Hugging Face's logo

RaphaelMourad
/
Mistral-Peptide-v1-422M

Safetensors
mixtral
pretrained
mistral
peptide
Model card Files Community
RaphaelMourad commited on
Commit
b9e077c
•
1 Parent(s): c534a90

Upload 10 files

Browse files
Files changed (10) hide show
  1. config.json +31 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +2091 -0
  8. tokenizer_config.json +52 -0
  9. trainer_state.json +3123 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "data/models/Mixtral-8x7B-v0.3-dna",
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": 2688,
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": "4.41.0",
29
+ "use_cache": true,
30
+ "vocab_size": 4096
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": "4.41.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d587d8fa4d4fce20ab937895748442ea05c2015b2c74b65a6cd4b56f11f64f
3
+ size 843210512
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52cca5856c568bc52c683b690919168fa27bfbdfefc6e0a62355afa6011157c3
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d31ce7f51f91e69c908c9d1cec2e767f9231eaf4319ad6bd12926394bf27ace
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 +1,3123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 5.560152530670166,
3
+ "best_model_checkpoint": "./results/models/mistral-peptide/checkpoint-215664",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 215664,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01854736998293642,
13
+ "grad_norm": 0.546875,
14
+ "learning_rate": 0.003998516210401365,
15
+ "loss": 5.9005,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.03709473996587284,
20
+ "grad_norm": 1.0859375,
21
+ "learning_rate": 0.0039970324208027305,
22
+ "loss": 5.775,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.055642109948809255,
27
+ "grad_norm": 0.259765625,
28
+ "learning_rate": 0.003995548631204095,
29
+ "loss": 5.7532,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.07418947993174568,
34
+ "grad_norm": 0.498046875,
35
+ "learning_rate": 0.00399406484160546,
36
+ "loss": 5.7288,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.0927368499146821,
41
+ "grad_norm": 0.248046875,
42
+ "learning_rate": 0.003992581052006825,
43
+ "loss": 5.7154,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.11128421989761851,
48
+ "grad_norm": 4.1875,
49
+ "learning_rate": 0.0039910972624081905,
50
+ "loss": 5.7002,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.12983158988055493,
55
+ "grad_norm": 0.28125,
56
+ "learning_rate": 0.003989613472809556,
57
+ "loss": 5.6792,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.14837895986349137,
62
+ "grad_norm": 0.248046875,
63
+ "learning_rate": 0.003988129683210921,
64
+ "loss": 5.6751,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.16692632984642777,
69
+ "grad_norm": 0.84765625,
70
+ "learning_rate": 0.003986645893612286,
71
+ "loss": 5.7071,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.1854736998293642,
76
+ "grad_norm": 1.046875,
77
+ "learning_rate": 0.0039851621040136505,
78
+ "loss": 5.7286,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.20402106981230061,
83
+ "grad_norm": 0.2060546875,
84
+ "learning_rate": 0.003983678314415016,
85
+ "loss": 5.7413,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.22256843979523702,
90
+ "grad_norm": 0.83984375,
91
+ "learning_rate": 0.003982194524816381,
92
+ "loss": 5.7345,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.24111580977817346,
97
+ "grad_norm": 4.625,
98
+ "learning_rate": 0.003980710735217746,
99
+ "loss": 5.7295,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.25966317976110986,
104
+ "grad_norm": 6.625,
105
+ "learning_rate": 0.003979226945619111,
106
+ "loss": 5.7137,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.2782105497440463,
111
+ "grad_norm": 0.43359375,
112
+ "learning_rate": 0.003977743156020477,
113
+ "loss": 5.7136,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.29675791972698273,
118
+ "grad_norm": 0.59375,
119
+ "learning_rate": 0.003976259366421842,
120
+ "loss": 5.7133,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.3153052897099191,
125
+ "grad_norm": 0.44921875,
126
+ "learning_rate": 0.003974775576823206,
127
+ "loss": 5.7126,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.33385265969285555,
132
+ "grad_norm": 0.75,
133
+ "learning_rate": 0.0039732917872245714,
134
+ "loss": 5.7146,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.352400029675792,
139
+ "grad_norm": 0.236328125,
140
+ "learning_rate": 0.003971807997625937,
141
+ "loss": 5.7079,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.3709473996587284,
146
+ "grad_norm": 0.275390625,
147
+ "learning_rate": 0.003970324208027302,
148
+ "loss": 5.7086,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.3894947696416648,
153
+ "grad_norm": 0.43359375,
154
+ "learning_rate": 0.003968840418428667,
155
+ "loss": 5.7079,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.40804213962460123,
160
+ "grad_norm": 0.322265625,
161
+ "learning_rate": 0.0039673566288300315,
162
+ "loss": 5.6996,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.42658950960753766,
167
+ "grad_norm": 0.26171875,
168
+ "learning_rate": 0.003965872839231397,
169
+ "loss": 5.6944,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.44513687959047404,
174
+ "grad_norm": 0.27734375,
175
+ "learning_rate": 0.003964389049632762,
176
+ "loss": 5.6964,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.4636842495734105,
181
+ "grad_norm": 0.283203125,
182
+ "learning_rate": 0.003962905260034127,
183
+ "loss": 5.6924,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.4822316195563469,
188
+ "grad_norm": 0.96484375,
189
+ "learning_rate": 0.003961421470435492,
190
+ "loss": 5.7065,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.5007789895392833,
195
+ "grad_norm": 0.287109375,
196
+ "learning_rate": 0.0039599376808368576,
197
+ "loss": 5.6997,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 0.5193263595222197,
202
+ "grad_norm": 0.41796875,
203
+ "learning_rate": 0.003958453891238223,
204
+ "loss": 5.6976,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 0.5378737295051562,
209
+ "grad_norm": 1.1171875,
210
+ "learning_rate": 0.003956970101639588,
211
+ "loss": 5.7148,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 0.5564210994880926,
216
+ "grad_norm": 0.69921875,
217
+ "learning_rate": 0.003955486312040952,
218
+ "loss": 5.7088,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.574968469471029,
223
+ "grad_norm": 0.330078125,
224
+ "learning_rate": 0.003954002522442318,
225
+ "loss": 5.7007,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 0.5935158394539655,
230
+ "grad_norm": 0.318359375,
231
+ "learning_rate": 0.003952518732843683,
232
+ "loss": 5.6958,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 0.6120632094369018,
237
+ "grad_norm": 0.298828125,
238
+ "learning_rate": 0.003951034943245048,
239
+ "loss": 5.6973,
240
+ "step": 16500
241
+ },
242
+ {
243
+ "epoch": 0.6306105794198382,
244
+ "grad_norm": 19.125,
245
+ "learning_rate": 0.003949551153646413,
246
+ "loss": 5.6959,
247
+ "step": 17000
248
+ },
249
+ {
250
+ "epoch": 0.6491579494027747,
251
+ "grad_norm": 0.41796875,
252
+ "learning_rate": 0.0039480673640477785,
253
+ "loss": 5.6943,
254
+ "step": 17500
255
+ },
256
+ {
257
+ "epoch": 0.6677053193857111,
258
+ "grad_norm": 1.828125,
259
+ "learning_rate": 0.003946583574449144,
260
+ "loss": 5.6879,
261
+ "step": 18000
262
+ },
263
+ {
264
+ "epoch": 0.6862526893686475,
265
+ "grad_norm": 0.58203125,
266
+ "learning_rate": 0.003945099784850508,
267
+ "loss": 5.6871,
268
+ "step": 18500
269
+ },
270
+ {
271
+ "epoch": 0.704800059351584,
272
+ "grad_norm": 0.248046875,
273
+ "learning_rate": 0.003943615995251873,
274
+ "loss": 5.6831,
275
+ "step": 19000
276
+ },
277
+ {
278
+ "epoch": 0.7233474293345203,
279
+ "grad_norm": 0.41796875,
280
+ "learning_rate": 0.0039421322056532385,
281
+ "loss": 5.6856,
282
+ "step": 19500
283
+ },
284
+ {
285
+ "epoch": 0.7418947993174568,
286
+ "grad_norm": 1.4921875,
287
+ "learning_rate": 0.003940648416054604,
288
+ "loss": 5.6844,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 0.7604421693003932,
293
+ "grad_norm": 1.703125,
294
+ "learning_rate": 0.003939164626455969,
295
+ "loss": 5.6741,
296
+ "step": 20500
297
+ },
298
+ {
299
+ "epoch": 0.7789895392833296,
300
+ "grad_norm": 1.75,
301
+ "learning_rate": 0.003937680836857333,
302
+ "loss": 5.6793,
303
+ "step": 21000
304
+ },
305
+ {
306
+ "epoch": 0.7975369092662661,
307
+ "grad_norm": 1.0625,
308
+ "learning_rate": 0.0039361970472586985,
309
+ "loss": 5.6735,
310
+ "step": 21500
311
+ },
312
+ {
313
+ "epoch": 0.8160842792492025,
314
+ "grad_norm": 2.859375,
315
+ "learning_rate": 0.003934713257660064,
316
+ "loss": 5.6737,
317
+ "step": 22000
318
+ },
319
+ {
320
+ "epoch": 0.8346316492321388,
321
+ "grad_norm": 0.333984375,
322
+ "learning_rate": 0.003933229468061429,
323
+ "loss": 5.6704,
324
+ "step": 22500
325
+ },
326
+ {
327
+ "epoch": 0.8531790192150753,
328
+ "grad_norm": 0.48828125,
329
+ "learning_rate": 0.003931745678462794,
330
+ "loss": 5.6643,
331
+ "step": 23000
332
+ },
333
+ {
334
+ "epoch": 0.8717263891980117,
335
+ "grad_norm": 0.34765625,
336
+ "learning_rate": 0.003930261888864159,
337
+ "loss": 5.6727,
338
+ "step": 23500
339
+ },
340
+ {
341
+ "epoch": 0.8902737591809481,
342
+ "grad_norm": 0.333984375,
343
+ "learning_rate": 0.003928778099265525,
344
+ "loss": 5.6689,
345
+ "step": 24000
346
+ },
347
+ {
348
+ "epoch": 0.9088211291638846,
349
+ "grad_norm": 0.2216796875,
350
+ "learning_rate": 0.00392729430966689,
351
+ "loss": 5.6722,
352
+ "step": 24500
353
+ },
354
+ {
355
+ "epoch": 0.927368499146821,
356
+ "grad_norm": 0.3359375,
357
+ "learning_rate": 0.003925810520068254,
358
+ "loss": 5.6649,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 0.9459158691297574,
363
+ "grad_norm": 0.359375,
364
+ "learning_rate": 0.003924326730469619,
365
+ "loss": 5.6693,
366
+ "step": 25500
367
+ },
368
+ {
369
+ "epoch": 0.9644632391126938,
370
+ "grad_norm": 0.56640625,
371
+ "learning_rate": 0.003922842940870985,
372
+ "loss": 5.6648,
373
+ "step": 26000
374
+ },
375
+ {
376
+ "epoch": 0.9830106090956302,
377
+ "grad_norm": 0.373046875,
378
+ "learning_rate": 0.00392135915127235,
379
+ "loss": 5.6681,
380
+ "step": 26500
381
+ },
382
+ {
383
+ "epoch": 1.0,
384
+ "eval_loss": 5.664683818817139,
385
+ "eval_runtime": 0.7133,
386
+ "eval_samples_per_second": 1211.22,
387
+ "eval_steps_per_second": 37.851,
388
+ "step": 26958
389
+ },
390
+ {
391
+ "epoch": 1.0015579790785667,
392
+ "grad_norm": 0.228515625,
393
+ "learning_rate": 0.003919875361673715,
394
+ "loss": 5.6673,
395
+ "step": 27000
396
+ },
397
+ {
398
+ "epoch": 1.020105349061503,
399
+ "grad_norm": 0.330078125,
400
+ "learning_rate": 0.00391839157207508,
401
+ "loss": 5.6679,
402
+ "step": 27500
403
+ },
404
+ {
405
+ "epoch": 1.0386527190444395,
406
+ "grad_norm": 0.369140625,
407
+ "learning_rate": 0.003916907782476445,
408
+ "loss": 5.6611,
409
+ "step": 28000
410
+ },
411
+ {
412
+ "epoch": 1.0572000890273758,
413
+ "grad_norm": 0.330078125,
414
+ "learning_rate": 0.00391542399287781,
415
+ "loss": 5.6592,
416
+ "step": 28500
417
+ },
418
+ {
419
+ "epoch": 1.0757474590103124,
420
+ "grad_norm": 0.28125,
421
+ "learning_rate": 0.003913940203279175,
422
+ "loss": 5.6571,
423
+ "step": 29000
424
+ },
425
+ {
426
+ "epoch": 1.0942948289932488,
427
+ "grad_norm": 0.59375,
428
+ "learning_rate": 0.00391245641368054,
429
+ "loss": 5.6557,
430
+ "step": 29500
431
+ },
432
+ {
433
+ "epoch": 1.1128421989761852,
434
+ "grad_norm": 0.33203125,
435
+ "learning_rate": 0.0039109726240819055,
436
+ "loss": 5.6538,
437
+ "step": 30000
438
+ },
439
+ {
440
+ "epoch": 1.1313895689591216,
441
+ "grad_norm": 2.609375,
442
+ "learning_rate": 0.00390948883448327,
443
+ "loss": 5.6498,
444
+ "step": 30500
445
+ },
446
+ {
447
+ "epoch": 1.149936938942058,
448
+ "grad_norm": 1.4296875,
449
+ "learning_rate": 0.003908005044884635,
450
+ "loss": 5.6497,
451
+ "step": 31000
452
+ },
453
+ {
454
+ "epoch": 1.1684843089249943,
455
+ "grad_norm": 0.365234375,
456
+ "learning_rate": 0.003906521255286,
457
+ "loss": 5.6488,
458
+ "step": 31500
459
+ },
460
+ {
461
+ "epoch": 1.187031678907931,
462
+ "grad_norm": 0.94921875,
463
+ "learning_rate": 0.003905037465687366,
464
+ "loss": 5.6523,
465
+ "step": 32000
466
+ },
467
+ {
468
+ "epoch": 1.2055790488908673,
469
+ "grad_norm": 0.380859375,
470
+ "learning_rate": 0.0039035536760887307,
471
+ "loss": 5.651,
472
+ "step": 32500
473
+ },
474
+ {
475
+ "epoch": 1.2241264188738037,
476
+ "grad_norm": 0.578125,
477
+ "learning_rate": 0.0039020698864900955,
478
+ "loss": 5.651,
479
+ "step": 33000
480
+ },
481
+ {
482
+ "epoch": 1.24267378885674,
483
+ "grad_norm": 4.40625,
484
+ "learning_rate": 0.0039005860968914607,
485
+ "loss": 5.6528,
486
+ "step": 33500
487
+ },
488
+ {
489
+ "epoch": 1.2612211588396764,
490
+ "grad_norm": 0.25,
491
+ "learning_rate": 0.003899102307292826,
492
+ "loss": 5.6541,
493
+ "step": 34000
494
+ },
495
+ {
496
+ "epoch": 1.279768528822613,
497
+ "grad_norm": 0.53125,
498
+ "learning_rate": 0.003897618517694191,
499
+ "loss": 5.6547,
500
+ "step": 34500
501
+ },
502
+ {
503
+ "epoch": 1.2983158988055494,
504
+ "grad_norm": 0.419921875,
505
+ "learning_rate": 0.003896134728095556,
506
+ "loss": 5.651,
507
+ "step": 35000
508
+ },
509
+ {
510
+ "epoch": 1.3168632687884858,
511
+ "grad_norm": 0.5,
512
+ "learning_rate": 0.003894650938496921,
513
+ "loss": 5.6542,
514
+ "step": 35500
515
+ },
516
+ {
517
+ "epoch": 1.3354106387714222,
518
+ "grad_norm": 0.2138671875,
519
+ "learning_rate": 0.0038931671488982864,
520
+ "loss": 5.6534,
521
+ "step": 36000
522
+ },
523
+ {
524
+ "epoch": 1.3539580087543586,
525
+ "grad_norm": 4.875,
526
+ "learning_rate": 0.0038916833592996516,
527
+ "loss": 5.6519,
528
+ "step": 36500
529
+ },
530
+ {
531
+ "epoch": 1.3725053787372952,
532
+ "grad_norm": 1.625,
533
+ "learning_rate": 0.003890199569701017,
534
+ "loss": 5.65,
535
+ "step": 37000
536
+ },
537
+ {
538
+ "epoch": 1.3910527487202315,
539
+ "grad_norm": 0.341796875,
540
+ "learning_rate": 0.003888715780102381,
541
+ "loss": 5.6486,
542
+ "step": 37500
543
+ },
544
+ {
545
+ "epoch": 1.409600118703168,
546
+ "grad_norm": 0.36328125,
547
+ "learning_rate": 0.0038872319905037464,
548
+ "loss": 5.6503,
549
+ "step": 38000
550
+ },
551
+ {
552
+ "epoch": 1.4281474886861043,
553
+ "grad_norm": 0.265625,
554
+ "learning_rate": 0.0038857482009051116,
555
+ "loss": 5.6419,
556
+ "step": 38500
557
+ },
558
+ {
559
+ "epoch": 1.4466948586690407,
560
+ "grad_norm": 0.48046875,
561
+ "learning_rate": 0.003884264411306477,
562
+ "loss": 5.6449,
563
+ "step": 39000
564
+ },
565
+ {
566
+ "epoch": 1.4652422286519773,
567
+ "grad_norm": 0.296875,
568
+ "learning_rate": 0.003882780621707842,
569
+ "loss": 5.6478,
570
+ "step": 39500
571
+ },
572
+ {
573
+ "epoch": 1.4837895986349134,
574
+ "grad_norm": 0.51171875,
575
+ "learning_rate": 0.003881296832109207,
576
+ "loss": 5.6423,
577
+ "step": 40000
578
+ },
579
+ {
580
+ "epoch": 1.50233696861785,
581
+ "grad_norm": 0.54296875,
582
+ "learning_rate": 0.003879813042510572,
583
+ "loss": 5.642,
584
+ "step": 40500
585
+ },
586
+ {
587
+ "epoch": 1.5208843386007864,
588
+ "grad_norm": 14.625,
589
+ "learning_rate": 0.0038783292529119373,
590
+ "loss": 5.6415,
591
+ "step": 41000
592
+ },
593
+ {
594
+ "epoch": 1.5394317085837228,
595
+ "grad_norm": 0.265625,
596
+ "learning_rate": 0.0038768454633133025,
597
+ "loss": 5.644,
598
+ "step": 41500
599
+ },
600
+ {
601
+ "epoch": 1.5579790785666594,
602
+ "grad_norm": 0.322265625,
603
+ "learning_rate": 0.0038753616737146677,
604
+ "loss": 5.6495,
605
+ "step": 42000
606
+ },
607
+ {
608
+ "epoch": 1.5765264485495956,
609
+ "grad_norm": 1.0234375,
610
+ "learning_rate": 0.003873877884116032,
611
+ "loss": 5.6514,
612
+ "step": 42500
613
+ },
614
+ {
615
+ "epoch": 1.5950738185325322,
616
+ "grad_norm": 1.71875,
617
+ "learning_rate": 0.0038723940945173973,
618
+ "loss": 5.6572,
619
+ "step": 43000
620
+ },
621
+ {
622
+ "epoch": 1.6136211885154685,
623
+ "grad_norm": 1.6640625,
624
+ "learning_rate": 0.0038709103049187625,
625
+ "loss": 5.6482,
626
+ "step": 43500
627
+ },
628
+ {
629
+ "epoch": 1.632168558498405,
630
+ "grad_norm": 0.50390625,
631
+ "learning_rate": 0.0038694265153201277,
632
+ "loss": 5.6448,
633
+ "step": 44000
634
+ },
635
+ {
636
+ "epoch": 1.6507159284813413,
637
+ "grad_norm": 2.25,
638
+ "learning_rate": 0.003867942725721493,
639
+ "loss": 5.6464,
640
+ "step": 44500
641
+ },
642
+ {
643
+ "epoch": 1.6692632984642777,
644
+ "grad_norm": 0.478515625,
645
+ "learning_rate": 0.0038664589361228578,
646
+ "loss": 5.6412,
647
+ "step": 45000
648
+ },
649
+ {
650
+ "epoch": 1.6878106684472143,
651
+ "grad_norm": 1.0625,
652
+ "learning_rate": 0.003864975146524223,
653
+ "loss": 5.6426,
654
+ "step": 45500
655
+ },
656
+ {
657
+ "epoch": 1.7063580384301507,
658
+ "grad_norm": 0.2890625,
659
+ "learning_rate": 0.003863491356925588,
660
+ "loss": 5.6435,
661
+ "step": 46000
662
+ },
663
+ {
664
+ "epoch": 1.724905408413087,
665
+ "grad_norm": 0.283203125,
666
+ "learning_rate": 0.0038620075673269534,
667
+ "loss": 5.6416,
668
+ "step": 46500
669
+ },
670
+ {
671
+ "epoch": 1.7434527783960234,
672
+ "grad_norm": 0.265625,
673
+ "learning_rate": 0.0038605237777283186,
674
+ "loss": 5.6395,
675
+ "step": 47000
676
+ },
677
+ {
678
+ "epoch": 1.7620001483789598,
679
+ "grad_norm": 0.212890625,
680
+ "learning_rate": 0.003859039988129683,
681
+ "loss": 5.6425,
682
+ "step": 47500
683
+ },
684
+ {
685
+ "epoch": 1.7805475183618964,
686
+ "grad_norm": 0.291015625,
687
+ "learning_rate": 0.003857556198531048,
688
+ "loss": 5.6401,
689
+ "step": 48000
690
+ },
691
+ {
692
+ "epoch": 1.7990948883448326,
693
+ "grad_norm": 0.2265625,
694
+ "learning_rate": 0.0038560724089324134,
695
+ "loss": 5.6375,
696
+ "step": 48500
697
+ },
698
+ {
699
+ "epoch": 1.8176422583277692,
700
+ "grad_norm": 0.4921875,
701
+ "learning_rate": 0.0038545886193337786,
702
+ "loss": 5.6349,
703
+ "step": 49000
704
+ },
705
+ {
706
+ "epoch": 1.8361896283107055,
707
+ "grad_norm": 0.2412109375,
708
+ "learning_rate": 0.0038531048297351434,
709
+ "loss": 5.6363,
710
+ "step": 49500
711
+ },
712
+ {
713
+ "epoch": 1.854736998293642,
714
+ "grad_norm": 1.6796875,
715
+ "learning_rate": 0.0038516210401365087,
716
+ "loss": 5.6365,
717
+ "step": 50000
718
+ },
719
+ {
720
+ "epoch": 1.8732843682765785,
721
+ "grad_norm": 0.4765625,
722
+ "learning_rate": 0.003850137250537874,
723
+ "loss": 5.6362,
724
+ "step": 50500
725
+ },
726
+ {
727
+ "epoch": 1.8918317382595147,
728
+ "grad_norm": 0.44140625,
729
+ "learning_rate": 0.003848653460939239,
730
+ "loss": 5.6348,
731
+ "step": 51000
732
+ },
733
+ {
734
+ "epoch": 1.9103791082424513,
735
+ "grad_norm": 0.314453125,
736
+ "learning_rate": 0.0038471696713406043,
737
+ "loss": 5.6407,
738
+ "step": 51500
739
+ },
740
+ {
741
+ "epoch": 1.9289264782253877,
742
+ "grad_norm": 11.25,
743
+ "learning_rate": 0.0038456858817419687,
744
+ "loss": 5.6373,
745
+ "step": 52000
746
+ },
747
+ {
748
+ "epoch": 1.947473848208324,
749
+ "grad_norm": 0.24609375,
750
+ "learning_rate": 0.003844202092143334,
751
+ "loss": 5.6393,
752
+ "step": 52500
753
+ },
754
+ {
755
+ "epoch": 1.9660212181912606,
756
+ "grad_norm": 1.6015625,
757
+ "learning_rate": 0.003842718302544699,
758
+ "loss": 5.6272,
759
+ "step": 53000
760
+ },
761
+ {
762
+ "epoch": 1.9845685881741968,
763
+ "grad_norm": 0.45703125,
764
+ "learning_rate": 0.0038412345129460643,
765
+ "loss": 5.6328,
766
+ "step": 53500
767
+ },
768
+ {
769
+ "epoch": 2.0,
770
+ "eval_loss": 5.620687007904053,
771
+ "eval_runtime": 0.6722,
772
+ "eval_samples_per_second": 1285.247,
773
+ "eval_steps_per_second": 40.164,
774
+ "step": 53916
775
+ },
776
+ {
777
+ "epoch": 2.0031159581571334,
778
+ "grad_norm": 1.03125,
779
+ "learning_rate": 0.0038397507233474295,
780
+ "loss": 5.6283,
781
+ "step": 54000
782
+ },
783
+ {
784
+ "epoch": 2.0216633281400695,
785
+ "grad_norm": 0.326171875,
786
+ "learning_rate": 0.0038382669337487943,
787
+ "loss": 5.6321,
788
+ "step": 54500
789
+ },
790
+ {
791
+ "epoch": 2.040210698123006,
792
+ "grad_norm": 0.70703125,
793
+ "learning_rate": 0.0038367831441501596,
794
+ "loss": 5.6296,
795
+ "step": 55000
796
+ },
797
+ {
798
+ "epoch": 2.0587580681059428,
799
+ "grad_norm": 0.30859375,
800
+ "learning_rate": 0.0038352993545515248,
801
+ "loss": 5.6252,
802
+ "step": 55500
803
+ },
804
+ {
805
+ "epoch": 2.077305438088879,
806
+ "grad_norm": 0.3515625,
807
+ "learning_rate": 0.00383381556495289,
808
+ "loss": 5.6294,
809
+ "step": 56000
810
+ },
811
+ {
812
+ "epoch": 2.0958528080718155,
813
+ "grad_norm": 0.27734375,
814
+ "learning_rate": 0.003832331775354255,
815
+ "loss": 5.6235,
816
+ "step": 56500
817
+ },
818
+ {
819
+ "epoch": 2.1144001780547517,
820
+ "grad_norm": 0.37890625,
821
+ "learning_rate": 0.0038308479857556196,
822
+ "loss": 5.6233,
823
+ "step": 57000
824
+ },
825
+ {
826
+ "epoch": 2.1329475480376883,
827
+ "grad_norm": 1.2578125,
828
+ "learning_rate": 0.003829364196156985,
829
+ "loss": 5.6275,
830
+ "step": 57500
831
+ },
832
+ {
833
+ "epoch": 2.151494918020625,
834
+ "grad_norm": 0.484375,
835
+ "learning_rate": 0.00382788040655835,
836
+ "loss": 5.626,
837
+ "step": 58000
838
+ },
839
+ {
840
+ "epoch": 2.170042288003561,
841
+ "grad_norm": 2.015625,
842
+ "learning_rate": 0.0038263966169597152,
843
+ "loss": 5.6238,
844
+ "step": 58500
845
+ },
846
+ {
847
+ "epoch": 2.1885896579864976,
848
+ "grad_norm": 0.232421875,
849
+ "learning_rate": 0.0038249128273610804,
850
+ "loss": 5.625,
851
+ "step": 59000
852
+ },
853
+ {
854
+ "epoch": 2.207137027969434,
855
+ "grad_norm": 0.4140625,
856
+ "learning_rate": 0.0038234290377624452,
857
+ "loss": 5.6198,
858
+ "step": 59500
859
+ },
860
+ {
861
+ "epoch": 2.2256843979523704,
862
+ "grad_norm": 0.27734375,
863
+ "learning_rate": 0.0038219452481638105,
864
+ "loss": 5.623,
865
+ "step": 60000
866
+ },
867
+ {
868
+ "epoch": 2.2442317679353065,
869
+ "grad_norm": 0.26171875,
870
+ "learning_rate": 0.0038204614585651757,
871
+ "loss": 5.632,
872
+ "step": 60500
873
+ },
874
+ {
875
+ "epoch": 2.262779137918243,
876
+ "grad_norm": 0.73046875,
877
+ "learning_rate": 0.003818977668966541,
878
+ "loss": 5.6247,
879
+ "step": 61000
880
+ },
881
+ {
882
+ "epoch": 2.2813265079011797,
883
+ "grad_norm": 1.09375,
884
+ "learning_rate": 0.003817493879367906,
885
+ "loss": 5.6222,
886
+ "step": 61500
887
+ },
888
+ {
889
+ "epoch": 2.299873877884116,
890
+ "grad_norm": 0.423828125,
891
+ "learning_rate": 0.0038160100897692705,
892
+ "loss": 5.6231,
893
+ "step": 62000
894
+ },
895
+ {
896
+ "epoch": 2.3184212478670525,
897
+ "grad_norm": 7.71875,
898
+ "learning_rate": 0.0038145263001706357,
899
+ "loss": 5.6204,
900
+ "step": 62500
901
+ },
902
+ {
903
+ "epoch": 2.3369686178499887,
904
+ "grad_norm": 0.38671875,
905
+ "learning_rate": 0.003813042510572001,
906
+ "loss": 5.6259,
907
+ "step": 63000
908
+ },
909
+ {
910
+ "epoch": 2.3555159878329253,
911
+ "grad_norm": 0.94140625,
912
+ "learning_rate": 0.003811558720973366,
913
+ "loss": 5.618,
914
+ "step": 63500
915
+ },
916
+ {
917
+ "epoch": 2.374063357815862,
918
+ "grad_norm": 0.5625,
919
+ "learning_rate": 0.003810074931374731,
920
+ "loss": 5.624,
921
+ "step": 64000
922
+ },
923
+ {
924
+ "epoch": 2.392610727798798,
925
+ "grad_norm": 3.15625,
926
+ "learning_rate": 0.003808591141776096,
927
+ "loss": 5.6262,
928
+ "step": 64500
929
+ },
930
+ {
931
+ "epoch": 2.4111580977817346,
932
+ "grad_norm": 0.279296875,
933
+ "learning_rate": 0.0038071073521774614,
934
+ "loss": 5.6213,
935
+ "step": 65000
936
+ },
937
+ {
938
+ "epoch": 2.429705467764671,
939
+ "grad_norm": 0.328125,
940
+ "learning_rate": 0.0038056235625788266,
941
+ "loss": 5.6239,
942
+ "step": 65500
943
+ },
944
+ {
945
+ "epoch": 2.4482528377476074,
946
+ "grad_norm": 0.2451171875,
947
+ "learning_rate": 0.003804139772980192,
948
+ "loss": 5.6291,
949
+ "step": 66000
950
+ },
951
+ {
952
+ "epoch": 2.466800207730544,
953
+ "grad_norm": 0.51953125,
954
+ "learning_rate": 0.0038026559833815566,
955
+ "loss": 5.6262,
956
+ "step": 66500
957
+ },
958
+ {
959
+ "epoch": 2.48534757771348,
960
+ "grad_norm": 0.62109375,
961
+ "learning_rate": 0.0038011721937829214,
962
+ "loss": 5.6221,
963
+ "step": 67000
964
+ },
965
+ {
966
+ "epoch": 2.5038949476964167,
967
+ "grad_norm": 0.42578125,
968
+ "learning_rate": 0.0037996884041842866,
969
+ "loss": 5.621,
970
+ "step": 67500
971
+ },
972
+ {
973
+ "epoch": 2.522442317679353,
974
+ "grad_norm": 0.287109375,
975
+ "learning_rate": 0.003798204614585652,
976
+ "loss": 5.6214,
977
+ "step": 68000
978
+ },
979
+ {
980
+ "epoch": 2.5409896876622895,
981
+ "grad_norm": 2.734375,
982
+ "learning_rate": 0.003796720824987017,
983
+ "loss": 5.6202,
984
+ "step": 68500
985
+ },
986
+ {
987
+ "epoch": 2.559537057645226,
988
+ "grad_norm": 5.65625,
989
+ "learning_rate": 0.003795237035388382,
990
+ "loss": 5.6223,
991
+ "step": 69000
992
+ },
993
+ {
994
+ "epoch": 2.5780844276281623,
995
+ "grad_norm": 0.412109375,
996
+ "learning_rate": 0.003793753245789747,
997
+ "loss": 5.6248,
998
+ "step": 69500
999
+ },
1000
+ {
1001
+ "epoch": 2.596631797611099,
1002
+ "grad_norm": 0.458984375,
1003
+ "learning_rate": 0.0037922694561911123,
1004
+ "loss": 5.6186,
1005
+ "step": 70000
1006
+ },
1007
+ {
1008
+ "epoch": 2.615179167594035,
1009
+ "grad_norm": 1.9765625,
1010
+ "learning_rate": 0.0037907856665924775,
1011
+ "loss": 5.6197,
1012
+ "step": 70500
1013
+ },
1014
+ {
1015
+ "epoch": 2.6337265375769716,
1016
+ "grad_norm": 0.65234375,
1017
+ "learning_rate": 0.0037893018769938427,
1018
+ "loss": 5.6179,
1019
+ "step": 71000
1020
+ },
1021
+ {
1022
+ "epoch": 2.652273907559908,
1023
+ "grad_norm": 0.51171875,
1024
+ "learning_rate": 0.0037878180873952075,
1025
+ "loss": 5.6212,
1026
+ "step": 71500
1027
+ },
1028
+ {
1029
+ "epoch": 2.6708212775428444,
1030
+ "grad_norm": 1.6640625,
1031
+ "learning_rate": 0.0037863342977965723,
1032
+ "loss": 5.6187,
1033
+ "step": 72000
1034
+ },
1035
+ {
1036
+ "epoch": 2.689368647525781,
1037
+ "grad_norm": 0.4140625,
1038
+ "learning_rate": 0.0037848505081979375,
1039
+ "loss": 5.6142,
1040
+ "step": 72500
1041
+ },
1042
+ {
1043
+ "epoch": 2.707916017508717,
1044
+ "grad_norm": 9.25,
1045
+ "learning_rate": 0.0037833667185993027,
1046
+ "loss": 5.6186,
1047
+ "step": 73000
1048
+ },
1049
+ {
1050
+ "epoch": 2.7264633874916537,
1051
+ "grad_norm": 0.421875,
1052
+ "learning_rate": 0.003781882929000668,
1053
+ "loss": 5.619,
1054
+ "step": 73500
1055
+ },
1056
+ {
1057
+ "epoch": 2.7450107574745903,
1058
+ "grad_norm": 0.314453125,
1059
+ "learning_rate": 0.0037803991394020327,
1060
+ "loss": 5.6144,
1061
+ "step": 74000
1062
+ },
1063
+ {
1064
+ "epoch": 2.7635581274575265,
1065
+ "grad_norm": 0.427734375,
1066
+ "learning_rate": 0.003778915349803398,
1067
+ "loss": 5.6135,
1068
+ "step": 74500
1069
+ },
1070
+ {
1071
+ "epoch": 2.782105497440463,
1072
+ "grad_norm": 0.70703125,
1073
+ "learning_rate": 0.003777431560204763,
1074
+ "loss": 5.6098,
1075
+ "step": 75000
1076
+ },
1077
+ {
1078
+ "epoch": 2.8006528674233993,
1079
+ "grad_norm": 1.0078125,
1080
+ "learning_rate": 0.0037759477706061284,
1081
+ "loss": 5.6077,
1082
+ "step": 75500
1083
+ },
1084
+ {
1085
+ "epoch": 2.819200237406336,
1086
+ "grad_norm": 0.30859375,
1087
+ "learning_rate": 0.003774463981007493,
1088
+ "loss": 5.6143,
1089
+ "step": 76000
1090
+ },
1091
+ {
1092
+ "epoch": 2.8377476073892725,
1093
+ "grad_norm": 0.60546875,
1094
+ "learning_rate": 0.0037729801914088584,
1095
+ "loss": 5.6068,
1096
+ "step": 76500
1097
+ },
1098
+ {
1099
+ "epoch": 2.8562949773722086,
1100
+ "grad_norm": 0.41796875,
1101
+ "learning_rate": 0.003771496401810223,
1102
+ "loss": 5.6022,
1103
+ "step": 77000
1104
+ },
1105
+ {
1106
+ "epoch": 2.8748423473551448,
1107
+ "grad_norm": 5.15625,
1108
+ "learning_rate": 0.0037700126122115884,
1109
+ "loss": 5.6061,
1110
+ "step": 77500
1111
+ },
1112
+ {
1113
+ "epoch": 2.8933897173380814,
1114
+ "grad_norm": 3.109375,
1115
+ "learning_rate": 0.0037685288226129536,
1116
+ "loss": 5.6119,
1117
+ "step": 78000
1118
+ },
1119
+ {
1120
+ "epoch": 2.911937087321018,
1121
+ "grad_norm": 0.294921875,
1122
+ "learning_rate": 0.0037670450330143184,
1123
+ "loss": 5.6074,
1124
+ "step": 78500
1125
+ },
1126
+ {
1127
+ "epoch": 2.9304844573039546,
1128
+ "grad_norm": 0.359375,
1129
+ "learning_rate": 0.0037655612434156836,
1130
+ "loss": 5.6091,
1131
+ "step": 79000
1132
+ },
1133
+ {
1134
+ "epoch": 2.9490318272868907,
1135
+ "grad_norm": 0.470703125,
1136
+ "learning_rate": 0.003764077453817049,
1137
+ "loss": 5.6098,
1138
+ "step": 79500
1139
+ },
1140
+ {
1141
+ "epoch": 2.967579197269827,
1142
+ "grad_norm": 1.796875,
1143
+ "learning_rate": 0.003762593664218414,
1144
+ "loss": 5.6066,
1145
+ "step": 80000
1146
+ },
1147
+ {
1148
+ "epoch": 2.9861265672527635,
1149
+ "grad_norm": 0.318359375,
1150
+ "learning_rate": 0.0037611098746197793,
1151
+ "loss": 5.6141,
1152
+ "step": 80500
1153
+ },
1154
+ {
1155
+ "epoch": 3.0,
1156
+ "eval_loss": 5.597402095794678,
1157
+ "eval_runtime": 0.6753,
1158
+ "eval_samples_per_second": 1279.346,
1159
+ "eval_steps_per_second": 39.98,
1160
+ "step": 80874
1161
+ },
1162
+ {
1163
+ "epoch": 3.0046739372357,
1164
+ "grad_norm": 0.462890625,
1165
+ "learning_rate": 0.003759626085021144,
1166
+ "loss": 5.6015,
1167
+ "step": 81000
1168
+ },
1169
+ {
1170
+ "epoch": 3.0232213072186362,
1171
+ "grad_norm": 0.447265625,
1172
+ "learning_rate": 0.0037581422954225093,
1173
+ "loss": 5.6081,
1174
+ "step": 81500
1175
+ },
1176
+ {
1177
+ "epoch": 3.041768677201573,
1178
+ "grad_norm": 0.419921875,
1179
+ "learning_rate": 0.003756658505823874,
1180
+ "loss": 5.6036,
1181
+ "step": 82000
1182
+ },
1183
+ {
1184
+ "epoch": 3.0603160471845094,
1185
+ "grad_norm": 9.8125,
1186
+ "learning_rate": 0.0037551747162252393,
1187
+ "loss": 5.6046,
1188
+ "step": 82500
1189
+ },
1190
+ {
1191
+ "epoch": 3.0788634171674456,
1192
+ "grad_norm": 0.35546875,
1193
+ "learning_rate": 0.0037536909266266045,
1194
+ "loss": 5.6093,
1195
+ "step": 83000
1196
+ },
1197
+ {
1198
+ "epoch": 3.097410787150382,
1199
+ "grad_norm": 0.63671875,
1200
+ "learning_rate": 0.0037522071370279693,
1201
+ "loss": 5.6081,
1202
+ "step": 83500
1203
+ },
1204
+ {
1205
+ "epoch": 3.1159581571333184,
1206
+ "grad_norm": 8.375,
1207
+ "learning_rate": 0.0037507233474293345,
1208
+ "loss": 5.6033,
1209
+ "step": 84000
1210
+ },
1211
+ {
1212
+ "epoch": 3.134505527116255,
1213
+ "grad_norm": 0.7890625,
1214
+ "learning_rate": 0.0037492395578306997,
1215
+ "loss": 5.6081,
1216
+ "step": 84500
1217
+ },
1218
+ {
1219
+ "epoch": 3.153052897099191,
1220
+ "grad_norm": 0.37890625,
1221
+ "learning_rate": 0.003747755768232065,
1222
+ "loss": 5.6031,
1223
+ "step": 85000
1224
+ },
1225
+ {
1226
+ "epoch": 3.1716002670821277,
1227
+ "grad_norm": 0.546875,
1228
+ "learning_rate": 0.00374627197863343,
1229
+ "loss": 5.6004,
1230
+ "step": 85500
1231
+ },
1232
+ {
1233
+ "epoch": 3.1901476370650643,
1234
+ "grad_norm": 0.455078125,
1235
+ "learning_rate": 0.003744788189034795,
1236
+ "loss": 5.5958,
1237
+ "step": 86000
1238
+ },
1239
+ {
1240
+ "epoch": 3.2086950070480005,
1241
+ "grad_norm": 0.6171875,
1242
+ "learning_rate": 0.00374330439943616,
1243
+ "loss": 5.6069,
1244
+ "step": 86500
1245
+ },
1246
+ {
1247
+ "epoch": 3.227242377030937,
1248
+ "grad_norm": 2.515625,
1249
+ "learning_rate": 0.003741820609837525,
1250
+ "loss": 5.6084,
1251
+ "step": 87000
1252
+ },
1253
+ {
1254
+ "epoch": 3.2457897470138732,
1255
+ "grad_norm": 1.1953125,
1256
+ "learning_rate": 0.00374033682023889,
1257
+ "loss": 5.6124,
1258
+ "step": 87500
1259
+ },
1260
+ {
1261
+ "epoch": 3.26433711699681,
1262
+ "grad_norm": 1.09375,
1263
+ "learning_rate": 0.0037388530306402554,
1264
+ "loss": 5.6012,
1265
+ "step": 88000
1266
+ },
1267
+ {
1268
+ "epoch": 3.2828844869797464,
1269
+ "grad_norm": 0.33984375,
1270
+ "learning_rate": 0.00373736924104162,
1271
+ "loss": 5.6012,
1272
+ "step": 88500
1273
+ },
1274
+ {
1275
+ "epoch": 3.3014318569626826,
1276
+ "grad_norm": 0.478515625,
1277
+ "learning_rate": 0.0037358854514429854,
1278
+ "loss": 5.6019,
1279
+ "step": 89000
1280
+ },
1281
+ {
1282
+ "epoch": 3.319979226945619,
1283
+ "grad_norm": 57.25,
1284
+ "learning_rate": 0.0037344016618443506,
1285
+ "loss": 5.6005,
1286
+ "step": 89500
1287
+ },
1288
+ {
1289
+ "epoch": 3.3385265969285554,
1290
+ "grad_norm": 1.25,
1291
+ "learning_rate": 0.003732917872245716,
1292
+ "loss": 5.6,
1293
+ "step": 90000
1294
+ },
1295
+ {
1296
+ "epoch": 3.357073966911492,
1297
+ "grad_norm": 0.53515625,
1298
+ "learning_rate": 0.0037314340826470806,
1299
+ "loss": 5.5993,
1300
+ "step": 90500
1301
+ },
1302
+ {
1303
+ "epoch": 3.3756213368944286,
1304
+ "grad_norm": 2.421875,
1305
+ "learning_rate": 0.003729950293048446,
1306
+ "loss": 5.6029,
1307
+ "step": 91000
1308
+ },
1309
+ {
1310
+ "epoch": 3.3941687068773647,
1311
+ "grad_norm": 1.0,
1312
+ "learning_rate": 0.003728466503449811,
1313
+ "loss": 5.5991,
1314
+ "step": 91500
1315
+ },
1316
+ {
1317
+ "epoch": 3.4127160768603013,
1318
+ "grad_norm": 0.7421875,
1319
+ "learning_rate": 0.003726982713851176,
1320
+ "loss": 5.5965,
1321
+ "step": 92000
1322
+ },
1323
+ {
1324
+ "epoch": 3.4312634468432375,
1325
+ "grad_norm": 0.41015625,
1326
+ "learning_rate": 0.003725498924252541,
1327
+ "loss": 5.6004,
1328
+ "step": 92500
1329
+ },
1330
+ {
1331
+ "epoch": 3.449810816826174,
1332
+ "grad_norm": 1.0859375,
1333
+ "learning_rate": 0.003724015134653906,
1334
+ "loss": 5.5991,
1335
+ "step": 93000
1336
+ },
1337
+ {
1338
+ "epoch": 3.4683581868091107,
1339
+ "grad_norm": 0.80859375,
1340
+ "learning_rate": 0.003722531345055271,
1341
+ "loss": 5.6098,
1342
+ "step": 93500
1343
+ },
1344
+ {
1345
+ "epoch": 3.486905556792047,
1346
+ "grad_norm": 0.48828125,
1347
+ "learning_rate": 0.0037210475554566363,
1348
+ "loss": 5.6072,
1349
+ "step": 94000
1350
+ },
1351
+ {
1352
+ "epoch": 3.5054529267749834,
1353
+ "grad_norm": 1.7734375,
1354
+ "learning_rate": 0.0037195637658580015,
1355
+ "loss": 5.6078,
1356
+ "step": 94500
1357
+ },
1358
+ {
1359
+ "epoch": 3.5240002967579196,
1360
+ "grad_norm": 10.25,
1361
+ "learning_rate": 0.0037180799762593668,
1362
+ "loss": 5.6109,
1363
+ "step": 95000
1364
+ },
1365
+ {
1366
+ "epoch": 3.542547666740856,
1367
+ "grad_norm": 3.859375,
1368
+ "learning_rate": 0.0037165961866607315,
1369
+ "loss": 5.6097,
1370
+ "step": 95500
1371
+ },
1372
+ {
1373
+ "epoch": 3.561095036723793,
1374
+ "grad_norm": 0.67578125,
1375
+ "learning_rate": 0.0037151123970620968,
1376
+ "loss": 5.6076,
1377
+ "step": 96000
1378
+ },
1379
+ {
1380
+ "epoch": 3.579642406706729,
1381
+ "grad_norm": 1.2890625,
1382
+ "learning_rate": 0.0037136286074634615,
1383
+ "loss": 5.6068,
1384
+ "step": 96500
1385
+ },
1386
+ {
1387
+ "epoch": 3.5981897766896656,
1388
+ "grad_norm": 1.1953125,
1389
+ "learning_rate": 0.0037121448178648268,
1390
+ "loss": 5.6083,
1391
+ "step": 97000
1392
+ },
1393
+ {
1394
+ "epoch": 3.6167371466726017,
1395
+ "grad_norm": 4.125,
1396
+ "learning_rate": 0.003710661028266192,
1397
+ "loss": 5.6109,
1398
+ "step": 97500
1399
+ },
1400
+ {
1401
+ "epoch": 3.6352845166555383,
1402
+ "grad_norm": 0.283203125,
1403
+ "learning_rate": 0.0037091772386675568,
1404
+ "loss": 5.6104,
1405
+ "step": 98000
1406
+ },
1407
+ {
1408
+ "epoch": 3.653831886638475,
1409
+ "grad_norm": 0.875,
1410
+ "learning_rate": 0.003707693449068922,
1411
+ "loss": 5.6158,
1412
+ "step": 98500
1413
+ },
1414
+ {
1415
+ "epoch": 3.672379256621411,
1416
+ "grad_norm": 7.0625,
1417
+ "learning_rate": 0.003706209659470287,
1418
+ "loss": 5.6205,
1419
+ "step": 99000
1420
+ },
1421
+ {
1422
+ "epoch": 3.6909266266043472,
1423
+ "grad_norm": 6.625,
1424
+ "learning_rate": 0.0037047258698716524,
1425
+ "loss": 5.6214,
1426
+ "step": 99500
1427
+ },
1428
+ {
1429
+ "epoch": 3.709473996587284,
1430
+ "grad_norm": 44.25,
1431
+ "learning_rate": 0.0037032420802730177,
1432
+ "loss": 5.6258,
1433
+ "step": 100000
1434
+ },
1435
+ {
1436
+ "epoch": 3.7280213665702204,
1437
+ "grad_norm": 0.9609375,
1438
+ "learning_rate": 0.0037017582906743824,
1439
+ "loss": 5.6237,
1440
+ "step": 100500
1441
+ },
1442
+ {
1443
+ "epoch": 3.746568736553157,
1444
+ "grad_norm": 1.6640625,
1445
+ "learning_rate": 0.0037002745010757477,
1446
+ "loss": 5.6164,
1447
+ "step": 101000
1448
+ },
1449
+ {
1450
+ "epoch": 3.765116106536093,
1451
+ "grad_norm": 1.1953125,
1452
+ "learning_rate": 0.0036987907114771124,
1453
+ "loss": 5.6159,
1454
+ "step": 101500
1455
+ },
1456
+ {
1457
+ "epoch": 3.7836634765190293,
1458
+ "grad_norm": 0.345703125,
1459
+ "learning_rate": 0.0036973069218784777,
1460
+ "loss": 5.6122,
1461
+ "step": 102000
1462
+ },
1463
+ {
1464
+ "epoch": 3.802210846501966,
1465
+ "grad_norm": 5.53125,
1466
+ "learning_rate": 0.003695823132279843,
1467
+ "loss": 5.609,
1468
+ "step": 102500
1469
+ },
1470
+ {
1471
+ "epoch": 3.8207582164849025,
1472
+ "grad_norm": 0.578125,
1473
+ "learning_rate": 0.0036943393426812077,
1474
+ "loss": 5.609,
1475
+ "step": 103000
1476
+ },
1477
+ {
1478
+ "epoch": 3.8393055864678387,
1479
+ "grad_norm": 6.6875,
1480
+ "learning_rate": 0.003692855553082573,
1481
+ "loss": 5.6056,
1482
+ "step": 103500
1483
+ },
1484
+ {
1485
+ "epoch": 3.8578529564507753,
1486
+ "grad_norm": 0.4296875,
1487
+ "learning_rate": 0.003691371763483938,
1488
+ "loss": 5.6102,
1489
+ "step": 104000
1490
+ },
1491
+ {
1492
+ "epoch": 3.8764003264337115,
1493
+ "grad_norm": 2.859375,
1494
+ "learning_rate": 0.0036898879738853033,
1495
+ "loss": 5.6058,
1496
+ "step": 104500
1497
+ },
1498
+ {
1499
+ "epoch": 3.894947696416648,
1500
+ "grad_norm": 1.9296875,
1501
+ "learning_rate": 0.003688404184286668,
1502
+ "loss": 5.6081,
1503
+ "step": 105000
1504
+ },
1505
+ {
1506
+ "epoch": 3.9134950663995847,
1507
+ "grad_norm": 8.3125,
1508
+ "learning_rate": 0.0036869203946880333,
1509
+ "loss": 5.6019,
1510
+ "step": 105500
1511
+ },
1512
+ {
1513
+ "epoch": 3.932042436382521,
1514
+ "grad_norm": 2.65625,
1515
+ "learning_rate": 0.0036854366050893986,
1516
+ "loss": 5.5993,
1517
+ "step": 106000
1518
+ },
1519
+ {
1520
+ "epoch": 3.9505898063654574,
1521
+ "grad_norm": 0.70703125,
1522
+ "learning_rate": 0.0036839528154907633,
1523
+ "loss": 5.6001,
1524
+ "step": 106500
1525
+ },
1526
+ {
1527
+ "epoch": 3.9691371763483936,
1528
+ "grad_norm": 0.7734375,
1529
+ "learning_rate": 0.0036824690258921286,
1530
+ "loss": 5.5992,
1531
+ "step": 107000
1532
+ },
1533
+ {
1534
+ "epoch": 3.98768454633133,
1535
+ "grad_norm": 0.88671875,
1536
+ "learning_rate": 0.0036809852362934934,
1537
+ "loss": 5.6038,
1538
+ "step": 107500
1539
+ },
1540
+ {
1541
+ "epoch": 4.0,
1542
+ "eval_loss": 5.593242645263672,
1543
+ "eval_runtime": 0.6663,
1544
+ "eval_samples_per_second": 1296.741,
1545
+ "eval_steps_per_second": 40.523,
1546
+ "step": 107832
1547
+ },
1548
+ {
1549
+ "epoch": 4.006231916314267,
1550
+ "grad_norm": 3.09375,
1551
+ "learning_rate": 0.0036795014466948586,
1552
+ "loss": 5.6019,
1553
+ "step": 108000
1554
+ },
1555
+ {
1556
+ "epoch": 4.024779286297203,
1557
+ "grad_norm": 0.546875,
1558
+ "learning_rate": 0.003678017657096224,
1559
+ "loss": 5.6019,
1560
+ "step": 108500
1561
+ },
1562
+ {
1563
+ "epoch": 4.043326656280139,
1564
+ "grad_norm": 2.96875,
1565
+ "learning_rate": 0.003676533867497589,
1566
+ "loss": 5.6004,
1567
+ "step": 109000
1568
+ },
1569
+ {
1570
+ "epoch": 4.061874026263076,
1571
+ "grad_norm": 3.796875,
1572
+ "learning_rate": 0.0036750500778989542,
1573
+ "loss": 5.5929,
1574
+ "step": 109500
1575
+ },
1576
+ {
1577
+ "epoch": 4.080421396246012,
1578
+ "grad_norm": 0.478515625,
1579
+ "learning_rate": 0.003673566288300319,
1580
+ "loss": 5.5989,
1581
+ "step": 110000
1582
+ },
1583
+ {
1584
+ "epoch": 4.098968766228949,
1585
+ "grad_norm": 0.453125,
1586
+ "learning_rate": 0.0036720824987016842,
1587
+ "loss": 5.5982,
1588
+ "step": 110500
1589
+ },
1590
+ {
1591
+ "epoch": 4.1175161362118855,
1592
+ "grad_norm": 3.78125,
1593
+ "learning_rate": 0.0036705987091030495,
1594
+ "loss": 5.5986,
1595
+ "step": 111000
1596
+ },
1597
+ {
1598
+ "epoch": 4.136063506194821,
1599
+ "grad_norm": 0.9375,
1600
+ "learning_rate": 0.0036691149195044142,
1601
+ "loss": 5.5984,
1602
+ "step": 111500
1603
+ },
1604
+ {
1605
+ "epoch": 4.154610876177758,
1606
+ "grad_norm": 3.09375,
1607
+ "learning_rate": 0.0036676311299057795,
1608
+ "loss": 5.5978,
1609
+ "step": 112000
1610
+ },
1611
+ {
1612
+ "epoch": 4.173158246160694,
1613
+ "grad_norm": 1.09375,
1614
+ "learning_rate": 0.0036661473403071443,
1615
+ "loss": 5.5957,
1616
+ "step": 112500
1617
+ },
1618
+ {
1619
+ "epoch": 4.191705616143631,
1620
+ "grad_norm": 0.408203125,
1621
+ "learning_rate": 0.0036646635507085095,
1622
+ "loss": 5.5914,
1623
+ "step": 113000
1624
+ },
1625
+ {
1626
+ "epoch": 4.210252986126568,
1627
+ "grad_norm": 0.41015625,
1628
+ "learning_rate": 0.0036631797611098747,
1629
+ "loss": 5.5971,
1630
+ "step": 113500
1631
+ },
1632
+ {
1633
+ "epoch": 4.228800356109503,
1634
+ "grad_norm": 0.81640625,
1635
+ "learning_rate": 0.00366169597151124,
1636
+ "loss": 5.5971,
1637
+ "step": 114000
1638
+ },
1639
+ {
1640
+ "epoch": 4.24734772609244,
1641
+ "grad_norm": 0.36328125,
1642
+ "learning_rate": 0.003660212181912605,
1643
+ "loss": 5.5985,
1644
+ "step": 114500
1645
+ },
1646
+ {
1647
+ "epoch": 4.2658950960753765,
1648
+ "grad_norm": 0.6015625,
1649
+ "learning_rate": 0.00365872839231397,
1650
+ "loss": 5.6023,
1651
+ "step": 115000
1652
+ },
1653
+ {
1654
+ "epoch": 4.284442466058313,
1655
+ "grad_norm": 1.8046875,
1656
+ "learning_rate": 0.003657244602715335,
1657
+ "loss": 5.6029,
1658
+ "step": 115500
1659
+ },
1660
+ {
1661
+ "epoch": 4.30298983604125,
1662
+ "grad_norm": 1.265625,
1663
+ "learning_rate": 0.0036557608131167004,
1664
+ "loss": 5.6077,
1665
+ "step": 116000
1666
+ },
1667
+ {
1668
+ "epoch": 4.3215372060241855,
1669
+ "grad_norm": 2.796875,
1670
+ "learning_rate": 0.003654277023518065,
1671
+ "loss": 5.604,
1672
+ "step": 116500
1673
+ },
1674
+ {
1675
+ "epoch": 4.340084576007122,
1676
+ "grad_norm": 5.375,
1677
+ "learning_rate": 0.00365279323391943,
1678
+ "loss": 5.6038,
1679
+ "step": 117000
1680
+ },
1681
+ {
1682
+ "epoch": 4.358631945990059,
1683
+ "grad_norm": 2.78125,
1684
+ "learning_rate": 0.003651309444320795,
1685
+ "loss": 5.6091,
1686
+ "step": 117500
1687
+ },
1688
+ {
1689
+ "epoch": 4.377179315972995,
1690
+ "grad_norm": 0.52734375,
1691
+ "learning_rate": 0.0036498256547221604,
1692
+ "loss": 5.606,
1693
+ "step": 118000
1694
+ },
1695
+ {
1696
+ "epoch": 4.395726685955932,
1697
+ "grad_norm": 0.65625,
1698
+ "learning_rate": 0.0036483418651235256,
1699
+ "loss": 5.5985,
1700
+ "step": 118500
1701
+ },
1702
+ {
1703
+ "epoch": 4.414274055938868,
1704
+ "grad_norm": 17.25,
1705
+ "learning_rate": 0.003646858075524891,
1706
+ "loss": 5.5961,
1707
+ "step": 119000
1708
+ },
1709
+ {
1710
+ "epoch": 4.432821425921804,
1711
+ "grad_norm": 1.0546875,
1712
+ "learning_rate": 0.0036453742859262556,
1713
+ "loss": 5.6007,
1714
+ "step": 119500
1715
+ },
1716
+ {
1717
+ "epoch": 4.451368795904741,
1718
+ "grad_norm": 6.40625,
1719
+ "learning_rate": 0.003643890496327621,
1720
+ "loss": 5.6029,
1721
+ "step": 120000
1722
+ },
1723
+ {
1724
+ "epoch": 4.469916165887677,
1725
+ "grad_norm": 0.400390625,
1726
+ "learning_rate": 0.003642406706728986,
1727
+ "loss": 5.5998,
1728
+ "step": 120500
1729
+ },
1730
+ {
1731
+ "epoch": 4.488463535870613,
1732
+ "grad_norm": 0.61328125,
1733
+ "learning_rate": 0.0036409229171303513,
1734
+ "loss": 5.6039,
1735
+ "step": 121000
1736
+ },
1737
+ {
1738
+ "epoch": 4.50701090585355,
1739
+ "grad_norm": 0.515625,
1740
+ "learning_rate": 0.003639439127531716,
1741
+ "loss": 5.5998,
1742
+ "step": 121500
1743
+ },
1744
+ {
1745
+ "epoch": 4.525558275836486,
1746
+ "grad_norm": 0.58203125,
1747
+ "learning_rate": 0.003637955337933081,
1748
+ "loss": 5.5987,
1749
+ "step": 122000
1750
+ },
1751
+ {
1752
+ "epoch": 4.544105645819423,
1753
+ "grad_norm": 3.296875,
1754
+ "learning_rate": 0.003636471548334446,
1755
+ "loss": 5.5986,
1756
+ "step": 122500
1757
+ },
1758
+ {
1759
+ "epoch": 4.5626530158023595,
1760
+ "grad_norm": 0.58203125,
1761
+ "learning_rate": 0.0036349877587358113,
1762
+ "loss": 5.601,
1763
+ "step": 123000
1764
+ },
1765
+ {
1766
+ "epoch": 4.581200385785296,
1767
+ "grad_norm": 0.3203125,
1768
+ "learning_rate": 0.0036335039691371765,
1769
+ "loss": 5.6043,
1770
+ "step": 123500
1771
+ },
1772
+ {
1773
+ "epoch": 4.599747755768232,
1774
+ "grad_norm": 2.796875,
1775
+ "learning_rate": 0.0036320201795385417,
1776
+ "loss": 5.6029,
1777
+ "step": 124000
1778
+ },
1779
+ {
1780
+ "epoch": 4.618295125751168,
1781
+ "grad_norm": 25.5,
1782
+ "learning_rate": 0.0036305363899399065,
1783
+ "loss": 5.5966,
1784
+ "step": 124500
1785
+ },
1786
+ {
1787
+ "epoch": 4.636842495734105,
1788
+ "grad_norm": 0.484375,
1789
+ "learning_rate": 0.0036290526003412717,
1790
+ "loss": 5.5938,
1791
+ "step": 125000
1792
+ },
1793
+ {
1794
+ "epoch": 4.655389865717042,
1795
+ "grad_norm": 0.89453125,
1796
+ "learning_rate": 0.003627568810742637,
1797
+ "loss": 5.5946,
1798
+ "step": 125500
1799
+ },
1800
+ {
1801
+ "epoch": 4.673937235699977,
1802
+ "grad_norm": 3.34375,
1803
+ "learning_rate": 0.003626085021144002,
1804
+ "loss": 5.5968,
1805
+ "step": 126000
1806
+ },
1807
+ {
1808
+ "epoch": 4.692484605682914,
1809
+ "grad_norm": 0.85546875,
1810
+ "learning_rate": 0.003624601231545367,
1811
+ "loss": 5.6008,
1812
+ "step": 126500
1813
+ },
1814
+ {
1815
+ "epoch": 4.7110319756658505,
1816
+ "grad_norm": 0.435546875,
1817
+ "learning_rate": 0.0036231174419467317,
1818
+ "loss": 5.5946,
1819
+ "step": 127000
1820
+ },
1821
+ {
1822
+ "epoch": 4.729579345648787,
1823
+ "grad_norm": 0.3671875,
1824
+ "learning_rate": 0.003621633652348097,
1825
+ "loss": 5.5876,
1826
+ "step": 127500
1827
+ },
1828
+ {
1829
+ "epoch": 4.748126715631724,
1830
+ "grad_norm": 0.474609375,
1831
+ "learning_rate": 0.003620149862749462,
1832
+ "loss": 5.5902,
1833
+ "step": 128000
1834
+ },
1835
+ {
1836
+ "epoch": 4.76667408561466,
1837
+ "grad_norm": 11.8125,
1838
+ "learning_rate": 0.0036186660731508274,
1839
+ "loss": 5.5933,
1840
+ "step": 128500
1841
+ },
1842
+ {
1843
+ "epoch": 4.785221455597596,
1844
+ "grad_norm": 1.203125,
1845
+ "learning_rate": 0.0036171822835521926,
1846
+ "loss": 5.5911,
1847
+ "step": 129000
1848
+ },
1849
+ {
1850
+ "epoch": 4.803768825580533,
1851
+ "grad_norm": 0.390625,
1852
+ "learning_rate": 0.0036156984939535574,
1853
+ "loss": 5.5877,
1854
+ "step": 129500
1855
+ },
1856
+ {
1857
+ "epoch": 4.822316195563469,
1858
+ "grad_norm": 0.416015625,
1859
+ "learning_rate": 0.0036142147043549226,
1860
+ "loss": 5.5947,
1861
+ "step": 130000
1862
+ },
1863
+ {
1864
+ "epoch": 4.840863565546406,
1865
+ "grad_norm": 0.419921875,
1866
+ "learning_rate": 0.003612730914756288,
1867
+ "loss": 5.5903,
1868
+ "step": 130500
1869
+ },
1870
+ {
1871
+ "epoch": 4.859410935529342,
1872
+ "grad_norm": 0.40234375,
1873
+ "learning_rate": 0.003611247125157653,
1874
+ "loss": 5.5873,
1875
+ "step": 131000
1876
+ },
1877
+ {
1878
+ "epoch": 4.877958305512278,
1879
+ "grad_norm": 0.5,
1880
+ "learning_rate": 0.0036097633355590174,
1881
+ "loss": 5.584,
1882
+ "step": 131500
1883
+ },
1884
+ {
1885
+ "epoch": 4.896505675495215,
1886
+ "grad_norm": 0.40234375,
1887
+ "learning_rate": 0.0036082795459603826,
1888
+ "loss": 5.588,
1889
+ "step": 132000
1890
+ },
1891
+ {
1892
+ "epoch": 4.915053045478151,
1893
+ "grad_norm": 1.8125,
1894
+ "learning_rate": 0.003606795756361748,
1895
+ "loss": 5.5897,
1896
+ "step": 132500
1897
+ },
1898
+ {
1899
+ "epoch": 4.933600415461088,
1900
+ "grad_norm": 0.40234375,
1901
+ "learning_rate": 0.003605311966763113,
1902
+ "loss": 5.5915,
1903
+ "step": 133000
1904
+ },
1905
+ {
1906
+ "epoch": 4.952147785444024,
1907
+ "grad_norm": 11.125,
1908
+ "learning_rate": 0.0036038281771644783,
1909
+ "loss": 5.5923,
1910
+ "step": 133500
1911
+ },
1912
+ {
1913
+ "epoch": 4.97069515542696,
1914
+ "grad_norm": 0.8046875,
1915
+ "learning_rate": 0.003602344387565843,
1916
+ "loss": 5.587,
1917
+ "step": 134000
1918
+ },
1919
+ {
1920
+ "epoch": 4.989242525409897,
1921
+ "grad_norm": 14.8125,
1922
+ "learning_rate": 0.0036008605979672083,
1923
+ "loss": 5.5909,
1924
+ "step": 134500
1925
+ },
1926
+ {
1927
+ "epoch": 5.0,
1928
+ "eval_loss": 5.58021354675293,
1929
+ "eval_runtime": 0.6821,
1930
+ "eval_samples_per_second": 1266.679,
1931
+ "eval_steps_per_second": 39.584,
1932
+ "step": 134790
1933
+ },
1934
+ {
1935
+ "epoch": 5.0077898953928335,
1936
+ "grad_norm": 0.470703125,
1937
+ "learning_rate": 0.0035993768083685735,
1938
+ "loss": 5.5842,
1939
+ "step": 135000
1940
+ },
1941
+ {
1942
+ "epoch": 5.02633726537577,
1943
+ "grad_norm": 3.125,
1944
+ "learning_rate": 0.0035978930187699387,
1945
+ "loss": 5.5836,
1946
+ "step": 135500
1947
+ },
1948
+ {
1949
+ "epoch": 5.044884635358706,
1950
+ "grad_norm": 0.88671875,
1951
+ "learning_rate": 0.003596409229171304,
1952
+ "loss": 5.5819,
1953
+ "step": 136000
1954
+ },
1955
+ {
1956
+ "epoch": 5.063432005341642,
1957
+ "grad_norm": 1.1484375,
1958
+ "learning_rate": 0.0035949254395726683,
1959
+ "loss": 5.5819,
1960
+ "step": 136500
1961
+ },
1962
+ {
1963
+ "epoch": 5.081979375324579,
1964
+ "grad_norm": 0.455078125,
1965
+ "learning_rate": 0.0035934416499740335,
1966
+ "loss": 5.5837,
1967
+ "step": 137000
1968
+ },
1969
+ {
1970
+ "epoch": 5.100526745307516,
1971
+ "grad_norm": 0.30859375,
1972
+ "learning_rate": 0.0035919578603753988,
1973
+ "loss": 5.5763,
1974
+ "step": 137500
1975
+ },
1976
+ {
1977
+ "epoch": 5.119074115290452,
1978
+ "grad_norm": 3.375,
1979
+ "learning_rate": 0.003590474070776764,
1980
+ "loss": 5.5774,
1981
+ "step": 138000
1982
+ },
1983
+ {
1984
+ "epoch": 5.137621485273388,
1985
+ "grad_norm": 0.71484375,
1986
+ "learning_rate": 0.003588990281178129,
1987
+ "loss": 5.5806,
1988
+ "step": 138500
1989
+ },
1990
+ {
1991
+ "epoch": 5.1561688552563245,
1992
+ "grad_norm": 0.5234375,
1993
+ "learning_rate": 0.003587506491579494,
1994
+ "loss": 5.5815,
1995
+ "step": 139000
1996
+ },
1997
+ {
1998
+ "epoch": 5.174716225239261,
1999
+ "grad_norm": 0.37890625,
2000
+ "learning_rate": 0.003586022701980859,
2001
+ "loss": 5.5823,
2002
+ "step": 139500
2003
+ },
2004
+ {
2005
+ "epoch": 5.193263595222198,
2006
+ "grad_norm": 0.427734375,
2007
+ "learning_rate": 0.0035845389123822244,
2008
+ "loss": 5.5808,
2009
+ "step": 140000
2010
+ },
2011
+ {
2012
+ "epoch": 5.211810965205134,
2013
+ "grad_norm": 0.390625,
2014
+ "learning_rate": 0.0035830551227835896,
2015
+ "loss": 5.5777,
2016
+ "step": 140500
2017
+ },
2018
+ {
2019
+ "epoch": 5.23035833518807,
2020
+ "grad_norm": 0.431640625,
2021
+ "learning_rate": 0.003581571333184955,
2022
+ "loss": 5.5755,
2023
+ "step": 141000
2024
+ },
2025
+ {
2026
+ "epoch": 5.248905705171007,
2027
+ "grad_norm": 2.796875,
2028
+ "learning_rate": 0.003580087543586319,
2029
+ "loss": 5.5739,
2030
+ "step": 141500
2031
+ },
2032
+ {
2033
+ "epoch": 5.267453075153943,
2034
+ "grad_norm": 0.953125,
2035
+ "learning_rate": 0.0035786037539876844,
2036
+ "loss": 5.5777,
2037
+ "step": 142000
2038
+ },
2039
+ {
2040
+ "epoch": 5.28600044513688,
2041
+ "grad_norm": 1.0,
2042
+ "learning_rate": 0.0035771199643890497,
2043
+ "loss": 5.5796,
2044
+ "step": 142500
2045
+ },
2046
+ {
2047
+ "epoch": 5.304547815119816,
2048
+ "grad_norm": 0.3203125,
2049
+ "learning_rate": 0.003575636174790415,
2050
+ "loss": 5.5775,
2051
+ "step": 143000
2052
+ },
2053
+ {
2054
+ "epoch": 5.323095185102752,
2055
+ "grad_norm": 0.3359375,
2056
+ "learning_rate": 0.00357415238519178,
2057
+ "loss": 5.5707,
2058
+ "step": 143500
2059
+ },
2060
+ {
2061
+ "epoch": 5.341642555085689,
2062
+ "grad_norm": 2.234375,
2063
+ "learning_rate": 0.003572668595593145,
2064
+ "loss": 5.5792,
2065
+ "step": 144000
2066
+ },
2067
+ {
2068
+ "epoch": 5.360189925068625,
2069
+ "grad_norm": 3.546875,
2070
+ "learning_rate": 0.00357118480599451,
2071
+ "loss": 5.5747,
2072
+ "step": 144500
2073
+ },
2074
+ {
2075
+ "epoch": 5.378737295051562,
2076
+ "grad_norm": 2.046875,
2077
+ "learning_rate": 0.0035697010163958753,
2078
+ "loss": 5.579,
2079
+ "step": 145000
2080
+ },
2081
+ {
2082
+ "epoch": 5.397284665034498,
2083
+ "grad_norm": 0.74609375,
2084
+ "learning_rate": 0.0035682172267972405,
2085
+ "loss": 5.5746,
2086
+ "step": 145500
2087
+ },
2088
+ {
2089
+ "epoch": 5.415832035017434,
2090
+ "grad_norm": 2.921875,
2091
+ "learning_rate": 0.003566733437198605,
2092
+ "loss": 5.5761,
2093
+ "step": 146000
2094
+ },
2095
+ {
2096
+ "epoch": 5.434379405000371,
2097
+ "grad_norm": 1.765625,
2098
+ "learning_rate": 0.00356524964759997,
2099
+ "loss": 5.5795,
2100
+ "step": 146500
2101
+ },
2102
+ {
2103
+ "epoch": 5.4529267749833075,
2104
+ "grad_norm": 1.453125,
2105
+ "learning_rate": 0.0035637658580013353,
2106
+ "loss": 5.5805,
2107
+ "step": 147000
2108
+ },
2109
+ {
2110
+ "epoch": 5.471474144966244,
2111
+ "grad_norm": 0.484375,
2112
+ "learning_rate": 0.0035622820684027006,
2113
+ "loss": 5.5802,
2114
+ "step": 147500
2115
+ },
2116
+ {
2117
+ "epoch": 5.490021514949181,
2118
+ "grad_norm": 2.328125,
2119
+ "learning_rate": 0.0035607982788040658,
2120
+ "loss": 5.5863,
2121
+ "step": 148000
2122
+ },
2123
+ {
2124
+ "epoch": 5.508568884932116,
2125
+ "grad_norm": 0.54296875,
2126
+ "learning_rate": 0.0035593144892054306,
2127
+ "loss": 5.5939,
2128
+ "step": 148500
2129
+ },
2130
+ {
2131
+ "epoch": 5.527116254915053,
2132
+ "grad_norm": 0.44140625,
2133
+ "learning_rate": 0.0035578306996067958,
2134
+ "loss": 5.5998,
2135
+ "step": 149000
2136
+ },
2137
+ {
2138
+ "epoch": 5.54566362489799,
2139
+ "grad_norm": 0.349609375,
2140
+ "learning_rate": 0.003556346910008161,
2141
+ "loss": 5.6138,
2142
+ "step": 149500
2143
+ },
2144
+ {
2145
+ "epoch": 5.564210994880926,
2146
+ "grad_norm": 1.2109375,
2147
+ "learning_rate": 0.0035548631204095262,
2148
+ "loss": 5.6063,
2149
+ "step": 150000
2150
+ },
2151
+ {
2152
+ "epoch": 5.582758364863862,
2153
+ "grad_norm": 36.25,
2154
+ "learning_rate": 0.0035533793308108914,
2155
+ "loss": 5.6083,
2156
+ "step": 150500
2157
+ },
2158
+ {
2159
+ "epoch": 5.6013057348467985,
2160
+ "grad_norm": 0.7734375,
2161
+ "learning_rate": 0.003551895541212256,
2162
+ "loss": 5.603,
2163
+ "step": 151000
2164
+ },
2165
+ {
2166
+ "epoch": 5.619853104829735,
2167
+ "grad_norm": 1.3515625,
2168
+ "learning_rate": 0.003550411751613621,
2169
+ "loss": 5.6061,
2170
+ "step": 151500
2171
+ },
2172
+ {
2173
+ "epoch": 5.638400474812672,
2174
+ "grad_norm": 3.1875,
2175
+ "learning_rate": 0.0035489279620149862,
2176
+ "loss": 5.6004,
2177
+ "step": 152000
2178
+ },
2179
+ {
2180
+ "epoch": 5.656947844795608,
2181
+ "grad_norm": 0.4921875,
2182
+ "learning_rate": 0.0035474441724163515,
2183
+ "loss": 5.5939,
2184
+ "step": 152500
2185
+ },
2186
+ {
2187
+ "epoch": 5.675495214778544,
2188
+ "grad_norm": 0.609375,
2189
+ "learning_rate": 0.0035459603828177167,
2190
+ "loss": 5.6008,
2191
+ "step": 153000
2192
+ },
2193
+ {
2194
+ "epoch": 5.694042584761481,
2195
+ "grad_norm": 4.0625,
2196
+ "learning_rate": 0.0035444765932190815,
2197
+ "loss": 5.608,
2198
+ "step": 153500
2199
+ },
2200
+ {
2201
+ "epoch": 5.712589954744417,
2202
+ "grad_norm": 0.5234375,
2203
+ "learning_rate": 0.0035429928036204467,
2204
+ "loss": 5.598,
2205
+ "step": 154000
2206
+ },
2207
+ {
2208
+ "epoch": 5.731137324727354,
2209
+ "grad_norm": 2.09375,
2210
+ "learning_rate": 0.003541509014021812,
2211
+ "loss": 5.5946,
2212
+ "step": 154500
2213
+ },
2214
+ {
2215
+ "epoch": 5.74968469471029,
2216
+ "grad_norm": 4.34375,
2217
+ "learning_rate": 0.003540025224423177,
2218
+ "loss": 5.5909,
2219
+ "step": 155000
2220
+ },
2221
+ {
2222
+ "epoch": 5.768232064693226,
2223
+ "grad_norm": 0.55859375,
2224
+ "learning_rate": 0.0035385414348245423,
2225
+ "loss": 5.5915,
2226
+ "step": 155500
2227
+ },
2228
+ {
2229
+ "epoch": 5.786779434676163,
2230
+ "grad_norm": 25.625,
2231
+ "learning_rate": 0.0035370576452259067,
2232
+ "loss": 5.6017,
2233
+ "step": 156000
2234
+ },
2235
+ {
2236
+ "epoch": 5.805326804659099,
2237
+ "grad_norm": 0.9453125,
2238
+ "learning_rate": 0.003535573855627272,
2239
+ "loss": 5.5936,
2240
+ "step": 156500
2241
+ },
2242
+ {
2243
+ "epoch": 5.823874174642036,
2244
+ "grad_norm": 0.5390625,
2245
+ "learning_rate": 0.003534090066028637,
2246
+ "loss": 5.6077,
2247
+ "step": 157000
2248
+ },
2249
+ {
2250
+ "epoch": 5.8424215446249725,
2251
+ "grad_norm": 1.5625,
2252
+ "learning_rate": 0.0035326062764300024,
2253
+ "loss": 5.601,
2254
+ "step": 157500
2255
+ },
2256
+ {
2257
+ "epoch": 5.860968914607908,
2258
+ "grad_norm": 28.0,
2259
+ "learning_rate": 0.003531122486831367,
2260
+ "loss": 5.5944,
2261
+ "step": 158000
2262
+ },
2263
+ {
2264
+ "epoch": 5.879516284590845,
2265
+ "grad_norm": 0.51953125,
2266
+ "learning_rate": 0.0035296386972327324,
2267
+ "loss": 5.5957,
2268
+ "step": 158500
2269
+ },
2270
+ {
2271
+ "epoch": 5.8980636545737815,
2272
+ "grad_norm": 1.140625,
2273
+ "learning_rate": 0.0035281549076340976,
2274
+ "loss": 5.5942,
2275
+ "step": 159000
2276
+ },
2277
+ {
2278
+ "epoch": 5.916611024556718,
2279
+ "grad_norm": 0.88671875,
2280
+ "learning_rate": 0.003526671118035463,
2281
+ "loss": 5.5923,
2282
+ "step": 159500
2283
+ },
2284
+ {
2285
+ "epoch": 5.935158394539655,
2286
+ "grad_norm": 0.61328125,
2287
+ "learning_rate": 0.003525187328436828,
2288
+ "loss": 5.5858,
2289
+ "step": 160000
2290
+ },
2291
+ {
2292
+ "epoch": 5.95370576452259,
2293
+ "grad_norm": 0.796875,
2294
+ "learning_rate": 0.003523703538838193,
2295
+ "loss": 5.5872,
2296
+ "step": 160500
2297
+ },
2298
+ {
2299
+ "epoch": 5.972253134505527,
2300
+ "grad_norm": 1.5625,
2301
+ "learning_rate": 0.0035222197492395576,
2302
+ "loss": 5.5848,
2303
+ "step": 161000
2304
+ },
2305
+ {
2306
+ "epoch": 5.990800504488464,
2307
+ "grad_norm": 0.703125,
2308
+ "learning_rate": 0.003520735959640923,
2309
+ "loss": 5.5871,
2310
+ "step": 161500
2311
+ },
2312
+ {
2313
+ "epoch": 6.0,
2314
+ "eval_loss": 5.576883792877197,
2315
+ "eval_runtime": 0.6871,
2316
+ "eval_samples_per_second": 1257.389,
2317
+ "eval_steps_per_second": 39.293,
2318
+ "step": 161748
2319
+ },
2320
+ {
2321
+ "epoch": 6.0093478744714,
2322
+ "grad_norm": 6.0625,
2323
+ "learning_rate": 0.003519252170042288,
2324
+ "loss": 5.5846,
2325
+ "step": 162000
2326
+ },
2327
+ {
2328
+ "epoch": 6.027895244454337,
2329
+ "grad_norm": 2.953125,
2330
+ "learning_rate": 0.0035177683804436533,
2331
+ "loss": 5.5851,
2332
+ "step": 162500
2333
+ },
2334
+ {
2335
+ "epoch": 6.0464426144372725,
2336
+ "grad_norm": 0.65234375,
2337
+ "learning_rate": 0.003516284590845018,
2338
+ "loss": 5.5869,
2339
+ "step": 163000
2340
+ },
2341
+ {
2342
+ "epoch": 6.064989984420209,
2343
+ "grad_norm": 1.296875,
2344
+ "learning_rate": 0.0035148008012463833,
2345
+ "loss": 5.5884,
2346
+ "step": 163500
2347
+ },
2348
+ {
2349
+ "epoch": 6.083537354403146,
2350
+ "grad_norm": 0.59375,
2351
+ "learning_rate": 0.0035133170116477485,
2352
+ "loss": 5.583,
2353
+ "step": 164000
2354
+ },
2355
+ {
2356
+ "epoch": 6.102084724386082,
2357
+ "grad_norm": 0.796875,
2358
+ "learning_rate": 0.0035118332220491137,
2359
+ "loss": 5.5868,
2360
+ "step": 164500
2361
+ },
2362
+ {
2363
+ "epoch": 6.120632094369019,
2364
+ "grad_norm": 1.8125,
2365
+ "learning_rate": 0.003510349432450479,
2366
+ "loss": 5.5819,
2367
+ "step": 165000
2368
+ },
2369
+ {
2370
+ "epoch": 6.139179464351955,
2371
+ "grad_norm": 0.65625,
2372
+ "learning_rate": 0.0035088656428518437,
2373
+ "loss": 5.5795,
2374
+ "step": 165500
2375
+ },
2376
+ {
2377
+ "epoch": 6.157726834334891,
2378
+ "grad_norm": 0.796875,
2379
+ "learning_rate": 0.0035073818532532085,
2380
+ "loss": 5.5837,
2381
+ "step": 166000
2382
+ },
2383
+ {
2384
+ "epoch": 6.176274204317828,
2385
+ "grad_norm": 2.203125,
2386
+ "learning_rate": 0.0035058980636545737,
2387
+ "loss": 5.5959,
2388
+ "step": 166500
2389
+ },
2390
+ {
2391
+ "epoch": 6.194821574300764,
2392
+ "grad_norm": 2.390625,
2393
+ "learning_rate": 0.003504414274055939,
2394
+ "loss": 5.586,
2395
+ "step": 167000
2396
+ },
2397
+ {
2398
+ "epoch": 6.213368944283701,
2399
+ "grad_norm": 0.99609375,
2400
+ "learning_rate": 0.003502930484457304,
2401
+ "loss": 5.5969,
2402
+ "step": 167500
2403
+ },
2404
+ {
2405
+ "epoch": 6.231916314266637,
2406
+ "grad_norm": 9.875,
2407
+ "learning_rate": 0.003501446694858669,
2408
+ "loss": 5.5835,
2409
+ "step": 168000
2410
+ },
2411
+ {
2412
+ "epoch": 6.250463684249573,
2413
+ "grad_norm": 0.734375,
2414
+ "learning_rate": 0.003499962905260034,
2415
+ "loss": 5.5868,
2416
+ "step": 168500
2417
+ },
2418
+ {
2419
+ "epoch": 6.26901105423251,
2420
+ "grad_norm": 12.125,
2421
+ "learning_rate": 0.0034984791156613994,
2422
+ "loss": 5.5823,
2423
+ "step": 169000
2424
+ },
2425
+ {
2426
+ "epoch": 6.2875584242154465,
2427
+ "grad_norm": 1.671875,
2428
+ "learning_rate": 0.0034969953260627646,
2429
+ "loss": 5.5801,
2430
+ "step": 169500
2431
+ },
2432
+ {
2433
+ "epoch": 6.306105794198382,
2434
+ "grad_norm": 0.734375,
2435
+ "learning_rate": 0.00349551153646413,
2436
+ "loss": 5.5808,
2437
+ "step": 170000
2438
+ },
2439
+ {
2440
+ "epoch": 6.324653164181319,
2441
+ "grad_norm": 12.0,
2442
+ "learning_rate": 0.0034940277468654946,
2443
+ "loss": 5.5859,
2444
+ "step": 170500
2445
+ },
2446
+ {
2447
+ "epoch": 6.3432005341642554,
2448
+ "grad_norm": 0.828125,
2449
+ "learning_rate": 0.0034925439572668594,
2450
+ "loss": 5.5807,
2451
+ "step": 171000
2452
+ },
2453
+ {
2454
+ "epoch": 6.361747904147192,
2455
+ "grad_norm": 2.53125,
2456
+ "learning_rate": 0.0034910601676682246,
2457
+ "loss": 5.5804,
2458
+ "step": 171500
2459
+ },
2460
+ {
2461
+ "epoch": 6.380295274130129,
2462
+ "grad_norm": 0.52734375,
2463
+ "learning_rate": 0.00348957637806959,
2464
+ "loss": 5.5731,
2465
+ "step": 172000
2466
+ },
2467
+ {
2468
+ "epoch": 6.398842644113064,
2469
+ "grad_norm": 0.79296875,
2470
+ "learning_rate": 0.0034880925884709546,
2471
+ "loss": 5.5813,
2472
+ "step": 172500
2473
+ },
2474
+ {
2475
+ "epoch": 6.417390014096001,
2476
+ "grad_norm": 0.578125,
2477
+ "learning_rate": 0.00348660879887232,
2478
+ "loss": 5.5763,
2479
+ "step": 173000
2480
+ },
2481
+ {
2482
+ "epoch": 6.435937384078938,
2483
+ "grad_norm": 0.70703125,
2484
+ "learning_rate": 0.003485125009273685,
2485
+ "loss": 5.5724,
2486
+ "step": 173500
2487
+ },
2488
+ {
2489
+ "epoch": 6.454484754061874,
2490
+ "grad_norm": 1.5234375,
2491
+ "learning_rate": 0.0034836412196750503,
2492
+ "loss": 5.5756,
2493
+ "step": 174000
2494
+ },
2495
+ {
2496
+ "epoch": 6.473032124044811,
2497
+ "grad_norm": 4.40625,
2498
+ "learning_rate": 0.0034821574300764155,
2499
+ "loss": 5.581,
2500
+ "step": 174500
2501
+ },
2502
+ {
2503
+ "epoch": 6.4915794940277465,
2504
+ "grad_norm": 0.5546875,
2505
+ "learning_rate": 0.0034806736404777803,
2506
+ "loss": 5.5756,
2507
+ "step": 175000
2508
+ },
2509
+ {
2510
+ "epoch": 6.510126864010683,
2511
+ "grad_norm": 0.51953125,
2512
+ "learning_rate": 0.0034791898508791455,
2513
+ "loss": 5.5735,
2514
+ "step": 175500
2515
+ },
2516
+ {
2517
+ "epoch": 6.52867423399362,
2518
+ "grad_norm": 0.55859375,
2519
+ "learning_rate": 0.0034777060612805103,
2520
+ "loss": 5.573,
2521
+ "step": 176000
2522
+ },
2523
+ {
2524
+ "epoch": 6.547221603976556,
2525
+ "grad_norm": 1.7578125,
2526
+ "learning_rate": 0.0034762222716818755,
2527
+ "loss": 5.5762,
2528
+ "step": 176500
2529
+ },
2530
+ {
2531
+ "epoch": 6.565768973959493,
2532
+ "grad_norm": 0.5625,
2533
+ "learning_rate": 0.0034747384820832407,
2534
+ "loss": 5.5689,
2535
+ "step": 177000
2536
+ },
2537
+ {
2538
+ "epoch": 6.584316343942429,
2539
+ "grad_norm": 0.54296875,
2540
+ "learning_rate": 0.0034732546924846055,
2541
+ "loss": 5.5706,
2542
+ "step": 177500
2543
+ },
2544
+ {
2545
+ "epoch": 6.602863713925365,
2546
+ "grad_norm": 0.63671875,
2547
+ "learning_rate": 0.0034717709028859707,
2548
+ "loss": 5.5762,
2549
+ "step": 178000
2550
+ },
2551
+ {
2552
+ "epoch": 6.621411083908302,
2553
+ "grad_norm": 0.76953125,
2554
+ "learning_rate": 0.003470287113287336,
2555
+ "loss": 5.5689,
2556
+ "step": 178500
2557
+ },
2558
+ {
2559
+ "epoch": 6.639958453891238,
2560
+ "grad_norm": 0.7421875,
2561
+ "learning_rate": 0.003468803323688701,
2562
+ "loss": 5.5731,
2563
+ "step": 179000
2564
+ },
2565
+ {
2566
+ "epoch": 6.658505823874175,
2567
+ "grad_norm": 0.73046875,
2568
+ "learning_rate": 0.0034673195340900664,
2569
+ "loss": 5.5723,
2570
+ "step": 179500
2571
+ },
2572
+ {
2573
+ "epoch": 6.677053193857111,
2574
+ "grad_norm": 0.3984375,
2575
+ "learning_rate": 0.003465835744491431,
2576
+ "loss": 5.5661,
2577
+ "step": 180000
2578
+ },
2579
+ {
2580
+ "epoch": 6.695600563840047,
2581
+ "grad_norm": 0.447265625,
2582
+ "learning_rate": 0.0034643519548927964,
2583
+ "loss": 5.5736,
2584
+ "step": 180500
2585
+ },
2586
+ {
2587
+ "epoch": 6.714147933822984,
2588
+ "grad_norm": 1.171875,
2589
+ "learning_rate": 0.003462868165294161,
2590
+ "loss": 5.5735,
2591
+ "step": 181000
2592
+ },
2593
+ {
2594
+ "epoch": 6.7326953038059205,
2595
+ "grad_norm": 1.09375,
2596
+ "learning_rate": 0.0034613843756955264,
2597
+ "loss": 5.5725,
2598
+ "step": 181500
2599
+ },
2600
+ {
2601
+ "epoch": 6.751242673788857,
2602
+ "grad_norm": 3.6875,
2603
+ "learning_rate": 0.0034599005860968916,
2604
+ "loss": 5.5738,
2605
+ "step": 182000
2606
+ },
2607
+ {
2608
+ "epoch": 6.769790043771793,
2609
+ "grad_norm": 1.078125,
2610
+ "learning_rate": 0.0034584167964982564,
2611
+ "loss": 5.5712,
2612
+ "step": 182500
2613
+ },
2614
+ {
2615
+ "epoch": 6.788337413754729,
2616
+ "grad_norm": 0.75390625,
2617
+ "learning_rate": 0.0034569330068996216,
2618
+ "loss": 5.5752,
2619
+ "step": 183000
2620
+ },
2621
+ {
2622
+ "epoch": 6.806884783737666,
2623
+ "grad_norm": 0.69140625,
2624
+ "learning_rate": 0.003455449217300987,
2625
+ "loss": 5.5772,
2626
+ "step": 183500
2627
+ },
2628
+ {
2629
+ "epoch": 6.825432153720603,
2630
+ "grad_norm": 3.296875,
2631
+ "learning_rate": 0.003453965427702352,
2632
+ "loss": 5.5729,
2633
+ "step": 184000
2634
+ },
2635
+ {
2636
+ "epoch": 6.843979523703538,
2637
+ "grad_norm": 0.578125,
2638
+ "learning_rate": 0.0034524816381037173,
2639
+ "loss": 5.5763,
2640
+ "step": 184500
2641
+ },
2642
+ {
2643
+ "epoch": 6.862526893686475,
2644
+ "grad_norm": 0.4921875,
2645
+ "learning_rate": 0.003450997848505082,
2646
+ "loss": 5.5831,
2647
+ "step": 185000
2648
+ },
2649
+ {
2650
+ "epoch": 6.8810742636694116,
2651
+ "grad_norm": 4.71875,
2652
+ "learning_rate": 0.0034495140589064473,
2653
+ "loss": 5.5789,
2654
+ "step": 185500
2655
+ },
2656
+ {
2657
+ "epoch": 6.899621633652348,
2658
+ "grad_norm": 1.65625,
2659
+ "learning_rate": 0.003448030269307812,
2660
+ "loss": 5.5779,
2661
+ "step": 186000
2662
+ },
2663
+ {
2664
+ "epoch": 6.918169003635285,
2665
+ "grad_norm": 2.90625,
2666
+ "learning_rate": 0.0034465464797091773,
2667
+ "loss": 5.5779,
2668
+ "step": 186500
2669
+ },
2670
+ {
2671
+ "epoch": 6.936716373618221,
2672
+ "grad_norm": 0.47265625,
2673
+ "learning_rate": 0.003445062690110542,
2674
+ "loss": 5.5792,
2675
+ "step": 187000
2676
+ },
2677
+ {
2678
+ "epoch": 6.955263743601157,
2679
+ "grad_norm": 1.015625,
2680
+ "learning_rate": 0.0034435789005119073,
2681
+ "loss": 5.5777,
2682
+ "step": 187500
2683
+ },
2684
+ {
2685
+ "epoch": 6.973811113584094,
2686
+ "grad_norm": 7.5625,
2687
+ "learning_rate": 0.0034420951109132725,
2688
+ "loss": 5.5787,
2689
+ "step": 188000
2690
+ },
2691
+ {
2692
+ "epoch": 6.99235848356703,
2693
+ "grad_norm": 0.55859375,
2694
+ "learning_rate": 0.0034406113213146378,
2695
+ "loss": 5.5825,
2696
+ "step": 188500
2697
+ },
2698
+ {
2699
+ "epoch": 7.0,
2700
+ "eval_loss": 5.567850112915039,
2701
+ "eval_runtime": 0.6773,
2702
+ "eval_samples_per_second": 1275.659,
2703
+ "eval_steps_per_second": 39.864,
2704
+ "step": 188706
2705
+ },
2706
+ {
2707
+ "epoch": 7.010905853549967,
2708
+ "grad_norm": 0.6484375,
2709
+ "learning_rate": 0.003439127531716003,
2710
+ "loss": 5.5696,
2711
+ "step": 189000
2712
+ },
2713
+ {
2714
+ "epoch": 7.0294532235329035,
2715
+ "grad_norm": 3.9375,
2716
+ "learning_rate": 0.0034376437421173678,
2717
+ "loss": 5.5744,
2718
+ "step": 189500
2719
+ },
2720
+ {
2721
+ "epoch": 7.048000593515839,
2722
+ "grad_norm": 3.890625,
2723
+ "learning_rate": 0.003436159952518733,
2724
+ "loss": 5.5745,
2725
+ "step": 190000
2726
+ },
2727
+ {
2728
+ "epoch": 7.066547963498776,
2729
+ "grad_norm": 0.6875,
2730
+ "learning_rate": 0.003434676162920098,
2731
+ "loss": 5.5733,
2732
+ "step": 190500
2733
+ },
2734
+ {
2735
+ "epoch": 7.085095333481712,
2736
+ "grad_norm": 1.6796875,
2737
+ "learning_rate": 0.003433192373321463,
2738
+ "loss": 5.5771,
2739
+ "step": 191000
2740
+ },
2741
+ {
2742
+ "epoch": 7.103642703464649,
2743
+ "grad_norm": 2.484375,
2744
+ "learning_rate": 0.003431708583722828,
2745
+ "loss": 5.5764,
2746
+ "step": 191500
2747
+ },
2748
+ {
2749
+ "epoch": 7.122190073447585,
2750
+ "grad_norm": 7.46875,
2751
+ "learning_rate": 0.003430224794124193,
2752
+ "loss": 5.5742,
2753
+ "step": 192000
2754
+ },
2755
+ {
2756
+ "epoch": 7.140737443430521,
2757
+ "grad_norm": 2.25,
2758
+ "learning_rate": 0.0034287410045255582,
2759
+ "loss": 5.5703,
2760
+ "step": 192500
2761
+ },
2762
+ {
2763
+ "epoch": 7.159284813413458,
2764
+ "grad_norm": 1.6640625,
2765
+ "learning_rate": 0.0034272572149269234,
2766
+ "loss": 5.5721,
2767
+ "step": 193000
2768
+ },
2769
+ {
2770
+ "epoch": 7.1778321833963945,
2771
+ "grad_norm": 2.296875,
2772
+ "learning_rate": 0.0034257734253282887,
2773
+ "loss": 5.5754,
2774
+ "step": 193500
2775
+ },
2776
+ {
2777
+ "epoch": 7.196379553379331,
2778
+ "grad_norm": 5.3125,
2779
+ "learning_rate": 0.003424289635729654,
2780
+ "loss": 5.5735,
2781
+ "step": 194000
2782
+ },
2783
+ {
2784
+ "epoch": 7.214926923362267,
2785
+ "grad_norm": 117.0,
2786
+ "learning_rate": 0.0034228058461310187,
2787
+ "loss": 5.5738,
2788
+ "step": 194500
2789
+ },
2790
+ {
2791
+ "epoch": 7.233474293345203,
2792
+ "grad_norm": 0.80078125,
2793
+ "learning_rate": 0.003421322056532384,
2794
+ "loss": 5.5748,
2795
+ "step": 195000
2796
+ },
2797
+ {
2798
+ "epoch": 7.25202166332814,
2799
+ "grad_norm": 3.125,
2800
+ "learning_rate": 0.0034198382669337487,
2801
+ "loss": 5.5712,
2802
+ "step": 195500
2803
+ },
2804
+ {
2805
+ "epoch": 7.270569033311077,
2806
+ "grad_norm": 0.57421875,
2807
+ "learning_rate": 0.003418354477335114,
2808
+ "loss": 5.5693,
2809
+ "step": 196000
2810
+ },
2811
+ {
2812
+ "epoch": 7.289116403294013,
2813
+ "grad_norm": 3.578125,
2814
+ "learning_rate": 0.003416870687736479,
2815
+ "loss": 5.5708,
2816
+ "step": 196500
2817
+ },
2818
+ {
2819
+ "epoch": 7.307663773276949,
2820
+ "grad_norm": 6.03125,
2821
+ "learning_rate": 0.003415386898137844,
2822
+ "loss": 5.5688,
2823
+ "step": 197000
2824
+ },
2825
+ {
2826
+ "epoch": 7.3262111432598855,
2827
+ "grad_norm": 3.25,
2828
+ "learning_rate": 0.003413903108539209,
2829
+ "loss": 5.5747,
2830
+ "step": 197500
2831
+ },
2832
+ {
2833
+ "epoch": 7.344758513242822,
2834
+ "grad_norm": 1.078125,
2835
+ "learning_rate": 0.0034124193189405743,
2836
+ "loss": 5.5745,
2837
+ "step": 198000
2838
+ },
2839
+ {
2840
+ "epoch": 7.363305883225759,
2841
+ "grad_norm": 7.03125,
2842
+ "learning_rate": 0.0034109355293419396,
2843
+ "loss": 5.5659,
2844
+ "step": 198500
2845
+ },
2846
+ {
2847
+ "epoch": 7.381853253208695,
2848
+ "grad_norm": 11.4375,
2849
+ "learning_rate": 0.0034094517397433048,
2850
+ "loss": 5.5678,
2851
+ "step": 199000
2852
+ },
2853
+ {
2854
+ "epoch": 7.400400623191631,
2855
+ "grad_norm": 9.3125,
2856
+ "learning_rate": 0.0034079679501446696,
2857
+ "loss": 5.5704,
2858
+ "step": 199500
2859
+ },
2860
+ {
2861
+ "epoch": 7.418947993174568,
2862
+ "grad_norm": 1.296875,
2863
+ "learning_rate": 0.003406484160546035,
2864
+ "loss": 5.5665,
2865
+ "step": 200000
2866
+ },
2867
+ {
2868
+ "epoch": 7.437495363157504,
2869
+ "grad_norm": 2.25,
2870
+ "learning_rate": 0.0034050003709473996,
2871
+ "loss": 5.5701,
2872
+ "step": 200500
2873
+ },
2874
+ {
2875
+ "epoch": 7.456042733140441,
2876
+ "grad_norm": 1.2109375,
2877
+ "learning_rate": 0.003403516581348765,
2878
+ "loss": 5.5667,
2879
+ "step": 201000
2880
+ },
2881
+ {
2882
+ "epoch": 7.4745901031233775,
2883
+ "grad_norm": 13.875,
2884
+ "learning_rate": 0.0034020327917501296,
2885
+ "loss": 5.5646,
2886
+ "step": 201500
2887
+ },
2888
+ {
2889
+ "epoch": 7.493137473106313,
2890
+ "grad_norm": 1.3359375,
2891
+ "learning_rate": 0.003400549002151495,
2892
+ "loss": 5.5665,
2893
+ "step": 202000
2894
+ },
2895
+ {
2896
+ "epoch": 7.51168484308925,
2897
+ "grad_norm": 16.875,
2898
+ "learning_rate": 0.00339906521255286,
2899
+ "loss": 5.5627,
2900
+ "step": 202500
2901
+ },
2902
+ {
2903
+ "epoch": 7.530232213072186,
2904
+ "grad_norm": 2.578125,
2905
+ "learning_rate": 0.0033975814229542252,
2906
+ "loss": 5.57,
2907
+ "step": 203000
2908
+ },
2909
+ {
2910
+ "epoch": 7.548779583055123,
2911
+ "grad_norm": 32.5,
2912
+ "learning_rate": 0.0033960976333555905,
2913
+ "loss": 5.5716,
2914
+ "step": 203500
2915
+ },
2916
+ {
2917
+ "epoch": 7.56732695303806,
2918
+ "grad_norm": 0.7265625,
2919
+ "learning_rate": 0.0033946138437569552,
2920
+ "loss": 5.5745,
2921
+ "step": 204000
2922
+ },
2923
+ {
2924
+ "epoch": 7.585874323020995,
2925
+ "grad_norm": 0.46875,
2926
+ "learning_rate": 0.0033931300541583205,
2927
+ "loss": 5.5691,
2928
+ "step": 204500
2929
+ },
2930
+ {
2931
+ "epoch": 7.604421693003932,
2932
+ "grad_norm": 3.015625,
2933
+ "learning_rate": 0.0033916462645596857,
2934
+ "loss": 5.5736,
2935
+ "step": 205000
2936
+ },
2937
+ {
2938
+ "epoch": 7.6229690629868685,
2939
+ "grad_norm": 75.5,
2940
+ "learning_rate": 0.0033901624749610505,
2941
+ "loss": 5.5712,
2942
+ "step": 205500
2943
+ },
2944
+ {
2945
+ "epoch": 7.641516432969805,
2946
+ "grad_norm": 1.6953125,
2947
+ "learning_rate": 0.0033886786853624157,
2948
+ "loss": 5.5746,
2949
+ "step": 206000
2950
+ },
2951
+ {
2952
+ "epoch": 7.660063802952742,
2953
+ "grad_norm": 0.73046875,
2954
+ "learning_rate": 0.0033871948957637805,
2955
+ "loss": 5.5719,
2956
+ "step": 206500
2957
+ },
2958
+ {
2959
+ "epoch": 7.678611172935677,
2960
+ "grad_norm": 0.77734375,
2961
+ "learning_rate": 0.0033857111061651457,
2962
+ "loss": 5.5718,
2963
+ "step": 207000
2964
+ },
2965
+ {
2966
+ "epoch": 7.697158542918614,
2967
+ "grad_norm": 1.1328125,
2968
+ "learning_rate": 0.003384227316566511,
2969
+ "loss": 5.5724,
2970
+ "step": 207500
2971
+ },
2972
+ {
2973
+ "epoch": 7.715705912901551,
2974
+ "grad_norm": 0.51953125,
2975
+ "learning_rate": 0.003382743526967876,
2976
+ "loss": 5.5642,
2977
+ "step": 208000
2978
+ },
2979
+ {
2980
+ "epoch": 7.734253282884487,
2981
+ "grad_norm": 6.65625,
2982
+ "learning_rate": 0.0033812597373692414,
2983
+ "loss": 5.5714,
2984
+ "step": 208500
2985
+ },
2986
+ {
2987
+ "epoch": 7.752800652867423,
2988
+ "grad_norm": 3.375,
2989
+ "learning_rate": 0.003379775947770606,
2990
+ "loss": 5.5713,
2991
+ "step": 209000
2992
+ },
2993
+ {
2994
+ "epoch": 7.7713480228503595,
2995
+ "grad_norm": 0.9453125,
2996
+ "learning_rate": 0.0033782921581719714,
2997
+ "loss": 5.5678,
2998
+ "step": 209500
2999
+ },
3000
+ {
3001
+ "epoch": 7.789895392833296,
3002
+ "grad_norm": 6.5625,
3003
+ "learning_rate": 0.0033768083685733366,
3004
+ "loss": 5.5661,
3005
+ "step": 210000
3006
+ },
3007
+ {
3008
+ "epoch": 7.808442762816233,
3009
+ "grad_norm": 0.90234375,
3010
+ "learning_rate": 0.0033753245789747014,
3011
+ "loss": 5.5663,
3012
+ "step": 210500
3013
+ },
3014
+ {
3015
+ "epoch": 7.826990132799169,
3016
+ "grad_norm": 0.5390625,
3017
+ "learning_rate": 0.0033738407893760666,
3018
+ "loss": 5.5659,
3019
+ "step": 211000
3020
+ },
3021
+ {
3022
+ "epoch": 7.845537502782106,
3023
+ "grad_norm": 3.0,
3024
+ "learning_rate": 0.0033723569997774314,
3025
+ "loss": 5.5639,
3026
+ "step": 211500
3027
+ },
3028
+ {
3029
+ "epoch": 7.864084872765042,
3030
+ "grad_norm": 0.48046875,
3031
+ "learning_rate": 0.0033708732101787966,
3032
+ "loss": 5.5662,
3033
+ "step": 212000
3034
+ },
3035
+ {
3036
+ "epoch": 7.882632242747978,
3037
+ "grad_norm": 0.5703125,
3038
+ "learning_rate": 0.003369389420580162,
3039
+ "loss": 5.5677,
3040
+ "step": 212500
3041
+ },
3042
+ {
3043
+ "epoch": 7.901179612730915,
3044
+ "grad_norm": 3.03125,
3045
+ "learning_rate": 0.003367905630981527,
3046
+ "loss": 5.5709,
3047
+ "step": 213000
3048
+ },
3049
+ {
3050
+ "epoch": 7.9197269827138514,
3051
+ "grad_norm": 0.99609375,
3052
+ "learning_rate": 0.003366421841382892,
3053
+ "loss": 5.5671,
3054
+ "step": 213500
3055
+ },
3056
+ {
3057
+ "epoch": 7.938274352696787,
3058
+ "grad_norm": 1.0859375,
3059
+ "learning_rate": 0.003364938051784257,
3060
+ "loss": 5.5698,
3061
+ "step": 214000
3062
+ },
3063
+ {
3064
+ "epoch": 7.956821722679724,
3065
+ "grad_norm": 0.99609375,
3066
+ "learning_rate": 0.0033634542621856223,
3067
+ "loss": 5.567,
3068
+ "step": 214500
3069
+ },
3070
+ {
3071
+ "epoch": 7.97536909266266,
3072
+ "grad_norm": 1.0,
3073
+ "learning_rate": 0.0033619704725869875,
3074
+ "loss": 5.5695,
3075
+ "step": 215000
3076
+ },
3077
+ {
3078
+ "epoch": 7.993916462645597,
3079
+ "grad_norm": 0.53125,
3080
+ "learning_rate": 0.0033604866829883523,
3081
+ "loss": 5.5664,
3082
+ "step": 215500
3083
+ },
3084
+ {
3085
+ "epoch": 8.0,
3086
+ "eval_loss": 5.560152530670166,
3087
+ "eval_runtime": 0.6991,
3088
+ "eval_samples_per_second": 1235.91,
3089
+ "eval_steps_per_second": 38.622,
3090
+ "step": 215664
3091
+ }
3092
+ ],
3093
+ "logging_steps": 500,
3094
+ "max_steps": 1347900,
3095
+ "num_input_tokens_seen": 0,
3096
+ "num_train_epochs": 50,
3097
+ "save_steps": 500,
3098
+ "stateful_callbacks": {
3099
+ "EarlyStoppingCallback": {
3100
+ "args": {
3101
+ "early_stopping_patience": 3,
3102
+ "early_stopping_threshold": 0.0
3103
+ },
3104
+ "attributes": {
3105
+ "early_stopping_patience_counter": 0
3106
+ }
3107
+ },
3108
+ "TrainerControl": {
3109
+ "args": {
3110
+ "should_epoch_stop": false,
3111
+ "should_evaluate": false,
3112
+ "should_log": false,
3113
+ "should_save": true,
3114
+ "should_training_stop": false
3115
+ },
3116
+ "attributes": {}
3117
+ }
3118
+ },
3119
+ "total_flos": 7.806432977547817e+17,
3120
+ "train_batch_size": 32,
3121
+ "trial_name": null,
3122
+ "trial_params": null
3123
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5190072fcf732d5235d15b10bc1cf8cba4d19109ee201b6da9e30b9663b2d7
3
+ size 5112