rabbitfishai commited on
Commit
17c8b8d
·
verified ·
1 Parent(s): c1a7cd4

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-2500/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:761f13539b9bf2f365017b5a0989de900ad87212e35437ce3ff59d64631a5373
3
+ size 735397076
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41362a70db048d9c42bb01c3de6d5773f985359c71e2484446a1351f70581831
3
+ size 1470918475
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:236a9997e7a4ee413eb83391ddabc90ee2ae25d7c2ff70856389c017bcbcb793
3
+ size 14645
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7c5782da63c15ac7c18611cac39c99c0cdbc60eb9a96abf66020cfa9f66671
3
+ size 1465
checkpoint-2500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-2500/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-2500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2500/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,909 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.7056277056277054,
6
+ "eval_steps": 500,
7
+ "global_step": 2500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.021645021645021644,
14
+ "grad_norm": 5.047379493713379,
15
+ "learning_rate": 1.9862914862914863e-05,
16
+ "loss": 1.5752,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.04329004329004329,
21
+ "grad_norm": 3.371302604675293,
22
+ "learning_rate": 1.971861471861472e-05,
23
+ "loss": 0.8153,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.06493506493506493,
28
+ "grad_norm": 1.9615145921707153,
29
+ "learning_rate": 1.9574314574314578e-05,
30
+ "loss": 0.5959,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.08658008658008658,
35
+ "grad_norm": 3.8159589767456055,
36
+ "learning_rate": 1.9430014430014433e-05,
37
+ "loss": 0.5437,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.10822510822510822,
42
+ "grad_norm": 1.7913705110549927,
43
+ "learning_rate": 1.928571428571429e-05,
44
+ "loss": 0.4788,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.12987012987012986,
49
+ "grad_norm": 2.2625105381011963,
50
+ "learning_rate": 1.9141414141414144e-05,
51
+ "loss": 0.4678,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.15151515151515152,
56
+ "grad_norm": 1.6875262260437012,
57
+ "learning_rate": 1.8997113997114e-05,
58
+ "loss": 0.3672,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.17316017316017315,
63
+ "grad_norm": 2.3179216384887695,
64
+ "learning_rate": 1.8852813852813855e-05,
65
+ "loss": 0.3275,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.19480519480519481,
70
+ "grad_norm": 11.622775077819824,
71
+ "learning_rate": 1.870851370851371e-05,
72
+ "loss": 0.2794,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.21645021645021645,
77
+ "grad_norm": 1.9436513185501099,
78
+ "learning_rate": 1.8564213564213566e-05,
79
+ "loss": 0.2397,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.23809523809523808,
84
+ "grad_norm": 1.332103967666626,
85
+ "learning_rate": 1.841991341991342e-05,
86
+ "loss": 0.1845,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.2597402597402597,
91
+ "grad_norm": 1.2064969539642334,
92
+ "learning_rate": 1.8275613275613276e-05,
93
+ "loss": 0.1534,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.2813852813852814,
98
+ "grad_norm": 1.5475531816482544,
99
+ "learning_rate": 1.8131313131313132e-05,
100
+ "loss": 0.1261,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.30303030303030304,
105
+ "grad_norm": 1.0386016368865967,
106
+ "learning_rate": 1.7987012987012987e-05,
107
+ "loss": 0.1491,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.3246753246753247,
112
+ "grad_norm": 1.127977728843689,
113
+ "learning_rate": 1.7842712842712843e-05,
114
+ "loss": 0.0947,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.3463203463203463,
119
+ "grad_norm": 0.7528420686721802,
120
+ "learning_rate": 1.7698412698412698e-05,
121
+ "loss": 0.0915,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 0.36796536796536794,
126
+ "grad_norm": 2.6987464427948,
127
+ "learning_rate": 1.7554112554112554e-05,
128
+ "loss": 0.0725,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 0.38961038961038963,
133
+ "grad_norm": 0.45937371253967285,
134
+ "learning_rate": 1.7409812409812412e-05,
135
+ "loss": 0.0598,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.41125541125541126,
140
+ "grad_norm": 0.5548325777053833,
141
+ "learning_rate": 1.7265512265512268e-05,
142
+ "loss": 0.0723,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 0.4329004329004329,
147
+ "grad_norm": 0.7995928525924683,
148
+ "learning_rate": 1.7121212121212123e-05,
149
+ "loss": 0.0677,
150
+ "step": 400
151
+ },
152
+ {
153
+ "epoch": 0.45454545454545453,
154
+ "grad_norm": 0.34620311856269836,
155
+ "learning_rate": 1.697691197691198e-05,
156
+ "loss": 0.0545,
157
+ "step": 420
158
+ },
159
+ {
160
+ "epoch": 0.47619047619047616,
161
+ "grad_norm": 0.38282573223114014,
162
+ "learning_rate": 1.6832611832611834e-05,
163
+ "loss": 0.064,
164
+ "step": 440
165
+ },
166
+ {
167
+ "epoch": 0.49783549783549785,
168
+ "grad_norm": 0.34734392166137695,
169
+ "learning_rate": 1.668831168831169e-05,
170
+ "loss": 0.0417,
171
+ "step": 460
172
+ },
173
+ {
174
+ "epoch": 0.5194805194805194,
175
+ "grad_norm": 0.5567700266838074,
176
+ "learning_rate": 1.6544011544011545e-05,
177
+ "loss": 0.0567,
178
+ "step": 480
179
+ },
180
+ {
181
+ "epoch": 0.5411255411255411,
182
+ "grad_norm": 0.24816854298114777,
183
+ "learning_rate": 1.6399711399711404e-05,
184
+ "loss": 0.0353,
185
+ "step": 500
186
+ },
187
+ {
188
+ "epoch": 0.5627705627705628,
189
+ "grad_norm": 0.2364570051431656,
190
+ "learning_rate": 1.625541125541126e-05,
191
+ "loss": 0.0488,
192
+ "step": 520
193
+ },
194
+ {
195
+ "epoch": 0.5844155844155844,
196
+ "grad_norm": 0.7323583364486694,
197
+ "learning_rate": 1.6111111111111115e-05,
198
+ "loss": 0.054,
199
+ "step": 540
200
+ },
201
+ {
202
+ "epoch": 0.6060606060606061,
203
+ "grad_norm": 0.2931612730026245,
204
+ "learning_rate": 1.5966810966810967e-05,
205
+ "loss": 0.0571,
206
+ "step": 560
207
+ },
208
+ {
209
+ "epoch": 0.6277056277056277,
210
+ "grad_norm": 0.25314539670944214,
211
+ "learning_rate": 1.5822510822510822e-05,
212
+ "loss": 0.0448,
213
+ "step": 580
214
+ },
215
+ {
216
+ "epoch": 0.6493506493506493,
217
+ "grad_norm": 0.20941877365112305,
218
+ "learning_rate": 1.5678210678210677e-05,
219
+ "loss": 0.0333,
220
+ "step": 600
221
+ },
222
+ {
223
+ "epoch": 0.670995670995671,
224
+ "grad_norm": 0.23521284759044647,
225
+ "learning_rate": 1.5533910533910533e-05,
226
+ "loss": 0.0347,
227
+ "step": 620
228
+ },
229
+ {
230
+ "epoch": 0.6926406926406926,
231
+ "grad_norm": 0.3161298930644989,
232
+ "learning_rate": 1.538961038961039e-05,
233
+ "loss": 0.0475,
234
+ "step": 640
235
+ },
236
+ {
237
+ "epoch": 0.7142857142857143,
238
+ "grad_norm": 0.8162543177604675,
239
+ "learning_rate": 1.5245310245310247e-05,
240
+ "loss": 0.0271,
241
+ "step": 660
242
+ },
243
+ {
244
+ "epoch": 0.7359307359307359,
245
+ "grad_norm": 0.20186349749565125,
246
+ "learning_rate": 1.5101010101010103e-05,
247
+ "loss": 0.0833,
248
+ "step": 680
249
+ },
250
+ {
251
+ "epoch": 0.7575757575757576,
252
+ "grad_norm": 0.19510218501091003,
253
+ "learning_rate": 1.4956709956709958e-05,
254
+ "loss": 0.043,
255
+ "step": 700
256
+ },
257
+ {
258
+ "epoch": 0.7792207792207793,
259
+ "grad_norm": 0.20879587531089783,
260
+ "learning_rate": 1.4812409812409813e-05,
261
+ "loss": 0.021,
262
+ "step": 720
263
+ },
264
+ {
265
+ "epoch": 0.8008658008658008,
266
+ "grad_norm": 0.18057775497436523,
267
+ "learning_rate": 1.4668109668109669e-05,
268
+ "loss": 0.0412,
269
+ "step": 740
270
+ },
271
+ {
272
+ "epoch": 0.8225108225108225,
273
+ "grad_norm": 0.15316598117351532,
274
+ "learning_rate": 1.4523809523809524e-05,
275
+ "loss": 0.0244,
276
+ "step": 760
277
+ },
278
+ {
279
+ "epoch": 0.8441558441558441,
280
+ "grad_norm": 0.1659492552280426,
281
+ "learning_rate": 1.437950937950938e-05,
282
+ "loss": 0.0294,
283
+ "step": 780
284
+ },
285
+ {
286
+ "epoch": 0.8658008658008658,
287
+ "grad_norm": 0.1682518869638443,
288
+ "learning_rate": 1.4235209235209237e-05,
289
+ "loss": 0.0184,
290
+ "step": 800
291
+ },
292
+ {
293
+ "epoch": 0.8874458874458875,
294
+ "grad_norm": 0.222774937748909,
295
+ "learning_rate": 1.4090909090909092e-05,
296
+ "loss": 0.0203,
297
+ "step": 820
298
+ },
299
+ {
300
+ "epoch": 0.9090909090909091,
301
+ "grad_norm": 0.13427211344242096,
302
+ "learning_rate": 1.3946608946608948e-05,
303
+ "loss": 0.0411,
304
+ "step": 840
305
+ },
306
+ {
307
+ "epoch": 0.9307359307359307,
308
+ "grad_norm": 5.2049126625061035,
309
+ "learning_rate": 1.3802308802308803e-05,
310
+ "loss": 0.0383,
311
+ "step": 860
312
+ },
313
+ {
314
+ "epoch": 0.9523809523809523,
315
+ "grad_norm": 0.23792877793312073,
316
+ "learning_rate": 1.3658008658008659e-05,
317
+ "loss": 0.0182,
318
+ "step": 880
319
+ },
320
+ {
321
+ "epoch": 0.974025974025974,
322
+ "grad_norm": 0.12495584785938263,
323
+ "learning_rate": 1.3513708513708514e-05,
324
+ "loss": 0.029,
325
+ "step": 900
326
+ },
327
+ {
328
+ "epoch": 0.9956709956709957,
329
+ "grad_norm": 0.28919360041618347,
330
+ "learning_rate": 1.336940836940837e-05,
331
+ "loss": 0.0192,
332
+ "step": 920
333
+ },
334
+ {
335
+ "epoch": 1.0173160173160174,
336
+ "grad_norm": 0.11999514698982239,
337
+ "learning_rate": 1.3225108225108225e-05,
338
+ "loss": 0.0157,
339
+ "step": 940
340
+ },
341
+ {
342
+ "epoch": 1.0389610389610389,
343
+ "grad_norm": 0.14448480308055878,
344
+ "learning_rate": 1.3080808080808084e-05,
345
+ "loss": 0.0156,
346
+ "step": 960
347
+ },
348
+ {
349
+ "epoch": 1.0606060606060606,
350
+ "grad_norm": 0.37867000699043274,
351
+ "learning_rate": 1.2936507936507937e-05,
352
+ "loss": 0.0158,
353
+ "step": 980
354
+ },
355
+ {
356
+ "epoch": 1.0822510822510822,
357
+ "grad_norm": 0.1649075597524643,
358
+ "learning_rate": 1.2792207792207793e-05,
359
+ "loss": 0.0156,
360
+ "step": 1000
361
+ },
362
+ {
363
+ "epoch": 1.103896103896104,
364
+ "grad_norm": 0.11258062720298767,
365
+ "learning_rate": 1.2647907647907648e-05,
366
+ "loss": 0.029,
367
+ "step": 1020
368
+ },
369
+ {
370
+ "epoch": 1.1255411255411256,
371
+ "grad_norm": 0.16054819524288177,
372
+ "learning_rate": 1.2503607503607504e-05,
373
+ "loss": 0.0366,
374
+ "step": 1040
375
+ },
376
+ {
377
+ "epoch": 1.1471861471861473,
378
+ "grad_norm": 0.16296619176864624,
379
+ "learning_rate": 1.2359307359307359e-05,
380
+ "loss": 0.0135,
381
+ "step": 1060
382
+ },
383
+ {
384
+ "epoch": 1.1688311688311688,
385
+ "grad_norm": 5.796433448791504,
386
+ "learning_rate": 1.2215007215007215e-05,
387
+ "loss": 0.0422,
388
+ "step": 1080
389
+ },
390
+ {
391
+ "epoch": 1.1904761904761905,
392
+ "grad_norm": 0.19343234598636627,
393
+ "learning_rate": 1.207070707070707e-05,
394
+ "loss": 0.0144,
395
+ "step": 1100
396
+ },
397
+ {
398
+ "epoch": 1.2121212121212122,
399
+ "grad_norm": 0.12345093488693237,
400
+ "learning_rate": 1.1926406926406929e-05,
401
+ "loss": 0.0124,
402
+ "step": 1120
403
+ },
404
+ {
405
+ "epoch": 1.2337662337662338,
406
+ "grad_norm": 0.17719799280166626,
407
+ "learning_rate": 1.1782106782106784e-05,
408
+ "loss": 0.0442,
409
+ "step": 1140
410
+ },
411
+ {
412
+ "epoch": 1.2554112554112553,
413
+ "grad_norm": 0.26392945647239685,
414
+ "learning_rate": 1.163780663780664e-05,
415
+ "loss": 0.0123,
416
+ "step": 1160
417
+ },
418
+ {
419
+ "epoch": 1.277056277056277,
420
+ "grad_norm": 0.06477934867143631,
421
+ "learning_rate": 1.1493506493506495e-05,
422
+ "loss": 0.0151,
423
+ "step": 1180
424
+ },
425
+ {
426
+ "epoch": 1.2987012987012987,
427
+ "grad_norm": 0.10530120134353638,
428
+ "learning_rate": 1.134920634920635e-05,
429
+ "loss": 0.0129,
430
+ "step": 1200
431
+ },
432
+ {
433
+ "epoch": 1.3203463203463204,
434
+ "grad_norm": 0.10538487881422043,
435
+ "learning_rate": 1.1204906204906206e-05,
436
+ "loss": 0.0156,
437
+ "step": 1220
438
+ },
439
+ {
440
+ "epoch": 1.341991341991342,
441
+ "grad_norm": 0.10836771875619888,
442
+ "learning_rate": 1.1060606060606061e-05,
443
+ "loss": 0.0178,
444
+ "step": 1240
445
+ },
446
+ {
447
+ "epoch": 1.3636363636363638,
448
+ "grad_norm": 3.7379777431488037,
449
+ "learning_rate": 1.0916305916305919e-05,
450
+ "loss": 0.0145,
451
+ "step": 1260
452
+ },
453
+ {
454
+ "epoch": 1.3852813852813852,
455
+ "grad_norm": 0.19971278309822083,
456
+ "learning_rate": 1.0772005772005774e-05,
457
+ "loss": 0.0458,
458
+ "step": 1280
459
+ },
460
+ {
461
+ "epoch": 1.406926406926407,
462
+ "grad_norm": 0.17772097885608673,
463
+ "learning_rate": 1.062770562770563e-05,
464
+ "loss": 0.0123,
465
+ "step": 1300
466
+ },
467
+ {
468
+ "epoch": 1.4285714285714286,
469
+ "grad_norm": 0.12699300050735474,
470
+ "learning_rate": 1.0483405483405485e-05,
