metinovadilet commited on
Commit
28f8f07
·
verified ·
1 Parent(s): f2f2161

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "pooler_fc_size": 768,
20
+ "pooler_num_attention_heads": 12,
21
+ "pooler_num_fc_layers": 3,
22
+ "pooler_size_per_head": 128,
23
+ "pooler_type": "first_token_transform",
24
+ "position_embedding_type": "absolute",
25
+ "problem_type": "single_label_classification",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.53.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9840922f4267733cb414eddc57f57a0c491d06e26b02ff5be86eff3211dede6
3
+ size 711443456
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:230fb937d783e73f3742237bf79790dce5a9c2814263367a7ed3f42975a0908b
3
+ size 1423007994
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd1ff8d8be8a39d4c534dc25a618168310236d646ebbf0c413b190bbb4b60b95
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9afa35fbab12d3ba639b2dac344f38e8ed6494ec52ba2df11a8ace36fbc8ae1
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b83f73ee1678f8a5eaa03031aac5211fe88ae4e84aef65a747406565292318e5
3
+ size 1064
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
trainer_state.json ADDED
@@ -0,0 +1,943 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 12630,
3
+ "best_metric": 0.8520642201834863,
4
+ "best_model_checkpoint": "./mbert-sst2-finetuned\\checkpoint-12630",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 12630,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.023752969121140142,
14
+ "grad_norm": 9.634153366088867,
15
+ "learning_rate": 1.9849564528899446e-05,
16
+ "loss": 0.666,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.047505938242280284,
21
+ "grad_norm": 4.3779520988464355,
22
+ "learning_rate": 1.969121140142518e-05,
23
+ "loss": 0.6312,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.07125890736342043,
28
+ "grad_norm": 4.55907678604126,
29
+ "learning_rate": 1.9532858273950912e-05,
30
+ "loss": 0.5593,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.09501187648456057,
35
+ "grad_norm": 7.7376017570495605,
36
+ "learning_rate": 1.9374505146476644e-05,
37
+ "loss": 0.5619,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.1187648456057007,
42
+ "grad_norm": 8.003072738647461,
43
+ "learning_rate": 1.9216152019002377e-05,
44
+ "loss": 0.5221,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.14251781472684086,
49
+ "grad_norm": 14.349533081054688,
50
+ "learning_rate": 1.905779889152811e-05,
51
+ "loss": 0.5207,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.166270783847981,
56
+ "grad_norm": 7.375957489013672,
57
+ "learning_rate": 1.889944576405384e-05,
58
+ "loss": 0.478,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.19002375296912113,
63
+ "grad_norm": 7.584378242492676,
64
+ "learning_rate": 1.8741092636579576e-05,
65
+ "loss": 0.4883,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.21377672209026127,
70
+ "grad_norm": 15.048194885253906,
71
+ "learning_rate": 1.8582739509105305e-05,
72
+ "loss": 0.496,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.2375296912114014,
77
+ "grad_norm": 9.2789945602417,
78
+ "learning_rate": 1.8424386381631038e-05,
79
