marbonora commited on
Commit
4bdf289
·
verified ·
1 Parent(s): 0d6518d

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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
14
+ "0": "FAC",
15
+ "1": "LF",
16
+ "2": "TXT"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "FAC": 0,
22
+ "LF": 1,
23
+ "TXT": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "transformers_version": "4.56.0",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 256000
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d463a22c3a6fad27515a9ef9421253082100142aa32e0bdf2264776f860b53
3
+ size 1130633956
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37210903d02cd19e0f3e901a8d63a80a9834609b642239f84df959c333f2c0e1
3
+ size 2261390731
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d6f7e96771fb57d8418929ea25b8a0e0e5f81aafaa3d86f078566684bf6357
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8aa6ddbdd9801352a9fe4a4d320431326103bc0f3f1475e83823d70240a292
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d42552cb1c1828701f1a7dbf8d3079ede2f29d7b9ba1eb0e5afd5fa7e43eea9
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 +1,1513 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2094,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.009551098376313277,
14
+ "grad_norm": 2.2569775581359863,
15
+ "learning_rate": 1.9914040114613182e-05,
16
+ "loss": 1.0939,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.019102196752626553,
21
+ "grad_norm": 2.2780814170837402,
22
+ "learning_rate": 1.981852913085005e-05,
23
+ "loss": 1.0778,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.02865329512893983,
28
+ "grad_norm": 6.2301554679870605,
29
+ "learning_rate": 1.9723018147086915e-05,
30
+ "loss": 0.9625,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.038204393505253106,
35
+ "grad_norm": 24.95392417907715,
36
+ "learning_rate": 1.9627507163323785e-05,
37
+ "loss": 0.8937,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.04775549188156638,
42
+ "grad_norm": 3.5438709259033203,
43
+ "learning_rate": 1.9531996179560652e-05,
44
+ "loss": 0.7843,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.05730659025787966,
49
+ "grad_norm": 3.102586269378662,
50
+ "learning_rate": 1.943648519579752e-05,
51
+ "loss": 0.6911,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.06685768863419293,
56
+ "grad_norm": 1.7375000715255737,
57
+ "learning_rate": 1.9340974212034385e-05,
58
+ "loss": 0.5772,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.07640878701050621,
63
+ "grad_norm": 4.719320774078369,
64
+ "learning_rate": 1.9245463228271252e-05,
65
+ "loss": 0.5894,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.08595988538681948,
70
+ "grad_norm": 1.8283956050872803,
71
+ "learning_rate": 1.9149952244508122e-05,
72
+ "loss": 0.405,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.09551098376313276,
77
+ "grad_norm": 27.354843139648438,
78
+ "learning_rate": 1.905444126074499e-05,
79
+ "loss": 0.4705,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.10506208213944604,
84
+ "grad_norm": 4.766273021697998,
85
+ "learning_rate": 1.8958930276981855e-05,
86
+ "loss": 0.3644,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.11461318051575932,
91
+ "grad_norm": 4.26953125,
92
+ "learning_rate": 1.8863419293218722e-05,
93
+ "loss": 0.2284,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.12416427889207259,
98
+ "grad_norm": 0.7594988942146301,
99
+ "learning_rate": 1.876790830945559e-05,
100
+ "loss": 0.2435,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.13371537726838587,
105
+ "grad_norm": 1.365365743637085,
106
+ "learning_rate": 1.8672397325692455e-05,
107
+ "loss": 0.2184,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.14326647564469913,
112
+ "grad_norm": 9.257822036743164,
113
+ "learning_rate": 1.857688634192932e-05,
114
+ "loss": 0.2248,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.15281757402101243,
119
+ "grad_norm": 0.5103208422660828,
120
+ "learning_rate": 1.848137535816619e-05,
121
+ "loss": 0.243,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.1623686723973257,
126
+ "grad_norm": Infinity,
127
+ "learning_rate": 1.8385864374403058e-05,
128
+ "loss": 0.2442,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.17191977077363896,
133
+ "grad_norm": 0.6302635669708252,
134
+ "learning_rate": 1.8290353390639925e-05,
135
+ "loss": 0.4167,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.18147086914995225,
140
+ "grad_norm": 4.381824493408203,
141
+ "learning_rate": 1.819484240687679e-05,
142
+ "loss": 0.2861,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.19102196752626552,
147
+ "grad_norm": 0.35794690251350403,
148
+ "learning_rate": 1.8099331423113658e-05,
149
+ "loss": 0.1059,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.20057306590257878,
154
+ "grad_norm": 0.4472959637641907,
155
+ "learning_rate": 1.8003820439350528e-05,
156
+ "loss": 0.0896,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.21012416427889208,
161
+ "grad_norm": 0.2821422517299652,
162
+ "learning_rate": 1.7908309455587395e-05,
163
+ "loss": 0.0837,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.21967526265520534,
168
+ "grad_norm": 26.638248443603516,
169
+ "learning_rate": 1.781279847182426e-05,
170
+ "loss": 0.1115,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.22922636103151864,
175
+ "grad_norm": 1.5657349824905396,
176
+ "learning_rate": 1.7717287488061128e-05,
177
+ "loss": 0.1829,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.2387774594078319,
182
+ "grad_norm": 0.2336825728416443,
183
+ "learning_rate": 1.7621776504297995e-05,
184
+ "loss": 0.0556,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.24832855778414517,
189
+ "grad_norm": 4.114994525909424,
190
+ "learning_rate": 1.752626552053486e-05,
191
+ "loss": 0.1532,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.25787965616045844,
196
+ "grad_norm": 13.862896919250488,
197
+ "learning_rate": 1.743075453677173e-05,
198
+ "loss": 0.2155,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.26743075453677173,
203
+ "grad_norm": 0.21343673765659332,
204
+ "learning_rate": 1.7335243553008598e-05,
205
+ "loss": 0.0374,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.276981852913085,
210
+ "grad_norm": 0.1753835529088974,
211
+ "learning_rate": 1.7239732569245464e-05,
212
+ "loss": 0.108,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.28653295128939826,
217
+ "grad_norm": 0.24574324488639832,
218
+ "learning_rate": 1.714422158548233e-05,
219
+ "loss": 0.1175,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.29608404966571156,
224
+ "grad_norm": 23.268014907836914,
225
+ "learning_rate": 1.7048710601719198e-05,
226
+ "loss": 0.1532,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.30563514804202485,
231
+ "grad_norm": 0.1591091752052307,
232
+ "learning_rate": 1.6953199617956068e-05,
233
+ "loss": 0.0994,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.3151862464183381,
238
+ "grad_norm": 0.17243853211402893,
239
+ "learning_rate": 1.6857688634192934e-05,
240
+ "loss": 0.083,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.3247373447946514,
245
+ "grad_norm": 2.6030852794647217,
246
+ "learning_rate": 1.67621776504298e-05,
247
+ "loss": 0.2142,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.3342884431709647,
252
+ "grad_norm": 0.15623551607131958,
253
+ "learning_rate": 1.6666666666666667e-05,
254
+ "loss": 0.0821,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.3438395415472779,
259
+ "grad_norm": 1.7919316291809082,
260
+ "learning_rate": 1.6571155682903534e-05,
261
+ "loss": 0.1883,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.3533906399235912,
266
+ "grad_norm": 0.2467084378004074,
267
+ "learning_rate": 1.6475644699140404e-05,
268
+ "loss": 0.083,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.3629417382999045,
273
+ "grad_norm": 1.9838752746582031,
274
+ "learning_rate": 1.6380133715377267e-05,
275
+ "loss": 0.0919,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.37249283667621774,
280
+ "grad_norm": 0.13745100796222687,
281
+ "learning_rate": 1.6284622731614137e-05,
282
+ "loss": 0.2578,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.38204393505253104,
287
+ "grad_norm": 23.14975929260254,
288
+ "learning_rate": 1.6189111747851004e-05,
289
+ "loss": 0.0609,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.39159503342884433,
294
+ "grad_norm": 0.16147832572460175,
295
+ "learning_rate": 1.609360076408787e-05,
296
+ "loss": 0.1865,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.40114613180515757,
301
+ "grad_norm": 8.0061616897583,
302
+ "learning_rate": 1.599808978032474e-05,
303
+ "loss": 0.1216,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.41069723018147086,
308
+ "grad_norm": 1.0904359817504883,
309
+ "learning_rate": 1.5902578796561604e-05,
310
+ "loss": 0.137,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.42024832855778416,
315
+ "grad_norm": 2.3162689208984375,
316
+ "learning_rate": 1.5807067812798474e-05,
317
+ "loss": 0.1358,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.4297994269340974,
322
+ "grad_norm": 0.11886035650968552,
323
+ "learning_rate": 1.571155682903534e-05,
324
+ "loss": 0.0733,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.4393505253104107,
329
+ "grad_norm": 7.155008792877197,
330
+ "learning_rate": 1.5616045845272207e-05,
331
+ "loss": 0.1238,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.448901623686724,
336
+ "grad_norm": 0.11069323867559433,
337
+ "learning_rate": 1.5520534861509077e-05,
338
+ "loss": 0.1987,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.4584527220630373,
343
+ "grad_norm": 0.10282690078020096,
344
+ "learning_rate": 1.542502387774594e-05,
345
+ "loss": 0.091,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.4680038204393505,
350
+ "grad_norm": 0.1403094232082367,
351
+ "learning_rate": 1.532951289398281e-05,
352
+ "loss": 0.1213,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.4775549188156638,
357
+ "grad_norm": 0.1331929713487625,
358
+ "learning_rate": 1.5234001910219675e-05,
359
+ "loss": 0.0154,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.4871060171919771,
364
+ "grad_norm": 0.11407709866762161,
365
+ "learning_rate": 1.5138490926456543e-05,
366
+ "loss": 0.1221,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.49665711556829034,
371
+ "grad_norm": 0.5473654270172119,
372
+ "learning_rate": 1.5042979942693412e-05,
373
+ "loss": 0.1143,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.5062082139446036,
378
+ "grad_norm": 0.11086848378181458,
379
+ "learning_rate": 1.4947468958930278e-05,
380
+ "loss": 0.0141,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.5157593123209169,
385
+ "grad_norm": 78.81968688964844,
386
+ "learning_rate": 1.4851957975167147e-05,
387
+ "loss": 0.1552,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.5253104106972302,
392
+ "grad_norm": 6.011876106262207,
393
+ "learning_rate": 1.4756446991404012e-05,
394
+ "loss": 0.1232,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.5348615090735435,
399
+ "grad_norm": 0.15130910277366638,
400
+ "learning_rate": 1.466093600764088e-05,
401
+ "loss": 0.1164,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.5444126074498568,
406
+ "grad_norm": 0.0998225063085556,
407
+ "learning_rate": 1.4565425023877747e-05,
408
+ "loss": 0.1248,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.55396370582617,
413
+ "grad_norm": 0.09413418173789978,
414
+ "learning_rate": 1.4469914040114615e-05,
415
+ "loss": 0.1258,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.5635148042024832,
420
+ "grad_norm": 30.505067825317383,
421
+ "learning_rate": 1.4374403056351483e-05,
422
+ "loss": 0.0788,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.5730659025787965,
427
+ "grad_norm": 0.10750491917133331,
428
+ "learning_rate": 1.4278892072588348e-05,
429
+ "loss": 0.1026,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.5826170009551098,
434
+ "grad_norm": 0.08975467830896378,
435
+ "learning_rate": 1.4183381088825216e-05,
436
+ "loss": 0.2408,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.5921680993314231,
441
+ "grad_norm": 0.12342803925275803,
442
+ "learning_rate": 1.4087870105062083e-05,
443
+ "loss": 0.0717,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.6017191977077364,
448
+ "grad_norm": 0.07816806435585022,
449
+ "learning_rate": 1.3992359121298951e-05,
450
+ "loss": 0.1131,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.6112702960840497,
455
+ "grad_norm": 0.06454802304506302,
456
+ "learning_rate": 1.389684813753582e-05,
457
+ "loss": 0.0096,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.620821394460363,
462
+ "grad_norm": 0.08184290677309036,
463
+ "learning_rate": 1.3801337153772685e-05,
464
+ "loss": 0.1253,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.6303724928366762,
469
+ "grad_norm": 0.07238755375146866,
470
+ "learning_rate": 1.3705826170009553e-05,
471
+ "loss": 0.0805,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.6399235912129895,
476
+ "grad_norm": 1.8935270309448242,
477
+ "learning_rate": 1.361031518624642e-05,
478
+ "loss": 0.1435,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.6494746895893028,
483
+ "grad_norm": 17.36036491394043,
484
+ "learning_rate": 1.3514804202483288e-05,
485
+ "loss": 0.0125,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.6590257879656161,
490
+ "grad_norm": 0.07514392584562302,
491
+ "learning_rate": 1.3419293218720153e-05,
492
+ "loss": 0.0106,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.6685768863419294,
497
+ "grad_norm": 4.228085041046143,
498
+ "learning_rate": 1.3323782234957021e-05,
499
+ "loss": 0.2031,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.6781279847182426,
504
+ "grad_norm": 0.21097038686275482,
505
+ "learning_rate": 1.322827125119389e-05,
506
+ "loss": 0.1307,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.6876790830945558,
511
+ "grad_norm": 0.10752805322408676,
512
+ "learning_rate": 1.3132760267430756e-05,
513
+ "loss": 0.0989,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.6972301814708691,
518
+ "grad_norm": 51.11091995239258,
519
+ "learning_rate": 1.3037249283667624e-05,
520
+ "loss": 0.1572,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.7067812798471824,
525
+ "grad_norm": 0.08639833331108093,
526
+ "learning_rate": 1.2941738299904489e-05,
527
+ "loss": 0.0508,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.7163323782234957,
532
+ "grad_norm": 0.09963525086641312,
533
+ "learning_rate": 1.2846227316141357e-05,
534
+ "loss": 0.0763,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.725883476599809,
539
+ "grad_norm": 0.0683053508400917,
540
+ "learning_rate": 1.2750716332378224e-05,
541
+ "loss": 0.0567,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.7354345749761223,
546
+ "grad_norm": 40.62727737426758,
547
+ "learning_rate": 1.2655205348615092e-05,
548
+ "loss": 0.2471,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.7449856733524355,
553
+ "grad_norm": 0.07331220805644989,
554
+ "learning_rate": 1.2559694364851959e-05,
555
+ "loss": 0.1743,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.7545367717287488,
560
+ "grad_norm": 0.06410760432481766,
561
+ "learning_rate": 1.2464183381088826e-05,
562
+ "loss": 0.0624,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.7640878701050621,
567
+ "grad_norm": 0.11088142544031143,
568
+ "learning_rate": 1.2368672397325694e-05,
569
+ "loss": 0.0087,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.7736389684813754,
574
+ "grad_norm": 0.05074993893504143,
575
+ "learning_rate": 1.227316141356256e-05,
576
+ "loss": 0.1333,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.7831900668576887,
581
+ "grad_norm": 0.05052105337381363,
582
+ "learning_rate": 1.2177650429799429e-05,
583
+ "loss": 0.0829,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.792741165234002,
588
+ "grad_norm": 0.06240995600819588,
589
+ "learning_rate": 1.2082139446036295e-05,
590
+ "loss": 0.0074,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.8022922636103151,
595
+ "grad_norm": 0.06128745898604393,
596
+ "learning_rate": 1.1986628462273162e-05,
597
+ "loss": 0.0705,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.8118433619866284,
602
+ "grad_norm": 4.010462760925293,
603
+ "learning_rate": 1.189111747851003e-05,
604
+ "loss": 0.1351,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.8213944603629417,
609
+ "grad_norm": 0.07143828272819519,
610
+ "learning_rate": 1.1795606494746897e-05,
611
+ "loss": 0.0514,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.830945558739255,
616
+ "grad_norm": 0.06396259367465973,
617
+ "learning_rate": 1.1700095510983764e-05,
618
+ "loss": 0.0713,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.8404966571155683,
623
+ "grad_norm": 14.529672622680664,
624
+ "learning_rate": 1.160458452722063e-05,
625
+ "loss": 0.0513,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.8500477554918816,
630
+ "grad_norm": 1.4704737663269043,
631
+ "learning_rate": 1.1509073543457498e-05,
632
+ "loss": 0.353,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.8595988538681948,
637
+ "grad_norm": 0.06813743710517883,
638
+ "learning_rate": 1.1413562559694367e-05,
639
+ "loss": 0.144,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.8691499522445081,
644
+ "grad_norm": 0.7163823843002319,
645
+ "learning_rate": 1.1318051575931233e-05,
646
+ "loss": 0.0415,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.8787010506208214,
651
+ "grad_norm": 0.05734021216630936,
652
+ "learning_rate": 1.12225405921681e-05,
653
+ "loss": 0.1911,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.8882521489971347,
658
+ "grad_norm": 0.06162785366177559,
659
+ "learning_rate": 1.1127029608404967e-05,
660
+ "loss": 0.0711,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.897803247373448,
665
+ "grad_norm": 0.1327008605003357,
666
+ "learning_rate": 1.1031518624641835e-05,
667
+ "loss": 0.058,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.9073543457497613,
672
+ "grad_norm": 0.05325314775109291,
673
+ "learning_rate": 1.0936007640878703e-05,
674
+ "loss": 0.0376,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.9169054441260746,
679
+ "grad_norm": 0.7295445799827576,
680
+ "learning_rate": 1.0840496657115568e-05,
681
+ "loss": 0.083,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.9264565425023877,
686
+ "grad_norm": 0.0540502592921257,
687
+ "learning_rate": 1.0744985673352436e-05,
688
+ "loss": 0.1386,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.936007640878701,
693
+ "grad_norm": 0.1747369021177292,
694
+ "learning_rate": 1.0649474689589303e-05,
695
+ "loss": 0.0063,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.9455587392550143,
700
+ "grad_norm": 0.04095704108476639,
701
+ "learning_rate": 1.0553963705826171e-05,
702
+ "loss": 0.0961,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.9551098376313276,
707
+ "grad_norm": 1.786160945892334,
708
+ "learning_rate": 1.0458452722063038e-05,
709
+ "loss": 0.2077,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.9646609360076409,
714
+ "grad_norm": 0.057904984802007675,
715
+ "learning_rate": 1.0362941738299905e-05,
716
+ "loss": 0.1009,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.9742120343839542,
721
+ "grad_norm": 0.04530341923236847,
722
+ "learning_rate": 1.0267430754536773e-05,
723
+ "loss": 0.0077,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.9837631327602674,
728
+ "grad_norm": 0.04884221404790878,
729
+ "learning_rate": 1.017191977077364e-05,
730
+ "loss": 0.0804,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.9933142311365807,
735
+ "grad_norm": 5.464759349822998,
736
+ "learning_rate": 1.0076408787010508e-05,
737
+ "loss": 0.1108,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 1.0,
742
+ "eval_loss": 0.10391418635845184,
743
+ "eval_runtime": 1.2229,
744
+ "eval_samples_per_second": 760.514,
745
+ "eval_steps_per_second": 95.678,
746
+ "step": 1047
747
+ },
748
+ {
749
+ "epoch": 1.002865329512894,
750
+ "grad_norm": 0.054792579263448715,
751
+ "learning_rate": 9.980897803247374e-06,
752
+ "loss": 0.0723,
753
+ "step": 1050
754
+ },
755
+ {
756
+ "epoch": 1.0124164278892072,
757
+ "grad_norm": 2.5259604454040527,
758
+ "learning_rate": 9.885386819484241e-06,
759
+ "loss": 0.074,
760
+ "step": 1060
761
+ },
762
+ {
763
+ "epoch": 1.0219675262655206,
764
+ "grad_norm": 0.06726188212633133,
765
+ "learning_rate": 9.78987583572111e-06,
766
+ "loss": 0.0709,
767
+ "step": 1070
768
+ },
769
+ {
770
+ "epoch": 1.0315186246418337,
771
+ "grad_norm": 0.05034675449132919,
772
+ "learning_rate": 9.694364851957976e-06,
773
+ "loss": 0.0072,
774
+ "step": 1080
775
+ },
776
+ {
777
+ "epoch": 1.0410697230181472,
778
+ "grad_norm": 1.9011842012405396,
779
+ "learning_rate": 9.598853868194843e-06,
780
+ "loss": 0.0803,
781
+ "step": 1090
782
+ },
783
+ {
784
+ "epoch": 1.0506208213944603,
785
+ "grad_norm": 0.05382240563631058,
786
+ "learning_rate": 9.50334288443171e-06,
787
+ "loss": 0.0247,
788
+ "step": 1100
789
+ },
790
+ {
791
+ "epoch": 1.0601719197707737,
792
+ "grad_norm": 0.22710120677947998,
793
+ "learning_rate": 9.407831900668578e-06,
794
+ "loss": 0.0061,
795
+ "step": 1110
796
+ },
797
+ {
798
+ "epoch": 1.069723018147087,
799
+ "grad_norm": 0.042488373816013336,
800
+ "learning_rate": 9.312320916905446e-06,
801
+ "loss": 0.1183,
802
+ "step": 1120
803
+ },
804
+ {
805
+ "epoch": 1.0792741165234,
806
+ "grad_norm": 2.047455072402954,
807
+ "learning_rate": 9.216809933142312e-06,
808
+ "loss": 0.0765,
809
+ "step": 1130
810
+ },
811
+ {
812
+ "epoch": 1.0888252148997135,
813
+ "grad_norm": 61.58501052856445,
814
+ "learning_rate": 9.121298949379179e-06,
815
+ "loss": 0.2333,
816
+ "step": 1140
817
+ },
818
+ {
819
+ "epoch": 1.0983763132760267,
820
+ "grad_norm": 0.06981759518384933,
821
+ "learning_rate": 9.025787965616046e-06,
822
+ "loss": 0.2329,
823
+ "step": 1150
824
+ },
825
+ {
826
+ "epoch": 1.10792741165234,
827
+ "grad_norm": 0.09120076149702072,
828
+ "learning_rate": 8.930276981852914e-06,
829
+ "loss": 0.0239,
830
+ "step": 1160
831
+ },
832
+ {
833
+ "epoch": 1.1174785100286533,
834
+ "grad_norm": 2.0684778690338135,
835
+ "learning_rate": 8.834765998089782e-06,
836
+ "loss": 0.0902,
837
+ "step": 1170
838
+ },
839
+ {
840
+ "epoch": 1.1270296084049667,
841
+ "grad_norm": 0.08632172644138336,
842
+ "learning_rate": 8.739255014326649e-06,
843
+ "loss": 0.1149,
844
+ "step": 1180
845
+ },
846
+ {
847
+ "epoch": 1.1365807067812799,
848
+ "grad_norm": 0.6690634489059448,
849
+ "learning_rate": 8.643744030563516e-06,
850
+ "loss": 0.0071,
851
+ "step": 1190
852
+ },
853
+ {
854
+ "epoch": 1.146131805157593,
855
+ "grad_norm": 0.09388808161020279,
856
+ "learning_rate": 8.548233046800382e-06,
857
+ "loss": 0.0717,
858
+ "step": 1200
859
+ },
860
+ {
861
+ "epoch": 1.1556829035339065,
862
+ "grad_norm": 0.06623850017786026,
863
+ "learning_rate": 8.45272206303725e-06,
864
+ "loss": 0.0866,
865
+ "step": 1210
866
+ },
867
+ {
868
+ "epoch": 1.1652340019102196,
869
+ "grad_norm": 0.05635674670338631,
870
+ "learning_rate": 8.357211079274117e-06,
871
+ "loss": 0.0914,
872
+ "step": 1220
873
+ },
874
+ {
875
+ "epoch": 1.174785100286533,
876
+ "grad_norm": 0.0588347390294075,
877
+ "learning_rate": 8.261700095510985e-06,
878
+ "loss": 0.0461,
879
+ "step": 1230
880
+ },
881
+ {
882
+ "epoch": 1.1843361986628462,
883
+ "grad_norm": 0.03934504836797714,
884
+ "learning_rate": 8.166189111747852e-06,
885
+ "loss": 0.1019,
886
+ "step": 1240
887
+ },
888
+ {
889
+ "epoch": 1.1938872970391594,
890
+ "grad_norm": 0.051371876150369644,
891
+ "learning_rate": 8.070678127984719e-06,
892
+ "loss": 0.016,
893
+ "step": 1250
894
+ },
895
+ {
896
+ "epoch": 1.2034383954154728,
897
+ "grad_norm": 0.061191458255052567,
898
+ "learning_rate": 7.975167144221587e-06,
899
+ "loss": 0.0077,
900
+ "step": 1260
901
+ },
902
+ {
903
+ "epoch": 1.212989493791786,
904
+ "grad_norm": 0.0495857410132885,
905
+ "learning_rate": 7.879656160458454e-06,
906
+ "loss": 0.0051,
907
+ "step": 1270
908
+ },
909
+ {
910
+ "epoch": 1.2225405921680994,
911
+ "grad_norm": 0.04128009453415871,
912
+ "learning_rate": 7.78414517669532e-06,
913
+ "loss": 0.317,
914
+ "step": 1280
915
+ },
916
+ {
917
+ "epoch": 1.2320916905444126,
918
+ "grad_norm": 0.03453819081187248,
919
+ "learning_rate": 7.688634192932188e-06,
920
+ "loss": 0.0608,
921
+ "step": 1290
922
+ },
923
+ {
924
+ "epoch": 1.2416427889207258,
925
+ "grad_norm": 0.03668952360749245,
926
+ "learning_rate": 7.593123209169055e-06,
927
+ "loss": 0.0264,
928
+ "step": 1300
929
+ },
930
+ {
931
+ "epoch": 1.2511938872970392,
932
+ "grad_norm": 0.03199330344796181,
933
+ "learning_rate": 7.4976122254059225e-06,
934
+ "loss": 0.0047,
935
+ "step": 1310
936
+ },
937
+ {
938
+ "epoch": 1.2607449856733524,
939
+ "grad_norm": 1.9187037944793701,
940
+ "learning_rate": 7.402101241642789e-06,
941
+ "loss": 0.1462,
942
+ "step": 1320
943
+ },
944
+ {
945
+ "epoch": 1.2702960840496658,
946
+ "grad_norm": 0.04411700740456581,
947
+ "learning_rate": 7.306590257879657e-06,
948
+ "loss": 0.0955,
949
+ "step": 1330
950
+ },
951
+ {
952
+ "epoch": 1.279847182425979,
953
+ "grad_norm": 0.03471948206424713,
954
+ "learning_rate": 7.211079274116523e-06,
955
+ "loss": 0.0062,
956
+ "step": 1340
957
+ },
958
+ {
959
+ "epoch": 1.2893982808022924,
960
+ "grad_norm": 0.042391568422317505,
961
+ "learning_rate": 7.115568290353391e-06,
962
+ "loss": 0.006,
963
+ "step": 1350
964
+ },
965
+ {
966
+ "epoch": 1.2989493791786055,
967
+ "grad_norm": 0.04176805168390274,
968
+ "learning_rate": 7.020057306590259e-06,
969
+ "loss": 0.1142,
970
+ "step": 1360
971
+ },
972
+ {
973
+ "epoch": 1.3085004775549187,
974
+ "grad_norm": 0.06825416535139084,
975
+ "learning_rate": 6.924546322827126e-06,
976
+ "loss": 0.1209,
977
+ "step": 1370
978
+ },
979
+ {
980
+ "epoch": 1.3180515759312321,
981
+ "grad_norm": 0.04017266258597374,
982
+ "learning_rate": 6.829035339063993e-06,
983
+ "loss": 0.0045,
984
+ "step": 1380
985
+ },
986
+ {
987
+ "epoch": 1.3276026743075453,
988
+ "grad_norm": 0.0732770562171936,
989
+ "learning_rate": 6.73352435530086e-06,
990
+ "loss": 0.1188,
991
+ "step": 1390
992
+ },
993
+ {
994
+ "epoch": 1.3371537726838587,
995
+ "grad_norm": 0.04319130256772041,
996
+ "learning_rate": 6.638013371537727e-06,
997
+ "loss": 0.007,
998
+ "step": 1400
999
+ },
1000
+ {
1001
+ "epoch": 1.346704871060172,
1002
+ "grad_norm": 0.08936483412981033,
1003
+ "learning_rate": 6.542502387774594e-06,
1004
+ "loss": 0.0118,
1005
+ "step": 1410
1006
+ },
1007
+ {
1008
+ "epoch": 1.3562559694364853,
1009
+ "grad_norm": 0.035478316247463226,
1010
+ "learning_rate": 6.446991404011462e-06,
1011
+ "loss": 0.0048,
1012
+ "step": 1420
1013
+ },
1014
+ {
1015
+ "epoch": 1.3658070678127985,
1016
+ "grad_norm": 0.10484705865383148,
1017
+ "learning_rate": 6.3514804202483295e-06,
1018
+ "loss": 0.0056,
1019
+ "step": 1430
1020
+ },
1021
+ {
1022
+ "epoch": 1.3753581661891117,
1023
+ "grad_norm": 0.03144150972366333,
1024
+ "learning_rate": 6.255969436485196e-06,
1025
+ "loss": 0.0758,
1026
+ "step": 1440
1027
+ },
1028
+ {
1029
+ "epoch": 1.384909264565425,
1030
+ "grad_norm": 0.12434408813714981,
1031
+ "learning_rate": 6.160458452722064e-06,
1032
+ "loss": 0.0049,
1033
+ "step": 1450
1034
+ },
1035
+ {
1036
+ "epoch": 1.3944603629417383,
1037
+ "grad_norm": 3.348506212234497,
1038
+ "learning_rate": 6.06494746895893e-06,
1039
+ "loss": 0.0309,
1040
+ "step": 1460
1041
+ },
1042
+ {
1043
+ "epoch": 1.4040114613180517,
1044
+ "grad_norm": 0.03951037675142288,
1045
+ "learning_rate": 5.969436485195798e-06,
1046
+ "loss": 0.0538,
1047
+ "step": 1470
1048
+ },
1049
+ {
1050
+ "epoch": 1.4135625596943648,
1051
+ "grad_norm": 0.04269490763545036,
1052
+ "learning_rate": 5.873925501432666e-06,
1053
+ "loss": 0.0044,
1054
+ "step": 1480
1055
+ },
1056
+ {
1057
+ "epoch": 1.4231136580706782,
1058
+ "grad_norm": 0.760600745677948,
1059
+ "learning_rate": 5.778414517669533e-06,
1060
+ "loss": 0.0973,
1061
+ "step": 1490
1062
+ },
1063
+ {
1064
+ "epoch": 1.4326647564469914,
1065
+ "grad_norm": 0.03149113059043884,
1066
+ "learning_rate": 5.6829035339064e-06,
1067
+ "loss": 0.0346,
1068
+ "step": 1500
1069
+ },
1070
+ {
1071
+ "epoch": 1.4422158548233046,
1072
+ "grad_norm": 0.05680393800139427,
1073
+ "learning_rate": 5.587392550143267e-06,
1074
+ "loss": 0.0043,
1075
+ "step": 1510
1076
+ },
1077
+ {
1078
+ "epoch": 1.451766953199618,
1079
+ "grad_norm": 0.03370094299316406,
1080
+ "learning_rate": 5.491881566380134e-06,
1081
+ "loss": 0.1295,
1082
+ "step": 1520
1083
+ },
1084
+ {
1085
+ "epoch": 1.4613180515759312,
1086
+ "grad_norm": 0.045079704374074936,
1087
+ "learning_rate": 5.396370582617001e-06,
1088
+ "loss": 0.0736,
1089
+ "step": 1530
1090
+ },
1091
+ {
1092
+ "epoch": 1.4708691499522444,
1093
+ "grad_norm": 0.7708030343055725,
1094
+ "learning_rate": 5.300859598853869e-06,
1095
+ "loss": 0.0042,
1096
+ "step": 1540
1097
+ },
1098
+ {
1099
+ "epoch": 1.4804202483285578,
1100
+ "grad_norm": 0.04070596769452095,
1101
+ "learning_rate": 5.2053486150907365e-06,
1102
+ "loss": 0.0301,
1103
+ "step": 1550
1104
+ },
1105
+ {
1106
+ "epoch": 1.4899713467048712,
1107
+ "grad_norm": 0.033276643604040146,
1108
+ "learning_rate": 5.109837631327603e-06,
1109
+ "loss": 0.0696,
1110
+ "step": 1560
1111
+ },
1112
+ {
1113
+ "epoch": 1.4995224450811844,
1114
+ "grad_norm": 0.04143739864230156,
1115
+ "learning_rate": 5.014326647564471e-06,
1116
+ "loss": 0.0753,
1117
+ "step": 1570
1118
+ },
1119
+ {
1120
+ "epoch": 1.5090735434574976,
1121
+ "grad_norm": 0.032175932079553604,
1122
+ "learning_rate": 4.918815663801337e-06,
1123
+ "loss": 0.1394,
1124
+ "step": 1580
1125
+ },
1126
+ {
1127
+ "epoch": 1.518624641833811,
1128
+ "grad_norm": 0.045357052236795425,
1129
+ "learning_rate": 4.823304680038205e-06,
1130
+ "loss": 0.0066,
1131
+ "step": 1590
1132
+ },
1133
+ {
1134
+ "epoch": 1.5281757402101241,
1135
+ "grad_norm": 0.04212405905127525,
1136
+ "learning_rate": 4.727793696275072e-06,
1137
+ "loss": 0.0758,
1138
+ "step": 1600
1139
+ },
1140
+ {
1141
+ "epoch": 1.5377268385864373,
1142
+ "grad_norm": 0.06627684831619263,
1143
+ "learning_rate": 4.632282712511939e-06,
1144
+ "loss": 0.0945,
1145
+ "step": 1610
1146
+ },
1147
+ {
1148
+ "epoch": 1.5472779369627507,
1149
+ "grad_norm": 0.04194959998130798,
1150
+ "learning_rate": 4.536771728748807e-06,
1151
+ "loss": 0.0046,
1152
+ "step": 1620
1153
+ },
1154
+ {
1155
+ "epoch": 1.5568290353390641,
1156
+ "grad_norm": 0.04786338284611702,
1157
+ "learning_rate": 4.441260744985674e-06,
1158
+ "loss": 0.0045,
1159
+ "step": 1630
1160
+ },
1161
+ {
1162
+ "epoch": 1.5663801337153773,
1163
+ "grad_norm": 0.030701184645295143,
1164
+ "learning_rate": 4.345749761222541e-06,
1165
+ "loss": 0.0699,
1166
+ "step": 1640
1167
+ },
1168
+ {
1169
+ "epoch": 1.5759312320916905,
1170
+ "grad_norm": 0.043966639786958694,
1171
+ "learning_rate": 4.250238777459409e-06,
1172
+ "loss": 0.122,
1173
+ "step": 1650
1174
+ },
1175
+ {
1176
+ "epoch": 1.585482330468004,
1177
+ "grad_norm": 0.04325714334845543,
1178
+ "learning_rate": 4.154727793696275e-06,
1179
+ "loss": 0.0051,
1180
+ "step": 1660
1181
+ },
1182
+ {
1183
+ "epoch": 1.595033428844317,
1184
+ "grad_norm": 0.03839458152651787,
1185
+ "learning_rate": 4.059216809933143e-06,
1186
+ "loss": 0.0041,
1187
+ "step": 1670
1188
+ },
1189
+ {
1190
+ "epoch": 1.6045845272206303,
1191
+ "grad_norm": 0.02976052649319172,
1192
+ "learning_rate": 3.96370582617001e-06,
1193
+ "loss": 0.0563,
1194
+ "step": 1680
1195
+ },
1196
+ {
1197
+ "epoch": 1.6141356255969437,
1198
+ "grad_norm": 55.89206314086914,
1199
+ "learning_rate": 3.868194842406877e-06,
1200
+ "loss": 0.0258,
1201
+ "step": 1690
1202
+ },
1203
+ {
1204
+ "epoch": 1.623686723973257,
1205
+ "grad_norm": 0.057242073118686676,
1206
+ "learning_rate": 3.772683858643744e-06,
1207
+ "loss": 0.0042,
1208
+ "step": 1700
1209
+ },
1210
+ {
1211
+ "epoch": 1.63323782234957,
1212
+ "grad_norm": 0.0714183896780014,
1213
+ "learning_rate": 3.6771728748806117e-06,
1214
+ "loss": 0.005,
1215
+ "step": 1710
1216
+ },
1217
+ {
1218
+ "epoch": 1.6427889207258835,
1219
+ "grad_norm": 0.0358208492398262,
1220
+ "learning_rate": 3.5816618911174787e-06,
1221
+ "loss": 0.0739,
1222
+ "step": 1720
1223
+ },
1224
+ {
1225
+ "epoch": 1.6523400191021969,
1226
+ "grad_norm": 0.039776891469955444,
1227
+ "learning_rate": 3.4861509073543457e-06,
1228
+ "loss": 0.0685,
1229
+ "step": 1730
1230
+ },
1231
+ {
1232
+ "epoch": 1.66189111747851,
1233
+ "grad_norm": 0.03394331783056259,
1234
+ "learning_rate": 3.3906399235912136e-06,
1235
+ "loss": 0.0794,
1236
+ "step": 1740
1237
+ },
1238
+ {
1239
+ "epoch": 1.6714422158548232,
1240
+ "grad_norm": 0.031364619731903076,
1241
+ "learning_rate": 3.2951289398280806e-06,
1242
+ "loss": 0.118,
1243
+ "step": 1750
1244
+ },
1245
+ {
1246
+ "epoch": 1.6809933142311366,
1247
+ "grad_norm": 2.0534205436706543,
1248
+ "learning_rate": 3.1996179560649477e-06,
1249
+ "loss": 0.1878,
1250
+ "step": 1760
1251
+ },
1252
+ {
1253
+ "epoch": 1.6905444126074498,
1254
+ "grad_norm": 0.038952384144067764,
1255
+ "learning_rate": 3.104106972301815e-06,
1256
+ "loss": 0.0738,
1257
+ "step": 1770
1258
+ },
1259
+ {
1260
+ "epoch": 1.700095510983763,
1261
+ "grad_norm": 0.029340583831071854,
1262
+ "learning_rate": 3.008595988538682e-06,
1263
+ "loss": 0.005,
1264
+ "step": 1780
1265
+ },
1266
+ {
1267
+ "epoch": 1.7096466093600764,
1268
+ "grad_norm": 0.04813091456890106,
1269
+ "learning_rate": 2.9130850047755492e-06,
1270
+ "loss": 0.0675,
1271
+ "step": 1790
1272
+ },
1273
+ {
1274
+ "epoch": 1.7191977077363898,
1275
+ "grad_norm": 0.05901302769780159,
1276
+ "learning_rate": 2.8175740210124163e-06,
1277
+ "loss": 0.0479,
1278
+ "step": 1800
1279
+ },
1280
+ {
1281
+ "epoch": 1.728748806112703,
1282
+ "grad_norm": 0.044173464179039,
1283
+ "learning_rate": 2.722063037249284e-06,
1284
+ "loss": 0.0423,
1285
+ "step": 1810
1286
+ },
1287
+ {
1288
+ "epoch": 1.7382999044890162,
1289
+ "grad_norm": 0.03839905560016632,
1290
+ "learning_rate": 2.626552053486151e-06,
1291
+ "loss": 0.1425,
1292
+ "step": 1820
1293
+ },
1294
+ {
1295
+ "epoch": 1.7478510028653296,
1296
+ "grad_norm": 0.059842657297849655,
1297
+ "learning_rate": 2.5310410697230182e-06,
1298
+ "loss": 0.0042,
1299
+ "step": 1830
1300
+ },
1301
+ {
1302
+ "epoch": 1.7574021012416428,
1303
+ "grad_norm": 0.24521498382091522,
1304
+ "learning_rate": 2.4355300859598857e-06,
1305
+ "loss": 0.0525,
1306
+ "step": 1840
1307
+ },
1308
+ {
1309
+ "epoch": 1.766953199617956,
1310
+ "grad_norm": 0.5483675003051758,
1311
+ "learning_rate": 2.3400191021967527e-06,
1312
+ "loss": 0.0752,
1313
+ "step": 1850
1314
+ },
1315
+ {
1316
+ "epoch": 1.7765042979942693,
1317
+ "grad_norm": 0.036952149122953415,
1318
+ "learning_rate": 2.24450811843362e-06,
1319
+ "loss": 0.1074,
1320
+ "step": 1860
1321
+ },
1322
+ {
1323
+ "epoch": 1.7860553963705827,
1324
+ "grad_norm": 0.8135057091712952,
1325
+ "learning_rate": 2.1489971346704872e-06,
1326
+ "loss": 0.0048,
1327
+ "step": 1870
1328
+ },
1329
+ {
1330
+ "epoch": 1.795606494746896,
1331
+ "grad_norm": 0.06449055671691895,
1332
+ "learning_rate": 2.0534861509073547e-06,
1333
+ "loss": 0.1038,
1334
+ "step": 1880
1335
+ },
1336
+ {
1337
+ "epoch": 1.8051575931232091,
1338
+ "grad_norm": 107.41304779052734,
1339
+ "learning_rate": 1.9579751671442217e-06,
1340
+ "loss": 0.0318,
1341
+ "step": 1890
1342
+ },
1343
+ {
1344
+ "epoch": 1.8147086914995225,
1345
+ "grad_norm": 0.04807087033987045,
1346
+ "learning_rate": 1.862464183381089e-06,
1347
+ "loss": 0.1689,
1348
+ "step": 1900
1349
+ },
1350
+ {
1351
+ "epoch": 1.8242597898758357,
1352
+ "grad_norm": 0.04132077470421791,
1353
+ "learning_rate": 1.7669531996179562e-06,
1354
+ "loss": 0.0041,
1355
+ "step": 1910
1356
+ },
1357
+ {
1358
+ "epoch": 1.8338108882521489,
1359
+ "grad_norm": 0.06250818073749542,
1360
+ "learning_rate": 1.6714422158548235e-06,
1361
+ "loss": 0.0052,
1362
+ "step": 1920
1363
+ },
1364
+ {
1365
+ "epoch": 1.8433619866284623,
1366
+ "grad_norm": 83.07594299316406,
1367
+ "learning_rate": 1.5759312320916905e-06,
1368
+ "loss": 0.174,
1369
+ "step": 1930
1370
+ },
1371
+ {
1372
+ "epoch": 1.8529130850047757,
1373
+ "grad_norm": 0.04571348428726196,
1374
+ "learning_rate": 1.480420248328558e-06,
1375
+ "loss": 0.0049,
1376
+ "step": 1940
1377
+ },
1378
+ {
1379
+ "epoch": 1.8624641833810889,
1380
+ "grad_norm": 0.04580092057585716,
1381
+ "learning_rate": 1.3849092645654252e-06,
1382
+ "loss": 0.0638,
1383
+ "step": 1950
1384
+ },
1385
+ {
1386
+ "epoch": 1.872015281757402,
1387
+ "grad_norm": 0.04569645971059799,
1388
+ "learning_rate": 1.2893982808022922e-06,
1389
+ "loss": 0.0551,
1390
+ "step": 1960
1391
+ },
1392
+ {
1393
+ "epoch": 1.8815663801337155,
1394
+ "grad_norm": 0.049619242548942566,
1395
+ "learning_rate": 1.1938872970391597e-06,
1396
+ "loss": 0.0436,
1397
+ "step": 1970
1398
+ },
1399
+ {
1400
+ "epoch": 1.8911174785100286,
1401
+ "grad_norm": 0.059808436781167984,
1402
+ "learning_rate": 1.0983763132760267e-06,
1403
+ "loss": 0.0653,
1404
+ "step": 1980
1405
+ },
1406
+ {
1407
+ "epoch": 1.9006685768863418,
1408
+ "grad_norm": 0.038019582629203796,
1409
+ "learning_rate": 1.002865329512894e-06,
1410
+ "loss": 0.0632,
1411
+ "step": 1990
1412
+ },
1413
+ {
1414
+ "epoch": 1.9102196752626552,
1415
+ "grad_norm": 0.037652261555194855,
1416
+ "learning_rate": 9.073543457497613e-07,
1417
+ "loss": 0.0676,
1418
+ "step": 2000
1419
+ },
1420
+ {
1421
+ "epoch": 1.9197707736389686,
1422
+ "grad_norm": 0.0339687243103981,
1423
+ "learning_rate": 8.118433619866285e-07,
1424
+ "loss": 0.0048,
1425
+ "step": 2010
1426
+ },
1427
+ {
1428
+ "epoch": 1.9293218720152816,
1429
+ "grad_norm": 0.043730951845645905,
1430
+ "learning_rate": 7.163323782234957e-07,
1431
+ "loss": 0.005,
1432
+ "step": 2020
1433
+ },
1434
+ {
1435
+ "epoch": 1.938872970391595,
1436
+ "grad_norm": 0.044012073427438736,
1437
+ "learning_rate": 6.20821394460363e-07,
1438
+ "loss": 0.0738,
1439
+ "step": 2030
1440
+ },
1441
+ {
1442
+ "epoch": 1.9484240687679084,
1443
+ "grad_norm": 0.34402212500572205,
1444
+ "learning_rate": 5.253104106972302e-07,
1445
+ "loss": 0.0062,
1446
+ "step": 2040
1447
+ },
1448
+ {
1449
+ "epoch": 1.9579751671442216,
1450
+ "grad_norm": 0.06250176578760147,
1451
+ "learning_rate": 4.2979942693409743e-07,
1452
+ "loss": 0.0665,
1453
+ "step": 2050
1454
+ },
1455
+ {
1456
+ "epoch": 1.9675262655205348,
1457
+ "grad_norm": 0.06154881417751312,
1458
+ "learning_rate": 3.342884431709647e-07,
1459
+ "loss": 0.0266,
1460
+ "step": 2060
1461
+ },
1462
+ {
1463
+ "epoch": 1.9770773638968482,
1464
+ "grad_norm": 0.038224026560783386,
1465
+ "learning_rate": 2.3877745940783193e-07,
1466
+ "loss": 0.0039,
1467
+ "step": 2070
1468
+ },
1469
+ {
1470
+ "epoch": 1.9866284622731614,
1471
+ "grad_norm": 0.668195903301239,
1472
+ "learning_rate": 1.4326647564469915e-07,
1473
+ "loss": 0.0162,
1474
+ "step": 2080
1475
+ },
1476
+ {
1477
+ "epoch": 1.9961795606494745,
1478
+ "grad_norm": 0.048277534544467926,
1479
+ "learning_rate": 4.775549188156639e-08,
1480
+ "loss": 0.0049,
1481
+ "step": 2090
1482
+ },
1483
+ {
1484
+ "epoch": 2.0,
1485
+ "eval_loss": 0.10492703318595886,
1486
+ "eval_runtime": 1.2317,
1487
+ "eval_samples_per_second": 755.069,
1488
+ "eval_steps_per_second": 94.993,
1489
+ "step": 2094
1490
+ }
1491
+ ],
1492
+ "logging_steps": 10,
1493
+ "max_steps": 2094,
1494
+ "num_input_tokens_seen": 0,
1495
+ "num_train_epochs": 2,
1496
+ "save_steps": 500,
1497
+ "stateful_callbacks": {
1498
+ "TrainerControl": {
1499
+ "args": {
1500
+ "should_epoch_stop": false,
1501
+ "should_evaluate": false,
1502
+ "should_log": false,
1503
+ "should_save": true,
1504
+ "should_training_stop": true
1505
+ },
1506
+ "attributes": {}
1507
+ }
1508
+ },
1509
+ "total_flos": 4403992385931264.0,
1510
+ "train_batch_size": 8,
1511
+ "trial_name": null,
1512
+ "trial_params": null
1513
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e107af7772db058e45d6d0cf99542c27d441f5d52c5a9ea05b5f3b98e4b63cb6
3
+ size 5841