BRlkl commited on
Commit
c668209
·
verified ·
1 Parent(s): 9b3f35e

Push best model used for final benchmarks

Browse files
checkpoint-6586/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "Seguro",
13
+ "1": "Inseguro"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "Inseguro": 1,
19
+ "Seguro": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "pooler_fc_size": 768,
29
+ "pooler_num_attention_heads": 12,
30
+ "pooler_num_fc_layers": 3,
31
+ "pooler_size_per_head": 128,
32
+ "pooler_type": "first_token_transform",
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.55.4",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 29794
40
+ }
checkpoint-6586/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69dd3bf148c59aaf31fc10c1cb18c0183dd902cf46015a867b2230f0a62f2e3a
3
+ size 435722224
checkpoint-6586/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a94e0f57997769dfa95911e9c1e093a22c48b6a00e719c92604e1a8bb08df0d
3
+ size 871568779
checkpoint-6586/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83137178291a7906dd728f04856c8554b1985096402542096350a33ce5783b7
3
+ size 14645
checkpoint-6586/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc5aa9a999d80e87547b573e38a50ccc818f8aca91cf8064e1f1bdf0d79d519a
3
+ size 1465
checkpoint-6586/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-6586/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6586/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoint-6586/trainer_state.json ADDED
@@ -0,0 +1,969 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6586,
3
+ "best_metric": 0.847490661036219,
4
+ "best_model_checkpoint": "outputs/final-run/checkpoint-6586",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 6586,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015186028853454821,
14
+ "grad_norm": 2.3480491638183594,
15
+ "learning_rate": 9.999658552822536e-06,
16
+ "loss": 0.6629,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.030372057706909643,
21
+ "grad_norm": 3.3713912963867188,
22
+ "learning_rate": 9.998606244733398e-06,
23
+ "loss": 0.5702,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.04555808656036447,
28
+ "grad_norm": 5.710732460021973,
29
+ "learning_rate": 9.996843083169648e-06,
30
+ "loss": 0.5245,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.060744115413819286,
35
+ "grad_norm": 5.55316686630249,
36
+ "learning_rate": 9.994369318871088e-06,
37
+ "loss": 0.4684,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.07593014426727411,
42
+ "grad_norm": 8.149177551269531,
43
+ "learning_rate": 9.991185303632574e-06,
44
+ "loss": 0.4783,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.09111617312072894,
49
+ "grad_norm": 7.209503650665283,
50
+ "learning_rate": 9.987291490253976e-06,
51
+ "loss": 0.4589,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.10630220197418375,
56
+ "grad_norm": 7.983670234680176,
57
+ "learning_rate": 9.98268843247581e-06,
58
+ "loss": 0.4623,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.12148823082763857,
63
+ "grad_norm": 4.2466206550598145,
64
+ "learning_rate": 9.977376784900465e-06,
65
+ "loss": 0.4694,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.1366742596810934,
70
+ "grad_norm": 6.11989164352417,
71
+ "learning_rate": 9.971357302899133e-06,
72
+ "loss": 0.4965,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.15186028853454822,