+ "loss": 0.4595,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.26128266033254155,
84
+ "grad_norm": 5.139932155609131,
85
+ "learning_rate": 1.826603325415677e-05,
86
+ "loss": 0.4463,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.2850356294536817,
91
+ "grad_norm": 9.257096290588379,
92
+ "learning_rate": 1.8107680126682503e-05,
93
+ "loss": 0.4465,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.3087885985748218,
98
+ "grad_norm": 7.5652313232421875,
99
+ "learning_rate": 1.7949326999208236e-05,
100
+ "loss": 0.4553,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.332541567695962,
105
+ "grad_norm": 5.573002815246582,
106
+ "learning_rate": 1.779097387173397e-05,
107
+ "loss": 0.4098,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.35629453681710216,
112
+ "grad_norm": 8.824542999267578,
113
+ "learning_rate": 1.76326207442597e-05,
114
+ "loss": 0.4441,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.38004750593824227,
119
+ "grad_norm": 8.202225685119629,
120
+ "learning_rate": 1.747426761678543e-05,
121
+ "loss": 0.4326,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.40380047505938244,
126
+ "grad_norm": 11.430865287780762,
127
+ "learning_rate": 1.7315914489311167e-05,
128
+ "loss": 0.4169,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.42755344418052255,
133
+ "grad_norm": 6.839201927185059,
134
+ "learning_rate": 1.71575613618369e-05,
135
+ "loss": 0.4369,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.4513064133016627,
140
+ "grad_norm": 7.273525714874268,
141
+ "learning_rate": 1.699920823436263e-05,
142
+ "loss": 0.4267,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.4750593824228028,
147
+ "grad_norm": 7.3494181632995605,
148
+ "learning_rate": 1.6842438638163107e-05,
149
+ "loss": 0.4025,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.498812351543943,
154
+ "grad_norm": 12.297106742858887,
155
+ "learning_rate": 1.6684085510688836e-05,
156
+ "loss": 0.438,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.5225653206650831,
161
+ "grad_norm": 3.992037057876587,
162
+ "learning_rate": 1.652573238321457e-05,
163
+ "loss": 0.4088,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.5463182897862233,
168
+ "grad_norm": 3.9685425758361816,
169
+ "learning_rate": 1.6367379255740302e-05,
170
+ "loss": 0.3806,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 0.5700712589073634,
175
+ "grad_norm": 10.497099876403809,
176
+ "learning_rate": 1.6209026128266034e-05,
177
+ "loss": 0.4047,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 0.5938242280285035,
182
+ "grad_norm": 3.8488385677337646,
183
+ "learning_rate": 1.6050673000791767e-05,
184
+ "loss": 0.3827,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 0.6175771971496437,
189
+ "grad_norm": 9.80221939086914,
190
+ "learning_rate": 1.58923198733175e-05,
191
+ "loss": 0.4008,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 0.6413301662707839,
196
+ "grad_norm": 4.120981693267822,
197
+ "learning_rate": 1.5733966745843233e-05,
198
+ "loss": 0.4045,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 0.665083135391924,
203
+ "grad_norm": 9.871939659118652,
204
