668183364c197019d5ed44e0df
3
+ size 1783444794
checkpoint-16000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94f1a071698d4c2d6f8a0cc90ec2737e814a3d150542271db527c7431f0602e
3
+ size 14244
checkpoint-16000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef703c05cc39b8daa8db83aa5ee7db7613af9a8ba41977c0510c078497bfb38a
3
+ size 1064
checkpoint-16000/special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
checkpoint-16000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-16000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16000/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
+ "32000": {
28
+ "content": "<extra_id_99>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<extra_id_98>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<extra_id_97>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "<extra_id_96>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<extra_id_95>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<extra_id_94>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "<extra_id_93>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "<extra_id_92>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "<extra_id_91>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "<extra_id_90>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "<extra_id_89>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "<extra_id_88>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "<extra_id_87>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "<extra_id_86>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "<extra_id_85>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "<extra_id_84>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32016": {
156
+ "content": "<extra_id_83>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "32017": {
164
+ "content": "<extra_id_82>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "32018": {
172
+ "content": "<extra_id_81>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "32019": {
180
+ "content": "<extra_id_80>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "32020": {
188
+ "content": "<extra_id_79>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "32021": {
196
+ "content": "<extra_id_78>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "32022": {
204
+ "content": "<extra_id_77>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "32023": {
212
+ "content": "<extra_id_76>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "32024": {
220
+ "content": "<extra_id_75>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "32025": {
228
+ "content": "<extra_id_74>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "32026": {
236
+ "content": "<extra_id_73>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32027": {
244
+ "content": "<extra_id_72>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "32028": {
252
+ "content": "<extra_id_71>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32029": {
260
+ "content": "<extra_id_70>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "32030": {
268
+ "content": "<extra_id_69>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "32031": {
276
+ "content": "<extra_id_68>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "32032": {
284
+ "content": "<extra_id_67>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "32033": {
292
+ "content": "<extra_id_66>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "32034": {
300
+ "content": "<extra_id_65>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "32035": {
308
+ "content": "<extra_id_64>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "32036": {
316
+ "content": "<extra_id_63>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "32037": {
324
+ "content": "<extra_id_62>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "32038": {
332
+ "content": "<extra_id_61>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "32039": {
340
+ "content": "<extra_id_60>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "32040": {
348
+ "content": "<extra_id_59>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "32041": {
356
+ "content": "<extra_id_58>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "32042": {
364
+ "content": "<extra_id_57>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "32043": {
372
+ "content": "<extra_id_56>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "32044": {
380
+ "content": "<extra_id_55>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "32045": {
388
+ "content": "<extra_id_54>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "32046": {
396
+ "content": "<extra_id_53>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "32047": {
404
+ "content": "<extra_id_52>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "32048": {
412
+ "content": "<extra_id_51>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "32049": {
420
+ "content": "<extra_id_50>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "32050": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "32051": {
