barghavani commited on
Commit
39170e4
1 Parent(s): f0b2d50

Upload 4 files

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +1 -0
  2. trainer_state.json +280 -0
  3. training_args.bin +2 -2
  4. vocab.json +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
trainer_state.json ADDED
@@ -0,0 +1,280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 11.0,
5
+ "global_step": 221540,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.25,
12
+ "learning_rate": 9.909609120521173e-05,
13
+ "loss": 2.4473,
14
+ "step": 5000
15
+ },
16
+ {
17
+ "epoch": 0.5,
18
+ "learning_rate": 9.796530039811799e-05,
19
+ "loss": 1.8064,
20
+ "step": 10000
21
+ },
22
+ {
23
+ "epoch": 0.74,
24
+ "learning_rate": 9.683473579442635e-05,
25
+ "loss": 1.6957,
26
+ "step": 15000
27
+ },
28
+ {
29
+ "epoch": 0.99,
30
+ "learning_rate": 9.570417119073471e-05,
31
+ "loss": 1.6302,
32
+ "step": 20000
33
+ },
34
+ {
35
+ "epoch": 1.24,
36
+ "learning_rate": 9.457383279044517e-05,
37
+ "loss": 1.5838,
38
+ "step": 25000
39
+ },
40
+ {
41
+ "epoch": 1.49,
42
+ "learning_rate": 9.344304198335143e-05,
43
+ "loss": 1.552,
44
+ "step": 30000
45
+ },
46
+ {
47
+ "epoch": 1.74,
48
+ "learning_rate": 9.23127035830619e-05,
49
+ "loss": 1.5235,
50
+ "step": 35000
51
+ },
52
+ {
53
+ "epoch": 1.99,
54
+ "learning_rate": 9.118236518277235e-05,
55
+ "loss": 1.5019,
56
+ "step": 40000
57
+ },
58
+ {
59
+ "epoch": 2.23,
60
+ "learning_rate": 9.005157437567862e-05,
61
+ "loss": 1.4807,
62
+ "step": 45000
63
+ },
64
+ {
65
+ "epoch": 2.48,
66
+ "learning_rate": 8.892100977198697e-05,
67
+ "loss": 1.4627,
68
+ "step": 50000
69
+ },
70
+ {
71
+ "epoch": 2.73,
72
+ "learning_rate": 8.779044516829533e-05,
73
+ "loss": 1.449,
74
+ "step": 55000
75
+ },
76
+ {
77
+ "epoch": 2.98,
78
+ "learning_rate": 8.665965436120159e-05,
79
+ "loss": 1.4371,
80
+ "step": 60000
81
+ },
82
+ {
83
+ "epoch": 3.23,
84
+ "learning_rate": 8.552931596091206e-05,
85
+ "loss": 1.4229,
86
+ "step": 65000
87
+ },
88
+ {
89
+ "epoch": 3.48,
90
+ "learning_rate": 8.439852515381831e-05,
91
+ "loss": 1.4127,
92
+ "step": 70000
93
+ },
94
+ {
95
+ "epoch": 3.72,
96
+ "learning_rate": 8.326773434672458e-05,
97
+ "loss": 1.4034,
98
+ "step": 75000
99
+ },
100
+ {
101
+ "epoch": 3.97,
102
+ "learning_rate": 8.213716974303293e-05,
103
+ "loss": 1.394,
104
+ "step": 80000
105
+ },
106
+ {
107
+ "epoch": 4.22,
108
+ "learning_rate": 8.100683134274339e-05,
109
+ "loss": 1.3822,
110
+ "step": 85000
111
+ },
112
+ {
113
+ "epoch": 4.47,
114
+ "learning_rate": 7.987581433224755e-05,
115
+ "loss": 1.3746,
116
+ "step": 90000
117
+ },
118
+ {
119
+ "epoch": 4.72,
120
+ "learning_rate": 7.874524972855593e-05,
121
+ "loss": 1.3659,
122
+ "step": 95000
123
+ },
124
+ {
125
+ "epoch": 4.97,
126
+ "learning_rate": 7.761468512486428e-05,
127
+ "loss": 1.3603,
128
+ "step": 100000
129
+ },
130
+ {
131
+ "epoch": 5.21,
132
+ "learning_rate": 7.648412052117264e-05,
133
+ "loss": 1.3509,
134
+ "step": 105000
135
+ },
136
+ {
137
+ "epoch": 5.46,
138
+ "learning_rate": 7.53533297140789e-05,
139
+ "loss": 1.3439,
140
+ "step": 110000
141
+ },
142
+ {
143
+ "epoch": 5.71,
144
+ "learning_rate": 7.422276511038726e-05,
145
+ "loss": 1.3389,
146
+ "step": 115000
147
+ },
148
+ {
149
+ "epoch": 5.96,
150
+ "learning_rate": 7.309220050669564e-05,
151
+ "loss": 1.3318,
152
+ "step": 120000
153
+ },
154
+ {
155
+ "epoch": 6.21,
156
+ "learning_rate": 7.196163590300398e-05,
157
+ "loss": 1.3233,
158
+ "step": 125000
159
+ },
160
+ {
161
+ "epoch": 6.45,
162
+ "learning_rate": 7.083107129931235e-05,
163
+ "loss": 1.3169,
164
+ "step": 130000
165
+ },
166
+ {
167
+ "epoch": 6.7,
168
+ "learning_rate": 6.97002804922186e-05,
169
+ "loss": 1.3104,
170
+ "step": 135000
171
+ },
172
+ {
173
+ "epoch": 6.95,
174
+ "learning_rate": 6.856994209192906e-05,
175
+ "loss": 1.3064,
176
+ "step": 140000
177
+ },
178
+ {
179
+ "epoch": 7.2,
180
+ "learning_rate": 6.743937748823743e-05,
181
+ "loss": 1.3007,
182
+ "step": 145000
183
+ },
184
+ {
185
+ "epoch": 7.45,
186
+ "learning_rate": 6.630858668114369e-05,
187
+ "loss": 1.2962,
188
+ "step": 150000
189
+ },
190
+ {
191
+ "epoch": 7.7,
192
+ "learning_rate": 6.517779587404995e-05,
193
+ "loss": 1.2915,
194
+ "step": 155000
195
+ },
196
+ {
197
+ "epoch": 7.94,
198
+ "learning_rate": 6.40470050669562e-05,
199
+ "loss": 1.2877,
200
+ "step": 160000
201
+ },
202
+ {
203
+ "epoch": 8.19,
204
+ "learning_rate": 6.291644046326457e-05,
205
+ "loss": 1.2783,
206
+ "step": 165000
207
+ },
208
+ {
209
+ "epoch": 8.44,
210
+ "learning_rate": 6.178564965617082e-05,
211
+ "loss": 1.2741,
212
+ "step": 170000
213
+ },
214
+ {
215
+ "epoch": 8.69,
216
+ "learning_rate": 6.065485884907709e-05,
217
+ "loss": 1.2705,
218
+ "step": 175000
219
+ },
220
+ {
221
+ "epoch": 8.94,
222
+ "learning_rate": 5.9524746652189655e-05,
223
+ "loss": 1.267,
224
+ "step": 180000
225
+ },
226
+ {
227
+ "epoch": 9.19,
228
+ "learning_rate": 5.839395584509592e-05,
229
+ "loss": 1.26,
230
+ "step": 185000
231
+ },
232
+ {
233
+ "epoch": 9.43,
234
+ "learning_rate": 5.7263391241404275e-05,
235
+ "loss": 1.2558,
236
+ "step": 190000
237
+ },
238
+ {
239
+ "epoch": 9.68,
240
+ "learning_rate": 5.613260043431053e-05,
241
+ "loss": 1.2531,
242
+ "step": 195000
243
+ },
244
+ {
245
+ "epoch": 9.93,
246
+ "learning_rate": 5.5002035830618894e-05,
247
+ "loss": 1.2492,
248
+ "step": 200000
249
+ },
250
+ {
251
+ "epoch": 10.18,
252
+ "learning_rate": 5.387124502352515e-05,
253
+ "loss": 1.2432,
254
+ "step": 205000
255
+ },
256
+ {
257
+ "epoch": 10.43,
258
+ "learning_rate": 5.274113282663772e-05,
259
+ "loss": 1.2391,
260
+ "step": 210000
261
+ },
262
+ {
263
+ "epoch": 10.68,
264
+ "learning_rate": 5.1610342019543975e-05,
265
+ "loss": 1.2347,
266
+ "step": 215000
267
+ },
268
+ {
269
+ "epoch": 10.92,
270
+ "learning_rate": 5.047977741585234e-05,
271
+ "loss": 1.231,
272
+ "step": 220000
273
+ }
274
+ ],
275
+ "max_steps": 443080,
276
+ "num_train_epochs": 22,
277
+ "total_flos": 7.46536345693738e+18,
278
+ "trial_name": null,
279
+ "trial_params": null
280
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16c18ed311ac42f92d5cd762d3f8e9844fe1d82eb565780cf4335553622aab47
3
- size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c9e0ecbf9a7cbe4296d2f5f31cd65dbebf3c105156255c5893727a3dd74bc2
3
+ size 2863
vocab.json ADDED
The diff for this file is too large to render. See raw diff