hanbin commited on
Commit
f94dccb
·
verified ·
1 Parent(s): de05e84

Upload 11 files

Browse files
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 2978959170994176.0,
4
+ "train_loss": 0.161040273276637,
5
+ "train_runtime": 34957.7462,
6
+ "train_samples_per_second": 19.698,
7
+ "train_steps_per_second": 0.077
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,275 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 2691, "loss": 0.3679, "learning_rate": 3.7037037037037036e-07, "epoch": 0.011148272017837236, "percentage": 0.37, "elapsed_time": "0:02:27", "remaining_time": "11:00:00", "throughput": "0.00", "total_tokens": 0}
2
+ {"current_steps": 20, "total_steps": 2691, "loss": 0.3385, "learning_rate": 7.407407407407407e-07, "epoch": 0.022296544035674472, "percentage": 0.74, "elapsed_time": "0:04:34", "remaining_time": "10:10:28", "throughput": "0.00", "total_tokens": 0}
3
+ {"current_steps": 30, "total_steps": 2691, "loss": 0.3008, "learning_rate": 1.111111111111111e-06, "epoch": 0.033444816053511704, "percentage": 1.11, "elapsed_time": "0:06:48", "remaining_time": "10:04:28", "throughput": "0.00", "total_tokens": 0}
4
+ {"current_steps": 40, "total_steps": 2691, "loss": 0.2689, "learning_rate": 1.4814814814814815e-06, "epoch": 0.044593088071348944, "percentage": 1.49, "elapsed_time": "0:08:56", "remaining_time": "9:52:51", "throughput": "0.00", "total_tokens": 0}
5
+ {"current_steps": 50, "total_steps": 2691, "loss": 0.2506, "learning_rate": 1.8518518518518519e-06, "epoch": 0.055741360089186176, "percentage": 1.86, "elapsed_time": "0:11:03", "remaining_time": "9:44:25", "throughput": "0.00", "total_tokens": 0}
6
+ {"current_steps": 60, "total_steps": 2691, "loss": 0.24, "learning_rate": 2.222222222222222e-06, "epoch": 0.06688963210702341, "percentage": 2.23, "elapsed_time": "0:13:02", "remaining_time": "9:31:31", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 70, "total_steps": 2691, "loss": 0.2374, "learning_rate": 2.5925925925925925e-06, "epoch": 0.07803790412486064, "percentage": 2.6, "elapsed_time": "0:15:02", "remaining_time": "9:23:02", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 80, "total_steps": 2691, "loss": 0.2343, "learning_rate": 2.962962962962963e-06, "epoch": 0.08918617614269789, "percentage": 2.97, "elapsed_time": "0:16:53", "remaining_time": "9:11:20", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 90, "total_steps": 2691, "loss": 0.2279, "learning_rate": 3.3333333333333333e-06, "epoch": 0.10033444816053512, "percentage": 3.34, "elapsed_time": "0:19:08", "remaining_time": "9:13:15", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 100, "total_steps": 2691, "loss": 0.2263, "learning_rate": 3.7037037037037037e-06, "epoch": 0.11148272017837235, "percentage": 3.72, "elapsed_time": "0:21:10", "remaining_time": "9:08:28", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 110, "total_steps": 2691, "loss": 0.2239, "learning_rate": 4.074074074074074e-06, "epoch": 0.12263099219620958, "percentage": 4.09, "elapsed_time": "0:23:47", "remaining_time": "9:18:10", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 120, "total_steps": 2691, "loss": 0.2232, "learning_rate": 4.444444444444444e-06, "epoch": 0.13377926421404682, "percentage": 4.46, "elapsed_time": "0:25:59", "remaining_time": "9:16:55", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 130, "total_steps": 2691, "loss": 0.2231, "learning_rate": 4.814814814814815e-06, "epoch": 0.14492753623188406, "percentage": 4.83, "elapsed_time": "0:28:04", "remaining_time": "9:13:00", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 140, "total_steps": 2691, "loss": 0.2215, "learning_rate": 5.185185185185185e-06, "epoch": 0.15607580824972128, "percentage": 5.2, "elapsed_time": "0:30:23", "remaining_time": "9:13:48", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 150, "total_steps": 2691, "loss": 0.2203, "learning_rate": 5.555555555555557e-06, "epoch": 0.16722408026755853, "percentage": 5.57, "elapsed_time": "0:32:22", "remaining_time": "9:08:28", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 160, "total_steps": 2691, "loss": 0.2186, "learning_rate": 5.925925925925926e-06, "epoch": 0.17837235228539577, "percentage": 5.95, "elapsed_time": "0:34:32", "remaining_time": "9:06:32", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 170, "total_steps": 2691, "loss": 0.2184, "learning_rate": 6.296296296296297e-06, "epoch": 0.189520624303233, "percentage": 6.32, "elapsed_time": "0:36:31", "remaining_time": "9:01:33", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 180, "total_steps": 2691, "loss": 0.22, "learning_rate": 6.666666666666667e-06, "epoch": 0.20066889632107024, "percentage": 6.69, "elapsed_time": "0:38:35", "remaining_time": "8:58:27", "throughput": "0.00", "total_tokens": 0}