436
+ "content": "<extra_id_48>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "32052": {
444
+ "content": "<extra_id_47>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "32053": {
452
+ "content": "<extra_id_46>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "32054": {
460
+ "content": "<extra_id_45>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "32055": {
468
+ "content": "<extra_id_44>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "32056": {
476
+ "content": "<extra_id_43>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "32057": {
484
+ "content": "<extra_id_42>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "32058": {
492
+ "content": "<extra_id_41>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "32059": {
500
+ "content": "<extra_id_40>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "32060": {
508
+ "content": "<extra_id_39>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "32061": {
516
+ "content": "<extra_id_38>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "32062": {
524
+ "content": "<extra_id_37>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "32063": {
532
+ "content": "<extra_id_36>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "32064": {
540
+ "content": "<extra_id_35>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "32065": {
548
+ "content": "<extra_id_34>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "32066": {
556
+ "content": "<extra_id_33>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "32067": {
564
+ "content": "<extra_id_32>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "32068": {
572
+ "content": "<extra_id_31>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "32069": {
580
+ "content": "<extra_id_30>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "32070": {
588
+ "content": "<extra_id_29>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "32071": {
596
+ "content": "<extra_id_28>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "32072": {
604
+ "content": "<extra_id_27>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "32073": {
612
+ "content": "<extra_id_26>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "32074": {
620
+ "content": "<extra_id_25>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "32075": {
628
+ "content": "<extra_id_24>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "32076": {
636
+ "content": "<extra_id_23>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "32077": {
644
+ "content": "<extra_id_22>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "32078": {
652
+ "content": "<extra_id_21>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "32079": {
660
+ "content": "<extra_id_20>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "32080": {
668
+ "content": "<extra_id_19>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "32081": {
676
+ "content": "<extra_id_18>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "32082": {
684
+ "content": "<extra_id_17>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "32083": {
692
+ "content": "<extra_id_16>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "32084": {
700
+ "content": "<extra_id_15>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "32085": {
708
+ "content": "<extra_id_14>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "32086": {
716
+ "content": "<extra_id_13>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "32087": {
724
+ "content": "<extra_id_12>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "32088": {
732
+ "content": "<extra_id_11>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "32089": {
740
+ "content": "<extra_id_10>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "32090": {
748
+ "content": "<extra_id_9>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "32091": {
756
+ "content": "<extra_id_8>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "32092": {
764
+ "content": "<extra_id_7>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "32093": {
772
+ "content": "<extra_id_6>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "32094": {
780
+ "content": "<extra_id_5>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "32095": {
788
+ "content": "<extra_id_4>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "32096": {
796
+ "content": "<extra_id_3>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "32097": {
804
+ "content": "<extra_id_2>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "32098": {
812
+ "content": "<extra_id_1>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "32099": {
820
+ "content": "<extra_id_0>",
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
+ }
checkpoint-16000/trainer_state.json ADDED
@@ -0,0 +1,1205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6973804646297346,
5
+ "eval_steps": 4000,
6
+ "global_step": 16000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004358627903935841,
