ai4anshu commited on
Commit
bdb70cd
1 Parent(s): 0dc70e4

Upload 11 files

Browse files
checkpoint-90000/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-t5/t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
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": "4.37.2",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-90000/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": "4.37.2"
6
+ }
checkpoint-90000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea0e7deaeb25baa757b1838f6e406e2dde4a9d3050554542cff8ae4c4a54421
3
+ size 242041896
checkpoint-90000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a0df10091bb1f416601b761079e0d4b3f162bb1548c41bf428e30a6535e985
3
+ size 484163514
checkpoint-90000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39bbb1ee164b03d198776dc30d32da98c69ce64337536757d509ec2b24b3f53
3
+ size 14244
checkpoint-90000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c796aad0b21f6c14f86a4d7b329ad7d4c730ee9fd128d9ca6e92eefc3fc751db
3
+ size 1064
checkpoint-90000/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
+ }
checkpoint-90000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-90000/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": 512,
934
+ "pad_token": "<pad>",
935
+ "tokenizer_class": "T5Tokenizer",
936
+ "unk_token": "<unk>"
937
+ }
checkpoint-90000/trainer_state.json ADDED
@@ -0,0 +1,1231 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 90000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 1.9889333333333336e-05,
14
+ "loss": 0.6763,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.11,
19
+ "learning_rate": 1.9778222222222224e-05,
20
+ "loss": 0.511,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.17,
25
+ "learning_rate": 1.9667333333333334e-05,
26
+ "loss": 0.4773,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.22,
31
+ "learning_rate": 1.9556222222222222e-05,
32
+ "loss": 0.4519,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.28,
37
+ "learning_rate": 1.9445111111111114e-05,
38
+ "loss": 0.4367,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.33,
43
+ "learning_rate": 1.9334e-05,
44
+ "loss": 0.4295,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.39,
49
+ "learning_rate": 1.922288888888889e-05,
50
+ "loss": 0.4105,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.44,
55
+ "learning_rate": 1.911177777777778e-05,
56
+ "loss": 0.4063,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.5,
61
+ "learning_rate": 1.9000666666666666e-05,
62
+ "loss": 0.3997,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.56,
67
+ "learning_rate": 1.8889555555555557e-05,
68
+ "loss": 0.3921,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.61,
73
+ "learning_rate": 1.8778444444444445e-05,
74
+ "loss": 0.3857,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.67,
79
+ "learning_rate": 1.8667333333333337e-05,
80
+ "loss": 0.3852,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.72,
85
+ "learning_rate": 1.8556222222222225e-05,
86
+ "loss": 0.3754,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.78,
91
+ "learning_rate": 1.8445111111111113e-05,
92
+ "loss": 0.373,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.83,
97
+ "learning_rate": 1.8334222222222226e-05,
98
+ "loss": 0.3731,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.89,
103
+ "learning_rate": 1.8223111111111114e-05,
104
+ "loss": 0.3745,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.94,
109
+ "learning_rate": 1.8112222222222224e-05,
110