19
+ {"current_steps": 190, "total_steps": 2691, "loss": 0.2181, "learning_rate": 7.0370370370370375e-06, "epoch": 0.21181716833890746, "percentage": 7.06, "elapsed_time": "0:40:45", "remaining_time": "8:56:30", "throughput": "0.00", "total_tokens": 0}
20
+ {"current_steps": 200, "total_steps": 2691, "loss": 0.221, "learning_rate": 7.4074074074074075e-06, "epoch": 0.2229654403567447, "percentage": 7.43, "elapsed_time": "0:42:59", "remaining_time": "8:55:28", "throughput": "0.00", "total_tokens": 0}
21
+ {"current_steps": 210, "total_steps": 2691, "loss": 0.2188, "learning_rate": 7.77777777777778e-06, "epoch": 0.23411371237458195, "percentage": 7.8, "elapsed_time": "0:45:35", "remaining_time": "8:58:32", "throughput": "0.00", "total_tokens": 0}
22
+ {"current_steps": 220, "total_steps": 2691, "loss": 0.2191, "learning_rate": 8.148148148148148e-06, "epoch": 0.24526198439241917, "percentage": 8.18, "elapsed_time": "0:47:42", "remaining_time": "8:55:49", "throughput": "0.00", "total_tokens": 0}
23
+ {"current_steps": 230, "total_steps": 2691, "loss": 0.222, "learning_rate": 8.518518518518519e-06, "epoch": 0.2564102564102564, "percentage": 8.55, "elapsed_time": "0:49:45", "remaining_time": "8:52:20", "throughput": "0.00", "total_tokens": 0}
24
+ {"current_steps": 240, "total_steps": 2691, "loss": 0.2189, "learning_rate": 8.888888888888888e-06, "epoch": 0.26755852842809363, "percentage": 8.92, "elapsed_time": "0:51:55", "remaining_time": "8:50:19", "throughput": "0.00", "total_tokens": 0}
25
+ {"current_steps": 250, "total_steps": 2691, "loss": 0.2177, "learning_rate": 9.25925925925926e-06, "epoch": 0.2787068004459309, "percentage": 9.29, "elapsed_time": "0:53:55", "remaining_time": "8:46:34", "throughput": "0.00", "total_tokens": 0}
26
+ {"current_steps": 260, "total_steps": 2691, "loss": 0.2202, "learning_rate": 9.62962962962963e-06, "epoch": 0.2898550724637681, "percentage": 9.66, "elapsed_time": "0:56:04", "remaining_time": "8:44:19", "throughput": "0.00", "total_tokens": 0}
27
+ {"current_steps": 270, "total_steps": 2691, "loss": 0.217, "learning_rate": 1e-05, "epoch": 0.3010033444816054, "percentage": 10.03, "elapsed_time": "0:58:15", "remaining_time": "8:42:22", "throughput": "0.00", "total_tokens": 0}
28
+ {"current_steps": 280, "total_steps": 2691, "loss": 0.2184, "learning_rate": 9.999579036849509e-06, "epoch": 0.31215161649944256, "percentage": 10.41, "elapsed_time": "1:00:13", "remaining_time": "8:38:35", "throughput": "0.00", "total_tokens": 0}
29
+ {"current_steps": 290, "total_steps": 2691, "loss": 0.2165, "learning_rate": 9.998316218282025e-06, "epoch": 0.3232998885172798, "percentage": 10.78, "elapsed_time": "1:02:08", "remaining_time": "8:34:33", "throughput": "0.00", "total_tokens": 0}
30
+ {"current_steps": 300, "total_steps": 2691, "loss": 0.2153, "learning_rate": 9.996211756937579e-06, "epoch": 0.33444816053511706, "percentage": 11.15, "elapsed_time": "1:04:22", "remaining_time": "8:33:06", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 310, "total_steps": 2691, "loss": 0.2183, "learning_rate": 9.993266007176446e-06, "epoch": 0.3455964325529543, "percentage": 11.52, "elapsed_time": "1:07:02", "remaining_time": "8:34:55", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 320, "total_steps": 2691, "loss": 0.2168, "learning_rate": 9.989479465019462e-06, "epoch": 0.35674470457079155, "percentage": 11.89, "elapsed_time": "1:09:15", "remaining_time": "8:33:07", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 330, "total_steps": 2691, "loss": 0.2164, "learning_rate": 9.984852768064516e-06, "epoch": 0.36789297658862874, "percentage": 12.26, "elapsed_time": "1:11:14", "remaining_time": "8:29:44", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 340, "total_steps": 2691, "loss": 0.2157, "learning_rate": 9.979386695379179e-06, "epoch": 0.379041248606466, "percentage": 12.63, "elapsed_time": "1:13:24", "remaining_time": "8:27:36", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 350, "total_steps": 2691, "loss": 0.2144, "learning_rate": 9.973082167369521e-06, "epoch": 0.39018952062430323, "percentage": 13.01, "elapsed_time": "1:15:33", "remaining_time": "8:25:23", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 360, "total_steps": 2691, "loss": 0.2109, "learning_rate": 9.965940245625131e-06, "epoch": 0.4013377926421405, "percentage": 13.38, "elapsed_time": "1:17:30", "remaining_time": "8:21:52", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 370, "total_steps": 2691, "loss": 0.2159, "learning_rate": 9.95796213274036e-06, "epoch": 0.4124860646599777, "percentage": 13.75, "elapsed_time": "1:19:36", "remaining_time": "8:19:20", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 380, "total_steps": 2691, "loss": 0.2154, "learning_rate": 9.949149172111825e-06, "epoch": 0.4236343366778149, "percentage": 14.12, "elapsed_time": "1:21:41", "remaining_time": "8:16:49", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 390, "total_steps": 2691, "loss": 0.215, "learning_rate": 9.93950284771219e-06, "epoch": 0.43478260869565216, "percentage": 14.49, "elapsed_time": "1:23:50", "remaining_time": "8:14:39", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 400, "total_steps": 2691, "loss": 0.2156, "learning_rate": 9.929024783840302e-06, "epoch": 0.4459308807134894, "percentage": 14.86, "elapsed_time": "1:26:03", "remaining_time": "8:12:55", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 410, "total_steps": 2691, "loss": 0.2135, "learning_rate": 9.917716744847674e-06, "epoch": 0.45707915273132665, "percentage": 15.24, "elapsed_time": "1:28:32", "remaining_time": "8:12:37", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 420, "total_steps": 2691, "loss": 0.2127, "learning_rate": 9.905580634841388e-06, "epoch": 0.4682274247491639, "percentage": 15.61, "elapsed_time": "1:30:41", "remaining_time": "8:10:23", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 430, "total_steps": 2691, "loss": 0.2152, "learning_rate": 9.892618497363491e-06, "epoch": 0.4793756967670011, "percentage": 15.98, "elapsed_time": "1:32:51", "remaining_time": "8:08:17", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 440, "total_steps": 2691, "loss": 0.2121, "learning_rate": 9.878832515046873e-06, "epoch": 0.49052396878483834, "percentage": 16.35, "elapsed_time": "1:34:53", "remaining_time": "8:05:28", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 450, "total_steps": 2691, "loss": 0.2124, "learning_rate": 9.864225009247753e-06, "epoch": 0.5016722408026756, "percentage": 16.72, "elapsed_time": "1:37:04", "remaining_time": "8:03:27", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 460, "total_steps": 2691, "loss": 0.2116, "learning_rate": 9.848798439654797e-06, "epoch": 0.5128205128205128, "percentage": 17.09, "elapsed_time": "1:39:09", "remaining_time": "8:00:56", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 470, "total_steps": 2691, "loss": 0.2107, "learning_rate": 9.832555403874937e-06, "epoch": 0.5239687848383501, "percentage": 17.47, "elapsed_time": "1:41:18", "remaining_time": "7:58:44", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 480, "total_steps": 2691, "loss": 0.2092, "learning_rate": 9.815498636995982e-06, "epoch": 0.5351170568561873, "percentage": 17.84, "elapsed_time": "1:43:25", "remaining_time": "7:56:24", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 490, "total_steps": 2691, "loss": 0.2098, "learning_rate": 9.797631011126061e-06, "epoch": 0.5462653288740246, "percentage": 18.21, "elapsed_time": "1:45:33", "remaining_time": "7:54:11", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 500, "total_steps": 2691, "loss": 0.2107, "learning_rate": 9.778955534910004e-06, "epoch": 0.5574136008918618, "percentage": 18.58, "elapsed_time": "1:47:44", "remaining_time": "7:52:05", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 500, "total_steps": 2691, "eval_loss": 0.21421977877616882, "epoch": 0.5574136008918618, "percentage": 18.58, "elapsed_time": "1:47:49", "remaining_time": "7:52:30", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 510, "total_steps": 2691, "loss": 0.2096, "learning_rate": 9.759475353022735e-06, "epoch": 0.568561872909699, "percentage": 18.95, "elapsed_time": "1:50:12", "remaining_time": "7:51:20", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 520, "total_steps": 2691, "loss": 0.2088, "learning_rate": 9.739193745639745e-06, "epoch": 0.5797101449275363, "percentage": 19.32, "elapsed_time": "1:52:28", "remaining_time": "7:49:35", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 530, "total_steps": 2691, "loss": 0.2079, "learning_rate": 9.718114127884774e-06, "epoch": 0.5908584169453734, "percentage": 19.7, "elapsed_time": "1:54:44", "remaining_time": "7:47:50", "throughput": "0.00", "total_tokens": 0}
55
+ {"current_steps": 540, "total_steps": 2691, "loss": 0.2095, "learning_rate": 9.696240049254744e-06, "epoch": 0.6020066889632107, "percentage": 20.07, "elapsed_time": "1:56:42", "remaining_time": "7:44:53", "throughput": "0.00", "total_tokens": 0}
