BlueDice commited on
Commit
07d602d
1 Parent(s): 5d9351e

Upload 11 files

Browse files
README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
adapter_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "tiiuae/falcon-7b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "layers_pattern": null,
8
+ "layers_to_transform": null,
9
+ "lora_alpha": 16,
10
+ "lora_dropout": 0.1,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 64,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "query_key_value"
17
+ ],
18
+ "task_type": "CAUSAL_LM"
19
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff88ee14af27c536377a623a5e6115612783ec863e469495320e42bb6a7de6bc
3
+ size 75521265
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15093583b34bc9b6aca3de095b3723ed380c174fa7aabea66b020c7639aef2c
3
+ size 151034501
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0054ab436a1e9769b804245c7399d978c851e5a51f9745777e734847b368990
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,1816 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.09129779820143337,
5
+ "global_step": 3000,
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": 0.0002,
13
+ "loss": 1.3803,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.3337,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.0002,
25
+ "loss": 1.2441,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 0.0002,
31
+ "loss": 1.1725,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.0309,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.0,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.0798,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "learning_rate": 0.0002,
49
+ "loss": 1.0219,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.0,
54
+ "learning_rate": 0.0002,
55
+ "loss": 1.02,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.0,
60
+ "learning_rate": 0.0002,
61
+ "loss": 0.9901,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.0,
66
+ "learning_rate": 0.0002,
67
+ "loss": 1.0439,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.0,
72
+ "learning_rate": 0.0002,
73
+ "loss": 1.0914,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.0,
78
+ "learning_rate": 0.0002,
79
+ "loss": 1.0088,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.0,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.9834,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.0,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.9685,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.0,
96
+ "learning_rate": 0.0002,
97
+ "loss": 0.9806,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.0,
102
+ "learning_rate": 0.0002,
103
+ "loss": 1.0164,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.01,
108
+ "learning_rate": 0.0002,
109
+ "loss": 1.0643,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.01,
114
+ "learning_rate": 0.0002,
115
+ "loss": 1.0656,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.01,
120
+ "learning_rate": 0.0002,
121
+ "loss": 1.0099,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.01,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.9956,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.01,
132
+ "learning_rate": 0.0002,
133
+ "loss": 1.0152,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.01,
138
+ "learning_rate": 0.0002,
139
+ "loss": 1.0031,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.01,
144
+ "learning_rate": 0.0002,
145
+ "loss": 1.0391,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.01,
150
+ "learning_rate": 0.0002,
151
+ "loss": 1.0417,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.01,
156
+ "learning_rate": 0.0002,
157
+ "loss": 0.9857,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.01,
162
+ "learning_rate": 0.0002,
163
+ "loss": 1.0188,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.01,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.9936,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.01,
174
+ "learning_rate": 0.0002,
175
+ "loss": 1.0099,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.01,
180
+ "learning_rate": 0.0002,
181
+ "loss": 0.9806,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.01,
186
+ "learning_rate": 0.0002,
187
+ "loss": 0.9884,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.01,
192
+ "learning_rate": 0.0002,
193
+ "loss": 0.9624,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.01,
198
+ "learning_rate": 0.0002,
199
+ "loss": 1.0911,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.01,
204
+ "learning_rate": 0.0002,
205
+ "loss": 1.0252,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.01,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.9595,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.01,
216
+ "learning_rate": 0.0002,
217
+ "loss": 0.9734,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.01,
222
+ "learning_rate": 0.0002,
223
+ "loss": 1.0987,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.01,
228
+ "learning_rate": 0.0002,
229
+ "loss": 1.0043,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.01,
234
+ "learning_rate": 0.0002,
235
+ "loss": 0.9461,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.01,
240
+ "learning_rate": 0.0002,
241
+ "loss": 1.0114,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.01,
246
+ "learning_rate": 0.0002,
247
+ "loss": 1.0184,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.01,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.0324,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.01,
258
+ "learning_rate": 0.0002,
259
+ "loss": 0.9781,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.01,
264
+ "learning_rate": 0.0002,
265
+ "loss": 1.0477,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.01,
270
+ "learning_rate": 0.0002,
271
+ "loss": 1.0079,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.01,
276
+ "learning_rate": 0.0002,
277
+ "loss": 1.0152,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.01,
282
+ "learning_rate": 0.0002,
283
+ "loss": 1.0896,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.01,
288
+ "learning_rate": 0.0002,
289
+ "loss": 1.0354,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.01,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.021,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.01,
300
+ "learning_rate": 0.0002,
301
+ "loss": 1.0111,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.02,
306
+ "learning_rate": 0.0002,
307
+ "loss": 1.0117,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.02,
312
+ "learning_rate": 0.0002,
313
+ "loss": 0.8965,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.02,
318
+ "learning_rate": 0.0002,
319
+ "loss": 0.8824,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.02,
324
+ "learning_rate": 0.0002,
325
+ "loss": 1.0408,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.02,
330
+ "learning_rate": 0.0002,
331
+ "loss": 1.022,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 0.02,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.054,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 0.02,
342
+ "learning_rate": 0.0002,
343
+ "loss": 1.0033,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 0.02,
348
+ "learning_rate": 0.0002,
349
+ "loss": 0.9612,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 0.02,
354
+ "learning_rate": 0.0002,
355
+ "loss": 0.9815,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 0.02,
360
+ "learning_rate": 0.0002,
361
+ "loss": 0.9495,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 0.02,
366
+ "learning_rate": 0.0002,
367
+ "loss": 0.9638,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 0.02,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.0592,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 0.02,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.9494,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 0.02,
384
+ "learning_rate": 0.0002,
385
+ "loss": 0.9956,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 0.02,
390
+ "learning_rate": 0.0002,
391
+ "loss": 1.0092,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 0.02,
396
+ "learning_rate": 0.0002,
397
+ "loss": 0.9631,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 0.02,
402
+ "learning_rate": 0.0002,
403
+ "loss": 1.0697,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 0.02,
408
+ "learning_rate": 0.0002,
409
+ "loss": 0.9548,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 0.02,
414
+ "learning_rate": 0.0002,
415
+ "loss": 0.9526,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 0.02,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.9932,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 0.02,
426
+ "learning_rate": 0.0002,
427
+ "loss": 1.0089,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 0.02,
432
+ "learning_rate": 0.0002,
433
+ "loss": 0.954,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 0.02,
438
+ "learning_rate": 0.0002,
439
+ "loss": 0.9754,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 0.02,
444
+ "learning_rate": 0.0002,
445
+ "loss": 1.0265,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 0.02,
450
+ "learning_rate": 0.0002,
451
+ "loss": 0.935,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 0.02,
456
+ "learning_rate": 0.0002,
457
+ "loss": 0.9285,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 0.02,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.9833,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 0.02,
468
+ "learning_rate": 0.0002,
469
+ "loss": 1.0277,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 0.02,
474
+ "learning_rate": 0.0002,
475
+ "loss": 0.98,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 0.02,
480
+ "learning_rate": 0.0002,
481
+ "loss": 0.8923,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 0.02,
486
+ "learning_rate": 0.0002,
487
+ "loss": 0.9666,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 0.02,
492
+ "learning_rate": 0.0002,
493
+ "loss": 0.9348,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 0.02,
498
+ "learning_rate": 0.0002,
499
+ "loss": 0.9661,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 0.03,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.9496,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 0.03,
510
+ "learning_rate": 0.0002,
511
+ "loss": 0.9591,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 0.03,
516
+ "learning_rate": 0.0002,
517
+ "loss": 0.9039,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 0.03,
522
+ "learning_rate": 0.0002,
523
+ "loss": 1.0044,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 0.03,
528
+ "learning_rate": 0.0002,
529
+ "loss": 0.9644,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 0.03,
534
+ "learning_rate": 0.0002,
535
+ "loss": 0.9052,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 0.03,
540
+ "learning_rate": 0.0002,
541
+ "loss": 0.991,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 0.03,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.9923,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 0.03,
552
+ "learning_rate": 0.0002,
553
+ "loss": 0.9085,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 0.03,
558
+ "learning_rate": 0.0002,
559
+ "loss": 0.9585,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 0.03,
564
+ "learning_rate": 0.0002,
565
+ "loss": 1.0032,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 0.03,
570
+ "learning_rate": 0.0002,
571
+ "loss": 0.964,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 0.03,
576
+ "learning_rate": 0.0002,
577
+ "loss": 0.9842,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 0.03,
582
+ "learning_rate": 0.0002,
583
+ "loss": 0.9337,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 0.03,
588
+ "learning_rate": 0.0002,
589
+ "loss": 1.0089,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 0.03,
594
+ "learning_rate": 0.0002,
595
+ "loss": 0.972,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 0.03,
600
+ "learning_rate": 0.0002,
601
+ "loss": 0.9441,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 0.03,
606
+ "learning_rate": 0.0002,
607
+ "loss": 0.97,
608
+ "step": 1000
609
+ },
610
+ {
611
+ "epoch": 0.03,
612
+ "learning_rate": 0.0002,
613
+ "loss": 1.0198,
614
+ "step": 1010
615
+ },
616
+ {
617
+ "epoch": 0.03,
618
+ "learning_rate": 0.0002,
619
+ "loss": 0.9641,
620
+ "step": 1020
621
+ },
622
+ {
623
+ "epoch": 0.03,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0165,
626
+ "step": 1030
627
+ },
628
+ {
629
+ "epoch": 0.03,
630
+ "learning_rate": 0.0002,
631
+ "loss": 0.9627,
632
+ "step": 1040
633
+ },
634
+ {
635
+ "epoch": 0.03,
636
+ "learning_rate": 0.0002,
637
+ "loss": 0.9617,
638
+ "step": 1050
639
+ },
640
+ {
641
+ "epoch": 0.03,
642
+ "learning_rate": 0.0002,
643
+ "loss": 1.0183,
644
+ "step": 1060
645
+ },
646
+ {
647
+ "epoch": 0.03,
648
+ "learning_rate": 0.0002,
649
+ "loss": 0.9691,
650
+ "step": 1070
651
+ },
652
+ {
653
+ "epoch": 0.03,
654
+ "learning_rate": 0.0002,
655
+ "loss": 0.9649,
656
+ "step": 1080
657
+ },
658
+ {
659
+ "epoch": 0.03,
660
+ "learning_rate": 0.0002,
661
+ "loss": 0.982,
662
+ "step": 1090
663
+ },
664
+ {
665
+ "epoch": 0.03,
666
+ "learning_rate": 0.0002,
667
+ "loss": 0.9803,
668
+ "step": 1100
669
+ },
670
+ {
671
+ "epoch": 0.03,
672
+ "learning_rate": 0.0002,
673
+ "loss": 0.9636,
674
+ "step": 1110
675
+ },
676
+ {
677
+ "epoch": 0.03,
678
+ "learning_rate": 0.0002,
679
+ "loss": 0.886,
680
+ "step": 1120
681
+ },
682
+ {
683
+ "epoch": 0.03,
684
+ "learning_rate": 0.0002,
685
+ "loss": 0.9982,
686
+ "step": 1130
687
+ },
688
+ {
689
+ "epoch": 0.03,
690
+ "learning_rate": 0.0002,
691
+ "loss": 0.9705,
692
+ "step": 1140
693
+ },
694
+ {
695
+ "epoch": 0.03,
696
+ "learning_rate": 0.0002,
697
+ "loss": 1.0027,
698
+ "step": 1150
699
+ },
700
+ {
701
+ "epoch": 0.04,
702
+ "learning_rate": 0.0002,
703
+ "loss": 0.9387,
704
+ "step": 1160
705
+ },
706
+ {
707
+ "epoch": 0.04,
708
+ "learning_rate": 0.0002,
709
+ "loss": 0.9143,
710
+ "step": 1170
711
+ },
712
+ {
713
+ "epoch": 0.04,
714
+ "learning_rate": 0.0002,
715
+ "loss": 0.9035,
716
+ "step": 1180
717
+ },
718
+ {
719
+ "epoch": 0.04,
720
+ "learning_rate": 0.0002,
721
+ "loss": 0.8783,
722
+ "step": 1190
723
+ },
724
+ {
725
+ "epoch": 0.04,
726
+ "learning_rate": 0.0002,
727
+ "loss": 0.9509,
728
+ "step": 1200
729
+ },
730
+ {
731
+ "epoch": 0.04,
732
+ "learning_rate": 0.0002,
733
+ "loss": 0.9569,
734
+ "step": 1210
735
+ },
736
+ {
737
+ "epoch": 0.04,
738
+ "learning_rate": 0.0002,
739
+ "loss": 0.8368,
740
+ "step": 1220
741
+ },
742
+ {
743
+ "epoch": 0.04,
744
+ "learning_rate": 0.0002,
745
+ "loss": 0.9268,
746
+ "step": 1230
747
+ },
748
+ {
749
+ "epoch": 0.04,
750
+ "learning_rate": 0.0002,
751
+ "loss": 0.9476,
752
+ "step": 1240
753
+ },
754
+ {
755
+ "epoch": 0.04,
756
+ "learning_rate": 0.0002,
757
+ "loss": 0.9381,
758
+ "step": 1250
759
+ },
760
+ {
761
+ "epoch": 0.04,
762
+ "learning_rate": 0.0002,
763
+ "loss": 1.0091,
764
+ "step": 1260
765
+ },
766
+ {
767
+ "epoch": 0.04,
768
+ "learning_rate": 0.0002,
769
+ "loss": 0.9909,
770
+ "step": 1270
771
+ },
772
+ {
773
+ "epoch": 0.04,
774
+ "learning_rate": 0.0002,
775
+ "loss": 0.9118,
776
+ "step": 1280
777
+ },
778
+ {
779
+ "epoch": 0.04,
780
+ "learning_rate": 0.0002,
781
+ "loss": 0.8771,
782
+ "step": 1290
783
+ },
784
+ {
785
+ "epoch": 0.04,
786
+ "learning_rate": 0.0002,
787
+ "loss": 0.9878,
788
+ "step": 1300
789
+ },
790
+ {
791
+ "epoch": 0.04,
792
+ "learning_rate": 0.0002,
793
+ "loss": 0.8639,
794
+ "step": 1310
795
+ },
796
+ {
797
+ "epoch": 0.04,
798
+ "learning_rate": 0.0002,
799
+ "loss": 0.9659,
800
+ "step": 1320
801
+ },
802
+ {
803
+ "epoch": 0.04,
804
+ "learning_rate": 0.0002,
805
+ "loss": 0.9987,
806
+ "step": 1330
807
+ },
808
+ {
809
+ "epoch": 0.04,
810
+ "learning_rate": 0.0002,
811
+ "loss": 0.8601,
812
+ "step": 1340
813
+ },
814
+ {
815
+ "epoch": 0.04,
816
+ "learning_rate": 0.0002,
817
+ "loss": 0.8855,
818
+ "step": 1350
819
+ },
820
+ {
821
+ "epoch": 0.04,
822
+ "learning_rate": 0.0002,
823
+ "loss": 0.9642,
824
+ "step": 1360
825
+ },
826
+ {
827
+ "epoch": 0.04,
828
+ "learning_rate": 0.0002,
829
+ "loss": 0.995,
830
+ "step": 1370
831
+ },
832
+ {
833
+ "epoch": 0.04,
834
+ "learning_rate": 0.0002,
835
+ "loss": 0.9776,
836
+ "step": 1380
837
+ },
838
+ {
839
+ "epoch": 0.04,
840
+ "learning_rate": 0.0002,
841
+ "loss": 0.8586,
842
+ "step": 1390
843
+ },
844
+ {
845
+ "epoch": 0.04,
846
+ "learning_rate": 0.0002,
847
+ "loss": 0.9499,
848
+ "step": 1400
849
+ },
850
+ {
851
+ "epoch": 0.04,
852
+ "learning_rate": 0.0002,
853
+ "loss": 0.9452,
854
+ "step": 1410
855
+ },
856
+ {
857
+ "epoch": 0.04,
858
+ "learning_rate": 0.0002,
859
+ "loss": 0.9872,
860
+ "step": 1420
861
+ },
862
+ {
863
+ "epoch": 0.04,
864
+ "learning_rate": 0.0002,
865
+ "loss": 0.8904,
866
+ "step": 1430
867
+ },
868
+ {
869
+ "epoch": 0.04,
870
+ "learning_rate": 0.0002,
871
+ "loss": 0.9409,
872
+ "step": 1440
873
+ },
874
+ {
875
+ "epoch": 0.04,
876
+ "learning_rate": 0.0002,
877
+ "loss": 0.943,
878
+ "step": 1450
879
+ },
880
+ {
881
+ "epoch": 0.04,
882
+ "learning_rate": 0.0002,
883
+ "loss": 0.9506,
884
+ "step": 1460
885
+ },
886
+ {
887
+ "epoch": 0.04,
888
+ "learning_rate": 0.0002,
889
+ "loss": 0.9147,
890
+ "step": 1470
891
+ },
892
+ {
893
+ "epoch": 0.05,
894
+ "learning_rate": 0.0002,
895
+ "loss": 1.0112,
896
+ "step": 1480
897
+ },
898
+ {
899
+ "epoch": 0.05,
900
+ "learning_rate": 0.0002,
901
+ "loss": 0.9424,
902
+ "step": 1490
903
+ },
904
+ {
905
+ "epoch": 0.05,
906
+ "learning_rate": 0.0002,
907
+ "loss": 0.9972,
908
+ "step": 1500
909
+ },
910
+ {
911
+ "epoch": 0.05,
912
+ "learning_rate": 0.0002,
913
+ "loss": 0.9265,
914
+ "step": 1510
915
+ },
916
+ {
917
+ "epoch": 0.05,
918
+ "learning_rate": 0.0002,
919
+ "loss": 0.9094,
920
+ "step": 1520
921
+ },
922
+ {
923
+ "epoch": 0.05,
924
+ "learning_rate": 0.0002,
925
+ "loss": 0.9445,
926
+ "step": 1530
927
+ },
928
+ {
929
+ "epoch": 0.05,
930
+ "learning_rate": 0.0002,
931
+ "loss": 0.9099,
932
+ "step": 1540
933
+ },
934
+ {
935
+ "epoch": 0.05,
936
+ "learning_rate": 0.0002,
937
+ "loss": 1.01,
938
+ "step": 1550
939
+ },
940
+ {
941
+ "epoch": 0.05,
942
+ "learning_rate": 0.0002,
943
+ "loss": 0.9437,
944
+ "step": 1560
945
+ },
946
+ {
947
+ "epoch": 0.05,
948
+ "learning_rate": 0.0002,
949
+ "loss": 1.0227,
950
+ "step": 1570
951
+ },
952
+ {
953
+ "epoch": 0.05,
954
+ "learning_rate": 0.0002,
955
+ "loss": 0.9871,
956
+ "step": 1580
957
+ },
958
+ {
959
+ "epoch": 0.05,
960
+ "learning_rate": 0.0002,
961
+ "loss": 1.0391,
962
+ "step": 1590
963
+ },
964
+ {
965
+ "epoch": 0.05,
966
+ "learning_rate": 0.0002,
967
+ "loss": 0.9657,
968
+ "step": 1600
969
+ },
970
+ {
971
+ "epoch": 0.05,
972
+ "learning_rate": 0.0002,
973
+ "loss": 0.9544,
974
+ "step": 1610
975
+ },
976
+ {
977
+ "epoch": 0.05,
978
+ "learning_rate": 0.0002,
979
+ "loss": 1.0456,
980
+ "step": 1620
981
+ },
982
+ {
983
+ "epoch": 0.05,
984
+ "learning_rate": 0.0002,
985
+ "loss": 0.9691,
986
+ "step": 1630
987
+ },
988
+ {
989
+ "epoch": 0.05,
990
+ "learning_rate": 0.0002,
991
+ "loss": 0.9475,
992
+ "step": 1640
993
+ },
994
+ {
995
+ "epoch": 0.05,
996
+ "learning_rate": 0.0002,
997
+ "loss": 0.8787,
998
+ "step": 1650
999
+ },
1000
+ {
1001
+ "epoch": 0.05,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 0.9666,
1004
+ "step": 1660
1005
+ },
1006
+ {
1007
+ "epoch": 0.05,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 1.0333,
1010
+ "step": 1670
1011
+ },
1012
+ {
1013
+ "epoch": 0.05,
1014
+ "learning_rate": 0.0002,
1015
+ "loss": 0.9421,
1016
+ "step": 1680
1017
+ },
1018
+ {
1019
+ "epoch": 0.05,
1020
+ "learning_rate": 0.0002,
1021
+ "loss": 0.9393,
1022
+ "step": 1690
1023
+ },
1024
+ {
1025
+ "epoch": 0.05,
1026
+ "learning_rate": 0.0002,
1027
+ "loss": 0.9616,
1028
+ "step": 1700
1029
+ },
1030
+ {
1031
+ "epoch": 0.05,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 0.9476,
1034
+ "step": 1710
1035
+ },
1036
+ {
1037
+ "epoch": 0.05,
1038
+ "learning_rate": 0.0002,
1039
+ "loss": 0.9289,
1040
+ "step": 1720
1041
+ },
1042
+ {
1043
+ "epoch": 0.05,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 0.9501,
1046
+ "step": 1730
1047
+ },
1048
+ {
1049
+ "epoch": 0.05,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 0.881,
1052
+ "step": 1740
1053
+ },
1054
+ {
1055
+ "epoch": 0.05,
1056
+ "learning_rate": 0.0002,
1057
+ "loss": 0.9853,
1058
+ "step": 1750
1059
+ },
1060
+ {
1061
+ "epoch": 0.05,
1062
+ "learning_rate": 0.0002,
1063
+ "loss": 0.9345,
1064
+ "step": 1760
1065
+ },
1066
+ {
1067
+ "epoch": 0.05,
1068
+ "learning_rate": 0.0002,
1069
+ "loss": 0.9126,
1070
+ "step": 1770
1071
+ },
1072
+ {
1073
+ "epoch": 0.05,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 0.9986,
1076
+ "step": 1780
1077
+ },
1078
+ {
1079
+ "epoch": 0.05,
1080
+ "learning_rate": 0.0002,
1081
+ "loss": 0.8682,
1082
+ "step": 1790
1083
+ },
1084
+ {
1085
+ "epoch": 0.05,
1086
+ "learning_rate": 0.0002,
1087
+ "loss": 0.9062,
1088
+ "step": 1800
1089
+ },
1090
+ {
1091
+ "epoch": 0.06,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 0.9296,
1094
+ "step": 1810
1095
+ },
1096
+ {
1097
+ "epoch": 0.06,
1098
+ "learning_rate": 0.0002,
1099
+ "loss": 0.9232,
1100
+ "step": 1820
1101
+ },
1102
+ {
1103
+ "epoch": 0.06,
1104
+ "learning_rate": 0.0002,
1105
+ "loss": 0.9249,
1106
+ "step": 1830
1107
+ },
1108
+ {
1109
+ "epoch": 0.06,
1110
+ "learning_rate": 0.0002,
1111
+ "loss": 1.023,
1112
+ "step": 1840
1113
+ },
1114
+ {
1115
+ "epoch": 0.06,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 0.9832,
1118
+ "step": 1850
1119
+ },
1120
+ {
1121
+ "epoch": 0.06,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 0.9519,
1124
+ "step": 1860
1125
+ },
1126
+ {
1127
+ "epoch": 0.06,
1128
+ "learning_rate": 0.0002,
1129
+ "loss": 0.9197,
1130
+ "step": 1870
1131
+ },
1132
+ {
1133
+ "epoch": 0.06,
1134
+ "learning_rate": 0.0002,
1135
+ "loss": 0.9655,
1136
+ "step": 1880
1137
+ },
1138
+ {
1139
+ "epoch": 0.06,
1140
+ "learning_rate": 0.0002,
1141
+ "loss": 0.9643,
1142
+ "step": 1890
1143
+ },
1144
+ {
1145
+ "epoch": 0.06,
1146
+ "learning_rate": 0.0002,
1147
+ "loss": 1.0405,
1148
+ "step": 1900
1149
+ },
1150
+ {
1151
+ "epoch": 0.06,
1152
+ "learning_rate": 0.0002,
1153
+ "loss": 1.0085,
1154
+ "step": 1910
1155
+ },
1156
+ {
1157
+ "epoch": 0.06,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 0.9276,
1160
+ "step": 1920
1161
+ },
1162
+ {
1163
+ "epoch": 0.06,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 0.9849,
1166
+ "step": 1930
1167
+ },
1168
+ {
1169
+ "epoch": 0.06,
1170
+ "learning_rate": 0.0002,
1171
+ "loss": 0.9225,
1172
+ "step": 1940
1173
+ },
1174
+ {
1175
+ "epoch": 0.06,
1176
+ "learning_rate": 0.0002,
1177
+ "loss": 0.9259,
1178
+ "step": 1950
1179
+ },
1180
+ {
1181
+ "epoch": 0.06,
1182
+ "learning_rate": 0.0002,
1183
+ "loss": 0.9252,
1184
+ "step": 1960
1185
+ },
1186
+ {
1187
+ "epoch": 0.06,
1188
+ "learning_rate": 0.0002,
1189
+ "loss": 0.9021,
1190
+ "step": 1970
1191
+ },
1192
+ {
1193
+ "epoch": 0.06,
1194
+ "learning_rate": 0.0002,
1195
+ "loss": 0.8711,
1196
+ "step": 1980
1197
+ },
1198
+ {
1199
+ "epoch": 0.06,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 0.901,
1202
+ "step": 1990
1203
+ },
1204
+ {
1205
+ "epoch": 0.06,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 0.8468,
1208
+ "step": 2000
1209
+ },
1210
+ {
1211
+ "epoch": 0.06,
1212
+ "learning_rate": 0.0002,
1213
+ "loss": 0.9045,
1214
+ "step": 2010
1215
+ },
1216
+ {
1217
+ "epoch": 0.06,
1218
+ "learning_rate": 0.0002,
1219
+ "loss": 0.8878,
1220
+ "step": 2020
1221
+ },
1222
+ {
1223
+ "epoch": 0.06,
1224
+ "learning_rate": 0.0002,
1225
+ "loss": 0.8619,
1226
+ "step": 2030
1227
+ },
1228
+ {
1229
+ "epoch": 0.06,
1230
+ "learning_rate": 0.0002,
1231
+ "loss": 0.9264,
1232
+ "step": 2040
1233
+ },
1234
+ {
1235
+ "epoch": 0.06,
1236
+ "learning_rate": 0.0002,
1237
+ "loss": 0.9525,
1238
+ "step": 2050
1239
+ },
1240
+ {
1241
+ "epoch": 0.06,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 0.9764,
1244
+ "step": 2060
1245
+ },
1246
+ {
1247
+ "epoch": 0.06,
1248
+ "learning_rate": 0.0002,
1249
+ "loss": 0.9241,
1250
+ "step": 2070
1251
+ },
1252
+ {
1253
+ "epoch": 0.06,
1254
+ "learning_rate": 0.0002,
1255
+ "loss": 0.9806,
1256
+ "step": 2080
1257
+ },
1258
+ {
1259
+ "epoch": 0.06,
1260
+ "learning_rate": 0.0002,
1261
+ "loss": 0.956,
1262
+ "step": 2090
1263
+ },
1264
+ {
1265
+ "epoch": 0.06,
1266
+ "learning_rate": 0.0002,
1267
+ "loss": 0.9367,
1268
+ "step": 2100
1269
+ },
1270
+ {
1271
+ "epoch": 0.06,
1272
+ "learning_rate": 0.0002,
1273
+ "loss": 0.9141,
1274
+ "step": 2110
1275
+ },
1276
+ {
1277
+ "epoch": 0.06,
1278
+ "learning_rate": 0.0002,
1279
+ "loss": 0.9708,
1280
+ "step": 2120
1281
+ },
1282
+ {
1283
+ "epoch": 0.06,
1284
+ "learning_rate": 0.0002,
1285
+ "loss": 0.9426,
1286
+ "step": 2130
1287
+ },
1288
+ {
1289
+ "epoch": 0.07,
1290
+ "learning_rate": 0.0002,
1291
+ "loss": 1.0053,
1292
+ "step": 2140
1293
+ },
1294
+ {
1295
+ "epoch": 0.07,
1296
+ "learning_rate": 0.0002,
1297
+ "loss": 0.9219,
1298
+ "step": 2150
1299
+ },
1300
+ {
1301
+ "epoch": 0.07,
1302
+ "learning_rate": 0.0002,
1303
+ "loss": 0.8843,
1304
+ "step": 2160
1305
+ },
1306
+ {
1307
+ "epoch": 0.07,
1308
+ "learning_rate": 0.0002,
1309
+ "loss": 0.9406,
1310
+ "step": 2170
1311
+ },
1312
+ {
1313
+ "epoch": 0.07,
1314
+ "learning_rate": 0.0002,
1315
+ "loss": 0.8876,
1316
+ "step": 2180
1317
+ },
1318
+ {
1319
+ "epoch": 0.07,
1320
+ "learning_rate": 0.0002,
1321
+ "loss": 0.926,
1322
+ "step": 2190
1323
+ },
1324
+ {
1325
+ "epoch": 0.07,
1326
+ "learning_rate": 0.0002,
1327
+ "loss": 0.8407,
1328
+ "step": 2200
1329
+ },
1330
+ {
1331
+ "epoch": 0.07,
1332
+ "learning_rate": 0.0002,
1333
+ "loss": 0.9493,
1334
+ "step": 2210
1335
+ },
1336
+ {
1337
+ "epoch": 0.07,
1338
+ "learning_rate": 0.0002,
1339
+ "loss": 0.8798,
1340
+ "step": 2220
1341
+ },
1342
+ {
1343
+ "epoch": 0.07,
1344
+ "learning_rate": 0.0002,
1345
+ "loss": 1.0029,
1346
+ "step": 2230
1347
+ },
1348
+ {
1349
+ "epoch": 0.07,
1350
+ "learning_rate": 0.0002,
1351
+ "loss": 0.9553,
1352
+ "step": 2240
1353
+ },
1354
+ {
1355
+ "epoch": 0.07,
1356
+ "learning_rate": 0.0002,
1357
+ "loss": 0.9593,
1358
+ "step": 2250
1359
+ },
1360
+ {
1361
+ "epoch": 0.07,
1362
+ "learning_rate": 0.0002,
1363
+ "loss": 0.9283,
1364
+ "step": 2260
1365
+ },
1366
+ {
1367
+ "epoch": 0.07,
1368
+ "learning_rate": 0.0002,
1369
+ "loss": 0.9993,
1370
+ "step": 2270
1371
+ },
1372
+ {
1373
+ "epoch": 0.07,
1374
+ "learning_rate": 0.0002,
1375
+ "loss": 0.9466,
1376
+ "step": 2280
1377
+ },
1378
+ {
1379
+ "epoch": 0.07,
1380
+ "learning_rate": 0.0002,
1381
+ "loss": 0.9172,
1382
+ "step": 2290
1383
+ },
1384
+ {
1385
+ "epoch": 0.07,
1386
+ "learning_rate": 0.0002,
1387
+ "loss": 0.9388,
1388
+ "step": 2300
1389
+ },
1390
+ {
1391
+ "epoch": 0.07,
1392
+ "learning_rate": 0.0002,
1393
+ "loss": 0.9758,
1394
+ "step": 2310
1395
+ },
1396
+ {
1397
+ "epoch": 0.07,
1398
+ "learning_rate": 0.0002,
1399
+ "loss": 0.8882,
1400
+ "step": 2320
1401
+ },
1402
+ {
1403
+ "epoch": 0.07,
1404
+ "learning_rate": 0.0002,
1405
+ "loss": 0.9951,
1406
+ "step": 2330
1407
+ },
1408
+ {
1409
+ "epoch": 0.07,
1410
+ "learning_rate": 0.0002,
1411
+ "loss": 0.8381,
1412
+ "step": 2340
1413
+ },
1414
+ {
1415
+ "epoch": 0.07,
1416
+ "learning_rate": 0.0002,
1417
+ "loss": 0.9627,
1418
+ "step": 2350
1419
+ },
1420
+ {
1421
+ "epoch": 0.07,
1422
+ "learning_rate": 0.0002,
1423
+ "loss": 0.9466,
1424
+ "step": 2360
1425
+ },
1426
+ {
1427
+ "epoch": 0.07,
1428
+ "learning_rate": 0.0002,
1429
+ "loss": 0.9285,
1430
+ "step": 2370
1431
+ },
1432
+ {
1433
+ "epoch": 0.07,
1434
+ "learning_rate": 0.0002,
1435
+ "loss": 0.957,
1436
+ "step": 2380
1437
+ },
1438
+ {
1439
+ "epoch": 0.07,
1440
+ "learning_rate": 0.0002,
1441
+ "loss": 0.9736,
1442
+ "step": 2390
1443
+ },
1444
+ {
1445
+ "epoch": 0.07,
1446
+ "learning_rate": 0.0002,
1447
+ "loss": 0.9807,
1448
+ "step": 2400
1449
+ },
1450
+ {
1451
+ "epoch": 0.07,
1452
+ "learning_rate": 0.0002,
1453
+ "loss": 1.0236,
1454
+ "step": 2410
1455
+ },
1456
+ {
1457
+ "epoch": 0.07,
1458
+ "learning_rate": 0.0002,
1459
+ "loss": 0.8485,
1460
+ "step": 2420
1461
+ },
1462
+ {
1463
+ "epoch": 0.07,
1464
+ "learning_rate": 0.0002,
1465
+ "loss": 0.9149,
1466
+ "step": 2430
1467
+ },
1468
+ {
1469
+ "epoch": 0.07,
1470
+ "learning_rate": 0.0002,
1471
+ "loss": 0.9259,
1472
+ "step": 2440
1473
+ },
1474
+ {
1475
+ "epoch": 0.07,
1476
+ "learning_rate": 0.0002,
1477
+ "loss": 0.9503,
1478
+ "step": 2450
1479
+ },
1480
+ {
1481
+ "epoch": 0.07,
1482
+ "learning_rate": 0.0002,
1483
+ "loss": 0.9582,
1484
+ "step": 2460
1485
+ },
1486
+ {
1487
+ "epoch": 0.08,
1488
+ "learning_rate": 0.0002,
1489
+ "loss": 1.0169,
1490
+ "step": 2470
1491
+ },
1492
+ {
1493
+ "epoch": 0.08,
1494
+ "learning_rate": 0.0002,
1495
+ "loss": 0.9397,
1496
+ "step": 2480
1497
+ },
1498
+ {
1499
+ "epoch": 0.08,
1500
+ "learning_rate": 0.0002,
1501
+ "loss": 0.9938,
1502
+ "step": 2490
1503
+ },
1504
+ {
1505
+ "epoch": 0.08,
1506
+ "learning_rate": 0.0002,
1507
+ "loss": 0.8555,
1508
+ "step": 2500
1509
+ },
1510
+ {
1511
+ "epoch": 0.08,
1512
+ "learning_rate": 0.0002,
1513
+ "loss": 0.8988,
1514
+ "step": 2510
1515
+ },
1516
+ {
1517
+ "epoch": 0.08,
1518
+ "learning_rate": 0.0002,
1519
+ "loss": 1.0256,
1520
+ "step": 2520
1521
+ },
1522
+ {
1523
+ "epoch": 0.08,
1524
+ "learning_rate": 0.0002,
1525
+ "loss": 0.9576,
1526
+ "step": 2530
1527
+ },
1528
+ {
1529
+ "epoch": 0.08,
1530
+ "learning_rate": 0.0002,
1531
+ "loss": 0.9676,
1532
+ "step": 2540
1533
+ },
1534
+ {
1535
+ "epoch": 0.08,
1536
+ "learning_rate": 0.0002,
1537
+ "loss": 0.9335,
1538
+ "step": 2550
1539
+ },
1540
+ {
1541
+ "epoch": 0.08,
1542
+ "learning_rate": 0.0002,
1543
+ "loss": 0.893,
1544
+ "step": 2560
1545
+ },
1546
+ {
1547
+ "epoch": 0.08,
1548
+ "learning_rate": 0.0002,
1549
+ "loss": 0.928,
1550
+ "step": 2570
1551
+ },
1552
+ {
1553
+ "epoch": 0.08,
1554
+ "learning_rate": 0.0002,
1555
+ "loss": 0.9079,
1556
+ "step": 2580
1557
+ },
1558
+ {
1559
+ "epoch": 0.08,
1560
+ "learning_rate": 0.0002,
1561
+ "loss": 0.8933,
1562
+ "step": 2590
1563
+ },
1564
+ {
1565
+ "epoch": 0.08,
1566
+ "learning_rate": 0.0002,
1567
+ "loss": 0.864,
1568
+ "step": 2600
1569
+ },
1570
+ {
1571
+ "epoch": 0.08,
1572
+ "learning_rate": 0.0002,
1573
+ "loss": 0.9228,
1574
+ "step": 2610
1575
+ },
1576
+ {
1577
+ "epoch": 0.08,
1578
+ "learning_rate": 0.0002,
1579
+ "loss": 0.9285,
1580
+ "step": 2620
1581
+ },
1582
+ {
1583
+ "epoch": 0.08,
1584
+ "learning_rate": 0.0002,
1585
+ "loss": 0.9536,
1586
+ "step": 2630
1587
+ },
1588
+ {
1589
+ "epoch": 0.08,
1590
+ "learning_rate": 0.0002,
1591
+ "loss": 0.951,
1592
+ "step": 2640
1593
+ },
1594
+ {
1595
+ "epoch": 0.08,
1596
+ "learning_rate": 0.0002,
1597
+ "loss": 1.0,
1598
+ "step": 2650
1599
+ },
1600
+ {
1601
+ "epoch": 0.08,
1602
+ "learning_rate": 0.0002,
1603
+ "loss": 1.0455,
1604
+ "step": 2660
1605
+ },
1606
+ {
1607
+ "epoch": 0.08,
1608
+ "learning_rate": 0.0002,
1609
+ "loss": 0.9643,
1610
+ "step": 2670
1611
+ },
1612
+ {
1613
+ "epoch": 0.08,
1614
+ "learning_rate": 0.0002,
1615
+ "loss": 0.8923,
1616
+ "step": 2680
1617
+ },
1618
+ {
1619
+ "epoch": 0.08,
1620
+ "learning_rate": 0.0002,
1621
+ "loss": 0.9002,
1622
+ "step": 2690
1623
+ },
1624
+ {
1625
+ "epoch": 0.08,
1626
+ "learning_rate": 0.0002,
1627
+ "loss": 1.0016,
1628
+ "step": 2700
1629
+ },
1630
+ {
1631
+ "epoch": 0.08,
1632
+ "learning_rate": 0.0002,
1633
+ "loss": 0.9125,
1634
+ "step": 2710
1635
+ },
1636
+ {
1637
+ "epoch": 0.08,
1638
+ "learning_rate": 0.0002,
1639
+ "loss": 0.9887,
1640
+ "step": 2720
1641
+ },
1642
+ {
1643
+ "epoch": 0.08,
1644
+ "learning_rate": 0.0002,
1645
+ "loss": 1.0255,
1646
+ "step": 2730
1647
+ },
1648
+ {
1649
+ "epoch": 0.08,
1650
+ "learning_rate": 0.0002,
1651
+ "loss": 0.9858,
1652
+ "step": 2740
1653
+ },
1654
+ {
1655
+ "epoch": 0.08,
1656
+ "learning_rate": 0.0002,
1657
+ "loss": 0.9468,
1658
+ "step": 2750
1659
+ },
1660
+ {
1661
+ "epoch": 0.08,
1662
+ "learning_rate": 0.0002,
1663
+ "loss": 0.9565,
1664
+ "step": 2760
1665
+ },
1666
+ {
1667
+ "epoch": 0.08,
1668
+ "learning_rate": 0.0002,
1669
+ "loss": 1.0201,
1670
+ "step": 2770
1671
+ },
1672
+ {
1673
+ "epoch": 0.08,
1674
+ "learning_rate": 0.0002,
1675
+ "loss": 0.9704,
1676
+ "step": 2780
1677
+ },
1678
+ {
1679
+ "epoch": 0.08,
1680
+ "learning_rate": 0.0002,
1681
+ "loss": 0.9759,
1682
+ "step": 2790
1683
+ },
1684
+ {
1685
+ "epoch": 0.09,
1686
+ "learning_rate": 0.0002,
1687
+ "loss": 0.895,
1688
+ "step": 2800
1689
+ },
1690
+ {
1691
+ "epoch": 0.09,
1692
+ "learning_rate": 0.0002,
1693
+ "loss": 0.9373,
1694
+ "step": 2810
1695
+ },
1696
+ {
1697
+ "epoch": 0.09,
1698
+ "learning_rate": 0.0002,
1699
+ "loss": 0.9414,
1700
+ "step": 2820
1701
+ },
1702
+ {
1703
+ "epoch": 0.09,
1704
+ "learning_rate": 0.0002,
1705
+ "loss": 0.9096,
1706
+ "step": 2830
1707
+ },
1708
+ {
1709
+ "epoch": 0.09,
1710
+ "learning_rate": 0.0002,
1711
+ "loss": 0.9426,
1712
+ "step": 2840
1713
+ },
1714
+ {
1715
+ "epoch": 0.09,
1716
+ "learning_rate": 0.0002,
1717
+ "loss": 0.8934,
1718
+ "step": 2850
1719
+ },
1720
+ {
1721
+ "epoch": 0.09,
1722
+ "learning_rate": 0.0002,
1723
+ "loss": 1.013,
1724
+ "step": 2860
1725
+ },
1726
+ {
1727
+ "epoch": 0.09,
1728
+ "learning_rate": 0.0002,
1729
+ "loss": 0.9339,
1730
+ "step": 2870
1731
+ },
1732
+ {
1733
+ "epoch": 0.09,
1734
+ "learning_rate": 0.0002,
1735
+ "loss": 0.9608,
1736
+ "step": 2880
1737
+ },
1738
+ {
1739
+ "epoch": 0.09,
1740
+ "learning_rate": 0.0002,
1741
+ "loss": 0.9184,
1742
+ "step": 2890
1743
+ },
1744
+ {
1745
+ "epoch": 0.09,
1746
+ "learning_rate": 0.0002,
1747
+ "loss": 0.977,
1748
+ "step": 2900
1749
+ },
1750
+ {
1751
+ "epoch": 0.09,
1752
+ "learning_rate": 0.0002,
1753
+ "loss": 0.9927,
1754
+ "step": 2910
1755
+ },
1756
+ {
1757
+ "epoch": 0.09,
1758
+ "learning_rate": 0.0002,
1759
+ "loss": 0.95,
1760
+ "step": 2920
1761
+ },
1762
+ {
1763
+ "epoch": 0.09,
1764
+ "learning_rate": 0.0002,
1765
+ "loss": 0.9045,
1766
+ "step": 2930
1767
+ },
1768
+ {
1769
+ "epoch": 0.09,
1770
+ "learning_rate": 0.0002,
1771
+ "loss": 0.9568,
1772
+ "step": 2940
1773
+ },
1774
+ {
1775
+ "epoch": 0.09,
1776
+ "learning_rate": 0.0002,
1777
+ "loss": 1.0211,
1778
+ "step": 2950
1779
+ },
1780
+ {
1781
+ "epoch": 0.09,
1782
+ "learning_rate": 0.0002,
1783
+ "loss": 0.9487,
1784
+ "step": 2960
1785
+ },
1786
+ {
1787
+ "epoch": 0.09,
1788
+ "learning_rate": 0.0002,
1789
+ "loss": 0.9498,
1790
+ "step": 2970
1791
+ },
1792
+ {
1793
+ "epoch": 0.09,
1794
+ "learning_rate": 0.0002,
1795
+ "loss": 0.9003,
1796
+ "step": 2980
1797
+ },
1798
+ {
1799
+ "epoch": 0.09,
1800
+ "learning_rate": 0.0002,
1801
+ "loss": 0.9497,
1802
+ "step": 2990
1803
+ },
1804
+ {
1805
+ "epoch": 0.09,
1806
+ "learning_rate": 0.0002,
1807
+ "loss": 0.9718,
1808
+ "step": 3000
1809
+ }
1810
+ ],
1811
+ "max_steps": 10000,
1812
+ "num_train_epochs": 1,
1813
+ "total_flos": 2.44965925453824e+17,
1814
+ "trial_name": null,
1815
+ "trial_params": null
1816
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3e70dba9c082e370a11bf21034c220de8a3dfa8c37fafc62797175ef13eb26
3
+ size 3899