77
+ "grad_norm": 4.606278896331787,
78
+ "learning_rate": 9.964630842504372e-06,
79
+ "loss": 0.4919,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.16704631738800305,
84
+ "grad_norm": 5.91365909576416,
85
+ "learning_rate": 9.957198360288374e-06,
86
+ "loss": 0.4536,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.18223234624145787,
91
+ "grad_norm": 5.541100025177002,
92
+ "learning_rate": 9.949060913226936e-06,
93
+ "loss": 0.4719,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.19741837509491267,
98
+ "grad_norm": 4.289076805114746,
99
+ "learning_rate": 9.94021965854914e-06,
100
+ "loss": 0.4136,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.2126044039483675,
105
+ "grad_norm": 14.322737693786621,
106
+ "learning_rate": 9.930675853572787e-06,
107
+ "loss": 0.4705,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.22779043280182232,
112
+ "grad_norm": 6.375570297241211,
113
+ "learning_rate": 9.920430855525589e-06,
114
+ "loss": 0.4701,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.24297646165527714,
119
+ "grad_norm": 3.261223316192627,
120
+ "learning_rate": 9.909486121352163e-06,
121
+ "loss": 0.4528,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.25816249050873197,
126
+ "grad_norm": 3.854436159133911,
127
+ "learning_rate": 9.89784320750684e-06,
128
+ "loss": 0.4265,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.2733485193621868,
133
+ "grad_norm": 10.977453231811523,
134
+ "learning_rate": 9.885503769732304e-06,
135
+ "loss": 0.4329,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.2885345482156416,
140
+ "grad_norm": 6.016301155090332,
141
+ "learning_rate": 9.872469562824157e-06,
142
+ "loss": 0.4147,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.30372057706909644,
147
+ "grad_norm": 5.806178569793701,
148
+ "learning_rate": 9.858742440381343e-06,
149
+ "loss": 0.4718,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.31890660592255127,
154
+ "grad_norm": 6.394021987915039,
155
+ "learning_rate": 9.844324354542558e-06,
156
+ "loss": 0.3912,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.3340926347760061,
161
+ "grad_norm": 7.948565483093262,
162
+ "learning_rate": 9.82921735570864e-06,
163
+ "loss": 0.4223,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.3492786636294609,
168
+ "grad_norm": 5.151625156402588,
169
+ "learning_rate": 9.813423592250969e-06,
170
+ "loss": 0.4079,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.36446469248291574,
175
+ "grad_norm": 6.724940299987793,
176
+ "learning_rate": 9.796945310205958e-06,
177
+ "loss": 0.4306,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.37965072133637057,
182
+ "grad_norm": 3.623936176300049,
183
+ "learning_rate": 9.779784852955636e-06,
184
+ "loss": 0.438,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.39483675018982534,
189
+ "grad_norm": 6.648692607879639,
190
+ "learning_rate": 9.761944660894397e-06,
191
+ "loss": 0.4515,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.41002277904328016,
196
+ "grad_norm": 5.989009380340576,
197
+ "learning_rate": 9.743427271081954e-06,
198
+ "loss": 0.3911,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.425208807896735,
203
+ "grad_norm": 3.3359053134918213,
204
+ "learning_rate": 9.724235316882537e-06,
205
+ "loss": 0.4454,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.4403948367501898,
210
+ "grad_norm": 11.017061233520508,
211
+ "learning_rate": 9.704371527590404e-06,
212
+ "loss": 0.4022,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.45558086560364464,
217
+ "grad_norm": 7.159852981567383,
218
+ "learning_rate": 9.68383872804171e-06,
219
+ "loss": 0.4464,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.47076689445709946,
224
+ "grad_norm": 4.259323596954346,
225
+ "learning_rate": 9.662639838212781e-06,
226
+ "loss": 0.3829,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.4859529233105543,
231
+ "grad_norm": 7.917912483215332,
232
+ "learning_rate": 9.640777872804868e-06,
233
+ "loss": 0.4186,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.5011389521640092,
238
+ "grad_norm": 8.7236967086792,
239
+ "learning_rate": 9.61825594081542e-06,
240
+ "loss": 0.3766,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.5163249810174639,
245
+ "grad_norm": 4.761518478393555,
246
+ "learning_rate": 9.595077245095959e-06,
247
+ "loss": 0.4057,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.5315110098709187,
252
+ "grad_norm": 2.5256729125976562,
253
+ "learning_rate": 9.571245081896594e-06,
254
+ "loss": 0.4321,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.5466970387243736,
259
+ "grad_norm": 9.82975959777832,
260
+ "learning_rate": 9.546762840397268e-06,
261
+ "loss": 0.4067,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.5618830675778284,
266
+ "grad_norm": 4.607714653015137,
267
+ "learning_rate": 9.521634002225774e-06,
268
+ "loss": 0.3834,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.5770690964312832,
273
+ "grad_norm": 8.330415725708008,
274
+ "learning_rate": 9.495862140962638e-06,
275
+ "loss": 0.374,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.592255125284738,
280
+ "grad_norm": 5.7992634773254395,
281
+ "learning_rate": 9.469450921632912e-06,
282
+ "loss": 0.3852,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.6074411541381929,
287
+ "grad_norm": 5.298435211181641,
288
+ "learning_rate": 9.44240410018498e-06,
289
+ "loss": 0.4345,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.6226271829916477,
294
+ "grad_norm": 6.483381271362305,
295
+ "learning_rate": 9.414725522956414e-06,
296
+ "loss": 0.407,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.6378132118451025,
301
+ "grad_norm": 5.179783821105957,
302
+ "learning_rate": 9.386419126126983e-06,
303
+ "loss": 0.432,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.6529992406985573,
308
+ "grad_norm": 5.316011428833008,
309
+ "learning_rate": 9.357488935158897e-06,
310
+ "loss": 0.4071,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.6681852695520122,
315
+ "grad_norm": 10.58410930633545,
316
+ "learning_rate": 9.327939064224346e-06,
317
+ "loss": 0.3772,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.683371298405467,
322
+ "grad_norm": 4.013734817504883,
323
+ "learning_rate": 9.297773715620406e-06,
324
+ "loss": 0.4064,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.6985573272589218,
329
+ "grad_norm": 9.252372741699219,
330
+ "learning_rate": 9.266997179171442e-06,
331
+ "loss": 0.3911,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.7137433561123766,
336
+ "grad_norm": 8.192291259765625,
337
+ "learning_rate": 9.235613831619052e-06,
