Fill-Mask
Transformers
PyTorch
4 languages
xlm-roberta
Inference Endpoints
5roop commited on
Commit
68e0c0c
1 Parent(s): 248ac9b

Upload 16 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlmrl_sl-bcms_exp/checkpoint-4000/",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.19.0.dev0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b75c04dc0c796cd5ccaec8fc706360ee7062da6245bf648bb691350aa0e676a
3
+ size 13623
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c365ec3c6594232b9538eb91703927ae2397a755def6460d25ffa9170919cdb0
3
+ size 13623
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67239be155f3ee42cd379ef1317071b5e270a1065df8470bc455458db2be0348
3
+ size 13623
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a112b3333173d3140c340082e44c9771019d62e5af1c6c01af80b6a38fa9b9
3
+ size 13623
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:812231e1117839fe43b26528fca71f1e9ec4914885acfb364484f2e88d4eb4dc
3
+ size 13623
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb83ad55bd773ac089261aed5aa3e9efe75accfdeae4a581cbceccdd3c45395
3
+ size 13623
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9563b1ee82a34c9e6619dae07d4e069e2a7018ef5e80c52128ecd42f9049ccb3
3
+ size 13623
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20f15a573426e23b56d1c33645ab44b199001836fa86f50919672e321db3501
3
+ size 13623
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11da03000c91298884c7ee520f5a3910dac998a2423fa3b1b4444963a544889
3
+ size 627
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlmrl_sl-bcms_exp/checkpoint-4000/", "tokenizer_class": "XLMRobertaTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,1168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.7564184767031974,
5
+ "global_step": 48000,
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": 1e-05,
13
+ "loss": 1.3064,
14
+ "step": 250
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 2e-05,
19
+ "loss": 1.2686,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 3e-05,
25
+ "loss": 1.2536,
26
+ "step": 750
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 4e-05,
31
+ "loss": 1.2402,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 5e-05,
37
+ "loss": 1.2291,
38
+ "step": 1250
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "learning_rate": 6e-05,
43
+ "loss": 1.2202,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "learning_rate": 7e-05,
49
+ "loss": 1.2107,
50
+ "step": 1750
51
+ },
52
+ {
53
+ "epoch": 0.03,
54
+ "learning_rate": 8e-05,
55
+ "loss": 1.2039,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 0.04,
60
+ "learning_rate": 9e-05,
61
+ "loss": 1.1978,
62
+ "step": 2250
63
+ },
64
+ {
65
+ "epoch": 0.04,
66
+ "learning_rate": 0.0001,
67
+ "loss": 1.1937,
68
+ "step": 2500
69
+ },
70
+ {
71
+ "epoch": 0.04,
72
+ "learning_rate": 9.9873417721519e-05,
73
+ "loss": 1.1933,
74
+ "step": 2750
75
+ },
76
+ {
77
+ "epoch": 0.05,
78
+ "learning_rate": 9.974683544303798e-05,
79
+ "loss": 1.1742,
80
+ "step": 3000
81
+ },
82
+ {
83
+ "epoch": 0.05,
84
+ "learning_rate": 9.962025316455697e-05,
85
+ "loss": 1.1665,
86
+ "step": 3250
87
+ },
88
+ {
89
+ "epoch": 0.06,
90
+ "learning_rate": 9.949367088607595e-05,
91
+ "loss": 1.1584,
92
+ "step": 3500
93
+ },
94
+ {
95
+ "epoch": 0.06,
96
+ "learning_rate": 9.936708860759493e-05,
97
+ "loss": 1.1502,
98
+ "step": 3750
99
+ },
100
+ {
101
+ "epoch": 0.06,
102
+ "learning_rate": 9.924050632911392e-05,
103
+ "loss": 1.147,
104
+ "step": 4000
105
+ },
106
+ {
107
+ "epoch": 0.07,
108
+ "learning_rate": 9.911392405063291e-05,
109
+ "loss": 1.1423,
110
+ "step": 4250
111
+ },
112
+ {
113
+ "epoch": 0.07,
114
+ "learning_rate": 9.89873417721519e-05,
115
+ "loss": 1.1343,
116
+ "step": 4500
117
+ },
118
+ {
119
+ "epoch": 0.07,
120
+ "learning_rate": 9.88607594936709e-05,
121
+ "loss": 1.1306,
122
+ "step": 4750
123
+ },
124
+ {
125
+ "epoch": 0.08,
126
+ "learning_rate": 9.873417721518988e-05,
127
+ "loss": 1.1237,
128
+ "step": 5000
129
+ },
130
+ {
131
+ "epoch": 0.08,
132
+ "learning_rate": 9.860759493670887e-05,
133
+ "loss": 1.1181,
134
+ "step": 5250
135
+ },
136
+ {
137
+ "epoch": 0.09,
138
+ "learning_rate": 9.848101265822785e-05,
139
+ "loss": 1.1135,
140
+ "step": 5500
141
+ },
142
+ {
143
+ "epoch": 0.09,
144
+ "learning_rate": 9.835443037974684e-05,
145
+ "loss": 1.1087,
146
+ "step": 5750
147
+ },
148
+ {
149
+ "epoch": 0.09,
150
+ "learning_rate": 9.822784810126583e-05,
151
+ "loss": 1.1047,
152
+ "step": 6000
153
+ },
154
+ {
155
+ "epoch": 0.1,
156
+ "learning_rate": 9.810126582278482e-05,
157
+ "loss": 1.101,
158
+ "step": 6250
159
+ },
160
+ {
161
+ "epoch": 0.1,
162
+ "learning_rate": 9.797468354430381e-05,
163
+ "loss": 1.0963,
164
+ "step": 6500
165
+ },
166
+ {
167
+ "epoch": 0.11,
168
+ "learning_rate": 9.784810126582278e-05,
169
+ "loss": 1.0933,
170
+ "step": 6750
171
+ },
172
+ {
173
+ "epoch": 0.11,
174
+ "learning_rate": 9.772151898734177e-05,
175
+ "loss": 1.0895,
176
+ "step": 7000
177
+ },
178
+ {
179
+ "epoch": 0.11,
180
+ "learning_rate": 9.759493670886076e-05,
181
+ "loss": 1.0879,
182
+ "step": 7250
183
+ },
184
+ {
185
+ "epoch": 0.12,
186
+ "learning_rate": 9.746835443037975e-05,
187
+ "loss": 1.0845,
188
+ "step": 7500
189
+ },
190
+ {
191
+ "epoch": 0.12,
192
+ "learning_rate": 9.734177215189874e-05,
193
+ "loss": 1.0802,
194
+ "step": 7750
195
+ },
196
+ {
197
+ "epoch": 0.13,
198
+ "learning_rate": 9.721518987341773e-05,
199
+ "loss": 1.077,
200
+ "step": 8000
201
+ },
202
+ {
203
+ "epoch": 0.13,
204
+ "learning_rate": 9.708860759493671e-05,
205
+ "loss": 1.075,
206
+ "step": 8250
207
+ },
208
+ {
209
+ "epoch": 0.13,
210
+ "learning_rate": 9.696202531645569e-05,
211
+ "loss": 1.0714,
212
+ "step": 8500
213
+ },
214
+ {
215
+ "epoch": 0.14,
216
+ "learning_rate": 9.683544303797469e-05,
217
+ "loss": 1.0696,
218
+ "step": 8750
219
+ },
220
+ {
221
+ "epoch": 0.14,
222
+ "learning_rate": 9.670886075949368e-05,
223
+ "loss": 1.0674,
224
+ "step": 9000
225
+ },
226
+ {
227
+ "epoch": 0.15,
228
+ "learning_rate": 9.658227848101267e-05,
229
+ "loss": 1.0647,
230
+ "step": 9250
231
+ },
232
+ {
233
+ "epoch": 0.15,
234
+ "learning_rate": 9.645569620253166e-05,
235
+ "loss": 1.0652,
236
+ "step": 9500
237
+ },
238
+ {
239
+ "epoch": 0.15,
240
+ "learning_rate": 9.632911392405065e-05,
241
+ "loss": 1.0622,
242
+ "step": 9750
243
+ },
244
+ {
245
+ "epoch": 0.16,
246
+ "learning_rate": 9.620253164556962e-05,
247
+ "loss": 1.0599,
248
+ "step": 10000
249
+ },
250
+ {
251
+ "epoch": 0.16,
252
+ "learning_rate": 9.607594936708861e-05,
253
+ "loss": 1.0568,
254
+ "step": 10250
255
+ },
256
+ {
257
+ "epoch": 0.17,
258
+ "learning_rate": 9.59493670886076e-05,
259
+ "loss": 1.0537,
260
+ "step": 10500
261
+ },
262
+ {
263
+ "epoch": 0.17,
264
+ "learning_rate": 9.582278481012659e-05,
265
+ "loss": 1.0504,
266
+ "step": 10750
267
+ },
268
+ {
269
+ "epoch": 0.17,
270
+ "learning_rate": 9.569620253164557e-05,
271
+ "loss": 1.0494,
272
+ "step": 11000
273
+ },
274
+ {
275
+ "epoch": 0.18,
276
+ "learning_rate": 9.556962025316456e-05,
277
+ "loss": 1.0485,
278
+ "step": 11250
279
+ },
280
+ {
281
+ "epoch": 0.18,
282
+ "learning_rate": 9.544303797468355e-05,
283
+ "loss": 1.0445,
284
+ "step": 11500
285
+ },
286
+ {
287
+ "epoch": 0.19,
288
+ "learning_rate": 9.531645569620253e-05,
289
+ "loss": 1.0423,
290
+ "step": 11750
291
+ },
292
+ {
293
+ "epoch": 0.19,
294
+ "learning_rate": 9.518987341772152e-05,
295
+ "loss": 1.0412,
296
+ "step": 12000
297
+ },
298
+ {
299
+ "epoch": 0.19,
300
+ "learning_rate": 9.50632911392405e-05,
301
+ "loss": 1.0392,
302
+ "step": 12250
303
+ },
304
+ {
305
+ "epoch": 0.2,
306
+ "learning_rate": 9.493670886075949e-05,
307
+ "loss": 1.0368,
308
+ "step": 12500
309
+ },
310
+ {
311
+ "epoch": 0.2,
312
+ "learning_rate": 9.481012658227848e-05,
313
+ "loss": 1.035,
314
+ "step": 12750
315
+ },
316
+ {
317
+ "epoch": 0.2,
318
+ "learning_rate": 9.468354430379748e-05,
319
+ "loss": 1.035,
320
+ "step": 13000
321
+ },
322
+ {
323
+ "epoch": 0.21,
324
+ "learning_rate": 9.455696202531646e-05,
325
+ "loss": 1.0337,
326
+ "step": 13250
327
+ },
328
+ {
329
+ "epoch": 0.21,
330
+ "learning_rate": 9.443037974683545e-05,
331
+ "loss": 1.0318,
332
+ "step": 13500
333
+ },
334
+ {
335
+ "epoch": 0.22,
336
+ "learning_rate": 9.430379746835444e-05,
337
+ "loss": 1.0314,
338
+ "step": 13750
339
+ },
340
+ {
341
+ "epoch": 0.22,
342
+ "learning_rate": 9.417721518987342e-05,
343
+ "loss": 1.0288,
344
+ "step": 14000
345
+ },
346
+ {
347
+ "epoch": 0.22,
348
+ "learning_rate": 9.405063291139241e-05,
349
+ "loss": 1.03,
350
+ "step": 14250
351
+ },
352
+ {
353
+ "epoch": 0.23,
354
+ "learning_rate": 9.39240506329114e-05,
355
+ "loss": 1.0261,
356
+ "step": 14500
357
+ },
358
+ {
359
+ "epoch": 0.23,
360
+ "learning_rate": 9.379746835443039e-05,
361
+ "loss": 1.026,
362
+ "step": 14750
363
+ },
364
+ {
365
+ "epoch": 0.24,
366
+ "learning_rate": 9.367088607594936e-05,
367
+ "loss": 1.0238,
368
+ "step": 15000
369
+ },
370
+ {
371
+ "epoch": 0.24,
372
+ "learning_rate": 9.354430379746835e-05,
373
+ "loss": 1.0248,
374
+ "step": 15250
375
+ },
376
+ {
377
+ "epoch": 0.24,
378
+ "learning_rate": 9.341772151898734e-05,
379
+ "loss": 1.0213,
380
+ "step": 15500
381
+ },
382
+ {
383
+ "epoch": 0.25,
384
+ "learning_rate": 9.329113924050633e-05,
385
+ "loss": 1.0212,
386
+ "step": 15750
387
+ },
388
+ {
389
+ "epoch": 0.25,
390
+ "learning_rate": 9.316455696202532e-05,
391
+ "loss": 1.0213,
392
+ "step": 16000
393
+ },
394
+ {
395
+ "epoch": 0.26,
396
+ "learning_rate": 9.303797468354431e-05,
397
+ "loss": 1.0177,
398
+ "step": 16250
399
+ },
400
+ {
401
+ "epoch": 0.26,
402
+ "learning_rate": 9.29113924050633e-05,
403
+ "loss": 1.0192,
404
+ "step": 16500
405
+ },
406
+ {
407
+ "epoch": 0.26,
408
+ "learning_rate": 9.278481012658227e-05,
409
+ "loss": 1.0155,
410
+ "step": 16750
411
+ },
412
+ {
413
+ "epoch": 0.27,
414
+ "learning_rate": 9.265822784810127e-05,
415
+ "loss": 1.0148,
416
+ "step": 17000
417
+ },
418
+ {
419
+ "epoch": 0.27,
420
+ "learning_rate": 9.253164556962026e-05,
421
+ "loss": 1.0139,
422
+ "step": 17250
423
+ },
424
+ {
425
+ "epoch": 0.28,
426
+ "learning_rate": 9.240506329113925e-05,
427
+ "loss": 1.0126,
428
+ "step": 17500
429
+ },
430
+ {
431
+ "epoch": 0.28,
432
+ "learning_rate": 9.227848101265824e-05,
433
+ "loss": 1.012,
434
+ "step": 17750
435
+ },
436
+ {
437
+ "epoch": 0.28,
438
+ "learning_rate": 9.215189873417723e-05,
439
+ "loss": 1.0108,
440
+ "step": 18000
441
+ },
442
+ {
443
+ "epoch": 0.29,
444
+ "learning_rate": 9.20253164556962e-05,
445
+ "loss": 1.0114,
446
+ "step": 18250
447
+ },
448
+ {
449
+ "epoch": 0.29,
450
+ "learning_rate": 9.189873417721519e-05,
451
+ "loss": 1.0103,
452
+ "step": 18500
453
+ },
454
+ {
455
+ "epoch": 0.3,
456
+ "learning_rate": 9.177215189873418e-05,
457
+ "loss": 1.0086,
458
+ "step": 18750
459
+ },
460
+ {
461
+ "epoch": 0.3,
462
+ "learning_rate": 9.164556962025317e-05,
463
+ "loss": 1.0082,
464
+ "step": 19000
465
+ },
466
+ {
467
+ "epoch": 0.3,
468
+ "learning_rate": 9.151898734177216e-05,
469
+ "loss": 1.0058,
470
+ "step": 19250
471
+ },
472
+ {
473
+ "epoch": 0.31,
474
+ "learning_rate": 9.139240506329115e-05,
475
+ "loss": 1.0049,
476
+ "step": 19500
477
+ },
478
+ {
479
+ "epoch": 0.31,
480
+ "learning_rate": 9.126582278481013e-05,
481
+ "loss": 1.0055,
482
+ "step": 19750
483
+ },
484
+ {
485
+ "epoch": 0.32,
486
+ "learning_rate": 9.113924050632912e-05,
487
+ "loss": 1.0006,
488
+ "step": 20000
489
+ },
490
+ {
491
+ "epoch": 0.32,
492
+ "learning_rate": 9.10126582278481e-05,
493
+ "loss": 1.0028,
494
+ "step": 20250
495
+ },
496
+ {
497
+ "epoch": 0.32,
498
+ "learning_rate": 9.088607594936709e-05,
499
+ "loss": 1.0,
500
+ "step": 20500
501
+ },
502
+ {
503
+ "epoch": 0.33,
504
+ "learning_rate": 9.075949367088607e-05,
505
+ "loss": 1.0012,
506
+ "step": 20750
507
+ },
508
+ {
509
+ "epoch": 0.33,
510
+ "learning_rate": 9.063291139240506e-05,
511
+ "loss": 0.9976,
512
+ "step": 21000
513
+ },
514
+ {
515
+ "epoch": 0.33,
516
+ "learning_rate": 9.050632911392407e-05,
517
+ "loss": 0.9963,
518
+ "step": 21250
519
+ },
520
+ {
521
+ "epoch": 0.34,
522
+ "learning_rate": 9.037974683544304e-05,
523
+ "loss": 0.9969,
524
+ "step": 21500
525
+ },
526
+ {
527
+ "epoch": 0.34,
528
+ "learning_rate": 9.025316455696203e-05,
529
+ "loss": 0.9963,
530
+ "step": 21750
531
+ },
532
+ {
533
+ "epoch": 0.35,
534
+ "learning_rate": 9.012658227848102e-05,
535
+ "loss": 0.9959,
536
+ "step": 22000
537
+ },
538
+ {
539
+ "epoch": 0.35,
540
+ "learning_rate": 9e-05,
541
+ "loss": 0.9939,
542
+ "step": 22250
543
+ },
544
+ {
545
+ "epoch": 0.35,
546
+ "learning_rate": 8.9873417721519e-05,
547
+ "loss": 0.9925,
548
+ "step": 22500
549
+ },
550
+ {
551
+ "epoch": 0.36,
552
+ "learning_rate": 8.974683544303798e-05,
553
+ "loss": 0.9935,
554
+ "step": 22750
555
+ },
556
+ {
557
+ "epoch": 0.36,
558
+ "learning_rate": 8.962025316455697e-05,
559
+ "loss": 0.991,
560
+ "step": 23000
561
+ },
562
+ {
563
+ "epoch": 0.37,
564
+ "learning_rate": 8.949367088607596e-05,
565
+ "loss": 0.9894,
566
+ "step": 23250
567
+ },
568
+ {
569
+ "epoch": 0.37,
570
+ "learning_rate": 8.936708860759493e-05,
571
+ "loss": 0.9892,
572
+ "step": 23500
573
+ },
574
+ {
575
+ "epoch": 0.37,
576
+ "learning_rate": 8.924050632911392e-05,
577
+ "loss": 0.9892,
578
+ "step": 23750
579
+ },
580
+ {
581
+ "epoch": 0.38,
582
+ "learning_rate": 8.911392405063291e-05,
583
+ "loss": 0.9895,
584
+ "step": 24000
585
+ },
586
+ {
587
+ "epoch": 0.38,
588
+ "learning_rate": 8.89873417721519e-05,
589
+ "loss": 0.9871,
590
+ "step": 24250
591
+ },
592
+ {
593
+ "epoch": 0.39,
594
+ "learning_rate": 8.886075949367089e-05,
595
+ "loss": 0.9857,
596
+ "step": 24500
597
+ },
598
+ {
599
+ "epoch": 0.39,
600
+ "learning_rate": 8.873417721518988e-05,
601
+ "loss": 0.9862,
602
+ "step": 24750
603
+ },
604
+ {
605
+ "epoch": 0.39,
606
+ "learning_rate": 8.860759493670887e-05,
607
+ "loss": 0.9853,
608
+ "step": 25000
609
+ },
610
+ {
611
+ "epoch": 0.4,
612
+ "learning_rate": 8.848101265822785e-05,
613
+ "loss": 0.9836,
614
+ "step": 25250
615
+ },
616
+ {
617
+ "epoch": 0.4,
618
+ "learning_rate": 8.835443037974684e-05,
619
+ "loss": 0.981,
620
+ "step": 25500
621
+ },
622
+ {
623
+ "epoch": 0.41,
624
+ "learning_rate": 8.822784810126583e-05,
625
+ "loss": 0.9832,
626
+ "step": 25750
627
+ },
628
+ {
629
+ "epoch": 0.41,
630
+ "learning_rate": 8.810126582278482e-05,
631
+ "loss": 0.9806,
632
+ "step": 26000
633
+ },
634
+ {
635
+ "epoch": 0.41,
636
+ "learning_rate": 8.797468354430381e-05,
637
+ "loss": 0.9815,
638
+ "step": 26250
639
+ },
640
+ {
641
+ "epoch": 0.42,
642
+ "learning_rate": 8.78481012658228e-05,
643
+ "loss": 0.9785,
644
+ "step": 26500
645
+ },
646
+ {
647
+ "epoch": 0.42,
648
+ "learning_rate": 8.772151898734177e-05,
649
+ "loss": 0.9782,
650
+ "step": 26750
651
+ },
652
+ {
653
+ "epoch": 0.43,
654
+ "learning_rate": 8.759493670886076e-05,
655
+ "loss": 0.9779,
656
+ "step": 27000
657
+ },
658
+ {
659
+ "epoch": 0.43,
660
+ "learning_rate": 8.746835443037975e-05,
661
+ "loss": 0.9787,
662
+ "step": 27250
663
+ },
664
+ {
665
+ "epoch": 0.43,
666
+ "learning_rate": 8.734177215189874e-05,
667
+ "loss": 0.9772,
668
+ "step": 27500
669
+ },
670
+ {
671
+ "epoch": 0.44,
672
+ "learning_rate": 8.721518987341773e-05,
673
+ "loss": 0.9774,
674
+ "step": 27750
675
+ },
676
+ {
677
+ "epoch": 0.44,
678
+ "learning_rate": 8.708860759493672e-05,
679
+ "loss": 0.9751,
680
+ "step": 28000
681
+ },
682
+ {
683
+ "epoch": 0.45,
684
+ "learning_rate": 8.69620253164557e-05,
685
+ "loss": 0.9752,
686
+ "step": 28250
687
+ },
688
+ {
689
+ "epoch": 0.45,
690
+ "learning_rate": 8.683544303797468e-05,
691
+ "loss": 0.9753,
692
+ "step": 28500
693
+ },
694
+ {
695
+ "epoch": 0.45,
696
+ "learning_rate": 8.670886075949367e-05,
697
+ "loss": 0.9724,
698
+ "step": 28750
699
+ },
700
+ {
701
+ "epoch": 0.46,
702
+ "learning_rate": 8.658227848101266e-05,
703
+ "loss": 0.9739,
704
+ "step": 29000
705
+ },
706
+ {
707
+ "epoch": 0.46,
708
+ "learning_rate": 8.645569620253166e-05,
709
+ "loss": 0.9712,
710
+ "step": 29250
711
+ },
712
+ {
713
+ "epoch": 0.46,
714
+ "learning_rate": 8.632911392405065e-05,
715
+ "loss": 0.9707,
716
+ "step": 29500
717
+ },
718
+ {
719
+ "epoch": 0.47,
720
+ "learning_rate": 8.620253164556964e-05,
721
+ "loss": 0.9747,
722
+ "step": 29750
723
+ },
724
+ {
725
+ "epoch": 0.47,
726
+ "learning_rate": 8.607594936708861e-05,
727
+ "loss": 0.97,
728
+ "step": 30000
729
+ },
730
+ {
731
+ "epoch": 0.48,
732
+ "learning_rate": 8.59493670886076e-05,
733
+ "loss": 0.9707,
734
+ "step": 30250
735
+ },
736
+ {
737
+ "epoch": 0.48,
738
+ "learning_rate": 8.582278481012659e-05,
739
+ "loss": 0.9708,
740
+ "step": 30500
741
+ },
742
+ {
743
+ "epoch": 0.48,
744
+ "learning_rate": 8.569620253164558e-05,
745
+ "loss": 0.9676,
746
+ "step": 30750
747
+ },
748
+ {
749
+ "epoch": 0.49,
750
+ "learning_rate": 8.556962025316456e-05,
751
+ "loss": 0.9672,
752
+ "step": 31000
753
+ },
754
+ {
755
+ "epoch": 0.49,
756
+ "learning_rate": 8.544303797468355e-05,
757
+ "loss": 0.9691,
758
+ "step": 31250
759
+ },
760
+ {
761
+ "epoch": 0.5,
762
+ "learning_rate": 8.531645569620254e-05,
763
+ "loss": 0.965,
764
+ "step": 31500
765
+ },
766
+ {
767
+ "epoch": 0.5,
768
+ "learning_rate": 8.518987341772152e-05,
769
+ "loss": 0.9645,
770
+ "step": 31750
771
+ },
772
+ {
773
+ "epoch": 0.5,
774
+ "learning_rate": 8.50632911392405e-05,
775
+ "loss": 0.9643,
776
+ "step": 32000
777
+ },
778
+ {
779
+ "epoch": 0.51,
780
+ "learning_rate": 8.49367088607595e-05,
781
+ "loss": 0.9631,
782
+ "step": 32250
783
+ },
784
+ {
785
+ "epoch": 0.51,
786
+ "learning_rate": 8.481012658227848e-05,
787
+ "loss": 0.9644,
788
+ "step": 32500
789
+ },
790
+ {
791
+ "epoch": 0.52,
792
+ "learning_rate": 8.468354430379747e-05,
793
+ "loss": 0.964,
794
+ "step": 32750
795
+ },
796
+ {
797
+ "epoch": 0.52,
798
+ "learning_rate": 8.455696202531646e-05,
799
+ "loss": 0.9627,
800
+ "step": 33000
801
+ },
802
+ {
803
+ "epoch": 0.52,
804
+ "learning_rate": 8.443037974683545e-05,
805
+ "loss": 0.9638,
806
+ "step": 33250
807
+ },
808
+ {
809
+ "epoch": 0.53,
810
+ "learning_rate": 8.430379746835444e-05,
811
+ "loss": 0.9606,
812
+ "step": 33500
813
+ },
814
+ {
815
+ "epoch": 0.53,
816
+ "learning_rate": 8.417721518987342e-05,
817
+ "loss": 0.9605,
818
+ "step": 33750
819
+ },
820
+ {
821
+ "epoch": 0.54,
822
+ "learning_rate": 8.405063291139241e-05,
823
+ "loss": 0.9604,
824
+ "step": 34000
825
+ },
826
+ {
827
+ "epoch": 0.54,
828
+ "learning_rate": 8.39240506329114e-05,
829
+ "loss": 0.9583,
830
+ "step": 34250
831
+ },
832
+ {
833
+ "epoch": 0.54,
834
+ "learning_rate": 8.379746835443039e-05,
835
+ "loss": 0.9589,
836
+ "step": 34500
837
+ },
838
+ {
839
+ "epoch": 0.55,
840
+ "learning_rate": 8.367088607594938e-05,
841
+ "loss": 0.9575,
842
+ "step": 34750
843
+ },
844
+ {
845
+ "epoch": 0.55,
846
+ "learning_rate": 8.354430379746835e-05,
847
+ "loss": 0.956,
848
+ "step": 35000
849
+ },
850
+ {
851
+ "epoch": 0.56,
852
+ "learning_rate": 8.341772151898734e-05,
853
+ "loss": 0.9562,
854
+ "step": 35250
855
+ },
856
+ {
857
+ "epoch": 0.56,
858
+ "learning_rate": 8.329113924050633e-05,
859
+ "loss": 0.9551,
860
+ "step": 35500
861
+ },
862
+ {
863
+ "epoch": 0.56,
864
+ "learning_rate": 8.316455696202532e-05,
865
+ "loss": 0.9538,
866
+ "step": 35750
867
+ },
868
+ {
869
+ "epoch": 0.57,
870
+ "learning_rate": 8.303797468354431e-05,
871
+ "loss": 0.9555,
872
+ "step": 36000
873
+ },
874
+ {
875
+ "epoch": 0.57,
876
+ "learning_rate": 8.29113924050633e-05,
877
+ "loss": 0.9547,
878
+ "step": 36250
879
+ },
880
+ {
881
+ "epoch": 0.58,
882
+ "learning_rate": 8.278481012658229e-05,
883
+ "loss": 0.9566,
884
+ "step": 36500
885
+ },
886
+ {
887
+ "epoch": 0.58,
888
+ "learning_rate": 8.265822784810126e-05,
889
+ "loss": 0.954,
890
+ "step": 36750
891
+ },
892
+ {
893
+ "epoch": 0.58,
894
+ "learning_rate": 8.253164556962025e-05,
895
+ "loss": 0.9533,
896
+ "step": 37000
897
+ },
898
+ {
899
+ "epoch": 0.59,
900
+ "learning_rate": 8.240506329113924e-05,
901
+ "loss": 0.9544,
902
+ "step": 37250
903
+ },
904
+ {
905
+ "epoch": 0.59,
906
+ "learning_rate": 8.227848101265824e-05,
907
+ "loss": 0.9516,
908
+ "step": 37500
909
+ },
910
+ {
911
+ "epoch": 0.59,
912
+ "learning_rate": 8.215189873417723e-05,
913
+ "loss": 0.9531,
914
+ "step": 37750
915
+ },
916
+ {
917
+ "epoch": 0.6,
918
+ "learning_rate": 8.202531645569622e-05,
919
+ "loss": 0.9538,
920
+ "step": 38000
921
+ },
922
+ {
923
+ "epoch": 0.6,
924
+ "learning_rate": 8.189873417721519e-05,
925
+ "loss": 0.953,
926
+ "step": 38250
927
+ },
928
+ {
929
+ "epoch": 0.61,
930
+ "learning_rate": 8.177215189873418e-05,
931
+ "loss": 0.9507,
932
+ "step": 38500
933
+ },
934
+ {
935
+ "epoch": 0.61,
936
+ "learning_rate": 8.164556962025317e-05,
937
+ "loss": 0.9504,
938
+ "step": 38750
939
+ },
940
+ {
941
+ "epoch": 0.61,
942
+ "learning_rate": 8.151898734177216e-05,
943
+ "loss": 0.9519,
944
+ "step": 39000
945
+ },
946
+ {
947
+ "epoch": 0.62,
948
+ "learning_rate": 8.139240506329115e-05,
949
+ "loss": 0.9494,
950
+ "step": 39250
951
+ },
952
+ {
953
+ "epoch": 0.62,
954
+ "learning_rate": 8.126582278481013e-05,
955
+ "loss": 0.9504,
956
+ "step": 39500
957
+ },
958
+ {
959
+ "epoch": 0.63,
960
+ "learning_rate": 8.113924050632912e-05,
961
+ "loss": 0.9479,
962
+ "step": 39750
963
+ },
964
+ {
965
+ "epoch": 0.63,
966
+ "learning_rate": 8.10126582278481e-05,
967
+ "loss": 0.9497,
968
+ "step": 40000
969
+ },
970
+ {
971
+ "epoch": 0.63,
972
+ "learning_rate": 8.088607594936709e-05,
973
+ "loss": 0.9483,
974
+ "step": 40250
975
+ },
976
+ {
977
+ "epoch": 0.64,
978
+ "learning_rate": 8.075949367088608e-05,
979
+ "loss": 0.9464,
980
+ "step": 40500
981
+ },
982
+ {
983
+ "epoch": 0.64,
984
+ "learning_rate": 8.063291139240506e-05,
985
+ "loss": 0.9478,
986
+ "step": 40750
987
+ },
988
+ {
989
+ "epoch": 0.65,
990
+ "learning_rate": 8.050632911392405e-05,
991
+ "loss": 0.9476,
992
+ "step": 41000
993
+ },
994
+ {
995
+ "epoch": 0.65,
996
+ "learning_rate": 8.037974683544304e-05,
997
+ "loss": 0.9444,
998
+ "step": 41250
999
+ },
1000
+ {
1001
+ "epoch": 0.65,
1002
+ "learning_rate": 8.025316455696203e-05,
1003
+ "loss": 0.9461,
1004
+ "step": 41500
1005
+ },
1006
+ {
1007
+ "epoch": 0.66,
1008
+ "learning_rate": 8.012658227848102e-05,
1009
+ "loss": 0.946,
1010
+ "step": 41750
1011
+ },
1012
+ {
1013
+ "epoch": 0.66,
1014
+ "learning_rate": 8e-05,
1015
+ "loss": 0.9454,
1016
+ "step": 42000
1017
+ },
1018
+ {
1019
+ "epoch": 0.67,
1020
+ "learning_rate": 7.9873417721519e-05,
1021
+ "loss": 0.9441,
1022
+ "step": 42250
1023
+ },
1024
+ {
1025
+ "epoch": 0.67,
1026
+ "learning_rate": 7.974683544303798e-05,
1027
+ "loss": 0.9431,
1028
+ "step": 42500
1029
+ },
1030
+ {
1031
+ "epoch": 0.67,
1032
+ "learning_rate": 7.962025316455697e-05,
1033
+ "loss": 0.9419,
1034
+ "step": 42750
1035
+ },
1036
+ {
1037
+ "epoch": 0.68,
1038
+ "learning_rate": 7.949367088607596e-05,
1039
+ "loss": 0.944,
1040
+ "step": 43000
1041
+ },
1042
+ {
1043
+ "epoch": 0.68,
1044
+ "learning_rate": 7.936708860759494e-05,
1045
+ "loss": 0.9433,
1046
+ "step": 43250
1047
+ },
1048
+ {
1049
+ "epoch": 0.69,
1050
+ "learning_rate": 7.924050632911392e-05,
1051
+ "loss": 0.9428,
1052
+ "step": 43500
1053
+ },
1054
+ {
1055
+ "epoch": 0.69,
1056
+ "learning_rate": 7.911392405063291e-05,
1057
+ "loss": 0.9406,
1058
+ "step": 43750
1059
+ },
1060
+ {
1061
+ "epoch": 0.69,
1062
+ "learning_rate": 7.89873417721519e-05,
1063
+ "loss": 0.9397,
1064
+ "step": 44000
1065
+ },
1066
+ {
1067
+ "epoch": 0.7,
1068
+ "learning_rate": 7.886075949367089e-05,
1069
+ "loss": 0.9392,
1070
+ "step": 44250
1071
+ },
1072
+ {
1073
+ "epoch": 0.7,
1074
+ "learning_rate": 7.873417721518988e-05,
1075
+ "loss": 0.9404,
1076
+ "step": 44500
1077
+ },
1078
+ {
1079
+ "epoch": 0.71,
1080
+ "learning_rate": 7.860759493670887e-05,
1081
+ "loss": 0.9388,
1082
+ "step": 44750
1083
+ },
1084
+ {
1085
+ "epoch": 0.71,
1086
+ "learning_rate": 7.848101265822784e-05,
1087
+ "loss": 0.9365,
1088
+ "step": 45000
1089
+ },
1090
+ {
1091
+ "epoch": 0.71,
1092
+ "learning_rate": 7.835443037974683e-05,
1093
+ "loss": 0.9387,
1094
+ "step": 45250
1095
+ },
1096
+ {
1097
+ "epoch": 0.72,
1098
+ "learning_rate": 7.822784810126582e-05,
1099
+ "loss": 0.9366,
1100
+ "step": 45500
1101
+ },
1102
+ {
1103
+ "epoch": 0.72,
1104
+ "learning_rate": 7.810126582278482e-05,
1105
+ "loss": 0.9361,
1106
+ "step": 45750
1107
+ },
1108
+ {
1109
+ "epoch": 0.72,
1110
+ "learning_rate": 7.797468354430381e-05,
1111
+ "loss": 0.935,
1112
+ "step": 46000
1113
+ },
1114
+ {
1115
+ "epoch": 0.73,
1116
+ "learning_rate": 7.78481012658228e-05,
1117
+ "loss": 0.9355,
1118
+ "step": 46250
1119
+ },
1120
+ {
1121
+ "epoch": 0.73,
1122
+ "learning_rate": 7.772151898734177e-05,
1123
+ "loss": 0.9352,
1124
+ "step": 46500
1125
+ },
1126
+ {
1127
+ "epoch": 0.74,
1128
+ "learning_rate": 7.759493670886076e-05,
1129
+ "loss": 0.9347,
1130
+ "step": 46750
1131
+ },
1132
+ {
1133
+ "epoch": 0.74,
1134
+ "learning_rate": 7.746835443037975e-05,
1135
+ "loss": 0.9343,
1136
+ "step": 47000
1137
+ },
1138
+ {
1139
+ "epoch": 0.74,
1140
+ "learning_rate": 7.734177215189874e-05,
1141
+ "loss": 0.934,
1142
+ "step": 47250
1143
+ },
1144
+ {
1145
+ "epoch": 0.75,
1146
+ "learning_rate": 7.721518987341773e-05,
1147
+ "loss": 0.9336,
1148
+ "step": 47500
1149
+ },
1150
+ {
1151
+ "epoch": 0.75,
1152
+ "learning_rate": 7.708860759493672e-05,
1153
+ "loss": 0.9345,
1154
+ "step": 47750
1155
+ },
1156
+ {
1157
+ "epoch": 0.76,
1158
+ "learning_rate": 7.69620253164557e-05,
1159
+ "loss": 0.932,
1160
+ "step": 48000
1161
+ }
1162
+ ],
1163
+ "max_steps": 200000,
1164
+ "num_train_epochs": 4,
1165
+ "total_flos": 5.730504888287232e+18,
1166
+ "trial_name": null,
1167
+ "trial_params": null
1168
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:171227121dba511a55187d5467e337bb165ba36da6b23ec1db811abdf2b92226
3
+ size 3195