+ "loss": 0.3698,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 1.0,
115
+ "learning_rate": 1.8001111111111115e-05,
116
+ "loss": 0.3717,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 1.0,
121
+ "eval_gen_len": 14.0401,
122
+ "eval_loss": 0.30105069279670715,
123
+ "eval_rouge1": 0.8165,
124
+ "eval_rouge2": 0.7413,
125
+ "eval_rougeL": 0.8143,
126
+ "eval_rougeLsum": 0.8143,
127
+ "eval_runtime": 2090.1403,
128
+ "eval_samples_per_second": 17.224,
129
+ "eval_steps_per_second": 4.306,
130
+ "step": 9000
131
+ },
132
+ {
133
+ "epoch": 1.06,
134
+ "learning_rate": 1.789e-05,
135
+ "loss": 0.359,
136
+ "step": 9500
137
+ },
138
+ {
139
+ "epoch": 1.11,
140
+ "learning_rate": 1.777888888888889e-05,
141
+ "loss": 0.3557,
142
+ "step": 10000
143
+ },
144
+ {
145
+ "epoch": 1.17,
146
+ "learning_rate": 1.766777777777778e-05,
147
+ "loss": 0.3485,
148
+ "step": 10500
149
+ },
150
+ {
151
+ "epoch": 1.22,
152
+ "learning_rate": 1.7556666666666667e-05,
153
+ "loss": 0.3501,
154
+ "step": 11000
155
+ },
156
+ {
157
+ "epoch": 1.28,
158
+ "learning_rate": 1.744555555555556e-05,
159
+ "loss": 0.3504,
160
+ "step": 11500
161
+ },
162
+ {
163
+ "epoch": 1.33,
164
+ "learning_rate": 1.7334444444444444e-05,
165
+ "loss": 0.3558,
166
+ "step": 12000
167
+ },
168
+ {
169
+ "epoch": 1.39,
170
+ "learning_rate": 1.7223555555555557e-05,
171
+ "loss": 0.3557,
172
+ "step": 12500
173
+ },
174
+ {
175
+ "epoch": 1.44,
176
+ "learning_rate": 1.7112444444444445e-05,
177
+ "loss": 0.3425,
178
+ "step": 13000
179
+ },
180
+ {
181
+ "epoch": 1.5,
182
+ "learning_rate": 1.7001333333333333e-05,
183
+ "loss": 0.3353,
184
+ "step": 13500
185
+ },
186
+ {
187
+ "epoch": 1.56,
188
+ "learning_rate": 1.6890222222222224e-05,
189
+ "loss": 0.3356,
190
+ "step": 14000
191
+ },
192
+ {
193
+ "epoch": 1.61,
194
+ "learning_rate": 1.6779333333333334e-05,
195
+ "loss": 0.3397,
196
+ "step": 14500
197
+ },
198
+ {
199
+ "epoch": 1.67,
200
+ "learning_rate": 1.6668222222222222e-05,
201
+ "loss": 0.3327,
202
+ "step": 15000
203
+ },
204
+ {
205
+ "epoch": 1.72,
206
+ "learning_rate": 1.6557111111111113e-05,
207
+ "loss": 0.343,
208
+ "step": 15500
209
+ },
210
+ {
211
+ "epoch": 1.78,
212
+ "learning_rate": 1.6446e-05,
213
+ "loss": 0.3357,
214
+ "step": 16000
215
+ },
216
+ {
217
+ "epoch": 1.83,
218
+ "learning_rate": 1.6334888888888893e-05,
219
+ "loss": 0.3359,
220
+ "step": 16500
221
+ },
222
+ {
223
+ "epoch": 1.89,
224
+ "learning_rate": 1.6224000000000003e-05,
225
+ "loss": 0.3307,
226
+ "step": 17000
227
+ },
228
+ {
229
+ "epoch": 1.94,
230
+ "learning_rate": 1.611288888888889e-05,
231
+ "loss": 0.337,
232
+ "step": 17500
233
+ },
234
+ {
235
+ "epoch": 2.0,
236
+ "learning_rate": 1.6002000000000004e-05,
237
+ "loss": 0.3255,
238
+ "step": 18000
239
+ },
240
+ {
241
+ "epoch": 2.0,
242
+ "eval_gen_len": 13.8117,
243
+ "eval_loss": 0.2776668965816498,
244
+ "eval_rouge1": 0.8238,
245
+ "eval_rouge2": 0.7501,
246
+ "eval_rougeL": 0.8217,
247
+ "eval_rougeLsum": 0.8217,
248
+ "eval_runtime": 1917.0267,
249
+ "eval_samples_per_second": 18.779,
250
+ "eval_steps_per_second": 4.695,
251
+ "step": 18000
252
+ },
253
+ {
254
+ "epoch": 2.06,
255
+ "learning_rate": 1.5890888888888892e-05,
256
+ "loss": 0.3292,
257
+ "step": 18500
258
+ },
259
+ {
260
+ "epoch": 2.11,
261
+ "learning_rate": 1.577977777777778e-05,
262
+ "loss": 0.3246,
263
+ "step": 19000
264
+ },
265
+ {
266
+ "epoch": 2.17,
267
+ "learning_rate": 1.5668666666666668e-05,
268
+ "loss": 0.3213,
269
+ "step": 19500
270
+ },
271
+ {
272
+ "epoch": 2.22,
273
+ "learning_rate": 1.5557555555555556e-05,
274
+ "loss": 0.3247,
275
+ "step": 20000
276
+ },
277
+ {
278
+ "epoch": 2.28,
279
+ "learning_rate": 1.5446444444444447e-05,
280
+ "loss": 0.3199,
281
+ "step": 20500
282
+ },
283
+ {
284
+ "epoch": 2.33,
285
+ "learning_rate": 1.5335555555555557e-05,
286
+ "loss": 0.3255,
287
+ "step": 21000
288
+ },
289
+ {
290
+ "epoch": 2.39,
291
+ "learning_rate": 1.5224444444444447e-05,
292
+ "loss": 0.3236,
293
+ "step": 21500
294
+ },
295
+ {
296
+ "epoch": 2.44,
297
+ "learning_rate": 1.5113333333333335e-05,
298
+ "loss": 0.3151,
299
+ "step": 22000
300
+ },
301
+ {
302
+ "epoch": 2.5,
303
+ "learning_rate": 1.5002222222222223e-05,
304
+ "loss": 0.3174,
305
+ "step": 22500
306
+ },
307
+ {
308
+ "epoch": 2.56,
309
+ "learning_rate": 1.4891111111111111e-05,
310
+ "loss": 0.3197,
311
+ "step": 23000
312
+ },
313
+ {
314
+ "epoch": 2.61,
315
+ "learning_rate": 1.478e-05,
316
+ "loss": 0.3206,
317
+ "step": 23500
318
+ },
319
+ {
320
+ "epoch": 2.67,
321
+ "learning_rate": 1.466888888888889e-05,
322
+ "loss": 0.3182,
323
+ "step": 24000
324
+ },
325
+ {
326
+ "epoch": 2.72,
327
+ "learning_rate": 1.4558e-05,
328
+ "loss": 0.3156,
329
+ "step": 24500
330
+ },
331
+ {
332
+ "epoch": 2.78,
333
+ "learning_rate": 1.444688888888889e-05,
334
+ "loss": 0.321,
335
+ "step": 25000
336
+ },
337
+ {
338
+ "epoch": 2.83,
339
+ "learning_rate": 1.433577777777778e-05,
340
+ "loss": 0.3166,
341
+ "step": 25500
342
+ },
343
+ {
344
+ "epoch": 2.89,
345
+ "learning_rate": 1.422466666666667e-05,
346
+ "loss": 0.3139,
347
+ "step": 26000
348
+ },
349
+ {
350
+ "epoch": 2.94,
351
+ "learning_rate": 1.4113555555555556e-05,
352
+ "loss": 0.314,
353
+ "step": 26500
354
+ },
355
+ {
356
+ "epoch": 3.0,
357
+ "learning_rate": 1.4002444444444446e-05,
358
+ "loss": 0.3163,
359
+ "step": 27000
360
+ },
361
+ {
362
+ "epoch": 3.0,
363
+ "eval_gen_len": 13.8253,
364
+ "eval_loss": 0.2683161795139313,
365
+ "eval_rouge1": 0.8272,
366
+ "eval_rouge2": 0.7541,
367
+ "eval_rougeL": 0.8252,
368
+ "eval_rougeLsum": 0.8251,
369
+ "eval_runtime": 2009.2942,
370
+ "eval_samples_per_second": 17.917,
371
+ "eval_steps_per_second": 4.479,
372
+ "step": 27000
373
+ },
374
+ {
375
+ "epoch": 3.06,
376
+ "learning_rate": 1.3891333333333334e-05,
377
+ "loss": 0.3092,
378
+ "step": 27500
379
+ },
380
+ {
381
+ "epoch": 3.11,
382
+ "learning_rate": 1.3780222222222223e-05,
383
+ "loss": 0.3068,
384
+ "step": 28000
385
+ },
386
+ {
387
+ "epoch": 3.17,
388
+ "learning_rate": 1.3669333333333335e-05,
389
+ "loss": 0.3124,
390
+ "step": 28500
391
+ },
392
+ {
393
+ "epoch": 3.22,
394
+ "learning_rate": 1.3558222222222223e-05,
395
+ "loss": 0.3059,
396
+ "step": 29000
397
+ },
398
+ {
399
+ "epoch": 3.28,
400
+ "learning_rate": 1.3447111111111113e-05,
401
+ "loss": 0.3098,
402
+ "step": 29500
403
+ },
404
+ {
405
+ "epoch": 3.33,
406
+ "learning_rate": 1.3336e-05,
407
+ "loss": 0.3053,
408
+ "step": 30000
409
+ },
410
+ {
411
+ "epoch": 3.39,
412
+ "learning_rate": 1.3224888888888889e-05,
413
+ "loss": 0.3083,
414
+ "step": 30500
415
+ },
416
+ {
417
+ "epoch": 3.44,
418
+ "learning_rate": 1.3113777777777779e-05,
419
+ "loss": 0.3095,
420
+ "step": 31000
421
+ },
422
+ {
423
+ "epoch": 3.5,
424
+ "learning_rate": 1.3002666666666668e-05,
425
+ "loss": 0.3059,
426
+ "step": 31500
427
+ },
428
+ {
429
+ "epoch": 3.56,
430
+ "learning_rate": 1.2891555555555556e-05,
431
+ "loss": 0.3038,
432
+ "step": 32000
433
+ },
434
+ {
435
+ "epoch": 3.61,
436
+ "learning_rate": 1.2780666666666668e-05,
437
+ "loss": 0.3116,
438
+ "step": 32500
439
+ },
440
+ {
441
+ "epoch": 3.67,
442
+ "learning_rate": 1.2669555555555558e-05,
443
+ "loss": 0.3032,
444
+ "step": 33000
445
+ },
446
+ {
447
+ "epoch": 3.72,
448
+ "learning_rate": 1.2558666666666667e-05,
449
+ "loss": 0.3046,
450
+ "step": 33500
451
+ },
452
+ {
453
+ "epoch": 3.78,
454
+ "learning_rate": 1.2447555555555557e-05,
455
+ "loss": 0.3021,
456
+ "step": 34000
457
+ },
458
+ {
459
+ "epoch": 3.83,
460
+ "learning_rate": 1.2336444444444447e-05,
461
+ "loss": 0.3044,
462
+ "step": 34500
463
+ },
464
+ {
465
+ "epoch": 3.89,
466
+ "learning_rate": 1.2225333333333333e-05,
467
+ "loss": 0.3034,
468
+ "step": 35000
469
+ },
470
+ {
471
+ "epoch": 3.94,
472
+ "learning_rate": 1.2114222222222223e-05,
473
+ "loss": 0.3026,
474
+ "step": 35500
475
+ },
476
+ {
477
+ "epoch": 4.0,
478
+ "learning_rate": 1.2003111111111113e-05,
479
+ "loss": 0.3001,
480
+ "step": 36000
481
+ },
482
+ {
483
+ "epoch": 4.0,
484
+ "eval_gen_len": 13.8589,
485
+ "eval_loss": 0.2630792558193207,
486
+ "eval_rouge1": 0.8295,
487
+ "eval_rouge2": 0.7568,
488
+ "eval_rougeL": 0.8275,
489
+ "eval_rougeLsum": 0.8275,
490
+ "eval_runtime": 2033.7364,
491
+ "eval_samples_per_second": 17.701,
492
+ "eval_steps_per_second": 4.425,
493
+ "step": 36000
494
+ },
495
+ {
496
+ "epoch": 4.06,
497
+ "learning_rate": 1.1892e-05,
498
+ "loss": 0.2956,
499
+ "step": 36500
500
+ },
501
+ {
502
+ "epoch": 4.11,
503
+ "learning_rate": 1.178088888888889e-05,
504
+ "loss": 0.3012,
505
+ "step": 37000
506
+ },
507
+ {
508
+ "epoch": 4.17,
509
+ "learning_rate": 1.1670000000000002e-05,
510
+ "loss": 0.2974,
511
+ "step": 37500
512
+ },
513
+ {
514
+ "epoch": 4.22,
515
+ "learning_rate": 1.155888888888889e-05,
516
+ "loss": 0.2904,
517
+ "step": 38000
518
+ },
519
+ {
520
+ "epoch": 4.28,
521
+ "learning_rate": 1.1447777777777778e-05,
522
+ "loss": 0.298,
523
+ "step": 38500
524
+ },
525
+ {
526
+ "epoch": 4.33,
527
+ "learning_rate": 1.1336666666666668e-05,
528
+ "loss": 0.2957,
529
+ "step": 39000
530
+ },
531
+ {
532
+ "epoch": 4.39,
533
+ "learning_rate": 1.1225777777777777e-05,
534
+ "loss": 0.296,
535
+ "step": 39500
536
+ },
537
+ {
538
+ "epoch": 4.44,
539
+ "learning_rate": 1.1114666666666667e-05,
540
+ "loss": 0.2955,
541
+ "step": 40000
542
+ },
543
+ {
544
+ "epoch": 4.5,
545
+ "learning_rate": 1.1003555555555557e-05,
546
+ "loss": 0.2973,
547
+ "step": 40500
548
+ },
549
+ {
550
+ "epoch": 4.56,
551
+ "learning_rate": 1.0892444444444445e-05,
552
+ "loss": 0.2963,
553
+ "step": 41000
554
+ },
555
+ {
556
+ "epoch": 4.61,
557
+ "learning_rate": 1.0781555555555556e-05,
558
+ "loss": 0.2977,
559
+ "step": 41500
560
+ },
561
+ {
562
+ "epoch": 4.67,
563
+ "learning_rate": 1.0670444444444446e-05,
564
+ "loss": 0.2956,
565
+ "step": 42000
566
+ },
567
+ {
568
+ "epoch": 4.72,
569
+ "learning_rate": 1.0559555555555556e-05,
570
+ "loss": 0.2966,
571
+ "step": 42500
572
+ },
573
+ {
574
+ "epoch": 4.78,
575
+ "learning_rate": 1.0448444444444445e-05,
576
+ "loss": 0.2969,
577
+ "step": 43000
578
+ },
579
+ {
580
+ "epoch": 4.83,
581
+ "learning_rate": 1.0337333333333335e-05,
582
+ "loss": 0.2969,
583
+ "step": 43500
584
+ },
585
+ {
586
+ "epoch": 4.89,
587
+ "learning_rate": 1.0226222222222223e-05,
588
+ "loss": 0.2945,
589
+ "step": 44000
590
+ },
591
+ {
592
+ "epoch": 4.94,
593
+ "learning_rate": 1.0115111111111111e-05,
594
+ "loss": 0.2923,
595
+ "step": 44500
596
+ },
597
+ {
598
+ "epoch": 5.0,
599
+ "learning_rate": 1.0004000000000001e-05,
600
+ "loss": 0.2957,
601
+ "step": 45000
602
+ },
603
+ {
604
+ "epoch": 5.0,
605
+ "eval_gen_len": 13.8742,
606
+ "eval_loss": 0.25948867201805115,
607
+ "eval_rouge1": 0.8307,
608
+ "eval_rouge2": 0.759,
609
+ "eval_rougeL": 0.8288,
610
+ "eval_rougeLsum": 0.8288,
611
+ "eval_runtime": 2061.1131,
612
+ "eval_samples_per_second": 17.466,
613
+ "eval_steps_per_second": 4.367,
614
+ "step": 45000
615
+ },
616
+ {
617
+ "epoch": 5.06,
618
+ "learning_rate": 9.89288888888889e-06,
619
+ "loss": 0.2965,
620
+ "step": 45500
621
+ },
622
+ {
623
+ "epoch": 5.11,
624
+ "learning_rate": 9.781777777777779e-06,
625
+ "loss": 0.2858,
626
+ "step": 46000
627
+ },
628
+ {
629
+ "epoch": 5.17,
630
+ "learning_rate": 9.67088888888889e-06,
631
+ "loss": 0.2933,
632
+ "step": 46500
633
+ },
634
+ {
635
+ "epoch": 5.22,
636
+ "learning_rate": 9.559777777777778e-06,
637
+ "loss": 0.2913,
638
+ "step": 47000
639
+ },
640
+ {
641
+ "epoch": 5.28,
642
+ "learning_rate": 9.448666666666666e-06,
643
+ "loss": 0.2896,
644
+ "step": 47500
645
+ },
646
+ {
647
+ "epoch": 5.33,
648
+ "learning_rate": 9.337555555555556e-06,
649
+ "loss": 0.2918,
650
+ "step": 48000
651
+ },
652
+ {
653
+ "epoch": 5.39,
654
+ "learning_rate": 9.226888888888889e-06,
655
+ "loss": 0.2908,
656
+ "step": 48500
657
+ },
658
+ {
659
+ "epoch": 5.44,
660
+ "learning_rate": 9.115777777777779e-06,
661
+ "loss": 0.2916,
662
+ "step": 49000
663
+ },
664
+ {
665
+ "epoch": 5.5,
666
+ "learning_rate": 9.004666666666667e-06,
667
+ "loss": 0.284,
668
+ "step": 49500
669
+ },
670
+ {
671
+ "epoch": 5.56,
672
+ "learning_rate": 8.893555555555557e-06,
673
+ "loss": 0.2853,
674
+ "step": 50000
675
+ },
676
+ {
677
+ "epoch": 5.61,
678
+ "learning_rate": 8.782444444444446e-06,
679
+ "loss": 0.2885,
680
+ "step": 50500
681
+ },
682
+ {
683
+ "epoch": 5.67,
684
+ "learning_rate": 8.671555555555556e-06,
685
+ "loss": 0.2878,
686
+ "step": 51000
687
+ },
688
+ {
689
+ "epoch": 5.72,
690
+ "learning_rate": 8.560444444444446e-06,
691
+ "loss": 0.2909,
692
+ "step": 51500
693
+ },
694
+ {
695
+ "epoch": 5.78,
696
+ "learning_rate": 8.449333333333334e-06,
697
+ "loss": 0.2845,
698
+ "step": 52000
699
+ },
700
+ {
701
+ "epoch": 5.83,
702
+ "learning_rate": 8.338222222222224e-06,
703
+ "loss": 0.2879,
704
+ "step": 52500
705
+ },
706
+ {
707
+ "epoch": 5.89,
708
+ "learning_rate": 8.227111111111112e-06,
709
+ "loss": 0.2843,
710
+ "step": 53000
711
+ },
712
+ {
713
+ "epoch": 5.94,
714
+ "learning_rate": 8.116e-06,
715
+ "loss": 0.289,
716
+ "step": 53500
717
+ },
718
+ {
719
+ "epoch": 6.0,
720
+ "learning_rate": 8.00488888888889e-06,
721
+ "loss": 0.2879,
722
+ "step": 54000
723
+ },
724
+ {
725
+ "epoch": 6.0,
726
+ "eval_gen_len": 13.932,
727
+ "eval_loss": 0.2565445601940155,
728
+ "eval_rouge1": 0.8315,
729
+ "eval_rouge2": 0.7594,
730
+ "eval_rougeL": 0.8296,
731
+ "eval_rougeLsum": 0.8296,
732
+ "eval_runtime": 2068.5889,
733
+ "eval_samples_per_second": 17.403,
734
+ "eval_steps_per_second": 4.351,
735
+ "step": 54000
736
+ },
737
+ {
738
+ "epoch": 6.06,
739
+ "learning_rate": 7.893777777777778e-06,
740
+ "loss": 0.2886,
741
+ "step": 54500
742
+ },
743
+ {
744
+ "epoch": 6.11,
745
+ "learning_rate": 7.782888888888889e-06,
746
+ "loss": 0.2886,
747
+ "step": 55000
748
+ },
749
+ {
750
+ "epoch": 6.17,
751
+ "learning_rate": 7.671777777777779e-06,
752
+ "loss": 0.2844,
753
+ "step": 55500
754
+ },
755
+ {
756
+ "epoch": 6.22,
757
+ "learning_rate": 7.560666666666667e-06,
758
+ "loss": 0.2814,
759
+ "step": 56000
760
+ },
761
+ {
762
+ "epoch": 6.28,
763
+ "learning_rate": 7.449555555555557e-06,
764
+ "loss": 0.2846,
765
+ "step": 56500
766
+ },
767
+ {
768
+ "epoch": 6.33,
769
+ "learning_rate": 7.338666666666667e-06,
770
+ "loss": 0.2782,
771
+ "step": 57000
772
+ },
773
+ {
774
+ "epoch": 6.39,
775
+ "learning_rate": 7.227555555555557e-06,
776
+ "loss": 0.2793,
777
+ "step": 57500
778
+ },
779
+ {
780
+ "epoch": 6.44,
781
+ "learning_rate": 7.116444444444445e-06,
782
+ "loss": 0.2822,
783
+ "step": 58000
784
+ },
785
+ {
786
+ "epoch": 6.5,
787
+ "learning_rate": 7.005333333333334e-06,
788
+ "loss": 0.2838,
789
+ "step": 58500
790
+ },
791
+ {
792
+ "epoch": 6.56,
793
+ "learning_rate": 6.894444444444444e-06,
794
+ "loss": 0.2871,
795
+ "step": 59000
796
+ },
797
+ {
798
+ "epoch": 6.61,
799
+ "learning_rate": 6.783333333333334e-06,
800
+ "loss": 0.2815,
801
+ "step": 59500
802
+ },
803
+ {
804
+ "epoch": 6.67,
805
+ "learning_rate": 6.672222222222223e-06,
806
+ "loss": 0.2819,
807
+ "step": 60000
808
+ },
809
+ {
810
+ "epoch": 6.72,
811
+ "learning_rate": 6.561333333333334e-06,
812
+ "loss": 0.2874,
813
+ "step": 60500
814
+ },
815
+ {
816
+ "epoch": 6.78,
817
+ "learning_rate": 6.450222222222223e-06,
818
+ "loss": 0.2911,
819
+ "step": 61000
820
+ },
821
+ {
822
+ "epoch": 6.83,
823
+ "learning_rate": 6.339111111111111e-06,
824
+ "loss": 0.279,
825
+ "step": 61500
826
+ },
827
+ {
828
+ "epoch": 6.89,
829
+ "learning_rate": 6.228e-06,
830
+ "loss": 0.2855,
831
+ "step": 62000
832
+ },
833
+ {
834
+ "epoch": 6.94,
835
+ "learning_rate": 6.116888888888889e-06,
836
+ "loss": 0.2887,
837
+ "step": 62500
838
+ },
839
+ {
840
+ "epoch": 7.0,
841
+ "learning_rate": 6.005777777777778e-06,
842
+ "loss": 0.2824,
843
+ "step": 63000
844
+ },
845
+ {
846
+ "epoch": 7.0,
847
+ "eval_gen_len": 13.8921,
848
+ "eval_loss": 0.2553006708621979,
849
+ "eval_rouge1": 0.8322,
850
+ "eval_rouge2": 0.7607,
851
+ "eval_rougeL": 0.8302,
852
+ "eval_rougeLsum": 0.8303,
853
+ "eval_runtime": 2073.9344,
854
+ "eval_samples_per_second": 17.358,
855
+ "eval_steps_per_second": 4.34,
856
+ "step": 63000
857
+ },
858
+ {
859
+ "epoch": 7.06,
860
+ "learning_rate": 5.894666666666667e-06,
861
+ "loss": 0.2793,
862
+ "step": 63500
863
+ },
864
+ {
865
+ "epoch": 7.11,
866
+ "learning_rate": 5.783555555555556e-06,
867
+ "loss": 0.2815,
868
+ "step": 64000
869
+ },
870
+ {
871
+ "epoch": 7.17,
872
+ "learning_rate": 5.672666666666667e-06,
873
+ "loss": 0.279,
874
+ "step": 64500
875
+ },
876
+ {
877
+ "epoch": 7.22,
878
+ "learning_rate": 5.5615555555555554e-06,
879
+ "loss": 0.2853,
880
+ "step": 65000
881
+ },
882
+ {
883
+ "epoch": 7.28,
884
+ "learning_rate": 5.450444444444445e-06,
885
+ "loss": 0.2798,
886
+ "step": 65500
887
+ },
888
+ {
889
+ "epoch": 7.33,
890
+ "learning_rate": 5.339333333333334e-06,
891
+ "loss": 0.276,
892
+ "step": 66000
893
+ },
894
+ {
895
+ "epoch": 7.39,
896
+ "learning_rate": 5.228444444444445e-06,
897
+ "loss": 0.2772,
898
+ "step": 66500
899
+ },
900
+ {
901
+ "epoch": 7.44,
902
+ "learning_rate": 5.117333333333334e-06,
903
+ "loss": 0.2815,
904
+ "step": 67000
905
+ },
906
+ {
907
+ "epoch": 7.5,
908
+ "learning_rate": 5.0062222222222224e-06,
909
+ "loss": 0.2816,
910
+ "step": 67500
911
+ },
912
+ {
913
+ "epoch": 7.56,
914
+ "learning_rate": 4.895111111111111e-06,
915
+ "loss": 0.2817,
916
+ "step": 68000
917
+ },
918
+ {
919
+ "epoch": 7.61,
920
+ "learning_rate": 4.784e-06,
921
+ "loss": 0.2801,
922
+ "step": 68500
923
+ },
924
+ {
925
+ "epoch": 7.67,
926
+ "learning_rate": 4.673111111111112e-06,
927
+ "loss": 0.2816,
928
+ "step": 69000
929
+ },
930
+ {
931
+ "epoch": 7.72,
932
+ "learning_rate": 4.5620000000000005e-06,
933
+ "loss": 0.2849,
934
+ "step": 69500
935
+ },
936
+ {
937
+ "epoch": 7.78,
938
+ "learning_rate": 4.451111111111112e-06,
939
+ "loss": 0.277,
940
+ "step": 70000
941
+ },
942
+ {
943
+ "epoch": 7.83,
944
+ "learning_rate": 4.34e-06,
945
+ "loss": 0.2722,
946
+ "step": 70500
947
+ },
948
+ {
949
+ "epoch": 7.89,
950
+ "learning_rate": 4.228888888888889e-06,
951
+ "loss": 0.2811,
952
+ "step": 71000
953
+ },
954
+ {
955
+ "epoch": 7.94,
956
+ "learning_rate": 4.117777777777779e-06,
957
+ "loss": 0.2754,
958
+ "step": 71500
959
+ },
960
+ {
961
+ "epoch": 8.0,
962
+ "learning_rate": 4.006666666666667e-06,
963
+ "loss": 0.2842,
964
+ "step": 72000
965
+ },
966
+ {
967
+ "epoch": 8.0,
968
+ "eval_gen_len": 13.8792,
969
+ "eval_loss": 0.2534540593624115,
970
+ "eval_rouge1": 0.8333,
971
+ "eval_rouge2": 0.762,
972
+ "eval_rougeL": 0.8313,
973
+ "eval_rougeLsum": 0.8313,
974
+ "eval_runtime": 2051.2088,
975
+ "eval_samples_per_second": 17.551,
976
+ "eval_steps_per_second": 4.388,
977
+ "step": 72000
978
+ },
979
+ {
980
+ "epoch": 8.06,
981
+ "learning_rate": 3.895555555555556e-06,
982
+ "loss": 0.279,
983
+ "step": 72500
984
+ },
985
+ {
986
+ "epoch": 8.11,
987
+ "learning_rate": 3.784444444444445e-06,
988
+ "loss": 0.2792,
989
+ "step": 73000
990
+ },
991
+ {
992
+ "epoch": 8.17,
993
+ "learning_rate": 3.673333333333334e-06,
994
+ "loss": 0.281,
995
+ "step": 73500
996
+ },
997
+ {
998
+ "epoch": 8.22,
999
+ "learning_rate": 3.5624444444444444e-06,
1000
+ "loss": 0.2793,
1001
+ "step": 74000
1002
+ },
1003
+ {
1004
+ "epoch": 8.28,
1005
+ "learning_rate": 3.4513333333333337e-06,
1006
+ "loss": 0.2761,
1007
+ "step": 74500
1008
+ },
1009
+ {
1010
+ "epoch": 8.33,
1011
+ "learning_rate": 3.340666666666667e-06,
1012
+ "loss": 0.2775,
1013
+ "step": 75000
1014
+ },
1015
+ {
1016
+ "epoch": 8.39,
1017
+ "learning_rate": 3.229555555555556e-06,
1018
+ "loss": 0.2801,
1019
+ "step": 75500
1020
+ },
1021
+ {
1022
+ "epoch": 8.44,
1023
+ "learning_rate": 3.1184444444444445e-06,
1024
+ "loss": 0.2767,
1025
+ "step": 76000
1026
+ },
1027
+ {
1028
+ "epoch": 8.5,
1029
+ "learning_rate": 3.007333333333334e-06,
1030
+ "loss": 0.2761,
1031
+ "step": 76500
1032
+ },
1033
+ {
1034
+ "epoch": 8.56,
1035
+ "learning_rate": 2.8964444444444443e-06,
1036
+ "loss": 0.2766,
1037
+ "step": 77000
1038
+ },
1039
+ {
1040
+ "epoch": 8.61,
1041
+ "learning_rate": 2.7853333333333337e-06,
1042
+ "loss": 0.2786,
1043
+ "step": 77500
1044
+ },
1045
+ {
1046
+ "epoch": 8.67,
1047
+ "learning_rate": 2.6742222222222226e-06,
1048
+ "loss": 0.2716,
1049
+ "step": 78000
1050
+ },
1051
+ {
1052
+ "epoch": 8.72,
1053
+ "learning_rate": 2.563111111111111e-06,
1054
+ "loss": 0.2791,
1055
+ "step": 78500
1056
+ },
1057
+ {
1058
+ "epoch": 8.78,
1059
+ "learning_rate": 2.4520000000000004e-06,
1060
+ "loss": 0.2769,
1061
+ "step": 79000
1062
+ },
1063
+ {
1064
+ "epoch": 8.83,
1065
+ "learning_rate": 2.3408888888888893e-06,
1066
+ "loss": 0.2797,
1067
+ "step": 79500
1068
+ },
1069
+ {
1070
+ "epoch": 8.89,
1071
+ "learning_rate": 2.229777777777778e-06,
1072
+ "loss": 0.2746,
1073
+ "step": 80000
1074
+ },
1075
+ {
1076
+ "epoch": 8.94,
1077
+ "learning_rate": 2.1186666666666667e-06,
1078
+ "loss": 0.2727,
1079
+ "step": 80500
1080
+ },
1081
+ {
1082
+ "epoch": 9.0,
1083
+ "learning_rate": 2.0075555555555557e-06,
1084
+ "loss": 0.2809,
1085
+ "step": 81000
1086
+ },
1087
+ {
1088
+ "epoch": 9.0,
1089
+ "eval_gen_len": 13.8298,
1090
+ "eval_loss": 0.25257840752601624,
1091
+ "eval_rouge1": 0.8331,
1092
+ "eval_rouge2": 0.7617,
1093
+ "eval_rougeL": 0.8312,
1094
+ "eval_rougeLsum": 0.8312,
1095
+ "eval_runtime": 2075.7734,
1096
+ "eval_samples_per_second": 17.343,
1097
+ "eval_steps_per_second": 4.336,
1098
+ "step": 81000
1099
+ },
1100
+ {
1101
+ "epoch": 9.06,
1102
+ "learning_rate": 1.8964444444444446e-06,
1103
+ "loss": 0.275,
1104
+ "step": 81500
1105
+ },
1106
+ {
1107
+ "epoch": 9.11,
1108
+ "learning_rate": 1.7853333333333333e-06,
1109
+ "loss": 0.275,
1110
+ "step": 82000
1111
+ },
1112
+ {
1113
+ "epoch": 9.17,
1114
+ "learning_rate": 1.6742222222222224e-06,
1115
+ "loss": 0.2727,
1116
+ "step": 82500
1117
+ },
1118
+ {
1119
+ "epoch": 9.22,
1120
+ "learning_rate": 1.5631111111111113e-06,
1121
+ "loss": 0.2769,
1122
+ "step": 83000
1123
+ },
1124
+ {
1125
+ "epoch": 9.28,
1126
+ "learning_rate": 1.452e-06,
1127
+ "loss": 0.2783,
1128
+ "step": 83500
1129
+ },
1130
+ {
1131
+ "epoch": 9.33,
1132
+ "learning_rate": 1.3408888888888892e-06,
1133
+ "loss": 0.2736,
1134
+ "step": 84000
1135
+ },
1136
+ {
1137
+ "epoch": 9.39,
1138
+ "learning_rate": 1.2297777777777779e-06,
1139
+ "loss": 0.2755,
1140
+ "step": 84500
1141
+ },
1142
+ {
1143
+ "epoch": 9.44,
1144
+ "learning_rate": 1.118888888888889e-06,
1145
+ "loss": 0.2797,
1146
+ "step": 85000
1147
+ },
1148
+ {
1149
+ "epoch": 9.5,
1150
+ "learning_rate": 1.0077777777777777e-06,
1151
+ "loss": 0.2786,
1152
+ "step": 85500
1153
+ },
1154
+ {
1155
+ "epoch": 9.56,
1156
+ "learning_rate": 8.966666666666668e-07,
1157
+ "loss": 0.2778,
1158
+ "step": 86000
1159
+ },
1160
+ {
1161
+ "epoch": 9.61,
1162
+ "learning_rate": 7.857777777777778e-07,
1163
+ "loss": 0.2759,
1164
+ "step": 86500
1165
+ },
1166
+ {
1167
+ "epoch": 9.67,
1168
+ "learning_rate": 6.746666666666667e-07,
1169
+ "loss": 0.2732,
1170
+ "step": 87000
1171
+ },
1172
+ {
1173
+ "epoch": 9.72,
1174
+ "learning_rate": 5.635555555555556e-07,
1175
+ "loss": 0.2715,
1176
+ "step": 87500
1177
+ },
1178
+ {
1179
+ "epoch": 9.78,
1180
+ "learning_rate": 4.5244444444444445e-07,
1181
+ "loss": 0.278,
1182
+ "step": 88000
1183
+ },
1184
+ {
1185
+ "epoch": 9.83,
1186
+ "learning_rate": 3.4133333333333337e-07,
1187
+ "loss": 0.2768,
1188
+ "step": 88500
1189
+ },
1190
+ {
1191
+ "epoch": 9.89,
1192
+ "learning_rate": 2.3022222222222224e-07,
1193
+ "loss": 0.2748,
1194
+ "step": 89000
1195
+ },
1196
+ {
1197
+ "epoch": 9.94,
1198
+ "learning_rate": 1.1911111111111113e-07,
1199
+ "loss": 0.2761,
1200
+ "step": 89500
1201
+ },
1202
+ {
1203
+ "epoch": 10.0,
1204
+ "learning_rate": 8e-09,
1205
+ "loss": 0.2738,
1206
+ "step": 90000
1207
+ },
1208
+ {
1209
+ "epoch": 10.0,
1210
+ "eval_gen_len": 12.9728,
1211
+ "eval_loss": 0.248253840752601624,
1212
+ "eval_rouge1": 0.8425,
1213
+ "eval_rouge2": 0.7724,
1214
+ "eval_rougeL": 0.8431,
1215
+ "eval_rougeLsum": 0.8461,
1216
+ "eval_runtime": 2075.7734,
1217
+ "eval_samples_per_second": 17.343,
1218
+ "eval_steps_per_second": 4.336,
1219
+ "step": 90000
1220
+ }
1221
+ ],
1222
+ "logging_steps": 500,
1223
+ "max_steps": 90000,
1224
+ "num_input_tokens_seen": 0,
1225
+ "num_train_epochs": 10,
1226
+ "save_steps": 500,
1227
+ "total_flos": 2.748847816389427e+16,
1228
+ "train_batch_size": 16,
1229
+ "trial_name": null,
1230
+ "trial_params": null
1231
+ }
checkpoint-90000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c146cd9e86d93c893fb75e6f623e1836146cd487f91f3dc68296bf2256effd
3
+ size 4792