+ "learning_rate": 1.5575613618368962e-05,
205
+ "loss": 0.3787,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 0.6888361045130641,
210
+ "grad_norm": 23.69073486328125,
211
+ "learning_rate": 1.5417260490894698e-05,
212
+ "loss": 0.369,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 0.7125890736342043,
217
+ "grad_norm": 8.312384605407715,
218
+ "learning_rate": 1.525890736342043e-05,
219
+ "loss": 0.391,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 0.7363420427553444,
224
+ "grad_norm": 5.4470367431640625,
225
+ "learning_rate": 1.510055423594616e-05,
226
+ "loss": 0.3951,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 0.7600950118764845,
231
+ "grad_norm": 9.961467742919922,
232
+ "learning_rate": 1.4942201108471895e-05,
233
+ "loss": 0.3768,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 0.7838479809976246,
238
+ "grad_norm": 4.254888534545898,
239
+ "learning_rate": 1.4783847980997626e-05,
240
+ "loss": 0.3401,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 0.8076009501187649,
245
+ "grad_norm": 8.969467163085938,
246
+ "learning_rate": 1.4625494853523359e-05,
247
+ "loss": 0.3865,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 0.831353919239905,
252
+ "grad_norm": 5.86577033996582,
253
+ "learning_rate": 1.446714172604909e-05,
254
+ "loss": 0.3819,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 0.8551068883610451,
259
+ "grad_norm": 6.642719268798828,
260
+ "learning_rate": 1.4308788598574822e-05,
261
+ "loss": 0.3693,
262
+ "step": 3600
263
+ },
264
+ {
265
+ "epoch": 0.8788598574821853,
266
+ "grad_norm": 3.827361583709717,
267
+ "learning_rate": 1.4150435471100557e-05,
268
+ "loss": 0.3726,
269
+ "step": 3700
270
+ },
271
+ {
272
+ "epoch": 0.9026128266033254,
273
+ "grad_norm": 13.236315727233887,
274
+ "learning_rate": 1.3992082343626288e-05,
275
+ "loss": 0.3504,
276
+ "step": 3800
277
+ },
278
+ {
279
+ "epoch": 0.9263657957244655,
280
+ "grad_norm": 9.49841594696045,
281
+ "learning_rate": 1.383372921615202e-05,
282
+ "loss": 0.3586,
283
+ "step": 3900
284
+ },
285
+ {
286
+ "epoch": 0.9501187648456056,
287
+ "grad_norm": 17.966522216796875,
288
+ "learning_rate": 1.3675376088677752e-05,
289
+ "loss": 0.347,
290
+ "step": 4000
291
+ },
292
+ {
293
+ "epoch": 0.9738717339667459,
294
+ "grad_norm": 10.867168426513672,
295
+ "learning_rate": 1.3517022961203485e-05,
296
+ "loss": 0.3441,
297
+ "step": 4100
298
+ },
299
+ {
300
+ "epoch": 0.997624703087886,
301
+ "grad_norm": 9.008316040039062,
302
+ "learning_rate": 1.3358669833729217e-05,
303
+ "loss": 0.3721,
304
+ "step": 4200
305
+ },
306
+ {
307
+ "epoch": 1.0,
308
+ "eval_accuracy": 0.8314220183486238,
309
+ "eval_loss": 0.38916900753974915,
310
+ "eval_runtime": 3.1803,
311
+ "eval_samples_per_second": 274.19,
312
+ "eval_steps_per_second": 17.294,
313
+ "step": 4210
314
+ },
315
+ {
316
+ "epoch": 1.0213776722090262,
317
+ "grad_norm": 20.658517837524414,
318
+ "learning_rate": 1.320031670625495e-05,
319
+ "loss": 0.3262,
320
+ "step": 4300
321
+ },
322
+ {
323
+ "epoch": 1.0451306413301662,
324
+ "grad_norm": 6.5011210441589355,
325
+ "learning_rate": 1.3041963578780683e-05,
326
+ "loss": 0.3062,
327
+ "step": 4400
328
+ },
329
+ {
330
+ "epoch": 1.0688836104513064,
331
+ "grad_norm": 15.551307678222656,
332
+ "learning_rate": 1.2883610451306414e-05,
333
+ "loss": 0.2908,
334
+ "step": 4500
335
+ },
336
+ {
337
+ "epoch": 1.0926365795724466,
338
+ "grad_norm": 28.33782958984375,
339
+ "learning_rate": 1.2725257323832148e-05,
340
+ "loss": 0.2983,
341
+ "step": 4600
342
+ },
343
+ {
344
+ "epoch": 1.1163895486935866,
345
+ "grad_norm": 10.99241828918457,
346
+ "learning_rate": 1.256690419635788e-05,
347
+ "loss": 0.2897,
348
+ "step": 4700
349
+ },
350
+ {
351
+ "epoch": 1.1401425178147269,
352
+ "grad_norm": 7.335752010345459,
353
+ "learning_rate": 1.2408551068883612e-05,
354
+ "loss": 0.3304,
355
+ "step": 4800
356
+ },
357
+ {
358
+ "epoch": 1.1638954869358669,
359
+ "grad_norm": 8.83614730834961,
360
+ "learning_rate": 1.2250197941409343e-05,
361
+ "loss": 0.3016,
362
+ "step": 4900
363
+ },
364
+ {
365
+ "epoch": 1.187648456057007,
366
+ "grad_norm": 10.162006378173828,
367
+ "learning_rate": 1.2091844813935076e-05,
368
+ "loss": 0.2776,
369
+ "step": 5000
370
+ },
371
+ {
372
+ "epoch": 1.2114014251781473,
373
+ "grad_norm": 10.363824844360352,
374
+ "learning_rate": 1.1933491686460807e-05,
375
+ "loss": 0.3019,
376
+ "step": 5100
377
+ },
378
+ {
379
+ "epoch": 1.2351543942992875,
380
+ "grad_norm": 1.9022657871246338,
381
+ "learning_rate": 1.1775138558986541e-05,
382
+ "loss": 0.2856,
383
+ "step": 5200
384
+ },
385
+ {
386
+ "epoch": 1.2589073634204275,
387
+ "grad_norm": 11.627281188964844,
388
+ "learning_rate": 1.1616785431512274e-05,
389
+ "loss": 0.284,
390
+ "step": 5300
391
+ },
392
+ {
393
+ "epoch": 1.2826603325415677,
394
+ "grad_norm": 2.0096428394317627,
395
+ "learning_rate": 1.1458432304038005e-05,
396
+ "loss": 0.2938,
397
+ "step": 5400
398
+ },
399
+ {
400
+ "epoch": 1.3064133016627077,
401
+ "grad_norm": 22.037084579467773,
402
+ "learning_rate": 1.1300079176563738e-05,
403
+ "loss": 0.293,
404
+ "step": 5500
405
+ },
406
+ {
407
+ "epoch": 1.330166270783848,
408
+ "grad_norm": 11.04839038848877,
409
+ "learning_rate": 1.1141726049089469e-05,
410
+ "loss": 0.2829,
411
+ "step": 5600
412
+ },
413
+ {
414
+ "epoch": 1.3539192399049882,
415
+ "grad_norm": 13.687749862670898,
416
+ "learning_rate": 1.0983372921615203e-05,
417
+ "loss": 0.3126,
418
+ "step": 5700
419
+ },
420
+ {
421
+ "epoch": 1.3776722090261282,
422
+ "grad_norm": 5.973034381866455,
423
+ "learning_rate": 1.0825019794140935e-05,
424
+ "loss": 0.2812,
425
+ "step": 5800
426
+ },
427
+ {
428
+ "epoch": 1.4014251781472684,
429
+ "grad_norm": 2.820462226867676,
430
+ "learning_rate": 1.0666666666666667e-05,
431
+ "loss": 0.3018,
432
+ "step": 5900
433
+ },
434
+ {
435
+ "epoch": 1.4251781472684084,
436
+ "grad_norm": 9.669486999511719,
437
+ "learning_rate": 1.05083135391924e-05,
438
+ "loss": 0.2653,
439
+ "step": 6000
440
+ },
441
+ {
442
+ "epoch": 1.4489311163895486,
443
+ "grad_norm": 9.360280990600586,
444
+ "learning_rate": 1.0349960411718131e-05,
445
+ "loss": 0.2887,
446
+ "step": 6100
447
+ },
448
+ {
449
+ "epoch": 1.4726840855106889,
450
+ "grad_norm": 8.551124572753906,
451
+ "learning_rate": 1.0191607284243866e-05,
452
+ "loss": 0.2948,
453
+ "step": 6200
454
+ },
455
+ {
456
+ "epoch": 1.496437054631829,
457
+ "grad_norm": 12.017287254333496,
458
+ "learning_rate": 1.0033254156769597e-05,
459
+ "loss": 0.2931,
460
+ "step": 6300
461
+ },
462
+ {
463
+ "epoch": 1.520190023752969,
464
+ "grad_norm": 18.4260311126709,
465
+ "learning_rate": 9.87490102929533e-06,
466
+ "loss": 0.2933,
467
+ "step": 6400
468
+ },
469
+ {
470
+ "epoch": 1.5439429928741093,
471
+ "grad_norm": 21.07431983947754,
472
+ "learning_rate": 9.716547901821062e-06,
473
+ "loss": 0.3061,
474
+ "step": 6500
475
+ },
476
+ {
477
+ "epoch": 1.5676959619952493,
478
+ "grad_norm": 8.733689308166504,
479
+ "learning_rate": 9.558194774346793e-06,
480
+ "loss": 0.2508,
481
+ "step": 6600
482
+ },
483
+ {
484
+ "epoch": 1.5914489311163895,
485
+ "grad_norm": 4.291722297668457,
486
+ "learning_rate": 9.399841646872526e-06,
487
+ "loss": 0.2988,
488
+ "step": 6700
489
+ },
490
+ {
491
+ "epoch": 1.6152019002375297,
492
+ "grad_norm": 9.211682319641113,
493
+ "learning_rate": 9.241488519398259e-06,
494
+ "loss": 0.3069,
495
+ "step": 6800
496
+ },
497
+ {
498
+ "epoch": 1.63895486935867,
499
+ "grad_norm": 9.624086380004883,
500
+ "learning_rate": 9.083135391923991e-06,
501
+ "loss": 0.2933,
502
+ "step": 6900
503
+ },
504
+ {
505
+ "epoch": 1.66270783847981,
506
+ "grad_norm": 9.931711196899414,
507
+ "learning_rate": 8.924782264449724e-06,
508
+ "loss": 0.2724,
509
+ "step": 7000
510
+ },
511
+ {
512
+ "epoch": 1.68646080760095,
513
+ "grad_norm": 4.174336910247803,
514
+ "learning_rate": 8.766429136975457e-06,
515
+ "loss": 0.2615,
516
+ "step": 7100
517
+ },
518
+ {
519
+ "epoch": 1.7102137767220902,
520
+ "grad_norm": 11.723244667053223,
521
+ "learning_rate": 8.608076009501188e-06,
522
+ "loss": 0.285,
523
+ "step": 7200
524
+ },
525
+ {
526
+ "epoch": 1.7339667458432304,
527
+ "grad_norm": 12.756488800048828,
528
+ "learning_rate": 8.44972288202692e-06,
529
+ "loss": 0.2771,
530
+ "step": 7300
531
+ },
532
+ {
533
+ "epoch": 1.7577197149643706,
534
+ "grad_norm": 9.429771423339844,
535
+ "learning_rate": 8.291369754552654e-06,
536
+ "loss": 0.2824,
537
+ "step": 7400
538
+ },
539
+ {
540
+ "epoch": 1.7814726840855108,
541
+ "grad_norm": 13.813314437866211,
542
+ "learning_rate": 8.133016627078385e-06,
543
+ "loss": 0.2965,
544
+ "step": 7500
545
+ },
546
+ {
547
+ "epoch": 1.8052256532066508,
548
+ "grad_norm": 8.05421257019043,
549
+ "learning_rate": 7.974663499604119e-06,
550
+ "loss": 0.2613,
551
+ "step": 7600
552
+ },
553
+ {
554
+ "epoch": 1.8289786223277908,
555
+ "grad_norm": 5.644511699676514,
556
+ "learning_rate": 7.81631037212985e-06,
557
+ "loss": 0.2827,
558
+ "step": 7700
559
+ },
560
+ {
561
+ "epoch": 1.852731591448931,
562
+ "grad_norm": 10.623388290405273,
563
+ "learning_rate": 7.657957244655583e-06,
564
+ "loss": 0.2655,
565
+ "step": 7800
566
+ },
567
+ {
568
+ "epoch": 1.8764845605700713,
569
+ "grad_norm": 27.798290252685547,
570
+ "learning_rate": 7.499604117181315e-06,
571
+ "loss": 0.2992,
572
+ "step": 7900
573
+ },
574
+ {
575
+ "epoch": 1.9002375296912115,
576
+ "grad_norm": 8.613077163696289,
577
+ "learning_rate": 7.3412509897070475e-06,
578
+ "loss": 0.2635,
579
+ "step": 8000
580
+ },
581
+ {
582
+ "epoch": 1.9239904988123515,
583
+ "grad_norm": 10.832771301269531,
584
+ "learning_rate": 7.1828978622327794e-06,
585
+ "loss": 0.2672,
586
+ "step": 8100
587
+ },
588
+ {
589
+ "epoch": 1.9477434679334917,
590
+ "grad_norm": 16.065528869628906,
591
+ "learning_rate": 7.024544734758511e-06,
592
+ "loss": 0.262,
593
+ "step": 8200
594
+ },
595
+ {
596
+ "epoch": 1.9714964370546317,
597
+ "grad_norm": 13.325654029846191,
598
+ "learning_rate": 6.866191607284245e-06,
599
+ "loss": 0.2826,
600
+ "step": 8300
601
+ },
602
+ {
603
+ "epoch": 1.995249406175772,
604
+ "grad_norm": 16.392105102539062,
605
+ "learning_rate": 6.707838479809977e-06,
606
+ "loss": 0.2661,
607
+ "step": 8400
608
+ },
609
+ {
610
+ "epoch": 2.0,
611
+ "eval_accuracy": 0.8497706422018348,
612
+ "eval_loss": 0.3956442177295685,
613
+ "eval_runtime": 2.9709,
614
+ "eval_samples_per_second": 293.511,
615
+ "eval_steps_per_second": 18.513,
616
+ "step": 8420
617
+ },
618
+ {
619
+ "epoch": 2.019002375296912,
620
+ "grad_norm": 24.83507537841797,
621
+ "learning_rate": 6.54948535233571e-06,
622
+ "loss": 0.2195,
623
+ "step": 8500
624
+ },
625
+ {
626
+ "epoch": 2.0427553444180524,
627
+ "grad_norm": 13.459088325500488,
628
+ "learning_rate": 6.3911322248614415e-06,
629
+ "loss": 0.2333,
630
+ "step": 8600
631
+ },
632
+ {
633
+ "epoch": 2.0665083135391926,
634
+ "grad_norm": 23.071367263793945,
635
+ "learning_rate": 6.232779097387173e-06,
636
+ "loss": 0.2222,
637
+ "step": 8700
638
+ },
639
+ {
640
+ "epoch": 2.0902612826603324,
641
+ "grad_norm": 20.328954696655273,
642
+ "learning_rate": 6.074425969912906e-06,
643
+ "loss": 0.2417,
644
+ "step": 8800
645
+ },
646
+ {
647
+ "epoch": 2.1140142517814726,
648
+ "grad_norm": 12.929640769958496,
649
+ "learning_rate": 5.916072842438638e-06,
650
+ "loss": 0.2158,
651
+ "step": 8900
652
+ },
653
+ {
654
+ "epoch": 2.137767220902613,
655
+ "grad_norm": 3.765835762023926,
656
+ "learning_rate": 5.757719714964372e-06,
657
+ "loss": 0.2228,
658
+ "step": 9000
659
+ },
660
+ {
661
+ "epoch": 2.161520190023753,
662
+ "grad_norm": 15.415190696716309,
663
+ "learning_rate": 5.599366587490104e-06,
664
+ "loss": 0.2107,
665
+ "step": 9100
666
+ },
667
+ {
668
+ "epoch": 2.1852731591448933,
669
+ "grad_norm": 8.424735069274902,
670
+ "learning_rate": 5.441013460015836e-06,
671
+ "loss": 0.2393,
672
+ "step": 9200
673
+ },
674
+ {
675
+ "epoch": 2.209026128266033,
676
+ "grad_norm": 10.958281517028809,
677
+ "learning_rate": 5.282660332541568e-06,
678
+ "loss": 0.206,
679
+ "step": 9300
680
+ },
681
+ {
682
+ "epoch": 2.2327790973871733,
683
+ "grad_norm": 9.020813941955566,
684
+ "learning_rate": 5.1243072050673e-06,
685
+ "loss": 0.1987,
686
+ "step": 9400
687
+ },
688
+ {
689
+ "epoch": 2.2565320665083135,
690
+ "grad_norm": 28.11874008178711,
691
+ "learning_rate": 4.965954077593033e-06,
692
+ "loss": 0.2121,
693
+ "step": 9500
694
+ },
695
+ {
696
+ "epoch": 2.2802850356294537,
697
+ "grad_norm": 13.661537170410156,
698
+ "learning_rate": 4.807600950118766e-06,
699
+ "loss": 0.2313,
700
+ "step": 9600
701
+ },
702
+ {
703
+ "epoch": 2.304038004750594,
704
+ "grad_norm": 5.820676803588867,
705
+ "learning_rate": 4.6492478226444976e-06,
706
+ "loss": 0.2076,
707
+ "step": 9700
708
+ },
709
+ {
710
+ "epoch": 2.3277909738717337,
711
+ "grad_norm": 30.28268051147461,
712
+ "learning_rate": 4.4908946951702295e-06,
713
+ "loss": 0.2142,
714
+ "step": 9800
715
+ },
716
+ {
717
+ "epoch": 2.351543942992874,
718
+ "grad_norm": 1.176238775253296,
719
+ "learning_rate": 4.332541567695962e-06,
720
+ "loss": 0.2058,
721
+ "step": 9900
722
+ },
723
+ {
724
+ "epoch": 2.375296912114014,
725
+ "grad_norm": 7.50606632232666,
726
+ "learning_rate": 4.1757719714964375e-06,
727
+ "loss": 0.2493,
728
+ "step": 10000
729
+ },
730
+ {
731
+ "epoch": 2.3990498812351544,
732
+ "grad_norm": 4.3427205085754395,
733
+ "learning_rate": 4.017418844022169e-06,
734
+ "loss": 0.2137,
735
+ "step": 10100
736
+ },
737
+ {
738
+ "epoch": 2.4228028503562946,
739
+ "grad_norm": 10.145256996154785,
740
+ "learning_rate": 3.859065716547902e-06,
741
+ "loss": 0.2129,
742
+ "step": 10200
743
+ },
744
+ {
745
+ "epoch": 2.446555819477435,
746
+ "grad_norm": 7.9584527015686035,
747
+ "learning_rate": 3.7007125890736345e-06,
748
+ "loss": 0.2107,
749
+ "step": 10300
750
+ },
751
+ {
752
+ "epoch": 2.470308788598575,
753
+ "grad_norm": 9.902059555053711,
754
+ "learning_rate": 3.542359461599367e-06,
755
+ "loss": 0.2231,
756
+ "step": 10400
757
+ },
758
+ {
759
+ "epoch": 2.494061757719715,
760
+ "grad_norm": 18.705286026000977,
761
+ "learning_rate": 3.3840063341250996e-06,
762
+ "loss": 0.2121,
763
+ "step": 10500
764
+ },
765
+ {
766
+ "epoch": 2.517814726840855,
767
+ "grad_norm": 29.508682250976562,
768
+ "learning_rate": 3.2256532066508315e-06,
769
+ "loss": 0.2421,
770
+ "step": 10600
771
+ },
772
+ {
773
+ "epoch": 2.5415676959619953,
774
+ "grad_norm": 4.328601360321045,
775
+ "learning_rate": 3.067300079176564e-06,
776
+ "loss": 0.1913,
777
+ "step": 10700
778
+ },
779
+ {
780
+ "epoch": 2.5653206650831355,
781
+ "grad_norm": 3.3285276889801025,
782
+ "learning_rate": 2.908946951702296e-06,
783
+ "loss": 0.2426,
784
+ "step": 10800
785
+ },
786
+ {
787
+ "epoch": 2.5890736342042757,
788
+ "grad_norm": 4.220156669616699,
789
+ "learning_rate": 2.750593824228029e-06,
790
+ "loss": 0.2375,
791
+ "step": 10900
792
+ },
793
+ {
794
+ "epoch": 2.6128266033254155,
795
+ "grad_norm": 24.65312385559082,
796
+ "learning_rate": 2.5922406967537612e-06,
797
+ "loss": 0.2304,
798
+ "step": 11000
799
+ },
800
+ {
801
+ "epoch": 2.6365795724465557,
802
+ "grad_norm": 8.729198455810547,
803
+ "learning_rate": 2.4338875692794936e-06,
804
+ "loss": 0.2067,
805
+ "step": 11100
806
+ },
807
+ {
808
+ "epoch": 2.660332541567696,
809
+ "grad_norm": 15.05286693572998,
810
+ "learning_rate": 2.275534441805226e-06,
811
+ "loss": 0.2415,
812
+ "step": 11200
813
+ },
814
+ {
815
+ "epoch": 2.684085510688836,
816
+ "grad_norm": 26.644716262817383,
817
+ "learning_rate": 2.1171813143309582e-06,
818
+ "loss": 0.2401,
819
+ "step": 11300
820
+ },
821
+ {
822
+ "epoch": 2.7078384798099764,
823
+ "grad_norm": 10.57201862335205,
824
+ "learning_rate": 1.9588281868566906e-06,
825
