Hugging Face's logo

RaphaelMourad
/
Mistral-Peptide-v1-134M

Safetensors
mixtral
pretrained
mistral
peptide
Model card Files Community
RaphaelMourad commited on
Commit
b4d116e
•
1 Parent(s): 226affd

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +31 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +7 -0
  8. tokenizer.json +2091 -0
  9. tokenizer_config.json +52 -0
  10. trainer_state.json +1880 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "data/models/Mixtral-8x7B-v0.2-prot",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 768,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 8,
16
+ "num_experts_per_tok": 1,
17
+ "num_hidden_layers": 8,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.42.3",
29
+ "use_cache": true,
30
+ "vocab_size": 1024
31
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.42.3"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db61b9850993a03b6239022fb005aa3d4bcf9eaa0d06072f59fd02842d5534ed
3
+ size 267541944
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9866603f585c78358b869e049dc349279a1a3abf0fcc47810a378499bada5325
3
+ size 535234618
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86f749dc73bc16a2502fef2f98f5c00b4400cb2c67fbe62653b7ed104d13779
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f479978769d6c33afcd541e3944187c788c9f14cc1f06bee1c0b85d35dd5c3
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,2091 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[CLS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[SEP]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "Whitespace"
55
+ },
56
+ "post_processor": null,
57
+ "decoder": null,
58
+ "model": {
59
+ "type": "BPE",
60
+ "dropout": null,
61
+ "unk_token": "[UNK]",
62
+ "continuing_subword_prefix": null,
63
+ "end_of_word_suffix": null,
64
+ "fuse_unk": false,
65
+ "byte_fallback": false,
66
+ "vocab": {
67
+ "[UNK]": 0,
68
+ "[CLS]": 1,
69
+ "[SEP]": 2,
70
+ "[PAD]": 3,
71
+ "[MASK]": 4,
72
+ "A": 5,
73
+ "B": 6,
74
+ "C": 7,
75
+ "D": 8,
76
+ "E": 9,
77
+ "F": 10,
78
+ "G": 11,
79
+ "H": 12,
80
+ "I": 13,
81
+ "K": 14,
82
+ "L": 15,
83
+ "M": 16,
84
+ "N": 17,
85
+ "P": 18,
86
+ "Q": 19,
87
+ "R": 20,
88
+ "S": 21,
89
+ "T": 22,
90
+ "V": 23,
91
+ "W": 24,
92
+ "X": 25,
93
+ "Y": 26,
94
+ "Z": 27,
95
+ "AA": 28,
96
+ "SS": 29,
97
+ "TT": 30,
98
+ "GG": 31,
99
+ "LL": 32,
100
+ "AG": 33,
101
+ "LS": 34,
102
+ "TV": 35,
103
+ "AV": 36,
104
+ "AL": 37,
105
+ "AS": 38,
106
+ "DG": 39,
107
+ "TG": 40,
108
+ "EE": 41,
109
+ "TL": 42,
110
+ "TS": 43,
111
+ "DV": 44,
112
+ "AE": 45,
113
+ "DL": 46,
114
+ "SG": 47,
115
+ "AP": 48,
116
+ "RL": 49,
117
+ "VV": 50,
118
+ "SL": 51,
119
+ "TP": 52,
120
+ "TI": 53,
121
+ "EL": 54,
122
+ "SV": 55,
123
+ "AD": 56,
124
+ "NG": 57,
125
+ "AR": 58,
126
+ "EV": 59,
127
+ "QL": 60,
128
+ "TD": 61,
129
+ "AI": 62,
130
+ "NL": 63,
131
+ "EG": 64,
132
+ "PV": 65,
133
+ "KL": 66,
134
+ "PG": 67,
135
+ "EI": 68,
136
+ "NV": 69,
137
+ "DI": 70,
138
+ "PL": 71,
139
+ "DS": 72,
140
+ "KK": 73,
141
+ "RV": 74,
142
+ "NI": 75,
143
+ "AQ": 76,
144
+ "PS": 77,
145
+ "AT": 78,
146
+ "EK": 79,
147
+ "ES": 80,
148
+ "RG": 81,
149
+ "QQ": 82,
150
+ "NS": 83,
151
+ "DD": 84,
152
+ "AK": 85,
153
+ "RR": 86,
154
+ "VL": 87,
155
+ "AF": 88,
156
+ "TF": 89,
157
+ "RI": 90,
158
+ "PP": 91,
159
+ "QV": 92,
160
+ "TE": 93,
161
+ "AN": 94,
162
+ "SI": 95,
163
+ "KV": 96,
164
+ "QG": 97,
165
+ "KI": 98,
166
+ "RS": 99,
167
+ "TY": 100,
168
+ "DP": 101,
169
+ "NN": 102,
170
+ "KG": 103,
171
+ "DE": 104,
172
+ "QI": 105,
173
+ "FG": 106,
174
+ "VG": 107,
175
+ "YL": 108,
176
+ "FL": 109,
177
+ "TN": 110,
178
+ "PI": 111,
179
+ "KS": 112,
180
+ "QS": 113,
181
+ "PE": 114,
182
+ "AY": 115,
183
+ "HL": 116,
184
+ "RE": 117,
185
+ "FS": 118,
186
+ "FV": 119,
187
+ "TK": 120,
188
+ "GL": 121,
189
+ "VS": 122,
190
+ "TQ": 123,
191
+ "DN": 124,
192
+ "IL": 125,
193
+ "RP": 126,
194
+ "GS": 127,
195
+ "KE": 128,
196
+ "IS": 129,
197
+ "DF": 130,
198
+ "TR": 131,
199
+ "DR": 132,
200
+ "DY": 133,
201
+ "AH": 134,
202
+ "DK": 135,
203
+ "IG": 136,
204
+ "QE": 137,
205
+ "AM": 138,
206
+ "YG": 139,
207
+ "NE": 140,
208
+ "IV": 141,
209
+ "YS": 142,
210
+ "NP": 143,
211
+ "ER": 144,
212
+ "QP": 145,
213
+ "YV": 146,
214
+ "ML": 147,
215
+ "TA": 148,
216
+ "QR": 149,
217
+ "GV": 150,
218
+ "ND": 151,
219
+ "KP": 152,
220
+ "FE": 153,
221
+ "FI": 154,
222
+ "NK": 155,
223
+ "HS": 156,
224
+ "HG": 157,
225
+ "QK": 158,
226
+ "CL": 159,
227
+ "HV": 160,
228
+ "NY": 161,
229
+ "IE": 162,
230
+ "DQ": 163,
231
+ "WL": 164,
232
+ "RK": 165,
233
+ "CS": 166,
234
+ "NF": 167,
235
+ "RD": 168,
236
+ "EP": 169,
237
+ "RF": 170,
238
+ "AAL": 171,
239
+ "ED": 172,
240
+ "II": 173,
241
+ "TM": 174,
242
+ "TC": 175,
243
+ "NQ": 176,
244
+ "TH": 177,
245
+ "AGG": 178,
246
+ "FD": 179,
247
+ "AAG": 180,
248
+ "RQ": 181,
249
+ "AC": 182,
250
+ "PD": 183,
251
+ "VI": 184,
252
+ "EQ": 185,
253
+ "LG": 186,
254
+ "YI": 187,
255
+ "AW": 188,
256
+ "MS": 189,
257
+ "MV": 190,
258
+ "KD": 191,
259
+ "LV": 192,
260
+ "SSS": 193,
261
+ "NR": 194,
262
+ "CG": 195,
263
+ "HI": 196,
264
+ "PK": 197,
265
+ "TW": 198,
266
+ "RY": 199,
267
+ "EF": 200,
268
+ "EN": 201,
269
+ "ADG": 202,
270
+ "ALL": 203,
271
+ "PQ": 204,
272
+ "EY": 205,
273
+ "CV": 206,
274
+ "TAA": 207,
275
+ "PF": 208,
276
+ "XX": 209,
277
+ "TSS": 210,
278
+ "MG": 211,
279
+ "KQ": 212,
280
+ "ID": 213,
281
+ "PR": 214,
282
+ "TLS": 215,
283
+ "ASS": 216,
284
+ "QD": 217,
285
+ "RN": 218,
286
+ "WS": 219,
287
+ "RH": 220,
288
+ "FK": 221,
289
+ "VD": 222,
290
+ "VE": 223,
291
+ "KN": 224,
292
+ "TGG": 225,
293
+ "FF": 226,
294
+ "ASG": 227,
295
+ "QN": 228,
296
+ "ATT": 229,
297
+ "QY": 230,
298
+ "HP": 231,
299
+ "ATG": 232,
300
+ "ATV": 233,
301
+ "KY": 234,
302
+ "VP": 235,
303
+ "ALS": 236,
304
+ "QF": 237,
305
+ "IN": 238,
306
+ "TAG": 239,
307
+ "IK": 240,
308
+ "TAS": 241,
309
+ "SP": 242,
310
+ "YY": 243,
311
+ "FN": 244,
312
+ "LP": 245,
313
+ "IP": 246,
314
+ "YD": 247,
315
+ "EH": 248,
316
+ "TAV": 249,
317
+ "KR": 250,
318
+ "SD": 251,
319
+ "VR": 252,
320
+ "ATL": 253,
321
+ "GD": 254,
322
+ "EM": 255,
323
+ "TLL": 256,
324
+ "QH": 257,
325
+ "LD": 258,
326
+ "YR": 259,
327
+ "AAV": 260,
328
+ "TAL": 261,
329
+ "ATS": 262,
330
+ "KF": 263,
331
+ "GGG": 264,
332
+ "CP": 265,
333
+ "ADV": 266,
334
+ "SE": 267,
335
+ "LSG": 268,
336
+ "AEL": 269,
337
+ "AGL": 270,
338
+ "SF": 271,
339
+ "YN": 272,
340
+ "DH": 273,
341
+ "PN": 274,
342
+ "TAP": 275,
343
+ "VN": 276,
344
+ "ADL": 277,
345
+ "LLL": 278,
346
+ "SSG": 279,
347
+ "ASL": 280,
348
+ "SSL": 281,
349
+ "FR": 282,
350
+ "YE": 283,
351
+ "IR": 284,
352
+ "YK": 285,
353
+ "ARL": 286,
354
+ "DM": 287,
355
+ "HH": 288,
356
+ "WG": 289,
357
+ "FP": 290,
358
+ "VK": 291,
359
+ "EEL": 292,
360
+ "IQ": 293,
361
+ "AAS": 294,
362
+ "LSL": 295,
363
+ "CR": 296,
364
+ "TDG": 297,
365
+ "TSG": 298,
366
+ "MP": 299,
367
+ "ALG": 300,
368
+ "ANG": 301,
369
+ "AVL": 302,
370
+ "HR": 303,
371
+ "CI": 304,
372
+ "AAAA": 305,
373
+ "VF": 306,
374
+ "TTG": 307,
375
+ "ME": 308,
376
+ "YF": 309,
377
+ "SN": 310,
378
+ "MK": 311,
379
+ "TAE": 312,
380
+ "AEE": 313,
381
+ "YP": 314,
382
+ "HE": 315,
383
+ "MI": 316,
384
+ "CE": 317,
385
+ "VQ": 318,
386
+ "TAT": 319,
387
+ "YQ": 320,
388
+ "ATP": 321,
389
+ "TTS": 322,
390
+ "GE": 323,
391
+ "LLS": 324,
392
+ "AGS": 325,
393
+ "TEE": 326,
394
+ "FQ": 327,
395
+ "AGV": 328,
396
+ "GR": 329,
397
+ "WV": 330,
398
+ "XXXX": 331,
399
+ "TTL": 332,
400
+ "TVS": 333,
401
+ "GI": 334,
402
+ "CD": 335,
403
+ "TSL": 336,
404
+ "HD": 337,
405
+ "TDV": 338,
406
+ "MD": 339,
407
+ "ATI": 340,
408
+ "CK": 341,
409
+ "ATD": 342,
410
+ "TTV": 343,
411
+ "TGL": 344,
412
+ "MR": 345,
413
+ "TAD": 346,
414
+ "HF": 347,
415
+ "DGS": 348,
416
+ "SGS": 349,
417
+ "HQ": 350,
418
+ "CQ": 351,
419
+ "GGS": 352,
420
+ "WR": 353,
421
+ "IF": 354,
422
+ "LLG": 355,
423
+ "TDL": 356,
424
+ "DSDS": 357,
425
+ "AQL": 358,
426
+ "DVL": 359,
427
+ "MN": 360,
428
+ "MQ": 361,
429
+ "ASV": 362,
430
+ "TGS": 363,
431
+ "TVL": 364,
432
+ "HK": 365,
433
+ "GN": 366,
434
+ "DGL": 367,
435
+ "IY": 368,
436
+ "TEL": 369,
437
+ "DW": 370,
438
+ "TAI": 371,
439
+ "GP": 372,
440
+ "AVV": 373,
441
+ "GGL": 374,
442
+ "EVL": 375,
443
+ "SGL": 376,
444
+ "CN": 377,
445
+ "FY": 378,
446
+ "DAA": 379,
447
+ "SSV": 380,
448
+ "HY": 381,
449
+ "AVG": 382,
450
+ "HN": 383,
451
+ "PY": 384,
452
+ "SR": 385,
453
+ "SK": 386,
454
+ "APG": 387,
455
+ "ALV": 388,
456
+ "DGG": 389,
457
+ "SVL": 390,
458
+ "APL": 391,
459
+ "RVL": 392,
460
+ "LSV": 393,
461
+ "TEV": 394,
462
+ "RM": 395,
463
+ "ALP": 396,
464
+ "RW": 397,
465
+ "AVS": 398,
466
+ "DGV": 399,
467
+ "TPL": 400,
468
+ "AKL": 401,
469
+ "TSV": 402,
470
+ "AAP": 403,
471
+ "VVL": 404,
472
+ "ALR": 405,
473
+ "EC": 406,
474
+ "TEI": 407,
475
+ "TTTT": 408,
476
+ "SVS": 409,
477
+ "TAR": 410,
478
+ "TNG": 411,
479
+ "TEG": 412,
480
+ "EW": 413,
481
+ "AEG": 414,
482
+ "APV": 415,
483
+ "QM": 416,
484
+ "TVV": 417,
485
+ "TAQ": 418,
486
+ "PH": 419,
487
+ "CF": 420,
488
+ "ANL": 421,
489
+ "TES": 422,
490
+ "KM": 423,
491
+ "TPS": 424,
492
+ "GGV": 425,
493
+ "RLV": 426,
494
+ "NM": 427,
495
+ "PVL": 428,
496
+ "TLG": 429,
497
+ "DAG": 430,
498
+ "SSSS": 431,
499
+ "DC": 432,
500
+ "WI": 433,
501
+ "ELL": 434,
502
+ "EGL": 435,
503
+ "RLL": 436,
504
+ "ELG": 437,
505
+ "ANV": 438,
506
+ "SY": 439,
507
+ "EAA": 440,
508
+ "NH": 441,
509
+ "TVG": 442,
510
+ "SLV": 443,
511
+ "QQQQ": 444,
512
+ "PAA": 445,
513
+ "WQ": 446,
514
+ "EAL": 447,
515
+ "KH": 448,
516
+ "TNV": 449,
517
+ "SQ": 450,
518
+ "TGV": 451,
519
+ "MF": 452,
520
+ "DAL": 453,
521
+ "PAG": 454,
522
+ "DAV": 455,
523
+ "DLS": 456,
524
+ "TPV": 457,
525
+ "AEV": 458,
526
+ "DIL": 459,
527
+ "TNL": 460,
528
+ "PSP": 461,
529
+ "TLV": 462,
530
+ "WN": 463,
531
+ "WK": 464,
532
+ "TRL": 465,
533
+ "TTP": 466,
534
+ "ARG": 467,
535
+ "RC": 468,
536
+ "DLL": 469,
537
+ "DLV": 470,
538
+ "TAK": 471,
539
+ "PGL": 472,
540
+ "DLG": 473,
541
+ "SLG": 474,
542
+ "RAA": 475,
543
+ "DVV": 476,
544
+ "NGG": 477,
545
+ "SGV": 478,
546
+ "SSI": 479,
547
+ "TIS": 480,
548
+ "TPG": 481,
549
+ "RGL": 482,
550
+ "NC": 483,
551
+ "EEV": 484,
552
+ "TEK": 485,
553
+ "VVV": 486,
554
+ "FH": 487,
555
+ "YH": 488,
556
+ "EIL": 489,
557
+ "TAN": 490,
558
+ "NGL": 491,
559
+ "APS": 492,
560
+ "IH": 493,
561
+ "WE": 494,
562
+ "TQL": 495,
563
+ "RLG": 496,
564
+ "VVG": 497,
565
+ "TNI": 498,
566
+ "TLP": 499,
567
+ "SSP": 500,
568
+ "TTI": 501,
569
+ "DAS": 502,
570
+ "TKL": 503,
571
+ "NVL": 504,
572
+ "QLL": 505,
573
+ "TDS": 506,
574
+ "AIL": 507,
575
+ "AKK": 508,
576
+ "PLP": 509,
577
+ "QC": 510,
578
+ "DSL": 511,
579
+ "ELV": 512,
580
+ "DVS": 513,
581
+ "ANI": 514,
582
+ "NW": 515,
583
+ "ANS": 516,
584
+ "QW": 517,
585
+ "TSP": 518,
586
+ "QAA": 519,
587
+ "TNS": 520,
588
+ "DSS": 521,
589
+ "TAF": 522,
590
+ "PGS": 523,
591
+ "DSG": 524,
592
+ "VVS": 525,
593
+ "PM": 526,
594
+ "GK": 527,
595
+ "DAD": 528,
596
+ "LLV": 529,
597
+ "AGN": 530,
598
+ "LSP": 531,
599
+ "ESL": 532,
600
+ "NGS": 533,
601
+ "DDV": 534,
602
+ "EAV": 535,
603
+ "DEL": 536,
604
+ "TIL": 537,
605
+ "SVG": 538,
606
+ "NGV": 539,
607
+ "EEI": 540,
608
+ "AIG": 541,
609
+ "XXXXXXXX": 542,
610
+ "DDL": 543,
611
+ "AGI": 544,
612
+ "ASI": 545,
613
+ "CY": 546,
614
+ "FM": 547,
615
+ "AAR": 548,
616
+ "AAE": 549,
617
+ "AAI": 550,
618
+ "NIL": 551,
619
+ "TKK": 552,
620
+ "TSI": 553,
621
+ "TKV": 554,
622
+ "TVN": 555,
623
+ "DTL": 556,
624
+ "MY": 557,
625
+ "QGL": 558,
626
+ "AGE": 559,
627
+ "DEE": 560,
628
+ "ADS": 561,
629
+ "AGR": 562,
630
+ "SLP": 563,
631
+ "AES": 564,
632
+ "ASP": 565,
633
+ "LLE": 566,
634
+ "LSI": 567,
635
+ "DTV": 568,
636
+ "DTT": 569,
637
+ "PVG": 570,
638
+ "GGGG": 571,
639
+ "TRV": 572,
640
+ "PGV": 573,
641
+ "RAL": 574,
642
+ "PVS": 575,
643
+ "EVS": 576,
644
+ "AYL": 577,
645
+ "KC": 578,
646
+ "ADI": 579,
647
+ "WF": 580,
648
+ "NSS": 581,
649
+ "TQV": 582,
650
+ "DSI": 583,
651
+ "QAL": 584,
652
+ "PPP": 585,
653
+ "ARV": 586,
654
+ "EEE": 587,
655
+ "NTL": 588,
656
+ "DDG": 589,
657
+ "PDG": 590,
658
+ "RLR": 591,
659
+ "LLR": 592,
660
+ "DSV": 593,
661
+ "TTE": 594,
662
+ "EEG": 595,
663
+ "CH": 596,
664
+ "KW": 597,
665
+ "TKI": 598,
666
+ "AEI": 599,
667
+ "LSE": 600,
668
+ "MM": 601,
669
+ "AQG": 602,
670
+ "NVS": 603,
671
+ "DLP": 604,
672
+ "EGV": 605,
673
+ "DEV": 606,
674
+ "QQL": 607,
675
+ "EKL": 608,
676
+ "YW": 609,
677
+ "REL": 610,
678
+ "RIL": 611,
679
+ "LLP": 612,
680
+ "PLV": 613,
681
+ "DIS": 614,
682
+ "TAY": 615,
683
+ "AFL": 616,
684
+ "PVP": 617,
685
+ "QSL": 618,
686
+ "TVP": 619,
687
+ "NAA": 620,
688
+ "AIS": 621,
689
+ "ERL": 622,
690
+ "NLG": 623,
691
+ "RAV": 624,
692
+ "AQV": 625,
693
+ "EES": 626,
694
+ "DGI": 627,
695
+ "TIG": 628,
696
+ "EGS": 629,
697
+ "APP": 630,
698
+ "PLG": 631,
699
+ "LLK": 632,
700
+ "NLS": 633,
701
+ "TDI": 634,
702
+ "NLV": 635,
703
+ "QLV": 636,
704
+ "TPP": 637,
705
+ "RLS": 638,
706
+ "EEK": 639,
707
+ "DRL": 640,
708
+ "ETL": 641,
709
+ "VLG": 642,
710
+ "TRS": 643,
711
+ "TGN": 644,
712
+ "TQI": 645,
713
+ "TRG": 646,
714
+ "AHL": 647,
715
+ "ELP": 648,
716
+ "FC": 649,
717
+ "TNN": 650,
718
+ "DSDSDSDS": 651,
719
+ "TGI": 652,
720
+ "DTS": 653,
721
+ "RVS": 654,
722
+ "EIS": 655,
723
+ "MH": 656,
724
+ "KGL": 657,
725
+ "TIV": 658,
726
+ "TVE": 659,
727
+ "TLN": 660,
728
+ "DDI": 661,
729
+ "QLG": 662,
730
+ "DAE": 663,
731
+ "TVI": 664,
732
+ "DVG": 665,
733
+ "TQG": 666,
734
+ "FGL": 667,
735
+ "TKS": 668,
736
+ "QAV": 669,
737
+ "ARS": 670,
738
+ "KLV": 671,
739
+ "NIS": 672,
740
+ "DAP": 673,
741
+ "TQS": 674,
742
+ "DLI": 675,
743
+ "RGG": 676,
744
+ "WP": 677,
745
+ "AIV": 678,
746
+ "NSL": 679,
747
+ "DGK": 680,
748
+ "YM": 681,
749
+ "ESI": 682,
750
+ "RRL": 683,
751
+ "RSL": 684,
752
+ "ELS": 685,
753
+ "PSS": 686,
754
+ "EGG": 687,
755
+ "EKV": 688,
756
+ "QLS": 689,
757
+ "NTT": 690,
758
+ "RSS": 691,
759
+ "ESS": 692,
760
+ "ETT": 693,
761
+ "QSS": 694,
762
+ "TRI": 695,
763
+ "PGG": 696,
764
+ "EAE": 697,
765
+ "KIL": 698,
766
+ "FSS": 699,
767
+ "EIV": 700,
768
+ "SIL": 701,
769
+ "TDP": 702,
770
+ "NSG": 703,
771
+ "RGS": 704,
772
+ "TRR": 705,
773
+ "ADP": 706,
774
+ "QVV": 707,
775
+ "RVG": 708,
776
+ "TQQ": 709,
777
+ "DIV": 710,
778
+ "NVG": 711,
779
+ "KEL": 712,
780
+ "TLI": 713,
781
+ "QRL": 714,
782
+ "EAG": 715,
783
+ "AKV": 716,
784
+ "QIL": 717,
785
+ "AVI": 718,
786
+ "NLL": 719,
787
+ "NAG": 720,
788
+ "YC": 721,
789
+ "DTG": 722,
790
+ "NAS": 723,
791
+ "RAG": 724,
792
+ "NSI": 725,
793
+ "TVTV": 726,
794
+ "QGG": 727,
795
+ "SGI": 728,
796
+ "KGV": 729,
797
+ "HM": 730,
798
+ "QVL": 731,
799
+ "FGG": 732,
800
+ "EVV": 733,
801
+ "ESV": 734,
802
+ "QEL": 735,
803
+ "KEE": 736,
804
+ "DVI": 737,
805
+ "ETV": 738,
806
+ "PC": 739,
807
+ "AFG": 740,
808
+ "EKI": 741,
809
+ "ALI": 742,
810
+ "HC": 743,
811
+ "EQL": 744,
812
+ "TFS": 745,
813
+ "TPI": 746,
814
+ "SIS": 747,
815
+ "FW": 748,
816
+ "RGV": 749,
817
+ "NIG": 750,
818
+ "QTL": 751,
819
+ "EAS": 752,
820
+ "KLK": 753,
821
+ "NLI": 754,
822
+ "FSG": 755,
823
+ "RSG": 756,
824
+ "FDL": 757,
825
+ "PSI": 758,
826
+ "AVP": 759,
827
+ "TKG": 760,
828
+ "EDL": 761,
829
+ "KKKK": 762,
830
+ "RAR": 763,
831
+ "QAG": 764,
832
+ "EKS": 765,
833
+ "EVG": 766,
834
+ "TVK": 767,
835
+ "NAL": 768,
836
+ "DAI": 769,
837
+ "VGL": 770,
838
+ "NGI": 771,
839
+ "DEI": 772,
840
+ "AKG": 773,
841
+ "TLK": 774,
842
+ "EDV": 775,
843
+ "ETS": 776,
844
+ "ESG": 777,
845
+ "PTT": 778,
846
+ "WY": 779,
847
+ "KAL": 780,
848
+ "TVD": 781,
849
+ "KLG": 782,
850
+ "RDL": 783,
851
+ "QSV": 784,
852
+ "YLG": 785,
853
+ "LSF": 786,
854
+ "DQL": 787,
855
+ "TSGS": 788,
856
+ "CSS": 789,
857
+ "DDS": 790,
858
+ "DAR": 791,
859
+ "PAP": 792,
860
+ "RVV": 793,
861
+ "NTS": 794,
862
+ "PAV": 795,
863
+ "QAS": 796,
864
+ "AQS": 797,
865
+ "LSK": 798,
866
+ "EDG": 799,
867
+ "CC": 800,
868
+ "SLI": 801,
869
+ "DTI": 802,
870
+ "NTG": 803,
871
+ "RRS": 804,
872
+ "ELI": 805,
873
+ "NAV": 806,
874
+ "EVI": 807,
875
+ "QSG": 808,
876
+ "KLL": 809,
877
+ "DNL": 810,
878
+ "GGI": 811,
879
+ "KSS": 812,
880
+ "AAF": 813,
881
+ "RLP": 814,
882
+ "QTV": 815,
883
+ "QVS": 816,
884
+ "PVI": 817,
885
+ "VLV": 818,
886
+ "AHG": 819,
887
+ "TFL": 820,
888
+ "NSV": 821,
889
+ "DPS": 822,
890
+ "AKS": 823,
891
+ "RAE": 824,
892
+ "PSG": 825,
893
+ "QTT": 826,
894
+ "EKG": 827,
895
+ "KLI": 828,
896
+ "ENL": 829,
897
+ "RTL": 830,
898
+ "KKK": 831,
899
+ "LLI": 832,
900
+ "DRV": 833,
901
+ "FTG": 834,
902
+ "DAT": 835,
903
+ "NVV": 836,
904
+ "DVP": 837,
905
+ "AFV": 838,
906
+ "KSL": 839,
907
+ "DIG": 840,
908
+ "HW": 841,
909
+ "EPG": 842,
910
+ "DTD": 843,
911
+ "RRG": 844,
912
+ "PIL": 845,
913
+ "AAK": 846,
914
+ "FLG": 847,
915
+ "EII": 848,
916
+ "QGS": 849,
917
+ "NNI": 850,
918
+ "NNL": 851,
919
+ "NVI": 852,
920
+ "SIG": 853,
921
+ "TGK": 854,
922
+ "RTV": 855,
923
+ "NDG": 856,
924
+ "KKS": 857,
925
+ "AAQ": 858,
926
+ "FTV": 859,
927
+ "NDL": 860,
928
+ "DES": 861,
929
+ "RSV": 862,
930
+ "LLQ": 863,
931
+ "RDG": 864,
932
+ "ALK": 865,
933
+ "DEG": 866,
934
+ "ALE": 867,
935
+ "PEP": 868,
936
+ "TGP": 869,
937
+ "RAS": 870,
938
+ "ELK": 871,
939
+ "GLG": 872,
940
+ "DPV": 873,
941
+ "EKP": 874,
942
+ "DKL": 875,
943
+ "REE": 876,
944
+ "RVI": 877,
945
+ "NTV": 878,
946
+ "KVS": 879,
947
+ "DII": 880,
948
+ "KKI": 881,
949
+ "AML": 882,
950
+ "TYL": 883,
951
+ "EIG": 884,
952
+ "FSL": 885,
953
+ "AYV": 886,
954
+ "FAA": 887,
955
+ "QVG": 888,
956
+ "SVI": 889,
957
+ "ETI": 890,
958
+ "YGG": 891,
959
+ "VGV": 892,
960
+ "TYS": 893,
961
+ "KKV": 894,
962
+ "QTI": 895,
963
+ "NTI": 896,
964
+ "FGS": 897,
965
+ "AFS": 898,
966
+ "EEEE": 899,
967
+ "RLI": 900,
968
+ "RDV": 901,
969
+ "VGS": 902,
970
+ "TFG": 903,
971
+ "AGP": 904,
972
+ "RQL": 905,
973
+ "TRE": 906,
974
+ "RPG": 907,
975
+ "KIS": 908,
976
+ "ALQ": 909,
977
+ "HLL": 910,
978
+ "ARI": 911,
979
+ "EAP": 912,
980
+ "NNS": 913,
981
+ "QTS": 914,
982
+ "EGI": 915,
983
+ "FDV": 916,
984
+ "EPV": 917,
985
+ "TRP": 918,
986
+ "VVI": 919,
987
+ "NIV": 920,
988
+ "KAG": 921,
989
+ "NDV": 922,
990
+ "DNG": 923,
991
+ "QQV": 924,
992
+ "KKG": 925,
993
+ "QSI": 926,
994
+ "NEL": 927,
995
+ "QGV": 928,
996
+ "DNV": 929,
997
+ "KLS": 930,
998
+ "TAH": 931,
999
+ "QEE": 932,
1000
+ "SVP": 933,
1001
+ "ASF": 934,
1002
+ "API": 935,
1003
+ "KDL": 936,
1004
+ "QAE": 937,
1005
+ "EDI": 938,
1006
+ "RPV": 939,
1007
+ "RPL": 940,
1008
+ "WH": 941,
1009
+ "YTL": 942,
1010
+ "DPG": 943,
1011
+ "NNG": 944,
1012
+ "YSG": 945,
1013
+ "DPL": 946,
1014
+ "RIV": 947,
1015
+ "NII": 948,
1016
+ "EAI": 949,
1017
+ "ETG": 950,
1018
+ "RIS": 951,
1019
+ "EPL": 952,
1020
+ "DKV": 953,
1021
+ "PLL": 954,
1022
+ "YTV": 955,
1023
+ "PIG": 956,
1024
+ "FTL": 957,
1025
+ "PSL": 958,
1026
+ "AQI": 959,
1027
+ "WM": 960,
1028
+ "NAT": 961,
1029
+ "THL": 962,
1030
+ "DNS": 963,
1031
+ "QDL": 964,
1032
+ "QAR": 965,
1033
+ "QPG": 966,
1034
+ "PAL": 967,
1035
+ "CM": 968,
1036
+ "YTG": 969,
1037
+ "TFV": 970,
1038
+ "YSS": 971,
1039
+ "RTG": 972,
1040
+ "QIS": 973,
1041
+ "FVS": 974,
1042
+ "PAS": 975,
1043
+ "KEK": 976,
1044
+ "QPV": 977,
1045
+ "KDG": 978,
1046
+ "KAV": 979,
1047
+ "TII": 980,
1048
+ "QLI": 981,
1049
+ "FAG": 982,
1050
+ "DAN": 983,
1051
+ "AKI": 984,
1052
+ "RIG": 985,
1053
+ "NDI": 986,
1054
+ "QPL": 987,
1055
+ "RTT": 988,
1056
+ "PLS": 989,
1057
+ "ERV": 990,
1058
+ "PW": 991,
1059
+ "NAI": 992,
1060
+ "QTG": 993,
1061
+ "QKL": 994,
1062
+ "TYG": 995,
1063
+ "EKK": 996,
1064
+ "EAR": 997,
1065
+ "TAM": 998,
1066
+ "KVL": 999,
1067
+ "FDG": 1000,
1068
+ "KTL": 1001,
1069
+ "KGS": 1002,
1070
+ "XXXXXXXXXXXXXXXX": 1003,
1071
+ "PTE": 1004,
1072
+ "REV": 1005,
1073
+ "DKI": 1006,
1074
+ "QQG": 1007,
1075
+ "DAF": 1008,
1076
+ "KKL": 1009,
1077
+ "DAQ": 1010,
1078
+ "KAA": 1011,
1079
+ "PSV": 1012,
1080
+ "FSV": 1013,
1081
+ "DNI": 1014,
1082
+ "FGV": 1015,
1083
+ "DTP": 1016,
1084
+ "PIS": 1017,
1085
+ "FLS": 1018,
1086
+ "PEE": 1019,
1087
+ "QEV": 1020,
1088
+ "KEI": 1021,
1089
+ "GLV": 1022,
1090
+ "FAE": 1023
1091
+ },
1092
+ "merges": [
1093
+ "A A",
1094
+ "S S",
1095
+ "T T",
1096
+ "G G",
1097
+ "L L",
1098
+ "A G",
1099
+ "L S",
1100
+ "T V",
1101
+ "A V",
1102
+ "A L",
1103
+ "A S",
1104
+ "D G",
1105
+ "T G",
1106
+ "E E",
1107
+ "T L",
1108
+ "T S",
1109
+ "D V",
1110
+ "A E",
1111
+ "D L",
1112
+ "S G",
1113
+ "A P",
1114
+ "R L",
1115
+ "V V",
1116
+ "S L",
1117
+ "T P",
1118
+ "T I",
1119
+ "E L",
1120
+ "S V",
1121
+ "A D",
1122
+ "N G",
1123
+ "A R",
1124
+ "E V",
1125
+ "Q L",
1126
+ "T D",
1127
+ "A I",
1128
+ "N L",
1129
+ "E G",
1130
+ "P V",
1131
+ "K L",
1132
+ "P G",
1133
+ "E I",
1134
+ "N V",
1135
+ "D I",
1136
+ "P L",
1137
+ "D S",
1138
+ "K K",
1139
+ "R V",
1140
+ "N I",
1141
+ "A Q",
1142
+ "P S",
1143
+ "A T",
1144
+ "E K",
1145
+ "E S",
1146
+ "R G",
1147
+ "Q Q",
1148
+ "N S",
1149
+ "D D",
1150
+ "A K",
1151
+ "R R",
1152
+ "V L",
1153
+ "A F",
1154
+ "T F",
1155
+ "R I",
1156
+ "P P",
1157
+ "Q V",
1158
+ "T E",
1159
+ "A N",
1160
+ "S I",
1161
+ "K V",
1162
+ "Q G",
1163
+ "K I",
1164
+ "R S",
1165
+ "T Y",
1166
+ "D P",
1167
+ "N N",
1168
+ "K G",
1169
+ "D E",
1170
+ "Q I",
1171
+ "F G",
1172
+ "V G",
1173
+ "Y L",
1174
+ "F L",
1175
+ "T N",
1176
+ "P I",
1177
+ "K S",
1178
+ "Q S",
1179
+ "P E",
1180
+ "A Y",
1181
+ "H L",
1182
+ "R E",
1183
+ "F S",
1184
+ "F V",
1185
+ "T K",
1186
+ "G L",
1187
+ "V S",
1188
+ "T Q",
1189
+ "D N",
1190
+ "I L",
1191
+ "R P",
1192
+ "G S",
1193
+ "K E",
1194
+ "I S",
1195
+ "D F",
1196
+ "T R",
1197
+ "D R",
1198
+ "D Y",
1199
+ "A H",
1200
+ "D K",
1201
+ "I G",
1202
+ "Q E",
1203
+ "A M",
1204
+ "Y G",
1205
+ "N E",
1206
+ "I V",
1207
+ "Y S",
1208
+ "N P",
1209
+ "E R",
1210
+ "Q P",
1211
+ "Y V",
1212
+ "M L",
1213
+ "T A",
1214
+ "Q R",
1215
+ "G V",
1216
+ "N D",
1217
+ "K P",
1218
+ "F E",
1219
+ "F I",
1220
+ "N K",
1221
+ "H S",
1222
+ "H G",
1223
+ "Q K",
1224
+ "C L",
1225
+ "H V",
1226
+ "N Y",
1227
+ "I E",
1228
+ "D Q",
1229
+ "W L",
1230
+ "R K",
1231
+ "C S",
1232
+ "N F",
1233
+ "R D",
1234
+ "E P",
1235
+ "R F",
1236
+ "AA L",
1237
+ "E D",
1238
+ "I I",
1239
+ "T M",
1240
+ "T C",
1241
+ "N Q",
1242
+ "T H",
1243
+ "A GG",
1244
+ "F D",
1245
+ "AA G",
1246
+ "R Q",
1247
+ "A C",
1248
+ "P D",
1249
+ "V I",
1250
+ "E Q",
1251
+ "L G",
1252
+ "Y I",
1253
+ "A W",
1254
+ "M S",
1255
+ "M V",
1256
+ "K D",
1257
+ "L V",
1258
+ "SS S",
1259
+ "N R",
1260
+ "C G",
1261
+ "H I",
1262
+ "P K",
1263
+ "T W",
1264
+ "R Y",
1265
+ "E F",
1266
+ "E N",
1267
+ "A DG",
1268
+ "A LL",
1269
+ "P Q",
1270
+ "E Y",
1271
+ "C V",
1272
+ "T AA",
1273
+ "P F",
1274
+ "X X",
1275
+ "T SS",
1276
+ "M G",
1277
+ "K Q",
1278
+ "I D",
1279
+ "P R",
1280
+ "T LS",
1281
+ "A SS",
1282
+ "Q D",
1283
+ "R N",
1284
+ "W S",
1285
+ "R H",
1286
+ "F K",
1287
+ "V D",
1288
+ "V E",
1289
+ "K N",
1290
+ "T GG",
1291
+ "F F",
1292
+ "AS G",
1293
+ "Q N",
1294
+ "A TT",
1295
+ "Q Y",
1296
+ "H P",
1297
+ "A TG",
1298
+ "A TV",
1299
+ "K Y",
1300
+ "V P",
1301
+ "A LS",
1302
+ "Q F",
1303
+ "I N",
1304
+ "T AG",
1305
+ "I K",
1306
+ "T AS",
1307
+ "S P",
1308
+ "Y Y",
1309
+ "F N",
1310
+ "L P",
1311
+ "I P",
1312
+ "Y D",
1313
+ "E H",
1314
+ "T AV",
1315
+ "K R",
1316
+ "S D",
1317
+ "V R",
1318
+ "A TL",
1319
+ "G D",
1320
+ "E M",
1321
+ "T LL",
1322
+ "Q H",
1323
+ "L D",
1324
+ "Y R",
1325
+ "AA V",
1326
+ "T AL",
1327
+ "A TS",
1328
+ "K F",
1329
+ "GG G",
1330
+ "C P",
1331
+ "A DV",
1332
+ "S E",
1333
+ "LS G",
1334
+ "AE L",
1335
+ "AG L",
1336
+ "S F",
1337
+ "Y N",
1338
+ "D H",
1339
+ "P N",
1340
+ "T AP",
1341
+ "V N",
1342
+ "A DL",
1343
+ "LL L",
1344
+ "SS G",
1345
+ "AS L",
1346
+ "SS L",
1347
+ "F R",
1348
+ "Y E",
1349
+ "I R",
1350
+ "Y K",
1351
+ "A RL",
1352
+ "D M",
1353
+ "H H",
1354
+ "W G",
1355
+ "F P",
1356
+ "V K",
1357
+ "EE L",
1358
+ "I Q",
1359
+ "AA S",
1360
+ "LS L",
1361
+ "C R",
1362
+ "T DG",
1363
+ "TS G",
1364
+ "M P",
1365
+ "AL G",
1366
+ "A NG",
1367
+ "AV L",
1368
+ "H R",
1369
+ "C I",
1370
+ "AA AA",
1371
+ "V F",
1372
+ "TT G",
1373
+ "M E",
1374
+ "Y F",
1375
+ "S N",
1376
+ "M K",
1377
+ "T AE",
1378
+ "A EE",
1379
+ "Y P",
1380
+ "H E",
1381
+ "M I",
1382
+ "C E",
1383
+ "V Q",
1384
+ "T AT",
1385
+ "Y Q",
1386
+ "A TP",
1387
+ "TT S",
1388
+ "G E",
1389
+ "LL S",
1390
+ "AG S",
1391
+ "T EE",
1392
+ "F Q",
1393
+ "AG V",
1394
+ "G R",
1395
+ "W V",
1396
+ "XX XX",
1397
+ "TT L",
1398
+ "TV S",
1399
+ "G I",
1400
+ "C D",
1401
+ "TS L",
1402
+ "H D",
1403
+ "T DV",
1404
+ "M D",
1405
+ "A TI",
1406
+ "C K",
1407
+ "A TD",
1408
+ "TT V",
1409
+ "TG L",
1410
+ "M R",
1411
+ "T AD",
1412
+ "H F",
1413
+ "DG S",
1414
+ "SG S",
1415
+ "H Q",
1416
+ "C Q",
1417
+ "GG S",
1418
+ "W R",
1419
+ "I F",
1420
+ "LL G",
1421
+ "T DL",
1422
+ "DS DS",
1423
+ "A QL",
1424
+ "DV L",
1425
+ "M N",
1426
+ "M Q",
1427
+ "AS V",
1428
+ "TG S",
1429
+ "TV L",
1430
+ "H K",
1431
+ "G N",
1432
+ "DG L",
1433
+ "I Y",
1434
+ "T EL",
1435
+ "D W",
1436
+ "T AI",
1437
+ "G P",
1438
+ "AV V",
1439
+ "GG L",
1440
+ "EV L",
1441
+ "SG L",
1442
+ "C N",
1443
+ "F Y",
1444
+ "D AA",
1445
+ "SS V",
1446
+ "H Y",
1447
+ "AV G",
1448
+ "H N",
1449
+ "P Y",
1450
+ "S R",
1451
+ "S K",
1452
+ "AP G",
1453
+ "AL V",
1454
+ "D GG",
1455
+ "SV L",
1456
+ "AP L",
1457
+ "RV L",
1458
+ "LS V",
1459
+ "T EV",
1460
+ "R M",
1461
+ "AL P",
1462
+ "R W",
1463
+ "AV S",
1464
+ "DG V",
1465
+ "TP L",
1466
+ "A KL",
1467
+ "TS V",
1468
+ "AA P",
1469
+ "VV L",
1470
+ "AL R",
1471
+ "E C",
1472
+ "T EI",
1473
+ "TT TT",
1474
+ "SV S",
1475
+ "T AR",
1476
+ "T NG",
1477
+ "T EG",
1478
+ "E W",
1479
+ "AE G",
1480
+ "AP V",
1481
+ "Q M",
1482
+ "TV V",
1483
+ "T AQ",
1484
+ "P H",
1485
+ "C F",
1486
+ "A NL",
1487
+ "T ES",
1488
+ "K M",
1489
+ "TP S",
1490
+ "GG V",
1491
+ "RL V",
1492
+ "N M",
1493
+ "PV L",
1494
+ "TL G",
1495
+ "D AG",
1496
+ "SS SS",
1497
+ "D C",
1498
+ "W I",
1499
+ "E LL",
1500
+ "EG L",
1501
+ "R LL",
1502
+ "EL G",
1503
+ "A NV",
1504
+ "S Y",
1505
+ "E AA",
1506
+ "N H",
1507
+ "TV G",
1508
+ "SL V",
1509
+ "QQ QQ",
1510
+ "P AA",
1511
+ "W Q",
1512
+ "E AL",
1513
+ "K H",
1514
+ "T NV",
1515
+ "S Q",
1516
+ "TG V",
1517
+ "M F",
1518
+ "D AL",
1519
+ "P AG",
1520
+ "D AV",
1521
+ "D LS",
1522
+ "TP V",
1523
+ "AE V",
1524
+ "DI L",
1525
+ "T NL",
1526
+ "PS P",
1527
+ "TL V",
1528
+ "W N",
1529
+ "W K",
1530
+ "T RL",
1531
+ "TT P",
1532
+ "AR G",
1533
+ "R C",
1534
+ "D LL",
1535
+ "DL V",
1536
+ "T AK",
1537
+ "PG L",
1538
+ "DL G",
1539
+ "SL G",
1540
+ "R AA",
1541
+ "DV V",
1542
+ "N GG",
1543
+ "SG V",
1544
+ "SS I",
1545
+ "TI S",
1546
+ "TP G",
1547
+ "RG L",
1548
+ "N C",
1549
+ "EE V",
1550
+ "T EK",
1551
+ "VV V",
1552
+ "F H",
1553
+ "Y H",
1554
+ "EI L",
1555
+ "T AN",
1556
+ "NG L",
1557
+ "AP S",
1558
+ "I H",
1559
+ "W E",
1560
+ "T QL",
1561
+ "RL G",
1562
+ "VV G",
1563
+ "T NI",
1564
+ "TL P",
1565
+ "SS P",
1566
+ "TT I",
1567
+ "D AS",
1568
+ "T KL",
1569
+ "NV L",
1570
+ "Q LL",
1571
+ "TD S",
1572
+ "AI L",
1573
+ "A KK",
1574
+ "PL P",
1575
+ "Q C",
1576
+ "D SL",
1577
+ "EL V",
1578
+ "DV S",
1579
+ "A NI",
1580
+ "N W",
1581
+ "A NS",
1582
+ "Q W",
1583
+ "TS P",
1584
+ "Q AA",
1585
+ "T NS",
1586
+ "D SS",
1587
+ "T AF",
1588
+ "PG S",
1589
+ "D SG",
1590
+ "VV S",
1591
+ "P M",
1592
+ "G K",
1593
+ "D AD",
1594
+ "LL V",
1595
+ "AG N",
1596
+ "LS P",
1597
+ "E SL",
1598
+ "NG S",
1599
+ "D DV",
1600
+ "E AV",
1601
+ "D EL",
1602
+ "TI L",
1603
+ "SV G",
1604
+ "NG V",
1605
+ "EE I",
1606
+ "AI G",
1607
+ "XXXX XXXX",
1608
+ "D DL",
1609
+ "AG I",
1610
+ "AS I",
1611
+ "C Y",
1612
+ "F M",
1613
+ "AA R",
1614
+ "AA E",
1615
+ "AA I",
1616
+ "NI L",
1617
+ "T KK",
1618
+ "TS I",
1619
+ "T KV",
1620
+ "TV N",
1621
+ "D TL",
1622
+ "M Y",
1623
+ "QG L",
1624
+ "AG E",
1625
+ "D EE",
1626
+ "AD S",
1627
+ "AG R",
1628
+ "SL P",
1629
+ "AE S",
1630
+ "AS P",
1631
+ "LL E",
1632
+ "LS I",
1633
+ "D TV",
1634
+ "D TT",
1635
+ "PV G",
1636
+ "GG GG",
1637
+ "T RV",
1638
+ "PG V",
1639
+ "R AL",
1640
+ "PV S",
1641
+ "EV S",
1642
+ "A YL",
1643
+ "K C",
1644
+ "AD I",
1645
+ "W F",
1646
+ "N SS",
1647
+ "T QV",
1648
+ "DS I",
1649
+ "Q AL",
1650
+ "PP P",
1651
+ "AR V",
1652
+ "EE E",
1653
+ "N TL",
1654
+ "D DG",
1655
+ "P DG",
1656
+ "RL R",
1657
+ "LL R",
1658
+ "D SV",
1659
+ "TT E",
1660
+ "EE G",
1661
+ "C H",
1662
+ "K W",
1663
+ "T KI",
1664
+ "AE I",
1665
+ "LS E",
1666
+ "M M",
1667
+ "AQ G",
1668
+ "NV S",
1669
+ "DL P",
1670
+ "EG V",
1671
+ "D EV",
1672
+ "Q QL",
1673
+ "E KL",
1674
+ "Y W",
1675
+ "R EL",
1676
+ "RI L",
1677
+ "LL P",
1678
+ "PL V",
1679
+ "DI S",
1680
+ "T AY",
1681
+ "AF L",
1682
+ "PV P",
1683
+ "Q SL",
1684
+ "TV P",
1685
+ "N AA",
1686
+ "AI S",
1687
+ "E RL",
1688
+ "NL G",
1689
+ "R AV",
1690
+ "AQ V",
1691
+ "EE S",
1692
+ "DG I",
1693
+ "TI G",
1694
+ "EG S",
1695
+ "AP P",
1696
+ "PL G",
1697
+ "LL K",
1698
+ "N LS",
1699
+ "TD I",
1700
+ "NL V",
1701
+ "QL V",
1702
+ "TP P",
1703
+ "R LS",
1704
+ "EE K",
1705
+ "D RL",
1706
+ "E TL",
1707
+ "VL G",
1708
+ "T RS",
1709
+ "TG N",
1710
+ "T QI",
1711
+ "T RG",
1712
+ "A HL",
1713
+ "EL P",
1714
+ "F C",
1715
+ "T NN",
1716
+ "DSDS DSDS",
1717
+ "TG I",
1718
+ "D TS",
1719
+ "RV S",
1720
+ "EI S",
1721
+ "M H",
1722
+ "KG L",
1723
+ "TI V",
1724
+ "TV E",
1725
+ "TL N",
1726
+ "D DI",
1727
+ "QL G",
1728
+ "D AE",
1729
+ "TV I",
1730
+ "DV G",
1731
+ "T QG",
1732
+ "FG L",
1733
+ "T KS",
1734
+ "Q AV",
1735
+ "AR S",
1736
+ "KL V",
1737
+ "NI S",
1738
+ "D AP",
1739
+ "T QS",
1740
+ "DL I",
1741
+ "R GG",
1742
+ "W P",
1743
+ "AI V",
1744
+ "N SL",
1745
+ "DG K",
1746
+ "Y M",
1747
+ "ES I",
1748
+ "R RL",
1749
+ "R SL",
1750
+ "E LS",
1751
+ "P SS",
1752
+ "E GG",
1753
+ "EK V",
1754
+ "Q LS",
1755
+ "N TT",
1756
+ "R SS",
1757
+ "E SS",
1758
+ "E TT",
1759
+ "Q SS",
1760
+ "T RI",
1761
+ "P GG",
1762
+ "E AE",
1763
+ "KI L",
1764
+ "F SS",
1765
+ "EI V",
1766
+ "SI L",
1767
+ "TD P",
1768
+ "N SG",
1769
+ "RG S",
1770
+ "T RR",
1771
+ "AD P",
1772
+ "Q VV",
1773
+ "RV G",
1774
+ "T QQ",
1775
+ "DI V",
1776
+ "NV G",
1777
+ "K EL",
1778
+ "TL I",
1779
+ "Q RL",
1780
+ "E AG",
1781
+ "AK V",
1782
+ "QI L",
1783
+ "AV I",
1784
+ "N LL",
1785
+ "N AG",
1786
+ "Y C",
1787
+ "D TG",
1788
+ "N AS",
1789
+ "R AG",
1790
+ "NS I",
1791
+ "TV TV",
1792
+ "Q GG",
1793
+ "SG I",
1794
+ "KG V",
1795
+ "H M",
1796
+ "Q VL",
1797
+ "F GG",
1798
+ "E VV",
1799
+ "E SV",
1800
+ "Q EL",
1801
+ "K EE",
1802
+ "DV I",
1803
+ "E TV",
1804
+ "P C",
1805
+ "AF G",
1806
+ "EK I",
1807
+ "AL I",
1808
+ "H C",
1809
+ "E QL",
1810
+ "TF S",
1811
+ "TP I",
1812
+ "SI S",
1813
+ "F W",
1814
+ "RG V",
1815
+ "NI G",
1816
+ "Q TL",
1817
+ "E AS",
1818
+ "KL K",
1819
+ "NL I",
1820
+ "F SG",
1821
+ "R SG",
1822
+ "F DL",
1823
+ "PS I",
1824
+ "AV P",
1825
+ "T KG",
1826
+ "E DL",
1827
+ "KK KK",
1828
+ "R AR",
1829
+ "Q AG",
1830
+ "EK S",
1831
+ "EV G",
1832
+ "TV K",
1833
+ "N AL",
1834
+ "D AI",
1835
+ "VG L",
1836
+ "NG I",
1837
+ "D EI",
1838
+ "AK G",
1839
+ "TL K",
1840
+ "E DV",
1841
+ "E TS",
1842
+ "E SG",
1843
+ "P TT",
1844
+ "W Y",
1845
+ "K AL",
1846
+ "TV D",
1847
+ "KL G",
1848
+ "R DL",
1849
+ "Q SV",
1850
+ "YL G",
1851
+ "LS F",
1852
+ "D QL",
1853
+ "TS GS",
1854
+ "C SS",
1855
+ "D DS",
1856
+ "D AR",
1857
+ "P AP",
1858
+ "R VV",
1859
+ "N TS",
1860
+ "P AV",
1861
+ "Q AS",
1862
+ "AQ S",
1863
+ "LS K",
1864
+ "E DG",
1865
+ "C C",
1866
+ "SL I",
1867
+ "D TI",
1868
+ "N TG",
1869
+ "RR S",
1870
+ "EL I",
1871
+ "N AV",
1872
+ "EV I",
1873
+ "Q SG",
1874
+ "K LL",
1875
+ "D NL",
1876
+ "GG I",
1877
+ "K SS",
1878
+ "AA F",
1879
+ "RL P",
1880
+ "Q TV",
1881
+ "QV S",
1882
+ "PV I",
1883
+ "VL V",
1884
+ "AH G",
1885
+ "TF L",
1886
+ "N SV",
1887
+ "D PS",
1888
+ "AK S",
1889
+ "R AE",
1890
+ "P SG",
1891
+ "Q TT",
1892
+ "EK G",
1893
+ "KL I",
1894
+ "E NL",
1895
+ "R TL",
1896
+ "KK K",
1897
+ "LL I",
1898
+ "D RV",
1899
+ "F TG",
1900
+ "D AT",
1901
+ "N VV",
1902
+ "DV P",
1903
+ "AF V",
1904
+ "K SL",
1905
+ "DI G",
1906
+ "H W",
1907
+ "E PG",
1908
+ "D TD",
1909
+ "R RG",
1910
+ "PI L",
1911
+ "AA K",
1912
+ "FL G",
1913
+ "EI I",
1914
+ "QG S",
1915
+ "N NI",
1916
+ "N NL",
1917
+ "NV I",
1918
+ "SI G",
1919
+ "TG K",
1920
+ "R TV",
1921
+ "N DG",
1922
+ "KK S",
1923
+ "AA Q",
1924
+ "F TV",
1925
+ "N DL",
1926
+ "D ES",
1927
+ "R SV",
1928
+ "LL Q",
1929
+ "R DG",
1930
+ "AL K",
1931
+ "D EG",
1932
+ "AL E",
1933
+ "PE P",
1934
+ "TG P",
1935
+ "R AS",
1936
+ "EL K",
1937
+ "GL G",
1938
+ "D PV",
1939
+ "EK P",
1940
+ "D KL",
1941
+ "R EE",
1942
+ "RV I",
1943
+ "N TV",
1944
+ "KV S",
1945
+ "DI I",
1946
+ "KK I",
1947
+ "AM L",
1948
+ "TY L",
1949
+ "EI G",
1950
+ "F SL",
1951
+ "AY V",
1952
+ "F AA",
1953
+ "QV G",
1954
+ "SV I",
1955
+ "E TI",
1956
+ "Y GG",
1957
+ "VG V",
1958
+ "TY S",
1959
+ "KK V",
1960
+ "Q TI",
1961
+ "N TI",
1962
+ "FG S",
1963
+ "AF S",
1964
+ "EE EE",
1965
+ "RL I",
1966
+ "R DV",
1967
+ "VG S",
1968
+ "TF G",
1969
+ "AG P",
1970
+ "R QL",
1971
+ "T RE",
1972
+ "R PG",
1973
+ "KI S",
1974
+ "AL Q",
1975
+ "H LL",
1976
+ "AR I",
1977
+ "E AP",
1978
+ "N NS",
1979
+ "Q TS",
1980
+ "EG I",
1981
+ "F DV",
1982
+ "E PV",
1983
+ "T RP",
1984
+ "VV I",
1985
+ "NI V",
1986
+ "K AG",
1987
+ "N DV",
1988
+ "D NG",
1989
+ "QQ V",
1990
+ "KK G",
1991
+ "Q SI",
1992
+ "N EL",
1993
+ "QG V",
1994
+ "D NV",
1995
+ "K LS",
1996
+ "T AH",
1997
+ "Q EE",
1998
+ "SV P",
1999
+ "AS F",
2000
+ "AP I",
2001
+ "K DL",
2002
+ "Q AE",
2003
+ "E DI",
2004
+ "R PV",
2005
+ "R PL",
2006
+ "W H",
2007
+ "Y TL",
2008
+ "D PG",
2009
+ "N NG",
2010
+ "Y SG",
2011
+ "D PL",
2012
+ "RI V",
2013
+ "NI I",
2014
+ "E AI",
2015
+ "E TG",
2016
+ "RI S",
2017
+ "E PL",
2018
+ "D KV",
2019
+ "P LL",
2020
+ "Y TV",
2021
+ "PI G",
2022
+ "F TL",
2023
+ "P SL",
2024
+ "AQ I",
2025
+ "W M",
2026
+ "N AT",
2027
+ "T HL",
2028
+ "D NS",
2029
+ "Q DL",
2030
+ "Q AR",
2031
+ "Q PG",
2032
+ "P AL",
2033
+ "C M",
2034
+ "Y TG",
2035
+ "TF V",
2036
+ "Y SS",
2037
+ "R TG",
2038
+ "QI S",
2039
+ "FV S",
2040
+ "P AS",
2041
+ "K EK",
2042
+ "Q PV",
2043
+ "K DG",
2044
+ "K AV",
2045
+ "TI I",
2046
+ "QL I",
2047
+ "F AG",
2048
+ "D AN",
2049
+ "AK I",
2050
+ "RI G",
2051
+ "N DI",
2052
+ "Q PL",
2053
+ "R TT",
2054
+ "P LS",
2055
+ "E RV",
2056
+ "P W",
2057
+ "N AI",
2058
+ "Q TG",
2059
+ "Q KL",
2060
+ "TY G",
2061
+ "E KK",
2062
+ "E AR",
2063
+ "T AM",
2064
+ "K VL",
2065
+ "F DG",
2066
+ "K TL",
2067
+ "KG S",
2068
+ "XXXXXXXX XXXXXXXX",
2069
+ "P TE",
2070
+ "R EV",
2071
+ "D KI",
2072
+ "QQ G",
2073
+ "D AF",
2074
+ "K KL",
2075
+ "D AQ",
2076
+ "K AA",
2077
+ "P SV",
2078
+ "F SV",
2079
+ "D NI",
2080
+ "FG V",
2081
+ "D TP",
2082
+ "PI S",
2083
+ "F LS",
2084
+ "P EE",
2085
+ "Q EV",
2086
+ "K EI",
2087
+ "GL V",
2088
+ "F AE"
2089
+ ]
2090
+ }
2091
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "mask_token": "[MASK]",
47
+ "model_max_length": 1000000000000000019884624838656,
48
+ "pad_token": "[PAD]",
49
+ "sep_token": "[SEP]",
50
+ "tokenizer_class": "PreTrainedTokenizerFast",
51
+ "unk_token": "[UNK]"
52
+ }
trainer_state.json ADDED
@@ -0,0 +1,1880 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 5.3026299476623535,
3
+ "best_model_checkpoint": "./results/models/checkpoint-121302",
4
+ "epoch": 18.0,
5
+ "eval_steps": 500,
6
+ "global_step": 121302,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07419498441905327,
13
+ "grad_norm": 0.6640625,
14
+ "learning_rate": 0.000998516100311619,
15
+ "loss": 5.6889,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.14838996883810654,
20
+ "grad_norm": 0.6484375,
21
+ "learning_rate": 0.0009970322006232378,
22
+ "loss": 5.5782,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.22258495325715982,
27
+ "grad_norm": 0.75,
28
+ "learning_rate": 0.0009955483009348569,
29
+ "loss": 5.5562,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.2967799376762131,
34
+ "grad_norm": 0.80078125,
35
+ "learning_rate": 0.0009940644012464757,
36
+ "loss": 5.5537,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.37097492209526634,
41
+ "grad_norm": 0.765625,
42
+ "learning_rate": 0.0009925805015580946,
43
+ "loss": 5.5436,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.44516990651431965,
48
+ "grad_norm": 2.109375,
49
+ "learning_rate": 0.0009910966018697137,
50
+ "loss": 5.5482,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.5193648909333729,
55
+ "grad_norm": 0.92578125,
56
+ "learning_rate": 0.0009896127021813326,
57
+ "loss": 5.5504,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.5935598753524262,
62
+ "grad_norm": 1.3359375,
63
+ "learning_rate": 0.0009881288024929514,
64
+ "loss": 5.5373,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.6677548597714794,
69
+ "grad_norm": 1.0078125,
70
+ "learning_rate": 0.0009866449028045703,
71
+ "loss": 5.5279,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.7419498441905327,
76
+ "grad_norm": 5.78125,
77
+ "learning_rate": 0.0009851610031161894,
78
+ "loss": 5.5215,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.816144828609586,
83
+ "grad_norm": 4.65625,
84
+ "learning_rate": 0.0009836771034278083,
85
+ "loss": 5.5206,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.8903398130286393,
90
+ "grad_norm": 10.125,
91
+ "learning_rate": 0.0009821932037394272,
92
+ "loss": 5.5186,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.9645347974476925,
97
+ "grad_norm": 12.0,
98
+ "learning_rate": 0.0009807093040510462,
99
+ "loss": 5.5166,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 1.0,
104
+ "eval_loss": 5.499637603759766,
105
+ "eval_runtime": 2.498,
106
+ "eval_samples_per_second": 400.319,
107
+ "eval_steps_per_second": 3.203,
108
+ "step": 6739
109
+ },
110
+ {
111
+ "epoch": 1.0387297818667458,
112
+ "grad_norm": 1.2734375,
113
+ "learning_rate": 0.0009792254043626651,
114
+ "loss": 5.5143,
115
+ "step": 7000
116
+ },
117
+ {
118
+ "epoch": 1.112924766285799,
119
+ "grad_norm": 0.76953125,
120
+ "learning_rate": 0.000977741504674284,
121
+ "loss": 5.5052,
122
+ "step": 7500
123
+ },
124
+ {
125
+ "epoch": 1.1871197507048523,
126
+ "grad_norm": 1.203125,
127
+ "learning_rate": 0.000976257604985903,
128
+ "loss": 5.5022,
129
+ "step": 8000
130
+ },
131
+ {
132
+ "epoch": 1.2613147351239056,
133
+ "grad_norm": 2.671875,
134
+ "learning_rate": 0.000974773705297522,
135
+ "loss": 5.4968,
136
+ "step": 8500
137
+ },
138
+ {
139
+ "epoch": 1.3355097195429588,
140
+ "grad_norm": 0.9375,
141
+ "learning_rate": 0.0009732898056091408,
142
+ "loss": 5.4938,
143
+ "step": 9000
144
+ },
145
+ {
146
+ "epoch": 1.4097047039620123,
147
+ "grad_norm": 7.21875,
148
+ "learning_rate": 0.0009718059059207598,
149
+ "loss": 5.4899,
150
+ "step": 9500
151
+ },
152
+ {
153
+ "epoch": 1.4838996883810656,
154
+ "grad_norm": 0.80078125,
155
+ "learning_rate": 0.0009703220062323788,
156
+ "loss": 5.4853,
157
+ "step": 10000
158
+ },
159
+ {
160
+ "epoch": 1.5580946728001188,
161
+ "grad_norm": 0.7890625,
162
+ "learning_rate": 0.0009688381065439977,
163
+ "loss": 5.4836,
164
+ "step": 10500
165
+ },
166
+ {
167
+ "epoch": 1.632289657219172,
168
+ "grad_norm": 1.3046875,
169
+ "learning_rate": 0.0009673542068556166,
170
+ "loss": 5.4761,
171
+ "step": 11000
172
+ },
173
+ {
174
+ "epoch": 1.7064846416382253,
175
+ "grad_norm": 1.09375,
176
+ "learning_rate": 0.0009658703071672355,
177
+ "loss": 5.4742,
178
+ "step": 11500
179
+ },
180
+ {
181
+ "epoch": 1.7806796260572786,
182
+ "grad_norm": 1.2109375,
183
+ "learning_rate": 0.0009643864074788544,
184
+ "loss": 5.4737,
185
+ "step": 12000
186
+ },
187
+ {
188
+ "epoch": 1.8548746104763318,
189
+ "grad_norm": 1.4453125,
190
+ "learning_rate": 0.0009629025077904734,
191
+ "loss": 5.4767,
192
+ "step": 12500
193
+ },
194
+ {
195
+ "epoch": 1.929069594895385,
196
+ "grad_norm": 4.09375,
197
+ "learning_rate": 0.0009614186081020924,
198
+ "loss": 5.4729,
199
+ "step": 13000
200
+ },
201
+ {
202
+ "epoch": 2.0,
203
+ "eval_loss": 5.460068702697754,
204
+ "eval_runtime": 2.5452,
205
+ "eval_samples_per_second": 392.895,
206
+ "eval_steps_per_second": 3.143,
207
+ "step": 13478
208
+ },
209
+ {
210
+ "epoch": 2.0032645793144384,
211
+ "grad_norm": 0.765625,
212
+ "learning_rate": 0.0009599347084137112,
213
+ "loss": 5.4755,
214
+ "step": 13500
215
+ },
216
+ {
217
+ "epoch": 2.0774595637334916,
218
+ "grad_norm": 0.89453125,
219
+ "learning_rate": 0.0009584508087253302,
220
+ "loss": 5.4638,
221
+ "step": 14000
222
+ },
223
+ {
224
+ "epoch": 2.151654548152545,
225
+ "grad_norm": 0.78125,
226
+ "learning_rate": 0.0009569669090369492,
227
+ "loss": 5.4658,
228
+ "step": 14500
229
+ },
230
+ {
231
+ "epoch": 2.225849532571598,
232
+ "grad_norm": 0.8125,
233
+ "learning_rate": 0.0009554830093485681,
234
+ "loss": 5.46,
235
+ "step": 15000
236
+ },
237
+ {
238
+ "epoch": 2.3000445169906514,
239
+ "grad_norm": 0.7265625,
240
+ "learning_rate": 0.000953999109660187,
241
+ "loss": 5.4562,
242
+ "step": 15500
243
+ },
244
+ {
245
+ "epoch": 2.3742395014097046,
246
+ "grad_norm": 1.7109375,
247
+ "learning_rate": 0.0009525152099718059,
248
+ "loss": 5.4593,
249
+ "step": 16000
250
+ },
251
+ {
252
+ "epoch": 2.448434485828758,
253
+ "grad_norm": 1.0390625,
254
+ "learning_rate": 0.0009510313102834248,
255
+ "loss": 5.4628,
256
+ "step": 16500
257
+ },
258
+ {
259
+ "epoch": 2.522629470247811,
260
+ "grad_norm": 2.4375,
261
+ "learning_rate": 0.0009495474105950438,
262
+ "loss": 5.4565,
263
+ "step": 17000
264
+ },
265
+ {
266
+ "epoch": 2.5968244546668644,
267
+ "grad_norm": 1.5625,
268
+ "learning_rate": 0.0009480635109066628,
269
+ "loss": 5.4576,
270
+ "step": 17500
271
+ },
272
+ {
273
+ "epoch": 2.6710194390859177,
274
+ "grad_norm": 0.9765625,
275
+ "learning_rate": 0.0009465796112182816,
276
+ "loss": 5.4535,
277
+ "step": 18000
278
+ },
279
+ {
280
+ "epoch": 2.745214423504971,
281
+ "grad_norm": 3.4375,
282
+ "learning_rate": 0.0009450957115299006,
283
+ "loss": 5.458,
284
+ "step": 18500
285
+ },
286
+ {
287
+ "epoch": 2.8194094079240246,
288
+ "grad_norm": 1.4765625,
289
+ "learning_rate": 0.0009436118118415196,
290
+ "loss": 5.4522,
291
+ "step": 19000
292
+ },
293
+ {
294
+ "epoch": 2.893604392343078,
295
+ "grad_norm": 0.93359375,
296
+ "learning_rate": 0.0009421279121531385,
297
+ "loss": 5.4521,
298
+ "step": 19500
299
+ },
300
+ {
301
+ "epoch": 2.967799376762131,
302
+ "grad_norm": 2.03125,
303
+ "learning_rate": 0.0009406440124647574,
304
+ "loss": 5.4537,
305
+ "step": 20000
306
+ },
307
+ {
308
+ "epoch": 3.0,
309
+ "eval_loss": 5.447722434997559,
310
+ "eval_runtime": 2.4611,
311
+ "eval_samples_per_second": 406.315,
312
+ "eval_steps_per_second": 3.251,
313
+ "step": 20217
314
+ },
315
+ {
316
+ "epoch": 3.041994361181184,
317
+ "grad_norm": 1.3359375,
318
+ "learning_rate": 0.0009391601127763763,
319
+ "loss": 5.4561,
320
+ "step": 20500
321
+ },
322
+ {
323
+ "epoch": 3.1161893456002376,
324
+ "grad_norm": 1.2109375,
325
+ "learning_rate": 0.0009376762130879952,
326
+ "loss": 5.4494,
327
+ "step": 21000
328
+ },
329
+ {
330
+ "epoch": 3.190384330019291,
331
+ "grad_norm": 3.453125,
332
+ "learning_rate": 0.0009361923133996142,
333
+ "loss": 5.4476,
334
+ "step": 21500
335
+ },
336
+ {
337
+ "epoch": 3.264579314438344,
338
+ "grad_norm": 0.7890625,
339
+ "learning_rate": 0.0009347084137112332,
340
+ "loss": 5.4441,
341
+ "step": 22000
342
+ },
343
+ {
344
+ "epoch": 3.3387742988573974,
345
+ "grad_norm": 0.8828125,
346
+ "learning_rate": 0.000933224514022852,
347
+ "loss": 5.4429,
348
+ "step": 22500
349
+ },
350
+ {
351
+ "epoch": 3.4129692832764507,
352
+ "grad_norm": 1.40625,
353
+ "learning_rate": 0.000931740614334471,
354
+ "loss": 5.4421,
355
+ "step": 23000
356
+ },
357
+ {
358
+ "epoch": 3.487164267695504,
359
+ "grad_norm": 0.97265625,
360
+ "learning_rate": 0.00093025671464609,
361
+ "loss": 5.4414,
362
+ "step": 23500
363
+ },
364
+ {
365
+ "epoch": 3.561359252114557,
366
+ "grad_norm": 1.5390625,
367
+ "learning_rate": 0.000928772814957709,
368
+ "loss": 5.4417,
369
+ "step": 24000
370
+ },
371
+ {
372
+ "epoch": 3.6355542365336104,
373
+ "grad_norm": 1.3125,
374
+ "learning_rate": 0.0009272889152693278,
375
+ "loss": 5.44,
376
+ "step": 24500
377
+ },
378
+ {
379
+ "epoch": 3.7097492209526637,
380
+ "grad_norm": 0.9765625,
381
+ "learning_rate": 0.0009258050155809467,
382
+ "loss": 5.4383,
383
+ "step": 25000
384
+ },
385
+ {
386
+ "epoch": 3.783944205371717,
387
+ "grad_norm": 0.83203125,
388
+ "learning_rate": 0.0009243211158925657,
389
+ "loss": 5.4373,
390
+ "step": 25500
391
+ },
392
+ {
393
+ "epoch": 3.85813918979077,
394
+ "grad_norm": 0.9140625,
395
+ "learning_rate": 0.0009228372162041846,
396
+ "loss": 5.4365,
397
+ "step": 26000
398
+ },
399
+ {
400
+ "epoch": 3.9323341742098235,
401
+ "grad_norm": 0.8671875,
402
+ "learning_rate": 0.0009213533165158036,
403
+ "loss": 5.4409,
404
+ "step": 26500
405
+ },
406
+ {
407
+ "epoch": 4.0,
408
+ "eval_loss": 5.42551326751709,
409
+ "eval_runtime": 2.856,
410
+ "eval_samples_per_second": 350.134,
411
+ "eval_steps_per_second": 2.801,
412
+ "step": 26956
413
+ },
414
+ {
415
+ "epoch": 4.006529158628877,
416
+ "grad_norm": 1.8359375,
417
+ "learning_rate": 0.0009198694168274225,
418
+ "loss": 5.4357,
419
+ "step": 27000
420
+ },
421
+ {
422
+ "epoch": 4.08072414304793,
423
+ "grad_norm": 0.74609375,
424
+ "learning_rate": 0.0009183855171390414,
425
+ "loss": 5.4394,
426
+ "step": 27500
427
+ },
428
+ {
429
+ "epoch": 4.154919127466983,
430
+ "grad_norm": 0.875,
431
+ "learning_rate": 0.0009169016174506604,
432
+ "loss": 5.4285,
433
+ "step": 28000
434
+ },
435
+ {
436
+ "epoch": 4.2291141118860365,
437
+ "grad_norm": 1.1953125,
438
+ "learning_rate": 0.0009154177177622794,
439
+ "loss": 5.4331,
440
+ "step": 28500
441
+ },
442
+ {
443
+ "epoch": 4.30330909630509,
444
+ "grad_norm": 0.94140625,
445
+ "learning_rate": 0.0009139338180738981,
446
+ "loss": 5.4298,
447
+ "step": 29000
448
+ },
449
+ {
450
+ "epoch": 4.377504080724143,
451
+ "grad_norm": 1.078125,
452
+ "learning_rate": 0.0009124499183855171,
453
+ "loss": 5.4261,
454
+ "step": 29500
455
+ },
456
+ {
457
+ "epoch": 4.451699065143196,
458
+ "grad_norm": 0.7421875,
459
+ "learning_rate": 0.0009109660186971361,
460
+ "loss": 5.4228,
461
+ "step": 30000
462
+ },
463
+ {
464
+ "epoch": 4.5258940495622495,
465
+ "grad_norm": 0.8671875,
466
+ "learning_rate": 0.000909482119008755,
467
+ "loss": 5.4248,
468
+ "step": 30500
469
+ },
470
+ {
471
+ "epoch": 4.600089033981303,
472
+ "grad_norm": 1.0703125,
473
+ "learning_rate": 0.000907998219320374,
474
+ "loss": 5.4221,
475
+ "step": 31000
476
+ },
477
+ {
478
+ "epoch": 4.674284018400356,
479
+ "grad_norm": 1.2734375,
480
+ "learning_rate": 0.0009065143196319929,
481
+ "loss": 5.4209,
482
+ "step": 31500
483
+ },
484
+ {
485
+ "epoch": 4.748479002819409,
486
+ "grad_norm": 2.125,
487
+ "learning_rate": 0.0009050304199436118,
488
+ "loss": 5.4231,
489
+ "step": 32000
490
+ },
491
+ {
492
+ "epoch": 4.8226739872384625,
493
+ "grad_norm": 1.1015625,
494
+ "learning_rate": 0.0009035465202552308,
495
+ "loss": 5.4172,
496
+ "step": 32500
497
+ },
498
+ {
499
+ "epoch": 4.896868971657516,
500
+ "grad_norm": 0.8515625,
501
+ "learning_rate": 0.0009020626205668498,
502
+ "loss": 5.4214,
503
+ "step": 33000
504
+ },
505
+ {
506
+ "epoch": 4.971063956076569,
507
+ "grad_norm": 0.875,
508
+ "learning_rate": 0.0009005787208784685,
509
+ "loss": 5.4197,
510
+ "step": 33500
511
+ },
512
+ {
513
+ "epoch": 5.0,
514
+ "eval_loss": 5.406287670135498,
515
+ "eval_runtime": 2.2248,
516
+ "eval_samples_per_second": 449.473,
517
+ "eval_steps_per_second": 3.596,
518
+ "step": 33695
519
+ },
520
+ {
521
+ "epoch": 5.045258940495622,
522
+ "grad_norm": 0.70703125,
523
+ "learning_rate": 0.0008990948211900875,
524
+ "loss": 5.4097,
525
+ "step": 34000
526
+ },
527
+ {
528
+ "epoch": 5.1194539249146755,
529
+ "grad_norm": 0.921875,
530
+ "learning_rate": 0.0008976109215017065,
531
+ "loss": 5.4088,
532
+ "step": 34500
533
+ },
534
+ {
535
+ "epoch": 5.193648909333729,
536
+ "grad_norm": 0.8671875,
537
+ "learning_rate": 0.0008961270218133254,
538
+ "loss": 5.4096,
539
+ "step": 35000
540
+ },
541
+ {
542
+ "epoch": 5.267843893752782,
543
+ "grad_norm": 1.0703125,
544
+ "learning_rate": 0.0008946431221249444,
545
+ "loss": 5.4136,
546
+ "step": 35500
547
+ },
548
+ {
549
+ "epoch": 5.342038878171835,
550
+ "grad_norm": 1.4375,
551
+ "learning_rate": 0.0008931592224365633,
552
+ "loss": 5.4113,
553
+ "step": 36000
554
+ },
555
+ {
556
+ "epoch": 5.416233862590889,
557
+ "grad_norm": 1.6796875,
558
+ "learning_rate": 0.0008916753227481822,
559
+ "loss": 5.4121,
560
+ "step": 36500
561
+ },
562
+ {
563
+ "epoch": 5.490428847009942,
564
+ "grad_norm": 32.75,
565
+ "learning_rate": 0.0008901914230598012,
566
+ "loss": 5.4103,
567
+ "step": 37000
568
+ },
569
+ {
570
+ "epoch": 5.564623831428995,
571
+ "grad_norm": 1.3984375,
572
+ "learning_rate": 0.0008887075233714202,
573
+ "loss": 5.4097,
574
+ "step": 37500
575
+ },
576
+ {
577
+ "epoch": 5.638818815848048,
578
+ "grad_norm": 1.078125,
579
+ "learning_rate": 0.0008872236236830389,
580
+ "loss": 5.4042,
581
+ "step": 38000
582
+ },
583
+ {
584
+ "epoch": 5.713013800267102,
585
+ "grad_norm": 0.8515625,
586
+ "learning_rate": 0.0008857397239946579,
587
+ "loss": 5.4061,
588
+ "step": 38500
589
+ },
590
+ {
591
+ "epoch": 5.787208784686155,
592
+ "grad_norm": 0.7109375,
593
+ "learning_rate": 0.0008842558243062769,
594
+ "loss": 5.4004,
595
+ "step": 39000
596
+ },
597
+ {
598
+ "epoch": 5.861403769105208,
599
+ "grad_norm": 0.78515625,
600
+ "learning_rate": 0.0008827719246178958,
601
+ "loss": 5.3987,
602
+ "step": 39500
603
+ },
604
+ {
605
+ "epoch": 5.935598753524262,
606
+ "grad_norm": 0.75390625,
607
+ "learning_rate": 0.0008812880249295148,
608
+ "loss": 5.3989,
609
+ "step": 40000
610
+ },
611
+ {
612
+ "epoch": 6.0,
613
+ "eval_loss": 5.391963481903076,
614
+ "eval_runtime": 2.6622,
615
+ "eval_samples_per_second": 375.626,
616
+ "eval_steps_per_second": 3.005,
617
+ "step": 40434
618
+ },
619
+ {
620
+ "epoch": 6.009793737943315,
621
+ "grad_norm": 1.421875,
622
+ "learning_rate": 0.0008798041252411337,
623
+ "loss": 5.3997,
624
+ "step": 40500
625
+ },
626
+ {
627
+ "epoch": 6.083988722362368,
628
+ "grad_norm": 1.03125,
629
+ "learning_rate": 0.0008783202255527527,
630
+ "loss": 5.3956,
631
+ "step": 41000
632
+ },
633
+ {
634
+ "epoch": 6.158183706781422,
635
+ "grad_norm": 1.2890625,
636
+ "learning_rate": 0.0008768363258643716,
637
+ "loss": 5.3922,
638
+ "step": 41500
639
+ },
640
+ {
641
+ "epoch": 6.232378691200475,
642
+ "grad_norm": 3.625,
643
+ "learning_rate": 0.0008753524261759906,
644
+ "loss": 5.3889,
645
+ "step": 42000
646
+ },
647
+ {
648
+ "epoch": 6.3065736756195285,
649
+ "grad_norm": 0.7890625,
650
+ "learning_rate": 0.0008738685264876095,
651
+ "loss": 5.3919,
652
+ "step": 42500
653
+ },
654
+ {
655
+ "epoch": 6.380768660038582,
656
+ "grad_norm": 1.3515625,
657
+ "learning_rate": 0.0008723846267992283,
658
+ "loss": 5.3939,
659
+ "step": 43000
660
+ },
661
+ {
662
+ "epoch": 6.454963644457635,
663
+ "grad_norm": 0.875,
664
+ "learning_rate": 0.0008709007271108473,
665
+ "loss": 5.3955,
666
+ "step": 43500
667
+ },
668
+ {
669
+ "epoch": 6.529158628876688,
670
+ "grad_norm": 2.46875,
671
+ "learning_rate": 0.0008694168274224663,
672
+ "loss": 5.3926,
673
+ "step": 44000
674
+ },
675
+ {
676
+ "epoch": 6.6033536132957416,
677
+ "grad_norm": 1.625,
678
+ "learning_rate": 0.0008679329277340852,
679
+ "loss": 5.3846,
680
+ "step": 44500
681
+ },
682
+ {
683
+ "epoch": 6.677548597714795,
684
+ "grad_norm": 0.984375,
685
+ "learning_rate": 0.0008664490280457041,
686
+ "loss": 5.3893,
687
+ "step": 45000
688
+ },
689
+ {
690
+ "epoch": 6.751743582133848,
691
+ "grad_norm": 0.90234375,
692
+ "learning_rate": 0.0008649651283573231,
693
+ "loss": 5.3905,
694
+ "step": 45500
695
+ },
696
+ {
697
+ "epoch": 6.825938566552901,
698
+ "grad_norm": 0.69140625,
699
+ "learning_rate": 0.000863481228668942,
700
+ "loss": 5.3902,
701
+ "step": 46000
702
+ },
703
+ {
704
+ "epoch": 6.900133550971955,
705
+ "grad_norm": 1.453125,
706
+ "learning_rate": 0.000861997328980561,
707
+ "loss": 5.3856,
708
+ "step": 46500
709
+ },
710
+ {
711
+ "epoch": 6.974328535391008,
712
+ "grad_norm": 1.015625,
713
+ "learning_rate": 0.0008605134292921799,
714
+ "loss": 5.3859,
715
+ "step": 47000
716
+ },
717
+ {
718
+ "epoch": 7.0,
719
+ "eval_loss": 5.379256725311279,
720
+ "eval_runtime": 2.4552,
721
+ "eval_samples_per_second": 407.295,
722
+ "eval_steps_per_second": 3.258,
723
+ "step": 47173
724
+ },
725
+ {
726
+ "epoch": 7.048523519810061,
727
+ "grad_norm": 1.2265625,
728
+ "learning_rate": 0.0008590295296037987,
729
+ "loss": 5.3794,
730
+ "step": 47500
731
+ },
732
+ {
733
+ "epoch": 7.122718504229114,
734
+ "grad_norm": 1.890625,
735
+ "learning_rate": 0.0008575456299154177,
736
+ "loss": 5.3824,
737
+ "step": 48000
738
+ },
739
+ {
740
+ "epoch": 7.196913488648168,
741
+ "grad_norm": 0.8515625,
742
+ "learning_rate": 0.0008560617302270367,
743
+ "loss": 5.3814,
744
+ "step": 48500
745
+ },
746
+ {
747
+ "epoch": 7.271108473067221,
748
+ "grad_norm": 1.3203125,
749
+ "learning_rate": 0.0008545778305386556,
750
+ "loss": 5.3778,
751
+ "step": 49000
752
+ },
753
+ {
754
+ "epoch": 7.345303457486274,
755
+ "grad_norm": 0.84765625,
756
+ "learning_rate": 0.0008530939308502745,
757
+ "loss": 5.3796,
758
+ "step": 49500
759
+ },
760
+ {
761
+ "epoch": 7.419498441905327,
762
+ "grad_norm": 2.953125,
763
+ "learning_rate": 0.0008516100311618935,
764
+ "loss": 5.3802,
765
+ "step": 50000
766
+ },
767
+ {
768
+ "epoch": 7.493693426324381,
769
+ "grad_norm": 0.875,
770
+ "learning_rate": 0.0008501261314735124,
771
+ "loss": 5.3821,
772
+ "step": 50500
773
+ },
774
+ {
775
+ "epoch": 7.567888410743434,
776
+ "grad_norm": 1.03125,
777
+ "learning_rate": 0.0008486422317851314,
778
+ "loss": 5.3796,
779
+ "step": 51000
780
+ },
781
+ {
782
+ "epoch": 7.642083395162487,
783
+ "grad_norm": 0.86328125,
784
+ "learning_rate": 0.0008471583320967503,
785
+ "loss": 5.3832,
786
+ "step": 51500
787
+ },
788
+ {
789
+ "epoch": 7.71627837958154,
790
+ "grad_norm": 0.91796875,
791
+ "learning_rate": 0.0008456744324083691,
792
+ "loss": 5.3821,
793
+ "step": 52000
794
+ },
795
+ {
796
+ "epoch": 7.790473364000594,
797
+ "grad_norm": 1.1015625,
798
+ "learning_rate": 0.0008441905327199881,
799
+ "loss": 5.3779,
800
+ "step": 52500
801
+ },
802
+ {
803
+ "epoch": 7.864668348419647,
804
+ "grad_norm": 1.203125,
805
+ "learning_rate": 0.0008427066330316071,
806
+ "loss": 5.3801,
807
+ "step": 53000
808
+ },
809
+ {
810
+ "epoch": 7.9388633328387,
811
+ "grad_norm": 1.0859375,
812
+ "learning_rate": 0.000841222733343226,
813
+ "loss": 5.3784,
814
+ "step": 53500
815
+ },
816
+ {
817
+ "epoch": 8.0,
818
+ "eval_loss": 5.376255512237549,
819
+ "eval_runtime": 2.4385,
820
+ "eval_samples_per_second": 410.092,
821
+ "eval_steps_per_second": 3.281,
822
+ "step": 53912
823
+ },
824
+ {
825
+ "epoch": 8.013058317257753,
826
+ "grad_norm": 1.2421875,
827
+ "learning_rate": 0.000839738833654845,
828
+ "loss": 5.3737,
829
+ "step": 54000
830
+ },
831
+ {
832
+ "epoch": 8.087253301676807,
833
+ "grad_norm": 1.53125,
834
+ "learning_rate": 0.0008382549339664639,
835
+ "loss": 5.3727,
836
+ "step": 54500
837
+ },
838
+ {
839
+ "epoch": 8.16144828609586,
840
+ "grad_norm": 0.80078125,
841
+ "learning_rate": 0.0008367710342780828,
842
+ "loss": 5.3665,
843
+ "step": 55000
844
+ },
845
+ {
846
+ "epoch": 8.235643270514913,
847
+ "grad_norm": 1.078125,
848
+ "learning_rate": 0.0008352871345897018,
849
+ "loss": 5.3711,
850
+ "step": 55500
851
+ },
852
+ {
853
+ "epoch": 8.309838254933966,
854
+ "grad_norm": 0.78515625,
855
+ "learning_rate": 0.0008338032349013207,
856
+ "loss": 5.3637,
857
+ "step": 56000
858
+ },
859
+ {
860
+ "epoch": 8.38403323935302,
861
+ "grad_norm": 0.84375,
862
+ "learning_rate": 0.0008323193352129396,
863
+ "loss": 5.3708,
864
+ "step": 56500
865
+ },
866
+ {
867
+ "epoch": 8.458228223772073,
868
+ "grad_norm": 1.5546875,
869
+ "learning_rate": 0.0008308354355245585,
870
+ "loss": 5.3706,
871
+ "step": 57000
872
+ },
873
+ {
874
+ "epoch": 8.532423208191126,
875
+ "grad_norm": 0.9375,
876
+ "learning_rate": 0.0008293515358361775,
877
+ "loss": 5.371,
878
+ "step": 57500
879
+ },
880
+ {
881
+ "epoch": 8.60661819261018,
882
+ "grad_norm": 0.80859375,
883
+ "learning_rate": 0.0008278676361477965,
884
+ "loss": 5.3719,
885
+ "step": 58000
886
+ },
887
+ {
888
+ "epoch": 8.680813177029233,
889
+ "grad_norm": 1.21875,
890
+ "learning_rate": 0.0008263837364594153,
891
+ "loss": 5.3708,
892
+ "step": 58500
893
+ },
894
+ {
895
+ "epoch": 8.755008161448286,
896
+ "grad_norm": 0.81640625,
897
+ "learning_rate": 0.0008248998367710343,
898
+ "loss": 5.367,
899
+ "step": 59000
900
+ },
901
+ {
902
+ "epoch": 8.82920314586734,
903
+ "grad_norm": 0.84375,
904
+ "learning_rate": 0.0008234159370826533,
905
+ "loss": 5.3645,
906
+ "step": 59500
907
+ },
908
+ {
909
+ "epoch": 8.903398130286392,
910
+ "grad_norm": 1.015625,
911
+ "learning_rate": 0.0008219320373942722,
912
+ "loss": 5.3625,
913
+ "step": 60000
914
+ },
915
+ {
916
+ "epoch": 8.977593114705446,
917
+ "grad_norm": 1.1796875,
918
+ "learning_rate": 0.0008204481377058911,
919
+ "loss": 5.364,
920
+ "step": 60500
921
+ },
922
+ {
923
+ "epoch": 9.0,
924
+ "eval_loss": 5.361752986907959,
925
+ "eval_runtime": 2.4227,
926
+ "eval_samples_per_second": 412.763,
927
+ "eval_steps_per_second": 3.302,
928
+ "step": 60651
929
+ },
930
+ {
931
+ "epoch": 9.051788099124499,
932
+ "grad_norm": 0.85546875,
933
+ "learning_rate": 0.00081896423801751,
934
+ "loss": 5.3608,
935
+ "step": 61000
936
+ },
937
+ {
938
+ "epoch": 9.125983083543552,
939
+ "grad_norm": 0.98828125,
940
+ "learning_rate": 0.0008174803383291289,
941
+ "loss": 5.3559,
942
+ "step": 61500
943
+ },
944
+ {
945
+ "epoch": 9.200178067962606,
946
+ "grad_norm": 0.80078125,
947
+ "learning_rate": 0.0008159964386407479,
948
+ "loss": 5.3547,
949
+ "step": 62000
950
+ },
951
+ {
952
+ "epoch": 9.274373052381659,
953
+ "grad_norm": 1.28125,
954
+ "learning_rate": 0.0008145125389523669,
955
+ "loss": 5.3533,
956
+ "step": 62500
957
+ },
958
+ {
959
+ "epoch": 9.348568036800712,
960
+ "grad_norm": 0.859375,
961
+ "learning_rate": 0.0008130286392639857,
962
+ "loss": 5.3545,
963
+ "step": 63000
964
+ },
965
+ {
966
+ "epoch": 9.422763021219765,
967
+ "grad_norm": 9.5625,
968
+ "learning_rate": 0.0008115447395756047,
969
+ "loss": 5.3574,
970
+ "step": 63500
971
+ },
972
+ {
973
+ "epoch": 9.496958005638819,
974
+ "grad_norm": 1.40625,
975
+ "learning_rate": 0.0008100608398872237,
976
+ "loss": 5.3565,
977
+ "step": 64000
978
+ },
979
+ {
980
+ "epoch": 9.571152990057872,
981
+ "grad_norm": 2.140625,
982
+ "learning_rate": 0.0008085769401988426,
983
+ "loss": 5.3529,
984
+ "step": 64500
985
+ },
986
+ {
987
+ "epoch": 9.645347974476925,
988
+ "grad_norm": 1.421875,
989
+ "learning_rate": 0.0008070930405104615,
990
+ "loss": 5.3565,
991
+ "step": 65000
992
+ },
993
+ {
994
+ "epoch": 9.719542958895978,
995
+ "grad_norm": 1.34375,
996
+ "learning_rate": 0.0008056091408220804,
997
+ "loss": 5.3566,
998
+ "step": 65500
999
+ },
1000
+ {
1001
+ "epoch": 9.793737943315032,
1002
+ "grad_norm": 1.15625,
1003
+ "learning_rate": 0.0008041252411336993,
1004
+ "loss": 5.3579,
1005
+ "step": 66000
1006
+ },
1007
+ {
1008
+ "epoch": 9.867932927734085,
1009
+ "grad_norm": 2.46875,
1010
+ "learning_rate": 0.0008026413414453183,
1011
+ "loss": 5.3545,
1012
+ "step": 66500
1013
+ },
1014
+ {
1015
+ "epoch": 9.942127912153138,
1016
+ "grad_norm": 1.953125,
1017
+ "learning_rate": 0.0008011574417569373,
1018
+ "loss": 5.3532,
1019
+ "step": 67000
1020
+ },
1021
+ {
1022
+ "epoch": 10.0,
1023
+ "eval_loss": 5.357708930969238,
1024
+ "eval_runtime": 2.5182,
1025
+ "eval_samples_per_second": 397.102,
1026
+ "eval_steps_per_second": 3.177,
1027
+ "step": 67390
1028
+ },
1029
+ {
1030
+ "epoch": 10.016322896572191,
1031
+ "grad_norm": 3.09375,
1032
+ "learning_rate": 0.0007996735420685562,
1033
+ "loss": 5.3531,
1034
+ "step": 67500
1035
+ },
1036
+ {
1037
+ "epoch": 10.090517880991245,
1038
+ "grad_norm": 5.59375,
1039
+ "learning_rate": 0.0007981896423801751,
1040
+ "loss": 5.3441,
1041
+ "step": 68000
1042
+ },
1043
+ {
1044
+ "epoch": 10.164712865410298,
1045
+ "grad_norm": 3.4375,
1046
+ "learning_rate": 0.0007967057426917941,
1047
+ "loss": 5.3464,
1048
+ "step": 68500
1049
+ },
1050
+ {
1051
+ "epoch": 10.238907849829351,
1052
+ "grad_norm": 1.0703125,
1053
+ "learning_rate": 0.000795221843003413,
1054
+ "loss": 5.3482,
1055
+ "step": 69000
1056
+ },
1057
+ {
1058
+ "epoch": 10.313102834248404,
1059
+ "grad_norm": 3.046875,
1060
+ "learning_rate": 0.0007937379433150319,
1061
+ "loss": 5.3481,
1062
+ "step": 69500
1063
+ },
1064
+ {
1065
+ "epoch": 10.387297818667458,
1066
+ "grad_norm": 0.74609375,
1067
+ "learning_rate": 0.0007922540436266508,
1068
+ "loss": 5.35,
1069
+ "step": 70000
1070
+ },
1071
+ {
1072
+ "epoch": 10.46149280308651,
1073
+ "grad_norm": 0.75390625,
1074
+ "learning_rate": 0.0007907701439382697,
1075
+ "loss": 5.3446,
1076
+ "step": 70500
1077
+ },
1078
+ {
1079
+ "epoch": 10.535687787505564,
1080
+ "grad_norm": 11.5,
1081
+ "learning_rate": 0.0007892862442498887,
1082
+ "loss": 5.3415,
1083
+ "step": 71000
1084
+ },
1085
+ {
1086
+ "epoch": 10.609882771924617,
1087
+ "grad_norm": 0.78515625,
1088
+ "learning_rate": 0.0007878023445615077,
1089
+ "loss": 5.3424,
1090
+ "step": 71500
1091
+ },
1092
+ {
1093
+ "epoch": 10.68407775634367,
1094
+ "grad_norm": 0.92578125,
1095
+ "learning_rate": 0.0007863184448731267,
1096
+ "loss": 5.3428,
1097
+ "step": 72000
1098
+ },
1099
+ {
1100
+ "epoch": 10.758272740762724,
1101
+ "grad_norm": 1.234375,
1102
+ "learning_rate": 0.0007848345451847455,
1103
+ "loss": 5.3442,
1104
+ "step": 72500
1105
+ },
1106
+ {
1107
+ "epoch": 10.832467725181777,
1108
+ "grad_norm": 4.21875,
1109
+ "learning_rate": 0.0007833506454963645,
1110
+ "loss": 5.3416,
1111
+ "step": 73000
1112
+ },
1113
+ {
1114
+ "epoch": 10.90666270960083,
1115
+ "grad_norm": 2.890625,
1116
+ "learning_rate": 0.0007818667458079835,
1117
+ "loss": 5.343,
1118
+ "step": 73500
1119
+ },
1120
+ {
1121
+ "epoch": 10.980857694019884,
1122
+ "grad_norm": 0.93359375,
1123
+ "learning_rate": 0.0007803828461196023,
1124
+ "loss": 5.3442,
1125
+ "step": 74000
1126
+ },
1127
+ {
1128
+ "epoch": 11.0,
1129
+ "eval_loss": 5.3484954833984375,
1130
+ "eval_runtime": 2.2047,
1131
+ "eval_samples_per_second": 453.582,
1132
+ "eval_steps_per_second": 3.629,
1133
+ "step": 74129
1134
+ },
1135
+ {
1136
+ "epoch": 11.055052678438937,
1137
+ "grad_norm": 14.625,
1138
+ "learning_rate": 0.0007788989464312212,
1139
+ "loss": 5.3356,
1140
+ "step": 74500
1141
+ },
1142
+ {
1143
+ "epoch": 11.12924766285799,
1144
+ "grad_norm": 1.25,
1145
+ "learning_rate": 0.0007774150467428402,
1146
+ "loss": 5.3352,
1147
+ "step": 75000
1148
+ },
1149
+ {
1150
+ "epoch": 11.203442647277043,
1151
+ "grad_norm": 0.80859375,
1152
+ "learning_rate": 0.0007759311470544591,
1153
+ "loss": 5.3376,
1154
+ "step": 75500
1155
+ },
1156
+ {
1157
+ "epoch": 11.277637631696097,
1158
+ "grad_norm": 1.0625,
1159
+ "learning_rate": 0.0007744472473660781,
1160
+ "loss": 5.3388,
1161
+ "step": 76000
1162
+ },
1163
+ {
1164
+ "epoch": 11.35183261611515,
1165
+ "grad_norm": 0.94140625,
1166
+ "learning_rate": 0.0007729633476776971,
1167
+ "loss": 5.3359,
1168
+ "step": 76500
1169
+ },
1170
+ {
1171
+ "epoch": 11.426027600534203,
1172
+ "grad_norm": 1.1875,
1173
+ "learning_rate": 0.0007714794479893159,
1174
+ "loss": 5.3373,
1175
+ "step": 77000
1176
+ },
1177
+ {
1178
+ "epoch": 11.500222584953256,
1179
+ "grad_norm": 0.9140625,
1180
+ "learning_rate": 0.0007699955483009349,
1181
+ "loss": 5.3385,
1182
+ "step": 77500
1183
+ },
1184
+ {
1185
+ "epoch": 11.57441756937231,
1186
+ "grad_norm": 0.99609375,
1187
+ "learning_rate": 0.0007685116486125539,
1188
+ "loss": 5.3334,
1189
+ "step": 78000
1190
+ },
1191
+ {
1192
+ "epoch": 11.648612553791363,
1193
+ "grad_norm": 1.671875,
1194
+ "learning_rate": 0.0007670277489241727,
1195
+ "loss": 5.3325,
1196
+ "step": 78500
1197
+ },
1198
+ {
1199
+ "epoch": 11.722807538210416,
1200
+ "grad_norm": 3.890625,
1201
+ "learning_rate": 0.0007655438492357916,
1202
+ "loss": 5.3376,
1203
+ "step": 79000
1204
+ },
1205
+ {
1206
+ "epoch": 11.79700252262947,
1207
+ "grad_norm": 1.9765625,
1208
+ "learning_rate": 0.0007640599495474106,
1209
+ "loss": 5.3335,
1210
+ "step": 79500
1211
+ },
1212
+ {
1213
+ "epoch": 11.871197507048523,
1214
+ "grad_norm": 4.5625,
1215
+ "learning_rate": 0.0007625760498590295,
1216
+ "loss": 5.3407,
1217
+ "step": 80000
1218
+ },
1219
+ {
1220
+ "epoch": 11.945392491467576,
1221
+ "grad_norm": 2.046875,
1222
+ "learning_rate": 0.0007610921501706485,
1223
+ "loss": 5.3363,
1224
+ "step": 80500
1225
+ },
1226
+ {
1227
+ "epoch": 12.0,
1228
+ "eval_loss": 5.337391376495361,
1229
+ "eval_runtime": 2.4996,
1230
+ "eval_samples_per_second": 400.069,
1231
+ "eval_steps_per_second": 3.201,
1232
+ "step": 80868
1233
+ },
1234
+ {
1235
+ "epoch": 12.01958747588663,
1236
+ "grad_norm": 1.59375,
1237
+ "learning_rate": 0.0007596082504822675,
1238
+ "loss": 5.3345,
1239
+ "step": 81000
1240
+ },
1241
+ {
1242
+ "epoch": 12.093782460305682,
1243
+ "grad_norm": 1.0625,
1244
+ "learning_rate": 0.0007581243507938863,
1245
+ "loss": 5.3255,
1246
+ "step": 81500
1247
+ },
1248
+ {
1249
+ "epoch": 12.167977444724736,
1250
+ "grad_norm": 1.0390625,
1251
+ "learning_rate": 0.0007566404511055053,
1252
+ "loss": 5.3327,
1253
+ "step": 82000
1254
+ },
1255
+ {
1256
+ "epoch": 12.242172429143789,
1257
+ "grad_norm": 1.6953125,
1258
+ "learning_rate": 0.0007551565514171243,
1259
+ "loss": 5.3312,
1260
+ "step": 82500
1261
+ },
1262
+ {
1263
+ "epoch": 12.316367413562844,
1264
+ "grad_norm": 0.71875,
1265
+ "learning_rate": 0.0007536726517287431,
1266
+ "loss": 5.3318,
1267
+ "step": 83000
1268
+ },
1269
+ {
1270
+ "epoch": 12.390562397981896,
1271
+ "grad_norm": 0.88671875,
1272
+ "learning_rate": 0.000752188752040362,
1273
+ "loss": 5.332,
1274
+ "step": 83500
1275
+ },
1276
+ {
1277
+ "epoch": 12.46475738240095,
1278
+ "grad_norm": 0.91796875,
1279
+ "learning_rate": 0.000750704852351981,
1280
+ "loss": 5.3283,
1281
+ "step": 84000
1282
+ },
1283
+ {
1284
+ "epoch": 12.538952366820002,
1285
+ "grad_norm": 0.86328125,
1286
+ "learning_rate": 0.0007492209526635999,
1287
+ "loss": 5.3296,
1288
+ "step": 84500
1289
+ },
1290
+ {
1291
+ "epoch": 12.613147351239057,
1292
+ "grad_norm": 1.6796875,
1293
+ "learning_rate": 0.0007477370529752189,
1294
+ "loss": 5.3338,
1295
+ "step": 85000
1296
+ },
1297
+ {
1298
+ "epoch": 12.68734233565811,
1299
+ "grad_norm": 2.6875,
1300
+ "learning_rate": 0.0007462531532868379,
1301
+ "loss": 5.3344,
1302
+ "step": 85500
1303
+ },
1304
+ {
1305
+ "epoch": 12.761537320077164,
1306
+ "grad_norm": 0.8515625,
1307
+ "learning_rate": 0.0007447692535984567,
1308
+ "loss": 5.328,
1309
+ "step": 86000
1310
+ },
1311
+ {
1312
+ "epoch": 12.835732304496217,
1313
+ "grad_norm": 2.921875,
1314
+ "learning_rate": 0.0007432853539100757,
1315
+ "loss": 5.3291,
1316
+ "step": 86500
1317
+ },
1318
+ {
1319
+ "epoch": 12.90992728891527,
1320
+ "grad_norm": 6.96875,
1321
+ "learning_rate": 0.0007418014542216947,
1322
+ "loss": 5.3239,
1323
+ "step": 87000
1324
+ },
1325
+ {
1326
+ "epoch": 12.984122273334323,
1327
+ "grad_norm": 1.3671875,
1328
+ "learning_rate": 0.0007403175545333135,
1329
+ "loss": 5.3225,
1330
+ "step": 87500
1331
+ },
1332
+ {
1333
+ "epoch": 13.0,
1334
+ "eval_loss": 5.332010746002197,
1335
+ "eval_runtime": 2.4611,
1336
+ "eval_samples_per_second": 406.325,
1337
+ "eval_steps_per_second": 3.251,
1338
+ "step": 87607
1339
+ },
1340
+ {
1341
+ "epoch": 13.058317257753377,
1342
+ "grad_norm": 1.21875,
1343
+ "learning_rate": 0.0007388336548449324,
1344
+ "loss": 5.3172,
1345
+ "step": 88000
1346
+ },
1347
+ {
1348
+ "epoch": 13.13251224217243,
1349
+ "grad_norm": 0.94921875,
1350
+ "learning_rate": 0.0007373497551565514,
1351
+ "loss": 5.3177,
1352
+ "step": 88500
1353
+ },
1354
+ {
1355
+ "epoch": 13.206707226591483,
1356
+ "grad_norm": 0.9140625,
1357
+ "learning_rate": 0.0007358658554681704,
1358
+ "loss": 5.3229,
1359
+ "step": 89000
1360
+ },
1361
+ {
1362
+ "epoch": 13.280902211010536,
1363
+ "grad_norm": 5.46875,
1364
+ "learning_rate": 0.0007343819557797893,
1365
+ "loss": 5.3208,
1366
+ "step": 89500
1367
+ },
1368
+ {
1369
+ "epoch": 13.35509719542959,
1370
+ "grad_norm": 1.703125,
1371
+ "learning_rate": 0.0007328980560914083,
1372
+ "loss": 5.3127,
1373
+ "step": 90000
1374
+ },
1375
+ {
1376
+ "epoch": 13.429292179848643,
1377
+ "grad_norm": 0.921875,
1378
+ "learning_rate": 0.0007314141564030272,
1379
+ "loss": 5.3193,
1380
+ "step": 90500
1381
+ },
1382
+ {
1383
+ "epoch": 13.503487164267696,
1384
+ "grad_norm": 0.9765625,
1385
+ "learning_rate": 0.0007299302567146461,
1386
+ "loss": 5.3168,
1387
+ "step": 91000
1388
+ },
1389
+ {
1390
+ "epoch": 13.57768214868675,
1391
+ "grad_norm": 0.87109375,
1392
+ "learning_rate": 0.000728446357026265,
1393
+ "loss": 5.3133,
1394
+ "step": 91500
1395
+ },
1396
+ {
1397
+ "epoch": 13.651877133105803,
1398
+ "grad_norm": 0.84375,
1399
+ "learning_rate": 0.000726962457337884,
1400
+ "loss": 5.3168,
1401
+ "step": 92000
1402
+ },
1403
+ {
1404
+ "epoch": 13.726072117524856,
1405
+ "grad_norm": 0.86328125,
1406
+ "learning_rate": 0.0007254785576495029,
1407
+ "loss": 5.3168,
1408
+ "step": 92500
1409
+ },
1410
+ {
1411
+ "epoch": 13.80026710194391,
1412
+ "grad_norm": 1.125,
1413
+ "learning_rate": 0.0007239946579611218,
1414
+ "loss": 5.3133,
1415
+ "step": 93000
1416
+ },
1417
+ {
1418
+ "epoch": 13.874462086362962,
1419
+ "grad_norm": 0.98828125,
1420
+ "learning_rate": 0.0007225107582727408,
1421
+ "loss": 5.3155,
1422
+ "step": 93500
1423
+ },
1424
+ {
1425
+ "epoch": 13.948657070782016,
1426
+ "grad_norm": 1.0,
1427
+ "learning_rate": 0.0007210268585843597,
1428
+ "loss": 5.3147,
1429
+ "step": 94000
1430
+ },
1431
+ {
1432
+ "epoch": 14.0,
1433
+ "eval_loss": 5.325437545776367,
1434
+ "eval_runtime": 2.4718,
1435
+ "eval_samples_per_second": 404.568,
1436
+ "eval_steps_per_second": 3.237,
1437
+ "step": 94346
1438
+ },
1439
+ {
1440
+ "epoch": 14.022852055201069,
1441
+ "grad_norm": 1.3515625,
1442
+ "learning_rate": 0.0007195429588959787,
1443
+ "loss": 5.3109,
1444
+ "step": 94500
1445
+ },
1446
+ {
1447
+ "epoch": 14.097047039620122,
1448
+ "grad_norm": 1.03125,
1449
+ "learning_rate": 0.0007180590592075977,
1450
+ "loss": 5.3044,
1451
+ "step": 95000
1452
+ },
1453
+ {
1454
+ "epoch": 14.171242024039175,
1455
+ "grad_norm": 0.9921875,
1456
+ "learning_rate": 0.0007165751595192165,
1457
+ "loss": 5.3132,
1458
+ "step": 95500
1459
+ },
1460
+ {
1461
+ "epoch": 14.245437008458229,
1462
+ "grad_norm": 1.3671875,
1463
+ "learning_rate": 0.0007150912598308354,
1464
+ "loss": 5.3108,
1465
+ "step": 96000
1466
+ },
1467
+ {
1468
+ "epoch": 14.319631992877282,
1469
+ "grad_norm": 1.7734375,
1470
+ "learning_rate": 0.0007136073601424544,
1471
+ "loss": 5.3107,
1472
+ "step": 96500
1473
+ },
1474
+ {
1475
+ "epoch": 14.393826977296335,
1476
+ "grad_norm": 3.71875,
1477
+ "learning_rate": 0.0007121234604540733,
1478
+ "loss": 5.3075,
1479
+ "step": 97000
1480
+ },
1481
+ {
1482
+ "epoch": 14.468021961715388,
1483
+ "grad_norm": 0.88671875,
1484
+ "learning_rate": 0.0007106395607656922,
1485
+ "loss": 5.3084,
1486
+ "step": 97500
1487
+ },
1488
+ {
1489
+ "epoch": 14.542216946134442,
1490
+ "grad_norm": 0.8984375,
1491
+ "learning_rate": 0.0007091556610773112,
1492
+ "loss": 5.3067,
1493
+ "step": 98000
1494
+ },
1495
+ {
1496
+ "epoch": 14.616411930553495,
1497
+ "grad_norm": 1.6015625,
1498
+ "learning_rate": 0.0007076717613889301,
1499
+ "loss": 5.3097,
1500
+ "step": 98500
1501
+ },
1502
+ {
1503
+ "epoch": 14.690606914972548,
1504
+ "grad_norm": 1.875,
1505
+ "learning_rate": 0.0007061878617005491,
1506
+ "loss": 5.3094,
1507
+ "step": 99000
1508
+ },
1509
+ {
1510
+ "epoch": 14.764801899391601,
1511
+ "grad_norm": 1.0078125,
1512
+ "learning_rate": 0.000704703962012168,
1513
+ "loss": 5.31,
1514
+ "step": 99500
1515
+ },
1516
+ {
1517
+ "epoch": 14.838996883810655,
1518
+ "grad_norm": 0.9296875,
1519
+ "learning_rate": 0.0007032200623237869,
1520
+ "loss": 5.3075,
1521
+ "step": 100000
1522
+ },
1523
+ {
1524
+ "epoch": 14.913191868229708,
1525
+ "grad_norm": 1.078125,
1526
+ "learning_rate": 0.0007017361626354058,
1527
+ "loss": 5.3088,
1528
+ "step": 100500
1529
+ },
1530
+ {
1531
+ "epoch": 14.987386852648761,
1532
+ "grad_norm": 0.828125,
1533
+ "learning_rate": 0.0007002522629470248,
1534
+ "loss": 5.3108,
1535
+ "step": 101000
1536
+ },
1537
+ {
1538
+ "epoch": 15.0,
1539
+ "eval_loss": 5.322704315185547,
1540
+ "eval_runtime": 2.0798,
1541
+ "eval_samples_per_second": 480.818,
1542
+ "eval_steps_per_second": 3.847,
1543
+ "step": 101085
1544
+ },
1545
+ {
1546
+ "epoch": 15.061581837067815,
1547
+ "grad_norm": 0.90625,
1548
+ "learning_rate": 0.0006987683632586437,
1549
+ "loss": 5.306,
1550
+ "step": 101500
1551
+ },
1552
+ {
1553
+ "epoch": 15.135776821486868,
1554
+ "grad_norm": 0.81640625,
1555
+ "learning_rate": 0.0006972844635702626,
1556
+ "loss": 5.3054,
1557
+ "step": 102000
1558
+ },
1559
+ {
1560
+ "epoch": 15.209971805905921,
1561
+ "grad_norm": 1.5,
1562
+ "learning_rate": 0.0006958005638818816,
1563
+ "loss": 5.3026,
1564
+ "step": 102500
1565
+ },
1566
+ {
1567
+ "epoch": 15.284166790324974,
1568
+ "grad_norm": 0.77734375,
1569
+ "learning_rate": 0.0006943166641935005,
1570
+ "loss": 5.3028,
1571
+ "step": 103000
1572
+ },
1573
+ {
1574
+ "epoch": 15.358361774744028,
1575
+ "grad_norm": 0.9140625,
1576
+ "learning_rate": 0.0006928327645051195,
1577
+ "loss": 5.3042,
1578
+ "step": 103500
1579
+ },
1580
+ {
1581
+ "epoch": 15.43255675916308,
1582
+ "grad_norm": 0.75,
1583
+ "learning_rate": 0.0006913488648167385,
1584
+ "loss": 5.3034,
1585
+ "step": 104000
1586
+ },
1587
+ {
1588
+ "epoch": 15.506751743582134,
1589
+ "grad_norm": 1.21875,
1590
+ "learning_rate": 0.0006898649651283574,
1591
+ "loss": 5.309,
1592
+ "step": 104500
1593
+ },
1594
+ {
1595
+ "epoch": 15.580946728001187,
1596
+ "grad_norm": 0.81640625,
1597
+ "learning_rate": 0.0006883810654399762,
1598
+ "loss": 5.3062,
1599
+ "step": 105000
1600
+ },
1601
+ {
1602
+ "epoch": 15.65514171242024,
1603
+ "grad_norm": 1.15625,
1604
+ "learning_rate": 0.0006868971657515952,
1605
+ "loss": 5.3026,
1606
+ "step": 105500
1607
+ },
1608
+ {
1609
+ "epoch": 15.729336696839294,
1610
+ "grad_norm": 0.984375,
1611
+ "learning_rate": 0.0006854132660632142,
1612
+ "loss": 5.3036,
1613
+ "step": 106000
1614
+ },
1615
+ {
1616
+ "epoch": 15.803531681258347,
1617
+ "grad_norm": 0.9921875,
1618
+ "learning_rate": 0.000683929366374833,
1619
+ "loss": 5.3002,
1620
+ "step": 106500
1621
+ },
1622
+ {
1623
+ "epoch": 15.8777266656774,
1624
+ "grad_norm": 1.1171875,
1625
+ "learning_rate": 0.000682445466686452,
1626
+ "loss": 5.302,
1627
+ "step": 107000
1628
+ },
1629
+ {
1630
+ "epoch": 15.951921650096454,
1631
+ "grad_norm": 0.90234375,
1632
+ "learning_rate": 0.000680961566998071,
1633
+ "loss": 5.3014,
1634
+ "step": 107500
1635
+ },
1636
+ {
1637
+ "epoch": 16.0,
1638
+ "eval_loss": 5.31771183013916,
1639
+ "eval_runtime": 2.1156,
1640
+ "eval_samples_per_second": 472.68,
1641
+ "eval_steps_per_second": 3.781,
1642
+ "step": 107824
1643
+ },
1644
+ {
1645
+ "epoch": 16.026116634515507,
1646
+ "grad_norm": 1.03125,
1647
+ "learning_rate": 0.0006794776673096899,
1648
+ "loss": 5.2981,
1649
+ "step": 108000
1650
+ },
1651
+ {
1652
+ "epoch": 16.10031161893456,
1653
+ "grad_norm": 4.15625,
1654
+ "learning_rate": 0.0006779937676213089,
1655
+ "loss": 5.2982,
1656
+ "step": 108500
1657
+ },
1658
+ {
1659
+ "epoch": 16.174506603353613,
1660
+ "grad_norm": 0.8359375,
1661
+ "learning_rate": 0.0006765098679329278,
1662
+ "loss": 5.2946,
1663
+ "step": 109000
1664
+ },
1665
+ {
1666
+ "epoch": 16.248701587772665,
1667
+ "grad_norm": 1.015625,
1668
+ "learning_rate": 0.0006750259682445466,
1669
+ "loss": 5.2957,
1670
+ "step": 109500
1671
+ },
1672
+ {
1673
+ "epoch": 16.32289657219172,
1674
+ "grad_norm": 1.0859375,
1675
+ "learning_rate": 0.0006735420685561656,
1676
+ "loss": 5.2964,
1677
+ "step": 110000
1678
+ },
1679
+ {
1680
+ "epoch": 16.397091556610775,
1681
+ "grad_norm": 1.9453125,
1682
+ "learning_rate": 0.0006720581688677846,
1683
+ "loss": 5.2931,
1684
+ "step": 110500
1685
+ },
1686
+ {
1687
+ "epoch": 16.471286541029826,
1688
+ "grad_norm": 1.0546875,
1689
+ "learning_rate": 0.0006705742691794034,
1690
+ "loss": 5.2916,
1691
+ "step": 111000
1692
+ },
1693
+ {
1694
+ "epoch": 16.545481525448878,
1695
+ "grad_norm": 0.79296875,
1696
+ "learning_rate": 0.0006690903694910224,
1697
+ "loss": 5.2989,
1698
+ "step": 111500
1699
+ },
1700
+ {
1701
+ "epoch": 16.619676509867933,
1702
+ "grad_norm": 1.234375,
1703
+ "learning_rate": 0.0006676064698026414,
1704
+ "loss": 5.2992,
1705
+ "step": 112000
1706
+ },
1707
+ {
1708
+ "epoch": 16.693871494286988,
1709
+ "grad_norm": 7.375,
1710
+ "learning_rate": 0.0006661225701142603,
1711
+ "loss": 5.2971,
1712
+ "step": 112500
1713
+ },
1714
+ {
1715
+ "epoch": 16.76806647870604,
1716
+ "grad_norm": 2.796875,
1717
+ "learning_rate": 0.0006646386704258793,
1718
+ "loss": 5.2931,
1719
+ "step": 113000
1720
+ },
1721
+ {
1722
+ "epoch": 16.842261463125094,
1723
+ "grad_norm": 0.94921875,
1724
+ "learning_rate": 0.0006631547707374982,
1725
+ "loss": 5.2875,
1726
+ "step": 113500
1727
+ },
1728
+ {
1729
+ "epoch": 16.916456447544146,
1730
+ "grad_norm": 0.74609375,
1731
+ "learning_rate": 0.000661670871049117,
1732
+ "loss": 5.2904,
1733
+ "step": 114000
1734
+ },
1735
+ {
1736
+ "epoch": 16.9906514319632,
1737
+ "grad_norm": 0.8515625,
1738
+ "learning_rate": 0.000660186971360736,
1739
+ "loss": 5.2886,
1740
+ "step": 114500
1741
+ },
1742
+ {
1743
+ "epoch": 17.0,
1744
+ "eval_loss": 5.307115077972412,
1745
+ "eval_runtime": 2.5,
1746
+ "eval_samples_per_second": 399.995,
1747
+ "eval_steps_per_second": 3.2,
1748
+ "step": 114563
1749
+ },
1750
+ {
1751
+ "epoch": 17.064846416382252,
1752
+ "grad_norm": 1.125,
1753
+ "learning_rate": 0.000658703071672355,
1754
+ "loss": 5.2867,
1755
+ "step": 115000
1756
+ },
1757
+ {
1758
+ "epoch": 17.139041400801307,
1759
+ "grad_norm": 0.85546875,
1760
+ "learning_rate": 0.0006572191719839738,
1761
+ "loss": 5.2857,
1762
+ "step": 115500
1763
+ },
1764
+ {
1765
+ "epoch": 17.21323638522036,
1766
+ "grad_norm": 0.8515625,
1767
+ "learning_rate": 0.0006557352722955928,
1768
+ "loss": 5.2865,
1769
+ "step": 116000
1770
+ },
1771
+ {
1772
+ "epoch": 17.287431369639414,
1773
+ "grad_norm": 0.95703125,
1774
+ "learning_rate": 0.0006542513726072118,
1775
+ "loss": 5.2885,
1776
+ "step": 116500
1777
+ },
1778
+ {
1779
+ "epoch": 17.361626354058465,
1780
+ "grad_norm": 1.1015625,
1781
+ "learning_rate": 0.0006527674729188307,
1782
+ "loss": 5.287,
1783
+ "step": 117000
1784
+ },
1785
+ {
1786
+ "epoch": 17.43582133847752,
1787
+ "grad_norm": 1.3828125,
1788
+ "learning_rate": 0.0006512835732304497,
1789
+ "loss": 5.2837,
1790
+ "step": 117500
1791
+ },
1792
+ {
1793
+ "epoch": 17.510016322896572,
1794
+ "grad_norm": 1.8046875,
1795
+ "learning_rate": 0.0006497996735420686,
1796
+ "loss": 5.2862,
1797
+ "step": 118000
1798
+ },
1799
+ {
1800
+ "epoch": 17.584211307315627,
1801
+ "grad_norm": 0.8984375,
1802
+ "learning_rate": 0.0006483157738536874,
1803
+ "loss": 5.2868,
1804
+ "step": 118500
1805
+ },
1806
+ {
1807
+ "epoch": 17.65840629173468,
1808
+ "grad_norm": 1.8046875,
1809
+ "learning_rate": 0.0006468318741653064,
1810
+ "loss": 5.28,
1811
+ "step": 119000
1812
+ },
1813
+ {
1814
+ "epoch": 17.732601276153733,
1815
+ "grad_norm": 1.0390625,
1816
+ "learning_rate": 0.0006453479744769254,
1817
+ "loss": 5.2887,
1818
+ "step": 119500
1819
+ },
1820
+ {
1821
+ "epoch": 17.806796260572785,
1822
+ "grad_norm": 2.015625,
1823
+ "learning_rate": 0.0006438640747885443,
1824
+ "loss": 5.2789,
1825
+ "step": 120000
1826
+ },
1827
+ {
1828
+ "epoch": 17.88099124499184,
1829
+ "grad_norm": 1.34375,
1830
+ "learning_rate": 0.0006423801751001632,
1831
+ "loss": 5.2849,
1832
+ "step": 120500
1833
+ },
1834
+ {
1835
+ "epoch": 17.95518622941089,
1836
+ "grad_norm": 0.85546875,
1837
+ "learning_rate": 0.0006408962754117822,
1838
+ "loss": 5.2823,
1839
+ "step": 121000
1840
+ },
1841
+ {
1842
+ "epoch": 18.0,
1843
+ "eval_loss": 5.3026299476623535,
1844
+ "eval_runtime": 2.0622,
1845
+ "eval_samples_per_second": 484.913,
1846
+ "eval_steps_per_second": 3.879,
1847
+ "step": 121302
1848
+ }
1849
+ ],
1850
+ "logging_steps": 500,
1851
+ "max_steps": 336950,
1852
+ "num_input_tokens_seen": 0,
1853
+ "num_train_epochs": 50,
1854
+ "save_steps": 500,
1855
+ "stateful_callbacks": {
1856
+ "EarlyStoppingCallback": {
1857
+ "args": {
1858
+ "early_stopping_patience": 3,
1859
+ "early_stopping_threshold": 0.0
1860
+ },
1861
+ "attributes": {
1862
+ "early_stopping_patience_counter": 0
1863
+ }
1864
+ },
1865
+ "TrainerControl": {
1866
+ "args": {
1867
+ "should_epoch_stop": false,
1868
+ "should_evaluate": false,
1869
+ "should_log": false,
1870
+ "should_save": true,
1871
+ "should_training_stop": false
1872
+ },
1873
+ "attributes": {}
1874
+ }
1875
+ },
1876
+ "total_flos": 6.515022957932667e+17,
1877
+ "train_batch_size": 128,
1878
+ "trial_name": null,
1879
+ "trial_params": null
1880
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269b13bef1340fe15fceb6aac7f82ef494ecd7ead967d2a91486844bdf31b7a7
3
+ size 5112