lkw2025 commited on
Commit
b74313b
·
verified ·
1 Parent(s): 6c91a17

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/kcbert-base",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 300,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.49.0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 30000
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0badb4647cee5a1a8da676e33cee9c66a5296c30d335b77d5b2c4430b38365
3
+ size 435706868
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe3b8e8655e0230758b69ece5742ce7dc19a325a467f8cb6daca13a91342921
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e791ab9d80f86918218addbef8bc409a05b5b07389076fdc345d3c8a1dbeb519
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": 300,
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
+ }
trainer_state.json ADDED
@@ -0,0 +1,853 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9087747458533976,
3
+ "best_model_checkpoint": "./checkpoints/beomi_kcbert-base\\checkpoint-5607",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5607,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02675227394328518,
13
+ "grad_norm": 5.228867053985596,
14
+ "learning_rate": 1.9821651507044767e-05,
15
+ "loss": 0.8035,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.05350454788657036,
20
+ "grad_norm": 20.66253662109375,
21
+ "learning_rate": 1.9643303014089533e-05,
22
+ "loss": 0.5287,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.08025682182985554,
27
+ "grad_norm": 9.66049575805664,
28
+ "learning_rate": 1.94649545211343e-05,
29
+ "loss": 0.5059,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.10700909577314072,
34
+ "grad_norm": 12.687285423278809,
35
+ "learning_rate": 1.9286606028179064e-05,
36
+ "loss": 0.5266,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.1337613697164259,
41
+ "grad_norm": 13.331902503967285,
42
+ "learning_rate": 1.910825753522383e-05,
43
+ "loss": 0.4482,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.16051364365971107,
48
+ "grad_norm": 6.606617450714111,
49
+ "learning_rate": 1.8929909042268595e-05,
50
+ "loss": 0.4771,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.18726591760299627,
55
+ "grad_norm": 3.6321372985839844,
56
+ "learning_rate": 1.8751560549313357e-05,
57
+ "loss": 0.5196,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.21401819154628143,
62
+ "grad_norm": 5.700988292694092,
63
+ "learning_rate": 1.8573212056358126e-05,
64
+ "loss": 0.4296,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.24077046548956663,
69
+ "grad_norm": 14.550703048706055,
70
+ "learning_rate": 1.8394863563402892e-05,
71
+ "loss": 0.4121,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.2675227394328518,
76
+ "grad_norm": 11.130396842956543,
77
+ "learning_rate": 1.8216515070447654e-05,
78
+ "loss": 0.4423,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.294275013376137,
83
+ "grad_norm": 13.779672622680664,
84
+ "learning_rate": 1.8038166577492423e-05,
85
+ "loss": 0.3953,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.32102728731942215,
90
+ "grad_norm": 7.454031944274902,
91
+ "learning_rate": 1.7859818084537185e-05,
92
+ "loss": 0.3708,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.3477795612627073,
97
+ "grad_norm": 5.720978260040283,