+ "loss": 0.2406,
826
+ "step": 11400
827
+ },
828
+ {
829
+ "epoch": 2.731591448931116,
830
+ "grad_norm": 6.5845465660095215,
831
+ "learning_rate": 1.800475059382423e-06,
832
+ "loss": 0.1857,
833
+ "step": 11500
834
+ },
835
+ {
836
+ "epoch": 2.7553444180522564,
837
+ "grad_norm": 7.665100574493408,
838
+ "learning_rate": 1.6421219319081552e-06,
839
+ "loss": 0.2249,
840
+ "step": 11600
841
+ },
842
+ {
843
+ "epoch": 2.7790973871733966,
844
+ "grad_norm": 1.698305368423462,
845
+ "learning_rate": 1.4837688044338878e-06,
846
+ "loss": 0.2164,
847
+ "step": 11700
848
+ },
849
+ {
850
+ "epoch": 2.802850356294537,
851
+ "grad_norm": 45.78740310668945,
852
+ "learning_rate": 1.3254156769596199e-06,
853
+ "loss": 0.2125,
854
+ "step": 11800
855
+ },
856
+ {
857
+ "epoch": 2.826603325415677,
858
+ "grad_norm": 18.53032684326172,
859
+ "learning_rate": 1.1670625494853524e-06,
860
+ "loss": 0.2076,
861
+ "step": 11900
862
+ },
863
+ {
864
+ "epoch": 2.850356294536817,
865
+ "grad_norm": 35.8634147644043,
866
+ "learning_rate": 1.0087094220110848e-06,
867
+ "loss": 0.2141,
868
+ "step": 12000
869
+ },
870
+ {
871
+ "epoch": 2.8741092636579575,
872
+ "grad_norm": 10.635025024414062,
873
+ "learning_rate": 8.503562945368171e-07,
874
+ "loss": 0.1897,
875
+ "step": 12100
876
+ },
877
+ {
878
+ "epoch": 2.8978622327790973,
879
+ "grad_norm": 2.4744296073913574,
880
+ "learning_rate": 6.920031670625496e-07,
881
+ "loss": 0.1959,
882
+ "step": 12200
883
+ },
884
+ {
885
+ "epoch": 2.9216152019002375,
886
+ "grad_norm": 24.558425903320312,
887
+ "learning_rate": 5.336500395882819e-07,
888
+ "loss": 0.2176,
889
+ "step": 12300
890
+ },
891
+ {
892
+ "epoch": 2.9453681710213777,
893
+ "grad_norm": 36.37364196777344,
894
+ "learning_rate": 3.76880443388757e-07,
895
+ "loss": 0.2252,
896
+ "step": 12400
897
+ },
898
+ {
899
+ "epoch": 2.969121140142518,
900
+ "grad_norm": 0.5130617022514343,
901
+ "learning_rate": 2.20110847189232e-07,
902
+ "loss": 0.1907,
903
+ "step": 12500
904
+ },
905
+ {
906
+ "epoch": 2.992874109263658,
907
+ "grad_norm": 33.36646270751953,
908
+ "learning_rate": 6.175771971496438e-08,
909
+ "loss": 0.2017,
910
+ "step": 12600
911
+ },
912
+ {
913
+ "epoch": 3.0,
914
+ "eval_accuracy": 0.8520642201834863,
915
+ "eval_loss": 0.5416586995124817,
916
+ "eval_runtime": 2.9354,
917
+ "eval_samples_per_second": 297.064,
918
+ "eval_steps_per_second": 18.737,
919
+ "step": 12630
920
+ }
921
+ ],
922
+ "logging_steps": 100,
923
+ "max_steps": 12630,
924
+ "num_input_tokens_seen": 0,
925
+ "num_train_epochs": 3,
926
+ "save_steps": 500,
927
+ "stateful_callbacks": {
928
+ "TrainerControl": {
929
+ "args": {
930
+ "should_epoch_stop": false,
931
+ "should_evaluate": false,
932
+ "should_log": false,
933
+ "should_save": true,
934
+ "should_training_stop": true
935
+ },
936
+ "attributes": {}
937
+ }
938
+ },
939
+ "total_flos": 5.316079940232192e+16,
940
+ "train_batch_size": 16,
941
+ "trial_name": null,
942
+ "trial_params": null
943
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebeac1c4178ea87538f00ed7982fbda41d402aae10dceb3e702c095dfe8d283
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff