CocoRoF commited on
Commit
7c82bc1
·
verified ·
1 Parent(s): 7752121

Training in progress, step 2500, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CocoRoF/ModernBERT-SimCSE-multitask_v03-distill",
3
+ "architectures": [
4
+ "ModernBertForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1",
26
+ "2": "LABEL_2",
27
+ "3": "LABEL_3",
28
+ "4": "LABEL_4",
29
+ "5": "LABEL_5",
30
+ "6": "LABEL_6",
31
+ "7": "LABEL_7",
32
+ "8": "LABEL_8",
33
+ "9": "LABEL_9",
34
+ "10": "LABEL_10",
35
+ "11": "LABEL_11",
36
+ "12": "LABEL_12",
37
+ "13": "LABEL_13",
38
+ "14": "LABEL_14",
39
+ "15": "LABEL_15",
40
+ "16": "LABEL_16"
41
+ },
42
+ "initializer_cutoff_factor": 2.0,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 1152,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1,
48
+ "LABEL_10": 10,
49
+ "LABEL_11": 11,
50
+ "LABEL_12": 12,
51
+ "LABEL_13": 13,
52
+ "LABEL_14": 14,
53
+ "LABEL_15": 15,
54
+ "LABEL_16": 16,
55
+ "LABEL_2": 2,
56
+ "LABEL_3": 3,
57
+ "LABEL_4": 4,
58
+ "LABEL_5": 5,
59
+ "LABEL_6": 6,
60
+ "LABEL_7": 7,
61
+ "LABEL_8": 8,
62
+ "LABEL_9": 9
63
+ },
64
+ "layer_norm_eps": 1e-05,
65
+ "local_attention": 128,
66
+ "local_rope_theta": 10000.0,
67
+ "max_position_embeddings": 8192,
68
+ "mlp_bias": false,
69
+ "mlp_dropout": 0.0,
70
+ "model_type": "modernbert",
71
+ "norm_bias": false,
72
+ "norm_eps": 1e-05,
73
+ "num_attention_heads": 12,
74
+ "num_hidden_layers": 22,
75
+ "pad_token_id": 50283,
76
+ "position_embedding_type": "absolute",
77
+ "problem_type": "single_label_classification",
78
+ "reference_compile": false,
79
+ "repad_logits_with_grad": false,
80
+ "sep_token_id": 50282,
81
+ "sparse_pred_ignore_index": -100,
82
+ "sparse_prediction": false,
83
+ "torch_dtype": "float32",
84
+ "transformers_version": "4.49.0",
85
+ "vocab_size": 95663
86
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0598cf4c0d949fb5d2ece8c2b9a49b542391a4aa397571645e38483ab748399c
3
+ size 737632172
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14bc3239240bf9024e747c23023fedf985bad39fcca09135776d56fd1cc9e50
3
+ size 1475354682
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74386f26f36ed67f56395205881e5db2d0c28ffcbeed50dd95b28771d2dac588
3
+ size 15984
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c88f9de084200454883a13c3717941ea3fd433e2f8735507fc30611f9c5501
3
+ size 15984
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965b00d4cb4710ebab57c8787b9925bb3f77b8eeba94a186ec4bc1c2f326ef3f
3
+ size 15984
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5dc374b8b9a4c45c950f9d136feab85a767081fa59f0c7d68ed3a62060c4949
3
+ size 15984
last-checkpoint/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7c212fb779217f1edac0baf44f67b608eefc1e0e4e3f5a9dd7eb557032c1bc
3
+ size 15984
last-checkpoint/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e1effd626ce1e95dd68a0c8089fe19218f2b24dfe9e45ed2cab1c0ebc10ba1
3
+ size 15984
last-checkpoint/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:799cc83f60dfc1c4243cfd6403592112414a2eec494e6832f10221c96ff62c20
3
+ size 15984
last-checkpoint/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:586777c398770c3255d3a1f48c7fef44ea9d89117c627c9ea490e16bfd9a49ba
3
+ size 15984
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458ea0fd6c5fd9a917dfe3f8b6bf19bb7e7cc081c80d7da750a7340a0cfca1f2
3
+ size 1000
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
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
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "95580": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "95581": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "95582": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "95583": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "95584": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "95585": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "95586": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "95587": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "95588": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "95589": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "95590": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "95591": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "95592": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "95593": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "95594": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "95595": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "95596": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "95597": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "95598": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "95599": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "95600": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "95601": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "95602": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "95603": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "95604": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "95605": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "95606": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "95607": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "95608": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "95609": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "95610": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "95611": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "95612": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "95613": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "95614": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "95615": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "95616": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "95617": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "95618": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "95619": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "95620": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "95621": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "95622": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "95623": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "95624": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "95625": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "95626": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "95627": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "95628": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "95629": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "95630": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "95631": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "95632": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "95633": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "95634": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "95635": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "95636": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "95637": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "95638": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "95639": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "95640": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "95641": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "95642": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "95643": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "95644": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "95645": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "95646": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "95647": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "95648": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "95649": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "95650": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "95651": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "95652": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "95653": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "95654": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "95655": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "95656": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "95657": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "95658": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "95659": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "95660": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "95661": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "95662": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "max_length": 2048,
937
+ "model_input_names": [
938
+ "input_ids",
939
+ "attention_mask"
940
+ ],
941
+ "model_max_length": 2048,
942
+ "pad_to_multiple_of": null,
943
+ "pad_token": "[PAD]",
944
+ "pad_token_type_id": 0,
945
+ "padding_side": "right",
946
+ "sep_token": "[SEP]",
947
+ "stride": 0,
948
+ "tokenizer_class": "PreTrainedTokenizer",
949
+ "truncation_side": "right",
950
+ "truncation_strategy": "longest_first",
951
+ "unk_token": "[UNK]"
952
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1799 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.11095023327286546,
5
+ "eval_steps": 1000,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00044380093309146184,
13
+ "grad_norm": 725.3771362304688,
14
+ "learning_rate": 9.999982664038074e-06,
15
+ "loss": 85.6201,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0008876018661829237,
20
+ "grad_norm": 471.7138977050781,
21
+ "learning_rate": 9.999965328076145e-06,
22
+ "loss": 58.4931,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0013314027992743854,
27
+ "grad_norm": 330.69317626953125,
28
+ "learning_rate": 9.999947992114218e-06,
29
+ "loss": 39.9778,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0017752037323658474,
34
+ "grad_norm": 283.2129821777344,
35
+ "learning_rate": 9.999930656152291e-06,
36
+ "loss": 30.2775,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.002219004665457309,
41
+ "grad_norm": 283.95977783203125,
42
+ "learning_rate": 9.999913320190363e-06,
43
+ "loss": 26.528,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.0026628055985487707,
48
+ "grad_norm": 327.2074890136719,
49
+ "learning_rate": 9.999895984228436e-06,
50
+ "loss": 25.2187,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.0031066065316402327,
55
+ "grad_norm": 290.6508483886719,
56
+ "learning_rate": 9.999878648266509e-06,
57
+ "loss": 23.4217,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.0035504074647316947,
62
+ "grad_norm": 268.8506774902344,
63
+ "learning_rate": 9.99986131230458e-06,
64
+ "loss": 22.3678,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.003994208397823156,
69
+ "grad_norm": 303.6665954589844,
70
+ "learning_rate": 9.999843976342653e-06,
71
+ "loss": 21.8689,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.004438009330914618,
76
+ "grad_norm": 221.8241424560547,
77
+ "learning_rate": 9.999826640380727e-06,
78
+ "loss": 21.7776,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.00488181026400608,
83
+ "grad_norm": 208.48538208007812,
84
+ "learning_rate": 9.9998093044188e-06,
85
+ "loss": 21.2487,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.0053256111970975415,
90
+ "grad_norm": 195.47113037109375,
91
+ "learning_rate": 9.999791968456871e-06,
92
+ "loss": 20.7403,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.0057694121301890035,
97
+ "grad_norm": 289.3889465332031,
98
+ "learning_rate": 9.999774632494944e-06,
99
+ "loss": 20.443,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.0062132130632804655,
104
+ "grad_norm": 321.8573303222656,
105
+ "learning_rate": 9.999757296533017e-06,
106
+ "loss": 20.8289,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.0066570139963719275,
111
+ "grad_norm": 297.0621337890625,
112
+ "learning_rate": 9.999739960571089e-06,
113
+ "loss": 19.7784,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.0071008149294633895,
118
+ "grad_norm": 240.9821014404297,
119
+ "learning_rate": 9.999722624609162e-06,
120
+ "loss": 19.0094,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.007544615862554851,
125
+ "grad_norm": 261.113037109375,
126
+ "learning_rate": 9.999705288647235e-06,
127
+ "loss": 19.1363,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.007988416795646313,
132
+ "grad_norm": 218.0191650390625,
133
+ "learning_rate": 9.999687952685306e-06,
134
+ "loss": 18.8289,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.008432217728737776,
139
+ "grad_norm": 310.36712646484375,
140
+ "learning_rate": 9.999670616723379e-06,
141
+ "loss": 19.4811,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.008876018661829237,
146
+ "grad_norm": 217.39454650878906,
147
+ "learning_rate": 9.999653280761452e-06,
148
+ "loss": 18.593,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.009319819594920698,
153
+ "grad_norm": 221.60879516601562,
154
+ "learning_rate": 9.999635944799524e-06,
155
+ "loss": 18.8921,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.00976362052801216,
160
+ "grad_norm": 254.957763671875,
161
+ "learning_rate": 9.999618608837597e-06,
162
+ "loss": 18.9504,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.010207421461103622,
167
+ "grad_norm": 230.76243591308594,
168
+ "learning_rate": 9.99960127287567e-06,
169
+ "loss": 18.8949,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.010651222394195083,
174
+ "grad_norm": 316.453857421875,
175
+ "learning_rate": 9.999583936913741e-06,
176
+ "loss": 18.6263,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.011095023327286546,
181
+ "grad_norm": 275.41265869140625,
182
+ "learning_rate": 9.999566600951814e-06,
183
+ "loss": 18.6316,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.011538824260378007,
188
+ "grad_norm": 275.3472595214844,
189
+ "learning_rate": 9.999549264989887e-06,
190
+ "loss": 18.6499,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.01198262519346947,
195
+ "grad_norm": 239.0996551513672,
196
+ "learning_rate": 9.999531929027959e-06,
197
+ "loss": 18.9865,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.012426426126560931,
202
+ "grad_norm": 176.33468627929688,
203
+ "learning_rate": 9.999514593066032e-06,
204
+ "loss": 18.2206,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.012870227059652392,
209
+ "grad_norm": 199.18878173828125,
210
+ "learning_rate": 9.999497257104105e-06,
211
+ "loss": 17.4809,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.013314027992743855,
216
+ "grad_norm": 212.03488159179688,
217
+ "learning_rate": 9.999479921142176e-06,
218
+ "loss": 17.9092,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.013757828925835316,
223
+ "grad_norm": 244.9204559326172,
224
+ "learning_rate": 9.99946258518025e-06,
225
+ "loss": 17.5332,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.014201629858926779,
230
+ "grad_norm": 215.74754333496094,
231
+ "learning_rate": 9.999445249218322e-06,
232
+ "loss": 18.2855,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.01464543079201824,
237
+ "grad_norm": 226.8377227783203,
238
+ "learning_rate": 9.999427913256395e-06,
239
+ "loss": 17.7032,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.015089231725109701,
244
+ "grad_norm": 242.4842987060547,
245
+ "learning_rate": 9.999410577294467e-06,
246
+ "loss": 17.7969,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.015533032658201164,
251
+ "grad_norm": 233.77847290039062,
252
+ "learning_rate": 9.99939324133254e-06,
253
+ "loss": 17.4911,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.015976833591292625,
258
+ "grad_norm": 291.48065185546875,
259
+ "learning_rate": 9.999375905370613e-06,
260
+ "loss": 17.5533,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.016420634524384088,
265
+ "grad_norm": 219.2302703857422,
266
+ "learning_rate": 9.999358569408684e-06,
267
+ "loss": 17.3406,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.01686443545747555,
272
+ "grad_norm": 219.14234924316406,
273
+ "learning_rate": 9.999341233446757e-06,
274
+ "loss": 17.208,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.01730823639056701,
279
+ "grad_norm": 224.26629638671875,
280
+ "learning_rate": 9.99932389748483e-06,
281
+ "loss": 17.2251,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.017752037323658473,
286
+ "grad_norm": 269.49090576171875,
287
+ "learning_rate": 9.999306561522902e-06,
288
+ "loss": 17.1339,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.018195838256749936,
293
+ "grad_norm": 268.406494140625,
294
+ "learning_rate": 9.999289225560975e-06,
295
+ "loss": 17.0892,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.018639639189841396,
300
+ "grad_norm": 319.0367431640625,
301
+ "learning_rate": 9.999271889599048e-06,
302
+ "loss": 17.3344,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.01908344012293286,
307
+ "grad_norm": 259.054443359375,
308
+ "learning_rate": 9.99925455363712e-06,
309
+ "loss": 17.0951,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.01952724105602432,
314
+ "grad_norm": 191.9784698486328,
315
+ "learning_rate": 9.999237217675193e-06,
316
+ "loss": 16.1768,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.01997104198911578,
321
+ "grad_norm": 214.4703826904297,
322
+ "learning_rate": 9.999219881713266e-06,
323
+ "loss": 17.0767,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.020414842922207244,
328
+ "grad_norm": 271.8641662597656,
329
+ "learning_rate": 9.999202545751337e-06,
330
+ "loss": 16.9147,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.020858643855298706,
335
+ "grad_norm": 293.4891357421875,
336
+ "learning_rate": 9.99918520978941e-06,
337
+ "loss": 17.3521,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.021302444788390166,
342
+ "grad_norm": 200.57672119140625,
343
+ "learning_rate": 9.999167873827483e-06,
344
+ "loss": 16.7094,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.02174624572148163,
349
+ "grad_norm": 167.0054931640625,
350
+ "learning_rate": 9.999150537865555e-06,
351
+ "loss": 16.874,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.02219004665457309,
356
+ "grad_norm": 155.45993041992188,
357
+ "learning_rate": 9.999133201903628e-06,
358
+ "loss": 16.6857,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.022633847587664555,
363
+ "grad_norm": 169.74298095703125,
364
+ "learning_rate": 9.9991158659417e-06,
365
+ "loss": 16.9436,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.023077648520756014,
370
+ "grad_norm": 175.02944946289062,
371
+ "learning_rate": 9.999098529979772e-06,
372
+ "loss": 16.4027,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.023521449453847477,
377
+ "grad_norm": 206.35028076171875,
378
+ "learning_rate": 9.999081194017845e-06,
379
+ "loss": 17.196,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.02396525038693894,
384
+ "grad_norm": 175.73011779785156,
385
+ "learning_rate": 9.999063858055918e-06,
386
+ "loss": 16.2829,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.0244090513200304,
391
+ "grad_norm": 193.17225646972656,
392
+ "learning_rate": 9.999046522093991e-06,
393
+ "loss": 16.3072,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.024852852253121862,
398
+ "grad_norm": 232.3939971923828,
399
+ "learning_rate": 9.999029186132063e-06,
400
+ "loss": 16.2658,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.025296653186213325,
405
+ "grad_norm": 200.2445526123047,
406
+ "learning_rate": 9.999011850170136e-06,
407
+ "loss": 16.8102,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.025740454119304784,
412
+ "grad_norm": 235.8720703125,
413
+ "learning_rate": 9.998994514208209e-06,
414
+ "loss": 16.5103,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.026184255052396247,
419
+ "grad_norm": 174.5557403564453,
420
+ "learning_rate": 9.99897717824628e-06,
421
+ "loss": 16.4585,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.02662805598548771,
426
+ "grad_norm": 211.39187622070312,
427
+ "learning_rate": 9.998959842284353e-06,
428
+ "loss": 16.0689,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.027071856918579173,
433
+ "grad_norm": 274.6959228515625,
434
+ "learning_rate": 9.998942506322426e-06,
435
+ "loss": 15.9399,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.027515657851670632,
440
+ "grad_norm": 220.5891571044922,
441
+ "learning_rate": 9.998925170360498e-06,
442
+ "loss": 16.2098,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.027959458784762095,
447
+ "grad_norm": 239.71881103515625,
448
+ "learning_rate": 9.998907834398571e-06,
449
+ "loss": 16.6608,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.028403259717853558,
454
+ "grad_norm": 192.038818359375,
455
+ "learning_rate": 9.998890498436644e-06,
456
+ "loss": 16.0857,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.028847060650945017,
461
+ "grad_norm": 197.78492736816406,
462
+ "learning_rate": 9.998873162474715e-06,
463
+ "loss": 16.4402,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.02929086158403648,
468
+ "grad_norm": 180.5525360107422,
469
+ "learning_rate": 9.998855826512788e-06,
470
+ "loss": 15.6789,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.029734662517127943,
475
+ "grad_norm": 190.83297729492188,
476
+ "learning_rate": 9.998838490550861e-06,
477
+ "loss": 16.3187,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.030178463450219403,
482
+ "grad_norm": 259.5210266113281,
483
+ "learning_rate": 9.998821154588933e-06,
484
+ "loss": 15.9802,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.030622264383310865,
489
+ "grad_norm": 193.27146911621094,
490
+ "learning_rate": 9.998803818627006e-06,
491
+ "loss": 16.3872,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.03106606531640233,
496
+ "grad_norm": 187.4614715576172,
497
+ "learning_rate": 9.998786482665079e-06,
498
+ "loss": 15.7645,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.03150986624949379,
503
+ "grad_norm": 201.60263061523438,
504
+ "learning_rate": 9.99876914670315e-06,
505
+ "loss": 15.6817,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.03195366718258525,
510
+ "grad_norm": 170.6359100341797,
511
+ "learning_rate": 9.998751810741223e-06,
512
+ "loss": 15.8353,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.03239746811567671,
517
+ "grad_norm": 239.1863555908203,
518
+ "learning_rate": 9.998734474779297e-06,
519
+ "loss": 15.6572,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.032841269048768176,
524
+ "grad_norm": 174.40811157226562,
525
+ "learning_rate": 9.998717138817368e-06,
526
+ "loss": 16.2995,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.033285069981859636,
531
+ "grad_norm": 208.86151123046875,
532
+ "learning_rate": 9.998699802855441e-06,
533
+ "loss": 15.5835,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.0337288709149511,
538
+ "grad_norm": 186.65267944335938,
539
+ "learning_rate": 9.998682466893514e-06,
540
+ "loss": 15.7859,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.03417267184804256,
545
+ "grad_norm": 178.12464904785156,
546
+ "learning_rate": 9.998665130931587e-06,
547
+ "loss": 15.9824,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.03461647278113402,
552
+ "grad_norm": 213.6521759033203,
553
+ "learning_rate": 9.998647794969659e-06,
554
+ "loss": 15.8112,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.03506027371422549,
559
+ "grad_norm": 158.35516357421875,
560
+ "learning_rate": 9.998630459007732e-06,
561
+ "loss": 15.7298,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.03550407464731695,
566
+ "grad_norm": 221.17010498046875,
567
+ "learning_rate": 9.998613123045805e-06,
568
+ "loss": 15.4734,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.035947875580408406,
573
+ "grad_norm": 218.5003204345703,
574
+ "learning_rate": 9.998595787083876e-06,
575
+ "loss": 16.2934,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.03639167651349987,
580
+ "grad_norm": 162.29537963867188,
581
+ "learning_rate": 9.99857845112195e-06,
582
+ "loss": 15.4424,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.03683547744659133,
587
+ "grad_norm": 233.5081787109375,
588
+ "learning_rate": 9.998561115160022e-06,
589
+ "loss": 15.3749,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.03727927837968279,
594
+ "grad_norm": 230.38172912597656,
595
+ "learning_rate": 9.998543779198094e-06,
596
+ "loss": 15.4327,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.03772307931277426,
601
+ "grad_norm": 187.3807373046875,
602
+ "learning_rate": 9.998526443236167e-06,
603
+ "loss": 15.2466,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.03816688024586572,
608
+ "grad_norm": 287.6422119140625,
609
+ "learning_rate": 9.99850910727424e-06,
610
+ "loss": 16.137,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.038610681178957176,
615
+ "grad_norm": 144.71505737304688,
616
+ "learning_rate": 9.998491771312311e-06,
617
+ "loss": 15.2375,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.03905448211204864,
622
+ "grad_norm": 195.58685302734375,
623
+ "learning_rate": 9.998474435350384e-06,
624
+ "loss": 15.2691,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.0394982830451401,
629
+ "grad_norm": 156.4313201904297,
630
+ "learning_rate": 9.998457099388457e-06,
631
+ "loss": 15.098,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.03994208397823156,
636
+ "grad_norm": 211.72653198242188,
637
+ "learning_rate": 9.998439763426529e-06,
638
+ "loss": 15.3399,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.04038588491132303,
643
+ "grad_norm": 188.71702575683594,
644
+ "learning_rate": 9.998422427464602e-06,
645
+ "loss": 15.563,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.04082968584441449,
650
+ "grad_norm": 183.34080505371094,
651
+ "learning_rate": 9.998405091502675e-06,
652
+ "loss": 15.077,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.04127348677750595,
657
+ "grad_norm": 195.2317657470703,
658
+ "learning_rate": 9.998387755540748e-06,
659
+ "loss": 15.5238,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.04171728771059741,
664
+ "grad_norm": 165.41636657714844,
665
+ "learning_rate": 9.99837041957882e-06,
666
+ "loss": 15.4294,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.04216108864368887,
671
+ "grad_norm": 161.98556518554688,
672
+ "learning_rate": 9.998353083616892e-06,
673
+ "loss": 15.3307,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.04260488957678033,
678
+ "grad_norm": 204.99436950683594,
679
+ "learning_rate": 9.998335747654965e-06,
680
+ "loss": 15.0829,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.0430486905098718,
685
+ "grad_norm": 153.96363830566406,
686
+ "learning_rate": 9.998318411693037e-06,
687
+ "loss": 14.9974,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.04349249144296326,
692
+ "grad_norm": 212.83502197265625,
693
+ "learning_rate": 9.99830107573111e-06,
694
+ "loss": 14.8463,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.043936292376054724,
699
+ "grad_norm": 171.2718505859375,
700
+ "learning_rate": 9.998283739769183e-06,
701
+ "loss": 15.22,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.04438009330914618,
706
+ "grad_norm": 159.00628662109375,
707
+ "learning_rate": 9.998266403807254e-06,
708
+ "loss": 15.608,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.04438009330914618,
713
+ "eval_loss": 0.47256025671958923,
714
+ "eval_runtime": 675.519,
715
+ "eval_samples_per_second": 1797.715,
716
+ "eval_steps_per_second": 56.179,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 0.04482389424223764,
721
+ "grad_norm": 268.4474792480469,
722
+ "learning_rate": 9.998249067845328e-06,
723
+ "loss": 15.0797,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 0.04526769517532911,
728
+ "grad_norm": 195.7564697265625,
729
+ "learning_rate": 9.9982317318834e-06,
730
+ "loss": 15.2636,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 0.04571149610842057,
735
+ "grad_norm": 156.26730346679688,
736
+ "learning_rate": 9.998214395921472e-06,
737
+ "loss": 15.5175,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 0.04615529704151203,
742
+ "grad_norm": 171.27798461914062,
743
+ "learning_rate": 9.998197059959545e-06,
744
+ "loss": 15.1707,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 0.046599097974603494,
749
+ "grad_norm": 180.56385803222656,
750
+ "learning_rate": 9.998179723997618e-06,
751
+ "loss": 15.7545,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 0.047042898907694954,
756
+ "grad_norm": 165.36468505859375,
757
+ "learning_rate": 9.998162388035691e-06,
758
+ "loss": 14.6627,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 0.04748669984078641,
763
+ "grad_norm": 189.90077209472656,
764
+ "learning_rate": 9.998145052073763e-06,
765
+ "loss": 14.6988,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 0.04793050077387788,
770
+ "grad_norm": 225.11740112304688,
771
+ "learning_rate": 9.998127716111836e-06,
772
+ "loss": 15.1959,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 0.04837430170696934,
777
+ "grad_norm": 174.7201690673828,
778
+ "learning_rate": 9.998110380149909e-06,
779
+ "loss": 15.2072,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 0.0488181026400608,
784
+ "grad_norm": 182.18833923339844,
785
+ "learning_rate": 9.99809304418798e-06,
786
+ "loss": 15.2541,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 0.049261903573152264,
791
+ "grad_norm": 166.11903381347656,
792
+ "learning_rate": 9.998075708226053e-06,
793
+ "loss": 14.5574,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 0.049705704506243724,
798
+ "grad_norm": 154.42739868164062,
799
+ "learning_rate": 9.998058372264126e-06,
800
+ "loss": 14.5568,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 0.05014950543933518,
805
+ "grad_norm": 204.05294799804688,
806
+ "learning_rate": 9.998041036302198e-06,
807
+ "loss": 15.9922,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 0.05059330637242665,
812
+ "grad_norm": 150.65687561035156,
813
+ "learning_rate": 9.99802370034027e-06,
814
+ "loss": 14.9494,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 0.05103710730551811,
819
+ "grad_norm": 214.66461181640625,
820
+ "learning_rate": 9.998006364378344e-06,
821
+ "loss": 14.969,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 0.05148090823860957,
826
+ "grad_norm": 150.3427734375,
827
+ "learning_rate": 9.997989028416417e-06,
828
+ "loss": 15.8738,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 0.051924709171701035,
833
+ "grad_norm": 200.99319458007812,
834
+ "learning_rate": 9.997971692454488e-06,
835
+ "loss": 15.0359,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 0.052368510104792494,
840
+ "grad_norm": 160.50755310058594,
841
+ "learning_rate": 9.997954356492561e-06,
842
+ "loss": 14.3384,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 0.05281231103788396,
847
+ "grad_norm": 198.73057556152344,
848
+ "learning_rate": 9.997937020530634e-06,
849
+ "loss": 14.6252,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 0.05325611197097542,
854
+ "grad_norm": 284.5395202636719,
855
+ "learning_rate": 9.997919684568706e-06,
856
+ "loss": 14.4951,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 0.05369991290406688,
861
+ "grad_norm": 197.24905395507812,
862
+ "learning_rate": 9.997902348606779e-06,
863
+ "loss": 14.0584,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 0.054143713837158346,
868
+ "grad_norm": 210.77964782714844,
869
+ "learning_rate": 9.997885012644852e-06,
870
+ "loss": 14.7978,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 0.054587514770249805,
875
+ "grad_norm": 227.98147583007812,
876
+ "learning_rate": 9.997867676682923e-06,
877
+ "loss": 14.5782,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 0.055031315703341264,
882
+ "grad_norm": 174.67752075195312,
883
+ "learning_rate": 9.997850340720996e-06,
884
+ "loss": 15.018,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 0.05547511663643273,
889
+ "grad_norm": 211.7549285888672,
890
+ "learning_rate": 9.99783300475907e-06,
891
+ "loss": 14.7918,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 0.05591891756952419,
896
+ "grad_norm": 170.83355712890625,
897
+ "learning_rate": 9.997815668797141e-06,
898
+ "loss": 14.4284,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 0.05636271850261565,
903
+ "grad_norm": 200.0304412841797,
904
+ "learning_rate": 9.997798332835214e-06,
905
+ "loss": 14.2359,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 0.056806519435707116,
910
+ "grad_norm": 198.56309509277344,
911
+ "learning_rate": 9.997780996873287e-06,
912
+ "loss": 15.2276,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 0.057250320368798575,
917
+ "grad_norm": 193.32701110839844,
918
+ "learning_rate": 9.99776366091136e-06,
919
+ "loss": 14.369,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 0.057694121301890035,
924
+ "grad_norm": 167.3224639892578,
925
+ "learning_rate": 9.997746324949432e-06,
926
+ "loss": 14.5175,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 0.0581379222349815,
931
+ "grad_norm": 222.6139678955078,
932
+ "learning_rate": 9.997728988987505e-06,
933
+ "loss": 14.3153,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 0.05858172316807296,
938
+ "grad_norm": 200.5888671875,
939
+ "learning_rate": 9.997711653025578e-06,
940
+ "loss": 15.0348,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 0.05902552410116442,
945
+ "grad_norm": 152.54669189453125,
946
+ "learning_rate": 9.997694317063649e-06,
947
+ "loss": 14.2657,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 0.059469325034255886,
952
+ "grad_norm": 208.6412811279297,
953
+ "learning_rate": 9.997676981101722e-06,
954
+ "loss": 14.4811,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 0.059913125967347346,
959
+ "grad_norm": 163.86343383789062,
960
+ "learning_rate": 9.997659645139795e-06,
961
+ "loss": 14.364,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 0.060356926900438805,
966
+ "grad_norm": 196.13272094726562,
967
+ "learning_rate": 9.997642309177867e-06,
968
+ "loss": 14.9816,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 0.06080072783353027,
973
+ "grad_norm": 184.44252014160156,
974
+ "learning_rate": 9.99762497321594e-06,
975
+ "loss": 14.3186,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 0.06124452876662173,
980
+ "grad_norm": 188.05926513671875,
981
+ "learning_rate": 9.997607637254013e-06,
982
+ "loss": 14.0344,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 0.06168832969971319,
987
+ "grad_norm": 145.69866943359375,
988
+ "learning_rate": 9.997590301292084e-06,
989
+ "loss": 14.584,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 0.06213213063280466,
994
+ "grad_norm": 158.0360107421875,
995
+ "learning_rate": 9.997572965330157e-06,
996
+ "loss": 14.2096,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 0.06257593156589612,
1001
+ "grad_norm": 197.41757202148438,
1002
+ "learning_rate": 9.99755562936823e-06,
1003
+ "loss": 14.7819,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 0.06301973249898758,
1008
+ "grad_norm": 164.63351440429688,
1009
+ "learning_rate": 9.997538293406303e-06,
1010
+ "loss": 14.3291,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 0.06346353343207904,
1015
+ "grad_norm": 186.9270782470703,
1016
+ "learning_rate": 9.997520957444375e-06,
1017
+ "loss": 14.3004,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 0.0639073343651705,
1022
+ "grad_norm": 167.5779266357422,
1023
+ "learning_rate": 9.997503621482448e-06,
1024
+ "loss": 14.0414,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 0.06435113529826196,
1029
+ "grad_norm": 148.85032653808594,
1030
+ "learning_rate": 9.997486285520521e-06,
1031
+ "loss": 14.3065,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 0.06479493623135342,
1036
+ "grad_norm": 222.2272491455078,
1037
+ "learning_rate": 9.997468949558592e-06,
1038
+ "loss": 14.6169,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 0.0652387371644449,
1043
+ "grad_norm": 144.12142944335938,
1044
+ "learning_rate": 9.997451613596665e-06,
1045
+ "loss": 15.0054,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 0.06568253809753635,
1050
+ "grad_norm": 205.4581298828125,
1051
+ "learning_rate": 9.997434277634738e-06,
1052
+ "loss": 14.3197,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 0.06612633903062781,
1057
+ "grad_norm": 183.8268280029297,
1058
+ "learning_rate": 9.99741694167281e-06,
1059
+ "loss": 14.046,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 0.06657013996371927,
1064
+ "grad_norm": 131.39759826660156,
1065
+ "learning_rate": 9.997399605710883e-06,
1066
+ "loss": 14.4233,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 0.06701394089681073,
1071
+ "grad_norm": 160.77137756347656,
1072
+ "learning_rate": 9.997382269748956e-06,
1073
+ "loss": 13.7336,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 0.0674577418299022,
1078
+ "grad_norm": 137.20225524902344,
1079
+ "learning_rate": 9.997364933787027e-06,
1080
+ "loss": 13.8353,
1081
+ "step": 1520
1082
+ },
1083
+ {
1084
+ "epoch": 0.06790154276299366,
1085
+ "grad_norm": 214.53268432617188,
1086
+ "learning_rate": 9.9973475978251e-06,
1087
+ "loss": 14.3842,
1088
+ "step": 1530
1089
+ },
1090
+ {
1091
+ "epoch": 0.06834534369608512,
1092
+ "grad_norm": 162.3836669921875,
1093
+ "learning_rate": 9.997330261863174e-06,
1094
+ "loss": 14.3846,
1095
+ "step": 1540
1096
+ },
1097
+ {
1098
+ "epoch": 0.06878914462917658,
1099
+ "grad_norm": 151.75082397460938,
1100
+ "learning_rate": 9.997312925901247e-06,
1101
+ "loss": 14.2962,
1102
+ "step": 1550
1103
+ },
1104
+ {
1105
+ "epoch": 0.06923294556226804,
1106
+ "grad_norm": 201.07388305664062,
1107
+ "learning_rate": 9.997295589939318e-06,
1108
+ "loss": 14.6052,
1109
+ "step": 1560
1110
+ },
1111
+ {
1112
+ "epoch": 0.0696767464953595,
1113
+ "grad_norm": 135.7477264404297,
1114
+ "learning_rate": 9.997278253977391e-06,
1115
+ "loss": 14.0033,
1116
+ "step": 1570
1117
+ },
1118
+ {
1119
+ "epoch": 0.07012054742845097,
1120
+ "grad_norm": 157.89686584472656,
1121
+ "learning_rate": 9.997260918015464e-06,
1122
+ "loss": 13.8008,
1123
+ "step": 1580
1124
+ },
1125
+ {
1126
+ "epoch": 0.07056434836154243,
1127
+ "grad_norm": 169.57518005371094,
1128
+ "learning_rate": 9.997243582053536e-06,
1129
+ "loss": 13.9898,
1130
+ "step": 1590
1131
+ },
1132
+ {
1133
+ "epoch": 0.0710081492946339,
1134
+ "grad_norm": 182.89100646972656,
1135
+ "learning_rate": 9.997226246091609e-06,
1136
+ "loss": 14.0484,
1137
+ "step": 1600
1138
+ },
1139
+ {
1140
+ "epoch": 0.07145195022772535,
1141
+ "grad_norm": 170.64639282226562,
1142
+ "learning_rate": 9.997208910129682e-06,
1143
+ "loss": 14.1716,
1144
+ "step": 1610
1145
+ },
1146
+ {
1147
+ "epoch": 0.07189575116081681,
1148
+ "grad_norm": 179.93946838378906,
1149
+ "learning_rate": 9.997191574167753e-06,
1150
+ "loss": 13.6771,
1151
+ "step": 1620
1152
+ },
1153
+ {
1154
+ "epoch": 0.07233955209390827,
1155
+ "grad_norm": 145.3518829345703,
1156
+ "learning_rate": 9.997174238205826e-06,
1157
+ "loss": 13.9909,
1158
+ "step": 1630
1159
+ },
1160
+ {
1161
+ "epoch": 0.07278335302699974,
1162
+ "grad_norm": 153.2678680419922,
1163
+ "learning_rate": 9.9971569022439e-06,
1164
+ "loss": 13.6993,
1165
+ "step": 1640
1166
+ },
1167
+ {
1168
+ "epoch": 0.0732271539600912,
1169
+ "grad_norm": 170.7726287841797,
1170
+ "learning_rate": 9.99713956628197e-06,
1171
+ "loss": 13.7267,
1172
+ "step": 1650
1173
+ },
1174
+ {
1175
+ "epoch": 0.07367095489318266,
1176
+ "grad_norm": 137.22825622558594,
1177
+ "learning_rate": 9.997122230320044e-06,
1178
+ "loss": 13.9653,
1179
+ "step": 1660
1180
+ },
1181
+ {
1182
+ "epoch": 0.07411475582627412,
1183
+ "grad_norm": 184.2819366455078,
1184
+ "learning_rate": 9.997104894358117e-06,
1185
+ "loss": 14.0155,
1186
+ "step": 1670
1187
+ },
1188
+ {
1189
+ "epoch": 0.07455855675936558,
1190
+ "grad_norm": 186.31808471679688,
1191
+ "learning_rate": 9.99708755839619e-06,
1192
+ "loss": 14.1664,
1193
+ "step": 1680
1194
+ },
1195
+ {
1196
+ "epoch": 0.07500235769245704,
1197
+ "grad_norm": 159.4346160888672,
1198
+ "learning_rate": 9.997070222434261e-06,
1199
+ "loss": 13.9029,
1200
+ "step": 1690
1201
+ },
1202
+ {
1203
+ "epoch": 0.07544615862554852,
1204
+ "grad_norm": 148.49266052246094,
1205
+ "learning_rate": 9.997052886472334e-06,
1206
+ "loss": 14.4053,
1207
+ "step": 1700
1208
+ },
1209
+ {
1210
+ "epoch": 0.07588995955863997,
1211
+ "grad_norm": 154.17291259765625,
1212
+ "learning_rate": 9.997035550510407e-06,
1213
+ "loss": 14.4536,
1214
+ "step": 1710
1215
+ },
1216
+ {
1217
+ "epoch": 0.07633376049173143,
1218
+ "grad_norm": 164.39495849609375,
1219
+ "learning_rate": 9.997018214548479e-06,
1220
+ "loss": 14.1982,
1221
+ "step": 1720
1222
+ },
1223
+ {
1224
+ "epoch": 0.0767775614248229,
1225
+ "grad_norm": 203.73599243164062,
1226
+ "learning_rate": 9.997000878586552e-06,
1227
+ "loss": 13.7706,
1228
+ "step": 1730
1229
+ },
1230
+ {
1231
+ "epoch": 0.07722136235791435,
1232
+ "grad_norm": 201.3606719970703,
1233
+ "learning_rate": 9.996983542624625e-06,
1234
+ "loss": 14.2293,
1235
+ "step": 1740
1236
+ },
1237
+ {
1238
+ "epoch": 0.07766516329100583,
1239
+ "grad_norm": 158.88832092285156,
1240
+ "learning_rate": 9.996966206662696e-06,
1241
+ "loss": 13.9448,
1242
+ "step": 1750
1243
+ },
1244
+ {
1245
+ "epoch": 0.07810896422409729,
1246
+ "grad_norm": 193.7799530029297,
1247
+ "learning_rate": 9.99694887070077e-06,
1248
+ "loss": 13.4655,
1249
+ "step": 1760
1250
+ },
1251
+ {
1252
+ "epoch": 0.07855276515718874,
1253
+ "grad_norm": 189.9005889892578,
1254
+ "learning_rate": 9.996931534738842e-06,
1255
+ "loss": 13.5407,
1256
+ "step": 1770
1257
+ },
1258
+ {
1259
+ "epoch": 0.0789965660902802,
1260
+ "grad_norm": 161.69204711914062,
1261
+ "learning_rate": 9.996914198776914e-06,
1262
+ "loss": 13.9047,
1263
+ "step": 1780
1264
+ },
1265
+ {
1266
+ "epoch": 0.07944036702337166,
1267
+ "grad_norm": 168.77694702148438,
1268
+ "learning_rate": 9.996896862814987e-06,
1269
+ "loss": 13.7892,
1270
+ "step": 1790
1271
+ },
1272
+ {
1273
+ "epoch": 0.07988416795646312,
1274
+ "grad_norm": 168.03192138671875,
1275
+ "learning_rate": 9.99687952685306e-06,
1276
+ "loss": 13.3482,
1277
+ "step": 1800
1278
+ },
1279
+ {
1280
+ "epoch": 0.0803279688895546,
1281
+ "grad_norm": 140.20399475097656,
1282
+ "learning_rate": 9.996862190891131e-06,
1283
+ "loss": 13.9784,
1284
+ "step": 1810
1285
+ },
1286
+ {
1287
+ "epoch": 0.08077176982264606,
1288
+ "grad_norm": 157.78277587890625,
1289
+ "learning_rate": 9.996844854929204e-06,
1290
+ "loss": 14.3328,
1291
+ "step": 1820
1292
+ },
1293
+ {
1294
+ "epoch": 0.08121557075573752,
1295
+ "grad_norm": 155.1420135498047,
1296
+ "learning_rate": 9.996827518967278e-06,
1297
+ "loss": 13.6884,
1298
+ "step": 1830
1299
+ },
1300
+ {
1301
+ "epoch": 0.08165937168882897,
1302
+ "grad_norm": 135.9541473388672,
1303
+ "learning_rate": 9.996810183005349e-06,
1304
+ "loss": 13.5477,
1305
+ "step": 1840
1306
+ },
1307
+ {
1308
+ "epoch": 0.08210317262192043,
1309
+ "grad_norm": 163.42974853515625,
1310
+ "learning_rate": 9.996792847043422e-06,
1311
+ "loss": 13.2751,
1312
+ "step": 1850
1313
+ },
1314
+ {
1315
+ "epoch": 0.0825469735550119,
1316
+ "grad_norm": 168.12744140625,
1317
+ "learning_rate": 9.996775511081495e-06,
1318
+ "loss": 13.8876,
1319
+ "step": 1860
1320
+ },
1321
+ {
1322
+ "epoch": 0.08299077448810337,
1323
+ "grad_norm": 173.35897827148438,
1324
+ "learning_rate": 9.996758175119568e-06,
1325
+ "loss": 14.0019,
1326
+ "step": 1870
1327
+ },
1328
+ {
1329
+ "epoch": 0.08343457542119483,
1330
+ "grad_norm": 160.2526397705078,
1331
+ "learning_rate": 9.99674083915764e-06,
1332
+ "loss": 13.6193,
1333
+ "step": 1880
1334
+ },
1335
+ {
1336
+ "epoch": 0.08387837635428629,
1337
+ "grad_norm": 140.53231811523438,
1338
+ "learning_rate": 9.996723503195713e-06,
1339
+ "loss": 13.6471,
1340
+ "step": 1890
1341
+ },
1342
+ {
1343
+ "epoch": 0.08432217728737774,
1344
+ "grad_norm": 134.29800415039062,
1345
+ "learning_rate": 9.996706167233786e-06,
1346
+ "loss": 13.6341,
1347
+ "step": 1900
1348
+ },
1349
+ {
1350
+ "epoch": 0.0847659782204692,
1351
+ "grad_norm": 176.61903381347656,
1352
+ "learning_rate": 9.996688831271857e-06,
1353
+ "loss": 13.7481,
1354
+ "step": 1910
1355
+ },
1356
+ {
1357
+ "epoch": 0.08520977915356066,
1358
+ "grad_norm": 141.41427612304688,
1359
+ "learning_rate": 9.99667149530993e-06,
1360
+ "loss": 13.5171,
1361
+ "step": 1920
1362
+ },
1363
+ {
1364
+ "epoch": 0.08565358008665214,
1365
+ "grad_norm": 155.45187377929688,
1366
+ "learning_rate": 9.996654159348003e-06,
1367
+ "loss": 13.2516,
1368
+ "step": 1930
1369
+ },
1370
+ {
1371
+ "epoch": 0.0860973810197436,
1372
+ "grad_norm": 130.82913208007812,
1373
+ "learning_rate": 9.996636823386075e-06,
1374
+ "loss": 13.1989,
1375
+ "step": 1940
1376
+ },
1377
+ {
1378
+ "epoch": 0.08654118195283506,
1379
+ "grad_norm": 158.8917694091797,
1380
+ "learning_rate": 9.996619487424148e-06,
1381
+ "loss": 13.1475,
1382
+ "step": 1950
1383
+ },
1384
+ {
1385
+ "epoch": 0.08698498288592652,
1386
+ "grad_norm": 175.22116088867188,
1387
+ "learning_rate": 9.99660215146222e-06,
1388
+ "loss": 13.5781,
1389
+ "step": 1960
1390
+ },
1391
+ {
1392
+ "epoch": 0.08742878381901797,
1393
+ "grad_norm": 152.9134979248047,
1394
+ "learning_rate": 9.996584815500292e-06,
1395
+ "loss": 13.7951,
1396
+ "step": 1970
1397
+ },
1398
+ {
1399
+ "epoch": 0.08787258475210945,
1400
+ "grad_norm": 139.04403686523438,
1401
+ "learning_rate": 9.996567479538365e-06,
1402
+ "loss": 13.6352,
1403
+ "step": 1980
1404
+ },
1405
+ {
1406
+ "epoch": 0.08831638568520091,
1407
+ "grad_norm": 166.22174072265625,
1408
+ "learning_rate": 9.996550143576438e-06,
1409
+ "loss": 14.035,
1410
+ "step": 1990
1411
+ },
1412
+ {
1413
+ "epoch": 0.08876018661829237,
1414
+ "grad_norm": 148.52734375,
1415
+ "learning_rate": 9.99653280761451e-06,
1416
+ "loss": 14.207,
1417
+ "step": 2000
1418
+ },
1419
+ {
1420
+ "epoch": 0.08876018661829237,
1421
+ "eval_loss": 0.4256989657878876,
1422
+ "eval_runtime": 673.4968,
1423
+ "eval_samples_per_second": 1803.113,
1424
+ "eval_steps_per_second": 56.348,
1425
+ "step": 2000
1426
+ },
1427
+ {
1428
+ "epoch": 0.08920398755138383,
1429
+ "grad_norm": 155.57510375976562,
1430
+ "learning_rate": 9.996515471652583e-06,
1431
+ "loss": 13.5324,
1432
+ "step": 2010
1433
+ },
1434
+ {
1435
+ "epoch": 0.08964778848447529,
1436
+ "grad_norm": 172.14755249023438,
1437
+ "learning_rate": 9.996498135690656e-06,
1438
+ "loss": 13.7738,
1439
+ "step": 2020
1440
+ },
1441
+ {
1442
+ "epoch": 0.09009158941756674,
1443
+ "grad_norm": 175.1804656982422,
1444
+ "learning_rate": 9.996480799728727e-06,
1445
+ "loss": 13.6314,
1446
+ "step": 2030
1447
+ },
1448
+ {
1449
+ "epoch": 0.09053539035065822,
1450
+ "grad_norm": 157.45474243164062,
1451
+ "learning_rate": 9.9964634637668e-06,
1452
+ "loss": 13.6318,
1453
+ "step": 2040
1454
+ },
1455
+ {
1456
+ "epoch": 0.09097919128374968,
1457
+ "grad_norm": 149.86843872070312,
1458
+ "learning_rate": 9.996446127804873e-06,
1459
+ "loss": 13.761,
1460
+ "step": 2050
1461
+ },
1462
+ {
1463
+ "epoch": 0.09142299221684114,
1464
+ "grad_norm": 139.11117553710938,
1465
+ "learning_rate": 9.996428791842945e-06,
1466
+ "loss": 13.7724,
1467
+ "step": 2060
1468
+ },
1469
+ {
1470
+ "epoch": 0.0918667931499326,
1471
+ "grad_norm": 207.54212951660156,
1472
+ "learning_rate": 9.996411455881018e-06,
1473
+ "loss": 13.5893,
1474
+ "step": 2070
1475
+ },
1476
+ {
1477
+ "epoch": 0.09231059408302406,
1478
+ "grad_norm": 160.33975219726562,
1479
+ "learning_rate": 9.996394119919091e-06,
1480
+ "loss": 13.624,
1481
+ "step": 2080
1482
+ },
1483
+ {
1484
+ "epoch": 0.09275439501611552,
1485
+ "grad_norm": 130.01426696777344,
1486
+ "learning_rate": 9.996376783957164e-06,
1487
+ "loss": 13.8974,
1488
+ "step": 2090
1489
+ },
1490
+ {
1491
+ "epoch": 0.09319819594920699,
1492
+ "grad_norm": 132.64810180664062,
1493
+ "learning_rate": 9.996359447995235e-06,
1494
+ "loss": 13.4078,
1495
+ "step": 2100
1496
+ },
1497
+ {
1498
+ "epoch": 0.09364199688229845,
1499
+ "grad_norm": 148.302734375,
1500
+ "learning_rate": 9.996342112033308e-06,
1501
+ "loss": 14.1865,
1502
+ "step": 2110
1503
+ },
1504
+ {
1505
+ "epoch": 0.09408579781538991,
1506
+ "grad_norm": 185.2609405517578,
1507
+ "learning_rate": 9.996324776071382e-06,
1508
+ "loss": 13.5624,
1509
+ "step": 2120
1510
+ },
1511
+ {
1512
+ "epoch": 0.09452959874848137,
1513
+ "grad_norm": 159.40829467773438,
1514
+ "learning_rate": 9.996307440109453e-06,
1515
+ "loss": 13.428,
1516
+ "step": 2130
1517
+ },
1518
+ {
1519
+ "epoch": 0.09497339968157283,
1520
+ "grad_norm": 162.26693725585938,
1521
+ "learning_rate": 9.996290104147526e-06,
1522
+ "loss": 14.0764,
1523
+ "step": 2140
1524
+ },
1525
+ {
1526
+ "epoch": 0.0954172006146643,
1527
+ "grad_norm": 144.18853759765625,
1528
+ "learning_rate": 9.996272768185599e-06,
1529
+ "loss": 13.581,
1530
+ "step": 2150
1531
+ },
1532
+ {
1533
+ "epoch": 0.09586100154775576,
1534
+ "grad_norm": 141.41928100585938,
1535
+ "learning_rate": 9.99625543222367e-06,
1536
+ "loss": 14.1607,
1537
+ "step": 2160
1538
+ },
1539
+ {
1540
+ "epoch": 0.09630480248084722,
1541
+ "grad_norm": 144.21542358398438,
1542
+ "learning_rate": 9.996238096261744e-06,
1543
+ "loss": 13.6053,
1544
+ "step": 2170
1545
+ },
1546
+ {
1547
+ "epoch": 0.09674860341393868,
1548
+ "grad_norm": 146.44114685058594,
1549
+ "learning_rate": 9.996220760299817e-06,
1550
+ "loss": 13.3627,
1551
+ "step": 2180
1552
+ },
1553
+ {
1554
+ "epoch": 0.09719240434703014,
1555
+ "grad_norm": 142.94996643066406,
1556
+ "learning_rate": 9.996203424337888e-06,
1557
+ "loss": 13.0106,
1558
+ "step": 2190
1559
+ },
1560
+ {
1561
+ "epoch": 0.0976362052801216,
1562
+ "grad_norm": 137.17572021484375,
1563
+ "learning_rate": 9.996186088375961e-06,
1564
+ "loss": 13.2873,
1565
+ "step": 2200
1566
+ },
1567
+ {
1568
+ "epoch": 0.09808000621321307,
1569
+ "grad_norm": 165.0562744140625,
1570
+ "learning_rate": 9.996168752414034e-06,
1571
+ "loss": 14.0056,
1572
+ "step": 2210
1573
+ },
1574
+ {
1575
+ "epoch": 0.09852380714630453,
1576
+ "grad_norm": 154.87319946289062,
1577
+ "learning_rate": 9.996151416452106e-06,
1578
+ "loss": 13.6771,
1579
+ "step": 2220
1580
+ },
1581
+ {
1582
+ "epoch": 0.09896760807939599,
1583
+ "grad_norm": 145.29185485839844,
1584
+ "learning_rate": 9.996134080490179e-06,
1585
+ "loss": 13.2175,
1586
+ "step": 2230
1587
+ },
1588
+ {
1589
+ "epoch": 0.09941140901248745,
1590
+ "grad_norm": 138.25790405273438,
1591
+ "learning_rate": 9.996116744528252e-06,
1592
+ "loss": 13.4874,
1593
+ "step": 2240
1594
+ },
1595
+ {
1596
+ "epoch": 0.09985520994557891,
1597
+ "grad_norm": 129.90760803222656,
1598
+ "learning_rate": 9.996099408566323e-06,
1599
+ "loss": 13.2961,
1600
+ "step": 2250
1601
+ },
1602
+ {
1603
+ "epoch": 0.10029901087867037,
1604
+ "grad_norm": 167.95828247070312,
1605
+ "learning_rate": 9.996082072604396e-06,
1606
+ "loss": 13.8555,
1607
+ "step": 2260
1608
+ },
1609
+ {
1610
+ "epoch": 0.10074281181176184,
1611
+ "grad_norm": 171.57943725585938,
1612
+ "learning_rate": 9.99606473664247e-06,
1613
+ "loss": 13.7328,
1614
+ "step": 2270
1615
+ },
1616
+ {
1617
+ "epoch": 0.1011866127448533,
1618
+ "grad_norm": 129.10914611816406,
1619
+ "learning_rate": 9.99604740068054e-06,
1620
+ "loss": 13.1205,
1621
+ "step": 2280
1622
+ },
1623
+ {
1624
+ "epoch": 0.10163041367794476,
1625
+ "grad_norm": 142.1722869873047,
1626
+ "learning_rate": 9.996030064718614e-06,
1627
+ "loss": 13.4908,
1628
+ "step": 2290
1629
+ },
1630
+ {
1631
+ "epoch": 0.10207421461103622,
1632
+ "grad_norm": 174.66026306152344,
1633
+ "learning_rate": 9.996012728756687e-06,
1634
+ "loss": 12.8445,
1635
+ "step": 2300
1636
+ },
1637
+ {
1638
+ "epoch": 0.10251801554412768,
1639
+ "grad_norm": 159.54783630371094,
1640
+ "learning_rate": 9.99599539279476e-06,
1641
+ "loss": 12.9509,
1642
+ "step": 2310
1643
+ },
1644
+ {
1645
+ "epoch": 0.10296181647721914,
1646
+ "grad_norm": 119.40794372558594,
1647
+ "learning_rate": 9.995978056832831e-06,
1648
+ "loss": 13.689,
1649
+ "step": 2320
1650
+ },
1651
+ {
1652
+ "epoch": 0.10340561741031061,
1653
+ "grad_norm": 114.7558364868164,
1654
+ "learning_rate": 9.995960720870904e-06,
1655
+ "loss": 12.7327,
1656
+ "step": 2330
1657
+ },
1658
+ {
1659
+ "epoch": 0.10384941834340207,
1660
+ "grad_norm": 163.34475708007812,
1661
+ "learning_rate": 9.995943384908977e-06,
1662
+ "loss": 13.5477,
1663
+ "step": 2340
1664
+ },
1665
+ {
1666
+ "epoch": 0.10429321927649353,
1667
+ "grad_norm": 169.064208984375,
1668
+ "learning_rate": 9.995926048947049e-06,
1669
+ "loss": 13.7607,
1670
+ "step": 2350
1671
+ },
1672
+ {
1673
+ "epoch": 0.10473702020958499,
1674
+ "grad_norm": 128.2354736328125,
1675
+ "learning_rate": 9.995908712985122e-06,
1676
+ "loss": 13.8691,
1677
+ "step": 2360
1678
+ },
1679
+ {
1680
+ "epoch": 0.10518082114267645,
1681
+ "grad_norm": 184.0960235595703,
1682
+ "learning_rate": 9.995891377023195e-06,
1683
+ "loss": 13.9122,
1684
+ "step": 2370
1685
+ },
1686
+ {
1687
+ "epoch": 0.10562462207576792,
1688
+ "grad_norm": 143.75611877441406,
1689
+ "learning_rate": 9.995874041061266e-06,
1690
+ "loss": 13.1847,
1691
+ "step": 2380
1692
+ },
1693
+ {
1694
+ "epoch": 0.10606842300885938,
1695
+ "grad_norm": 160.75901794433594,
1696
+ "learning_rate": 9.99585670509934e-06,
1697
+ "loss": 13.3183,
1698
+ "step": 2390
1699
+ },
1700
+ {
1701
+ "epoch": 0.10651222394195084,
1702
+ "grad_norm": 178.99951171875,
1703
+ "learning_rate": 9.995839369137413e-06,
1704
+ "loss": 12.9939,
1705
+ "step": 2400
1706
+ },
1707
+ {
1708
+ "epoch": 0.1069560248750423,
1709
+ "grad_norm": 161.1572723388672,
1710
+ "learning_rate": 9.995822033175484e-06,
1711
+ "loss": 12.9724,
1712
+ "step": 2410
1713
+ },
1714
+ {
1715
+ "epoch": 0.10739982580813376,
1716
+ "grad_norm": 138.41233825683594,
1717
+ "learning_rate": 9.995804697213557e-06,
1718
+ "loss": 13.3155,
1719
+ "step": 2420
1720
+ },
1721
+ {
1722
+ "epoch": 0.10784362674122522,
1723
+ "grad_norm": 186.98597717285156,
1724
+ "learning_rate": 9.99578736125163e-06,
1725
+ "loss": 13.385,
1726
+ "step": 2430
1727
+ },
1728
+ {
1729
+ "epoch": 0.10828742767431669,
1730
+ "grad_norm": 148.47291564941406,
1731
+ "learning_rate": 9.995770025289701e-06,
1732
+ "loss": 12.6492,
1733
+ "step": 2440
1734
+ },
1735
+ {
1736
+ "epoch": 0.10873122860740815,
1737
+ "grad_norm": 187.78671264648438,
1738
+ "learning_rate": 9.995752689327775e-06,
1739
+ "loss": 13.181,
1740
+ "step": 2450
1741
+ },
1742
+ {
1743
+ "epoch": 0.10917502954049961,
1744
+ "grad_norm": 119.649658203125,
1745
+ "learning_rate": 9.995735353365848e-06,
1746
+ "loss": 13.285,
1747
+ "step": 2460
1748
+ },
1749
+ {
1750
+ "epoch": 0.10961883047359107,
1751
+ "grad_norm": 165.08554077148438,
1752
+ "learning_rate": 9.995718017403919e-06,
1753
+ "loss": 13.2161,
1754
+ "step": 2470
1755
+ },
1756
+ {
1757
+ "epoch": 0.11006263140668253,
1758
+ "grad_norm": 201.1644287109375,
1759
+ "learning_rate": 9.995700681441992e-06,
1760
+ "loss": 13.8907,
1761
+ "step": 2480
1762
+ },
1763
+ {
1764
+ "epoch": 0.11050643233977399,
1765
+ "grad_norm": 127.61051940917969,
1766
+ "learning_rate": 9.995683345480065e-06,
1767
+ "loss": 13.1687,
1768
+ "step": 2490
1769
+ },
1770
+ {
1771
+ "epoch": 0.11095023327286546,
1772
+ "grad_norm": 152.43359375,
1773
+ "learning_rate": 9.995666009518137e-06,
1774
+ "loss": 13.7492,
1775
+ "step": 2500
1776
+ }
1777
+ ],
1778
+ "logging_steps": 10,
1779
+ "max_steps": 22532,
1780
+ "num_input_tokens_seen": 0,
1781
+ "num_train_epochs": 1,
1782
+ "save_steps": 2500,
1783
+ "stateful_callbacks": {
1784
+ "TrainerControl": {
1785
+ "args": {
1786
+ "should_epoch_stop": false,
1787
+ "should_evaluate": false,
1788
+ "should_log": false,
1789
+ "should_save": true,
1790
+ "should_training_stop": false
1791
+ },
1792
+ "attributes": {}
1793
+ }
1794
+ },
1795
+ "total_flos": 8.72430801256448e+17,
1796
+ "train_batch_size": 4,
1797
+ "trial_name": null,
1798
+ "trial_params": null
1799
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8645fade10e36c63fb16b30876169d83bbbc9703d2205ae38a09c61598097e4f
3
+ size 5368