56
+ {"current_steps": 550, "total_steps": 2691, "loss": 0.2103, "learning_rate": 9.673575193022073e-06, "epoch": 0.6131549609810479, "percentage": 20.44, "elapsed_time": "1:58:44", "remaining_time": "7:42:12", "throughput": "0.00", "total_tokens": 0}
57
+ {"current_steps": 560, "total_steps": 2691, "loss": 0.209, "learning_rate": 9.650123375614477e-06, "epoch": 0.6243032329988851, "percentage": 20.81, "elapsed_time": "2:00:42", "remaining_time": "7:39:21", "throughput": "0.00", "total_tokens": 0}
58
+ {"current_steps": 570, "total_steps": 2691, "loss": 0.2109, "learning_rate": 9.625888545972333e-06, "epoch": 0.6354515050167224, "percentage": 21.18, "elapsed_time": "2:02:45", "remaining_time": "7:36:49", "throughput": "0.00", "total_tokens": 0}
59
+ {"current_steps": 580, "total_steps": 2691, "loss": 0.2072, "learning_rate": 9.600874784883736e-06, "epoch": 0.6465997770345596, "percentage": 21.55, "elapsed_time": "2:04:53", "remaining_time": "7:34:32", "throughput": "0.00", "total_tokens": 0}
60
+ {"current_steps": 590, "total_steps": 2691, "loss": 0.2068, "learning_rate": 9.575086304297351e-06, "epoch": 0.6577480490523969, "percentage": 21.92, "elapsed_time": "2:07:00", "remaining_time": "7:32:16", "throughput": "0.00", "total_tokens": 0}
61
+ {"current_steps": 600, "total_steps": 2691, "loss": 0.2088, "learning_rate": 9.548527446613198e-06, "epoch": 0.6688963210702341, "percentage": 22.3, "elapsed_time": "2:09:21", "remaining_time": "7:30:48", "throughput": "0.00", "total_tokens": 0}
62
+ {"current_steps": 610, "total_steps": 2691, "loss": 0.2079, "learning_rate": 9.521202683951436e-06, "epoch": 0.6800445930880713, "percentage": 22.67, "elapsed_time": "2:11:56", "remaining_time": "7:30:07", "throughput": "0.00", "total_tokens": 0}
63
+ {"current_steps": 620, "total_steps": 2691, "loss": 0.2086, "learning_rate": 9.493116617399333e-06, "epoch": 0.6911928651059086, "percentage": 23.04, "elapsed_time": "2:14:10", "remaining_time": "7:28:12", "throughput": "0.00", "total_tokens": 0}
64
+ {"current_steps": 630, "total_steps": 2691, "loss": 0.2079, "learning_rate": 9.464273976236518e-06, "epoch": 0.7023411371237458, "percentage": 23.41, "elapsed_time": "2:16:16", "remaining_time": "7:25:50", "throughput": "0.00", "total_tokens": 0}
65
+ {"current_steps": 640, "total_steps": 2691, "loss": 0.207, "learning_rate": 9.434679617138624e-06, "epoch": 0.7134894091415831, "percentage": 23.78, "elapsed_time": "2:18:20", "remaining_time": "7:23:19", "throughput": "0.00", "total_tokens": 0}
66
+ {"current_steps": 650, "total_steps": 2691, "loss": 0.2072, "learning_rate": 9.404338523359511e-06, "epoch": 0.7246376811594203, "percentage": 24.15, "elapsed_time": "2:20:29", "remaining_time": "7:21:07", "throughput": "0.00", "total_tokens": 0}
67
+ {"current_steps": 660, "total_steps": 2691, "loss": 0.2043, "learning_rate": 9.373255803892149e-06, "epoch": 0.7357859531772575, "percentage": 24.53, "elapsed_time": "2:22:45", "remaining_time": "7:19:17", "throughput": "0.00", "total_tokens": 0}
68
+ {"current_steps": 670, "total_steps": 2691, "loss": 0.2059, "learning_rate": 9.341436692608341e-06, "epoch": 0.7469342251950948, "percentage": 24.9, "elapsed_time": "2:24:51", "remaining_time": "7:16:56", "throughput": "0.00", "total_tokens": 0}
69
+ {"current_steps": 680, "total_steps": 2691, "loss": 0.2045, "learning_rate": 9.30888654737742e-06, "epoch": 0.758082497212932, "percentage": 25.27, "elapsed_time": "2:26:58", "remaining_time": "7:14:37", "throughput": "0.00", "total_tokens": 0}
70
+ {"current_steps": 690, "total_steps": 2691, "loss": 0.2037, "learning_rate": 9.275610849164066e-06, "epoch": 0.7692307692307693, "percentage": 25.64, "elapsed_time": "2:29:07", "remaining_time": "7:12:26", "throughput": "0.00", "total_tokens": 0}
71
+ {"current_steps": 700, "total_steps": 2691, "loss": 0.2055, "learning_rate": 9.241615201105372e-06, "epoch": 0.7803790412486065, "percentage": 26.01, "elapsed_time": "2:31:16", "remaining_time": "7:10:14", "throughput": "0.00", "total_tokens": 0}
72
+ {"current_steps": 710, "total_steps": 2691, "loss": 0.2084, "learning_rate": 9.206905327567385e-06, "epoch": 0.7915273132664437, "percentage": 26.38, "elapsed_time": "2:33:50", "remaining_time": "7:09:14", "throughput": "0.00", "total_tokens": 0}
73
+ {"current_steps": 720, "total_steps": 2691, "loss": 0.2054, "learning_rate": 9.171487073181198e-06, "epoch": 0.802675585284281, "percentage": 26.76, "elapsed_time": "2:35:56", "remaining_time": "7:06:53", "throughput": "0.00", "total_tokens": 0}
74
+ {"current_steps": 730, "total_steps": 2691, "loss": 0.2073, "learning_rate": 9.135366401858782e-06, "epoch": 0.8138238573021181, "percentage": 27.13, "elapsed_time": "2:38:03", "remaining_time": "7:04:34", "throughput": "0.00", "total_tokens": 0}
75
+ {"current_steps": 740, "total_steps": 2691, "loss": 0.2073, "learning_rate": 9.098549395788784e-06, "epoch": 0.8249721293199554, "percentage": 27.5, "elapsed_time": "2:40:09", "remaining_time": "7:02:14", "throughput": "0.00", "total_tokens": 0}
76
+ {"current_steps": 750, "total_steps": 2691, "loss": 0.2039, "learning_rate": 9.061042254412346e-06, "epoch": 0.8361204013377926, "percentage": 27.87, "elapsed_time": "2:42:12", "remaining_time": "6:59:47", "throughput": "0.00", "total_tokens": 0}
77
+ {"current_steps": 760, "total_steps": 2691, "loss": 0.2053, "learning_rate": 9.022851293379232e-06, "epoch": 0.8472686733556298, "percentage": 28.24, "elapsed_time": "2:44:12", "remaining_time": "6:57:13", "throughput": "0.00", "total_tokens": 0}
78
+ {"current_steps": 770, "total_steps": 2691, "loss": 0.2023, "learning_rate": 8.983982943484348e-06, "epoch": 0.8584169453734671, "percentage": 28.61, "elapsed_time": "2:46:23", "remaining_time": "6:55:07", "throughput": "0.00", "total_tokens": 0}
79
+ {"current_steps": 780, "total_steps": 2691, "loss": 0.2043, "learning_rate": 8.944443749584908e-06, "epoch": 0.8695652173913043, "percentage": 28.99, "elapsed_time": "2:48:30", "remaining_time": "6:52:51", "throughput": "0.00", "total_tokens": 0}
80
+ {"current_steps": 790, "total_steps": 2691, "loss": 0.2013, "learning_rate": 8.904240369498363e-06, "epoch": 0.8807134894091416, "percentage": 29.36, "elapsed_time": "2:50:34", "remaining_time": "6:50:28", "throughput": "0.00", "total_tokens": 0}
81
+ {"current_steps": 800, "total_steps": 2691, "loss": 0.2038, "learning_rate": 8.863379572881328e-06, "epoch": 0.8918617614269788, "percentage": 29.73, "elapsed_time": "2:52:39", "remaining_time": "6:48:07", "throughput": "0.00", "total_tokens": 0}
82
+ {"current_steps": 810, "total_steps": 2691, "loss": 0.2044, "learning_rate": 8.821868240089676e-06, "epoch": 0.903010033444816, "percentage": 30.1, "elapsed_time": "2:55:20", "remaining_time": "6:47:11", "throughput": "0.00", "total_tokens": 0}
83
+ {"current_steps": 820, "total_steps": 2691, "loss": 0.2068, "learning_rate": 8.779713361019983e-06, "epoch": 0.9141583054626533, "percentage": 30.47, "elapsed_time": "2:57:22", "remaining_time": "6:44:42", "throughput": "0.00", "total_tokens": 0}
84
+ {"current_steps": 830, "total_steps": 2691, "loss": 0.2022, "learning_rate": 8.736922033932522e-06, "epoch": 0.9253065774804905, "percentage": 30.84, "elapsed_time": "2:59:26", "remaining_time": "6:42:19", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 840, "total_steps": 2691, "loss": 0.2027, "learning_rate": 8.693501464256046e-06, "epoch": 0.9364548494983278, "percentage": 31.22, "elapsed_time": "3:01:36", "remaining_time": "6:40:10", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 850, "total_steps": 2691, "loss": 0.2032, "learning_rate": 8.649458963374474e-06, "epoch": 0.947603121516165, "percentage": 31.59, "elapsed_time": "3:03:47", "remaining_time": "6:38:03", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 860, "total_steps": 2691, "loss": 0.2, "learning_rate": 8.604801947395776e-06, "epoch": 0.9587513935340022, "percentage": 31.96, "elapsed_time": "3:06:03", "remaining_time": "6:36:08", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 870, "total_steps": 2691, "loss": 0.2021, "learning_rate": 8.55953793590321e-06, "epoch": 0.9698996655518395, "percentage": 32.33, "elapsed_time": "3:08:14", "remaining_time": "6:34:00", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 880, "total_steps": 2691, "loss": 0.2002, "learning_rate": 8.513674550689128e-06, "epoch": 0.9810479375696767, "percentage": 32.7, "elapsed_time": "3:10:18", "remaining_time": "6:31:38", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 890, "total_steps": 2691, "loss": 0.2024, "learning_rate": 8.46721951447158e-06, "epoch": 0.992196209587514, "percentage": 33.07, "elapsed_time": "3:12:21", "remaining_time": "6:29:16", "throughput": "0.00", "total_tokens": 0}
91
+ {"current_steps": 900, "total_steps": 2691, "loss": 0.1903, "learning_rate": 8.42018064959393e-06, "epoch": 1.0033444816053512, "percentage": 33.44, "elapsed_time": "3:14:33", "remaining_time": "6:27:10", "throughput": "0.00", "total_tokens": 0}
92
+ {"current_steps": 910, "total_steps": 2691, "loss": 0.1599, "learning_rate": 8.37256587670768e-06, "epoch": 1.0144927536231885, "percentage": 33.82, "elapsed_time": "3:17:04", "remaining_time": "6:25:42", "throughput": "0.00", "total_tokens": 0}
93
+ {"current_steps": 920, "total_steps": 2691, "loss": 0.1578, "learning_rate": 8.32438321343875e-06, "epoch": 1.0256410256410255, "percentage": 34.19, "elapsed_time": "3:19:14", "remaining_time": "6:23:32", "throughput": "0.00", "total_tokens": 0}
94
+ {"current_steps": 930, "total_steps": 2691, "loss": 0.1584, "learning_rate": 8.275640773037432e-06, "epoch": 1.0367892976588629, "percentage": 34.56, "elapsed_time": "3:21:27", "remaining_time": "6:21:28", "throughput": "0.00", "total_tokens": 0}
95
+ {"current_steps": 940, "total_steps": 2691, "loss": 0.1591, "learning_rate": 8.226346763012234e-06, "epoch": 1.0479375696767002, "percentage": 34.93, "elapsed_time": "3:23:37", "remaining_time": "6:19:17", "throughput": "0.00", "total_tokens": 0}
96
+ {"current_steps": 950, "total_steps": 2691, "loss": 0.1587, "learning_rate": 8.176509483747863e-06, "epoch": 1.0590858416945372, "percentage": 35.3, "elapsed_time": "3:25:46", "remaining_time": "6:17:07", "throughput": "0.00", "total_tokens": 0}
97
+ {"current_steps": 960, "total_steps": 2691, "loss": 0.1559, "learning_rate": 8.126137327107556e-06, "epoch": 1.0702341137123745, "percentage": 35.67, "elapsed_time": "3:27:55", "remaining_time": "6:14:55", "throughput": "0.00", "total_tokens": 0}
98
+ {"current_steps": 970, "total_steps": 2691, "loss": 0.1582, "learning_rate": 8.075238775020011e-06, "epoch": 1.0813823857302118, "percentage": 36.05, "elapsed_time": "3:29:52", "remaining_time": "6:12:22", "throughput": "0.00", "total_tokens": 0}
99
+ {"current_steps": 980, "total_steps": 2691, "loss": 0.1588, "learning_rate": 8.023822398051168e-06, "epoch": 1.0925306577480491, "percentage": 36.42, "elapsed_time": "3:31:59", "remaining_time": "6:10:06", "throughput": "0.00", "total_tokens": 0}
100
+ {"current_steps": 990, "total_steps": 2691, "loss": 0.1576, "learning_rate": 7.971896853961043e-06, "epoch": 1.1036789297658862, "percentage": 36.79, "elapsed_time": "3:34:09", "remaining_time": "6:07:57", "throughput": "0.00", "total_tokens": 0}
101
+ {"current_steps": 1000, "total_steps": 2691, "loss": 0.1561, "learning_rate": 7.919470886245886e-06, "epoch": 1.1148272017837235, "percentage": 37.16, "elapsed_time": "3:36:22", "remaining_time": "6:05:53", "throughput": "0.00", "total_tokens": 0}
102
+ {"current_steps": 1000, "total_steps": 2691, "eval_loss": 0.20845723152160645, "epoch": 1.1148272017837235, "percentage": 37.16, "elapsed_time": "3:36:27", "remaining_time": "6:06:02", "throughput": "0.00", "total_tokens": 0}
103
+ {"current_steps": 1010, "total_steps": 2691, "loss": 0.1586, "learning_rate": 7.86655332266591e-06, "epoch": 1.1259754738015608, "percentage": 37.53, "elapsed_time": "3:38:57", "remaining_time": "6:04:25", "throughput": "0.00", "total_tokens": 0}
104
+ {"current_steps": 1020, "total_steps": 2691, "loss": 0.1582, "learning_rate": 7.813153073758833e-06, "epoch": 1.137123745819398, "percentage": 37.9, "elapsed_time": "3:41:09", "remaining_time": "6:02:18", "throughput": "0.00", "total_tokens": 0}
105
+ {"current_steps": 1030, "total_steps": 2691, "loss": 0.1579, "learning_rate": 7.759279131339455e-06, "epoch": 1.1482720178372352, "percentage": 38.28, "elapsed_time": "3:43:18", "remaining_time": "6:00:06", "throughput": "0.00", "total_tokens": 0}
106
+ {"current_steps": 1040, "total_steps": 2691, "loss": 0.163, "learning_rate": 7.704940566985592e-06, "epoch": 1.1594202898550725, "percentage": 38.65, "elapsed_time": "3:45:24", "remaining_time": "5:57:50", "throughput": "0.00", "total_tokens": 0}
107
+ {"current_steps": 1050, "total_steps": 2691, "loss": 0.1617, "learning_rate": 7.650146530510542e-06, "epoch": 1.1705685618729098, "percentage": 39.02, "elapsed_time": "3:47:29", "remaining_time": "5:55:32", "throughput": "0.00", "total_tokens": 0}
108
+ {"current_steps": 1060, "total_steps": 2691, "loss": 0.1596, "learning_rate": 7.594906248422392e-06, "epoch": 1.1817168338907469, "percentage": 39.39, "elapsed_time": "3:49:33", "remaining_time": "5:53:12", "throughput": "0.00", "total_tokens": 0}
109
+ {"current_steps": 1070, "total_steps": 2691, "loss": 0.1603, "learning_rate": 7.539229022370418e-06, "epoch": 1.1928651059085842, "percentage": 39.76, "elapsed_time": "3:51:37", "remaining_time": "5:50:54", "throughput": "0.00", "total_tokens": 0}
110
+ {"current_steps": 1080, "total_steps": 2691, "loss": 0.1579, "learning_rate": 7.483124227578811e-06, "epoch": 1.2040133779264215, "percentage": 40.13, "elapsed_time": "3:53:46", "remaining_time": "5:48:43", "throughput": "0.00", "total_tokens": 0}
111
+ {"current_steps": 1090, "total_steps": 2691, "loss": 0.16, "learning_rate": 7.426601311268043e-06, "epoch": 1.2151616499442586, "percentage": 40.51, "elapsed_time": "3:55:57", "remaining_time": "5:46:34", "throughput": "0.00", "total_tokens": 0}
112
+ {"current_steps": 1100, "total_steps": 2691, "loss": 0.1596, "learning_rate": 7.369669791064085e-06, "epoch": 1.2263099219620959, "percentage": 40.88, "elapsed_time": "3:58:00", "remaining_time": "5:44:15", "throughput": "0.00", "total_tokens": 0}
113
+ {"current_steps": 1110, "total_steps": 2691, "loss": 0.1582, "learning_rate": 7.312339253395778e-06, "epoch": 1.2374581939799332, "percentage": 41.25, "elapsed_time": "4:00:34", "remaining_time": "5:42:39", "throughput": "0.00", "total_tokens": 0}
114
+ {"current_steps": 1120, "total_steps": 2691, "loss": 0.1581, "learning_rate": 7.254619351880625e-06, "epoch": 1.2486064659977703, "percentage": 41.62, "elapsed_time": "4:02:43", "remaining_time": "5:40:27", "throughput": "0.00", "total_tokens": 0}
115
+ {"current_steps": 1130, "total_steps": 2691, "loss": 0.1592, "learning_rate": 7.1965198056992615e-06, "epoch": 1.2597547380156076, "percentage": 41.99, "elapsed_time": "4:04:51", "remaining_time": "5:38:14", "throughput": "0.00", "total_tokens": 0}
116
+ {"current_steps": 1140, "total_steps": 2691, "loss": 0.1595, "learning_rate": 7.138050397958889e-06, "epoch": 1.2709030100334449, "percentage": 42.36, "elapsed_time": "4:06:54", "remaining_time": "5:35:56", "throughput": "0.00", "total_tokens": 0}
117
+ {"current_steps": 1150, "total_steps": 2691, "loss": 0.1584, "learning_rate": 7.079220974045941e-06, "epoch": 1.282051282051282, "percentage": 42.74, "elapsed_time": "4:08:55", "remaining_time": "5:33:33", "throughput": "0.00", "total_tokens": 0}
118
+ {"current_steps": 1160, "total_steps": 2691, "loss": 0.1584, "learning_rate": 7.0200414399682745e-06, "epoch": 1.2931995540691192, "percentage": 43.11, "elapsed_time": "4:11:00", "remaining_time": "5:31:17", "throughput": "0.00", "total_tokens": 0}
119
+ {"current_steps": 1170, "total_steps": 2691, "loss": 0.1576, "learning_rate": 6.96052176068713e-06, "epoch": 1.3043478260869565, "percentage": 43.48, "elapsed_time": "4:13:10", "remaining_time": "5:29:07", "throughput": "0.00", "total_tokens": 0}
120
+ {"current_steps": 1180, "total_steps": 2691, "loss": 0.1599, "learning_rate": 6.900671958439192e-06, "epoch": 1.3154960981047936, "percentage": 43.85, "elapsed_time": "4:15:19", "remaining_time": "5:26:56", "throughput": "0.00", "total_tokens": 0}
121
+ {"current_steps": 1190, "total_steps": 2691, "loss": 0.158, "learning_rate": 6.840502111048982e-06, "epoch": 1.326644370122631, "percentage": 44.22, "elapsed_time": "4:17:22", "remaining_time": "5:24:37", "throughput": "0.00", "total_tokens": 0}
122
+ {"current_steps": 1200, "total_steps": 2691, "loss": 0.1604, "learning_rate": 6.780022350231912e-06, "epoch": 1.3377926421404682, "percentage": 44.59, "elapsed_time": "4:19:30", "remaining_time": "5:22:26", "throughput": "0.00", "total_tokens": 0}
123
+ {"current_steps": 1210, "total_steps": 2691, "loss": 0.1576, "learning_rate": 6.719242859888243e-06, "epoch": 1.3489409141583055, "percentage": 44.96, "elapsed_time": "4:21:58", "remaining_time": "5:20:39", "throughput": "0.00", "total_tokens": 0}
124
+ {"current_steps": 1220, "total_steps": 2691, "loss": 0.1588, "learning_rate": 6.65817387438827e-06, "epoch": 1.3600891861761428, "percentage": 45.34, "elapsed_time": "4:24:15", "remaining_time": "5:18:37", "throughput": "0.00", "total_tokens": 0}
125
+ {"current_steps": 1230, "total_steps": 2691, "loss": 0.1581, "learning_rate": 6.596825676849006e-06, "epoch": 1.37123745819398, "percentage": 45.71, "elapsed_time": "4:26:13", "remaining_time": "5:16:13", "throughput": "0.00", "total_tokens": 0}
126
+ {"current_steps": 1240, "total_steps": 2691, "loss": 0.1588, "learning_rate": 6.535208597402658e-06, "epoch": 1.3823857302118172, "percentage": 46.08, "elapsed_time": "4:28:18", "remaining_time": "5:13:57", "throughput": "0.00", "total_tokens": 0}
127
+ {"current_steps": 1250, "total_steps": 2691, "loss": 0.1586, "learning_rate": 6.473333011457181e-06, "epoch": 1.3935340022296545, "percentage": 46.45, "elapsed_time": "4:30:23", "remaining_time": "5:11:42", "throughput": "0.00", "total_tokens": 0}
128