98
+ "learning_rate": 1.768146959158195e-05,
99
+ "loss": 0.421,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.37453183520599254,
104
+ "grad_norm": 14.370809555053711,
105
+ "learning_rate": 1.750312109862672e-05,
106
+ "loss": 0.4154,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.4012841091492777,
111
+ "grad_norm": 3.7566840648651123,
112
+ "learning_rate": 1.7324772605671482e-05,
113
+ "loss": 0.3827,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.42803638309256287,
118
+ "grad_norm": 13.605573654174805,
119
+ "learning_rate": 1.7146424112716248e-05,
120
+ "loss": 0.3827,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.45478865703584803,
125
+ "grad_norm": 3.2871532440185547,
126
+ "learning_rate": 1.6968075619761017e-05,
127
+ "loss": 0.4183,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.48154093097913325,
132
+ "grad_norm": 5.473564624786377,
133
+ "learning_rate": 1.678972712680578e-05,
134
+ "loss": 0.3829,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.5082932049224184,
139
+ "grad_norm": 20.812192916870117,
140
+ "learning_rate": 1.6611378633850545e-05,
141
+ "loss": 0.3746,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.5350454788657036,
146
+ "grad_norm": 9.71611499786377,
147
+ "learning_rate": 1.643303014089531e-05,
148
+ "loss": 0.3721,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.5617977528089888,
153
+ "grad_norm": 9.370783805847168,
154
+ "learning_rate": 1.6254681647940076e-05,
155
+ "loss": 0.3902,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.588550026752274,
160
+ "grad_norm": 5.628559112548828,
161
+ "learning_rate": 1.607633315498484e-05,
162
+ "loss": 0.3221,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.6153023006955591,
167
+ "grad_norm": 9.518179893493652,
168
+ "learning_rate": 1.5897984662029607e-05,
169
+ "loss": 0.3722,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.6420545746388443,
174
+ "grad_norm": 12.84173583984375,
175
+ "learning_rate": 1.5719636169074372e-05,
176
+ "loss": 0.3963,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.6688068485821295,
181
+ "grad_norm": 2.825850486755371,
182
+ "learning_rate": 1.5541287676119138e-05,
183
+ "loss": 0.3787,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.6955591225254146,
188
+ "grad_norm": 18.818218231201172,
189
+ "learning_rate": 1.5362939183163904e-05,
190
+ "loss": 0.3443,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.7223113964686998,
195
+ "grad_norm": 8.157448768615723,
196
+ "learning_rate": 1.518459069020867e-05,
197
+ "loss": 0.3857,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.7490636704119851,
202
+ "grad_norm": 6.142508029937744,
203
+ "learning_rate": 1.5006242197253433e-05,
204
+ "loss": 0.3516,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.7758159443552702,
209
+ "grad_norm": 13.665266990661621,
210
+ "learning_rate": 1.48278937042982e-05,
211
+ "loss": 0.3564,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.8025682182985554,
216
+ "grad_norm": 6.96636962890625,
217
+ "learning_rate": 1.4649545211342966e-05,
218
+ "loss": 0.3241,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.8293204922418406,
223
+ "grad_norm": 4.158944606781006,
224
+ "learning_rate": 1.447119671838773e-05,
225
+ "loss": 0.3507,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.8560727661851257,
230
+ "grad_norm": 12.31186294555664,
231
+ "learning_rate": 1.4292848225432496e-05,
232
+ "loss": 0.3741,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.8828250401284109,
237
+ "grad_norm": 8.98780632019043,
238
+ "learning_rate": 1.4114499732477263e-05,
239
+ "loss": 0.3327,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.9095773140716961,
244
+ "grad_norm": 4.7375335693359375,
245
+ "learning_rate": 1.3936151239522027e-05,
246
+ "loss": 0.3146,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.9363295880149812,
251
+ "grad_norm": 7.906491756439209,
252
+ "learning_rate": 1.3757802746566792e-05,
253
+ "loss": 0.3437,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.9630818619582665,
258
+ "grad_norm": 3.6906189918518066,
259
+ "learning_rate": 1.3579454253611556e-05,
260
+ "loss": 0.3023,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.9898341359015517,
265
+ "grad_norm": 9.612889289855957,
266
+ "learning_rate": 1.3401105760656324e-05,
267
+ "loss": 0.2908,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 1.0,
272
+ "eval_accuracy": 0.8865703584804708,
273
+ "eval_f1": 0.8776064533107432,
274
+ "eval_loss": 0.2936590015888214,
275
+ "eval_precision": 0.879542702484244,
276
+ "eval_recall": 0.8757295845022814,
277
+ "eval_runtime": 2.8948,
278
+ "eval_samples_per_second": 1291.298,
279
+ "eval_steps_per_second": 80.836,
280
+ "step": 1869
281
+ },
282
+ {
283
+ "epoch": 1.0165864098448367,
284
+ "grad_norm": 5.979121685028076,
285
+ "learning_rate": 1.3222757267701089e-05,
286
+ "loss": 0.2547,
287
+ "step": 1900
288
+ },
289
+ {
290
+ "epoch": 1.043338683788122,
291
+ "grad_norm": 3.420891284942627,
292
+ "learning_rate": 1.3044408774745853e-05,
293
+ "loss": 0.2483,
294
+ "step": 1950
295
+ },
296
+ {
297
+ "epoch": 1.070090957731407,
298
+ "grad_norm": 6.0562520027160645,
299
+ "learning_rate": 1.286606028179062e-05,
300
+ "loss": 0.2334,
301
+ "step": 2000
302
+ },
303
+ {
304
+ "epoch": 1.0968432316746923,
305
+ "grad_norm": 5.684343338012695,
306
+ "learning_rate": 1.2687711788835386e-05,
307
+ "loss": 0.2165,
308
+ "step": 2050
309
+ },
310
+ {
311
+ "epoch": 1.1235955056179776,
312
+ "grad_norm": 12.342307090759277,
313
+ "learning_rate": 1.250936329588015e-05,
314
+ "loss": 0.2185,
315
+ "step": 2100
316
+ },
317
+ {
318
+ "epoch": 1.1503477795612627,
319
+ "grad_norm": 10.415166854858398,
320
+ "learning_rate": 1.2331014802924917e-05,
321
+ "loss": 0.2436,
322
+ "step": 2150
323
+ },
324
+ {
325
+ "epoch": 1.177100053504548,
326
+ "grad_norm": 24.330848693847656,
327
+ "learning_rate": 1.2152666309969681e-05,
328
+ "loss": 0.2218,
329
+ "step": 2200
330
+ },
331
+ {
332
+ "epoch": 1.203852327447833,
333
+ "grad_norm": 19.10972785949707,
334
+ "learning_rate": 1.1974317817014447e-05,
335
+ "loss": 0.2268,
336
+ "step": 2250
337
+ },
338
+ {
339
+ "epoch": 1.2306046013911183,
340
+ "grad_norm": 5.752458572387695,
341
+ "learning_rate": 1.1795969324059214e-05,
342
+ "loss": 0.1923,
343
+ "step": 2300
344
+ },
345
+ {
346
+ "epoch": 1.2573568753344033,
347
+ "grad_norm": 7.389070510864258,
348
+ "learning_rate": 1.1617620831103978e-05,
349
+ "loss": 0.2207,
350
+ "step": 2350
351
+ },
352
+ {
353
+ "epoch": 1.2841091492776886,
354
+ "grad_norm": 8.551554679870605,
355
+ "learning_rate": 1.1439272338148743e-05,
356
+ "loss": 0.2634,
357
+ "step": 2400
358
+ },
359
+ {
360
+ "epoch": 1.3108614232209739,
361
+ "grad_norm": 8.443785667419434,
362
+ "learning_rate": 1.126092384519351e-05,
363
+ "loss": 0.2116,
364
+ "step": 2450
365
+ },
366
+ {
367
+ "epoch": 1.337613697164259,
368
+ "grad_norm": 0.6092638969421387,
369
+ "learning_rate": 1.1082575352238275e-05,
370
+ "loss": 0.2033,
371
+ "step": 2500
372
+ },
373
+ {
374
+ "epoch": 1.3643659711075442,
375
+ "grad_norm": 2.732888698577881,
376
+ "learning_rate": 1.090422685928304e-05,
377
+ "loss": 0.2469,
378
+ "step": 2550
379
+ },
380
+ {
381
+ "epoch": 1.3911182450508293,
382
+ "grad_norm": 5.319647312164307,
383
+ "learning_rate": 1.0725878366327804e-05,
384
+ "loss": 0.2212,
385
+ "step": 2600
386
+ },
387
+ {
388
+ "epoch": 1.4178705189941145,
389
+ "grad_norm": 7.216152191162109,
390
+ "learning_rate": 1.0547529873372571e-05,
391
+ "loss": 0.2124,
392
+ "step": 2650
393
+ },
394
+ {
395
+ "epoch": 1.4446227929373996,
396
+ "grad_norm": 9.755507469177246,
397
+ "learning_rate": 1.0369181380417337e-05,
398
+ "loss": 0.2129,
399
+ "step": 2700
400
+ },
401
+ {
402
+ "epoch": 1.4713750668806849,
403
+ "grad_norm": 14.041426658630371,
404
+ "learning_rate": 1.01908328874621e-05,
405
+ "loss": 0.1971,
406
+ "step": 2750
407
+ },
408
+ {
409
+ "epoch": 1.4981273408239701,
410
+ "grad_norm": 14.255478858947754,
411
+ "learning_rate": 1.0012484394506868e-05,
412
+ "loss": 0.1675,
413
+ "step": 2800
414
+ },
415
+ {
416
+ "epoch": 1.5248796147672552,
417
+ "grad_norm": 2.1935946941375732,
418
+ "learning_rate": 9.834135901551632e-06,
419
+ "loss": 0.2042,
420
+ "step": 2850
421
+ },
422
+ {
423
+ "epoch": 1.5516318887105403,
424
+ "grad_norm": 8.990334510803223,
425
+ "learning_rate": 9.655787408596398e-06,
426
+ "loss": 0.226,
427
+ "step": 2900
428
+ },
429
+ {
430
+ "epoch": 1.5783841626538255,
431
+ "grad_norm": 2.0768239498138428,
432
+ "learning_rate": 9.477438915641163e-06,
433
+ "loss": 0.1659,
434
+ "step": 2950
435
+ },
436
+ {
437
+ "epoch": 1.6051364365971108,
438
+ "grad_norm": 9.156929016113281,
439
+ "learning_rate": 9.299090422685929e-06,
440
+ "loss": 0.2023,
441
+ "step": 3000
442
+ },
443
+ {
444
+ "epoch": 1.6318887105403959,
445
+ "grad_norm": 9.479352951049805,
446
+ "learning_rate": 9.120741929730694e-06,
447
+ "loss": 0.2452,
448
+ "step": 3050
449
+ },
450
+ {
451
+ "epoch": 1.6586409844836811,
452
+ "grad_norm": 10.488241195678711,
453
+ "learning_rate": 8.94239343677546e-06,
454
+ "loss": 0.1783,
455
+ "step": 3100
456
+ },
457
+ {
458
+ "epoch": 1.6853932584269664,
459
+ "grad_norm": 24.130321502685547,
460
+ "learning_rate": 8.764044943820226e-06,
461
+ "loss": 0.261,
462
+ "step": 3150
463
+ },
464
+ {
465
+ "epoch": 1.7121455323702515,
466
+ "grad_norm": 14.768345832824707,
467
+ "learning_rate": 8.585696450864991e-06,
468
+ "loss": 0.219,
469
+ "step": 3200
470
+ },
471
+ {
472
+ "epoch": 1.7388978063135365,
473
+ "grad_norm": 15.370089530944824,
474
+ "learning_rate": 8.407347957909757e-06,
475
+ "loss": 0.1993,
476
+ "step": 3250
477
+ },
478
+ {
479
+ "epoch": 1.7656500802568218,
480
+ "grad_norm": 3.223907232284546,
481
+ "learning_rate": 8.22899946495452e-06,
482
+ "loss": 0.1752,
483
+ "step": 3300
484
+ },
485
+ {
486
+ "epoch": 1.792402354200107,
487
+ "grad_norm": 11.258790016174316,
488
+ "learning_rate": 8.050650971999288e-06,
489
+ "loss": 0.1844,
490
+ "step": 3350
491
+ },
492
+ {
493
+ "epoch": 1.8191546281433921,
494
+ "grad_norm": 2.2796430587768555,
495
+ "learning_rate": 7.872302479044054e-06,
496
+ "loss": 0.1728,
497
+ "step": 3400
498
+ },
499
+ {
500
+ "epoch": 1.8459069020866774,
501
+ "grad_norm": 7.105353355407715,
502
+ "learning_rate": 7.693953986088817e-06,
503
+ "loss": 0.2508,
504
+ "step": 3450
505
+ },
506
+ {
507
+ "epoch": 1.8726591760299627,
508
+ "grad_norm": 3.3236451148986816,
509
+ "learning_rate": 7.515605493133583e-06,
510
+ "loss": 0.1902,
511
+ "step": 3500
512
+ },
513
+ {
514
+ "epoch": 1.8994114499732477,
515
+ "grad_norm": 17.00351905822754,
516
+ "learning_rate": 7.3372570001783495e-06,
517
+ "loss": 0.1954,
518
+ "step": 3550
519
+ },
520
+ {
521
+ "epoch": 1.9261637239165328,
522
+ "grad_norm": 5.1884331703186035,
523
+ "learning_rate": 7.158908507223114e-06,
524
+ "loss": 0.1975,
525
+ "step": 3600
526
+ },
527
+ {
528
+ "epoch": 1.952915997859818,
529
+ "grad_norm": 7.371060848236084,
530
+ "learning_rate": 6.98056001426788e-06,
531
+ "loss": 0.1979,
532
+ "step": 3650
533
+ },
534
+ {
535
+ "epoch": 1.9796682718031033,
536
+ "grad_norm": 14.774871826171875,
537
+ "learning_rate": 6.8022115213126446e-06,
538
+ "loss": 0.1868,
539
+ "step": 3700
540
+ },
541
+ {
542
+ "epoch": 2.0,
543
+ "eval_accuracy": 0.9018191546281434,
544
+ "eval_f1": 0.8926409675168582,
545
+ "eval_loss": 0.2982310950756073,
546
+ "eval_precision": 0.9016177612582297,
547
+ "eval_recall": 0.8848553089710288,
548
+ "eval_runtime": 3.0671,
549
+ "eval_samples_per_second": 1218.757,
550
+ "eval_steps_per_second": 76.295,
551
+ "step": 3738
552
+ },
553
+ {
554
+ "epoch": 2.0064205457463884,
555
+ "grad_norm": 2.9711053371429443,
556
+ "learning_rate": 6.623863028357411e-06,
557
+ "loss": 0.1811,
558
+ "step": 3750
559
+ },
560
+ {
561
+ "epoch": 2.0331728196896734,
562
+ "grad_norm": 11.470788955688477,
563
+ "learning_rate": 6.445514535402177e-06,
564
+ "loss": 0.1382,
565
+ "step": 3800
566
+ },
567
+ {
568
+ "epoch": 2.059925093632959,
569
+ "grad_norm": 3.6617465019226074,
570
+ "learning_rate": 6.267166042446941e-06,
571
+ "loss": 0.1374,
572
+ "step": 3850
573
+ },
574
+ {
575
+ "epoch": 2.086677367576244,
576
+ "grad_norm": 14.748554229736328,
577
+ "learning_rate": 6.088817549491707e-06,
578
+ "loss": 0.0932,
579
+ "step": 3900
580
+ },
581
+ {
582
+ "epoch": 2.113429641519529,
583
+ "grad_norm": 2.309537172317505,
584
+ "learning_rate": 5.910469056536473e-06,
585
+ "loss": 0.1017,
586
+ "step": 3950
587
+ },
588
+ {
589
+ "epoch": 2.140181915462814,
590
+ "grad_norm": 5.085292339324951,
591
+ "learning_rate": 5.732120563581238e-06,
592
+ "loss": 0.1598,
593
+ "step": 4000
594
+ },
595
+ {
596
+ "epoch": 2.1669341894060996,
597
+ "grad_norm": 15.087725639343262,
598
+ "learning_rate": 5.553772070626004e-06,
599
+ "loss": 0.1095,
600
+ "step": 4050
601
+ },
602
+ {
603
+ "epoch": 2.1936864633493847,
604
+ "grad_norm": 20.651540756225586,
605
+ "learning_rate": 5.3754235776707685e-06,
606
+ "loss": 0.1128,
607
+ "step": 4100
608
+ },
609
+ {
610
+ "epoch": 2.2204387372926697,
611
+ "grad_norm": 23.393356323242188,
612
+ "learning_rate": 5.197075084715535e-06,
613
+ "loss": 0.099,
614
+ "step": 4150
615
+ },
616
+ {
617
+ "epoch": 2.247191011235955,
618
+ "grad_norm": 30.76633644104004,
619
+ "learning_rate": 5.0187265917603005e-06,
620
+ "loss": 0.1015,
621
+ "step": 4200
622
+ },
623
+ {
624
+ "epoch": 2.2739432851792403,
625
+ "grad_norm": 10.410665512084961,
626
+ "learning_rate": 4.840378098805065e-06,
627
+ "loss": 0.1583,
628
+ "step": 4250
629
+ },
630
+ {
631
+ "epoch": 2.3006955591225253,
632
+ "grad_norm": 0.0475541315972805,
633
+ "learning_rate": 4.662029605849831e-06,
634
+ "loss": 0.118,
635
+ "step": 4300
636
+ },
637
+ {
638
+ "epoch": 2.3274478330658104,
639
+ "grad_norm": 0.0829029381275177,
640
+ "learning_rate": 4.4836811128945964e-06,
641
+ "loss": 0.1169,
642
+ "step": 4350
643
+ },
644
+ {
645
+ "epoch": 2.354200107009096,
646
+ "grad_norm": 25.78684425354004,
647
+ "learning_rate": 4.305332619939362e-06,
648
+ "loss": 0.0962,
649
+ "step": 4400
650
+ },
651
+ {
652
+ "epoch": 2.380952380952381,
653
+ "grad_norm": 1.0623866319656372,
654
+ "learning_rate": 4.126984126984127e-06,
655
+ "loss": 0.179,
656
+ "step": 4450
657
+ },
658
+ {
659
+ "epoch": 2.407704654895666,
660
+ "grad_norm": 8.90683650970459,
661
+ "learning_rate": 3.948635634028893e-06,
662
+ "loss": 0.1481,
663
+ "step": 4500
664
+ },
665
+ {
666
+ "epoch": 2.4344569288389515,
667
+ "grad_norm": 3.296332836151123,
668
+ "learning_rate": 3.770287141073658e-06,
669
+ "loss": 0.1109,
670
+ "step": 4550
671
+ },
672
+ {
673
+ "epoch": 2.4612092027822365,
674
+ "grad_norm": 11.87473201751709,
675
+ "learning_rate": 3.5919386481184236e-06,
676
+ "loss": 0.0927,
677
+ "step": 4600
678
+ },
679
+ {
680
+ "epoch": 2.4879614767255216,
681
+ "grad_norm": 13.711977005004883,
682
+ "learning_rate": 3.4135901551631887e-06,
683
+ "loss": 0.1389,
684
+ "step": 4650
685
+ },
686
+ {
687
+ "epoch": 2.5147137506688066,
688
+ "grad_norm": 48.17192840576172,
689
+ "learning_rate": 3.2352416622079547e-06,
690
+ "loss": 0.0996,
691
+ "step": 4700
692
+ },
693
+ {
694
+ "epoch": 2.541466024612092,
695
+ "grad_norm": 0.33165135979652405,
696
+ "learning_rate": 3.05689316925272e-06,
697
+ "loss": 0.1331,
698
+ "step": 4750
699
+ },
700
+ {
701
+ "epoch": 2.568218298555377,
702
+ "grad_norm": 0.20608340203762054,
703
+ "learning_rate": 2.8785446762974855e-06,
704
+ "loss": 0.1066,
705
+ "step": 4800
706
+ },
707
+ {
708
+ "epoch": 2.5949705724986623,
709
+ "grad_norm": 0.3617757260799408,
710
+ "learning_rate": 2.7001961833422507e-06,
711
+ "loss": 0.1585,
712
+ "step": 4850
713
+ },
714
+ {
715
+ "epoch": 2.6217228464419478,
716
+ "grad_norm": 5.1519670486450195,
717
+ "learning_rate": 2.5218476903870167e-06,
718
+ "loss": 0.1266,
719
+ "step": 4900
720
+ },
721
+ {
722
+ "epoch": 2.648475120385233,
723
+ "grad_norm": 35.215240478515625,
724
+ "learning_rate": 2.343499197431782e-06,
725
+ "loss": 0.1083,
726
+ "step": 4950
727
+ },
728
+ {
729
+ "epoch": 2.675227394328518,
730
+ "grad_norm": 10.100606918334961,
731
+ "learning_rate": 2.1651507044765475e-06,
732
+ "loss": 0.1342,
733
+ "step": 5000
734
+ },
735
+ {
736
+ "epoch": 2.701979668271803,
737
+ "grad_norm": 15.540501594543457,
738
+ "learning_rate": 1.986802211521313e-06,
739
+ "loss": 0.17,
740
+ "step": 5050
741
+ },
742
+ {
743
+ "epoch": 2.7287319422150884,
744
+ "grad_norm": 0.2651878297328949,
745
+ "learning_rate": 1.8084537185660782e-06,
746
+ "loss": 0.0879,
747
+ "step": 5100
748
+ },
749
+ {
750
+ "epoch": 2.7554842161583735,
751
+ "grad_norm": 0.8803261518478394,
752
+ "learning_rate": 1.6301052256108438e-06,
753
+ "loss": 0.0985,
754
+ "step": 5150
755
+ },
756
+ {
757
+ "epoch": 2.7822364901016585,
758
+ "grad_norm": 0.043911464512348175,
759
+ "learning_rate": 1.4517567326556092e-06,
760
+ "loss": 0.1241,
761
+ "step": 5200
762
+ },
763
+ {
764
+ "epoch": 2.808988764044944,
765
+ "grad_norm": 0.012229884043335915,
766
+ "learning_rate": 1.2734082397003748e-06,
767
+ "loss": 0.1167,
768
+ "step": 5250
769
+ },
770
+ {
771
+ "epoch": 2.835741037988229,
772
+ "grad_norm": 5.769114017486572,
773
+ "learning_rate": 1.0950597467451402e-06,
774
+ "loss": 0.1411,
775
+ "step": 5300
776
+ },
777
+ {
778
+ "epoch": 2.862493311931514,
779
+ "grad_norm": 14.51673698425293,
780
+ "learning_rate": 9.167112537899057e-07,
781
+ "loss": 0.085,
782
+ "step": 5350
783
+ },
784
+ {
785
+ "epoch": 2.889245585874799,
786
+ "grad_norm": 7.242597579956055,
787
+ "learning_rate": 7.38362760834671e-07,
788
+ "loss": 0.1215,
789
+ "step": 5400
790
+ },
791
+ {
792
+ "epoch": 2.9159978598180847,
793
+ "grad_norm": 3.783128023147583,
794
+ "learning_rate": 5.600142678794364e-07,
795
+ "loss": 0.0713,
796
+ "step": 5450
797
+ },
798
+ {
799
+ "epoch": 2.9427501337613697,
800
+ "grad_norm": 0.4435977637767792,
801
+ "learning_rate": 3.816657749242019e-07,
802
+ "loss": 0.1135,
803
+ "step": 5500
804
+ },
805
+ {
806
+ "epoch": 2.969502407704655,
807
+ "grad_norm": 22.0134220123291,
808
+ "learning_rate": 2.0331728196896737e-07,
809
+ "loss": 0.0976,
810
+ "step": 5550
811
+ },
812
+ {
813
+ "epoch": 2.9962546816479403,
814
+ "grad_norm": 0.05080915242433548,
815
+ "learning_rate": 2.4968789013732835e-08,
816
+ "loss": 0.1141,
817
+ "step": 5600
818
+ },
819
+ {
820
+ "epoch": 3.0,
821
+ "eval_accuracy": 0.9087747458533976,
822
+ "eval_f1": 0.901188417064033,
823
+ "eval_loss": 0.41310834884643555,
824
+ "eval_precision": 0.9053103806790227,
825
+ "eval_recall": 0.8972911214880508,
826
+ "eval_runtime": 3.2883,
827
+ "eval_samples_per_second": 1136.766,
828
+ "eval_steps_per_second": 71.162,
829
+ "step": 5607
830
+ }
831
+ ],
832
+ "logging_steps": 50,
833
+ "max_steps": 5607,
834
+ "num_input_tokens_seen": 0,
835
+ "num_train_epochs": 3,
836
+ "save_steps": 500,
837
+ "stateful_callbacks": {
838
+ "TrainerControl": {
839
+ "args": {
840
+ "should_epoch_stop": false,
841
+ "should_evaluate": false,
842
+ "should_log": false,
843
+ "should_save": true,
844
+ "should_training_stop": true
845
+ },
846
+ "attributes": {}
847
+ }
848
+ },
849
+ "total_flos": 922607713156626.0,
850
+ "train_batch_size": 16,
851
+ "trial_name": null,
852
+ "trial_params": null
853
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9942b3dbf3957d01db1464eb14f30a3a8c96d4e1aa02286d535c893137551e29
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff