marbonora commited on
Commit
199413d
·
verified ·
1 Parent(s): 186af26

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "transformers_version": "4.56.0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 256000
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d91193dc1895a9a02735687607444cdb8fae6d47b552b4ec01d6dd46ff0bfe5
3
+ size 1130630880
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d828864d8565c2a3446b27caeb854003dc84990bf724f15aa7153ce3218b8c57
3
+ size 2261384587
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d1697ca460ec93a99cfa03b73968f583a457394479516f496de0c0a65e9b9b
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9640cd2ff44a68bffb9f115e57d330e566ff20c251826e8aaafddead9568d40
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de87d8e9eaead51ee576de13f7b271debd8d7996875faee0b239a26bd172629f
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34843a8fb66baf3ad74af453bd472639c6a5dac922d6e23f9c30ae8d6a2cb1af
3
+ size 37008227
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5072e3209a04aa01dbf4db72b8fec52cf8cd06a042c9ba819678e084f7b665d5
3
+ size 4813283
tokenizer_config.json ADDED
@@ -0,0 +1,1100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<pad>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<|im_end|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<|reserved_token_1|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<|reserved_token_2|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "8": {
71
+ "content": "<|reserved_token_3|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "9": {
79
+ "content": "<|reserved_token_4|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "10": {
87
+ "content": "<|reserved_token_5|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "11": {
95
+ "content": "<|reserved_token_6|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "12": {
103
+ "content": "<|reserved_token_7|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "13": {
111
+ "content": "<|reserved_token_8|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "14": {
119
+ "content": "<|reserved_token_9|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "15": {
127
+ "content": "<|reserved_token_10|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "16": {
135
+ "content": "<|reserved_token_11|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "17": {
143
+ "content": "<|reserved_token_12|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "18": {
151
+ "content": "<|reserved_token_13|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "19": {
159
+ "content": "<|reserved_token_14|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "20": {
167
+ "content": "<|reserved_token_15|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "21": {
175
+ "content": "<|reserved_token_16|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "22": {
183
+ "content": "<|reserved_token_17|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "23": {
191
+ "content": "<|reserved_token_18|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "24": {
199
+ "content": "<|reserved_token_19|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "25": {
207
+ "content": "<|reserved_token_20|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "26": {
215
+ "content": "<|reserved_token_21|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "27": {
223
+ "content": "<|reserved_token_22|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "28": {
231
+ "content": "<|reserved_token_23|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "29": {
239
+ "content": "<|reserved_token_24|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "30": {
247
+ "content": "<|reserved_token_25|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "31": {
255
+ "content": "<|reserved_token_26|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "32": {
263
+ "content": "<|reserved_token_27|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "33": {
271
+ "content": "<|reserved_token_28|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "34": {
279
+ "content": "<|reserved_token_29|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "35": {
287
+ "content": "<|reserved_token_30|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "36": {
295
+ "content": "<|reserved_token_31|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "37": {
303
+ "content": "<|reserved_token_32|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "38": {
311
+ "content": "<|reserved_token_33|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "39": {
319
+ "content": "<|reserved_token_34|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "40": {
327
+ "content": "<|reserved_token_35|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "41": {
335
+ "content": "<|reserved_token_36|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "42": {
343
+ "content": "<|reserved_token_37|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "43": {
351
+ "content": "<|reserved_token_38|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "44": {
359
+ "content": "<|reserved_token_39|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "45": {
367
+ "content": "<|reserved_token_40|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "46": {
375
+ "content": "<|reserved_token_41|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "47": {
383
+ "content": "<|reserved_token_42|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "48": {
391
+ "content": "<|reserved_token_43|>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "49": {
399
+ "content": "<|reserved_token_44|>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "50": {
407
+ "content": "<|reserved_token_45|>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "51": {
415
+ "content": "<|reserved_token_46|>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "52": {
423
+ "content": "<|reserved_token_47|>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "53": {
431
+ "content": "<|reserved_token_48|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "54": {
439
+ "content": "<|reserved_token_49|>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "55": {
447
+ "content": "<|reserved_token_50|>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "56": {
455
+ "content": "<|reserved_token_51|>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "57": {
463
+ "content": "<|reserved_token_52|>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "58": {
471
+ "content": "<|reserved_token_53|>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "59": {
479
+ "content": "<|reserved_token_54|>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "60": {
487
+ "content": "<|reserved_token_55|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "61": {
495
+ "content": "<|reserved_token_56|>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "62": {
503
+ "content": "<|reserved_token_57|>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "63": {
511
+ "content": "<|reserved_token_58|>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "64": {
519
+ "content": "<|reserved_token_59|>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "65": {
527
+ "content": "<|reserved_token_60|>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "66": {
535
+ "content": "<|reserved_token_61|>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "67": {
543
+ "content": "<|reserved_token_62|>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "68": {
551
+ "content": "<|reserved_token_63|>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "69": {
559
+ "content": "<|reserved_token_64|>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "70": {
567
+ "content": "<|reserved_token_65|>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "71": {
575
+ "content": "<|reserved_token_66|>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "72": {
583
+ "content": "<|reserved_token_67|>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "73": {
591
+ "content": "<|reserved_token_68|>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "74": {
599
+ "content": "<|reserved_token_69|>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "75": {
607
+ "content": "<|reserved_token_70|>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "76": {
615
+ "content": "<|reserved_token_71|>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "77": {
623
+ "content": "<|reserved_token_72|>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "78": {
631
+ "content": "<|reserved_token_73|>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "79": {
639
+ "content": "<|reserved_token_74|>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "80": {
647
+ "content": "<|reserved_token_75|>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "81": {
655
+ "content": "<|reserved_token_76|>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "82": {
663
+ "content": "<|reserved_token_77|>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "83": {
671
+ "content": "<|reserved_token_78|>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "84": {
679
+ "content": "<|reserved_token_79|>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "85": {
687
+ "content": "<|reserved_token_80|>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "86": {
695
+ "content": "<|reserved_token_81|>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "87": {
703
+ "content": "<|reserved_token_82|>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "88": {
711
+ "content": "<|reserved_token_83|>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "89": {
719
+ "content": "<|reserved_token_84|>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "90": {
727
+ "content": "<|reserved_token_85|>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "91": {
735
+ "content": "<|reserved_token_86|>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "92": {
743
+ "content": "<|reserved_token_87|>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "93": {
751
+ "content": "<|reserved_token_88|>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "94": {
759
+ "content": "<|reserved_token_89|>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "95": {
767
+ "content": "<|reserved_token_90|>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "96": {
775
+ "content": "<|reserved_token_91|>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "97": {
783
+ "content": "<|reserved_token_92|>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "98": {
791
+ "content": "<|reserved_token_93|>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "99": {
799
+ "content": "<|reserved_token_94|>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "100": {
807
+ "content": "<|reserved_token_95|>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "101": {
815
+ "content": "<|reserved_token_96|>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "102": {
823
+ "content": "<|reserved_token_97|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "103": {
831
+ "content": "<mask>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ },
838
+ "104": {
839
+ "content": "\\r",
840
+ "lstrip": false,
841
+ "normalized": false,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": false
845
+ },
846
+ "105": {
847
+ "content": "▁▁",
848
+ "lstrip": false,
849
+ "normalized": false,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": false
853
+ },
854
+ "106": {
855
+ "content": "▁▁▁",
856
+ "lstrip": false,
857
+ "normalized": false,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": false
861
+ },
862
+ "107": {
863
+ "content": "▁▁▁▁",
864
+ "lstrip": false,
865
+ "normalized": false,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": false
869
+ },
870
+ "108": {
871
+ "content": "▁▁▁▁▁",
872
+ "lstrip": false,
873
+ "normalized": false,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": false
877
+ },
878
+ "109": {
879
+ "content": "▁▁▁▁▁▁",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": false
885
+ },
886
+ "110": {
887
+ "content": "▁▁▁▁▁▁▁",
888
+ "lstrip": false,
889
+ "normalized": false,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": false
893
+ },
894
+ "111": {
895
+ "content": "▁▁▁▁▁▁▁▁",
896
+ "lstrip": false,
897
+ "normalized": false,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": false
901
+ },
902
+ "112": {
903
+ "content": "▁▁▁▁▁▁▁▁▁",
904
+ "lstrip": false,
905
+ "normalized": false,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": false
909
+ },
910
+ "113": {
911
+ "content": "▁▁▁▁▁▁▁▁▁▁",
912
+ "lstrip": false,
913
+ "normalized": false,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": false
917
+ },
918
+ "114": {
919
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
920
+ "lstrip": false,
921
+ "normalized": false,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": false
925
+ },
926
+ "115": {
927
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
928
+ "lstrip": false,
929
+ "normalized": false,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": false
933
+ },
934
+ "116": {
935
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false,
940
+ "special": false
941
+ },
942
+ "117": {
943
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
944
+ "lstrip": false,
945
+ "normalized": false,
946
+ "rstrip": false,
947
+ "single_word": false,
948
+ "special": false
949
+ },
950
+ "118": {
951
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
952
+ "lstrip": false,
953
+ "normalized": false,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": false
957
+ },
958
+ "119": {
959
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
960
+ "lstrip": false,
961
+ "normalized": false,
962
+ "rstrip": false,
963
+ "single_word": false,
964
+ "special": false
965
+ },
966
+ "120": {
967
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
968
+ "lstrip": false,
969
+ "normalized": false,
970
+ "rstrip": false,
971
+ "single_word": false,
972
+ "special": false
973
+ },
974
+ "121": {
975
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
976
+ "lstrip": false,
977
+ "normalized": false,
978
+ "rstrip": false,
979
+ "single_word": false,
980
+ "special": false
981
+ },
982
+ "122": {
983
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
984
+ "lstrip": false,
985
+ "normalized": false,
986
+ "rstrip": false,
987
+ "single_word": false,
988
+ "special": false
989
+ },
990
+ "123": {
991
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false,
996
+ "special": false
997
+ },
998
+ "124": {
999
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1000
+ "lstrip": false,
1001
+ "normalized": false,
1002
+ "rstrip": false,
1003
+ "single_word": false,
1004
+ "special": false
1005
+ },
1006
+ "125": {
1007
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1008
+ "lstrip": false,
1009
+ "normalized": false,
1010
+ "rstrip": false,
1011
+ "single_word": false,
1012
+ "special": false
1013
+ },
1014
+ "126": {
1015
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1016
+ "lstrip": false,
1017
+ "normalized": false,
1018
+ "rstrip": false,
1019
+ "single_word": false,
1020
+ "special": false
1021
+ },
1022
+ "127": {
1023
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1024
+ "lstrip": false,
1025
+ "normalized": false,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": false
1029
+ },
1030
+ "128": {
1031
+ "content": "\t\t",
1032
+ "lstrip": false,
1033
+ "normalized": false,
1034
+ "rstrip": false,
1035
+ "single_word": false,
1036
+ "special": false
1037
+ },
1038
+ "129": {
1039
+ "content": "\t\t\t",
1040
+ "lstrip": false,
1041
+ "normalized": false,
1042
+ "rstrip": false,
1043
+ "single_word": false,
1044
+ "special": false
1045
+ },
1046
+ "130": {
1047
+ "content": "\t\t\t\t",
1048
+ "lstrip": false,
1049
+ "normalized": false,
1050
+ "rstrip": false,
1051
+ "single_word": false,
1052
+ "special": false
1053
+ },
1054
+ "131": {
1055
+ "content": "\t\t\t\t\t",
1056
+ "lstrip": false,
1057
+ "normalized": false,
1058
+ "rstrip": false,
1059
+ "single_word": false,
1060
+ "special": false
1061
+ },
1062
+ "132": {
1063
+ "content": "\t\t\t\t\t\t",
1064
+ "lstrip": false,
1065
+ "normalized": false,
1066
+ "rstrip": false,
1067
+ "single_word": false,
1068
+ "special": false
1069
+ },
1070
+ "133": {
1071
+ "content": "\n\n",
1072
+ "lstrip": false,
1073
+ "normalized": false,
1074
+ "rstrip": false,
1075
+ "single_word": false,
1076
+ "special": false
1077
+ },
1078
+ "134": {
1079
+ "content": "\n\n\n",
1080
+ "lstrip": false,
1081
+ "normalized": false,
1082
+ "rstrip": false,
1083
+ "single_word": false,
1084
+ "special": false
1085
+ }
1086
+ },
1087
+ "bos_token": "<s>",
1088
+ "clean_up_tokenization_spaces": false,
1089
+ "eos_token": "</s>",
1090
+ "extra_special_tokens": {},
1091
+ "legacy": true,
1092
+ "mask_token": "<mask>",
1093
+ "model_max_length": 512,
1094
+ "pad_token": "<pad>",
1095
+ "sp_model_kwargs": {},
1096
+ "spaces_between_special_tokens": false,
1097
+ "tokenizer_class": "LlamaTokenizer",
1098
+ "unk_token": "<unk>",
1099
+ "use_default_system_prompt": false
1100
+ }
trainer_state.json ADDED
@@ -0,0 +1,1534 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2120,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.009433962264150943,
14
+ "grad_norm": 2.1125893592834473,
15
+ "learning_rate": 1.9915094339622643e-05,
16
+ "loss": 0.6661,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.018867924528301886,
21
+ "grad_norm": 4.568980693817139,
22
+ "learning_rate": 1.9820754716981134e-05,
23
+ "loss": 0.6476,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.02830188679245283,
28
+ "grad_norm": 4.55064582824707,
29
+ "learning_rate": 1.9726415094339625e-05,
30
+ "loss": 0.609,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.03773584905660377,
35
+ "grad_norm": 2.458791732788086,
36
+ "learning_rate": 1.9632075471698116e-05,
37
+ "loss": 0.5465,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.04716981132075472,
42
+ "grad_norm": 5.235497951507568,
43
+ "learning_rate": 1.9537735849056604e-05,
44
+ "loss": 0.4277,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.05660377358490566,
49
+ "grad_norm": 2.81006121635437,
50
+ "learning_rate": 1.9443396226415095e-05,
51
+ "loss": 0.3367,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0660377358490566,
56
+ "grad_norm": 5.580306529998779,
57
+ "learning_rate": 1.9349056603773586e-05,
58
+ "loss": 0.232,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.07547169811320754,
63
+ "grad_norm": 6.972874641418457,
64
+ "learning_rate": 1.9254716981132077e-05,
65
+ "loss": 0.1852,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.08490566037735849,
70
+ "grad_norm": 2.1650376319885254,
71
+ "learning_rate": 1.9160377358490568e-05,
72
+ "loss": 0.1581,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.09433962264150944,
77
+ "grad_norm": 0.42251577973365784,
78
+ "learning_rate": 1.906603773584906e-05,
79
+ "loss": 0.1821,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.10377358490566038,
84
+ "grad_norm": 0.361060231924057,
85
+ "learning_rate": 1.8971698113207547e-05,
86
+ "loss": 0.3396,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.11320754716981132,
91
+ "grad_norm": 1.1767176389694214,
92
+ "learning_rate": 1.887735849056604e-05,
93
+ "loss": 0.0724,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.12264150943396226,
98
+ "grad_norm": 0.310159295797348,
99
+ "learning_rate": 1.878301886792453e-05,
100
+ "loss": 0.1826,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.1320754716981132,
105
+ "grad_norm": 0.29479867219924927,
106
+ "learning_rate": 1.868867924528302e-05,
107
+ "loss": 0.1407,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.14150943396226415,
112
+ "grad_norm": 0.25081831216812134,
113
+ "learning_rate": 1.859433962264151e-05,
114
+ "loss": 0.0804,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.1509433962264151,
119
+ "grad_norm": 7.194790840148926,
120
+ "learning_rate": 1.8500000000000002e-05,
121
+ "loss": 0.1394,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.16037735849056603,
126
+ "grad_norm": 0.19942767918109894,
127
+ "learning_rate": 1.8405660377358494e-05,
128
+ "loss": 0.0876,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.16981132075471697,
133
+ "grad_norm": 12.822174072265625,
134
+ "learning_rate": 1.8311320754716985e-05,
135
+ "loss": 0.1606,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.1792452830188679,
140
+ "grad_norm": 1.3328683376312256,
141
+ "learning_rate": 1.8216981132075472e-05,
142
+ "loss": 0.1835,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.18867924528301888,
147
+ "grad_norm": 0.17138229310512543,
148
+ "learning_rate": 1.8122641509433963e-05,
149
+ "loss": 0.2355,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.19811320754716982,
154
+ "grad_norm": 0.21127229928970337,
155
+ "learning_rate": 1.8028301886792454e-05,
156
+ "loss": 0.2031,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.20754716981132076,
161
+ "grad_norm": 2.211583137512207,
162
+ "learning_rate": 1.7933962264150946e-05,
163
+ "loss": 0.0223,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.2169811320754717,
168
+ "grad_norm": 0.17399153113365173,
169
+ "learning_rate": 1.7839622641509437e-05,
170
+ "loss": 0.2204,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.22641509433962265,
175
+ "grad_norm": 0.26820316910743713,
176
+ "learning_rate": 1.7745283018867928e-05,
177
+ "loss": 0.1022,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.2358490566037736,
182
+ "grad_norm": 0.15803369879722595,
183
+ "learning_rate": 1.7650943396226415e-05,
184
+ "loss": 0.0638,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.24528301886792453,
189
+ "grad_norm": 0.15400823950767517,
190
+ "learning_rate": 1.7556603773584907e-05,
191
+ "loss": 0.1257,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.25471698113207547,
196
+ "grad_norm": 0.7688778638839722,
197
+ "learning_rate": 1.7462264150943398e-05,
198
+ "loss": 0.2443,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.2641509433962264,
203
+ "grad_norm": 0.243111252784729,
204
+ "learning_rate": 1.736792452830189e-05,
205
+ "loss": 0.2897,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.27358490566037735,
210
+ "grad_norm": 5.870262145996094,
211
+ "learning_rate": 1.727358490566038e-05,
212
+ "loss": 0.2198,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.2830188679245283,
217
+ "grad_norm": 0.2840751111507416,
218
+ "learning_rate": 1.7179245283018867e-05,
219
+ "loss": 0.3108,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.29245283018867924,
224
+ "grad_norm": 0.1476099044084549,
225
+ "learning_rate": 1.708490566037736e-05,
226
+ "loss": 0.1688,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.3018867924528302,
231
+ "grad_norm": 0.3752176761627197,
232
+ "learning_rate": 1.699056603773585e-05,
233
+ "loss": 0.2876,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.3113207547169811,
238
+ "grad_norm": 30.54532241821289,
239
+ "learning_rate": 1.689622641509434e-05,
240
+ "loss": 0.1215,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.32075471698113206,
245
+ "grad_norm": 0.15333189070224762,
246
+ "learning_rate": 1.6801886792452832e-05,
247
+ "loss": 0.2964,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.330188679245283,
252
+ "grad_norm": 0.23220475018024445,
253
+ "learning_rate": 1.6707547169811323e-05,
254
+ "loss": 0.1506,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.33962264150943394,
259
+ "grad_norm": 121.28533172607422,
260
+ "learning_rate": 1.661320754716981e-05,
261
+ "loss": 0.2107,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.3490566037735849,
266
+ "grad_norm": 1.4383134841918945,
267
+ "learning_rate": 1.6518867924528305e-05,
268
+ "loss": 0.2117,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.3584905660377358,
273
+ "grad_norm": 0.14638499915599823,
274
+ "learning_rate": 1.6424528301886793e-05,
275
+ "loss": 0.1013,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.36792452830188677,
280
+ "grad_norm": 0.124303437769413,
281
+ "learning_rate": 1.6330188679245284e-05,
282
+ "loss": 0.0478,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.37735849056603776,
287
+ "grad_norm": 0.11256200820207596,
288
+ "learning_rate": 1.6235849056603775e-05,
289
+ "loss": 0.0689,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.3867924528301887,
294
+ "grad_norm": 0.10450290888547897,
295
+ "learning_rate": 1.6141509433962266e-05,
296
+ "loss": 0.1293,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.39622641509433965,
301
+ "grad_norm": 0.09205685555934906,
302
+ "learning_rate": 1.6047169811320754e-05,
303
+ "loss": 0.0672,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.4056603773584906,
308
+ "grad_norm": 1.0851916074752808,
309
+ "learning_rate": 1.5952830188679248e-05,
310
+ "loss": 0.1918,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.41509433962264153,
315
+ "grad_norm": 0.1460585743188858,
316
+ "learning_rate": 1.5858490566037736e-05,
317
+ "loss": 0.0866,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.42452830188679247,
322
+ "grad_norm": 0.10592811554670334,
323
+ "learning_rate": 1.5764150943396227e-05,
324
+ "loss": 0.0327,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.4339622641509434,
329
+ "grad_norm": 0.09917836636304855,
330
+ "learning_rate": 1.5669811320754718e-05,
331
+ "loss": 0.268,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.44339622641509435,
336
+ "grad_norm": 0.2683676481246948,
337
+ "learning_rate": 1.557547169811321e-05,
338
+ "loss": 0.2433,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.4528301886792453,
343
+ "grad_norm": 0.3096301853656769,
344
+ "learning_rate": 1.54811320754717e-05,
345
+ "loss": 0.0106,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.46226415094339623,
350
+ "grad_norm": 0.14542903006076813,
351
+ "learning_rate": 1.538679245283019e-05,
352
+ "loss": 0.1084,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.4716981132075472,
357
+ "grad_norm": 0.09798438102006912,
358
+ "learning_rate": 1.529245283018868e-05,
359
+ "loss": 0.1217,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.4811320754716981,
364
+ "grad_norm": 0.5679267644882202,
365
+ "learning_rate": 1.5198113207547172e-05,
366
+ "loss": 0.1084,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.49056603773584906,
371
+ "grad_norm": 0.07084541022777557,
372
+ "learning_rate": 1.5103773584905661e-05,
373
+ "loss": 0.1496,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.5,
378
+ "grad_norm": 0.09527801722288132,
379
+ "learning_rate": 1.5009433962264152e-05,
380
+ "loss": 0.0397,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.5094339622641509,
385
+ "grad_norm": 2.7925026416778564,
386
+ "learning_rate": 1.4915094339622642e-05,
387
+ "loss": 0.0082,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.5188679245283019,
392
+ "grad_norm": 61.901344299316406,
393
+ "learning_rate": 1.4820754716981134e-05,
394
+ "loss": 0.2448,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.5283018867924528,
399
+ "grad_norm": 0.10737080127000809,
400
+ "learning_rate": 1.4726415094339624e-05,
401
+ "loss": 0.2122,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.5377358490566038,
406
+ "grad_norm": 0.08159242570400238,
407
+ "learning_rate": 1.4632075471698115e-05,
408
+ "loss": 0.2056,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.5471698113207547,
413
+ "grad_norm": 26.218284606933594,
414
+ "learning_rate": 1.4537735849056604e-05,
415
+ "loss": 0.2137,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.5566037735849056,
420
+ "grad_norm": 0.09104019403457642,
421
+ "learning_rate": 1.4443396226415095e-05,
422
+ "loss": 0.1235,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.5660377358490566,
427
+ "grad_norm": 44.143577575683594,
428
+ "learning_rate": 1.4349056603773586e-05,
429
+ "loss": 0.1708,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.5754716981132075,
434
+ "grad_norm": 0.09825887531042099,
435
+ "learning_rate": 1.4254716981132078e-05,
436
+ "loss": 0.2829,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.5849056603773585,
441
+ "grad_norm": 0.08215257525444031,
442
+ "learning_rate": 1.4160377358490567e-05,
443
+ "loss": 0.0978,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.5943396226415094,
448
+ "grad_norm": 0.0858820378780365,
449
+ "learning_rate": 1.4066037735849058e-05,
450
+ "loss": 0.1308,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.6037735849056604,
455
+ "grad_norm": 0.07820013910531998,
456
+ "learning_rate": 1.3971698113207547e-05,
457
+ "loss": 0.0083,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.6132075471698113,
462
+ "grad_norm": 0.07088133692741394,
463
+ "learning_rate": 1.387735849056604e-05,
464
+ "loss": 0.0343,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.6226415094339622,
469
+ "grad_norm": 0.07562941312789917,
470
+ "learning_rate": 1.378301886792453e-05,
471
+ "loss": 0.1503,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.6320754716981132,
476
+ "grad_norm": 0.10470731556415558,
477
+ "learning_rate": 1.368867924528302e-05,
478
+ "loss": 0.0474,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.6415094339622641,
483
+ "grad_norm": 0.06047428399324417,
484
+ "learning_rate": 1.359433962264151e-05,
485
+ "loss": 0.3286,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.6509433962264151,
490
+ "grad_norm": 0.12241201102733612,
491
+ "learning_rate": 1.3500000000000001e-05,
492
+ "loss": 0.163,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.660377358490566,
497
+ "grad_norm": 0.07547236233949661,
498
+ "learning_rate": 1.3405660377358492e-05,
499
+ "loss": 0.1182,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.6698113207547169,
504
+ "grad_norm": 0.06518665701150894,
505
+ "learning_rate": 1.3311320754716983e-05,
506
+ "loss": 0.1177,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.6792452830188679,
511
+ "grad_norm": 0.05459102615714073,
512
+ "learning_rate": 1.3216981132075473e-05,
513
+ "loss": 0.0056,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.6886792452830188,
518
+ "grad_norm": 0.06507308781147003,
519
+ "learning_rate": 1.3122641509433964e-05,
520
+ "loss": 0.194,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.6981132075471698,
525
+ "grad_norm": 0.06847833096981049,
526
+ "learning_rate": 1.3028301886792453e-05,
527
+ "loss": 0.0334,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.7075471698113207,
532
+ "grad_norm": 0.05916672945022583,
533
+ "learning_rate": 1.2933962264150946e-05,
534
+ "loss": 0.1326,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.7169811320754716,
539
+ "grad_norm": 0.05806839466094971,
540
+ "learning_rate": 1.2839622641509435e-05,
541
+ "loss": 0.0734,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.7264150943396226,
546
+ "grad_norm": 0.058394916355609894,
547
+ "learning_rate": 1.2745283018867926e-05,
548
+ "loss": 0.3154,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.7358490566037735,
553
+ "grad_norm": 0.08128712326288223,
554
+ "learning_rate": 1.2650943396226416e-05,
555
+ "loss": 0.1004,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.7452830188679245,
560
+ "grad_norm": 0.1772662252187729,
561
+ "learning_rate": 1.2556603773584907e-05,
562
+ "loss": 0.1408,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.7547169811320755,
567
+ "grad_norm": 0.07657451182603836,
568
+ "learning_rate": 1.2462264150943398e-05,
569
+ "loss": 0.1138,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.7641509433962265,
574
+ "grad_norm": 0.0920625552535057,
575
+ "learning_rate": 1.2367924528301887e-05,
576
+ "loss": 0.0064,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.7735849056603774,
581
+ "grad_norm": 3.893165111541748,
582
+ "learning_rate": 1.2273584905660379e-05,
583
+ "loss": 0.1015,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.7830188679245284,
588
+ "grad_norm": 0.06635797768831253,
589
+ "learning_rate": 1.2179245283018868e-05,
590
+ "loss": 0.1405,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.7924528301886793,
595
+ "grad_norm": 1.1072912216186523,
596
+ "learning_rate": 1.2084905660377359e-05,
597
+ "loss": 0.1225,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.8018867924528302,
602
+ "grad_norm": 0.04783385619521141,
603
+ "learning_rate": 1.1990566037735848e-05,
604
+ "loss": 0.0895,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.8113207547169812,
609
+ "grad_norm": 0.05416665971279144,
610
+ "learning_rate": 1.1896226415094341e-05,
611
+ "loss": 0.1095,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.8207547169811321,
616
+ "grad_norm": 0.10190918296575546,
617
+ "learning_rate": 1.180188679245283e-05,
618
+ "loss": 0.1404,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.8301886792452831,
623
+ "grad_norm": 92.75904083251953,
624
+ "learning_rate": 1.1707547169811322e-05,
625
+ "loss": 0.0269,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.839622641509434,
630
+ "grad_norm": 0.06948844343423843,
631
+ "learning_rate": 1.1613207547169811e-05,
632
+ "loss": 0.0046,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.8490566037735849,
637
+ "grad_norm": 0.0549422986805439,
638
+ "learning_rate": 1.1518867924528304e-05,
639
+ "loss": 0.1588,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.8584905660377359,
644
+ "grad_norm": 0.09215264767408371,
645
+ "learning_rate": 1.1424528301886793e-05,
646
+ "loss": 0.0639,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.8679245283018868,
651
+ "grad_norm": 0.0980132520198822,
652
+ "learning_rate": 1.1330188679245284e-05,
653
+ "loss": 0.21,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.8773584905660378,
658
+ "grad_norm": 0.06740464270114899,
659
+ "learning_rate": 1.1235849056603774e-05,
660
+ "loss": 0.0059,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.8867924528301887,
665
+ "grad_norm": 0.42118075489997864,
666
+ "learning_rate": 1.1141509433962265e-05,
667
+ "loss": 0.1012,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.8962264150943396,
672
+ "grad_norm": 0.09071939438581467,
673
+ "learning_rate": 1.1047169811320754e-05,
674
+ "loss": 0.0636,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.9056603773584906,
679
+ "grad_norm": 0.06605428457260132,
680
+ "learning_rate": 1.0952830188679247e-05,
681
+ "loss": 0.1424,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.9150943396226415,
686
+ "grad_norm": 0.054869458079338074,
687
+ "learning_rate": 1.0858490566037736e-05,
688
+ "loss": 0.1506,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.9245283018867925,
693
+ "grad_norm": 8.528816223144531,
694
+ "learning_rate": 1.0764150943396227e-05,
695
+ "loss": 0.0766,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.9339622641509434,
700
+ "grad_norm": 0.04189067333936691,
701
+ "learning_rate": 1.0669811320754717e-05,
702
+ "loss": 0.0383,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.9433962264150944,
707
+ "grad_norm": 0.19604367017745972,
708
+ "learning_rate": 1.057547169811321e-05,
709
+ "loss": 0.0474,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.9528301886792453,
714
+ "grad_norm": 0.04203261435031891,
715
+ "learning_rate": 1.0481132075471699e-05,
716
+ "loss": 0.0571,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.9622641509433962,
721
+ "grad_norm": 20.811012268066406,
722
+ "learning_rate": 1.038679245283019e-05,
723
+ "loss": 0.2019,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.9716981132075472,
728
+ "grad_norm": 0.10877203941345215,
729
+ "learning_rate": 1.029245283018868e-05,
730
+ "loss": 0.1336,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.9811320754716981,
735
+ "grad_norm": 0.10228094458580017,
736
+ "learning_rate": 1.019811320754717e-05,
737
+ "loss": 0.0273,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.9905660377358491,
742
+ "grad_norm": 1.2278637886047363,
743
+ "learning_rate": 1.010377358490566e-05,
744
+ "loss": 0.0452,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 1.0,
749
+ "grad_norm": 0.03946210443973541,
750
+ "learning_rate": 1.0009433962264153e-05,
751
+ "loss": 0.0109,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 1.0,
756
+ "eval_loss": 0.08500511199235916,
757
+ "eval_runtime": 1.6971,
758
+ "eval_samples_per_second": 555.67,
759
+ "eval_steps_per_second": 69.532,
760
+ "step": 1060
761
+ },
762
+ {
763
+ "epoch": 1.009433962264151,
764
+ "grad_norm": 0.03779453784227371,
765
+ "learning_rate": 9.915094339622642e-06,
766
+ "loss": 0.1822,
767
+ "step": 1070
768
+ },
769
+ {
770
+ "epoch": 1.0188679245283019,
771
+ "grad_norm": 0.040553513914346695,
772
+ "learning_rate": 9.820754716981133e-06,
773
+ "loss": 0.054,
774
+ "step": 1080
775
+ },
776
+ {
777
+ "epoch": 1.028301886792453,
778
+ "grad_norm": 0.02908136695623398,
779
+ "learning_rate": 9.726415094339623e-06,
780
+ "loss": 0.0062,
781
+ "step": 1090
782
+ },
783
+ {
784
+ "epoch": 1.0377358490566038,
785
+ "grad_norm": 0.04287223890423775,
786
+ "learning_rate": 9.632075471698114e-06,
787
+ "loss": 0.0039,
788
+ "step": 1100
789
+ },
790
+ {
791
+ "epoch": 1.0471698113207548,
792
+ "grad_norm": 0.03865998610854149,
793
+ "learning_rate": 9.537735849056605e-06,
794
+ "loss": 0.0446,
795
+ "step": 1110
796
+ },
797
+ {
798
+ "epoch": 1.0566037735849056,
799
+ "grad_norm": 0.04521052539348602,
800
+ "learning_rate": 9.443396226415094e-06,
801
+ "loss": 0.0029,
802
+ "step": 1120
803
+ },
804
+ {
805
+ "epoch": 1.0660377358490567,
806
+ "grad_norm": 0.03594714403152466,
807
+ "learning_rate": 9.349056603773585e-06,
808
+ "loss": 0.148,
809
+ "step": 1130
810
+ },
811
+ {
812
+ "epoch": 1.0754716981132075,
813
+ "grad_norm": 0.029539430513978004,
814
+ "learning_rate": 9.254716981132076e-06,
815
+ "loss": 0.0271,
816
+ "step": 1140
817
+ },
818
+ {
819
+ "epoch": 1.0849056603773586,
820
+ "grad_norm": 4.038683891296387,
821
+ "learning_rate": 9.160377358490566e-06,
822
+ "loss": 0.165,
823
+ "step": 1150
824
+ },
825
+ {
826
+ "epoch": 1.0943396226415094,
827
+ "grad_norm": 0.027737464755773544,
828
+ "learning_rate": 9.066037735849057e-06,
829
+ "loss": 0.0028,
830
+ "step": 1160
831
+ },
832
+ {
833
+ "epoch": 1.1037735849056605,
834
+ "grad_norm": 0.03591258078813553,
835
+ "learning_rate": 8.971698113207548e-06,
836
+ "loss": 0.1371,
837
+ "step": 1170
838
+ },
839
+ {
840
+ "epoch": 1.1132075471698113,
841
+ "grad_norm": 12.058833122253418,
842
+ "learning_rate": 8.877358490566039e-06,
843
+ "loss": 0.236,
844
+ "step": 1180
845
+ },
846
+ {
847
+ "epoch": 1.1226415094339623,
848
+ "grad_norm": 0.04443644732236862,
849
+ "learning_rate": 8.783018867924528e-06,
850
+ "loss": 0.003,
851
+ "step": 1190
852
+ },
853
+ {
854
+ "epoch": 1.1320754716981132,
855
+ "grad_norm": 40.05979919433594,
856
+ "learning_rate": 8.68867924528302e-06,
857
+ "loss": 0.0157,
858
+ "step": 1200
859
+ },
860
+ {
861
+ "epoch": 1.1415094339622642,
862
+ "grad_norm": 0.04003468528389931,
863
+ "learning_rate": 8.59433962264151e-06,
864
+ "loss": 0.0029,
865
+ "step": 1210
866
+ },
867
+ {
868
+ "epoch": 1.150943396226415,
869
+ "grad_norm": 2.571934223175049,
870
+ "learning_rate": 8.5e-06,
871
+ "loss": 0.1204,
872
+ "step": 1220
873
+ },
874
+ {
875
+ "epoch": 1.1603773584905661,
876
+ "grad_norm": 0.06405159831047058,
877
+ "learning_rate": 8.405660377358491e-06,
878
+ "loss": 0.0146,
879
+ "step": 1230
880
+ },
881
+ {
882
+ "epoch": 1.169811320754717,
883
+ "grad_norm": 8.398702621459961,
884
+ "learning_rate": 8.311320754716982e-06,
885
+ "loss": 0.0048,
886
+ "step": 1240
887
+ },
888
+ {
889
+ "epoch": 1.179245283018868,
890
+ "grad_norm": 19.97818946838379,
891
+ "learning_rate": 8.216981132075471e-06,
892
+ "loss": 0.0688,
893
+ "step": 1250
894
+ },
895
+ {
896
+ "epoch": 1.1886792452830188,
897
+ "grad_norm": 0.03282918781042099,
898
+ "learning_rate": 8.122641509433963e-06,
899
+ "loss": 0.0035,
900
+ "step": 1260
901
+ },
902
+ {
903
+ "epoch": 1.1981132075471699,
904
+ "grad_norm": 0.03513512760400772,
905
+ "learning_rate": 8.028301886792454e-06,
906
+ "loss": 0.0355,
907
+ "step": 1270
908
+ },
909
+ {
910
+ "epoch": 1.2075471698113207,
911
+ "grad_norm": 0.03274456784129143,
912
+ "learning_rate": 7.933962264150945e-06,
913
+ "loss": 0.188,
914
+ "step": 1280
915
+ },
916
+ {
917
+ "epoch": 1.2169811320754718,
918
+ "grad_norm": 0.03626378998160362,
919
+ "learning_rate": 7.839622641509434e-06,
920
+ "loss": 0.014,
921
+ "step": 1290
922
+ },
923
+ {
924
+ "epoch": 1.2264150943396226,
925
+ "grad_norm": 0.8501767516136169,
926
+ "learning_rate": 7.745283018867925e-06,
927
+ "loss": 0.1076,
928
+ "step": 1300
929
+ },
930
+ {
931
+ "epoch": 1.2358490566037736,
932
+ "grad_norm": 0.0267633106559515,
933
+ "learning_rate": 7.650943396226416e-06,
934
+ "loss": 0.0025,
935
+ "step": 1310
936
+ },
937
+ {
938
+ "epoch": 1.2452830188679245,
939
+ "grad_norm": 0.04418088495731354,
940
+ "learning_rate": 7.5566037735849066e-06,
941
+ "loss": 0.1331,
942
+ "step": 1320
943
+ },
944
+ {
945
+ "epoch": 1.2547169811320755,
946
+ "grad_norm": 6.747396469116211,
947
+ "learning_rate": 7.462264150943397e-06,
948
+ "loss": 0.3259,
949
+ "step": 1330
950
+ },
951
+ {
952
+ "epoch": 1.2641509433962264,
953
+ "grad_norm": 0.032822128385305405,
954
+ "learning_rate": 7.367924528301887e-06,
955
+ "loss": 0.1229,
956
+ "step": 1340
957
+ },
958
+ {
959
+ "epoch": 1.2735849056603774,
960
+ "grad_norm": 0.06315261125564575,
961
+ "learning_rate": 7.273584905660378e-06,
962
+ "loss": 0.0039,
963
+ "step": 1350
964
+ },
965
+ {
966
+ "epoch": 1.2830188679245282,
967
+ "grad_norm": 0.03962039574980736,
968
+ "learning_rate": 7.179245283018868e-06,
969
+ "loss": 0.0072,
970
+ "step": 1360
971
+ },
972
+ {
973
+ "epoch": 1.2924528301886793,
974
+ "grad_norm": 0.03726816922426224,
975
+ "learning_rate": 7.0849056603773594e-06,
976
+ "loss": 0.0138,
977
+ "step": 1370
978
+ },
979
+ {
980
+ "epoch": 1.3018867924528301,
981
+ "grad_norm": 0.04036370664834976,
982
+ "learning_rate": 6.99056603773585e-06,
983
+ "loss": 0.1472,
984
+ "step": 1380
985
+ },
986
+ {
987
+ "epoch": 1.3113207547169812,
988
+ "grad_norm": 0.03037635050714016,
989
+ "learning_rate": 6.89622641509434e-06,
990
+ "loss": 0.0069,
991
+ "step": 1390
992
+ },
993
+ {
994
+ "epoch": 1.320754716981132,
995
+ "grad_norm": 0.02670077607035637,
996
+ "learning_rate": 6.801886792452831e-06,
997
+ "loss": 0.0021,
998
+ "step": 1400
999
+ },
1000
+ {
1001
+ "epoch": 1.330188679245283,
1002
+ "grad_norm": 0.05846339091658592,
1003
+ "learning_rate": 6.707547169811321e-06,
1004
+ "loss": 0.0022,
1005
+ "step": 1410
1006
+ },
1007
+ {
1008
+ "epoch": 1.3396226415094339,
1009
+ "grad_norm": 9.76332950592041,
1010
+ "learning_rate": 6.613207547169812e-06,
1011
+ "loss": 0.1445,
1012
+ "step": 1420
1013
+ },
1014
+ {
1015
+ "epoch": 1.349056603773585,
1016
+ "grad_norm": 0.048967599868774414,
1017
+ "learning_rate": 6.5188679245283026e-06,
1018
+ "loss": 0.0441,
1019
+ "step": 1430
1020
+ },
1021
+ {
1022
+ "epoch": 1.3584905660377358,
1023
+ "grad_norm": 0.025179484859108925,
1024
+ "learning_rate": 6.424528301886793e-06,
1025
+ "loss": 0.0188,
1026
+ "step": 1440
1027
+ },
1028
+ {
1029
+ "epoch": 1.3679245283018868,
1030
+ "grad_norm": 0.02890361286699772,
1031
+ "learning_rate": 6.330188679245284e-06,
1032
+ "loss": 0.0021,
1033
+ "step": 1450
1034
+ },
1035
+ {
1036
+ "epoch": 1.3773584905660377,
1037
+ "grad_norm": 0.02526584453880787,
1038
+ "learning_rate": 6.235849056603774e-06,
1039
+ "loss": 0.0022,
1040
+ "step": 1460
1041
+ },
1042
+ {
1043
+ "epoch": 1.3867924528301887,
1044
+ "grad_norm": 2.650209903717041,
1045
+ "learning_rate": 6.141509433962265e-06,
1046
+ "loss": 0.0482,
1047
+ "step": 1470
1048
+ },
1049
+ {
1050
+ "epoch": 1.3962264150943398,
1051
+ "grad_norm": 0.0368034765124321,
1052
+ "learning_rate": 6.0471698113207555e-06,
1053
+ "loss": 0.0034,
1054
+ "step": 1480
1055
+ },
1056
+ {
1057
+ "epoch": 1.4056603773584906,
1058
+ "grad_norm": 0.021781697869300842,
1059
+ "learning_rate": 5.952830188679246e-06,
1060
+ "loss": 0.0022,
1061
+ "step": 1490
1062
+ },
1063
+ {
1064
+ "epoch": 1.4150943396226414,
1065
+ "grad_norm": 0.019001835957169533,
1066
+ "learning_rate": 5.858490566037737e-06,
1067
+ "loss": 0.2058,
1068
+ "step": 1500
1069
+ },
1070
+ {
1071
+ "epoch": 1.4245283018867925,
1072
+ "grad_norm": 0.047584012150764465,
1073
+ "learning_rate": 5.764150943396227e-06,
1074
+ "loss": 0.1632,
1075
+ "step": 1510
1076
+ },
1077
+ {
1078
+ "epoch": 1.4339622641509435,
1079
+ "grad_norm": 0.02781420387327671,
1080
+ "learning_rate": 5.669811320754718e-06,
1081
+ "loss": 0.0018,
1082
+ "step": 1520
1083
+ },
1084
+ {
1085
+ "epoch": 1.4433962264150944,
1086
+ "grad_norm": 0.03572264313697815,
1087
+ "learning_rate": 5.575471698113208e-06,
1088
+ "loss": 0.0184,
1089
+ "step": 1530
1090
+ },
1091
+ {
1092
+ "epoch": 1.4528301886792452,
1093
+ "grad_norm": 0.021896662190556526,
1094
+ "learning_rate": 5.4811320754716994e-06,
1095
+ "loss": 0.155,
1096
+ "step": 1540
1097
+ },
1098
+ {
1099
+ "epoch": 1.4622641509433962,
1100
+ "grad_norm": 0.024771416559815407,
1101
+ "learning_rate": 5.38679245283019e-06,
1102
+ "loss": 0.0018,
1103
+ "step": 1550
1104
+ },
1105
+ {
1106
+ "epoch": 1.4716981132075473,
1107
+ "grad_norm": 3.849034547805786,
1108
+ "learning_rate": 5.29245283018868e-06,
1109
+ "loss": 0.1006,
1110
+ "step": 1560
1111
+ },
1112
+ {
1113
+ "epoch": 1.4811320754716981,
1114
+ "grad_norm": 0.12136558443307877,
1115
+ "learning_rate": 5.198113207547171e-06,
1116
+ "loss": 0.0024,
1117
+ "step": 1570
1118
+ },
1119
+ {
1120
+ "epoch": 1.490566037735849,
1121
+ "grad_norm": 0.029468955472111702,
1122
+ "learning_rate": 5.103773584905661e-06,
1123
+ "loss": 0.0021,
1124
+ "step": 1580
1125
+ },
1126
+ {
1127
+ "epoch": 1.5,
1128
+ "grad_norm": 2.4301178455352783,
1129
+ "learning_rate": 5.009433962264152e-06,
1130
+ "loss": 0.0024,
1131
+ "step": 1590
1132
+ },
1133
+ {
1134
+ "epoch": 1.509433962264151,
1135
+ "grad_norm": 0.024639485403895378,
1136
+ "learning_rate": 4.915094339622642e-06,
1137
+ "loss": 0.0019,
1138
+ "step": 1600
1139
+ },
1140
+ {
1141
+ "epoch": 1.5188679245283019,
1142
+ "grad_norm": 5.811135768890381,
1143
+ "learning_rate": 4.820754716981133e-06,
1144
+ "loss": 0.0282,
1145
+ "step": 1610
1146
+ },
1147
+ {
1148
+ "epoch": 1.5283018867924527,
1149
+ "grad_norm": 0.02190409228205681,
1150
+ "learning_rate": 4.726415094339623e-06,
1151
+ "loss": 0.0016,
1152
+ "step": 1620
1153
+ },
1154
+ {
1155
+ "epoch": 1.5377358490566038,
1156
+ "grad_norm": 0.025405917316675186,
1157
+ "learning_rate": 4.632075471698113e-06,
1158
+ "loss": 0.0505,
1159
+ "step": 1630
1160
+ },
1161
+ {
1162
+ "epoch": 1.5471698113207548,
1163
+ "grad_norm": 16.779964447021484,
1164
+ "learning_rate": 4.537735849056604e-06,
1165
+ "loss": 0.1169,
1166
+ "step": 1640
1167
+ },
1168
+ {
1169
+ "epoch": 1.5566037735849056,
1170
+ "grad_norm": 43.401329040527344,
1171
+ "learning_rate": 4.443396226415095e-06,
1172
+ "loss": 0.0245,
1173
+ "step": 1650
1174
+ },
1175
+ {
1176
+ "epoch": 1.5660377358490565,
1177
+ "grad_norm": 0.9246163964271545,
1178
+ "learning_rate": 4.349056603773586e-06,
1179
+ "loss": 0.0354,
1180
+ "step": 1660
1181
+ },
1182
+ {
1183
+ "epoch": 1.5754716981132075,
1184
+ "grad_norm": 0.02293049544095993,
1185
+ "learning_rate": 4.254716981132076e-06,
1186
+ "loss": 0.0036,
1187
+ "step": 1670
1188
+ },
1189
+ {
1190
+ "epoch": 1.5849056603773586,
1191
+ "grad_norm": 0.019884012639522552,
1192
+ "learning_rate": 4.160377358490566e-06,
1193
+ "loss": 0.0017,
1194
+ "step": 1680
1195
+ },
1196
+ {
1197
+ "epoch": 1.5943396226415094,
1198
+ "grad_norm": 0.0297381728887558,
1199
+ "learning_rate": 4.066037735849057e-06,
1200
+ "loss": 0.002,
1201
+ "step": 1690
1202
+ },
1203
+ {
1204
+ "epoch": 1.6037735849056602,
1205
+ "grad_norm": 0.01664115861058235,
1206
+ "learning_rate": 3.9716981132075475e-06,
1207
+ "loss": 0.0029,
1208
+ "step": 1700
1209
+ },
1210
+ {
1211
+ "epoch": 1.6132075471698113,
1212
+ "grad_norm": 0.021111104637384415,
1213
+ "learning_rate": 3.8773584905660386e-06,
1214
+ "loss": 0.0019,
1215
+ "step": 1710
1216
+ },
1217
+ {
1218
+ "epoch": 1.6226415094339623,
1219
+ "grad_norm": 5.916421890258789,
1220
+ "learning_rate": 3.783018867924529e-06,
1221
+ "loss": 0.0597,
1222
+ "step": 1720
1223
+ },
1224
+ {
1225
+ "epoch": 1.6320754716981132,
1226
+ "grad_norm": 0.11948911845684052,
1227
+ "learning_rate": 3.688679245283019e-06,
1228
+ "loss": 0.0288,
1229
+ "step": 1730
1230
+ },
1231
+ {
1232
+ "epoch": 1.641509433962264,
1233
+ "grad_norm": 0.029013920575380325,
1234
+ "learning_rate": 3.5943396226415093e-06,
1235
+ "loss": 0.0022,
1236
+ "step": 1740
1237
+ },
1238
+ {
1239
+ "epoch": 1.650943396226415,
1240
+ "grad_norm": 0.021010151132941246,
1241
+ "learning_rate": 3.5e-06,
1242
+ "loss": 0.0021,
1243
+ "step": 1750
1244
+ },
1245
+ {
1246
+ "epoch": 1.6603773584905661,
1247
+ "grad_norm": 0.020002691075205803,
1248
+ "learning_rate": 3.4056603773584906e-06,
1249
+ "loss": 0.0016,
1250
+ "step": 1760
1251
+ },
1252
+ {
1253
+ "epoch": 1.669811320754717,
1254
+ "grad_norm": 0.02407264895737171,
1255
+ "learning_rate": 3.3113207547169813e-06,
1256
+ "loss": 0.0928,
1257
+ "step": 1770
1258
+ },
1259
+ {
1260
+ "epoch": 1.6792452830188678,
1261
+ "grad_norm": 0.024595679715275764,
1262
+ "learning_rate": 3.216981132075472e-06,
1263
+ "loss": 0.0018,
1264
+ "step": 1780
1265
+ },
1266
+ {
1267
+ "epoch": 1.6886792452830188,
1268
+ "grad_norm": 0.017810633406043053,
1269
+ "learning_rate": 3.122641509433962e-06,
1270
+ "loss": 0.1722,
1271
+ "step": 1790
1272
+ },
1273
+ {
1274
+ "epoch": 1.6981132075471699,
1275
+ "grad_norm": 0.01612844318151474,
1276
+ "learning_rate": 3.028301886792453e-06,
1277
+ "loss": 0.1158,
1278
+ "step": 1800
1279
+ },
1280
+ {
1281
+ "epoch": 1.7075471698113207,
1282
+ "grad_norm": 0.023075569421052933,
1283
+ "learning_rate": 2.9339622641509435e-06,
1284
+ "loss": 0.0016,
1285
+ "step": 1810
1286
+ },
1287
+ {
1288
+ "epoch": 1.7169811320754715,
1289
+ "grad_norm": 0.01716834492981434,
1290
+ "learning_rate": 2.839622641509434e-06,
1291
+ "loss": 0.0015,
1292
+ "step": 1820
1293
+ },
1294
+ {
1295
+ "epoch": 1.7264150943396226,
1296
+ "grad_norm": 0.0205362718552351,
1297
+ "learning_rate": 2.745283018867925e-06,
1298
+ "loss": 0.0017,
1299
+ "step": 1830
1300
+ },
1301
+ {
1302
+ "epoch": 1.7358490566037736,
1303
+ "grad_norm": 0.023218706250190735,
1304
+ "learning_rate": 2.6509433962264155e-06,
1305
+ "loss": 0.0014,
1306
+ "step": 1840
1307
+ },
1308
+ {
1309
+ "epoch": 1.7452830188679245,
1310
+ "grad_norm": 0.018329111859202385,
1311
+ "learning_rate": 2.5566037735849057e-06,
1312
+ "loss": 0.1204,
1313
+ "step": 1850
1314
+ },
1315
+ {
1316
+ "epoch": 1.7547169811320755,
1317
+ "grad_norm": 0.019258936867117882,
1318
+ "learning_rate": 2.4622641509433964e-06,
1319
+ "loss": 0.0018,
1320
+ "step": 1860
1321
+ },
1322
+ {
1323
+ "epoch": 1.7641509433962264,
1324
+ "grad_norm": 0.023526819422841072,
1325
+ "learning_rate": 2.367924528301887e-06,
1326
+ "loss": 0.0074,
1327
+ "step": 1870
1328
+ },
1329
+ {
1330
+ "epoch": 1.7735849056603774,
1331
+ "grad_norm": 0.01679695025086403,
1332
+ "learning_rate": 2.2735849056603777e-06,
1333
+ "loss": 0.0014,
1334
+ "step": 1880
1335
+ },
1336
+ {
1337
+ "epoch": 1.7830188679245285,
1338
+ "grad_norm": 0.014311902225017548,
1339
+ "learning_rate": 2.1792452830188684e-06,
1340
+ "loss": 0.0015,
1341
+ "step": 1890
1342
+ },
1343
+ {
1344
+ "epoch": 1.7924528301886793,
1345
+ "grad_norm": 1.5082017183303833,
1346
+ "learning_rate": 2.0849056603773586e-06,
1347
+ "loss": 0.0708,
1348
+ "step": 1900
1349
+ },
1350
+ {
1351
+ "epoch": 1.8018867924528301,
1352
+ "grad_norm": 52.86256408691406,
1353
+ "learning_rate": 1.9905660377358493e-06,
1354
+ "loss": 0.0666,
1355
+ "step": 1910
1356
+ },
1357
+ {
1358
+ "epoch": 1.8113207547169812,
1359
+ "grad_norm": 0.020178191363811493,
1360
+ "learning_rate": 1.89622641509434e-06,
1361
+ "loss": 0.0694,
1362
+ "step": 1920
1363
+ },
1364
+ {
1365
+ "epoch": 1.8207547169811322,
1366
+ "grad_norm": 0.01885703019797802,
1367
+ "learning_rate": 1.8018867924528302e-06,
1368
+ "loss": 0.0416,
1369
+ "step": 1930
1370
+ },
1371
+ {
1372
+ "epoch": 1.830188679245283,
1373
+ "grad_norm": 0.021212713792920113,
1374
+ "learning_rate": 1.7075471698113208e-06,
1375
+ "loss": 0.0015,
1376
+ "step": 1940
1377
+ },
1378
+ {
1379
+ "epoch": 1.8396226415094339,
1380
+ "grad_norm": 0.020716039463877678,
1381
+ "learning_rate": 1.6132075471698113e-06,
1382
+ "loss": 0.0446,
1383
+ "step": 1950
1384
+ },
1385
+ {
1386
+ "epoch": 1.849056603773585,
1387
+ "grad_norm": 0.01979793794453144,
1388
+ "learning_rate": 1.518867924528302e-06,
1389
+ "loss": 0.0017,
1390
+ "step": 1960
1391
+ },
1392
+ {
1393
+ "epoch": 1.858490566037736,
1394
+ "grad_norm": 0.029191287234425545,
1395
+ "learning_rate": 1.4245283018867926e-06,
1396
+ "loss": 0.0016,
1397
+ "step": 1970
1398
+ },
1399
+ {
1400
+ "epoch": 1.8679245283018868,
1401
+ "grad_norm": 0.02217436581850052,
1402
+ "learning_rate": 1.330188679245283e-06,
1403
+ "loss": 0.0441,
1404
+ "step": 1980
1405
+ },
1406
+ {
1407
+ "epoch": 1.8773584905660377,
1408
+ "grad_norm": 0.0228409580886364,
1409
+ "learning_rate": 1.2358490566037737e-06,
1410
+ "loss": 0.0016,
1411
+ "step": 1990
1412
+ },
1413
+ {
1414
+ "epoch": 1.8867924528301887,
1415
+ "grad_norm": 0.022314254194498062,
1416
+ "learning_rate": 1.1415094339622642e-06,
1417
+ "loss": 0.1457,
1418
+ "step": 2000
1419
+ },
1420
+ {
1421
+ "epoch": 1.8962264150943398,
1422
+ "grad_norm": 0.017337264493107796,
1423
+ "learning_rate": 1.0471698113207548e-06,
1424
+ "loss": 0.1144,
1425
+ "step": 2010
1426
+ },
1427
+ {
1428
+ "epoch": 1.9056603773584906,
1429
+ "grad_norm": 0.021478446200489998,
1430
+ "learning_rate": 9.528301886792454e-07,
1431
+ "loss": 0.0014,
1432
+ "step": 2020
1433
+ },
1434
+ {
1435
+ "epoch": 1.9150943396226414,
1436
+ "grad_norm": 0.021643251180648804,
1437
+ "learning_rate": 8.584905660377358e-07,
1438
+ "loss": 0.0284,
1439
+ "step": 2030
1440
+ },
1441
+ {
1442
+ "epoch": 1.9245283018867925,
1443
+ "grad_norm": 0.02016671560704708,
1444
+ "learning_rate": 7.641509433962264e-07,
1445
+ "loss": 0.0482,
1446
+ "step": 2040
1447
+ },
1448
+ {
1449
+ "epoch": 1.9339622641509435,
1450
+ "grad_norm": 0.019274510443210602,
1451
+ "learning_rate": 6.698113207547171e-07,
1452
+ "loss": 0.0016,
1453
+ "step": 2050
1454
+ },
1455
+ {
1456
+ "epoch": 1.9433962264150944,
1457
+ "grad_norm": 0.014301498420536518,
1458
+ "learning_rate": 5.754716981132076e-07,
1459
+ "loss": 0.0045,
1460
+ "step": 2060
1461
+ },
1462
+ {
1463
+ "epoch": 1.9528301886792452,
1464
+ "grad_norm": 0.01988300494849682,
1465
+ "learning_rate": 4.811320754716982e-07,
1466
+ "loss": 0.0015,
1467
+ "step": 2070
1468
+ },
1469
+ {
1470
+ "epoch": 1.9622641509433962,
1471
+ "grad_norm": 0.02060701698064804,
1472
+ "learning_rate": 3.867924528301887e-07,
1473
+ "loss": 0.0044,
1474
+ "step": 2080
1475
+ },
1476
+ {
1477
+ "epoch": 1.9716981132075473,
1478
+ "grad_norm": 41.62403106689453,
1479
+ "learning_rate": 2.924528301886793e-07,
1480
+ "loss": 0.1818,
1481
+ "step": 2090
1482
+ },
1483
+ {
1484
+ "epoch": 1.9811320754716981,
1485
+ "grad_norm": 0.0649556890130043,
1486
+ "learning_rate": 1.9811320754716982e-07,
1487
+ "loss": 0.0016,
1488
+ "step": 2100
1489
+ },
1490
+ {
1491
+ "epoch": 1.990566037735849,
1492
+ "grad_norm": 0.02280914969742298,
1493
+ "learning_rate": 1.0377358490566039e-07,
1494
+ "loss": 0.0414,
1495
+ "step": 2110
1496
+ },
1497
+ {
1498
+ "epoch": 2.0,
1499
+ "grad_norm": 0.01854662224650383,
1500
+ "learning_rate": 9.433962264150945e-09,
1501
+ "loss": 0.0015,
1502
+ "step": 2120
1503
+ },
1504
+ {
1505
+ "epoch": 2.0,
1506
+ "eval_loss": 0.06546525657176971,
1507
+ "eval_runtime": 1.7009,
1508
+ "eval_samples_per_second": 554.403,
1509
+ "eval_steps_per_second": 69.374,
1510
+ "step": 2120
1511
+ }
1512
+ ],
1513
+ "logging_steps": 10,
1514
+ "max_steps": 2120,
1515
+ "num_input_tokens_seen": 0,
1516
+ "num_train_epochs": 2,
1517
+ "save_steps": 500,
1518
+ "stateful_callbacks": {
1519
+ "TrainerControl": {
1520
+ "args": {
1521
+ "should_epoch_stop": false,
1522
+ "should_evaluate": false,
1523
+ "should_log": false,
1524
+ "should_save": true,
1525
+ "should_training_stop": true
1526
+ },
1527
+ "attributes": {}
1528
+ }
1529
+ },
1530
+ "total_flos": 4461837276794880.0,
1531
+ "train_batch_size": 8,
1532
+ "trial_name": null,
1533
+ "trial_params": null
1534
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f8378db2b776ca5ccea1c7f23bb55f2db0dab729578a11003daf76a9cbb0d5
3
+ size 5841