471
+ "loss": 0.0306,
472
+ "step": 1320
473
+ },
474
+ {
475
+ "epoch": 1.4502164502164503,
476
+ "grad_norm": 0.08466625213623047,
477
+ "learning_rate": 1.033910533910534e-05,
478
+ "loss": 0.0108,
479
+ "step": 1340
480
+ },
481
+ {
482
+ "epoch": 1.4718614718614718,
483
+ "grad_norm": 0.09285025298595428,
484
+ "learning_rate": 1.0194805194805196e-05,
485
+ "loss": 0.0131,
486
+ "step": 1360
487
+ },
488
+ {
489
+ "epoch": 1.4935064935064934,
490
+ "grad_norm": 0.1555718034505844,
491
+ "learning_rate": 1.0050505050505051e-05,
492
+ "loss": 0.0182,
493
+ "step": 1380
494
+ },
495
+ {
496
+ "epoch": 1.5151515151515151,
497
+ "grad_norm": 0.1831505000591278,
498
+ "learning_rate": 9.906204906204907e-06,
499
+ "loss": 0.0102,
500
+ "step": 1400
501
+ },
502
+ {
503
+ "epoch": 1.5367965367965368,
504
+ "grad_norm": 0.09224329888820648,
505
+ "learning_rate": 9.761904761904762e-06,
506
+ "loss": 0.0116,
507
+ "step": 1420
508
+ },
509
+ {
510
+ "epoch": 1.5584415584415585,
511
+ "grad_norm": 0.08490342646837234,
512
+ "learning_rate": 9.617604617604619e-06,
513
+ "loss": 0.0102,
514
+ "step": 1440
515
+ },
516
+ {
517
+ "epoch": 1.5800865800865802,
518
+ "grad_norm": 0.16526533663272858,
519
+ "learning_rate": 9.473304473304474e-06,
520
+ "loss": 0.0217,
521
+ "step": 1460
522
+ },
523
+ {
524
+ "epoch": 1.601731601731602,
525
+ "grad_norm": 0.08393661677837372,
526
+ "learning_rate": 9.32900432900433e-06,
527
+ "loss": 0.0103,
528
+ "step": 1480
529
+ },
530
+ {
531
+ "epoch": 1.6233766233766234,
532
+ "grad_norm": 0.13095460832118988,
533
+ "learning_rate": 9.184704184704185e-06,
534
+ "loss": 0.022,
535
+ "step": 1500
536
+ },
537
+ {
538
+ "epoch": 1.645021645021645,
539
+ "grad_norm": 0.13940352201461792,
540
+ "learning_rate": 9.040404040404042e-06,
541
+ "loss": 0.0229,
542
+ "step": 1520
543
+ },
544
+ {
545
+ "epoch": 1.6666666666666665,
546
+ "grad_norm": 0.11868056654930115,
547
+ "learning_rate": 8.896103896103896e-06,
548
+ "loss": 0.0104,
549
+ "step": 1540
550
+ },
551
+ {
552
+ "epoch": 1.6883116883116882,
553
+ "grad_norm": 0.060605239123106,
554
+ "learning_rate": 8.751803751803752e-06,
555
+ "loss": 0.0162,
556
+ "step": 1560
557
+ },
558
+ {
559
+ "epoch": 1.70995670995671,
560
+ "grad_norm": 0.10808888077735901,
561
+ "learning_rate": 8.607503607503607e-06,
562
+ "loss": 0.0087,
563
+ "step": 1580
564
+ },
565
+ {
566
+ "epoch": 1.7316017316017316,
567
+ "grad_norm": 0.08839452266693115,
568
+ "learning_rate": 8.463203463203464e-06,
569
+ "loss": 0.0091,
570
+ "step": 1600
571
+ },
572
+ {
573
+ "epoch": 1.7532467532467533,
574
+ "grad_norm": 0.10623842477798462,
575
+ "learning_rate": 8.31890331890332e-06,
576
+ "loss": 0.0122,
577
+ "step": 1620
578
+ },
579
+ {
580
+ "epoch": 1.774891774891775,
581
+ "grad_norm": 0.056098755449056625,
582
+ "learning_rate": 8.174603174603175e-06,
583
+ "loss": 0.0092,
584
+ "step": 1640
585
+ },
586
+ {
587
+ "epoch": 1.7965367965367967,
588
+ "grad_norm": 0.11627987772226334,
589
+ "learning_rate": 8.03030303030303e-06,
590
+ "loss": 0.0082,
591
+ "step": 1660
592
+ },
593
+ {
594
+ "epoch": 1.8181818181818183,
595
+ "grad_norm": 0.08929106593132019,
596
+ "learning_rate": 7.886002886002888e-06,
597
+ "loss": 0.018,
598
+ "step": 1680
599
+ },
600
+ {
601
+ "epoch": 1.8398268398268398,
602
+ "grad_norm": 0.0906723365187645,
603
+ "learning_rate": 7.741702741702743e-06,
604
+ "loss": 0.0153,
605
+ "step": 1700
606
+ },
607
+ {
608
+ "epoch": 1.8614718614718615,
609
+ "grad_norm": 0.06793191283941269,
610
+ "learning_rate": 7.597402597402598e-06,
611
+ "loss": 0.0184,
612
+ "step": 1720
613
+ },
614
+ {
615
+ "epoch": 1.883116883116883,
616
+ "grad_norm": 0.12505404651165009,
617
+ "learning_rate": 7.453102453102453e-06,
618
+ "loss": 0.0092,
619
+ "step": 1740
620
+ },
621
+ {
622
+ "epoch": 1.9047619047619047,
623
+ "grad_norm": 0.09465266019105911,
624
+ "learning_rate": 7.308802308802309e-06,
625
+ "loss": 0.0133,
626
+ "step": 1760
627
+ },
628
+ {
629
+ "epoch": 1.9264069264069263,
630
+ "grad_norm": 0.09390600025653839,
631
+ "learning_rate": 7.164502164502165e-06,
632
+ "loss": 0.0179,
633
+ "step": 1780
634
+ },
635
+ {
636
+ "epoch": 1.948051948051948,
637
+ "grad_norm": 0.07343223690986633,
638
+ "learning_rate": 7.02020202020202e-06,
639
+ "loss": 0.0104,
640
+ "step": 1800
641
+ },
642
+ {
643
+ "epoch": 1.9696969696969697,
644
+ "grad_norm": 0.13794736564159393,
645
+ "learning_rate": 6.875901875901877e-06,
646
+ "loss": 0.0188,
647
+ "step": 1820
648
+ },
649
+ {
650
+ "epoch": 1.9913419913419914,
651
+ "grad_norm": 0.04812062159180641,
652
+ "learning_rate": 6.731601731601733e-06,
653
+ "loss": 0.0193,
654
+ "step": 1840
655
+ },
656
+ {
657
+ "epoch": 2.012987012987013,
658
+ "grad_norm": 0.08907242119312286,
659
+ "learning_rate": 6.587301587301588e-06,
660
+ "loss": 0.0342,
661
+ "step": 1860
662
+ },
663
+ {
664
+ "epoch": 2.034632034632035,
665
+ "grad_norm": 0.06940910965204239,
666
+ "learning_rate": 6.443001443001443e-06,
667
+ "loss": 0.0085,
668
+ "step": 1880
669
+ },
670
+ {
671
+ "epoch": 2.0562770562770565,
672
+ "grad_norm": 0.07371290028095245,
673
+ "learning_rate": 6.2987012987013e-06,
674
+ "loss": 0.0101,
675
+ "step": 1900
676
+ },
677
+ {
678
+ "epoch": 2.0779220779220777,
679
+ "grad_norm": 0.10616641491651535,
680
+ "learning_rate": 6.154401154401155e-06,
681
+ "loss": 0.0256,
682
+ "step": 1920
683
+ },
684
+ {
685
+ "epoch": 2.0995670995670994,
686
+ "grad_norm": 0.07746961712837219,
687
+ "learning_rate": 6.010101010101011e-06,
688
+ "loss": 0.0093,
689
+ "step": 1940
690
+ },
691
+ {
692
+ "epoch": 2.121212121212121,
693
+ "grad_norm": 0.19828535616397858,
694
+ "learning_rate": 5.865800865800866e-06,
695
+ "loss": 0.008,
696
+ "step": 1960
697
+ },
698
+ {
699
+ "epoch": 2.142857142857143,
700
+ "grad_norm": 0.11058467626571655,
701
+ "learning_rate": 5.721500721500722e-06,
702
+ "loss": 0.0172,
703
+ "step": 1980
704
+ },
705
+ {
706
+ "epoch": 2.1645021645021645,
707
+ "grad_norm": 0.04194315895438194,
708
+ "learning_rate": 5.577200577200578e-06,
709
+ "loss": 0.0095,
710
+ "step": 2000
711
+ },
712
+ {
713
+ "epoch": 2.186147186147186,
714
+ "grad_norm": 0.10634741187095642,
715
+ "learning_rate": 5.432900432900433e-06,
716
+ "loss": 0.0133,
717
+ "step": 2020
718
+ },
719
+ {
720
+ "epoch": 2.207792207792208,
721
+ "grad_norm": 0.0997764989733696,
722
+ "learning_rate": 5.288600288600289e-06,
723
+ "loss": 0.0135,
724
+ "step": 2040
725
+ },
726
+ {
727
+ "epoch": 2.2294372294372296,
728
+ "grad_norm": 0.1089092567563057,
729
+ "learning_rate": 5.144300144300145e-06,
730
+ "loss": 0.0267,
731
+ "step": 2060
732
+ },
733
+ {
734
+ "epoch": 2.2510822510822512,
735
+ "grad_norm": 0.09123284369707108,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.0076,
738
+ "step": 2080
739
+ },
740
+ {
741
+ "epoch": 2.2727272727272725,
742
+ "grad_norm": 0.06854091584682465,
743
+ "learning_rate": 4.855699855699857e-06,
744
+ "loss": 0.0147,
745
+ "step": 2100
746
+ },
747
+ {
748
+ "epoch": 2.2943722943722946,
749
+ "grad_norm": 0.11229178309440613,
750
+ "learning_rate": 4.711399711399712e-06,
751
+ "loss": 0.0072,
752
+ "step": 2120
753
+ },
754
+ {
755
+ "epoch": 2.316017316017316,
756
+ "grad_norm": 0.0881107822060585,
757
+ "learning_rate": 4.5670995670995675e-06,
758
+ "loss": 0.0141,
759
+ "step": 2140
760
+ },
761
+ {
762
+ "epoch": 2.3376623376623376,
763
+ "grad_norm": 0.08736357092857361,
764
+ "learning_rate": 4.422799422799423e-06,
765
+ "loss": 0.0162,
766
+ "step": 2160
767
+ },
768
+ {
769
+ "epoch": 2.3593073593073592,
770
+ "grad_norm": 0.06391258537769318,
771
+ "learning_rate": 4.278499278499279e-06,
772
+ "loss": 0.0076,
773
+ "step": 2180
774
+ },
775
+ {
776
+ "epoch": 2.380952380952381,
777
+ "grad_norm": 0.08132211863994598,
778
+ "learning_rate": 4.134199134199135e-06,
779
+ "loss": 0.007,
780
+ "step": 2200
781
+ },
782
+ {
783
+ "epoch": 2.4025974025974026,
784
+ "grad_norm": 0.06198592483997345,
785
+ "learning_rate": 3.98989898989899e-06,
786
+ "loss": 0.0061,
787
+ "step": 2220
788
+ },
789
+ {
790
+ "epoch": 2.4242424242424243,
791
+ "grad_norm": 0.07765072584152222,
792
+ "learning_rate": 3.8455988455988455e-06,
793
+ "loss": 0.0075,
794
+ "step": 2240
795
+ },
796
+ {
797
+ "epoch": 2.445887445887446,
798
+ "grad_norm": 0.092200867831707,
799
+ "learning_rate": 3.701298701298702e-06,
800
+ "loss": 0.0167,
801
+ "step": 2260
802
+ },
803
+ {
804
+ "epoch": 2.4675324675324677,
805
+ "grad_norm": 0.07408732175827026,
806
+ "learning_rate": 3.5569985569985572e-06,
807
+ "loss": 0.0065,
808
+ "step": 2280
809
+ },
810
+ {
811
+ "epoch": 2.4891774891774894,
812
+ "grad_norm": 0.05288136005401611,
813
+ "learning_rate": 3.412698412698413e-06,
814
+ "loss": 0.0148,
815
+ "step": 2300
816
+ },
817
+ {
818
+ "epoch": 2.5108225108225106,
819
+ "grad_norm": 0.08382824063301086,
820
+ "learning_rate": 3.2683982683982685e-06,
821
+ "loss": 0.0174,
822
+ "step": 2320
823
+ },
824
+ {
825
+ "epoch": 2.5324675324675323,
826
+ "grad_norm": 0.06475148350000381,
827
+ "learning_rate": 3.1240981240981244e-06,
828
+ "loss": 0.008,
829
+ "step": 2340
830
+ },
831
+ {
832
+ "epoch": 2.554112554112554,
833
+ "grad_norm": 0.08863703906536102,
834
+ "learning_rate": 2.97979797979798e-06,
835
+ "loss": 0.0066,
836
+ "step": 2360
837
+ },
838
+ {
839
+ "epoch": 2.5757575757575757,
840
+ "grad_norm": 0.08658093959093094,
841
+ "learning_rate": 2.8354978354978357e-06,
842
+ "loss": 0.0134,
843
+ "step": 2380
844
+ },
845
+ {
846
+ "epoch": 2.5974025974025974,
847
+ "grad_norm": 0.0753917247056961,
848
+ "learning_rate": 2.691197691197691e-06,
849
+ "loss": 0.0065,
850
+ "step": 2400
851
+ },
852
+ {
853
+ "epoch": 2.619047619047619,
854
+ "grad_norm": 0.15559795498847961,
855
+ "learning_rate": 2.546897546897547e-06,
856
+ "loss": 0.0065,
857
+ "step": 2420
858
+ },
859
+ {
860
+ "epoch": 2.6406926406926408,
861
+ "grad_norm": 0.051586903631687164,
862
+ "learning_rate": 2.402597402597403e-06,
863
+ "loss": 0.0088,
864
+ "step": 2440
865
+ },
866
+ {
867
+ "epoch": 2.6623376623376624,
868
+ "grad_norm": 0.04571373015642166,
869
+ "learning_rate": 2.2582972582972586e-06,
870
+ "loss": 0.0265,
871
+ "step": 2460
872
+ },
873
+ {
874
+ "epoch": 2.683982683982684,
875
+ "grad_norm": 0.08445149660110474,
876
+ "learning_rate": 2.113997113997114e-06,
877
+ "loss": 0.0079,
878
+ "step": 2480
879
+ },
880
+ {
881
+ "epoch": 2.7056277056277054,
882
+ "grad_norm": 0.0789010226726532,
883
+ "learning_rate": 1.96969696969697e-06,
884
+ "loss": 0.0088,
885
+ "step": 2500
886
+ }
887
+ ],
888
+ "logging_steps": 20,
889
+ "max_steps": 2772,
890
+ "num_input_tokens_seen": 0,
891
+ "num_train_epochs": 3,
892
+ "save_steps": 500,
893
+ "stateful_callbacks": {
894
+ "TrainerControl": {
895
+ "args": {
896
+ "should_epoch_stop": false,
897
+ "should_evaluate": false,
898
+ "should_log": false,
899
+ "should_save": true,
900
+ "should_training_stop": false
901
+ },
902
+ "attributes": {}
903
+ }
904
+ },
905
+ "total_flos": 0.0,
906
+ "train_batch_size": 16,
907
+ "trial_name": null,
908
+ "trial_params": null
909
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf723c2d0b1b8fe4f313e3091797d2a7106afbdafeb0077464451ff5c28790c
3
+ size 5777
checkpoint-2772/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-2772/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3abc568578d1d9f7486ebd7f388fcec6850a1fe47c13572ecad77ab181728d
3
+ size 735397076
checkpoint-2772/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652f4c15321b2d212aab967f996ffd96fcf03fb8034aec32df11871ba03a83c7
3
+ size 1470918475
checkpoint-2772/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528c3ffe2d4eff6c65459ef3024c7570d540627e74510de0cb50a14b201a9664
3
+ size 14645
checkpoint-2772/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b933c13499fb316a1d06ef21c8f554142572418141979d4e12dbccc0909b8cc6
3
+ size 1465
checkpoint-2772/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-2772/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-2772/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2772/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-2772/trainer_state.json ADDED
@@ -0,0 +1,1000 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2772,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.021645021645021644,
14
+ "grad_norm": 5.047379493713379,
15
+ "learning_rate": 1.9862914862914863e-05,
16
+ "loss": 1.5752,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.04329004329004329,
21
+ "grad_norm": 3.371302604675293,
22
+ "learning_rate": 1.971861471861472e-05,
23
+ "loss": 0.8153,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.06493506493506493,
28
+ "grad_norm": 1.9615145921707153,
29
+ "learning_rate": 1.9574314574314578e-05,
