eljavatar commited on
Commit
a5f479d
1 Parent(s): 3166f32

Upload model finetuned on utg4java-220m using strategy src_fm_fc_dctx

Browse files
README.md CHANGED
@@ -1,3 +1,50 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bsd-3-clause
3
+ base_model: eljavatar/pretrain_utg4java_codet5p
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: finetuning_04_utg4java_src_fm_fc_dctx
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # finetuning_04_utg4java_src_fm_fc_dctx
15
+
16
+ This model is a fine-tuned version of [eljavatar/pretrain_utg4java_codet5p](https://huggingface.co/eljavatar/pretrain_utg4java_codet5p) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 32
37
+ - eval_batch_size: 64
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_steps: 800
42
+ - num_epochs: 5
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Framework versions
46
+
47
+ - Transformers 4.38.2
48
+ - Pytorch 2.1.0
49
+ - Datasets 2.20.0
50
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</ECTX>": 32103,
3
+ "</FCTX>": 32101,
4
+ "</PRIVATE_FCTX>": 32105,
5
+ "<ECTX>": 32102,
6
+ "<FCTX>": 32100,
7
+ "<PRIVATE_FCTX>": 32104
8
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "eljavatar/pretrain_utg4java_codet5p",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": false,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.2",
31
+ "use_cache": true,
32
+ "vocab_size": 32106
33
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.38.2"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90311733d52a43da9e4b018287b1bc2b4b5aa601211029bebdd30ff4f10e4c04
3
+ size 891635790
special_tokens_map.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<FCTX>",
4
+ "</FCTX>",
5
+ "<ECTX>",
6
+ "</ECTX>",
7
+ "<PRIVATE_FCTX>",
8
+ "</PRIVATE_FCTX>"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "cls_token": {
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "eos_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "mask_token": {
32
+ "content": "<mask>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "pad_token": {
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "sep_token": {
46
+ "content": "</s>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ "unk_token": {
53
+ "content": "<unk>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ }
59
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,917 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32000": {
45
+ "content": "<extra_id_99>",
46
+ "lstrip": true,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32001": {
53
+ "content": "<extra_id_98>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32002": {
61
+ "content": "<extra_id_97>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32003": {
69
+ "content": "<extra_id_96>",
70
+ "lstrip": true,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32004": {
77
+ "content": "<extra_id_95>",
78
+ "lstrip": true,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32005": {
85
+ "content": "<extra_id_94>",
86
+ "lstrip": true,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32006": {
93
+ "content": "<extra_id_93>",
94
+ "lstrip": true,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32007": {
101
+ "content": "<extra_id_92>",
102
+ "lstrip": true,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32008": {
109
+ "content": "<extra_id_91>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32009": {
117
+ "content": "<extra_id_90>",
118
+ "lstrip": true,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32010": {
125
+ "content": "<extra_id_89>",
126
+ "lstrip": true,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32011": {
133
+ "content": "<extra_id_88>",
134
+ "lstrip": true,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32012": {
141
+ "content": "<extra_id_87>",
142
+ "lstrip": true,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32013": {
149
+ "content": "<extra_id_86>",
150
+ "lstrip": true,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32014": {
157
+ "content": "<extra_id_85>",
158
+ "lstrip": true,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32015": {
165
+ "content": "<extra_id_84>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32016": {
173
+ "content": "<extra_id_83>",
174
+ "lstrip": true,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32017": {
181
+ "content": "<extra_id_82>",
182
+ "lstrip": true,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32018": {
189
+ "content": "<extra_id_81>",
190
+ "lstrip": true,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32019": {
197
+ "content": "<extra_id_80>",
198
+ "lstrip": true,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32020": {
205
+ "content": "<extra_id_79>",
206
+ "lstrip": true,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32021": {
213
+ "content": "<extra_id_78>",
214
+ "lstrip": true,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32022": {
221
+ "content": "<extra_id_77>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32023": {
229
+ "content": "<extra_id_76>",
230
+ "lstrip": true,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32024": {
237
+ "content": "<extra_id_75>",
238
+ "lstrip": true,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32025": {
245
+ "content": "<extra_id_74>",
246
+ "lstrip": true,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32026": {
253
+ "content": "<extra_id_73>",
254
+ "lstrip": true,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32027": {
261
+ "content": "<extra_id_72>",
262
+ "lstrip": true,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32028": {
269
+ "content": "<extra_id_71>",
270
+ "lstrip": true,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32029": {
277
+ "content": "<extra_id_70>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32030": {
285
+ "content": "<extra_id_69>",
286
+ "lstrip": true,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32031": {
293
+ "content": "<extra_id_68>",
294
+ "lstrip": true,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32032": {
301
+ "content": "<extra_id_67>",
302
+ "lstrip": true,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32033": {
309
+ "content": "<extra_id_66>",
310
+ "lstrip": true,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32034": {
317
+ "content": "<extra_id_65>",
318
+ "lstrip": true,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32035": {
325
+ "content": "<extra_id_64>",
326
+ "lstrip": true,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32036": {
333
+ "content": "<extra_id_63>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32037": {
341
+ "content": "<extra_id_62>",
342
+ "lstrip": true,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32038": {
349
+ "content": "<extra_id_61>",
350
+ "lstrip": true,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32039": {
357
+ "content": "<extra_id_60>",
358
+ "lstrip": true,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32040": {
365
+ "content": "<extra_id_59>",
366
+ "lstrip": true,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32041": {
373
+ "content": "<extra_id_58>",
374
+ "lstrip": true,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32042": {
381
+ "content": "<extra_id_57>",
382
+ "lstrip": true,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32043": {
389
+ "content": "<extra_id_56>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32044": {
397
+ "content": "<extra_id_55>",
398
+ "lstrip": true,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32045": {
405
+ "content": "<extra_id_54>",
406
+ "lstrip": true,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32046": {
413
+ "content": "<extra_id_53>",
414
+ "lstrip": true,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32047": {
421
+ "content": "<extra_id_52>",
422
+ "lstrip": true,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32048": {
429
+ "content": "<extra_id_51>",
430
+ "lstrip": true,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32049": {
437
+ "content": "<extra_id_50>",
438
+ "lstrip": true,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32050": {
445
+ "content": "<extra_id_49>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32051": {
453
+ "content": "<extra_id_48>",
454
+ "lstrip": true,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32052": {
461
+ "content": "<extra_id_47>",
462
+ "lstrip": true,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32053": {
469
+ "content": "<extra_id_46>",
470
+ "lstrip": true,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32054": {
477
+ "content": "<extra_id_45>",
478
+ "lstrip": true,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32055": {
485
+ "content": "<extra_id_44>",
486
+ "lstrip": true,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32056": {
493
+ "content": "<extra_id_43>",
494
+ "lstrip": true,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32057": {
501
+ "content": "<extra_id_42>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32058": {
509
+ "content": "<extra_id_41>",
510
+ "lstrip": true,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32059": {
517
+ "content": "<extra_id_40>",
518
+ "lstrip": true,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32060": {
525
+ "content": "<extra_id_39>",
526
+ "lstrip": true,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32061": {
533
+ "content": "<extra_id_38>",
534
+ "lstrip": true,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32062": {
541
+ "content": "<extra_id_37>",
542
+ "lstrip": true,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32063": {
549
+ "content": "<extra_id_36>",
550
+ "lstrip": true,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32064": {
557
+ "content": "<extra_id_35>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32065": {
565
+ "content": "<extra_id_34>",
566
+ "lstrip": true,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32066": {
573
+ "content": "<extra_id_33>",
574
+ "lstrip": true,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32067": {
581
+ "content": "<extra_id_32>",
582
+ "lstrip": true,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32068": {
589
+ "content": "<extra_id_31>",
590
+ "lstrip": true,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32069": {
597
+ "content": "<extra_id_30>",
598
+ "lstrip": true,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32070": {
605
+ "content": "<extra_id_29>",
606
+ "lstrip": true,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32071": {
613
+ "content": "<extra_id_28>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32072": {
621
+ "content": "<extra_id_27>",
622
+ "lstrip": true,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32073": {
629
+ "content": "<extra_id_26>",
630
+ "lstrip": true,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32074": {
637
+ "content": "<extra_id_25>",
638
+ "lstrip": true,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32075": {
645
+ "content": "<extra_id_24>",
646
+ "lstrip": true,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32076": {
653
+ "content": "<extra_id_23>",
654
+ "lstrip": true,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32077": {
661
+ "content": "<extra_id_22>",
662
+ "lstrip": true,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32078": {
669
+ "content": "<extra_id_21>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32079": {
677
+ "content": "<extra_id_20>",
678
+ "lstrip": true,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32080": {
685
+ "content": "<extra_id_19>",
686
+ "lstrip": true,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32081": {
693
+ "content": "<extra_id_18>",
694
+ "lstrip": true,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32082": {
701
+ "content": "<extra_id_17>",
702
+ "lstrip": true,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32083": {
709
+ "content": "<extra_id_16>",
710
+ "lstrip": true,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32084": {
717
+ "content": "<extra_id_15>",
718
+ "lstrip": true,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32085": {
725
+ "content": "<extra_id_14>",
726
+ "lstrip": true,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32086": {
733
+ "content": "<extra_id_13>",
734
+ "lstrip": true,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32087": {
741
+ "content": "<extra_id_12>",
742
+ "lstrip": true,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32088": {
749
+ "content": "<extra_id_11>",
750
+ "lstrip": true,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32089": {
757
+ "content": "<extra_id_10>",
758
+ "lstrip": true,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32090": {
765
+ "content": "<extra_id_9>",
766
+ "lstrip": true,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32091": {
773
+ "content": "<extra_id_8>",
774
+ "lstrip": true,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32092": {
781
+ "content": "<extra_id_7>",
782
+ "lstrip": true,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32093": {
789
+ "content": "<extra_id_6>",
790
+ "lstrip": true,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32094": {
797
+ "content": "<extra_id_5>",
798
+ "lstrip": true,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32095": {
805
+ "content": "<extra_id_4>",
806
+ "lstrip": true,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32096": {
813
+ "content": "<extra_id_3>",
814
+ "lstrip": true,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32097": {
821
+ "content": "<extra_id_2>",
822
+ "lstrip": true,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32098": {
829
+ "content": "<extra_id_1>",
830
+ "lstrip": true,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32099": {
837
+ "content": "<extra_id_0>",
838
+ "lstrip": true,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "32100": {
845
+ "content": "<FCTX>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "32101": {
853
+ "content": "</FCTX>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "32102": {
861
+ "content": "<ECTX>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "32103": {
869
+ "content": "</ECTX>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "32104": {
877
+ "content": "<PRIVATE_FCTX>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "32105": {
885
+ "content": "</PRIVATE_FCTX>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ }
892
+ },
893
+ "additional_special_tokens": [
894
+ "<FCTX>",
895
+ "</FCTX>",
896
+ "<ECTX>",
897
+ "</ECTX>",
898
+ "<PRIVATE_FCTX>",
899
+ "</PRIVATE_FCTX>"
900
+ ],
901
+ "bos_token": "<s>",
902
+ "clean_up_tokenization_spaces": true,
903
+ "cls_token": "<s>",
904
+ "eos_token": "</s>",
905
+ "errors": "replace",
906
+ "mask_token": "<mask>",
907
+ "max_length": 512,
908
+ "model_max_length": 512,
909
+ "pad_token": "<pad>",
910
+ "sep_token": "</s>",
911
+ "stride": 0,
912
+ "tokenizer_class": "RobertaTokenizer",
913
+ "trim_offsets": true,
914
+ "truncation_side": "right",
915
+ "truncation_strategy": "longest_first",
916
+ "unk_token": "<unk>"
917
+ }
trainer_state.json ADDED
@@ -0,0 +1,1603 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1765093803405762,
3
+ "best_model_checkpoint": "/root/finetuning_executions/finetuning_04_utg4java_src_fm_fc_dctx/checkpoint-52644",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 87740,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 2.022568941116333,
14
+ "learning_rate": 2.45625e-05,
15
+ "loss": 3.9615,
16
+ "step": 400
17
+ },
18
+ {
19
+ "epoch": 0.05,
20
+ "grad_norm": 1.4656506776809692,
21
+ "learning_rate": 4.95625e-05,
22
+ "loss": 1.7529,
23
+ "step": 800
24
+ },
25
+ {
26
+ "epoch": 0.07,
27
+ "grad_norm": 1.1944507360458374,
28
+ "learning_rate": 4.977398205659076e-05,
29
+ "loss": 1.544,
30
+ "step": 1200
31
+ },
32
+ {
33
+ "epoch": 0.09,
34
+ "grad_norm": 1.3468198776245117,
35
+ "learning_rate": 4.954393834828618e-05,
36
+ "loss": 1.4706,
37
+ "step": 1600
38
+ },
39
+ {
40
+ "epoch": 0.11,
41
+ "grad_norm": 1.04371178150177,
42
+ "learning_rate": 4.93138946399816e-05,
43
+ "loss": 1.4141,
44
+ "step": 2000
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "grad_norm": 1.1084234714508057,
49
+ "learning_rate": 4.908385093167702e-05,
50
+ "loss": 1.376,
51
+ "step": 2400
52
+ },
53
+ {
54
+ "epoch": 0.16,
55
+ "grad_norm": 1.1234780550003052,
56
+ "learning_rate": 4.885380722337244e-05,
57
+ "loss": 1.3424,
58
+ "step": 2800
59
+ },
60
+ {
61
+ "epoch": 0.18,
62
+ "grad_norm": 1.5502243041992188,
63
+ "learning_rate": 4.8623763515067866e-05,
64
+ "loss": 1.3219,
65
+ "step": 3200
66
+ },
67
+ {
68
+ "epoch": 0.21,
69
+ "grad_norm": 1.0266711711883545,
70
+ "learning_rate": 4.839371980676329e-05,
71
+ "loss": 1.2912,
72
+ "step": 3600
73
+ },
74
+ {
75
+ "epoch": 0.23,
76
+ "grad_norm": 1.1499156951904297,
77
+ "learning_rate": 4.816367609845871e-05,
78
+ "loss": 1.2708,
79
+ "step": 4000
80
+ },
81
+ {
82
+ "epoch": 0.25,
83
+ "grad_norm": 1.2277108430862427,
84
+ "learning_rate": 4.7933632390154135e-05,
85
+ "loss": 1.266,
86
+ "step": 4400
87
+ },
88
+ {
89
+ "epoch": 0.27,
90
+ "grad_norm": 1.151228427886963,
91
+ "learning_rate": 4.770358868184955e-05,
92
+ "loss": 1.2418,
93
+ "step": 4800
94
+ },
95
+ {
96
+ "epoch": 0.3,
97
+ "grad_norm": 1.230625867843628,
98
+ "learning_rate": 4.7473544973544974e-05,
99
+ "loss": 1.2383,
100
+ "step": 5200
101
+ },
102
+ {
103
+ "epoch": 0.32,
104
+ "grad_norm": 0.9033710360527039,
105
+ "learning_rate": 4.72435012652404e-05,
106
+ "loss": 1.2078,
107
+ "step": 5600
108
+ },
109
+ {
110
+ "epoch": 0.34,
111
+ "grad_norm": 0.9645096659660339,
112
+ "learning_rate": 4.701345755693582e-05,
113
+ "loss": 1.1893,
114
+ "step": 6000
115
+ },
116
+ {
117
+ "epoch": 0.36,
118
+ "grad_norm": 1.1617854833602905,
119
+ "learning_rate": 4.678341384863124e-05,
120
+ "loss": 1.1773,
121
+ "step": 6400
122
+ },
123
+ {
124
+ "epoch": 0.39,
125
+ "grad_norm": 0.9844051003456116,
126
+ "learning_rate": 4.6553370140326666e-05,
127
+ "loss": 1.1652,
128
+ "step": 6800
129
+ },
130
+ {
131
+ "epoch": 0.41,
132
+ "grad_norm": 0.9416425824165344,
133
+ "learning_rate": 4.632332643202208e-05,
134
+ "loss": 1.1752,
135
+ "step": 7200
136
+ },
137
+ {
138
+ "epoch": 0.43,
139
+ "grad_norm": 1.103413701057434,
140
+ "learning_rate": 4.6093282723717505e-05,
141
+ "loss": 1.1423,
142
+ "step": 7600
143
+ },
144
+ {
145
+ "epoch": 0.46,
146
+ "grad_norm": 1.1644244194030762,
147
+ "learning_rate": 4.586323901541293e-05,
148
+ "loss": 1.1412,
149
+ "step": 8000
150
+ },
151
+ {
152
+ "epoch": 0.48,
153
+ "grad_norm": 0.9481434226036072,
154
+ "learning_rate": 4.563319530710835e-05,
155
+ "loss": 1.1406,
156
+ "step": 8400
157
+ },
158
+ {
159
+ "epoch": 0.5,
160
+ "grad_norm": 1.1336678266525269,
161
+ "learning_rate": 4.5403151598803774e-05,
162
+ "loss": 1.1247,
163
+ "step": 8800
164
+ },
165
+ {
166
+ "epoch": 0.52,
167
+ "grad_norm": 1.1613398790359497,
168
+ "learning_rate": 4.51731078904992e-05,
169
+ "loss": 1.1139,
170
+ "step": 9200
171
+ },
172
+ {
173
+ "epoch": 0.55,
174
+ "grad_norm": 0.9106454849243164,
175
+ "learning_rate": 4.494306418219462e-05,
176
+ "loss": 1.1018,
177
+ "step": 9600
178
+ },
179
+ {
180
+ "epoch": 0.57,
181
+ "grad_norm": 1.121297001838684,
182
+ "learning_rate": 4.471302047389004e-05,
183
+ "loss": 1.093,
184
+ "step": 10000
185
+ },
186
+ {
187
+ "epoch": 0.59,
188
+ "grad_norm": 1.2510058879852295,
189
+ "learning_rate": 4.4482976765585466e-05,
190
+ "loss": 1.0772,
191
+ "step": 10400
192
+ },
193
+ {
194
+ "epoch": 0.62,
195
+ "grad_norm": 1.0042085647583008,
196
+ "learning_rate": 4.425293305728089e-05,
197
+ "loss": 1.0952,
198
+ "step": 10800
199
+ },
200
+ {
201
+ "epoch": 0.64,
202
+ "grad_norm": 0.9691294431686401,
203
+ "learning_rate": 4.402288934897631e-05,
204
+ "loss": 1.0728,
205
+ "step": 11200
206
+ },
207
+ {
208
+ "epoch": 0.66,
209
+ "grad_norm": 0.900873064994812,
210
+ "learning_rate": 4.379284564067173e-05,
211
+ "loss": 1.0683,
212
+ "step": 11600
213
+ },
214
+ {
215
+ "epoch": 0.68,
216
+ "grad_norm": 0.942535936832428,
217
+ "learning_rate": 4.356280193236715e-05,
218
+ "loss": 1.0574,
219
+ "step": 12000
220
+ },
221
+ {
222
+ "epoch": 0.71,
223
+ "grad_norm": 0.9630743265151978,
224
+ "learning_rate": 4.3332758224062574e-05,
225
+ "loss": 1.0626,
226
+ "step": 12400
227
+ },
228
+ {
229
+ "epoch": 0.73,
230
+ "grad_norm": 0.9657124280929565,
231
+ "learning_rate": 4.3102714515758e-05,
232
+ "loss": 1.0664,
233
+ "step": 12800
234
+ },
235
+ {
236
+ "epoch": 0.75,
237
+ "grad_norm": 1.0142230987548828,
238
+ "learning_rate": 4.287267080745342e-05,
239
+ "loss": 1.0421,
240
+ "step": 13200
241
+ },
242
+ {
243
+ "epoch": 0.78,
244
+ "grad_norm": 1.021824598312378,
245
+ "learning_rate": 4.264262709914884e-05,
246
+ "loss": 1.0393,
247
+ "step": 13600
248
+ },
249
+ {
250
+ "epoch": 0.8,
251
+ "grad_norm": 0.866675853729248,
252
+ "learning_rate": 4.241258339084426e-05,
253
+ "loss": 1.0398,
254
+ "step": 14000
255
+ },
256
+ {
257
+ "epoch": 0.82,
258
+ "grad_norm": 1.0492345094680786,
259
+ "learning_rate": 4.218253968253968e-05,
260
+ "loss": 1.0266,
261
+ "step": 14400
262
+ },
263
+ {
264
+ "epoch": 0.84,
265
+ "grad_norm": 1.1229575872421265,
266
+ "learning_rate": 4.1953071083505865e-05,
267
+ "loss": 1.0328,
268
+ "step": 14800
269
+ },
270
+ {
271
+ "epoch": 0.87,
272
+ "grad_norm": 0.9247739315032959,
273
+ "learning_rate": 4.172302737520129e-05,
274
+ "loss": 1.033,
275
+ "step": 15200
276
+ },
277
+ {
278
+ "epoch": 0.89,
279
+ "grad_norm": 0.8983958959579468,
280
+ "learning_rate": 4.149298366689671e-05,
281
+ "loss": 1.0075,
282
+ "step": 15600
283
+ },
284
+ {
285
+ "epoch": 0.91,
286
+ "grad_norm": 0.9420925974845886,
287
+ "learning_rate": 4.1262939958592134e-05,
288
+ "loss": 1.0005,
289
+ "step": 16000
290
+ },
291
+ {
292
+ "epoch": 0.93,
293
+ "grad_norm": 0.9218415021896362,
294
+ "learning_rate": 4.103289625028756e-05,
295
+ "loss": 1.0117,
296
+ "step": 16400
297
+ },
298
+ {
299
+ "epoch": 0.96,
300
+ "grad_norm": 0.9700437784194946,
301
+ "learning_rate": 4.080285254198298e-05,
302
+ "loss": 1.0018,
303
+ "step": 16800
304
+ },
305
+ {
306
+ "epoch": 0.98,
307
+ "grad_norm": 0.9360381960868835,
308
+ "learning_rate": 4.0572808833678396e-05,
309
+ "loss": 0.9986,
310
+ "step": 17200
311
+ },
312
+ {
313
+ "epoch": 1.0,
314
+ "eval_loss": 1.2005890607833862,
315
+ "eval_runtime": 368.0591,
316
+ "eval_samples_per_second": 163.764,
317
+ "eval_steps_per_second": 2.559,
318
+ "step": 17548
319
+ },
320
+ {
321
+ "epoch": 1.0,
322
+ "grad_norm": 0.8369306921958923,
323
+ "learning_rate": 4.034276512537382e-05,
324
+ "loss": 0.9929,
325
+ "step": 17600
326
+ },
327
+ {
328
+ "epoch": 1.03,
329
+ "grad_norm": 0.9470133781433105,
330
+ "learning_rate": 4.011272141706924e-05,
331
+ "loss": 0.9462,
332
+ "step": 18000
333
+ },
334
+ {
335
+ "epoch": 1.05,
336
+ "grad_norm": 0.9572529196739197,
337
+ "learning_rate": 3.9882677708764665e-05,
338
+ "loss": 0.95,
339
+ "step": 18400
340
+ },
341
+ {
342
+ "epoch": 1.07,
343
+ "grad_norm": 1.0236432552337646,
344
+ "learning_rate": 3.965263400046009e-05,
345
+ "loss": 0.947,
346
+ "step": 18800
347
+ },
348
+ {
349
+ "epoch": 1.09,
350
+ "grad_norm": 1.105034589767456,
351
+ "learning_rate": 3.942259029215551e-05,
352
+ "loss": 0.9382,
353
+ "step": 19200
354
+ },
355
+ {
356
+ "epoch": 1.12,
357
+ "grad_norm": 1.322292447090149,
358
+ "learning_rate": 3.9192546583850934e-05,
359
+ "loss": 0.941,
360
+ "step": 19600
361
+ },
362
+ {
363
+ "epoch": 1.14,
364
+ "grad_norm": 1.137208104133606,
365
+ "learning_rate": 3.896250287554636e-05,
366
+ "loss": 0.9247,
367
+ "step": 20000
368
+ },
369
+ {
370
+ "epoch": 1.16,
371
+ "grad_norm": 1.1079697608947754,
372
+ "learning_rate": 3.873245916724178e-05,
373
+ "loss": 0.9383,
374
+ "step": 20400
375
+ },
376
+ {
377
+ "epoch": 1.19,
378
+ "grad_norm": 1.3894723653793335,
379
+ "learning_rate": 3.85024154589372e-05,
380
+ "loss": 0.9381,
381
+ "step": 20800
382
+ },
383
+ {
384
+ "epoch": 1.21,
385
+ "grad_norm": 0.900830864906311,
386
+ "learning_rate": 3.8272371750632626e-05,
387
+ "loss": 0.9175,
388
+ "step": 21200
389
+ },
390
+ {
391
+ "epoch": 1.23,
392
+ "grad_norm": 1.0307693481445312,
393
+ "learning_rate": 3.804232804232805e-05,
394
+ "loss": 0.924,
395
+ "step": 21600
396
+ },
397
+ {
398
+ "epoch": 1.25,
399
+ "grad_norm": 1.0316811800003052,
400
+ "learning_rate": 3.7812284334023465e-05,
401
+ "loss": 0.9165,
402
+ "step": 22000
403
+ },
404
+ {
405
+ "epoch": 1.28,
406
+ "grad_norm": 1.1016398668289185,
407
+ "learning_rate": 3.758224062571889e-05,
408
+ "loss": 0.9168,
409
+ "step": 22400
410
+ },
411
+ {
412
+ "epoch": 1.3,
413
+ "grad_norm": 1.0044025182724,
414
+ "learning_rate": 3.735277202668507e-05,
415
+ "loss": 0.9146,
416
+ "step": 22800
417
+ },
418
+ {
419
+ "epoch": 1.32,
420
+ "grad_norm": 1.1868786811828613,
421
+ "learning_rate": 3.7122728318380494e-05,
422
+ "loss": 0.9253,
423
+ "step": 23200
424
+ },
425
+ {
426
+ "epoch": 1.34,
427
+ "grad_norm": 1.041280746459961,
428
+ "learning_rate": 3.689268461007592e-05,
429
+ "loss": 0.9003,
430
+ "step": 23600
431
+ },
432
+ {
433
+ "epoch": 1.37,
434
+ "grad_norm": 1.0607842206954956,
435
+ "learning_rate": 3.666264090177134e-05,
436
+ "loss": 0.9075,
437
+ "step": 24000
438
+ },
439
+ {
440
+ "epoch": 1.39,
441
+ "grad_norm": 0.8795559406280518,
442
+ "learning_rate": 3.643259719346676e-05,
443
+ "loss": 0.907,
444
+ "step": 24400
445
+ },
446
+ {
447
+ "epoch": 1.41,
448
+ "grad_norm": 1.0717073678970337,
449
+ "learning_rate": 3.6203128594432946e-05,
450
+ "loss": 0.9081,
451
+ "step": 24800
452
+ },
453
+ {
454
+ "epoch": 1.44,
455
+ "grad_norm": 0.9691916108131409,
456
+ "learning_rate": 3.597308488612837e-05,
457
+ "loss": 0.8907,
458
+ "step": 25200
459
+ },
460
+ {
461
+ "epoch": 1.46,
462
+ "grad_norm": 1.1249741315841675,
463
+ "learning_rate": 3.574304117782379e-05,
464
+ "loss": 0.8942,
465
+ "step": 25600
466
+ },
467
+ {
468
+ "epoch": 1.48,
469
+ "grad_norm": 0.8723602890968323,
470
+ "learning_rate": 3.551299746951921e-05,
471
+ "loss": 0.9014,
472
+ "step": 26000
473
+ },
474
+ {
475
+ "epoch": 1.5,
476
+ "grad_norm": 1.1265227794647217,
477
+ "learning_rate": 3.528295376121463e-05,
478
+ "loss": 0.8862,
479
+ "step": 26400
480
+ },
481
+ {
482
+ "epoch": 1.53,
483
+ "grad_norm": 0.8394224047660828,
484
+ "learning_rate": 3.5052910052910054e-05,
485
+ "loss": 0.8823,
486
+ "step": 26800
487
+ },
488
+ {
489
+ "epoch": 1.55,
490
+ "grad_norm": 1.1697936058044434,
491
+ "learning_rate": 3.482344145387624e-05,
492
+ "loss": 0.8786,
493
+ "step": 27200
494
+ },
495
+ {
496
+ "epoch": 1.57,
497
+ "grad_norm": 0.8561883568763733,
498
+ "learning_rate": 3.459339774557166e-05,
499
+ "loss": 0.8816,
500
+ "step": 27600
501
+ },
502
+ {
503
+ "epoch": 1.6,
504
+ "grad_norm": 1.054382562637329,
505
+ "learning_rate": 3.436335403726708e-05,
506
+ "loss": 0.8862,
507
+ "step": 28000
508
+ },
509
+ {
510
+ "epoch": 1.62,
511
+ "grad_norm": 1.1177219152450562,
512
+ "learning_rate": 3.4133310328962506e-05,
513
+ "loss": 0.8867,
514
+ "step": 28400
515
+ },
516
+ {
517
+ "epoch": 1.64,
518
+ "grad_norm": 0.9827663898468018,
519
+ "learning_rate": 3.390326662065793e-05,
520
+ "loss": 0.8893,
521
+ "step": 28800
522
+ },
523
+ {
524
+ "epoch": 1.66,
525
+ "grad_norm": 0.9570045471191406,
526
+ "learning_rate": 3.3673222912353345e-05,
527
+ "loss": 0.8839,
528
+ "step": 29200
529
+ },
530
+ {
531
+ "epoch": 1.69,
532
+ "grad_norm": 3.5448367595672607,
533
+ "learning_rate": 3.3444904531861054e-05,
534
+ "loss": 0.8851,
535
+ "step": 29600
536
+ },
537
+ {
538
+ "epoch": 1.71,
539
+ "grad_norm": 1.0004465579986572,
540
+ "learning_rate": 3.321543593282724e-05,
541
+ "loss": 0.8824,
542
+ "step": 30000
543
+ },
544
+ {
545
+ "epoch": 1.73,
546
+ "grad_norm": 0.9247887134552002,
547
+ "learning_rate": 3.298539222452266e-05,
548
+ "loss": 0.8633,
549
+ "step": 30400
550
+ },
551
+ {
552
+ "epoch": 1.76,
553
+ "grad_norm": 1.1364272832870483,
554
+ "learning_rate": 3.275534851621808e-05,
555
+ "loss": 0.8755,
556
+ "step": 30800
557
+ },
558
+ {
559
+ "epoch": 1.78,
560
+ "grad_norm": 1.057548999786377,
561
+ "learning_rate": 3.2525304807913506e-05,
562
+ "loss": 0.867,
563
+ "step": 31200
564
+ },
565
+ {
566
+ "epoch": 1.8,
567
+ "grad_norm": 0.9271708130836487,
568
+ "learning_rate": 3.229526109960893e-05,
569
+ "loss": 0.8795,
570
+ "step": 31600
571
+ },
572
+ {
573
+ "epoch": 1.82,
574
+ "grad_norm": 1.1106973886489868,
575
+ "learning_rate": 3.2065217391304345e-05,
576
+ "loss": 0.8636,
577
+ "step": 32000
578
+ },
579
+ {
580
+ "epoch": 1.85,
581
+ "grad_norm": 1.1093181371688843,
582
+ "learning_rate": 3.183517368299977e-05,
583
+ "loss": 0.8633,
584
+ "step": 32400
585
+ },
586
+ {
587
+ "epoch": 1.87,
588
+ "grad_norm": 1.1222974061965942,
589
+ "learning_rate": 3.160512997469519e-05,
590
+ "loss": 0.8637,
591
+ "step": 32800
592
+ },
593
+ {
594
+ "epoch": 1.89,
595
+ "grad_norm": 0.9591478109359741,
596
+ "learning_rate": 3.1375086266390614e-05,
597
+ "loss": 0.8632,
598
+ "step": 33200
599
+ },
600
+ {
601
+ "epoch": 1.91,
602
+ "grad_norm": 0.9238194823265076,
603
+ "learning_rate": 3.1145042558086044e-05,
604
+ "loss": 0.8489,
605
+ "step": 33600
606
+ },
607
+ {
608
+ "epoch": 1.94,
609
+ "grad_norm": 1.0500926971435547,
610
+ "learning_rate": 3.091499884978146e-05,
611
+ "loss": 0.8581,
612
+ "step": 34000
613
+ },
614
+ {
615
+ "epoch": 1.96,
616
+ "grad_norm": 1.459464430809021,
617
+ "learning_rate": 3.068495514147688e-05,
618
+ "loss": 0.8522,
619
+ "step": 34400
620
+ },
621
+ {
622
+ "epoch": 1.98,
623
+ "grad_norm": 1.1386796236038208,
624
+ "learning_rate": 3.045548654244307e-05,
625
+ "loss": 0.8615,
626
+ "step": 34800
627
+ },
628
+ {
629
+ "epoch": 2.0,
630
+ "eval_loss": 1.1808243989944458,
631
+ "eval_runtime": 367.8213,
632
+ "eval_samples_per_second": 163.87,
633
+ "eval_steps_per_second": 2.561,
634
+ "step": 35096
635
+ },
636
+ {
637
+ "epoch": 2.01,
638
+ "grad_norm": 1.064687728881836,
639
+ "learning_rate": 3.022544283413849e-05,
640
+ "loss": 0.8377,
641
+ "step": 35200
642
+ },
643
+ {
644
+ "epoch": 2.03,
645
+ "grad_norm": 1.260934591293335,
646
+ "learning_rate": 2.999539912583391e-05,
647
+ "loss": 0.8038,
648
+ "step": 35600
649
+ },
650
+ {
651
+ "epoch": 2.05,
652
+ "grad_norm": 1.0460811853408813,
653
+ "learning_rate": 2.9765355417529335e-05,
654
+ "loss": 0.7998,
655
+ "step": 36000
656
+ },
657
+ {
658
+ "epoch": 2.07,
659
+ "grad_norm": 1.0479072332382202,
660
+ "learning_rate": 2.9535311709224754e-05,
661
+ "loss": 0.8006,
662
+ "step": 36400
663
+ },
664
+ {
665
+ "epoch": 2.1,
666
+ "grad_norm": 1.1579115390777588,
667
+ "learning_rate": 2.9305268000920177e-05,
668
+ "loss": 0.7927,
669
+ "step": 36800
670
+ },
671
+ {
672
+ "epoch": 2.12,
673
+ "grad_norm": 1.0748111009597778,
674
+ "learning_rate": 2.90752242926156e-05,
675
+ "loss": 0.7942,
676
+ "step": 37200
677
+ },
678
+ {
679
+ "epoch": 2.14,
680
+ "grad_norm": 1.0448018312454224,
681
+ "learning_rate": 2.884518058431102e-05,
682
+ "loss": 0.8047,
683
+ "step": 37600
684
+ },
685
+ {
686
+ "epoch": 2.17,
687
+ "grad_norm": 1.122674822807312,
688
+ "learning_rate": 2.8615136876006443e-05,
689
+ "loss": 0.8034,
690
+ "step": 38000
691
+ },
692
+ {
693
+ "epoch": 2.19,
694
+ "grad_norm": 1.0929648876190186,
695
+ "learning_rate": 2.8385093167701866e-05,
696
+ "loss": 0.7982,
697
+ "step": 38400
698
+ },
699
+ {
700
+ "epoch": 2.21,
701
+ "grad_norm": 1.0236926078796387,
702
+ "learning_rate": 2.8155049459397285e-05,
703
+ "loss": 0.804,
704
+ "step": 38800
705
+ },
706
+ {
707
+ "epoch": 2.23,
708
+ "grad_norm": 1.4479929208755493,
709
+ "learning_rate": 2.792558086036347e-05,
710
+ "loss": 0.7986,
711
+ "step": 39200
712
+ },
713
+ {
714
+ "epoch": 2.26,
715
+ "grad_norm": 1.0635368824005127,
716
+ "learning_rate": 2.769553715205889e-05,
717
+ "loss": 0.793,
718
+ "step": 39600
719
+ },
720
+ {
721
+ "epoch": 2.28,
722
+ "grad_norm": 0.9539445638656616,
723
+ "learning_rate": 2.7466068553025077e-05,
724
+ "loss": 0.7891,
725
+ "step": 40000
726
+ },
727
+ {
728
+ "epoch": 2.3,
729
+ "grad_norm": 1.0995815992355347,
730
+ "learning_rate": 2.723659995399126e-05,
731
+ "loss": 0.8014,
732
+ "step": 40400
733
+ },
734
+ {
735
+ "epoch": 2.33,
736
+ "grad_norm": 0.9494262337684631,
737
+ "learning_rate": 2.7006556245686683e-05,
738
+ "loss": 0.7913,
739
+ "step": 40800
740
+ },
741
+ {
742
+ "epoch": 2.35,
743
+ "grad_norm": 0.9940603375434875,
744
+ "learning_rate": 2.6776512537382103e-05,
745
+ "loss": 0.7967,
746
+ "step": 41200
747
+ },
748
+ {
749
+ "epoch": 2.37,
750
+ "grad_norm": 1.0324065685272217,
751
+ "learning_rate": 2.6546468829077526e-05,
752
+ "loss": 0.783,
753
+ "step": 41600
754
+ },
755
+ {
756
+ "epoch": 2.39,
757
+ "grad_norm": 0.9601799845695496,
758
+ "learning_rate": 2.631642512077295e-05,
759
+ "loss": 0.7871,
760
+ "step": 42000
761
+ },
762
+ {
763
+ "epoch": 2.42,
764
+ "grad_norm": 1.0334033966064453,
765
+ "learning_rate": 2.6086381412468368e-05,
766
+ "loss": 0.793,
767
+ "step": 42400
768
+ },
769
+ {
770
+ "epoch": 2.44,
771
+ "grad_norm": 1.070986270904541,
772
+ "learning_rate": 2.5856912813434555e-05,
773
+ "loss": 0.7908,
774
+ "step": 42800
775
+ },
776
+ {
777
+ "epoch": 2.46,
778
+ "grad_norm": 0.9531447887420654,
779
+ "learning_rate": 2.5626869105129974e-05,
780
+ "loss": 0.7806,
781
+ "step": 43200
782
+ },
783
+ {
784
+ "epoch": 2.48,
785
+ "grad_norm": 1.2823644876480103,
786
+ "learning_rate": 2.5397400506096157e-05,
787
+ "loss": 0.7953,
788
+ "step": 43600
789
+ },
790
+ {
791
+ "epoch": 2.51,
792
+ "grad_norm": 0.8898524641990662,
793
+ "learning_rate": 2.516735679779158e-05,
794
+ "loss": 0.7926,
795
+ "step": 44000
796
+ },
797
+ {
798
+ "epoch": 2.53,
799
+ "grad_norm": 1.2231683731079102,
800
+ "learning_rate": 2.4937313089487006e-05,
801
+ "loss": 0.7895,
802
+ "step": 44400
803
+ },
804
+ {
805
+ "epoch": 2.55,
806
+ "grad_norm": 0.9554850459098816,
807
+ "learning_rate": 2.4707269381182426e-05,
808
+ "loss": 0.7871,
809
+ "step": 44800
810
+ },
811
+ {
812
+ "epoch": 2.58,
813
+ "grad_norm": 1.007906436920166,
814
+ "learning_rate": 2.447722567287785e-05,
815
+ "loss": 0.7713,
816
+ "step": 45200
817
+ },
818
+ {
819
+ "epoch": 2.6,
820
+ "grad_norm": 1.0699195861816406,
821
+ "learning_rate": 2.4247181964573272e-05,
822
+ "loss": 0.7817,
823
+ "step": 45600
824
+ },
825
+ {
826
+ "epoch": 2.62,
827
+ "grad_norm": 1.1465818881988525,
828
+ "learning_rate": 2.401713825626869e-05,
829
+ "loss": 0.7779,
830
+ "step": 46000
831
+ },
832
+ {
833
+ "epoch": 2.64,
834
+ "grad_norm": 0.8878755569458008,
835
+ "learning_rate": 2.3787094547964114e-05,
836
+ "loss": 0.7759,
837
+ "step": 46400
838
+ },
839
+ {
840
+ "epoch": 2.67,
841
+ "grad_norm": 1.0451282262802124,
842
+ "learning_rate": 2.3557050839659537e-05,
843
+ "loss": 0.775,
844
+ "step": 46800
845
+ },
846
+ {
847
+ "epoch": 2.69,
848
+ "grad_norm": 1.015073299407959,
849
+ "learning_rate": 2.3327007131354957e-05,
850
+ "loss": 0.7799,
851
+ "step": 47200
852
+ },
853
+ {
854
+ "epoch": 2.71,
855
+ "grad_norm": 1.1620949506759644,
856
+ "learning_rate": 2.309696342305038e-05,
857
+ "loss": 0.7732,
858
+ "step": 47600
859
+ },
860
+ {
861
+ "epoch": 2.74,
862
+ "grad_norm": 0.8986193537712097,
863
+ "learning_rate": 2.2866919714745803e-05,
864
+ "loss": 0.7819,
865
+ "step": 48000
866
+ },
867
+ {
868
+ "epoch": 2.76,
869
+ "grad_norm": 1.1293410062789917,
870
+ "learning_rate": 2.2636876006441222e-05,
871
+ "loss": 0.7709,
872
+ "step": 48400
873
+ },
874
+ {
875
+ "epoch": 2.78,
876
+ "grad_norm": 1.0725595951080322,
877
+ "learning_rate": 2.2406832298136645e-05,
878
+ "loss": 0.7635,
879
+ "step": 48800
880
+ },
881
+ {
882
+ "epoch": 2.8,
883
+ "grad_norm": 0.98313307762146,
884
+ "learning_rate": 2.2176788589832072e-05,
885
+ "loss": 0.7692,
886
+ "step": 49200
887
+ },
888
+ {
889
+ "epoch": 2.83,
890
+ "grad_norm": 1.0612819194793701,
891
+ "learning_rate": 2.194674488152749e-05,
892
+ "loss": 0.7626,
893
+ "step": 49600
894
+ },
895
+ {
896
+ "epoch": 2.85,
897
+ "grad_norm": 1.1520133018493652,
898
+ "learning_rate": 2.1717276282493678e-05,
899
+ "loss": 0.7608,
900
+ "step": 50000
901
+ },
902
+ {
903
+ "epoch": 2.87,
904
+ "grad_norm": 1.0242923498153687,
905
+ "learning_rate": 2.1487232574189097e-05,
906
+ "loss": 0.7787,
907
+ "step": 50400
908
+ },
909
+ {
910
+ "epoch": 2.89,
911
+ "grad_norm": 1.09690523147583,
912
+ "learning_rate": 2.125718886588452e-05,
913
+ "loss": 0.7716,
914
+ "step": 50800
915
+ },
916
+ {
917
+ "epoch": 2.92,
918
+ "grad_norm": 1.1755789518356323,
919
+ "learning_rate": 2.1027145157579943e-05,
920
+ "loss": 0.7713,
921
+ "step": 51200
922
+ },
923
+ {
924
+ "epoch": 2.94,
925
+ "grad_norm": 0.9996896386146545,
926
+ "learning_rate": 2.0797101449275363e-05,
927
+ "loss": 0.7733,
928
+ "step": 51600
929
+ },
930
+ {
931
+ "epoch": 2.96,
932
+ "grad_norm": 1.0416631698608398,
933
+ "learning_rate": 2.0567057740970786e-05,
934
+ "loss": 0.7707,
935
+ "step": 52000
936
+ },
937
+ {
938
+ "epoch": 2.99,
939
+ "grad_norm": 1.2188984155654907,
940
+ "learning_rate": 2.033701403266621e-05,
941
+ "loss": 0.7639,
942
+ "step": 52400
943
+ },
944
+ {
945
+ "epoch": 3.0,
946
+ "eval_loss": 1.1765093803405762,
947
+ "eval_runtime": 367.9851,
948
+ "eval_samples_per_second": 163.797,
949
+ "eval_steps_per_second": 2.56,
950
+ "step": 52644
951
+ },
952
+ {
953
+ "epoch": 3.01,
954
+ "grad_norm": 1.4339423179626465,
955
+ "learning_rate": 2.0106970324361628e-05,
956
+ "loss": 0.7487,
957
+ "step": 52800
958
+ },
959
+ {
960
+ "epoch": 3.03,
961
+ "grad_norm": 1.022152304649353,
962
+ "learning_rate": 1.987692661605705e-05,
963
+ "loss": 0.7295,
964
+ "step": 53200
965
+ },
966
+ {
967
+ "epoch": 3.05,
968
+ "grad_norm": 1.0018941164016724,
969
+ "learning_rate": 1.9646882907752474e-05,
970
+ "loss": 0.7181,
971
+ "step": 53600
972
+ },
973
+ {
974
+ "epoch": 3.08,
975
+ "grad_norm": 0.9470273852348328,
976
+ "learning_rate": 1.9416839199447894e-05,
977
+ "loss": 0.7245,
978
+ "step": 54000
979
+ },
980
+ {
981
+ "epoch": 3.1,
982
+ "grad_norm": 0.9430755972862244,
983
+ "learning_rate": 1.918737060041408e-05,
984
+ "loss": 0.7293,
985
+ "step": 54400
986
+ },
987
+ {
988
+ "epoch": 3.12,
989
+ "grad_norm": 1.1047594547271729,
990
+ "learning_rate": 1.89573268921095e-05,
991
+ "loss": 0.7243,
992
+ "step": 54800
993
+ },
994
+ {
995
+ "epoch": 3.15,
996
+ "grad_norm": 1.011172890663147,
997
+ "learning_rate": 1.8727858293075682e-05,
998
+ "loss": 0.734,
999
+ "step": 55200
1000
+ },
1001
+ {
1002
+ "epoch": 3.17,
1003
+ "grad_norm": 1.0907740592956543,
1004
+ "learning_rate": 1.849781458477111e-05,
1005
+ "loss": 0.7139,
1006
+ "step": 55600
1007
+ },
1008
+ {
1009
+ "epoch": 3.19,
1010
+ "grad_norm": 0.9432533979415894,
1011
+ "learning_rate": 1.8267770876466532e-05,
1012
+ "loss": 0.7144,
1013
+ "step": 56000
1014
+ },
1015
+ {
1016
+ "epoch": 3.21,
1017
+ "grad_norm": 1.0588159561157227,
1018
+ "learning_rate": 1.803772716816195e-05,
1019
+ "loss": 0.7205,
1020
+ "step": 56400
1021
+ },
1022
+ {
1023
+ "epoch": 3.24,
1024
+ "grad_norm": 1.0993419885635376,
1025
+ "learning_rate": 1.7807683459857374e-05,
1026
+ "loss": 0.7245,
1027
+ "step": 56800
1028
+ },
1029
+ {
1030
+ "epoch": 3.26,
1031
+ "grad_norm": 1.082985520362854,
1032
+ "learning_rate": 1.7577639751552797e-05,
1033
+ "loss": 0.72,
1034
+ "step": 57200
1035
+ },
1036
+ {
1037
+ "epoch": 3.28,
1038
+ "grad_norm": 1.021746039390564,
1039
+ "learning_rate": 1.7347596043248217e-05,
1040
+ "loss": 0.7165,
1041
+ "step": 57600
1042
+ },
1043
+ {
1044
+ "epoch": 3.31,
1045
+ "grad_norm": 1.167556643486023,
1046
+ "learning_rate": 1.7118127444214403e-05,
1047
+ "loss": 0.7177,
1048
+ "step": 58000
1049
+ },
1050
+ {
1051
+ "epoch": 3.33,
1052
+ "grad_norm": 1.1957422494888306,
1053
+ "learning_rate": 1.6888083735909823e-05,
1054
+ "loss": 0.7199,
1055
+ "step": 58400
1056
+ },
1057
+ {
1058
+ "epoch": 3.35,
1059
+ "grad_norm": 1.0189940929412842,
1060
+ "learning_rate": 1.6658040027605246e-05,
1061
+ "loss": 0.7142,
1062
+ "step": 58800
1063
+ },
1064
+ {
1065
+ "epoch": 3.37,
1066
+ "grad_norm": 1.7046924829483032,
1067
+ "learning_rate": 1.642799631930067e-05,
1068
+ "loss": 0.7187,
1069
+ "step": 59200
1070
+ },
1071
+ {
1072
+ "epoch": 3.4,
1073
+ "grad_norm": 1.220874309539795,
1074
+ "learning_rate": 1.6197952610996088e-05,
1075
+ "loss": 0.7252,
1076
+ "step": 59600
1077
+ },
1078
+ {
1079
+ "epoch": 3.42,
1080
+ "grad_norm": 1.0041950941085815,
1081
+ "learning_rate": 1.596790890269151e-05,
1082
+ "loss": 0.7053,
1083
+ "step": 60000
1084
+ },
1085
+ {
1086
+ "epoch": 3.44,
1087
+ "grad_norm": 1.0260080099105835,
1088
+ "learning_rate": 1.5737865194386934e-05,
1089
+ "loss": 0.7118,
1090
+ "step": 60400
1091
+ },
1092
+ {
1093
+ "epoch": 3.46,
1094
+ "grad_norm": 1.1826013326644897,
1095
+ "learning_rate": 1.5507821486082354e-05,
1096
+ "loss": 0.7176,
1097
+ "step": 60800
1098
+ },
1099
+ {
1100
+ "epoch": 3.49,
1101
+ "grad_norm": 0.9184863567352295,
1102
+ "learning_rate": 1.527835288704854e-05,
1103
+ "loss": 0.7227,
1104
+ "step": 61200
1105
+ },
1106
+ {
1107
+ "epoch": 3.51,
1108
+ "grad_norm": 1.1603368520736694,
1109
+ "learning_rate": 1.5048309178743963e-05,
1110
+ "loss": 0.7162,
1111
+ "step": 61600
1112
+ },
1113
+ {
1114
+ "epoch": 3.53,
1115
+ "grad_norm": 1.2338982820510864,
1116
+ "learning_rate": 1.4818265470439386e-05,
1117
+ "loss": 0.718,
1118
+ "step": 62000
1119
+ },
1120
+ {
1121
+ "epoch": 3.56,
1122
+ "grad_norm": 1.1764419078826904,
1123
+ "learning_rate": 1.4588221762134807e-05,
1124
+ "loss": 0.7213,
1125
+ "step": 62400
1126
+ },
1127
+ {
1128
+ "epoch": 3.58,
1129
+ "grad_norm": 1.0851845741271973,
1130
+ "learning_rate": 1.4358178053830229e-05,
1131
+ "loss": 0.717,
1132
+ "step": 62800
1133
+ },
1134
+ {
1135
+ "epoch": 3.6,
1136
+ "grad_norm": 1.0550730228424072,
1137
+ "learning_rate": 1.4128134345525652e-05,
1138
+ "loss": 0.7037,
1139
+ "step": 63200
1140
+ },
1141
+ {
1142
+ "epoch": 3.62,
1143
+ "grad_norm": 1.1784164905548096,
1144
+ "learning_rate": 1.3898665746491834e-05,
1145
+ "loss": 0.7194,
1146
+ "step": 63600
1147
+ },
1148
+ {
1149
+ "epoch": 3.65,
1150
+ "grad_norm": 0.9505347609519958,
1151
+ "learning_rate": 1.3668622038187256e-05,
1152
+ "loss": 0.7105,
1153
+ "step": 64000
1154
+ },
1155
+ {
1156
+ "epoch": 3.67,
1157
+ "grad_norm": 1.266885757446289,
1158
+ "learning_rate": 1.3438578329882679e-05,
1159
+ "loss": 0.7101,
1160
+ "step": 64400
1161
+ },
1162
+ {
1163
+ "epoch": 3.69,
1164
+ "grad_norm": 1.092987060546875,
1165
+ "learning_rate": 1.32085346215781e-05,
1166
+ "loss": 0.7089,
1167
+ "step": 64800
1168
+ },
1169
+ {
1170
+ "epoch": 3.72,
1171
+ "grad_norm": 1.2043814659118652,
1172
+ "learning_rate": 1.2978490913273523e-05,
1173
+ "loss": 0.6956,
1174
+ "step": 65200
1175
+ },
1176
+ {
1177
+ "epoch": 3.74,
1178
+ "grad_norm": 1.230975866317749,
1179
+ "learning_rate": 1.2748447204968944e-05,
1180
+ "loss": 0.7118,
1181
+ "step": 65600
1182
+ },
1183
+ {
1184
+ "epoch": 3.76,
1185
+ "grad_norm": 1.2574669122695923,
1186
+ "learning_rate": 1.2518978605935127e-05,
1187
+ "loss": 0.7102,
1188
+ "step": 66000
1189
+ },
1190
+ {
1191
+ "epoch": 3.78,
1192
+ "grad_norm": 1.1570420265197754,
1193
+ "learning_rate": 1.2288934897630552e-05,
1194
+ "loss": 0.696,
1195
+ "step": 66400
1196
+ },
1197
+ {
1198
+ "epoch": 3.81,
1199
+ "grad_norm": 1.3489502668380737,
1200
+ "learning_rate": 1.2058891189325973e-05,
1201
+ "loss": 0.7108,
1202
+ "step": 66800
1203
+ },
1204
+ {
1205
+ "epoch": 3.83,
1206
+ "grad_norm": 1.2118040323257446,
1207
+ "learning_rate": 1.1828847481021394e-05,
1208
+ "loss": 0.7211,
1209
+ "step": 67200
1210
+ },
1211
+ {
1212
+ "epoch": 3.85,
1213
+ "grad_norm": 1.1167511940002441,
1214
+ "learning_rate": 1.1599378881987579e-05,
1215
+ "loss": 0.7044,
1216
+ "step": 67600
1217
+ },
1218
+ {
1219
+ "epoch": 3.88,
1220
+ "grad_norm": 1.0914174318313599,
1221
+ "learning_rate": 1.1369335173683e-05,
1222
+ "loss": 0.7051,
1223
+ "step": 68000
1224
+ },
1225
+ {
1226
+ "epoch": 3.9,
1227
+ "grad_norm": 1.059415340423584,
1228
+ "learning_rate": 1.1139291465378423e-05,
1229
+ "loss": 0.7142,
1230
+ "step": 68400
1231
+ },
1232
+ {
1233
+ "epoch": 3.92,
1234
+ "grad_norm": 0.94761723279953,
1235
+ "learning_rate": 1.0909247757073844e-05,
1236
+ "loss": 0.7072,
1237
+ "step": 68800
1238
+ },
1239
+ {
1240
+ "epoch": 3.94,
1241
+ "grad_norm": 1.2550498247146606,
1242
+ "learning_rate": 1.0679204048769266e-05,
1243
+ "loss": 0.7034,
1244
+ "step": 69200
1245
+ },
1246
+ {
1247
+ "epoch": 3.97,
1248
+ "grad_norm": 1.0935131311416626,
1249
+ "learning_rate": 1.0449160340464689e-05,
1250
+ "loss": 0.6976,
1251
+ "step": 69600
1252
+ },
1253
+ {
1254
+ "epoch": 3.99,
1255
+ "grad_norm": 1.8066422939300537,
1256
+ "learning_rate": 1.0219116632160112e-05,
1257
+ "loss": 0.698,
1258
+ "step": 70000
1259
+ },
1260
+ {
1261
+ "epoch": 4.0,
1262
+ "eval_loss": 1.1811184883117676,
1263
+ "eval_runtime": 368.0007,
1264
+ "eval_samples_per_second": 163.79,
1265
+ "eval_steps_per_second": 2.56,
1266
+ "step": 70192
1267
+ },
1268
+ {
1269
+ "epoch": 4.01,
1270
+ "grad_norm": 1.1222364902496338,
1271
+ "learning_rate": 9.989072923855533e-06,
1272
+ "loss": 0.6825,
1273
+ "step": 70400
1274
+ },
1275
+ {
1276
+ "epoch": 4.03,
1277
+ "grad_norm": 1.1273374557495117,
1278
+ "learning_rate": 9.759029215550954e-06,
1279
+ "loss": 0.6736,
1280
+ "step": 70800
1281
+ },
1282
+ {
1283
+ "epoch": 4.06,
1284
+ "grad_norm": 1.1399248838424683,
1285
+ "learning_rate": 9.528985507246377e-06,
1286
+ "loss": 0.6667,
1287
+ "step": 71200
1288
+ },
1289
+ {
1290
+ "epoch": 4.08,
1291
+ "grad_norm": 1.0817917585372925,
1292
+ "learning_rate": 9.298941798941798e-06,
1293
+ "loss": 0.6826,
1294
+ "step": 71600
1295
+ },
1296
+ {
1297
+ "epoch": 4.1,
1298
+ "grad_norm": 1.085259199142456,
1299
+ "learning_rate": 9.068898090637221e-06,
1300
+ "loss": 0.6699,
1301
+ "step": 72000
1302
+ },
1303
+ {
1304
+ "epoch": 4.13,
1305
+ "grad_norm": 1.1712231636047363,
1306
+ "learning_rate": 8.838854382332644e-06,
1307
+ "loss": 0.677,
1308
+ "step": 72400
1309
+ },
1310
+ {
1311
+ "epoch": 4.15,
1312
+ "grad_norm": 1.1486331224441528,
1313
+ "learning_rate": 8.608810674028066e-06,
1314
+ "loss": 0.674,
1315
+ "step": 72800
1316
+ },
1317
+ {
1318
+ "epoch": 4.17,
1319
+ "grad_norm": 1.0690157413482666,
1320
+ "learning_rate": 8.378766965723487e-06,
1321
+ "loss": 0.6712,
1322
+ "step": 73200
1323
+ },
1324
+ {
1325
+ "epoch": 4.19,
1326
+ "grad_norm": 1.0190378427505493,
1327
+ "learning_rate": 8.14872325741891e-06,
1328
+ "loss": 0.666,
1329
+ "step": 73600
1330
+ },
1331
+ {
1332
+ "epoch": 4.22,
1333
+ "grad_norm": 1.2103822231292725,
1334
+ "learning_rate": 7.919254658385093e-06,
1335
+ "loss": 0.673,
1336
+ "step": 74000
1337
+ },
1338
+ {
1339
+ "epoch": 4.24,
1340
+ "grad_norm": 1.1462812423706055,
1341
+ "learning_rate": 7.689210950080516e-06,
1342
+ "loss": 0.669,
1343
+ "step": 74400
1344
+ },
1345
+ {
1346
+ "epoch": 4.26,
1347
+ "grad_norm": 1.0003070831298828,
1348
+ "learning_rate": 7.459167241775939e-06,
1349
+ "loss": 0.6806,
1350
+ "step": 74800
1351
+ },
1352
+ {
1353
+ "epoch": 4.29,
1354
+ "grad_norm": 1.0154987573623657,
1355
+ "learning_rate": 7.22912353347136e-06,
1356
+ "loss": 0.6838,
1357
+ "step": 75200
1358
+ },
1359
+ {
1360
+ "epoch": 4.31,
1361
+ "grad_norm": 1.0686919689178467,
1362
+ "learning_rate": 6.999079825166782e-06,
1363
+ "loss": 0.6677,
1364
+ "step": 75600
1365
+ },
1366
+ {
1367
+ "epoch": 4.33,
1368
+ "grad_norm": 1.0061548948287964,
1369
+ "learning_rate": 6.769611226132966e-06,
1370
+ "loss": 0.6696,
1371
+ "step": 76000
1372
+ },
1373
+ {
1374
+ "epoch": 4.35,
1375
+ "grad_norm": 4.049505710601807,
1376
+ "learning_rate": 6.539567517828388e-06,
1377
+ "loss": 0.6625,
1378
+ "step": 76400
1379
+ },
1380
+ {
1381
+ "epoch": 4.38,
1382
+ "grad_norm": 1.1459605693817139,
1383
+ "learning_rate": 6.30952380952381e-06,
1384
+ "loss": 0.6747,
1385
+ "step": 76800
1386
+ },
1387
+ {
1388
+ "epoch": 4.4,
1389
+ "grad_norm": 1.0267729759216309,
1390
+ "learning_rate": 6.079480101219232e-06,
1391
+ "loss": 0.684,
1392
+ "step": 77200
1393
+ },
1394
+ {
1395
+ "epoch": 4.42,
1396
+ "grad_norm": 1.109384298324585,
1397
+ "learning_rate": 5.849436392914654e-06,
1398
+ "loss": 0.6695,
1399
+ "step": 77600
1400
+ },
1401
+ {
1402
+ "epoch": 4.44,
1403
+ "grad_norm": 1.1579252481460571,
1404
+ "learning_rate": 5.619392684610076e-06,
1405
+ "loss": 0.6727,
1406
+ "step": 78000
1407
+ },
1408
+ {
1409
+ "epoch": 4.47,
1410
+ "grad_norm": 1.2438113689422607,
1411
+ "learning_rate": 5.3893489763054985e-06,
1412
+ "loss": 0.6778,
1413
+ "step": 78400
1414
+ },
1415
+ {
1416
+ "epoch": 4.49,
1417
+ "grad_norm": 1.1091639995574951,
1418
+ "learning_rate": 5.159305268000921e-06,
1419
+ "loss": 0.6665,
1420
+ "step": 78800
1421
+ },
1422
+ {
1423
+ "epoch": 4.51,
1424
+ "grad_norm": 1.0381008386611938,
1425
+ "learning_rate": 4.929261559696342e-06,
1426
+ "loss": 0.6641,
1427
+ "step": 79200
1428
+ },
1429
+ {
1430
+ "epoch": 4.54,
1431
+ "grad_norm": 1.0532902479171753,
1432
+ "learning_rate": 4.699217851391765e-06,
1433
+ "loss": 0.6629,
1434
+ "step": 79600
1435
+ },
1436
+ {
1437
+ "epoch": 4.56,
1438
+ "grad_norm": 1.0946133136749268,
1439
+ "learning_rate": 4.469174143087187e-06,
1440
+ "loss": 0.6765,
1441
+ "step": 80000
1442
+ },
1443
+ {
1444
+ "epoch": 4.58,
1445
+ "grad_norm": 1.119805932044983,
1446
+ "learning_rate": 4.239130434782608e-06,
1447
+ "loss": 0.6707,
1448
+ "step": 80400
1449
+ },
1450
+ {
1451
+ "epoch": 4.6,
1452
+ "grad_norm": 1.2089961767196655,
1453
+ "learning_rate": 4.009086726478031e-06,
1454
+ "loss": 0.6753,
1455
+ "step": 80800
1456
+ },
1457
+ {
1458
+ "epoch": 4.63,
1459
+ "grad_norm": 1.2102470397949219,
1460
+ "learning_rate": 3.779618127444214e-06,
1461
+ "loss": 0.6644,
1462
+ "step": 81200
1463
+ },
1464
+ {
1465
+ "epoch": 4.65,
1466
+ "grad_norm": 1.0439101457595825,
1467
+ "learning_rate": 3.5495744191396367e-06,
1468
+ "loss": 0.6713,
1469
+ "step": 81600
1470
+ },
1471
+ {
1472
+ "epoch": 4.67,
1473
+ "grad_norm": 1.1744842529296875,
1474
+ "learning_rate": 3.319530710835059e-06,
1475
+ "loss": 0.6599,
1476
+ "step": 82000
1477
+ },
1478
+ {
1479
+ "epoch": 4.7,
1480
+ "grad_norm": 0.9925849437713623,
1481
+ "learning_rate": 3.089487002530481e-06,
1482
+ "loss": 0.6656,
1483
+ "step": 82400
1484
+ },
1485
+ {
1486
+ "epoch": 4.72,
1487
+ "grad_norm": 1.2233749628067017,
1488
+ "learning_rate": 2.8600184034966646e-06,
1489
+ "loss": 0.6813,
1490
+ "step": 82800
1491
+ },
1492
+ {
1493
+ "epoch": 4.74,
1494
+ "grad_norm": 1.1348555088043213,
1495
+ "learning_rate": 2.6299746951920863e-06,
1496
+ "loss": 0.6738,
1497
+ "step": 83200
1498
+ },
1499
+ {
1500
+ "epoch": 4.76,
1501
+ "grad_norm": 1.0024689435958862,
1502
+ "learning_rate": 2.399930986887509e-06,
1503
+ "loss": 0.6654,
1504
+ "step": 83600
1505
+ },
1506
+ {
1507
+ "epoch": 4.79,
1508
+ "grad_norm": 1.049222469329834,
1509
+ "learning_rate": 2.1704623878536926e-06,
1510
+ "loss": 0.6782,
1511
+ "step": 84000
1512
+ },
1513
+ {
1514
+ "epoch": 4.81,
1515
+ "grad_norm": 1.2224096059799194,
1516
+ "learning_rate": 1.9404186795491143e-06,
1517
+ "loss": 0.6623,
1518
+ "step": 84400
1519
+ },
1520
+ {
1521
+ "epoch": 4.83,
1522
+ "grad_norm": 1.0780987739562988,
1523
+ "learning_rate": 1.7103749712445366e-06,
1524
+ "loss": 0.6633,
1525
+ "step": 84800
1526
+ },
1527
+ {
1528
+ "epoch": 4.86,
1529
+ "grad_norm": 1.0614657402038574,
1530
+ "learning_rate": 1.4803312629399585e-06,
1531
+ "loss": 0.6748,
1532
+ "step": 85200
1533
+ },
1534
+ {
1535
+ "epoch": 4.88,
1536
+ "grad_norm": 1.1810928583145142,
1537
+ "learning_rate": 1.2502875546353809e-06,
1538
+ "loss": 0.6623,
1539
+ "step": 85600
1540
+ },
1541
+ {
1542
+ "epoch": 4.9,
1543
+ "grad_norm": 1.1799181699752808,
1544
+ "learning_rate": 1.0202438463308028e-06,
1545
+ "loss": 0.6653,
1546
+ "step": 86000
1547
+ },
1548
+ {
1549
+ "epoch": 4.92,
1550
+ "grad_norm": 1.012217402458191,
1551
+ "learning_rate": 7.902001380262249e-07,
1552
+ "loss": 0.6632,
1553
+ "step": 86400
1554
+ },
1555
+ {
1556
+ "epoch": 4.95,
1557
+ "grad_norm": 1.2088865041732788,
1558
+ "learning_rate": 5.601564297216472e-07,
1559
+ "loss": 0.6719,
1560
+ "step": 86800
1561
+ },
1562
+ {
1563
+ "epoch": 4.97,
1564
+ "grad_norm": 1.1404399871826172,
1565
+ "learning_rate": 3.301127214170693e-07,
1566
+ "loss": 0.6636,
1567
+ "step": 87200
1568
+ },
1569
+ {
1570
+ "epoch": 4.99,
1571
+ "grad_norm": 1.2054311037063599,
1572
+ "learning_rate": 1.0006901311249138e-07,
1573
+ "loss": 0.6656,
1574
+ "step": 87600
1575
+ },
1576
+ {
1577
+ "epoch": 5.0,
1578
+ "eval_loss": 1.1946403980255127,
1579
+ "eval_runtime": 367.8686,
1580
+ "eval_samples_per_second": 163.849,
1581
+ "eval_steps_per_second": 2.561,
1582
+ "step": 87740
1583
+ },
1584
+ {
1585
+ "epoch": 5.0,
1586
+ "step": 87740,
1587
+ "total_flos": 1.7097588901675008e+18,
1588
+ "train_loss": 0.858644689469069,
1589
+ "train_runtime": 51993.6603,
1590
+ "train_samples_per_second": 54.003,
1591
+ "train_steps_per_second": 1.688
1592
+ }
1593
+ ],
1594
+ "logging_steps": 400,
1595
+ "max_steps": 87740,
1596
+ "num_input_tokens_seen": 0,
1597
+ "num_train_epochs": 5,
1598
+ "save_steps": 500,
1599
+ "total_flos": 1.7097588901675008e+18,
1600
+ "train_batch_size": 32,
1601
+ "trial_name": null,
1602
+ "trial_params": null
1603
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fda0fec77f51b031796c13d28d728df9d7d5631c539195c29ef6174efc00d44
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff