Joemgu commited on
Commit
0fb8d41
1 Parent(s): 4e43a87

Training in progress, step 250

Browse files
.gitattributes CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agemagician/mlong-t5-tglobal-large",
3
+ "architectures": [
4
+ "LongT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "encoder_attention_type": "transient-global",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "global_block_size": 16,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "local_radius": 127,
21
+ "model_type": "longt5",
22
+ "n_positions": 4096,
23
+ "num_decoder_layers": 24,
24
+ "num_heads": 16,
25
+ "num_layers": 24,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "relative_attention_max_distance": 128,
29
+ "relative_attention_num_buckets": 32,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.30.0",
33
+ "use_cache": false,
34
+ "vocab_size": 256384
35
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agemagician/mlong-t5-tglobal-large",
3
+ "architectures": [
4
+ "LongT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "encoder_attention_type": "transient-global",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "global_block_size": 16,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "local_radius": 127,
21
+ "model_type": "longt5",
22
+ "n_positions": 4096,
23
+ "num_decoder_layers": 24,
24
+ "num_heads": 16,
25
+ "num_layers": 24,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "relative_attention_max_distance": 128,
29
+ "relative_attention_num_buckets": 32,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.30.0",
33
+ "use_cache": false,
34
+ "vocab_size": 256384
35
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "max_length": 1024,
4
+ "transformers_version": "4.30.0"
5
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbae7e1fe4d1b6228b99345517a477af94260db08bbd0947b4c15acf605a357
3
+ size 9940136798
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f6ae4a54d9d6b8a3bb6ba480a9bcdcda69e0ca282fc7d1ac0107196645bb7c
3
+ size 4970010649
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93895edfad50fb299d747e4ff2f1be8170e1732957c868a9359d42614f312549
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eaee6d19b3157fa253c3ea0d345a4245a2559513cf1b4e52fd46dbfc341a289
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
last-checkpoint/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df39d1fc39c686038078faca93a76cbae9e199a3b652997417ef370ad8c5677
3
+ size 4555103
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1aeab8f9f01e0f5c8f9b8e06e3c1546696dff62a47a6729a0f91aaa24c98da4
3
+ size 16795620
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "extra_ids": 0,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "tokenizer_class": "T5Tokenizer",
10
+ "unk_token": "<unk>"
11
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1529 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.9963864088058472,
3
+ "best_model_checkpoint": "output/checkpoint-250",
4
+ "epoch": 0.041666666666666664,
5
+ "global_step": 250,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 5e-06,
13
+ "loss": 4.4985,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 1e-05,
19
+ "loss": 4.9103,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 1.5e-05,
25
+ "loss": 4.6958,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 2e-05,
31
+ "loss": 5.0638,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 2.5e-05,
37
+ "loss": 4.588,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.0,
42
+ "learning_rate": 3e-05,
43
+ "loss": 4.4131,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "learning_rate": 3.5000000000000004e-05,
49
+ "loss": 4.9837,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.0,
54
+ "learning_rate": 4e-05,
55
+ "loss": 4.3112,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.0,
60
+ "learning_rate": 4.4999999999999996e-05,
61
+ "loss": 4.8598,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.0,
66
+ "learning_rate": 5e-05,
67
+ "loss": 4.7387,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.0,
72
+ "learning_rate": 5.5e-05,
73
+ "loss": 4.5859,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.0,
78
+ "learning_rate": 6e-05,
79
+ "loss": 4.958,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.0,
84
+ "learning_rate": 6.500000000000001e-05,
85
+ "loss": 4.6871,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.0,
90
+ "learning_rate": 7.000000000000001e-05,
91
+ "loss": 4.9336,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.0,
96
+ "learning_rate": 7.5e-05,
97
+ "loss": 4.6115,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.0,
102
+ "learning_rate": 8e-05,
103
+ "loss": 4.3188,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.0,
108
+ "learning_rate": 8.5e-05,
109
+ "loss": 4.6045,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.0,
114
+ "learning_rate": 8.999999999999999e-05,
115
+ "loss": 4.0343,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.0,
120
+ "learning_rate": 9.5e-05,
121
+ "loss": 4.1379,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.0,
126
+ "learning_rate": 0.0001,
127
+ "loss": 4.5752,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.0,
132
+ "learning_rate": 0.000105,
133
+ "loss": 4.3199,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.0,
138
+ "learning_rate": 0.00011,
139
+ "loss": 4.3148,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.0,
144
+ "learning_rate": 0.000115,
145
+ "loss": 3.8599,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.0,
150
+ "learning_rate": 0.00012,
151
+ "loss": 4.0002,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.0,
156
+ "learning_rate": 0.000125,
157
+ "loss": 3.9161,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.0,
162
+ "learning_rate": 0.00013000000000000002,
163
+ "loss": 3.9049,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.0,
168
+ "learning_rate": 0.000135,
169
+ "loss": 3.8149,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.0,
174
+ "learning_rate": 0.00014000000000000001,
175
+ "loss": 3.6388,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.0,
180
+ "learning_rate": 0.000145,
181
+ "loss": 3.4915,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.01,
186
+ "learning_rate": 0.00015,
187
+ "loss": 3.4805,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.01,
192
+ "learning_rate": 0.000155,
193
+ "loss": 3.3052,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.01,
198
+ "learning_rate": 0.00016,
199
+ "loss": 3.1385,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.01,
204
+ "learning_rate": 0.000165,
205
+ "loss": 3.121,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.01,
210
+ "learning_rate": 0.00017,
211
+ "loss": 3.1415,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.01,
216
+ "learning_rate": 0.000175,
217
+ "loss": 3.0643,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.01,
222
+ "learning_rate": 0.00017999999999999998,
223
+ "loss": 2.9809,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.01,
228
+ "learning_rate": 0.000185,
229
+ "loss": 3.0295,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.01,
234
+ "learning_rate": 0.00019,
235
+ "loss": 3.0945,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.01,
240
+ "learning_rate": 0.00019500000000000002,
241
+ "loss": 2.9501,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.01,
246
+ "learning_rate": 0.0002,
247
+ "loss": 2.9358,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.01,
252
+ "learning_rate": 0.000205,
253
+ "loss": 2.915,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.01,
258
+ "learning_rate": 0.00021,
259
+ "loss": 2.7445,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.01,
264
+ "learning_rate": 0.000215,
265
+ "loss": 2.7352,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.01,
270
+ "learning_rate": 0.00022,
271
+ "loss": 2.7662,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.01,
276
+ "learning_rate": 0.00022500000000000002,
277
+ "loss": 2.6828,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.01,
282
+ "learning_rate": 0.00023,
283
+ "loss": 2.6451,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.01,
288
+ "learning_rate": 0.000235,
289
+ "loss": 2.6842,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.01,
294
+ "learning_rate": 0.00024,
295
+ "loss": 2.6543,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.01,
300
+ "learning_rate": 0.000245,
301
+ "loss": 2.5892,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.01,
306
+ "learning_rate": 0.00025,
307
+ "loss": 2.49,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.01,
312
+ "learning_rate": 0.000255,
313
+ "loss": 2.5954,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.01,
318
+ "learning_rate": 0.00026000000000000003,
319
+ "loss": 2.5552,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.01,
324
+ "learning_rate": 0.00026500000000000004,
325
+ "loss": 2.5406,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.01,
330
+ "learning_rate": 0.00027,
331
+ "loss": 2.5237,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.01,
336
+ "learning_rate": 0.000275,
337
+ "loss": 2.5773,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.01,
342
+ "learning_rate": 0.00028000000000000003,
343
+ "loss": 2.5432,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.01,
348
+ "learning_rate": 0.000285,
349
+ "loss": 2.4555,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.01,
354
+ "learning_rate": 0.00029,
355
+ "loss": 2.4223,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.01,
360
+ "learning_rate": 0.000295,
361
+ "loss": 2.4397,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.01,
366
+ "learning_rate": 0.0003,
367
+ "loss": 2.4535,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.01,
372
+ "learning_rate": 0.000305,
373
+ "loss": 2.3823,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.01,
378
+ "learning_rate": 0.00031,
379
+ "loss": 2.4813,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.01,
384
+ "learning_rate": 0.000315,
385
+ "loss": 2.3828,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.01,
390
+ "learning_rate": 0.00032,
391
+ "loss": 2.488,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.01,
396
+ "learning_rate": 0.00032500000000000004,
397
+ "loss": 2.3947,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.01,
402
+ "learning_rate": 0.00033,
403
+ "loss": 2.4411,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.01,
408
+ "learning_rate": 0.000335,
409
+ "loss": 2.5039,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.01,
414
+ "learning_rate": 0.00034,
415
+ "loss": 2.4039,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.01,
420
+ "learning_rate": 0.000345,
421
+ "loss": 2.3924,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.01,
426
+ "learning_rate": 0.00035,
427
+ "loss": 2.3745,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.01,
432
+ "learning_rate": 0.000355,
433
+ "loss": 2.3098,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.01,
438
+ "learning_rate": 0.00035999999999999997,
439
+ "loss": 2.3694,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.01,
444
+ "learning_rate": 0.000365,
445
+ "loss": 2.3753,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.01,
450
+ "learning_rate": 0.00037,
451
+ "loss": 2.2472,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.01,
456
+ "learning_rate": 0.000375,
457
+ "loss": 2.402,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.01,
462
+ "learning_rate": 0.00038,
463
+ "loss": 2.4102,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.01,
468
+ "learning_rate": 0.00038500000000000003,
469
+ "loss": 2.459,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.01,
474
+ "learning_rate": 0.00039000000000000005,
475
+ "loss": 2.3445,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.01,
480
+ "learning_rate": 0.000395,
481
+ "loss": 2.3456,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.01,
486
+ "learning_rate": 0.0004,
487
+ "loss": 2.399,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.01,
492
+ "learning_rate": 0.00040500000000000003,
493
+ "loss": 2.3885,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.01,
498
+ "learning_rate": 0.00041,
499
+ "loss": 2.4083,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.01,
504
+ "learning_rate": 0.000415,
505
+ "loss": 2.3559,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.01,
510
+ "learning_rate": 0.00042,
511
+ "loss": 2.3256,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.01,
516
+ "learning_rate": 0.000425,
517
+ "loss": 2.3741,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.01,
522
+ "learning_rate": 0.00043,
523
+ "loss": 2.3922,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.01,
528
+ "learning_rate": 0.000435,
529
+ "loss": 2.4278,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.01,
534
+ "learning_rate": 0.00044,
535
+ "loss": 2.3309,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.01,
540
+ "learning_rate": 0.00044500000000000003,
541
+ "loss": 2.3462,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.01,
546
+ "learning_rate": 0.00045000000000000004,
547
+ "loss": 2.4298,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.02,
552
+ "learning_rate": 0.000455,
553
+ "loss": 2.3494,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.02,
558
+ "learning_rate": 0.00046,
559
+ "loss": 2.3557,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.02,
564
+ "learning_rate": 0.000465,
565
+ "loss": 2.3381,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.02,
570
+ "learning_rate": 0.00047,
571
+ "loss": 2.396,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.02,
576
+ "learning_rate": 0.000475,
577
+ "loss": 2.3382,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.02,
582
+ "learning_rate": 0.00048,
583
+ "loss": 2.3339,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.02,
588
+ "learning_rate": 0.00048499999999999997,
589
+ "loss": 2.384,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.02,
594
+ "learning_rate": 0.00049,
595
+ "loss": 2.3916,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.02,
600
+ "learning_rate": 0.000495,
601
+ "loss": 2.2884,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.02,
606
+ "learning_rate": 0.0005,
607
+ "loss": 2.4124,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.02,
612
+ "learning_rate": 0.0004999152542372881,
613
+ "loss": 2.4458,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.02,
618
+ "learning_rate": 0.0004998305084745763,
619
+ "loss": 2.3689,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.02,
624
+ "learning_rate": 0.0004997457627118644,
625
+ "loss": 2.3983,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.02,
630
+ "learning_rate": 0.0004996610169491526,
631
+ "loss": 2.4062,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.02,
636
+ "learning_rate": 0.0004995762711864407,
637
+ "loss": 2.3034,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.02,
642
+ "learning_rate": 0.0004994915254237289,
643
+ "loss": 2.3648,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.02,
648
+ "learning_rate": 0.0004994067796610169,
649
+ "loss": 2.3478,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.02,
654
+ "learning_rate": 0.0004993220338983051,
655
+ "loss": 2.4845,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.02,
660
+ "learning_rate": 0.0004992372881355932,
661
+ "loss": 2.3216,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.02,
666
+ "learning_rate": 0.0004991525423728814,
667
+ "loss": 2.433,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.02,
672
+ "learning_rate": 0.0004990677966101695,
673
+ "loss": 2.4103,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.02,
678
+ "learning_rate": 0.0004989830508474577,
679
+ "loss": 2.3842,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.02,
684
+ "learning_rate": 0.0004988983050847458,
685
+ "loss": 2.3335,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.02,
690
+ "learning_rate": 0.000498813559322034,
691
+ "loss": 2.3887,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.02,
696
+ "learning_rate": 0.0004987288135593221,
697
+ "loss": 2.3307,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.02,
702
+ "learning_rate": 0.0004986440677966102,
703
+ "loss": 2.313,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.02,
708
+ "learning_rate": 0.0004985593220338983,
709
+ "loss": 2.3206,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.02,
714
+ "learning_rate": 0.0004984745762711864,
715
+ "loss": 2.39,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.02,
720
+ "learning_rate": 0.0004983898305084746,
721
+ "loss": 2.4717,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.02,
726
+ "learning_rate": 0.0004983050847457627,
727
+ "loss": 2.3574,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.02,
732
+ "learning_rate": 0.0004982203389830509,
733
+ "loss": 2.4505,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.02,
738
+ "learning_rate": 0.000498135593220339,
739
+ "loss": 2.3297,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.02,
744
+ "learning_rate": 0.0004980508474576272,
745
+ "loss": 2.3063,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.02,
750
+ "learning_rate": 0.0004979661016949153,
751
+ "loss": 2.3955,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.02,
756
+ "learning_rate": 0.0004978813559322035,
757
+ "loss": 2.3589,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.02,
762
+ "learning_rate": 0.0004977966101694915,
763
+ "loss": 2.337,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.02,
768
+ "learning_rate": 0.0004977118644067796,
769
+ "loss": 2.3332,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.02,
774
+ "learning_rate": 0.0004976271186440678,
775
+ "loss": 2.3803,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.02,
780
+ "learning_rate": 0.0004975423728813559,
781
+ "loss": 2.3611,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.02,
786
+ "learning_rate": 0.0004974576271186441,
787
+ "loss": 2.3554,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.02,
792
+ "learning_rate": 0.0004973728813559322,
793
+ "loss": 2.4101,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.02,
798
+ "learning_rate": 0.0004972881355932204,
799
+ "loss": 2.4309,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.02,
804
+ "learning_rate": 0.0004972033898305085,
805
+ "loss": 2.28,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.02,
810
+ "learning_rate": 0.0004971186440677967,
811
+ "loss": 2.4093,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.02,
816
+ "learning_rate": 0.0004970338983050847,
817
+ "loss": 2.4303,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.02,
822
+ "learning_rate": 0.0004969491525423728,
823
+ "loss": 2.4194,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.02,
828
+ "learning_rate": 0.000496864406779661,
829
+ "loss": 2.4032,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.02,
834
+ "learning_rate": 0.0004967796610169491,
835
+ "loss": 2.3526,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.02,
840
+ "learning_rate": 0.0004966949152542373,
841
+ "loss": 2.3505,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.02,
846
+ "learning_rate": 0.0004966101694915254,
847
+ "loss": 2.3653,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.02,
852
+ "learning_rate": 0.0004965254237288136,
853
+ "loss": 2.2969,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.02,
858
+ "learning_rate": 0.0004964406779661017,
859
+ "loss": 2.3262,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.02,
864
+ "learning_rate": 0.0004963559322033899,
865
+ "loss": 2.2601,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.02,
870
+ "learning_rate": 0.000496271186440678,
871
+ "loss": 2.4252,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.02,
876
+ "learning_rate": 0.000496186440677966,
877
+ "loss": 2.34,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.02,
882
+ "learning_rate": 0.0004961016949152542,
883
+ "loss": 2.372,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.02,
888
+ "learning_rate": 0.0004960169491525423,
889
+ "loss": 2.296,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.02,
894
+ "learning_rate": 0.0004959322033898305,
895
+ "loss": 2.2997,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.02,
900
+ "learning_rate": 0.0004958474576271186,
901
+ "loss": 2.2999,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.03,
906
+ "learning_rate": 0.0004957627118644068,
907
+ "loss": 2.3452,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.03,
912
+ "learning_rate": 0.0004956779661016949,
913
+ "loss": 2.2956,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.03,
918
+ "learning_rate": 0.0004955932203389831,
919
+ "loss": 2.2542,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.03,
924
+ "learning_rate": 0.0004955084745762712,
925
+ "loss": 2.2831,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.03,
930
+ "learning_rate": 0.0004954237288135594,
931
+ "loss": 2.3547,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.03,
936
+ "learning_rate": 0.0004953389830508474,
937
+ "loss": 2.2986,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.03,
942
+ "learning_rate": 0.0004952542372881356,
943
+ "loss": 2.3739,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.03,
948
+ "learning_rate": 0.0004951694915254237,
949
+ "loss": 2.3628,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.03,
954
+ "learning_rate": 0.0004950847457627119,
955
+ "loss": 2.3686,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.03,
960
+ "learning_rate": 0.000495,
961
+ "loss": 2.3178,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.03,
966
+ "learning_rate": 0.0004949152542372882,
967
+ "loss": 2.2912,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.03,
972
+ "learning_rate": 0.0004948305084745763,
973
+ "loss": 2.2516,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 0.03,
978
+ "learning_rate": 0.0004947457627118645,
979
+ "loss": 2.3826,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 0.03,
984
+ "learning_rate": 0.0004946610169491526,
985
+ "loss": 2.3779,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 0.03,
990
+ "learning_rate": 0.0004945762711864406,
991
+ "loss": 2.407,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 0.03,
996
+ "learning_rate": 0.0004944915254237288,
997
+ "loss": 2.3459,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 0.03,
1002
+ "learning_rate": 0.0004944067796610169,
1003
+ "loss": 2.3394,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 0.03,
1008
+ "learning_rate": 0.0004943220338983051,
1009
+ "loss": 2.3575,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 0.03,
1014
+ "learning_rate": 0.0004942372881355932,
1015
+ "loss": 2.337,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 0.03,
1020
+ "learning_rate": 0.0004941525423728814,
1021
+ "loss": 2.2534,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 0.03,
1026
+ "learning_rate": 0.0004940677966101695,
1027
+ "loss": 2.3056,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 0.03,
1032
+ "learning_rate": 0.0004939830508474577,
1033
+ "loss": 2.3595,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 0.03,
1038
+ "learning_rate": 0.0004938983050847458,
1039
+ "loss": 2.2519,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 0.03,
1044
+ "learning_rate": 0.000493813559322034,
1045
+ "loss": 2.2968,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 0.03,
1050
+ "learning_rate": 0.000493728813559322,
1051
+ "loss": 2.3444,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 0.03,
1056
+ "learning_rate": 0.0004936440677966102,
1057
+ "loss": 2.2988,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 0.03,
1062
+ "learning_rate": 0.0004935593220338983,
1063
+ "loss": 2.2193,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 0.03,
1068
+ "learning_rate": 0.0004934745762711865,
1069
+ "loss": 2.325,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 0.03,
1074
+ "learning_rate": 0.0004933898305084746,
1075
+ "loss": 2.3135,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 0.03,
1080
+ "learning_rate": 0.0004933050847457628,
1081
+ "loss": 2.2869,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 0.03,
1086
+ "learning_rate": 0.0004932203389830509,
1087
+ "loss": 2.371,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 0.03,
1092
+ "learning_rate": 0.000493135593220339,
1093
+ "loss": 2.3293,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 0.03,
1098
+ "learning_rate": 0.0004930508474576272,
1099
+ "loss": 2.2483,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 0.03,
1104
+ "learning_rate": 0.0004929661016949152,
1105
+ "loss": 2.317,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 0.03,
1110
+ "learning_rate": 0.0004928813559322034,
1111
+ "loss": 2.3836,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 0.03,
1116
+ "learning_rate": 0.0004927966101694915,
1117
+ "loss": 2.3599,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 0.03,
1122
+ "learning_rate": 0.0004927118644067797,
1123
+ "loss": 2.2669,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 0.03,
1128
+ "learning_rate": 0.0004926271186440678,
1129
+ "loss": 2.3605,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 0.03,
1134
+ "learning_rate": 0.000492542372881356,
1135
+ "loss": 2.2419,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 0.03,
1140
+ "learning_rate": 0.0004924576271186441,
1141
+ "loss": 2.3,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 0.03,
1146
+ "learning_rate": 0.0004923728813559322,
1147
+ "loss": 2.304,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 0.03,
1152
+ "learning_rate": 0.0004922881355932204,
1153
+ "loss": 2.3371,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 0.03,
1158
+ "learning_rate": 0.0004922033898305085,
1159
+ "loss": 2.3064,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 0.03,
1164
+ "learning_rate": 0.0004921186440677966,
1165
+ "loss": 2.2496,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 0.03,
1170
+ "learning_rate": 0.0004920338983050847,
1171
+ "loss": 2.3298,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 0.03,
1176
+ "learning_rate": 0.0004919491525423729,
1177
+ "loss": 2.3429,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 0.03,
1182
+ "learning_rate": 0.000491864406779661,
1183
+ "loss": 2.2897,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 0.03,
1188
+ "learning_rate": 0.0004917796610169492,
1189
+ "loss": 2.3197,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 0.03,
1194
+ "learning_rate": 0.0004916949152542373,
1195
+ "loss": 2.2984,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 0.03,
1200
+ "learning_rate": 0.0004916101694915254,
1201
+ "loss": 2.2688,
1202
+ "step": 199
1203
+ },
1204
+ {
1205
+ "epoch": 0.03,
1206
+ "learning_rate": 0.0004915254237288136,
1207
+ "loss": 2.3088,
1208
+ "step": 200
1209
+ },
1210
+ {
1211
+ "epoch": 0.03,
1212
+ "learning_rate": 0.0004914406779661017,
1213
+ "loss": 2.2954,
1214
+ "step": 201
1215
+ },
1216
+ {
1217
+ "epoch": 0.03,
1218
+ "learning_rate": 0.0004913559322033899,
1219
+ "loss": 2.2482,
1220
+ "step": 202
1221
+ },
1222
+ {
1223
+ "epoch": 0.03,
1224
+ "learning_rate": 0.0004912711864406779,
1225
+ "loss": 2.2175,
1226
+ "step": 203
1227
+ },
1228
+ {
1229
+ "epoch": 0.03,
1230
+ "learning_rate": 0.0004911864406779661,
1231
+ "loss": 2.2773,
1232
+ "step": 204
1233
+ },
1234
+ {
1235
+ "epoch": 0.03,
1236
+ "learning_rate": 0.0004911016949152542,
1237
+ "loss": 2.3321,
1238
+ "step": 205
1239
+ },
1240
+ {
1241
+ "epoch": 0.03,
1242
+ "learning_rate": 0.0004910169491525423,
1243
+ "loss": 2.2648,
1244
+ "step": 206
1245
+ },
1246
+ {
1247
+ "epoch": 0.03,
1248
+ "learning_rate": 0.0004909322033898305,
1249
+ "loss": 2.2507,
1250
+ "step": 207
1251
+ },
1252
+ {
1253
+ "epoch": 0.03,
1254
+ "learning_rate": 0.0004908474576271186,
1255
+ "loss": 2.3099,
1256
+ "step": 208
1257
+ },
1258
+ {
1259
+ "epoch": 0.03,
1260
+ "learning_rate": 0.0004907627118644068,
1261
+ "loss": 2.2771,
1262
+ "step": 209
1263
+ },
1264
+ {
1265
+ "epoch": 0.04,
1266
+ "learning_rate": 0.0004906779661016949,
1267
+ "loss": 2.3824,
1268
+ "step": 210
1269
+ },
1270
+ {
1271
+ "epoch": 0.04,
1272
+ "learning_rate": 0.0004905932203389831,
1273
+ "loss": 2.1398,
1274
+ "step": 211
1275
+ },
1276
+ {
1277
+ "epoch": 0.04,
1278
+ "learning_rate": 0.0004905084745762711,
1279
+ "loss": 2.2114,
1280
+ "step": 212
1281
+ },
1282
+ {
1283
+ "epoch": 0.04,
1284
+ "learning_rate": 0.0004904237288135593,
1285
+ "loss": 2.2262,
1286
+ "step": 213
1287
+ },
1288
+ {
1289
+ "epoch": 0.04,
1290
+ "learning_rate": 0.0004903389830508474,
1291
+ "loss": 2.2057,
1292
+ "step": 214
1293
+ },
1294
+ {
1295
+ "epoch": 0.04,
1296
+ "learning_rate": 0.0004902542372881356,
1297
+ "loss": 2.2878,
1298
+ "step": 215
1299
+ },
1300
+ {
1301
+ "epoch": 0.04,
1302
+ "learning_rate": 0.0004901694915254237,
1303
+ "loss": 2.2418,
1304
+ "step": 216
1305
+ },
1306
+ {
1307
+ "epoch": 0.04,
1308
+ "learning_rate": 0.0004900847457627119,
1309
+ "loss": 2.2456,
1310
+ "step": 217
1311
+ },
1312
+ {
1313
+ "epoch": 0.04,
1314
+ "learning_rate": 0.00049,
1315
+ "loss": 2.2267,
1316
+ "step": 218
1317
+ },
1318
+ {
1319
+ "epoch": 0.04,
1320
+ "learning_rate": 0.0004899152542372882,
1321
+ "loss": 2.1876,
1322
+ "step": 219
1323
+ },
1324
+ {
1325
+ "epoch": 0.04,
1326
+ "learning_rate": 0.0004898305084745763,
1327
+ "loss": 2.2439,
1328
+ "step": 220
1329
+ },
1330
+ {
1331
+ "epoch": 0.04,
1332
+ "learning_rate": 0.0004897457627118645,
1333
+ "loss": 2.1952,
1334
+ "step": 221
1335
+ },
1336
+ {
1337
+ "epoch": 0.04,
1338
+ "learning_rate": 0.0004896610169491525,
1339
+ "loss": 2.215,
1340
+ "step": 222
1341
+ },
1342
+ {
1343
+ "epoch": 0.04,
1344
+ "learning_rate": 0.0004895762711864407,
1345
+ "loss": 2.2313,
1346
+ "step": 223
1347
+ },
1348
+ {
1349
+ "epoch": 0.04,
1350
+ "learning_rate": 0.0004894915254237288,
1351
+ "loss": 2.2823,
1352
+ "step": 224
1353
+ },
1354
+ {
1355
+ "epoch": 0.04,
1356
+ "learning_rate": 0.0004894067796610169,
1357
+ "loss": 2.2705,
1358
+ "step": 225
1359
+ },
1360
+ {
1361
+ "epoch": 0.04,
1362
+ "learning_rate": 0.0004893220338983051,
1363
+ "loss": 2.167,
1364
+ "step": 226
1365
+ },
1366
+ {
1367
+ "epoch": 0.04,
1368
+ "learning_rate": 0.0004892372881355932,
1369
+ "loss": 2.2286,
1370
+ "step": 227
1371
+ },
1372
+ {
1373
+ "epoch": 0.04,
1374
+ "learning_rate": 0.0004891525423728814,
1375
+ "loss": 2.2877,
1376
+ "step": 228
1377
+ },
1378
+ {
1379
+ "epoch": 0.04,
1380
+ "learning_rate": 0.0004890677966101695,
1381
+ "loss": 2.2448,
1382
+ "step": 229
1383
+ },
1384
+ {
1385
+ "epoch": 0.04,
1386
+ "learning_rate": 0.0004889830508474577,
1387
+ "loss": 2.2232,
1388
+ "step": 230
1389
+ },
1390
+ {
1391
+ "epoch": 0.04,
1392
+ "learning_rate": 0.0004888983050847457,
1393
+ "loss": 2.2535,
1394
+ "step": 231
1395
+ },
1396
+ {
1397
+ "epoch": 0.04,
1398
+ "learning_rate": 0.0004888135593220339,
1399
+ "loss": 2.2222,
1400
+ "step": 232
1401
+ },
1402
+ {
1403
+ "epoch": 0.04,
1404
+ "learning_rate": 0.000488728813559322,
1405
+ "loss": 2.2819,
1406
+ "step": 233
1407
+ },
1408
+ {
1409
+ "epoch": 0.04,
1410
+ "learning_rate": 0.0004886440677966102,
1411
+ "loss": 2.1981,
1412
+ "step": 234
1413
+ },
1414
+ {
1415
+ "epoch": 0.04,
1416
+ "learning_rate": 0.0004885593220338983,
1417
+ "loss": 2.2716,
1418
+ "step": 235
1419
+ },
1420
+ {
1421
+ "epoch": 0.04,
1422
+ "learning_rate": 0.0004884745762711865,
1423
+ "loss": 2.2013,
1424
+ "step": 236
1425
+ },
1426
+ {
1427
+ "epoch": 0.04,
1428
+ "learning_rate": 0.0004883898305084746,
1429
+ "loss": 2.3319,
1430
+ "step": 237
1431
+ },
1432
+ {
1433
+ "epoch": 0.04,
1434
+ "learning_rate": 0.0004883050847457628,
1435
+ "loss": 2.2559,
1436
+ "step": 238
1437
+ },
1438
+ {
1439
+ "epoch": 0.04,
1440
+ "learning_rate": 0.00048822033898305087,
1441
+ "loss": 2.193,
1442
+ "step": 239
1443
+ },
1444
+ {
1445
+ "epoch": 0.04,
1446
+ "learning_rate": 0.000488135593220339,
1447
+ "loss": 2.2776,
1448
+ "step": 240
1449
+ },
1450
+ {
1451
+ "epoch": 0.04,
1452
+ "learning_rate": 0.00048805084745762715,
1453
+ "loss": 2.2398,
1454
+ "step": 241
1455
+ },
1456
+ {
1457
+ "epoch": 0.04,
1458
+ "learning_rate": 0.0004879661016949153,
1459
+ "loss": 2.2511,
1460
+ "step": 242
1461
+ },
1462
+ {
1463
+ "epoch": 0.04,
1464
+ "learning_rate": 0.0004878813559322034,
1465
+ "loss": 2.1962,
1466
+ "step": 243
1467
+ },
1468
+ {
1469
+ "epoch": 0.04,
1470
+ "learning_rate": 0.00048779661016949157,
1471
+ "loss": 2.2218,
1472
+ "step": 244
1473
+ },
1474
+ {
1475
+ "epoch": 0.04,
1476
+ "learning_rate": 0.00048771186440677965,
1477
+ "loss": 2.1811,
1478
+ "step": 245
1479
+ },
1480
+ {
1481
+ "epoch": 0.04,
1482
+ "learning_rate": 0.0004876271186440678,
1483
+ "loss": 2.2381,
1484
+ "step": 246
1485
+ },
1486
+ {
1487
+ "epoch": 0.04,
1488
+ "learning_rate": 0.00048754237288135593,
1489
+ "loss": 2.3434,
1490
+ "step": 247
1491
+ },
1492
+ {
1493
+ "epoch": 0.04,
1494
+ "learning_rate": 0.0004874576271186441,
1495
+ "loss": 2.2563,
1496
+ "step": 248
1497
+ },
1498
+ {
1499
+ "epoch": 0.04,
1500
+ "learning_rate": 0.0004873728813559322,
1501
+ "loss": 2.2949,
1502
+ "step": 249
1503
+ },
1504
+ {
1505
+ "epoch": 0.04,
1506
+ "learning_rate": 0.0004872881355932203,
1507
+ "loss": 2.2758,
1508
+ "step": 250
1509
+ },
1510
+ {
1511
+ "epoch": 0.04,
1512
+ "eval_gen_len": 19.0,
1513
+ "eval_loss": 1.9963864088058472,
1514
+ "eval_rouge1": 0.2486,
1515
+ "eval_rouge2": 0.0909,
1516
+ "eval_rougeL": 0.2094,
1517
+ "eval_rougeLsum": 0.2095,
1518
+ "eval_runtime": 125.5893,
1519
+ "eval_samples_per_second": 1.592,
1520
+ "eval_steps_per_second": 0.199,
1521
+ "step": 250
1522
+ }
1523
+ ],
1524
+ "max_steps": 6000,
1525
+ "num_train_epochs": 9223372036854775807,
1526
+ "total_flos": 5.876308597389558e+17,
1527
+ "trial_name": null,
1528
+ "trial_params": null
1529
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90ad9fb0069c958005282374fec83368bb8274554af1728a3f0cc925c136c927
3
+ size 5371
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f6ae4a54d9d6b8a3bb6ba480a9bcdcda69e0ca282fc7d1ac0107196645bb7c
3
+ size 4970010649
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df39d1fc39c686038078faca93a76cbae9e199a3b652997417ef370ad8c5677
3
+ size 4555103
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1aeab8f9f01e0f5c8f9b8e06e3c1546696dff62a47a6729a0f91aaa24c98da4
3
+ size 16795620
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "extra_ids": 0,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "tokenizer_class": "T5Tokenizer",
10
+ "unk_token": "<unk>"
11
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90ad9fb0069c958005282374fec83368bb8274554af1728a3f0cc925c136c927
3
+ size 5371