338
+ "loss": 0.3816,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.7289293849658315,
343
+ "grad_norm": 4.068896770477295,
344
+ "learning_rate": 9.203628135999643e-06,
345
+ "loss": 0.4304,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.7441154138192863,
350
+ "grad_norm": 2.9444737434387207,
351
+ "learning_rate": 9.171044641009741e-06,
352
+ "loss": 0.4231,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.7593014426727411,
357
+ "grad_norm": 4.700106620788574,
358
+ "learning_rate": 9.137867980359126e-06,
359
+ "loss": 0.3982,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.7744874715261959,
364
+ "grad_norm": 14.975322723388672,
365
+ "learning_rate": 9.104102872111858e-06,
366
+ "loss": 0.4241,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.7896735003796507,
371
+ "grad_norm": 4.325404644012451,
372
+ "learning_rate": 9.069754118015339e-06,
373
+ "loss": 0.3725,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.8048595292331056,
378
+ "grad_norm": 3.829643964767456,
379
+ "learning_rate": 9.034826602817433e-06,
380
+ "loss": 0.4048,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.8200455580865603,
385
+ "grad_norm": 6.086367607116699,
386
+ "learning_rate": 8.99932529357182e-06,
387
+ "loss": 0.4333,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.8352315869400152,
392
+ "grad_norm": 4.058459758758545,
393
+ "learning_rate": 8.963255238931623e-06,
394
+ "loss": 0.4004,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.85041761579347,
399
+ "grad_norm": 4.049592971801758,
400
+ "learning_rate": 8.926621568431442e-06,
401
+ "loss": 0.4126,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.8656036446469249,
406
+ "grad_norm": 3.434569835662842,
407
+ "learning_rate": 8.889429491757872e-06,
408
+ "loss": 0.4134,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.8807896735003796,
413
+ "grad_norm": 5.300995349884033,
414
+ "learning_rate": 8.851684298008642e-06,
415
+ "loss": 0.4224,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.8959757023538345,
420
+ "grad_norm": 8.158344268798828,
421
+ "learning_rate": 8.813391354940445e-06,
422
+ "loss": 0.3538,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.9111617312072893,
427
+ "grad_norm": 6.747292518615723,
428
+ "learning_rate": 8.77455610820559e-06,
429
+ "loss": 0.3907,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.9263477600607442,
434
+ "grad_norm": 6.279948711395264,
435
+ "learning_rate": 8.735184080577569e-06,
436
+ "loss": 0.4344,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.9415337889141989,
441
+ "grad_norm": 4.355826377868652,
442
+ "learning_rate": 8.69528087116567e-06,
443
+ "loss": 0.4082,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.9567198177676538,
448
+ "grad_norm": 6.685491561889648,
449
+ "learning_rate": 8.65485215461872e-06,
450
+ "loss": 0.3851,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.9719058466211086,
455
+ "grad_norm": 5.933023452758789,
456
+ "learning_rate": 8.61390368031809e-06,
457
+ "loss": 0.3734,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.9870918754745635,
462
+ "grad_norm": 9.179722785949707,
463
+ "learning_rate": 8.572441271560077e-06,
464
+ "loss": 0.3934,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 1.0,
469
+ "eval_f1": 0.8445935154128733,
470
+ "eval_loss": 0.37980714440345764,
471
+ "eval_runtime": 7.8494,
472
+ "eval_samples_per_second": 745.663,
473
+ "eval_steps_per_second": 23.314,
474
+ "step": 3293
475
+ },
476
+ {
477
+ "epoch": 1.0021260440394837,
478
+ "grad_norm": 1.5981299877166748,
479
+ "learning_rate": 8.53047082472777e-06,
480
+ "loss": 0.3967,
481
+ "step": 3300
482
+ },
483
+ {
484
+ "epoch": 1.0173120728929386,
485
+ "grad_norm": 5.159671783447266,
486
+ "learning_rate": 8.487998308452525e-06,
487
+ "loss": 0.3125,
488
+ "step": 3350
489
+ },
490
+ {
491
+ "epoch": 1.0324981017463932,
492
+ "grad_norm": 8.904830932617188,
493
+ "learning_rate": 8.445029762765159e-06,
494
+ "loss": 0.3201,
495
+ "step": 3400
496
+ },
497
+ {
498
+ "epoch": 1.047684130599848,
499
+ "grad_norm": 4.215548992156982,
500
+ "learning_rate": 8.401571298237e-06,
501
+ "loss": 0.3043,
502
+ "step": 3450
503
+ },
504
+ {
505
+ "epoch": 1.062870159453303,
506
+ "grad_norm": 2.9603254795074463,
507
+ "learning_rate": 8.357629095110906e-06,
508
+ "loss": 0.307,
509
+ "step": 3500
510
+ },
511
+ {
512
+ "epoch": 1.0780561883067579,
513
+ "grad_norm": 8.665258407592773,
514
+ "learning_rate": 8.313209402422348e-06,
515
+ "loss": 0.3081,
516
+ "step": 3550
517
+ },
518
+ {
519
+ "epoch": 1.0932422171602125,
520
+ "grad_norm": 7.101922512054443,
521
+ "learning_rate": 8.268318537110762e-06,
522
+ "loss": 0.3536,
523
+ "step": 3600
524
+ },
525
+ {
526
+ "epoch": 1.1084282460136674,
527
+ "grad_norm": 9.113100051879883,
528
+ "learning_rate": 8.222962883121196e-06,
529
+ "loss": 0.3557,
530
+ "step": 3650
531
+ },
532
+ {
533
+ "epoch": 1.1236142748671223,
534
+ "grad_norm": 3.427243947982788,
535
+ "learning_rate": 8.177148890496452e-06,
536
+ "loss": 0.2984,
537
+ "step": 3700
538
+ },
539
+ {
540
+ "epoch": 1.138800303720577,
541
+ "grad_norm": 6.6492695808410645,
542
+ "learning_rate": 8.130883074459823e-06,
543
+ "loss": 0.3407,
544
+ "step": 3750
545
+ },
546
+ {
547
+ "epoch": 1.1539863325740318,
548
+ "grad_norm": 9.254618644714355,
549
+ "learning_rate": 8.084172014488564e-06,
550
+ "loss": 0.3487,
551
+ "step": 3800
552
+ },
553
+ {
554
+ "epoch": 1.1691723614274867,
555
+ "grad_norm": 3.8507754802703857,
556
+ "learning_rate": 8.037022353378218e-06,
557
+ "loss": 0.3374,
558
+ "step": 3850
559
+ },
560
+ {
561
+ "epoch": 1.1843583902809416,
562
+ "grad_norm": 18.62590217590332,
563
+ "learning_rate": 7.989440796297943e-06,
564
+ "loss": 0.3269,
565
+ "step": 3900
566
+ },
567
+ {
568
+ "epoch": 1.1995444191343965,
569
+ "grad_norm": 14.359010696411133,
570
+ "learning_rate": 7.941434109836968e-06,
571
+ "loss": 0.3219,
572
+ "step": 3950
573
+ },
574
+ {
575
+ "epoch": 1.2147304479878511,
576
+ "grad_norm": 8.173829078674316,
577
+ "learning_rate": 7.893009121042314e-06,
578
+ "loss": 0.2944,
579
+ "step": 4000
580
+ },
581
+ {
582
+ "epoch": 1.229916476841306,
583
+ "grad_norm": 6.0913591384887695,
584
+ "learning_rate": 7.844172716447918e-06,
585
+ "loss": 0.366,
586
+ "step": 4050
587
+ },
588
+ {
589
+ "epoch": 1.2451025056947609,
590
+ "grad_norm": 8.989174842834473,
591
+ "learning_rate": 7.794931841095297e-06,
592
+ "loss": 0.3223,
593
+ "step": 4100
594
+ },
595
+ {
596
+ "epoch": 1.2602885345482155,
597
+ "grad_norm": 4.618454456329346,
598
+ "learning_rate": 7.745293497545892e-06,
599
+ "loss": 0.3718,
600
+ "step": 4150
601
+ },
602
+ {
603
+ "epoch": 1.2754745634016704,
604
+ "grad_norm": 6.966646194458008,
605
+ "learning_rate": 7.695264744885225e-06,
606
+ "loss": 0.34,
607
+ "step": 4200
608
+ },
609
+ {
610
+ "epoch": 1.2906605922551253,
611
+ "grad_norm": 8.476325988769531,
612
+ "learning_rate": 7.64485269771903e-06,
613
+ "loss": 0.309,
614
+ "step": 4250
615
+ },
616
+ {
617
+ "epoch": 1.3058466211085802,
618
+ "grad_norm": 3.3412492275238037,
619
+ "learning_rate": 7.594064525161487e-06,
620
+ "loss": 0.3491,
621
+ "step": 4300
622
+ },
623
+ {
624
+ "epoch": 1.321032649962035,
625
+ "grad_norm": 9.971606254577637,
626
+ "learning_rate": 7.54290744981569e-06,
627
+ "loss": 0.3097,
628
+ "step": 4350
629
+ },
630
+ {
631
+ "epoch": 1.3362186788154897,
632
+ "grad_norm": 7.083515167236328,
633
+ "learning_rate": 7.491388746746522e-06,
634
+ "loss": 0.3446,
635
+ "step": 4400
636
+ },
637
+ {
638
+ "epoch": 1.3514047076689446,
639
+ "grad_norm": 5.6028361320495605,
640
+ "learning_rate": 7.439515742446065e-06,
641
+ "loss": 0.3229,
642
+ "step": 4450
643
+ },
644
+ {
645
+ "epoch": 1.3665907365223995,
646
+ "grad_norm": 9.373847961425781,
647
+ "learning_rate": 7.387295813791705e-06,
648
+ "loss": 0.3022,
649
+ "step": 4500
650
+ },
651
+ {
652
+ "epoch": 1.3817767653758541,
653
+ "grad_norm": 5.378981590270996,
654
+ "learning_rate": 7.334736386997049e-06,
655
+ "loss": 0.2955,
656
+ "step": 4550
657
+ },
658
+ {
659
+ "epoch": 1.396962794229309,
660
+ "grad_norm": 9.248358726501465,
661
+ "learning_rate": 7.281844936555853e-06,
662
+ "loss": 0.3562,
663
+ "step": 4600
664
+ },
665
+ {
666
+ "epoch": 1.412148823082764,
667
+ "grad_norm": 6.579871654510498,
668
+ "learning_rate": 7.228628984179068e-06,
669
+ "loss": 0.3436,
670
+ "step": 4650
671
+ },
672
+ {
673
+ "epoch": 1.4273348519362186,
674
+ "grad_norm": 2.5316176414489746,
675
+ "learning_rate": 7.175096097725169e-06,
676
+ "loss": 0.3464,
677
+ "step": 4700
678
+ },
679
+ {
680
+ "epoch": 1.4425208807896734,
681
+ "grad_norm": 12.828206062316895,
682
+ "learning_rate": 7.121253890123941e-06,
683
+ "loss": 0.3333,
684
+ "step": 4750
685
+ },
686
+ {
687
+ "epoch": 1.4577069096431283,
688
+ "grad_norm": 8.807774543762207,
689
+ "learning_rate": 7.067110018293828e-06,
690
+ "loss": 0.2955,
691
+ "step": 4800
692
+ },
693
+ {
694
+ "epoch": 1.4728929384965832,
695
+ "grad_norm": 10.35312557220459,
696
+ "learning_rate": 7.012672182053043e-06,
697
+ "loss": 0.3321,
698
+ "step": 4850
699
+ },
700
+ {
701
+ "epoch": 1.488078967350038,
702
+ "grad_norm": 2.2814652919769287,
703
+ "learning_rate": 6.9579481230245835e-06,
704
+ "loss": 0.3466,
705
+ "step": 4900
706
+ },
707
+ {
708
+ "epoch": 1.5032649962034927,
709
+ "grad_norm": 5.442550182342529,
710
+ "learning_rate": 6.9029456235352795e-06,
711
+ "loss": 0.3321,
712
+ "step": 4950
713
+ },
714
+ {
715
+ "epoch": 1.5184510250569476,
716
+ "grad_norm": 12.557025909423828,
717
+ "learning_rate": 6.847672505509079e-06,
718
+ "loss": 0.3429,
719
+ "step": 5000
720
+ },
721
+ {
722
+ "epoch": 1.5336370539104025,
723
+ "grad_norm": 4.002285480499268,
724
+ "learning_rate": 6.792136629354677e-06,
725
+ "loss": 0.3274,
726
+ "step": 5050
727
+ },
728
+ {
729
+ "epoch": 1.5488230827638572,
730
+ "grad_norm": 17.179048538208008,
731
+ "learning_rate": 6.736345892847691e-06,
732
+ "loss": 0.3472,
733
+ "step": 5100
734
+ },
735
+ {
736
+ "epoch": 1.564009111617312,
737
+ "grad_norm": 8.354110717773438,
738
+ "learning_rate": 6.680308230007521e-06,
739
+ "loss": 0.3282,
740
+ "step": 5150
741
+ },
742
+ {
743
+ "epoch": 1.579195140470767,
744
+ "grad_norm": 5.1743035316467285,
745
+ "learning_rate": 6.624031609969036e-06,
746
+ "loss": 0.3443,
747
+ "step": 5200
748
+ },
749
+ {
750
+ "epoch": 1.5943811693242216,
751
+ "grad_norm": 6.959432601928711,
752
+ "learning_rate": 6.567524035849293e-06,
753
+ "loss": 0.35,
754
+ "step": 5250
755
+ },
756
+ {
757
+ "epoch": 1.6095671981776767,
758
+ "grad_norm": 20.55417823791504,
759
+ "learning_rate": 6.5107935436094076e-06,
760
+ "loss": 0.3158,
761
+ "step": 5300
762
+ },
763
+ {
764
+ "epoch": 1.6247532270311313,
765
+ "grad_norm": 14.025495529174805,
766
+ "learning_rate": 6.453848200911752e-06,
767
+ "loss": 0.3287,
768
+ "step": 5350
769
+ },
770
+ {
771
+ "epoch": 1.6399392558845862,
772
+ "grad_norm": 12.094548225402832,
773
+ "learning_rate": 6.396696105972655e-06,
774
+ "loss": 0.3448,
775
+ "step": 5400
776
+ },
777
+ {
778
+ "epoch": 1.655125284738041,
779
+ "grad_norm": 3.596747398376465,
780
+ "learning_rate": 6.339345386410756e-06,
781
+ "loss": 0.3544,
782
+ "step": 5450
783
+ },
784
+ {
785
+ "epoch": 1.6703113135914958,
786
+ "grad_norm": 4.897212505340576,
787
+ "learning_rate": 6.2818041980911635e-06,
788
+ "loss": 0.3363,
789
+ "step": 5500
790
+ },
791
+ {
792
+ "epoch": 1.6854973424449506,
793
+ "grad_norm": 2.7992074489593506,
794
+ "learning_rate": 6.224080723965616e-06,
795
+ "loss": 0.3405,
796
+ "step": 5550
797
+ },
798
+ {
799
+ "epoch": 1.7006833712984055,
800
+ "grad_norm": 8.647635459899902,
801
+ "learning_rate": 6.1661831729087705e-06,
802
+ "loss": 0.3218,
803
+ "step": 5600
804
+ },
805
+ {
806
+ "epoch": 1.7158694001518602,
807
+ "grad_norm": 16.2703800201416,
808
+ "learning_rate": 6.1081197785508335e-06,
809
+ "loss": 0.3569,
810
+ "step": 5650
811
+ },
812
+ {
813
+ "epoch": 1.731055429005315,
814
+ "grad_norm": 9.62259578704834,
815
+ "learning_rate": 6.049898798106636e-06,
816
+ "loss": 0.3181,
817
+ "step": 5700
818
+ },
819
+ {
820
+ "epoch": 1.74624145785877,
821
+ "grad_norm": 10.183274269104004,
822
+ "learning_rate": 5.991528511201382e-06,
823
+ "loss": 0.3191,
824
+ "step": 5750
825
+ },
826
+ {
827
+ "epoch": 1.7614274867122246,
828
+ "grad_norm": 20.28440284729004,
829
+ "learning_rate": 5.933017218693193e-06,
830
+ "loss": 0.3162,
831
+ "step": 5800
832
+ },
833
+ {
834
+ "epoch": 1.7766135155656797,
835
+ "grad_norm": 18.231319427490234,
836
+ "learning_rate": 5.874373241492651e-06,
837
+ "loss": 0.3788,
838
+ "step": 5850
839
+ },
840
+ {
841
+ "epoch": 1.7917995444191344,
842
+ "grad_norm": 14.682201385498047,
843
+ "learning_rate": 5.815604919379472e-06,
844
+ "loss": 0.3242,
845
+ "step": 5900
846
+ },
847
+ {
848
+ "epoch": 1.8069855732725892,
849
+ "grad_norm": 6.563547611236572,
850
+ "learning_rate": 5.7567206098164965e-06,
851
+ "loss": 0.3377,
852
+ "step": 5950
853
+ },
854
+ {
855
+ "epoch": 1.8221716021260441,
856
+ "grad_norm": 8.406890869140625,
857
+ "learning_rate": 5.697728686761189e-06,
858
+ "loss": 0.3222,
859
+ "step": 6000
860
+ },
861
+ {
862
+ "epoch": 1.8373576309794988,
863
+ "grad_norm": 5.706462860107422,
864
+ "learning_rate": 5.638637539474758e-06,
865
+ "loss": 0.3169,
866
+ "step": 6050
867
+ },
868
+ {
869
+ "epoch": 1.8525436598329537,
870
+ "grad_norm": 3.566732883453369,
871
+ "learning_rate": 5.579455571329128e-06,
872
+ "loss": 0.2993,
873
+ "step": 6100
874
+ },
875
+ {
876
+ "epoch": 1.8677296886864085,
877
+ "grad_norm": 21.842191696166992,
878
+ "learning_rate": 5.520191198611883e-06,
879
+ "loss": 0.3411,
880
+ "step": 6150
881
+ },
882
+ {
883
+ "epoch": 1.8829157175398632,
884
+ "grad_norm": 7.155375957489014,
885
+ "learning_rate": 5.460852849329394e-06,
886
+ "loss": 0.3168,
887
+ "step": 6200
888
+ },
889
+ {
890
+ "epoch": 1.8981017463933183,
891
+ "grad_norm": 5.166109085083008,
892
+ "learning_rate": 5.401448962008262e-06,
893
+ "loss": 0.3526,
894
+ "step": 6250
895
+ },
896
+ {
897
+ "epoch": 1.913287775246773,
898
+ "grad_norm": 10.691755294799805,
899
+ "learning_rate": 5.341987984495275e-06,
900
+ "loss": 0.334,
901
+ "step": 6300
902
+ },
903
+ {
904
+ "epoch": 1.9284738041002278,
905
+ "grad_norm": 1.8157846927642822,
906
+ "learning_rate": 5.282478372756036e-06,
907
+ "loss": 0.2981,
908
+ "step": 6350
909
+ },
910
+ {
911
+ "epoch": 1.9436598329536827,
912
+ "grad_norm": 6.267528057098389,
913
+ "learning_rate": 5.222928589672436e-06,
914
+ "loss": 0.3443,
915
+ "step": 6400
916
+ },
917
+ {
918
+ "epoch": 1.9588458618071374,
919
+ "grad_norm": 8.20384407043457,
920
+ "learning_rate": 5.163347103839149e-06,
921
+ "loss": 0.3196,
922
+ "step": 6450
923
+ },
924
+ {
925
+ "epoch": 1.9740318906605923,
926
+ "grad_norm": 6.2834882736206055,
927
+ "learning_rate": 5.10374238835931e-06,
928
+ "loss": 0.3176,
929
+ "step": 6500
930
+ },
931
+ {
932
+ "epoch": 1.9892179195140471,
933
+ "grad_norm": 7.512860298156738,
934
+ "learning_rate": 5.0441229196395416e-06,
935
+ "loss": 0.3216,
936
+ "step": 6550
937
+ },
938
+ {
939
+ "epoch": 2.0,
940
+ "eval_f1": 0.847490661036219,
941
+ "eval_loss": 0.39481809735298157,
942
+ "eval_runtime": 7.8513,
943
+ "eval_samples_per_second": 745.486,
944
+ "eval_steps_per_second": 23.308,
945
+ "step": 6586
946
+ }
947
+ ],
948
+ "logging_steps": 50,
949
+ "max_steps": 13172,
950
+ "num_input_tokens_seen": 0,
951
+ "num_train_epochs": 4,
952
+ "save_steps": 500,
953
+ "stateful_callbacks": {
954
+ "TrainerControl": {
955
+ "args": {
956
+ "should_epoch_stop": false,
957
+ "should_evaluate": false,
958
+ "should_log": false,
959
+ "should_save": true,
960
+ "should_training_stop": false
961
+ },
962
+ "attributes": {}
963
+ }
964
+ },
965
+ "total_flos": 2.771769723795456e+16,
966
+ "train_batch_size": 8,
967
+ "trial_name": null,
968
+ "trial_params": null
969
+ }
checkpoint-6586/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f88b0df8840444e7236f1853ca7948048e7723185bbb9834773b915cc6955be
3
+ size 5841
checkpoint-6586/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86ab942e305f61190437f2f888d80b07fe269a89c0e402f03e3cc2d723de3d5a
3
  size 435722224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69dd3bf148c59aaf31fc10c1cb18c0183dd902cf46015a867b2230f0a62f2e3a
3
  size 435722224
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e5624c1d30b611ca76a53ce896f111af2d2aaa730e1008205e8270c5a108248
3
  size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f88b0df8840444e7236f1853ca7948048e7723185bbb9834773b915cc6955be
3
  size 5841