30
+ "loss": 0.5959,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.08658008658008658,
35
+ "grad_norm": 3.8159589767456055,
36
+ "learning_rate": 1.9430014430014433e-05,
37
+ "loss": 0.5437,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.10822510822510822,
42
+ "grad_norm": 1.7913705110549927,
43
+ "learning_rate": 1.928571428571429e-05,
44
+ "loss": 0.4788,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.12987012987012986,
49
+ "grad_norm": 2.2625105381011963,
50
+ "learning_rate": 1.9141414141414144e-05,
51
+ "loss": 0.4678,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.15151515151515152,
56
+ "grad_norm": 1.6875262260437012,
57
+ "learning_rate": 1.8997113997114e-05,
58
+ "loss": 0.3672,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.17316017316017315,
63
+ "grad_norm": 2.3179216384887695,
64
+ "learning_rate": 1.8852813852813855e-05,
65
+ "loss": 0.3275,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.19480519480519481,
70
+ "grad_norm": 11.622775077819824,
71
+ "learning_rate": 1.870851370851371e-05,
72
+ "loss": 0.2794,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.21645021645021645,
77
+ "grad_norm": 1.9436513185501099,
78
+ "learning_rate": 1.8564213564213566e-05,
79
+ "loss": 0.2397,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.23809523809523808,
84
+ "grad_norm": 1.332103967666626,
85
+ "learning_rate": 1.841991341991342e-05,
86
+ "loss": 0.1845,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.2597402597402597,
91
+ "grad_norm": 1.2064969539642334,
92
+ "learning_rate": 1.8275613275613276e-05,
93
+ "loss": 0.1534,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.2813852813852814,
98
+ "grad_norm": 1.5475531816482544,
99
+ "learning_rate": 1.8131313131313132e-05,
100
+ "loss": 0.1261,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.30303030303030304,
105
+ "grad_norm": 1.0386016368865967,
106
+ "learning_rate": 1.7987012987012987e-05,
107
+ "loss": 0.1491,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.3246753246753247,
112
+ "grad_norm": 1.127977728843689,
113
+ "learning_rate": 1.7842712842712843e-05,
114
+ "loss": 0.0947,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.3463203463203463,
119
+ "grad_norm": 0.7528420686721802,
120
+ "learning_rate": 1.7698412698412698e-05,
121
+ "loss": 0.0915,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 0.36796536796536794,
126
+ "grad_norm": 2.6987464427948,
127
+ "learning_rate": 1.7554112554112554e-05,
128
+ "loss": 0.0725,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 0.38961038961038963,
133
+ "grad_norm": 0.45937371253967285,
134
+ "learning_rate": 1.7409812409812412e-05,
135
+ "loss": 0.0598,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.41125541125541126,
140
+ "grad_norm": 0.5548325777053833,
141
+ "learning_rate": 1.7265512265512268e-05,
142
+ "loss": 0.0723,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 0.4329004329004329,
147
+ "grad_norm": 0.7995928525924683,
148
+ "learning_rate": 1.7121212121212123e-05,
149
+ "loss": 0.0677,
150
+ "step": 400
151
+ },
152
+ {
153
+ "epoch": 0.45454545454545453,
154
+ "grad_norm": 0.34620311856269836,
155
+ "learning_rate": 1.697691197691198e-05,
156
+ "loss": 0.0545,
157
+ "step": 420
158
+ },
159
+ {
160
+ "epoch": 0.47619047619047616,
161
+ "grad_norm": 0.38282573223114014,
162
+ "learning_rate": 1.6832611832611834e-05,
163
+ "loss": 0.064,
164
+ "step": 440
165
+ },
166
+ {
167
+ "epoch": 0.49783549783549785,
168
+ "grad_norm": 0.34734392166137695,
169
+ "learning_rate": 1.668831168831169e-05,
170
+ "loss": 0.0417,
171
+ "step": 460
172
+ },
173
+ {
174
+ "epoch": 0.5194805194805194,
175
+ "grad_norm": 0.5567700266838074,
176
+ "learning_rate": 1.6544011544011545e-05,
177
+ "loss": 0.0567,
178
+ "step": 480
179
+ },
180
+ {
181
+ "epoch": 0.5411255411255411,
182
+ "grad_norm": 0.24816854298114777,
183
+ "learning_rate": 1.6399711399711404e-05,
184
+ "loss": 0.0353,
185
+ "step": 500
186
+ },
187
+ {
188
+ "epoch": 0.5627705627705628,
189
+ "grad_norm": 0.2364570051431656,
190
+ "learning_rate": 1.625541125541126e-05,
191
+ "loss": 0.0488,
192
+ "step": 520
193
+ },
194
+ {
195
+ "epoch": 0.5844155844155844,
196
+ "grad_norm": 0.7323583364486694,
197
+ "learning_rate": 1.6111111111111115e-05,
198
+ "loss": 0.054,
199
+ "step": 540
200
+ },
201
+ {
202
+ "epoch": 0.6060606060606061,
203
+ "grad_norm": 0.2931612730026245,
204
+ "learning_rate": 1.5966810966810967e-05,
205
+ "loss": 0.0571,
206
+ "step": 560
207
+ },
208
+ {
209
+ "epoch": 0.6277056277056277,
210
+ "grad_norm": 0.25314539670944214,
211
+ "learning_rate": 1.5822510822510822e-05,
212
+ "loss": 0.0448,
213
+ "step": 580
214
+ },
215
+ {
216
+ "epoch": 0.6493506493506493,
217
+ "grad_norm": 0.20941877365112305,
218
+ "learning_rate": 1.5678210678210677e-05,
219
+ "loss": 0.0333,
220
+ "step": 600
221
+ },
222
+ {
223
+ "epoch": 0.670995670995671,
224
+ "grad_norm": 0.23521284759044647,
225
+ "learning_rate": 1.5533910533910533e-05,
226
+ "loss": 0.0347,
227
+ "step": 620
228
+ },
229
+ {
230
+ "epoch": 0.6926406926406926,
231
+ "grad_norm": 0.3161298930644989,
232
+ "learning_rate": 1.538961038961039e-05,
233
+ "loss": 0.0475,
234
+ "step": 640
235
+ },
236
+ {
237
+ "epoch": 0.7142857142857143,
238
+ "grad_norm": 0.8162543177604675,
239
+ "learning_rate": 1.5245310245310247e-05,
240
+ "loss": 0.0271,
241
+ "step": 660
242
+ },
243
+ {
244
+ "epoch": 0.7359307359307359,
245
+ "grad_norm": 0.20186349749565125,
246
+ "learning_rate": 1.5101010101010103e-05,
247
+ "loss": 0.0833,
248
+ "step": 680
249
+ },
250
+ {
251
+ "epoch": 0.7575757575757576,
252
+ "grad_norm": 0.19510218501091003,
253
+ "learning_rate": 1.4956709956709958e-05,
254
+ "loss": 0.043,
255
+ "step": 700
256
+ },
257
+ {
258
+ "epoch": 0.7792207792207793,
259
+ "grad_norm": 0.20879587531089783,
260
+ "learning_rate": 1.4812409812409813e-05,
261
+ "loss": 0.021,
262
+ "step": 720
263
+ },
264
+ {
265
+ "epoch": 0.8008658008658008,
266
+ "grad_norm": 0.18057775497436523,
267
+ "learning_rate": 1.4668109668109669e-05,
268
+ "loss": 0.0412,
269
+ "step": 740
270
+ },
271
+ {
272
+ "epoch": 0.8225108225108225,
273
+ "grad_norm": 0.15316598117351532,
274
+ "learning_rate": 1.4523809523809524e-05,
275
+ "loss": 0.0244,
276
+ "step": 760
277
+ },
278
+ {
279
+ "epoch": 0.8441558441558441,
280
+ "grad_norm": 0.1659492552280426,
281
+ "learning_rate": 1.437950937950938e-05,
282
+ "loss": 0.0294,
283
+ "step": 780
284
+ },
285
+ {
286
+ "epoch": 0.8658008658008658,
287
+ "grad_norm": 0.1682518869638443,
288
+ "learning_rate": 1.4235209235209237e-05,
289
+ "loss": 0.0184,
290
+ "step": 800
291
+ },
292
+ {
293
+ "epoch": 0.8874458874458875,
294
+ "grad_norm": 0.222774937748909,
295
+ "learning_rate": 1.4090909090909092e-05,
296
+ "loss": 0.0203,
297
+ "step": 820
298
+ },
299
+ {
300
+ "epoch": 0.9090909090909091,
301
+ "grad_norm": 0.13427211344242096,
302
+ "learning_rate": 1.3946608946608948e-05,
303
+ "loss": 0.0411,
304
+ "step": 840
305
+ },
306
+ {
307
+ "epoch": 0.9307359307359307,
308
+ "grad_norm": 5.2049126625061035,
309
+ "learning_rate": 1.3802308802308803e-05,
310
+ "loss": 0.0383,
311
+ "step": 860
312
+ },
313
+ {
314
+ "epoch": 0.9523809523809523,
315
+ "grad_norm": 0.23792877793312073,
316
+ "learning_rate": 1.3658008658008659e-05,
317
+ "loss": 0.0182,
318
+ "step": 880
319
+ },
320
+ {
321
+ "epoch": 0.974025974025974,
322
+ "grad_norm": 0.12495584785938263,
323
+ "learning_rate": 1.3513708513708514e-05,
324
+ "loss": 0.029,
325
+ "step": 900
326
+ },
327
+ {
328
+ "epoch": 0.9956709956709957,
329
+ "grad_norm": 0.28919360041618347,
330
+ "learning_rate": 1.336940836940837e-05,
331
+ "loss": 0.0192,
332
+ "step": 920
333
+ },
334
+ {
335
+ "epoch": 1.0173160173160174,
336
+ "grad_norm": 0.11999514698982239,
337
+ "learning_rate": 1.3225108225108225e-05,
338
+ "loss": 0.0157,
339
+ "step": 940
340
+ },
341
+ {
342
+ "epoch": 1.0389610389610389,
343
+ "grad_norm": 0.14448480308055878,
344
+ "learning_rate": 1.3080808080808084e-05,
345
+ "loss": 0.0156,
346
+ "step": 960
347
+ },
348
+ {
349
+ "epoch": 1.0606060606060606,
350
+ "grad_norm": 0.37867000699043274,
351
+ "learning_rate": 1.2936507936507937e-05,
352
+ "loss": 0.0158,
353
+ "step": 980
354
+ },
355
+ {
356
+ "epoch": 1.0822510822510822,
357
+ "grad_norm": 0.1649075597524643,
358
+ "learning_rate": 1.2792207792207793e-05,
359
+ "loss": 0.0156,
360
+ "step": 1000
361
+ },
362
+ {
363
+ "epoch": 1.103896103896104,
364
+ "grad_norm": 0.11258062720298767,
365
+ "learning_rate": 1.2647907647907648e-05,
366
+ "loss": 0.029,
367
+ "step": 1020
368
+ },
369
+ {
370
+ "epoch": 1.1255411255411256,
371
+ "grad_norm": 0.16054819524288177,
372
+ "learning_rate": 1.2503607503607504e-05,
373
+ "loss": 0.0366,
374
+ "step": 1040
375
+ },
376
+ {
377
+ "epoch": 1.1471861471861473,
378
+ "grad_norm": 0.16296619176864624,
379
+ "learning_rate": 1.2359307359307359e-05,
380
+ "loss": 0.0135,
381
+ "step": 1060
382
+ },
383
+ {
384
+ "epoch": 1.1688311688311688,
385
+ "grad_norm": 5.796433448791504,
386
+ "learning_rate": 1.2215007215007215e-05,
387
+ "loss": 0.0422,
388
+ "step": 1080
389
+ },
390
+ {
391
+ "epoch": 1.1904761904761905,
392
+ "grad_norm": 0.19343234598636627,
393
+ "learning_rate": 1.207070707070707e-05,
394
+ "loss": 0.0144,
395
+ "step": 1100
396
+ },
397
+ {
398
+ "epoch": 1.2121212121212122,
399
+ "grad_norm": 0.12345093488693237,
400
+ "learning_rate": 1.1926406926406929e-05,
401
+ "loss": 0.0124,
402
+ "step": 1120
403
+ },
404
+ {
405
+ "epoch": 1.2337662337662338,
406
+ "grad_norm": 0.17719799280166626,
407
+ "learning_rate": 1.1782106782106784e-05,
408
+ "loss": 0.0442,
409
+ "step": 1140
410
+ },
411
+ {
412
+ "epoch": 1.2554112554112553,
413
+ "grad_norm": 0.26392945647239685,
414
+ "learning_rate": 1.163780663780664e-05,
415
+ "loss": 0.0123,
416
+ "step": 1160
417
+ },
418
+ {
419
+ "epoch": 1.277056277056277,
420
+ "grad_norm": 0.06477934867143631,
421
+ "learning_rate": 1.1493506493506495e-05,
422
+ "loss": 0.0151,
423
+ "step": 1180
424
+ },
425
+ {
426
+ "epoch": 1.2987012987012987,
427
+ "grad_norm": 0.10530120134353638,
428
+ "learning_rate": 1.134920634920635e-05,
429
+ "loss": 0.0129,
430
+ "step": 1200
431
+ },
432
+ {
433
+ "epoch": 1.3203463203463204,
434
+ "grad_norm": 0.10538487881422043,
435
+ "learning_rate": 1.1204906204906206e-05,
436
+ "loss": 0.0156,
437
+ "step": 1220
438
+ },
439
+ {
440
+ "epoch": 1.341991341991342,
441
+ "grad_norm": 0.10836771875619888,
442
+ "learning_rate": 1.1060606060606061e-05,
443
+ "loss": 0.0178,
444
+ "step": 1240
445
+ },
446
+ {
447
+ "epoch": 1.3636363636363638,
448
+ "grad_norm": 3.7379777431488037,
449
+ "learning_rate": 1.0916305916305919e-05,
450
+ "loss": 0.0145,
451
+ "step": 1260
452
+ },
453
+ {
454
+ "epoch": 1.3852813852813852,
455
+ "grad_norm": 0.19971278309822083,
456
+ "learning_rate": 1.0772005772005774e-05,
457
+ "loss": 0.0458,
458
+ "step": 1280
459
+ },
460
+ {
461
+ "epoch": 1.406926406926407,
462
+ "grad_norm": 0.17772097885608673,
463
+ "learning_rate": 1.062770562770563e-05,
464
+ "loss": 0.0123,
465
+ "step": 1300
466
+ },
467
+ {
468
+ "epoch": 1.4285714285714286,
469
+ "grad_norm": 0.12699300050735474,
470
+ "learning_rate": 1.0483405483405485e-05,
471
+ "loss": 0.0306,
472
+ "step": 1320
473
+ },
474
+ {
475
+ "epoch": 1.4502164502164503,
476
+ "grad_norm": 0.08466625213623047,
477
+ "learning_rate": 1.033910533910534e-05,
478
+ "loss": 0.0108,
479
+ "step": 1340
480
+ },
481
+ {
482
+ "epoch": 1.4718614718614718,
483
+ "grad_norm": 0.09285025298595428,
484
+ "learning_rate": 1.0194805194805196e-05,
485
+ "loss": 0.0131,
486
+ "step": 1360
487
+ },
488
+ {
489
+ "epoch": 1.4935064935064934,
490
+ "grad_norm": 0.1555718034505844,
491
+ "learning_rate": 1.0050505050505051e-05,
492
+ "loss": 0.0182,
493
+ "step": 1380
494
+ },
495
+ {
496
+ "epoch": 1.5151515151515151,
497
+ "grad_norm": 0.1831505000591278,
498
+ "learning_rate": 9.906204906204907e-06,
499
+ "loss": 0.0102,
500
+ "step": 1400
501
+ },
502
+ {
503
+ "epoch": 1.5367965367965368,
504
+ "grad_norm": 0.09224329888820648,
505
+ "learning_rate": 9.761904761904762e-06,
506
+ "loss": 0.0116,
507
+ "step": 1420
508
+ },
509
+ {
510
+ "epoch": 1.5584415584415585,
511
+ "grad_norm": 0.08490342646837234,
512
+ "learning_rate": 9.617604617604619e-06,
513
+ "loss": 0.0102,
514
+ "step": 1440
515
+ },
516
+ {
517
+ "epoch": 1.5800865800865802,
518
+ "grad_norm": 0.16526533663272858,
519
+ "learning_rate": 9.473304473304474e-06,
520
+ "loss": 0.0217,
521
+ "step": 1460
522
+ },
523
+ {
524
+ "epoch": 1.601731601731602,
525
+ "grad_norm": 0.08393661677837372,
526
+ "learning_rate": 9.32900432900433e-06,
527
+ "loss": 0.0103,
528
+ "step": 1480
529
+ },
530
+ {
531
+ "epoch": 1.6233766233766234,
532
+ "grad_norm": 0.13095460832118988,
533
+ "learning_rate": 9.184704184704185e-06,
534
+ "loss": 0.022,
535
+ "step": 1500
536
+ },
537
+ {
538
+ "epoch": 1.645021645021645,
539
+ "grad_norm": 0.13940352201461792,
540
+ "learning_rate": 9.040404040404042e-06,
541
+ "loss": 0.0229,
542
+ "step": 1520
543
+ },
544
+ {
545
+ "epoch": 1.6666666666666665,
546
+ "grad_norm": 0.11868056654930115,
547
+ "learning_rate": 8.896103896103896e-06,
548
+ "loss": 0.0104,
549
+ "step": 1540
550
+ },
551
+ {
552
+ "epoch": 1.6883116883116882,
553
+ "grad_norm": 0.060605239123106,
554
+ "learning_rate": 8.751803751803752e-06,
555
+ "loss": 0.0162,
556
+ "step": 1560
557
+ },
558
+ {
559
+ "epoch": 1.70995670995671,
560
+ "grad_norm": 0.10808888077735901,
561
+ "learning_rate": 8.607503607503607e-06,
562
+ "loss": 0.0087,
563
+ "step": 1580
564
+ },
565
+ {
566
+ "epoch": 1.7316017316017316,
567
+ "grad_norm": 0.08839452266693115,
568
+ "learning_rate": 8.463203463203464e-06,
569
+ "loss": 0.0091,
570
+ "step": 1600
571
+ },
572
+ {
573
+ "epoch": 1.7532467532467533,
574
+ "grad_norm": 0.10623842477798462,
575
+ "learning_rate": 8.31890331890332e-06,
576
+ "loss": 0.0122,
577
+ "step": 1620
578
+ },
579
+ {
580
+ "epoch": 1.774891774891775,
581
+ "grad_norm": 0.056098755449056625,
582
+ "learning_rate": 8.174603174603175e-06,
583
+ "loss": 0.0092,
584
+ "step": 1640
585
+ },
586
+ {
587
+ "epoch": 1.7965367965367967,
588
+ "grad_norm": 0.11627987772226334,
589
+ "learning_rate": 8.03030303030303e-06,
590
+ "loss": 0.0082,
591
+ "step": 1660
592
+ },
593
+ {
594
+ "epoch": 1.8181818181818183,
595
+ "grad_norm": 0.08929106593132019,
596
+ "learning_rate": 7.886002886002888e-06,
597
+ "loss": 0.018,
598
+ "step": 1680
599
+ },
600
+ {
601
+ "epoch": 1.8398268398268398,
602
+ "grad_norm": 0.0906723365187645,
603
+ "learning_rate": 7.741702741702743e-06,
604
+ "loss": 0.0153,
605
+ "step": 1700
606
+ },
607
+ {
608
+ "epoch": 1.8614718614718615,
609
+ "grad_norm": 0.06793191283941269,
610
+ "learning_rate": 7.597402597402598e-06,
611
+ "loss": 0.0184,
612
+ "step": 1720
613
+ },
614
+ {
615
+ "epoch": 1.883116883116883,
616
+ "grad_norm": 0.12505404651165009,
617
+ "learning_rate": 7.453102453102453e-06,
618
+ "loss": 0.0092,
619
+ "step": 1740
620
+ },
621
+ {
622
+ "epoch": 1.9047619047619047,
623
+ "grad_norm": 0.09465266019105911,
624
+ "learning_rate": 7.308802308802309e-06,
625
+ "loss": 0.0133,
626
+ "step": 1760
627
+ },
628
+ {
629
+ "epoch": 1.9264069264069263,
630
+ "grad_norm": 0.09390600025653839,
631
+ "learning_rate": 7.164502164502165e-06,
632
+ "loss": 0.0179,
633
+ "step": 1780
634
+ },
635
+ {
636
+ "epoch": 1.948051948051948,
637
+ "grad_norm": 0.07343223690986633,
638
+ "learning_rate": 7.02020202020202e-06,
639
+ "loss": 0.0104,
640
+ "step": 1800
641
+ },
642
+ {
643
+ "epoch": 1.9696969696969697,
644
+ "grad_norm": 0.13794736564159393,
645
+ "learning_rate": 6.875901875901877e-06,
646
+ "loss": 0.0188,
647
+ "step": 1820
648
+ },
649
+ {
650
+ "epoch": 1.9913419913419914,
651
+ "grad_norm": 0.04812062159180641,
652
+ "learning_rate": 6.731601731601733e-06,
653
+ "loss": 0.0193,
654
+ "step": 1840
655
+ },
656
+ {
657
+ "epoch": 2.012987012987013,
658
+ "grad_norm": 0.08907242119312286,
659
+ "learning_rate": 6.587301587301588e-06,
660
+ "loss": 0.0342,
661
+ "step": 1860
662
+ },
663
+ {
664
+ "epoch": 2.034632034632035,
665
+ "grad_norm": 0.06940910965204239,
666
+ "learning_rate": 6.443001443001443e-06,
667
+ "loss": 0.0085,
668
+ "step": 1880
669
+ },
670
+ {
671
+ "epoch": 2.0562770562770565,
672
+ "grad_norm": 0.07371290028095245,
673
+ "learning_rate": 6.2987012987013e-06,
674
+ "loss": 0.0101,
675
+ "step": 1900
676
+ },
677
+ {
678
+ "epoch": 2.0779220779220777,
679
+ "grad_norm": 0.10616641491651535,
680
+ "learning_rate": 6.154401154401155e-06,
681
+ "loss": 0.0256,
682
+ "step": 1920
683
+ },
684
+ {
685
+ "epoch": 2.0995670995670994,
686
+ "grad_norm": 0.07746961712837219,
687
+ "learning_rate": 6.010101010101011e-06,
688
+ "loss": 0.0093,
689
+ "step": 1940
690
+ },
691
+ {
692
+ "epoch": 2.121212121212121,
693
+ "grad_norm": 0.19828535616397858,
694
+ "learning_rate": 5.865800865800866e-06,
695
+ "loss": 0.008,
696
+ "step": 1960
697
+ },
698
+ {
699
+ "epoch": 2.142857142857143,
700
+ "grad_norm": 0.11058467626571655,
701
+ "learning_rate": 5.721500721500722e-06,
702
+ "loss": 0.0172,
703
+ "step": 1980
704
+ },
705
+ {
706
+ "epoch": 2.1645021645021645,
707
+ "grad_norm": 0.04194315895438194,
708
+ "learning_rate": 5.577200577200578e-06,
709
+ "loss": 0.0095,
710
+ "step": 2000
711
+ },
712
+ {
713
+ "epoch": 2.186147186147186,
714
+ "grad_norm": 0.10634741187095642,
715
+ "learning_rate": 5.432900432900433e-06,
716
+ "loss": 0.0133,
717
+ "step": 2020
718
+ },
719
+ {
720
+ "epoch": 2.207792207792208,
721
+ "grad_norm": 0.0997764989733696,
722
+ "learning_rate": 5.288600288600289e-06,
723
+ "loss": 0.0135,
724
+ "step": 2040
725
+ },
726
+ {
727
+ "epoch": 2.2294372294372296,
728
+ "grad_norm": 0.1089092567563057,
729
+ "learning_rate": 5.144300144300145e-06,
730
+ "loss": 0.0267,
731
+ "step": 2060
732
+ },
733
+ {
734
+ "epoch": 2.2510822510822512,
735
+ "grad_norm": 0.09123284369707108,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.0076,
738
+ "step": 2080
739
+ },
740
+ {
741
+ "epoch": 2.2727272727272725,
742
+ "grad_norm": 0.06854091584682465,
743
+ "learning_rate": 4.855699855699857e-06,
744
+ "loss": 0.0147,
745
+ "step": 2100
746
+ },
747
+ {
748
+ "epoch": 2.2943722943722946,
749
+ "grad_norm": 0.11229178309440613,
750
+ "learning_rate": 4.711399711399712e-06,
751
+ "loss": 0.0072,
752
+ "step": 2120
753
+ },
754
+ {
755
+ "epoch": 2.316017316017316,
756
+ "grad_norm": 0.0881107822060585,
757
+ "learning_rate": 4.5670995670995675e-06,
758
+ "loss": 0.0141,
759
+ "step": 2140
760
+ },
761
+ {
762
+ "epoch": 2.3376623376623376,
763
+ "grad_norm": 0.08736357092857361,
764
+ "learning_rate": 4.422799422799423e-06,
765
+ "loss": 0.0162,
766
+ "step": 2160
767
+ },
768
+ {
769
+ "epoch": 2.3593073593073592,
770
+ "grad_norm": 0.06391258537769318,
771
+ "learning_rate": 4.278499278499279e-06,
772
+ "loss": 0.0076,
773
+ "step": 2180
774
+ },
775
+ {
776
+ "epoch": 2.380952380952381,
777
+ "grad_norm": 0.08132211863994598,
778
+ "learning_rate": 4.134199134199135e-06,
779
+ "loss": 0.007,
780
+ "step": 2200
781
+ },
782
+ {
783
+ "epoch": 2.4025974025974026,
784
+ "grad_norm": 0.06198592483997345,
785
+ "learning_rate": 3.98989898989899e-06,
786
+ "loss": 0.0061,
787
+ "step": 2220
788
+ },
789
+ {
790
+ "epoch": 2.4242424242424243,
791
+ "grad_norm": 0.07765072584152222,
792
+ "learning_rate": 3.8455988455988455e-06,
793
+ "loss": 0.0075,
794
+ "step": 2240
795
+ },
796
+ {
797
+ "epoch": 2.445887445887446,
798
+ "grad_norm": 0.092200867831707,
799
+ "learning_rate": 3.701298701298702e-06,
800
+ "loss": 0.0167,
801
+ "step": 2260
802
+ },
803
+ {
804
+ "epoch": 2.4675324675324677,
805
+ "grad_norm": 0.07408732175827026,
806
+ "learning_rate": 3.5569985569985572e-06,
807
+ "loss": 0.0065,
808
+ "step": 2280
809
+ },
810
+ {
811
+ "epoch": 2.4891774891774894,
812
+ "grad_norm": 0.05288136005401611,
813
+ "learning_rate": 3.412698412698413e-06,
814
+ "loss": 0.0148,
815
+ "step": 2300
816
+ },
817
+ {
818
+ "epoch": 2.5108225108225106,
819
+ "grad_norm": 0.08382824063301086,
820
+ "learning_rate": 3.2683982683982685e-06,
821
+ "loss": 0.0174,
822
+ "step": 2320
823
+ },
824
+ {
825
+ "epoch": 2.5324675324675323,
826
+ "grad_norm": 0.06475148350000381,
827
+ "learning_rate": 3.1240981240981244e-06,
828
+ "loss": 0.008,
829
+ "step": 2340
830
+ },
831
+ {
832
+ "epoch": 2.554112554112554,
833
+ "grad_norm": 0.08863703906536102,
834
+ "learning_rate": 2.97979797979798e-06,
835
+ "loss": 0.0066,
836
+ "step": 2360
837
+ },
838
+ {
839
+ "epoch": 2.5757575757575757,
840
+ "grad_norm": 0.08658093959093094,
841
+ "learning_rate": 2.8354978354978357e-06,
842
+ "loss": 0.0134,
843
+ "step": 2380
844
+ },
845
+ {
846
+ "epoch": 2.5974025974025974,
847
+ "grad_norm": 0.0753917247056961,
848
+ "learning_rate": 2.691197691197691e-06,
849
+ "loss": 0.0065,
850
+ "step": 2400
851
+ },
852
+ {
853
+ "epoch": 2.619047619047619,
854
+ "grad_norm": 0.15559795498847961,
855
+ "learning_rate": 2.546897546897547e-06,
856
+ "loss": 0.0065,
857
+ "step": 2420
858
+ },
859
+ {
860
+ "epoch": 2.6406926406926408,
861
+ "grad_norm": 0.051586903631687164,
862
+ "learning_rate": 2.402597402597403e-06,
863
+ "loss": 0.0088,
864
+ "step": 2440
865
+ },
866
+ {
867
+ "epoch": 2.6623376623376624,
868
+ "grad_norm": 0.04571373015642166,
869
+ "learning_rate": 2.2582972582972586e-06,
870
+ "loss": 0.0265,
871
+ "step": 2460
872
+ },
873
+ {
874
+ "epoch": 2.683982683982684,
875
+ "grad_norm": 0.08445149660110474,
876
+ "learning_rate": 2.113997113997114e-06,
877
+ "loss": 0.0079,
878
+ "step": 2480
879
+ },
880
+ {
881
+ "epoch": 2.7056277056277054,
882
+ "grad_norm": 0.0789010226726532,
883
+ "learning_rate": 1.96969696969697e-06,
884
+ "loss": 0.0088,
885
+ "step": 2500
886
+ },
887
+ {
888
+ "epoch": 2.7272727272727275,
889
+ "grad_norm": 0.07792507857084274,
890
+ "learning_rate": 1.8253968253968254e-06,
891
+ "loss": 0.0263,
892
+ "step": 2520
893
+ },
894
+ {
895
+ "epoch": 2.7489177489177488,
896
+ "grad_norm": 0.08237048238515854,
897
+ "learning_rate": 1.6810966810966812e-06,
898
+ "loss": 0.0095,
899
+ "step": 2540
900
+ },
901
+ {
902
+ "epoch": 2.7705627705627704,
903
+ "grad_norm": 0.0714096799492836,
904
+ "learning_rate": 1.5367965367965368e-06,
905
+ "loss": 0.0145,
906
+ "step": 2560
907
+ },
908
+ {
909
+ "epoch": 2.792207792207792,
910
+ "grad_norm": 0.0596635565161705,
911
+ "learning_rate": 1.3924963924963927e-06,
912
+ "loss": 0.0177,
913
+ "step": 2580
914
+ },
915
+ {
916
+ "epoch": 2.813852813852814,
917
+ "grad_norm": 0.0577537827193737,
918
+ "learning_rate": 1.2481962481962483e-06,
919
+ "loss": 0.0097,
920
+ "step": 2600
921
+ },
922
+ {
923
+ "epoch": 2.8354978354978355,
924
+ "grad_norm": 0.06280733644962311,
925
+ "learning_rate": 1.103896103896104e-06,
926
+ "loss": 0.0211,
927
+ "step": 2620
928
+ },
929
+ {
930
+ "epoch": 2.857142857142857,
931
+ "grad_norm": 0.05112572759389877,
932
+ "learning_rate": 9.595959595959596e-07,
933
+ "loss": 0.0089,
934
+ "step": 2640
935
+ },
936
+ {
937
+ "epoch": 2.878787878787879,
938
+ "grad_norm": 0.0603049136698246,
939
+ "learning_rate": 8.152958152958154e-07,
940
+ "loss": 0.0067,
941
+ "step": 2660
942
+ },
943
+ {
944
+ "epoch": 2.9004329004329006,
945
+ "grad_norm": 0.8938813805580139,
946
+ "learning_rate": 6.709956709956711e-07,
947
+ "loss": 0.0099,
948
+ "step": 2680
949
+ },
950
+ {
951
+ "epoch": 2.9220779220779223,
952
+ "grad_norm": 0.11178398132324219,
953
+ "learning_rate": 5.266955266955268e-07,
954
+ "loss": 0.0226,
955
+ "step": 2700
956
+ },
957
+ {
958
+ "epoch": 2.9437229437229435,
959
+ "grad_norm": 0.06617637723684311,
960
+ "learning_rate": 3.8239538239538245e-07,
961
+ "loss": 0.0071,
962
+ "step": 2720
963
+ },
964
+ {
965
+ "epoch": 2.965367965367965,
966
+ "grad_norm": 0.11734533309936523,
967
+ "learning_rate": 2.3809523809523811e-07,
968
+ "loss": 0.0088,
969
+ "step": 2740
970
+ },
971
+ {
972
+ "epoch": 2.987012987012987,
973
+ "grad_norm": 0.051227644085884094,
974
+ "learning_rate": 9.379509379509381e-08,
975
+ "loss": 0.0062,
976
+ "step": 2760
977
+ }
978
+ ],
979
+ "logging_steps": 20,
980
+ "max_steps": 2772,
981
+ "num_input_tokens_seen": 0,
982
+ "num_train_epochs": 3,
983
+ "save_steps": 500,
984
+ "stateful_callbacks": {
985
+ "TrainerControl": {
986
+ "args": {
987
+ "should_epoch_stop": false,
988
+ "should_evaluate": false,
989
+ "should_log": false,
990
+ "should_save": true,
991
+ "should_training_stop": true
992
+ },
993
+ "attributes": {}
994
+ }
995
+ },
996
+ "total_flos": 0.0,
997
+ "train_batch_size": 16,
998
+ "trial_name": null,
999
+ "trial_params": null
1000
+ }
checkpoint-2772/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf723c2d0b1b8fe4f313e3091797d2a7106afbdafeb0077464451ff5c28790c
3
+ size 5777
label_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "intents": [
3
+ "healthcare_help_seeking",
4
+ "healthcare_info",
5
+ "non_healthcare"
6
+ ],
7
+ "symptoms": [
8
+ "abdominal pain",
9
+ "chest pain",
10
+ "fever",
11
+ "headache",
12
+ "rash",
13
+ "shortness of breath"
14
+ ],
15
+ "specialties": [
16
+ "cardiology",
17
+ "gastro",
18
+ "infectious_disease",
19
+ "neurology",
20
+ "pharmacy",
21
+ "physiotherapy"
22
+ ]
23
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3abc568578d1d9f7486ebd7f388fcec6850a1fe47c13572ecad77ab181728d
3
+ size 735397076
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf723c2d0b1b8fe4f313e3091797d2a7106afbdafeb0077464451ff5c28790c
3
+ size 5777