aiface commited on
Commit
5a32931
1 Parent(s): c3e2bec

Training in progress, step 12000, checkpoint

Browse files
checkpoint-12000/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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": "4.34.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-12000/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": "4.34.1"
6
+ }
checkpoint-12000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a30ffbcd023aafd8287d35961aca9cb44757c00561c087ebcdf7cc104cd6bf
3
+ size 484163514
checkpoint-12000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1db3d089a77ccc2ee2c7d6f4ec86bfa547a228c885cc166b5a6bff578d46132
3
+ size 242072086
checkpoint-12000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1359d69bfba5e04ab322cad7091c136d3a9d1376fdb44d0a4f7be668e8b33b88
3
+ size 14244
checkpoint-12000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b126826abc915cb99fa3fca262b01c069307a34a190ff89306fc6711c53b43
3
+ size 1064
checkpoint-12000/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-12000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12000/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-12000/trainer_state.json ADDED
@@ -0,0 +1,955 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0720593881991554,
5
+ "eval_steps": 500,
6
+ "global_step": 12000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 0.0004957330602491893,
14
+ "loss": 2.0441,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 0.0004914661204983786,
20
+ "loss": 1.713,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 0.00048719918074756785,
26
+ "loss": 1.6007,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 0.00048293224099675715,
32
+ "loss": 1.5181,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 0.00047866530124594645,
38
+ "loss": 1.4493,
39
+ "step": 500
40
+ },
41
+ {
42
+ "epoch": 0.13,
43
+ "eval_bleu": 3.9997520454971136,
44
+ "eval_loss": 1.3540712594985962,
45
+ "eval_runtime": 10.3322,
46
+ "eval_samples_per_second": 193.569,
47
+ "eval_steps_per_second": 1.549,
48
+ "step": 500
49
+ },
50
+ {
51
+ "epoch": 0.15,
52
+ "learning_rate": 0.0004743983614951357,
53
+ "loss": 1.4096,
54
+ "step": 600
55
+ },
56
+ {
57
+ "epoch": 0.18,
58
+ "learning_rate": 0.000470131421744325,
59
+ "loss": 1.3729,
60
+ "step": 700
61
+ },
62
+ {
63
+ "epoch": 0.2,
64
+ "learning_rate": 0.0004658644819935143,
65
+ "loss": 1.3389,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.23,
70
+ "learning_rate": 0.00046159754224270354,
71
+ "loss": 1.3166,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.26,
76
+ "learning_rate": 0.00045733060249189284,
77
+ "loss": 1.2915,
78
+ "step": 1000
79
+ },
80
+ {
81
+ "epoch": 0.26,
82
+ "eval_bleu": 5.393565315342523,
83
+ "eval_loss": 1.2113043069839478,
84
+ "eval_runtime": 8.5631,
85
+ "eval_samples_per_second": 233.562,
86
+ "eval_steps_per_second": 1.868,
87
+ "step": 1000
88
+ },
89
+ {
90
+ "epoch": 0.28,
91
+ "learning_rate": 0.00045306366274108214,
92
+ "loss": 1.2669,
93
+ "step": 1100
94
+ },
95
+ {
96
+ "epoch": 0.31,
97
+ "learning_rate": 0.0004487967229902714,
98
+ "loss": 1.2492,
99
+ "step": 1200
100
+ },
101
+ {
102
+ "epoch": 0.33,
103
+ "learning_rate": 0.0004445297832394607,
104
+ "loss": 1.2371,
105
+ "step": 1300
106
+ },
107
+ {
108
+ "epoch": 0.36,
109
+ "learning_rate": 0.00044026284348864993,
110
+ "loss": 1.2231,
111
+ "step": 1400
112
+ },
113
+ {
114
+ "epoch": 0.38,
115
+ "learning_rate": 0.00043599590373783923,
116
+ "loss": 1.2059,
117
+ "step": 1500
118
+ },
119
+ {
120
+ "epoch": 0.38,
121
+ "eval_bleu": 5.838067918496751,
122
+ "eval_loss": 1.1367273330688477,
123
+ "eval_runtime": 9.2404,
124
+ "eval_samples_per_second": 216.442,
125
+ "eval_steps_per_second": 1.732,
126
+ "step": 1500
127
+ },
128
+ {
129
+ "epoch": 0.41,
130
+ "learning_rate": 0.0004317289639870285,
131
+ "loss": 1.1931,
132
+ "step": 1600
133
+ },
134
+ {
135
+ "epoch": 0.44,
136
+ "learning_rate": 0.0004274620242362178,
137
+ "loss": 1.1761,
138
+ "step": 1700
139
+ },
140
+ {
141
+ "epoch": 0.46,
142
+ "learning_rate": 0.0004231950844854071,
143
+ "loss": 1.1792,
144
+ "step": 1800
145
+ },
146
+ {
147
+ "epoch": 0.49,
148
+ "learning_rate": 0.0004189281447345963,
149
+ "loss": 1.1614,
150
+ "step": 1900
151
+ },
152
+ {
153
+ "epoch": 0.51,
154
+ "learning_rate": 0.0004146612049837856,
155
+ "loss": 1.1573,
156
+ "step": 2000
157
+ },
158
+ {
159
+ "epoch": 0.51,
160
+ "eval_bleu": 6.242227124133382,
161
+ "eval_loss": 1.0900604724884033,
162
+ "eval_runtime": 8.3953,
163
+ "eval_samples_per_second": 238.228,
164
+ "eval_steps_per_second": 1.906,
165
+ "step": 2000
166
+ },
167
+ {
168
+ "epoch": 0.54,
169
+ "learning_rate": 0.0004103942652329749,
170
+ "loss": 1.1449,
171
+ "step": 2100
172
+ },
173
+ {
174
+ "epoch": 0.56,
175
+ "learning_rate": 0.00040612732548216417,
176
+ "loss": 1.1379,
177
+ "step": 2200
178
+ },
179
+ {
180
+ "epoch": 0.59,
181
+ "learning_rate": 0.00040186038573135347,
182
+ "loss": 1.1281,
183
+ "step": 2300
184
+ },
185
+ {
186
+ "epoch": 0.61,
187
+ "learning_rate": 0.00039759344598054277,
188
+ "loss": 1.1226,
189
+ "step": 2400
190
+ },
191
+ {
192
+ "epoch": 0.64,
193
+ "learning_rate": 0.00039332650622973206,
194
+ "loss": 1.1121,
195
+ "step": 2500
196
+ },
197
+ {
198
+ "epoch": 0.64,
199
+ "eval_bleu": 6.627148578471305,
200
+ "eval_loss": 1.0542418956756592,
201
+ "eval_runtime": 9.2835,
202
+ "eval_samples_per_second": 215.436,
203
+ "eval_steps_per_second": 1.723,
204
+ "step": 2500
205
+ },
206
+ {
207
+ "epoch": 0.67,
208
+ "learning_rate": 0.0003890595664789213,
209
+ "loss": 1.1076,
210
+ "step": 2600
211
+ },
212
+ {
213
+ "epoch": 0.69,
214
+ "learning_rate": 0.0003847926267281106,
215
+ "loss": 1.1001,
216
+ "step": 2700
217
+ },
218
+ {
219
+ "epoch": 0.72,
220
+ "learning_rate": 0.0003805256869772999,
221
+ "loss": 1.0996,
222
+ "step": 2800
223
+ },
224
+ {
225
+ "epoch": 0.74,
226
+ "learning_rate": 0.00037625874722648915,
227
+ "loss": 1.088,
228
+ "step": 2900
229
+ },
230
+ {
231
+ "epoch": 0.77,
232
+ "learning_rate": 0.00037199180747567845,
233
+ "loss": 1.0867,
234
+ "step": 3000
235
+ },
236
+ {
237
+ "epoch": 0.77,
238
+ "eval_bleu": 6.879580310573366,
239
+ "eval_loss": 1.025155782699585,
240
+ "eval_runtime": 8.5706,
241
+ "eval_samples_per_second": 233.355,
242
+ "eval_steps_per_second": 1.867,
243
+ "step": 3000
244
+ },
245
+ {
246
+ "epoch": 0.79,
247
+ "learning_rate": 0.00036772486772486775,
248
+ "loss": 1.0784,
249
+ "step": 3100
250
+ },
251
+ {
252
+ "epoch": 0.82,
253
+ "learning_rate": 0.000363457927974057,
254
+ "loss": 1.0794,
255
+ "step": 3200
256
+ },
257
+ {
258
+ "epoch": 0.84,
259
+ "learning_rate": 0.0003591909882232463,
260
+ "loss": 1.0736,
261
+ "step": 3300
262
+ },
263
+ {
264
+ "epoch": 0.87,
265
+ "learning_rate": 0.0003549240484724356,
266
+ "loss": 1.0684,
267
+ "step": 3400
268
+ },
269
+ {
270
+ "epoch": 0.9,
271
+ "learning_rate": 0.0003506571087216249,
272
+ "loss": 1.0623,
273
+ "step": 3500
274
+ },
275
+ {
276
+ "epoch": 0.9,
277
+ "eval_bleu": 7.039305128716119,
278
+ "eval_loss": 1.0067821741104126,
279
+ "eval_runtime": 9.3223,
280
+ "eval_samples_per_second": 214.539,
281
+ "eval_steps_per_second": 1.716,
282
+ "step": 3500
283
+ },
284
+ {
285
+ "epoch": 0.92,
286
+ "learning_rate": 0.00034639016897081414,
287
+ "loss": 1.0609,
288
+ "step": 3600
289
+ },
290
+ {
291
+ "epoch": 0.95,
292
+ "learning_rate": 0.00034212322922000344,
293
+ "loss": 1.0579,
294
+ "step": 3700
295
+ },
296
+ {
297
+ "epoch": 0.97,
298
+ "learning_rate": 0.00033785628946919274,
299
+ "loss": 1.0517,
300
+ "step": 3800
301
+ },
302
+ {
303
+ "epoch": 1.0,
304
+ "learning_rate": 0.000333589349718382,
305
+ "loss": 1.054,
306
+ "step": 3900
307
+ },
308
+ {
309
+ "epoch": 1.02,
310
+ "learning_rate": 0.0003293224099675713,
311
+ "loss": 1.0408,
312
+ "step": 4000
313
+ },
314
+ {
315
+ "epoch": 1.02,
316
+ "eval_bleu": 7.2660174031875915,
317
+ "eval_loss": 0.9882246255874634,
318
+ "eval_runtime": 8.4135,
319
+ "eval_samples_per_second": 237.713,
320
+ "eval_steps_per_second": 1.902,
321
+ "step": 4000
322
+ },
323
+ {
324
+ "epoch": 1.05,
325
+ "learning_rate": 0.0003250554702167606,
326
+ "loss": 1.0317,
327
+ "step": 4100
328
+ },
329
+ {
330
+ "epoch": 1.08,
331
+ "learning_rate": 0.0003207885304659498,
332
+ "loss": 1.0344,
333
+ "step": 4200
334
+ },
335
+ {
336
+ "epoch": 1.1,
337
+ "learning_rate": 0.0003165215907151391,
338
+ "loss": 1.0274,
339
+ "step": 4300
340
+ },
341
+ {
342
+ "epoch": 1.13,
343
+ "learning_rate": 0.0003122546509643284,
344
+ "loss": 1.0216,
345
+ "step": 4400
346
+ },
347
+ {
348
+ "epoch": 1.15,
349
+ "learning_rate": 0.0003079877112135177,
350
+ "loss": 1.0203,
351
+ "step": 4500
352
+ },
353
+ {
354
+ "epoch": 1.15,
355
+ "eval_bleu": 7.055297387993883,
356
+ "eval_loss": 0.9723305702209473,
357
+ "eval_runtime": 9.3412,
358
+ "eval_samples_per_second": 214.105,
359
+ "eval_steps_per_second": 1.713,
360
+ "step": 4500
361
+ },
362
+ {
363
+ "epoch": 1.18,
364
+ "learning_rate": 0.0003037207714627069,
365
+ "loss": 1.0217,
366
+ "step": 4600
367
+ },
368
+ {
369
+ "epoch": 1.2,
370
+ "learning_rate": 0.0002994538317118962,
371
+ "loss": 1.0184,
372
+ "step": 4700
373
+ },
374
+ {
375
+ "epoch": 1.23,
376
+ "learning_rate": 0.0002951868919610855,
377
+ "loss": 1.015,
378
+ "step": 4800
379
+ },
380
+ {
381
+ "epoch": 1.25,
382
+ "learning_rate": 0.00029091995221027477,
383
+ "loss": 1.011,
384
+ "step": 4900
385
+ },
386
+ {
387
+ "epoch": 1.28,
388
+ "learning_rate": 0.00028665301245946406,
389
+ "loss": 1.0054,
390
+ "step": 5000
391
+ },
392
+ {
393
+ "epoch": 1.28,
394
+ "eval_bleu": 7.455525040183996,
395
+ "eval_loss": 0.9624391198158264,
396
+ "eval_runtime": 8.4826,
397
+ "eval_samples_per_second": 235.778,
398
+ "eval_steps_per_second": 1.886,
399
+ "step": 5000
400
+ },
401
+ {
402
+ "epoch": 1.31,
403
+ "learning_rate": 0.00028238607270865336,
404
+ "loss": 1.0062,
405
+ "step": 5100
406
+ },
407
+ {
408
+ "epoch": 1.33,
409
+ "learning_rate": 0.0002781191329578426,
410
+ "loss": 1.0081,
411
+ "step": 5200
412
+ },
413
+ {
414
+ "epoch": 1.36,
415
+ "learning_rate": 0.0002738521932070319,
416
+ "loss": 1.0007,
417
+ "step": 5300
418
+ },
419
+ {
420
+ "epoch": 1.38,
421
+ "learning_rate": 0.0002695852534562212,
422
+ "loss": 0.9973,
423
+ "step": 5400
424
+ },
425
+ {
426
+ "epoch": 1.41,
427
+ "learning_rate": 0.0002653183137054105,
428
+ "loss": 0.9977,
429
+ "step": 5500
430
+ },
431
+ {
432
+ "epoch": 1.41,
433
+ "eval_bleu": 7.426000467701662,
434
+ "eval_loss": 0.9526358842849731,
435
+ "eval_runtime": 9.3659,
436
+ "eval_samples_per_second": 213.542,
437
+ "eval_steps_per_second": 1.708,
438
+ "step": 5500
439
+ },
440
+ {
441
+ "epoch": 1.43,
442
+ "learning_rate": 0.00026105137395459975,
443
+ "loss": 0.9982,
444
+ "step": 5600
445
+ },
446
+ {
447
+ "epoch": 1.46,
448
+ "learning_rate": 0.00025678443420378905,
449
+ "loss": 0.9956,
450
+ "step": 5700
451
+ },
452
+ {
453
+ "epoch": 1.48,
454
+ "learning_rate": 0.00025251749445297835,
455
+ "loss": 0.9941,
456
+ "step": 5800
457
+ },
458
+ {
459
+ "epoch": 1.51,
460
+ "learning_rate": 0.0002482505547021676,
461
+ "loss": 0.9881,
462
+ "step": 5900
463
+ },
464
+ {
465
+ "epoch": 1.54,
466
+ "learning_rate": 0.0002439836149513569,
467
+ "loss": 0.9931,
468
+ "step": 6000
469
+ },
470
+ {
471
+ "epoch": 1.54,
472
+ "eval_bleu": 7.523072732517067,
473
+ "eval_loss": 0.9395684003829956,
474
+ "eval_runtime": 9.0823,
475
+ "eval_samples_per_second": 220.209,
476
+ "eval_steps_per_second": 1.762,
477
+ "step": 6000
478
+ },
479
+ {
480
+ "epoch": 1.56,
481
+ "learning_rate": 0.0002397166752005462,
482
+ "loss": 0.9834,
483
+ "step": 6100
484
+ },
485
+ {
486
+ "epoch": 1.59,
487
+ "learning_rate": 0.00023544973544973544,
488
+ "loss": 0.9821,
489
+ "step": 6200
490
+ },
491
+ {
492
+ "epoch": 1.61,
493
+ "learning_rate": 0.00023118279569892471,
494
+ "loss": 0.9859,
495
+ "step": 6300
496
+ },
497
+ {
498
+ "epoch": 1.64,
499
+ "learning_rate": 0.00022691585594811401,
500
+ "loss": 0.9762,
501
+ "step": 6400
502
+ },
503
+ {
504
+ "epoch": 1.66,
505
+ "learning_rate": 0.0002226489161973033,
506
+ "loss": 0.9804,
507
+ "step": 6500
508
+ },
509
+ {
510
+ "epoch": 1.66,
511
+ "eval_bleu": 7.43758431482021,
512
+ "eval_loss": 0.9323887825012207,
513
+ "eval_runtime": 9.0344,
514
+ "eval_samples_per_second": 221.376,
515
+ "eval_steps_per_second": 1.771,
516
+ "step": 6500
517
+ },
518
+ {
519
+ "epoch": 1.69,
520
+ "learning_rate": 0.00021838197644649259,
521
+ "loss": 0.9794,
522
+ "step": 6600
523
+ },
524
+ {
525
+ "epoch": 1.72,
526
+ "learning_rate": 0.00021411503669568186,
527
+ "loss": 0.9737,
528
+ "step": 6700
529
+ },
530
+ {
531
+ "epoch": 1.74,
532
+ "learning_rate": 0.00020984809694487113,
533
+ "loss": 0.9696,
534
+ "step": 6800
535
+ },
536
+ {
537
+ "epoch": 1.77,
538
+ "learning_rate": 0.00020558115719406043,
539
+ "loss": 0.9735,
540
+ "step": 6900
541
+ },
542
+ {
543
+ "epoch": 1.79,
544
+ "learning_rate": 0.0002013142174432497,
545
+ "loss": 0.9691,
546
+ "step": 7000
547
+ },
548
+ {
549
+ "epoch": 1.79,
550
+ "eval_bleu": 7.52270860836675,
551
+ "eval_loss": 0.9264442324638367,
552
+ "eval_runtime": 9.3377,
553
+ "eval_samples_per_second": 214.186,
554
+ "eval_steps_per_second": 1.713,
555
+ "step": 7000
556
+ },
557
+ {
558
+ "epoch": 1.82,
559
+ "learning_rate": 0.000197047277692439,
560
+ "loss": 0.9754,
561
+ "step": 7100
562
+ },
563
+ {
564
+ "epoch": 1.84,
565
+ "learning_rate": 0.00019278033794162827,
566
+ "loss": 0.9688,
567
+ "step": 7200
568
+ },
569
+ {
570
+ "epoch": 1.87,
571
+ "learning_rate": 0.00018851339819081755,
572
+ "loss": 0.968,
573
+ "step": 7300
574
+ },
575
+ {
576
+ "epoch": 1.89,
577
+ "learning_rate": 0.00018424645844000685,
578
+ "loss": 0.9628,
579
+ "step": 7400
580
+ },
581
+ {
582
+ "epoch": 1.92,
583
+ "learning_rate": 0.00017997951868919612,
584
+ "loss": 0.9645,
585
+ "step": 7500
586
+ },
587
+ {
588
+ "epoch": 1.92,
589
+ "eval_bleu": 7.685904345266889,
590
+ "eval_loss": 0.9192501306533813,
591
+ "eval_runtime": 8.7414,
592
+ "eval_samples_per_second": 228.796,
593
+ "eval_steps_per_second": 1.83,
594
+ "step": 7500
595
+ },
596
+ {
597
+ "epoch": 1.95,
598
+ "learning_rate": 0.0001757125789383854,
599
+ "loss": 0.9674,
600
+ "step": 7600
601
+ },
602
+ {
603
+ "epoch": 1.97,
604
+ "learning_rate": 0.00017144563918757466,
605
+ "loss": 0.9659,
606
+ "step": 7700
607
+ },
608
+ {
609
+ "epoch": 2.0,
610
+ "learning_rate": 0.00016717869943676394,
611
+ "loss": 0.9646,
612
+ "step": 7800
613
+ },
614
+ {
615
+ "epoch": 2.02,
616
+ "learning_rate": 0.00016291175968595324,
617
+ "loss": 0.9477,
618
+ "step": 7900
619
+ },
620
+ {
621
+ "epoch": 2.05,
622
+ "learning_rate": 0.0001586448199351425,
623
+ "loss": 0.9509,
624
+ "step": 8000
625
+ },
626
+ {
627
+ "epoch": 2.05,
628
+ "eval_bleu": 7.647325378973634,
629
+ "eval_loss": 0.9144095778465271,
630
+ "eval_runtime": 9.1538,
631
+ "eval_samples_per_second": 218.489,
632
+ "eval_steps_per_second": 1.748,
633
+ "step": 8000
634
+ },
635
+ {
636
+ "epoch": 2.07,
637
+ "learning_rate": 0.00024078341013824886,
638
+ "loss": 0.9532,
639
+ "step": 8100
640
+ },
641
+ {
642
+ "epoch": 2.1,
643
+ "learning_rate": 0.00023758320532514082,
644
+ "loss": 0.949,
645
+ "step": 8200
646
+ },
647
+ {
648
+ "epoch": 2.12,
649
+ "learning_rate": 0.00023438300051203275,
650
+ "loss": 0.9506,
651
+ "step": 8300
652
+ },
653
+ {
654
+ "epoch": 2.15,
655
+ "learning_rate": 0.00023118279569892471,
656
+ "loss": 0.9539,
657
+ "step": 8400
658
+ },
659
+ {
660
+ "epoch": 2.18,
661
+ "learning_rate": 0.00022798259088581668,
662
+ "loss": 0.9485,
663
+ "step": 8500
664
+ },
665
+ {
666
+ "epoch": 2.18,
667
+ "eval_bleu": 7.654834398763605,
668
+ "eval_loss": 0.9117684364318848,
669
+ "eval_runtime": 11.8365,
670
+ "eval_samples_per_second": 168.969,
671
+ "eval_steps_per_second": 1.352,
672
+ "step": 8500
673
+ },
674
+ {
675
+ "epoch": 2.2,
676
+ "learning_rate": 0.00022478238607270864,
677
+ "loss": 0.9495,
678
+ "step": 8600
679
+ },
680
+ {
681
+ "epoch": 2.23,
682
+ "learning_rate": 0.00022158218125960063,
683
+ "loss": 0.9484,
684
+ "step": 8700
685
+ },
686
+ {
687
+ "epoch": 2.25,
688
+ "learning_rate": 0.00021838197644649259,
689
+ "loss": 0.9486,
690
+ "step": 8800
691
+ },
692
+ {
693
+ "epoch": 2.28,
694
+ "learning_rate": 0.00021518177163338455,
695
+ "loss": 0.9445,
696
+ "step": 8900
697
+ },
698
+ {
699
+ "epoch": 2.3,
700
+ "learning_rate": 0.0002119815668202765,
701
+ "loss": 0.9437,
702
+ "step": 9000
703
+ },
704
+ {
705
+ "epoch": 2.3,
706
+ "eval_bleu": 7.606584348844775,
707
+ "eval_loss": 0.9072746634483337,
708
+ "eval_runtime": 9.3821,
709
+ "eval_samples_per_second": 213.171,
710
+ "eval_steps_per_second": 1.705,
711
+ "step": 9000
712
+ },
713
+ {
714
+ "epoch": 2.33,
715
+ "learning_rate": 0.00020878136200716847,
716
+ "loss": 0.9406,
717
+ "step": 9100
718
+ },
719
+ {
720
+ "epoch": 2.36,
721
+ "learning_rate": 0.00020558115719406043,
722
+ "loss": 0.9418,
723
+ "step": 9200
724
+ },
725
+ {
726
+ "epoch": 2.38,
727
+ "learning_rate": 0.0002023809523809524,
728
+ "loss": 0.9402,
729
+ "step": 9300
730
+ },
731
+ {
732
+ "epoch": 2.41,
733
+ "learning_rate": 0.00019918074756784435,
734
+ "loss": 0.94,
735
+ "step": 9400
736
+ },
737
+ {
738
+ "epoch": 2.43,
739
+ "learning_rate": 0.00019598054275473631,
740
+ "loss": 0.9393,
741
+ "step": 9500
742
+ },
743
+ {
744
+ "epoch": 2.43,
745
+ "eval_bleu": 7.714033503089272,
746
+ "eval_loss": 0.9019351601600647,
747
+ "eval_runtime": 9.2531,
748
+ "eval_samples_per_second": 216.144,
749
+ "eval_steps_per_second": 1.729,
750
+ "step": 9500
751
+ },
752
+ {
753
+ "epoch": 2.46,
754
+ "learning_rate": 0.00019278033794162827,
755
+ "loss": 0.9378,
756
+ "step": 9600
757
+ },
758
+ {
759
+ "epoch": 2.48,
760
+ "learning_rate": 0.00018958013312852024,
761
+ "loss": 0.9345,
762
+ "step": 9700
763
+ },
764
+ {
765
+ "epoch": 2.51,
766
+ "learning_rate": 0.0001863799283154122,
767
+ "loss": 0.936,
768
+ "step": 9800
769
+ },
770
+ {
771
+ "epoch": 2.53,
772
+ "learning_rate": 0.00018317972350230416,
773
+ "loss": 0.9389,
774
+ "step": 9900
775
+ },
776
+ {
777
+ "epoch": 2.56,
778
+ "learning_rate": 0.00017997951868919612,
779
+ "loss": 0.9336,
780
+ "step": 10000
781
+ },
782
+ {
783
+ "epoch": 2.56,
784
+ "eval_bleu": 7.80952091204729,
785
+ "eval_loss": 0.897022545337677,
786
+ "eval_runtime": 9.0616,
787
+ "eval_samples_per_second": 220.711,
788
+ "eval_steps_per_second": 1.766,
789
+ "step": 10000
790
+ },
791
+ {
792
+ "epoch": 2.59,
793
+ "learning_rate": 0.00017677931387608805,
794
+ "loss": 0.9376,
795
+ "step": 10100
796
+ },
797
+ {
798
+ "epoch": 2.61,
799
+ "learning_rate": 0.00017357910906298001,
800
+ "loss": 0.9344,
801
+ "step": 10200
802
+ },
803
+ {
804
+ "epoch": 2.64,
805
+ "learning_rate": 0.00017037890424987198,
806
+ "loss": 0.9358,
807
+ "step": 10300
808
+ },
809
+ {
810
+ "epoch": 2.66,
811
+ "learning_rate": 0.00016717869943676394,
812
+ "loss": 0.9309,
813
+ "step": 10400
814
+ },
815
+ {
816
+ "epoch": 2.69,
817
+ "learning_rate": 0.0001639784946236559,
818
+ "loss": 0.9368,
819
+ "step": 10500
820
+ },
821
+ {
822
+ "epoch": 2.69,
823
+ "eval_bleu": 7.937668751101428,
824
+ "eval_loss": 0.8936744928359985,
825
+ "eval_runtime": 9.5691,
826
+ "eval_samples_per_second": 209.006,
827
+ "eval_steps_per_second": 1.672,
828
+ "step": 10500
829
+ },
830
+ {
831
+ "epoch": 2.71,
832
+ "learning_rate": 0.00016077828981054789,
833
+ "loss": 0.9337,
834
+ "step": 10600
835
+ },
836
+ {
837
+ "epoch": 2.74,
838
+ "learning_rate": 0.00015757808499743985,
839
+ "loss": 0.9266,
840
+ "step": 10700
841
+ },
842
+ {
843
+ "epoch": 2.76,
844
+ "learning_rate": 0.0001543778801843318,
845
+ "loss": 0.9276,
846
+ "step": 10800
847
+ },
848
+ {
849
+ "epoch": 2.79,
850
+ "learning_rate": 0.00015117767537122377,
851
+ "loss": 0.9266,
852
+ "step": 10900
853
+ },
854
+ {
855
+ "epoch": 2.82,
856
+ "learning_rate": 0.00014797747055811573,
857
+ "loss": 0.925,
858
+ "step": 11000
859
+ },
860
+ {
861
+ "epoch": 2.82,
862
+ "eval_bleu": 7.842526661794731,
863
+ "eval_loss": 0.8898113965988159,
864
+ "eval_runtime": 9.4133,
865
+ "eval_samples_per_second": 212.466,
866
+ "eval_steps_per_second": 1.7,
867
+ "step": 11000
868
+ },
869
+ {
870
+ "epoch": 2.84,
871
+ "learning_rate": 0.0001447772657450077,
872
+ "loss": 0.9161,
873
+ "step": 11100
874
+ },
875
+ {
876
+ "epoch": 2.87,
877
+ "learning_rate": 0.00014157706093189965,
878
+ "loss": 0.9263,
879
+ "step": 11200
880
+ },
881
+ {
882
+ "epoch": 2.89,
883
+ "learning_rate": 0.0001383768561187916,
884
+ "loss": 0.9293,
885
+ "step": 11300
886
+ },
887
+ {
888
+ "epoch": 2.92,
889
+ "learning_rate": 0.00013517665130568357,
890
+ "loss": 0.924,
891
+ "step": 11400
892
+ },
893
+ {
894
+ "epoch": 2.94,
895
+ "learning_rate": 0.00013197644649257554,
896
+ "loss": 0.921,
897
+ "step": 11500
898
+ },
899
+ {
900
+ "epoch": 2.94,
901
+ "eval_bleu": 7.900750479934787,
902
+ "eval_loss": 0.8863839507102966,
903
+ "eval_runtime": 9.7323,
904
+ "eval_samples_per_second": 205.501,
905
+ "eval_steps_per_second": 1.644,
906
+ "step": 11500
907
+ },
908
+ {
909
+ "epoch": 2.97,
910
+ "learning_rate": 0.0001287762416794675,
911
+ "loss": 0.9213,
912
+ "step": 11600
913
+ },
914
+ {
915
+ "epoch": 3.0,
916
+ "learning_rate": 0.00012557603686635946,
917
+ "loss": 0.9219,
918
+ "step": 11700
919
+ },
920
+ {
921
+ "epoch": 3.02,
922
+ "learning_rate": 0.00012237583205325142,
923
+ "loss": 0.9141,
924
+ "step": 11800
925
+ },
926
+ {
927
+ "epoch": 3.05,
928
+ "learning_rate": 0.00011917562724014337,
929
+ "loss": 0.9125,
930
+ "step": 11900
931
+ },
932
+ {
933
+ "epoch": 3.07,
934
+ "learning_rate": 0.00011597542242703534,
935
+ "loss": 0.9177,
936
+ "step": 12000
937
+ },
938
+ {
939
+ "epoch": 3.07,
940
+ "eval_bleu": 7.913356299834283,
941
+ "eval_loss": 0.8835927844047546,
942
+ "eval_runtime": 9.3736,
943
+ "eval_samples_per_second": 213.364,
944
+ "eval_steps_per_second": 1.707,
945
+ "step": 12000
946
+ }
947
+ ],
948
+ "logging_steps": 100,
949
+ "max_steps": 15624,
950
+ "num_train_epochs": 4,
951
+ "save_steps": 2000,
952
+ "total_flos": 3.5049026466349056e+16,
953
+ "trial_name": null,
954
+ "trial_params": null
955
+ }
checkpoint-12000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b969aee6095b42032e11a1bf2baeaf8d49b7f5379f3896930e1c01a735c4fa9a
3
+ size 4664