13
+ "grad_norm": 30.40549087524414,
14
+ "learning_rate": 9.991544261866365e-07,
15
+ "loss": 9.7914,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.008717255807871681,
20
+ "grad_norm": 23.055740356445312,
21
+ "learning_rate": 9.982827006058492e-07,
22
+ "loss": 8.5435,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.013075883711807523,
27
+ "grad_norm": 16.28481674194336,
28
+ "learning_rate": 9.97410975025062e-07,
29
+ "loss": 7.9154,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.017434511615743362,
34
+ "grad_norm": 21.263378143310547,
35
+ "learning_rate": 9.96539249444275e-07,
36
+ "loss": 7.3876,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.021793139519679205,
41
+ "grad_norm": 25.245298385620117,
42
+ "learning_rate": 9.956675238634877e-07,
43
+ "loss": 6.3013,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.026151767423615045,
48
+ "grad_norm": 11.57956314086914,
49
+ "learning_rate": 9.947957982827006e-07,
50
+ "loss": 5.6204,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.03051039532755089,
55
+ "grad_norm": 12.328071594238281,
56
+ "learning_rate": 9.939240727019133e-07,
57
+ "loss": 5.0561,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.034869023231486725,
62
+ "grad_norm": 6.695566654205322,
63
+ "learning_rate": 9.930523471211262e-07,
64
+ "loss": 4.6239,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.03922765113542257,
69
+ "grad_norm": 5.218314170837402,
70
+ "learning_rate": 9.921806215403392e-07,
71
+ "loss": 4.3892,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.04358627903935841,
76
+ "grad_norm": 3.0057296752929688,
77
+ "learning_rate": 9.913088959595519e-07,
78
+ "loss": 4.2331,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.04794490694329425,
83
+ "grad_norm": 5.0231475830078125,
84
+ "learning_rate": 9.904371703787648e-07,
85
+ "loss": 4.1711,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.05230353484723009,
90
+ "grad_norm": 2.6531741619110107,
91
+ "learning_rate": 9.895654447979775e-07,
92
+ "loss": 4.0637,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.05666216275116593,
97
+ "grad_norm": 2.5700411796569824,
98
+ "learning_rate": 9.887024364729981e-07,
99
+ "loss": 3.99,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.06102079065510178,
104
+ "grad_norm": 2.2256696224212646,
105
+ "learning_rate": 9.87830710892211e-07,
106
+ "loss": 4.0391,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.06537941855903762,
111
+ "grad_norm": 2.429391860961914,
112
+ "learning_rate": 9.86967702567232e-07,
113
+ "loss": 4.0632,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.06973804646297345,
118
+ "grad_norm": 2.8544466495513916,
119
+ "learning_rate": 9.860959769864446e-07,
120
+ "loss": 4.0077,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.0740966743669093,
125
+ "grad_norm": 2.9580471515655518,
126
+ "learning_rate": 9.852329686614652e-07,
127
+ "loss": 3.981,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.07845530227084514,
132
+ "grad_norm": 2.4251883029937744,
133
+ "learning_rate": 9.84369960336486e-07,
134
+ "loss": 3.9854,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.08281393017478098,
139
+ "grad_norm": 3.6600637435913086,
140
+ "learning_rate": 9.834982347556988e-07,
141
+ "loss": 3.9396,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.08717255807871682,
146
+ "grad_norm": 2.000615358352661,
147
+ "learning_rate": 9.826265091749117e-07,
148
+ "loss": 3.9047,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.09153118598265265,
153
+ "grad_norm": 2.1824817657470703,
154
+ "learning_rate": 9.817547835941246e-07,
155
+ "loss": 3.9306,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.0958898138865885,
160
+ "grad_norm": 2.6124613285064697,
161
+ "learning_rate": 9.809004925249532e-07,
162
+ "loss": 3.9145,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.10024844179052435,
167
+ "grad_norm": 2.304738998413086,
168
+ "learning_rate": 9.80028766944166e-07,
169
+ "loss": 3.9333,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.10460706969446018,
174
+ "grad_norm": 2.216799020767212,
175
+ "learning_rate": 9.791570413633788e-07,
176
+ "loss": 3.8542,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.10896569759839603,
181
+ "grad_norm": 2.139524221420288,
182
+ "learning_rate": 9.782853157825915e-07,
183
+ "loss": 3.8202,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.11332432550233186,
188
+ "grad_norm": 2.912883996963501,
189
+ "learning_rate": 9.774223074576124e-07,
190
+ "loss": 3.8677,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.1176829534062677,
195
+ "grad_norm": 2.124760389328003,
196
+ "learning_rate": 9.76550581876825e-07,
197
+ "loss": 3.8609,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.12204158131020355,
202
+ "grad_norm": 1.7955399751663208,
203
+ "learning_rate": 9.756875735518457e-07,
204
+ "loss": 3.8286,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.1264002092141394,
209
+ "grad_norm": 2.2948408126831055,
210
+ "learning_rate": 9.748158479710586e-07,
211
+ "loss": 3.8297,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.13075883711807523,
216
+ "grad_norm": 1.8445340394973755,
217
+ "learning_rate": 9.739441223902716e-07,
218
+ "loss": 3.8535,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.13511746502201108,
223
+ "grad_norm": 1.911111831665039,
224
+ "learning_rate": 9.730723968094843e-07,
225
+ "loss": 3.8011,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.1394760929259469,
230
+ "grad_norm": 1.8173906803131104,
231
+ "learning_rate": 9.722006712286972e-07,
232
+ "loss": 3.8245,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.14383472082988275,
237
+ "grad_norm": NaN,
238
+ "learning_rate": 9.713376629037178e-07,
239
+ "loss": 3.8505,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.1481933487338186,
244
+ "grad_norm": 1.7375200986862183,
245
+ "learning_rate": 9.704659373229307e-07,
246
+ "loss": 3.8695,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.15255197663775444,
251
+ "grad_norm": 1.8474202156066895,
252
+ "learning_rate": 9.695942117421434e-07,
253
+ "loss": 3.7777,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.15691060454169029,
258
+ "grad_norm": 1.6612401008605957,
259
+ "learning_rate": 9.687224861613564e-07,
260
+ "loss": 3.7772,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.1612692324456261,
265
+ "grad_norm": 2.0957448482513428,
266
+ "learning_rate": 9.678507605805693e-07,
267
+ "loss": 3.8124,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.16562786034956195,
272
+ "grad_norm": 1.9771664142608643,
273
+ "learning_rate": 9.6698775225559e-07,
274
+ "loss": 3.8018,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.1699864882534978,
279
+ "grad_norm": 1.731178641319275,
280
+ "learning_rate": 9.661247439306106e-07,
281
+ "loss": 3.8308,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.17434511615743364,
286
+ "grad_norm": 3.0937631130218506,
287
+ "learning_rate": 9.652530183498235e-07,
288
+ "loss": 3.8204,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.17434511615743364,
293
+ "eval_gen_len": 258.3977,
294
+ "eval_loss": 3.743095874786377,
295
+ "eval_rouge1": 11.0785,
296
+ "eval_rouge2": 1.4258,
297
+ "eval_rougeL": 9.2011,
298
+ "eval_rougeLsum": 9.7537,
299
+ "eval_runtime": 1000.5304,
300
+ "eval_samples_per_second": 5.443,
301
+ "eval_steps_per_second": 0.086,
302
+ "step": 4000
303
+ },
304
+ {
305
+ "epoch": 0.1787037440613695,
306
+ "grad_norm": 1.7788825035095215,
307
+ "learning_rate": 9.643900100248441e-07,
308
+ "loss": 3.8099,
309
+ "step": 4100
310
+ },
311
+ {
312
+ "epoch": 0.1830623719653053,
313
+ "grad_norm": 1.9720195531845093,
314
+ "learning_rate": 9.635182844440568e-07,
315
+ "loss": 3.7094,
316
+ "step": 4200
317
+ },
318
+ {
319
+ "epoch": 0.18742099986924116,
320
+ "grad_norm": 1.9566844701766968,
321
+ "learning_rate": 9.626465588632697e-07,
322
+ "loss": 3.7826,
323
+ "step": 4300
324
+ },
325
+ {
326
+ "epoch": 0.191779627773177,
327
+ "grad_norm": 1.6677696704864502,
328
+ "learning_rate": 9.617748332824827e-07,
329
+ "loss": 3.7683,
330
+ "step": 4400
331
+ },
332
+ {
333
+ "epoch": 0.19613825567711285,
334
+ "grad_norm": 1.7738280296325684,
335
+ "learning_rate": 9.609031077016956e-07,
336
+ "loss": 3.7828,
337
+ "step": 4500
338
+ },
339
+ {
340
+ "epoch": 0.2004968835810487,
341
+ "grad_norm": 1.6880650520324707,
342
+ "learning_rate": 9.600313821209083e-07,
343
+ "loss": 3.7524,
344
+ "step": 4600
345
+ },
346
+ {
347
+ "epoch": 0.20485551148498451,
348
+ "grad_norm": 2.1983208656311035,
349
+ "learning_rate": 9.591596565401212e-07,
350
+ "loss": 3.752,
351
+ "step": 4700
352
+ },
353
+ {
354
+ "epoch": 0.20921413938892036,
355
+ "grad_norm": 1.9678415060043335,
356
+ "learning_rate": 9.582966482151418e-07,
357
+ "loss": 3.7699,
358
+ "step": 4800
359
+ },
360
+ {
361
+ "epoch": 0.2135727672928562,
362
+ "grad_norm": 2.111438512802124,
363
+ "learning_rate": 9.574336398901625e-07,
364
+ "loss": 3.7878,
365
+ "step": 4900
366
+ },
367
+ {
368
+ "epoch": 0.21793139519679205,
369
+ "grad_norm": 1.5860246419906616,
370
+ "learning_rate": 9.565706315651833e-07,
371
+ "loss": 3.7865,
372
+ "step": 5000
373
+ },
374
+ {
375
+ "epoch": 0.2222900231007279,
376
+ "grad_norm": 1.6452280282974243,
377
+ "learning_rate": 9.55707623240204e-07,
378
+ "loss": 3.7863,
379
+ "step": 5100
380
+ },
381
+ {
382
+ "epoch": 0.22664865100466372,
383
+ "grad_norm": 1.43221116065979,
384
+ "learning_rate": 9.548358976594167e-07,
385
+ "loss": 3.7756,
386
+ "step": 5200
387
+ },
388
+ {
389
+ "epoch": 0.23100727890859957,
390
+ "grad_norm": 1.6508175134658813,
391
+ "learning_rate": 9.539641720786296e-07,
392
+ "loss": 3.7635,
393
+ "step": 5300
394
+ },
395
+ {
396
+ "epoch": 0.2353659068125354,
397
+ "grad_norm": 1.3596303462982178,
398
+ "learning_rate": 9.530924464978425e-07,
399
+ "loss": 3.8022,
400
+ "step": 5400
401
+ },
402
+ {
403
+ "epoch": 0.23972453471647126,
404
+ "grad_norm": 1.434622049331665,
405
+ "learning_rate": 9.522294381728631e-07,
406
+ "loss": 3.8525,
407
+ "step": 5500
408
+ },
409
+ {
410
+ "epoch": 0.2440831626204071,
411
+ "grad_norm": 1.3105734586715698,
412
+ "learning_rate": 9.51357712592076e-07,
413
+ "loss": 3.8133,
414
+ "step": 5600
415
+ },
416
+ {
417
+ "epoch": 0.24844179052434293,
418
+ "grad_norm": 1.3989108800888062,
419
+ "learning_rate": 9.504859870112888e-07,
420
+ "loss": 3.7857,
421
+ "step": 5700
422
+ },
423
+ {
424
+ "epoch": 0.2528004184282788,
425
+ "grad_norm": 0.8452894687652588,
426
+ "learning_rate": 9.496229786863095e-07,
427
+ "loss": 3.7578,
428
+ "step": 5800
429
+ },
430
+ {
431
+ "epoch": 0.2571590463322146,
432
+ "grad_norm": 1.7360140085220337,
433
+ "learning_rate": 9.487686876171381e-07,
434
+ "loss": 3.7573,
435
+ "step": 5900
436
+ },
437
+ {
438
+ "epoch": 0.26151767423615047,
439
+ "grad_norm": 1.5747486352920532,
440
+ "learning_rate": 9.479056792921588e-07,
441
+ "loss": 3.7993,
442
+ "step": 6000
443
+ },
444
+ {
445
+ "epoch": 0.2658763021400863,
446
+ "grad_norm": 1.6522992849349976,
447
+ "learning_rate": 9.470426709671795e-07,
448
+ "loss": 3.7737,
449
+ "step": 6100
450
+ },
451
+ {
452
+ "epoch": 0.27023493004402216,
453
+ "grad_norm": 2.4300875663757324,
454
+ "learning_rate": 9.461709453863923e-07,
455
+ "loss": 3.7746,
456
+ "step": 6200
457
+ },
458
+ {
459
+ "epoch": 0.274593557947958,
460
+ "grad_norm": 1.9024791717529297,
461
+ "learning_rate": 9.452992198056051e-07,
462
+ "loss": 3.786,
463
+ "step": 6300
464
+ },
465
+ {
466
+ "epoch": 0.2789521858518938,
467
+ "grad_norm": 1.8614801168441772,
468
+ "learning_rate": 9.444274942248179e-07,
469
+ "loss": 3.8174,
470
+ "step": 6400
471
+ },
472
+ {
473
+ "epoch": 0.28331081375582967,
474
+ "grad_norm": 2.356868028640747,
475
+ "learning_rate": 9.435644858998388e-07,
476
+ "loss": 3.804,
477
+ "step": 6500
478
+ },
479
+ {
480
+ "epoch": 0.2876694416597655,
481
+ "grad_norm": 2.2077884674072266,
482
+ "learning_rate": 9.427014775748594e-07,
483
+ "loss": 3.7839,
484
+ "step": 6600
485
+ },
486
+ {
487
+ "epoch": 0.29202806956370136,
488
+ "grad_norm": 3.3564858436584473,
489
+ "learning_rate": 9.4183846924988e-07,
490
+ "loss": 3.7923,
491
+ "step": 6700
492
+ },
493
+ {
494
+ "epoch": 0.2963866974676372,
495
+ "grad_norm": 2.885087013244629,
496
+ "learning_rate": 9.409667436690929e-07,
497
+ "loss": 3.8136,
498
+ "step": 6800
499
+ },
500
+ {
501
+ "epoch": 0.300745325371573,
502
+ "grad_norm": 3.5900139808654785,
503
+ "learning_rate": 9.400950180883058e-07,
504
+ "loss": 3.8064,
505
+ "step": 6900
506
+ },
507
+ {
508
+ "epoch": 0.3051039532755089,
509
+ "grad_norm": 3.0556740760803223,
510
+ "learning_rate": 9.392320097633265e-07,
511
+ "loss": 3.7845,
512
+ "step": 7000
513
+ },
514
+ {
515
+ "epoch": 0.3094625811794447,
516
+ "grad_norm": 3.6052465438842773,
517
+ "learning_rate": 9.383602841825393e-07,
518
+ "loss": 3.7735,
519
+ "step": 7100
520
+ },
521
+ {
522
+ "epoch": 0.31382120908338057,
523
+ "grad_norm": 3.893676519393921,
524
+ "learning_rate": 9.374885586017521e-07,
525
+ "loss": 3.7444,
526
+ "step": 7200
527
+ },
528
+ {
529
+ "epoch": 0.3181798369873164,
530
+ "grad_norm": 3.3053371906280518,
531
+ "learning_rate": 9.366168330209649e-07,
532
+ "loss": 3.7802,
533
+ "step": 7300
534
+ },
535
+ {
536
+ "epoch": 0.3225384648912522,
537
+ "grad_norm": 3.144166946411133,
538
+ "learning_rate": 9.357451074401778e-07,
539
+ "loss": 3.7388,
540
+ "step": 7400
541
+ },
542
+ {
543
+ "epoch": 0.3268970927951881,
544
+ "grad_norm": 3.3398513793945312,
545
+ "learning_rate": 9.348733818593906e-07,
546
+ "loss": 3.8147,
547
+ "step": 7500
548
+ },
549
+ {
550
+ "epoch": 0.3312557206991239,
551
+ "grad_norm": 2.581552267074585,
552
+ "learning_rate": 9.340016562786035e-07,
553
+ "loss": 3.7542,
554
+ "step": 7600
555
+ },
556
+ {
557
+ "epoch": 0.3356143486030598,
558
+ "grad_norm": 2.9723496437072754,
559
+ "learning_rate": 9.331299306978163e-07,
560
+ "loss": 3.7923,
561
+ "step": 7700
562
+ },
563
+ {
564
+ "epoch": 0.3399729765069956,
565
+ "grad_norm": 3.501049757003784,
566
+ "learning_rate": 9.322582051170291e-07,
567
+ "loss": 3.7978,
568
+ "step": 7800
569
+ },
570
+ {
571
+ "epoch": 0.3443316044109314,
572
+ "grad_norm": 3.292762279510498,
573
+ "learning_rate": 9.313864795362419e-07,
574
+ "loss": 3.7684,
575
+ "step": 7900
576
+ },
577
+ {
578
+ "epoch": 0.3486902323148673,
579
+ "grad_norm": 7.055439472198486,
580
+ "learning_rate": 9.305409057228783e-07,
581
+ "loss": 3.8167,
582
+ "step": 8000
583
+ },
584
+ {
585
+ "epoch": 0.3486902323148673,
586
+ "eval_gen_len": 182.3386,
587
+ "eval_loss": 3.720294952392578,
588
+ "eval_rouge1": 12.7469,
589
+ "eval_rouge2": 1.7143,
590
+ "eval_rougeL": 10.3719,
591
+ "eval_rougeLsum": 11.2293,
592
+ "eval_runtime": 976.3587,
593
+ "eval_samples_per_second": 5.578,
594
+ "eval_steps_per_second": 0.088,
595
+ "step": 8000
596
+ },
597
+ {
598
+ "epoch": 0.3530488602188031,
599
+ "grad_norm": 0.0,
600
+ "learning_rate": 9.296691801420912e-07,
601
+ "loss": 3.7368,
602
+ "step": 8100
603
+ },
604
+ {
605
+ "epoch": 0.357407488122739,
606
+ "grad_norm": 0.0,
607
+ "learning_rate": 9.288148890729198e-07,
608
+ "loss": 3.8094,
609
+ "step": 8200
610
+ },
611
+ {
612
+ "epoch": 0.3617661160266748,
613
+ "grad_norm": 0.0,
614
+ "learning_rate": 9.279431634921326e-07,
615
+ "loss": 3.806,
616
+ "step": 8300
617
+ },
618
+ {
619
+ "epoch": 0.3661247439306106,
620
+ "grad_norm": 0.0,
621
+ "learning_rate": 9.270714379113454e-07,
622
+ "loss": 3.7526,
623
+ "step": 8400
624
+ },
625
+ {
626
+ "epoch": 0.3704833718345465,
627
+ "grad_norm": 0.0,
628
+ "learning_rate": 9.262084295863662e-07,
629
+ "loss": 3.7902,
630
+ "step": 8500
631
+ },
632
+ {
633
+ "epoch": 0.3748419997384823,
634
+ "grad_norm": 0.0,
635
+ "learning_rate": 9.25336704005579e-07,
636
+ "loss": 3.8063,
637
+ "step": 8600
638
+ },
639
+ {
640
+ "epoch": 0.3792006276424182,
641
+ "grad_norm": 0.0,
642
+ "learning_rate": 9.244649784247919e-07,
643
+ "loss": 3.79,
644
+ "step": 8700
645
+ },
646
+ {
647
+ "epoch": 0.383559255546354,
648
+ "grad_norm": 0.0,
649
+ "learning_rate": 9.235932528440047e-07,
650
+ "loss": 3.8446,
651
+ "step": 8800
652
+ },
653
+ {
654
+ "epoch": 0.3879178834502898,
655
+ "grad_norm": 0.0,
656
+ "learning_rate": 9.227302445190254e-07,
657
+ "loss": 3.8016,
658
+ "step": 8900
659
+ },
660
+ {
661
+ "epoch": 0.3922765113542257,
662
+ "grad_norm": 0.0,
663
+ "learning_rate": 9.218585189382382e-07,
664
+ "loss": 3.789,
665
+ "step": 9000
666
+ },
667
+ {
668
+ "epoch": 0.3966351392581615,
669
+ "grad_norm": 0.0,
670
+ "learning_rate": 9.20986793357451e-07,
671
+ "loss": 3.7935,
672
+ "step": 9100
673
+ },
674
+ {
675
+ "epoch": 0.4009937671620974,
676
+ "grad_norm": 0.0,
677
+ "learning_rate": 9.201150677766638e-07,
678
+ "loss": 3.7818,
679
+ "step": 9200
680
+ },
681
+ {
682
+ "epoch": 0.4053523950660332,
683
+ "grad_norm": 0.0,
684
+ "learning_rate": 9.192520594516846e-07,
685
+ "loss": 3.8178,
686
+ "step": 9300
687
+ },
688
+ {
689
+ "epoch": 0.40971102296996903,
690
+ "grad_norm": 0.0,
691
+ "learning_rate": 9.183803338708975e-07,
692
+ "loss": 3.7768,
693
+ "step": 9400
694
+ },
695
+ {
696
+ "epoch": 0.4140696508739049,
697
+ "grad_norm": 0.0,
698
+ "learning_rate": 9.175086082901103e-07,
699
+ "loss": 3.8288,
700
+ "step": 9500
701
+ },
702
+ {
703
+ "epoch": 0.4184282787778407,
704
+ "grad_norm": 0.0,
705
+ "learning_rate": 9.166455999651309e-07,
706
+ "loss": 3.7903,
707
+ "step": 9600
708
+ },
709
+ {
710
+ "epoch": 0.4227869066817766,
711
+ "grad_norm": 0.0,
712
+ "learning_rate": 9.157738743843437e-07,
713
+ "loss": 3.8076,
714
+ "step": 9700
715
+ },
716
+ {
717
+ "epoch": 0.4271455345857124,
718
+ "grad_norm": 0.0,
719
+ "learning_rate": 9.149108660593646e-07,
720
+ "loss": 3.77,
721
+ "step": 9800
722
+ },
723
+ {
724
+ "epoch": 0.43150416248964824,
725
+ "grad_norm": 0.0,
726
+ "learning_rate": 9.140478577343852e-07,
727
+ "loss": 3.7931,
728
+ "step": 9900
729
+ },
730
+ {
731
+ "epoch": 0.4358627903935841,
732
+ "grad_norm": 0.0,
733
+ "learning_rate": 9.13176132153598e-07,
734
+ "loss": 3.7802,
735
+ "step": 10000
736
+ },
737
+ {
738
+ "epoch": 0.44022141829751993,
739
+ "grad_norm": 0.0,
740
+ "learning_rate": 9.123044065728108e-07,
741
+ "loss": 3.8273,
742
+ "step": 10100
743
+ },
744
+ {
745
+ "epoch": 0.4445800462014558,
746
+ "grad_norm": 0.0,
747
+ "learning_rate": 9.114326809920236e-07,
748
+ "loss": 3.7708,
749
+ "step": 10200
750
+ },
751
+ {
752
+ "epoch": 0.4489386741053916,
753
+ "grad_norm": 0.0,
754
+ "learning_rate": 9.105609554112364e-07,
755
+ "loss": 3.7881,
756
+ "step": 10300
757
+ },
758
+ {
759
+ "epoch": 0.45329730200932744,
760
+ "grad_norm": 0.0,
761
+ "learning_rate": 9.096892298304494e-07,
762
+ "loss": 3.7923,
763
+ "step": 10400
764
+ },
765
+ {
766
+ "epoch": 0.4576559299132633,
767
+ "grad_norm": 0.0,
768
+ "learning_rate": 9.088175042496622e-07,
769
+ "loss": 3.7904,
770
+ "step": 10500
771
+ },
772
+ {
773
+ "epoch": 0.46201455781719913,
774
+ "grad_norm": 0.0,
775
+ "learning_rate": 9.07945778668875e-07,
776
+ "loss": 3.7758,
777
+ "step": 10600
778
+ },
779
+ {
780
+ "epoch": 0.466373185721135,
781
+ "grad_norm": 0.0,
782
+ "learning_rate": 9.070740530880878e-07,
783
+ "loss": 3.7181,
784
+ "step": 10700
785
+ },
786
+ {
787
+ "epoch": 0.4707318136250708,
788
+ "grad_norm": 0.0,
789
+ "learning_rate": 9.062023275073006e-07,
790
+ "loss": 3.82,
791
+ "step": 10800
792
+ },
793
+ {
794
+ "epoch": 0.47509044152900665,
795
+ "grad_norm": 0.0,
796
+ "learning_rate": 9.053306019265134e-07,
797
+ "loss": 3.7387,
798
+ "step": 10900
799
+ },
800
+ {
801
+ "epoch": 0.4794490694329425,
802
+ "grad_norm": 0.0,
803
+ "learning_rate": 9.044588763457263e-07,
804
+ "loss": 3.8448,
805
+ "step": 11000
806
+ },
807
+ {
808
+ "epoch": 0.48380769733687834,
809
+ "grad_norm": 0.0,
810
+ "learning_rate": 9.035958680207471e-07,
811
+ "loss": 3.785,
812
+ "step": 11100
813
+ },
814
+ {
815
+ "epoch": 0.4881663252408142,
816
+ "grad_norm": 0.0,
817
+ "learning_rate": 9.027241424399599e-07,
818
+ "loss": 3.8292,
819
+ "step": 11200
820
+ },
821
+ {
822
+ "epoch": 0.49252495314475003,
823
+ "grad_norm": 0.0,
824
+ "learning_rate": 9.018611341149805e-07,
825
+ "loss": 3.7867,
826
+ "step": 11300
827
+ },
828
+ {
829
+ "epoch": 0.49688358104868585,
830
+ "grad_norm": 0.0,
831
+ "learning_rate": 9.009981257900013e-07,
832
+ "loss": 3.7749,
833
+ "step": 11400
834
+ },
835
+ {
836
+ "epoch": 0.5012422089526217,
837
+ "grad_norm": 0.0,
838
+ "learning_rate": 9.00135117465022e-07,
839
+ "loss": 3.8242,
840
+ "step": 11500
841
+ },
842
+ {
843
+ "epoch": 0.5056008368565575,
844
+ "grad_norm": 0.0,
845
+ "learning_rate": 8.992808263958506e-07,
846
+ "loss": 3.7584,
847
+ "step": 11600
848
+ },
849
+ {
850
+ "epoch": 0.5099594647604934,
851
+ "grad_norm": 0.0,
852
+ "learning_rate": 8.984091008150634e-07,
853
+ "loss": 3.7408,
854
+ "step": 11700
855
+ },
856
+ {
857
+ "epoch": 0.5143180926644292,
858
+ "grad_norm": 0.0,
859
+ "learning_rate": 8.975373752342762e-07,
860
+ "loss": 3.8061,
861
+ "step": 11800
862
+ },
863
+ {
864
+ "epoch": 0.5186767205683651,
865
+ "grad_norm": 0.0,
866
+ "learning_rate": 8.966743669092969e-07,
867
+ "loss": 3.8047,
868
+ "step": 11900
869
+ },
870
+ {
871
+ "epoch": 0.5230353484723009,
872
+ "grad_norm": 0.0,
873
+ "learning_rate": 8.958113585843177e-07,
874
+ "loss": 3.7662,
875
+ "step": 12000
876
+ },
877
+ {
878
+ "epoch": 0.5230353484723009,
879
+ "eval_gen_len": 182.7448,
880
+ "eval_loss": 3.7201850414276123,
881
+ "eval_rouge1": 12.752,
882
+ "eval_rouge2": 1.7119,
883
+ "eval_rougeL": 10.3684,
884
+ "eval_rougeLsum": 11.228,
885
+ "eval_runtime": 973.1101,
886
+ "eval_samples_per_second": 5.596,
887
+ "eval_steps_per_second": 0.088,
888
+ "step": 12000
889
+ },
890
+ {
891
+ "epoch": 0.5273939763762368,
892
+ "grad_norm": 0.0,
893
+ "learning_rate": 8.949483502593384e-07,
894
+ "loss": 3.7775,
895
+ "step": 12100
896
+ },
897
+ {
898
+ "epoch": 0.5317526042801726,
899
+ "grad_norm": 0.0,
900
+ "learning_rate": 8.94085341934359e-07,
901
+ "loss": 3.7863,
902
+ "step": 12200
903
+ },
904
+ {
905
+ "epoch": 0.5361112321841084,
906
+ "grad_norm": 0.0,
907
+ "learning_rate": 8.932136163535718e-07,
908
+ "loss": 3.7689,
909
+ "step": 12300
910
+ },
911
+ {
912
+ "epoch": 0.5404698600880443,
913
+ "grad_norm": 0.0,
914
+ "learning_rate": 8.923418907727846e-07,
915
+ "loss": 3.7787,
916
+ "step": 12400
917
+ },
918
+ {
919
+ "epoch": 0.5448284879919801,
920
+ "grad_norm": 0.0,
921
+ "learning_rate": 8.914701651919974e-07,
922
+ "loss": 3.7484,
923
+ "step": 12500
924
+ },
925
+ {
926
+ "epoch": 0.549187115895916,
927
+ "grad_norm": 0.0,
928
+ "learning_rate": 8.906071568670183e-07,
929
+ "loss": 3.7399,
930
+ "step": 12600
931
+ },
932
+ {
933
+ "epoch": 0.5535457437998518,
934
+ "grad_norm": 0.0,
935
+ "learning_rate": 8.897354312862311e-07,
936
+ "loss": 3.8051,
937
+ "step": 12700
938
+ },
939
+ {
940
+ "epoch": 0.5579043717037876,
941
+ "grad_norm": 0.0,
942
+ "learning_rate": 8.888637057054439e-07,
943
+ "loss": 3.8352,
944
+ "step": 12800
945
+ },
946
+ {
947
+ "epoch": 0.5622629996077235,
948
+ "grad_norm": 0.0,
949
+ "learning_rate": 8.879919801246567e-07,
950
+ "loss": 3.8274,
951
+ "step": 12900
952
+ },
953
+ {
954
+ "epoch": 0.5666216275116593,
955
+ "grad_norm": 0.0,
956
+ "learning_rate": 8.871289717996773e-07,
957
+ "loss": 3.8084,
958
+ "step": 13000
959
+ },
960
+ {
961
+ "epoch": 0.5709802554155952,
962
+ "grad_norm": 0.0,
963
+ "learning_rate": 8.862572462188903e-07,
964
+ "loss": 3.7881,
965
+ "step": 13100
966
+ },
967
+ {
968
+ "epoch": 0.575338883319531,
969
+ "grad_norm": 0.0,
970
+ "learning_rate": 8.85394237893911e-07,
971
+ "loss": 3.7847,
972
+ "step": 13200
973
+ },
974
+ {
975
+ "epoch": 0.5796975112234668,
976
+ "grad_norm": 0.0,
977
+ "learning_rate": 8.845225123131238e-07,
978
+ "loss": 3.8208,
979
+ "step": 13300
980
+ },
981
+ {
982
+ "epoch": 0.5840561391274027,
983
+ "grad_norm": 0.0,
984
+ "learning_rate": 8.836507867323366e-07,
985
+ "loss": 3.8001,
986
+ "step": 13400
987
+ },
988
+ {
989
+ "epoch": 0.5884147670313385,
990
+ "grad_norm": 0.0,
991
+ "learning_rate": 8.827790611515494e-07,
992
+ "loss": 3.7548,
993
+ "step": 13500
994
+ },
995
+ {
996
+ "epoch": 0.5927733949352744,
997
+ "grad_norm": 0.0,
998
+ "learning_rate": 8.819073355707623e-07,
999
+ "loss": 3.7239,
1000
+ "step": 13600
1001
+ },
1002
+ {
1003
+ "epoch": 0.5971320228392102,
1004
+ "grad_norm": 0.0,
1005
+ "learning_rate": 8.810356099899752e-07,
1006
+ "loss": 3.7832,
1007
+ "step": 13700
1008
+ },
1009
+ {
1010
+ "epoch": 0.601490650743146,
1011
+ "grad_norm": 0.0,
1012
+ "learning_rate": 8.80163884409188e-07,
1013
+ "loss": 3.7644,
1014
+ "step": 13800
1015
+ },
1016
+ {
1017
+ "epoch": 0.6058492786470819,
1018
+ "grad_norm": 0.0,
1019
+ "learning_rate": 8.792921588284008e-07,
1020
+ "loss": 3.7871,
1021
+ "step": 13900
1022
+ },
1023
+ {
1024
+ "epoch": 0.6102079065510178,
1025
+ "grad_norm": 0.0,
1026
+ "learning_rate": 8.784204332476136e-07,
1027
+ "loss": 3.7594,
1028
+ "step": 14000
1029
+ },
1030
+ {
1031
+ "epoch": 0.6145665344549536,
1032
+ "grad_norm": 0.0,
1033
+ "learning_rate": 8.775487076668264e-07,
1034
+ "loss": 3.7967,
1035
+ "step": 14100
1036
+ },
1037
+ {
1038
+ "epoch": 0.6189251623588894,
1039
+ "grad_norm": 0.0,
1040
+ "learning_rate": 8.766769820860392e-07,
1041
+ "loss": 3.8017,
1042
+ "step": 14200
1043
+ },
1044
+ {
1045
+ "epoch": 0.6232837902628252,
1046
+ "grad_norm": 0.0,
1047
+ "learning_rate": 8.75805256505252e-07,
1048
+ "loss": 3.7972,
1049
+ "step": 14300
1050
+ },
1051
+ {
1052
+ "epoch": 0.6276424181667611,
1053
+ "grad_norm": 0.0,
1054
+ "learning_rate": 8.74933530924465e-07,
1055
+ "loss": 3.8165,
1056
+ "step": 14400
1057
+ },
1058
+ {
1059
+ "epoch": 0.632001046070697,
1060
+ "grad_norm": 0.0,
1061
+ "learning_rate": 8.740618053436778e-07,
1062
+ "loss": 3.7934,
1063
+ "step": 14500
1064
+ },
1065
+ {
1066
+ "epoch": 0.6363596739746328,
1067
+ "grad_norm": 0.0,
1068
+ "learning_rate": 8.731900797628906e-07,
1069
+ "loss": 3.8056,
1070
+ "step": 14600
1071
+ },
1072
+ {
1073
+ "epoch": 0.6407183018785686,
1074
+ "grad_norm": 0.0,
1075
+ "learning_rate": 8.723270714379113e-07,
1076
+ "loss": 3.7537,
1077
+ "step": 14700
1078
+ },
1079
+ {
1080
+ "epoch": 0.6450769297825044,
1081
+ "grad_norm": 0.0,
1082
+ "learning_rate": 8.714553458571241e-07,
1083
+ "loss": 3.8102,
1084
+ "step": 14800
1085
+ },
1086
+ {
1087
+ "epoch": 0.6494355576864403,
1088
+ "grad_norm": 0.0,
1089
+ "learning_rate": 8.705836202763369e-07,
1090
+ "loss": 3.8053,
1091
+ "step": 14900
1092
+ },
1093
+ {
1094
+ "epoch": 0.6537941855903762,
1095
+ "grad_norm": 0.0,
1096
+ "learning_rate": 8.697206119513577e-07,
1097
+ "loss": 3.7925,
1098
+ "step": 15000
1099
+ },
1100
+ {
1101
+ "epoch": 0.658152813494312,
1102
+ "grad_norm": 0.0,
1103
+ "learning_rate": 8.688576036263784e-07,
1104
+ "loss": 3.7678,
1105
+ "step": 15100
1106
+ },
1107
+ {
1108
+ "epoch": 0.6625114413982478,
1109
+ "grad_norm": 0.0,
1110
+ "learning_rate": 8.679945953013991e-07,
1111
+ "loss": 3.7588,
1112
+ "step": 15200
1113
+ },
1114
+ {
1115
+ "epoch": 0.6668700693021836,
1116
+ "grad_norm": 0.0,
1117
+ "learning_rate": 8.671315869764197e-07,
1118
+ "loss": 3.7971,
1119
+ "step": 15300
1120
+ },
1121
+ {
1122
+ "epoch": 0.6712286972061196,
1123
+ "grad_norm": 0.0,
1124
+ "learning_rate": 8.662598613956325e-07,
1125
+ "loss": 3.8028,
1126
+ "step": 15400
1127
+ },
1128
+ {
1129
+ "epoch": 0.6755873251100554,
1130
+ "grad_norm": 0.0,
1131
+ "learning_rate": 8.653881358148454e-07,
1132
+ "loss": 3.8079,
1133
+ "step": 15500
1134
+ },
1135
+ {
1136
+ "epoch": 0.6799459530139912,
1137
+ "grad_norm": 0.0,
1138
+ "learning_rate": 8.645251274898662e-07,
1139
+ "loss": 3.7807,
1140
+ "step": 15600
1141
+ },
1142
+ {
1143
+ "epoch": 0.684304580917927,
1144
+ "grad_norm": 0.0,
1145
+ "learning_rate": 8.636708364206948e-07,
1146
+ "loss": 3.7709,
1147
+ "step": 15700
1148
+ },
1149
+ {
1150
+ "epoch": 0.6886632088218628,
1151
+ "grad_norm": 0.0,
1152
+ "learning_rate": 8.628078280957154e-07,
1153
+ "loss": 3.835,
1154
+ "step": 15800
1155
+ },
1156
+ {
1157
+ "epoch": 0.6930218367257988,
1158
+ "grad_norm": 0.0,
1159
+ "learning_rate": 8.619361025149282e-07,
1160
+ "loss": 3.7721,
1161
+ "step": 15900
1162
+ },
1163
+ {
1164
+ "epoch": 0.6973804646297346,
1165
+ "grad_norm": 0.0,
1166
+ "learning_rate": 8.61073094189949e-07,
1167
+ "loss": 3.7919,
1168
+ "step": 16000
1169
+ },
1170
+ {
1171
+ "epoch": 0.6973804646297346,
1172
+ "eval_gen_len": 182.7448,
1173
+ "eval_loss": 3.7201850414276123,
1174
+ "eval_rouge1": 12.752,
1175
+ "eval_rouge2": 1.7119,
1176
+ "eval_rougeL": 10.3684,
1177
+ "eval_rougeLsum": 11.228,
1178
+ "eval_runtime": 973.8648,
1179
+ "eval_samples_per_second": 5.592,
1180
+ "eval_steps_per_second": 0.088,
1181
+ "step": 16000
1182
+ }
1183
+ ],
1184
+ "logging_steps": 100,
1185
+ "max_steps": 114715,
1186
+ "num_input_tokens_seen": 0,
1187
+ "num_train_epochs": 5,
1188
+ "save_steps": 4000,
1189
+ "stateful_callbacks": {
1190
+ "TrainerControl": {
1191
+ "args": {
1192
+ "should_epoch_stop": false,
1193
+ "should_evaluate": false,
1194
+ "should_log": false,
1195
+ "should_save": true,
1196
+ "should_training_stop": false
1197
+ },
1198
+ "attributes": {}
1199
+ }
1200
+ },
1201
+ "total_flos": 3.897330499584e+16,
1202
+ "train_batch_size": 4,
1203
+ "trial_name": null,
1204
+ "trial_params": null
1205
+ }
checkpoint-16000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898178f402d363c4fcb6dfdbd636696637ca22db5edb4cd05fe7b9946e7a201e
3
+ size 5240