+ {"current_steps": 1260, "total_steps": 2691, "loss": 0.1594, "learning_rate": 6.411209337949214e-06, "epoch": 1.4046822742474916, "percentage": 46.82, "elapsed_time": "4:32:34", "remaining_time": "5:09:34", "throughput": "0.00", "total_tokens": 0}
129
+ {"current_steps": 1270, "total_steps": 2691, "loss": 0.159, "learning_rate": 6.348848037589683e-06, "epoch": 1.415830546265329, "percentage": 47.19, "elapsed_time": "4:34:35", "remaining_time": "5:07:14", "throughput": "0.00", "total_tokens": 0}
130
+ {"current_steps": 1280, "total_steps": 2691, "loss": 0.1589, "learning_rate": 6.286259611102376e-06, "epoch": 1.4269788182831662, "percentage": 47.57, "elapsed_time": "4:36:44", "remaining_time": "5:05:04", "throughput": "0.00", "total_tokens": 0}
131
+ {"current_steps": 1290, "total_steps": 2691, "loss": 0.1587, "learning_rate": 6.223454597455776e-06, "epoch": 1.4381270903010033, "percentage": 47.94, "elapsed_time": "4:38:58", "remaining_time": "5:02:58", "throughput": "0.00", "total_tokens": 0}
132
+ {"current_steps": 1300, "total_steps": 2691, "loss": 0.1595, "learning_rate": 6.160443572088443e-06, "epoch": 1.4492753623188406, "percentage": 48.31, "elapsed_time": "4:41:03", "remaining_time": "5:00:43", "throughput": "0.00", "total_tokens": 0}
133
+ {"current_steps": 1310, "total_steps": 2691, "loss": 0.1584, "learning_rate": 6.097237145128282e-06, "epoch": 1.4604236343366779, "percentage": 48.68, "elapsed_time": "4:43:33", "remaining_time": "4:58:55", "throughput": "0.00", "total_tokens": 0}
134
+ {"current_steps": 1320, "total_steps": 2691, "loss": 0.1554, "learning_rate": 6.0338459596059395e-06, "epoch": 1.471571906354515, "percentage": 49.05, "elapsed_time": "4:45:47", "remaining_time": "4:56:50", "throughput": "0.00", "total_tokens": 0}
135
+ {"current_steps": 1330, "total_steps": 2691, "loss": 0.1585, "learning_rate": 5.9702806896626855e-06, "epoch": 1.4827201783723523, "percentage": 49.42, "elapsed_time": "4:47:50", "remaining_time": "4:54:33", "throughput": "0.00", "total_tokens": 0}
136
+ {"current_steps": 1340, "total_steps": 2691, "loss": 0.159, "learning_rate": 5.90655203875304e-06, "epoch": 1.4938684503901896, "percentage": 49.8, "elapsed_time": "4:49:55", "remaining_time": "4:52:18", "throughput": "0.00", "total_tokens": 0}
137
+ {"current_steps": 1350, "total_steps": 2691, "loss": 0.1579, "learning_rate": 5.8426707378424675e-06, "epoch": 1.5050167224080266, "percentage": 50.17, "elapsed_time": "4:51:59", "remaining_time": "4:50:02", "throughput": "0.00", "total_tokens": 0}
138
+ {"current_steps": 1360, "total_steps": 2691, "loss": 0.1564, "learning_rate": 5.778647543600443e-06, "epoch": 1.516164994425864, "percentage": 50.54, "elapsed_time": "4:54:10", "remaining_time": "4:47:54", "throughput": "0.00", "total_tokens": 0}
139
+ {"current_steps": 1370, "total_steps": 2691, "loss": 0.1545, "learning_rate": 5.714493236589187e-06, "epoch": 1.5273132664437012, "percentage": 50.91, "elapsed_time": "4:56:15", "remaining_time": "4:45:40", "throughput": "0.00", "total_tokens": 0}
140
+ {"current_steps": 1380, "total_steps": 2691, "loss": 0.1552, "learning_rate": 5.650218619448379e-06, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "4:58:27", "remaining_time": "4:43:31", "throughput": "0.00", "total_tokens": 0}
141
+ {"current_steps": 1390, "total_steps": 2691, "loss": 0.1556, "learning_rate": 5.5858345150761515e-06, "epoch": 1.5496098104793758, "percentage": 51.65, "elapsed_time": "5:00:43", "remaining_time": "4:41:28", "throughput": "0.00", "total_tokens": 0}
142
+ {"current_steps": 1400, "total_steps": 2691, "loss": 0.1568, "learning_rate": 5.521351764806672e-06, "epoch": 1.560758082497213, "percentage": 52.03, "elapsed_time": "5:02:57", "remaining_time": "4:39:22", "throughput": "0.00", "total_tokens": 0}
143
+ {"current_steps": 1410, "total_steps": 2691, "loss": 0.158, "learning_rate": 5.456781226584621e-06, "epoch": 1.57190635451505, "percentage": 52.4, "elapsed_time": "5:05:35", "remaining_time": "4:37:38", "throughput": "0.00", "total_tokens": 0}
144
+ {"current_steps": 1420, "total_steps": 2691, "loss": 0.1602, "learning_rate": 5.392133773136877e-06, "epoch": 1.5830546265328875, "percentage": 52.77, "elapsed_time": "5:07:47", "remaining_time": "4:35:29", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 1430, "total_steps": 2691, "loss": 0.1571, "learning_rate": 5.327420290141712e-06, "epoch": 1.5942028985507246, "percentage": 53.14, "elapsed_time": "5:09:52", "remaining_time": "4:33:14", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 1440, "total_steps": 2691, "loss": 0.1567, "learning_rate": 5.262651674395799e-06, "epoch": 1.605351170568562, "percentage": 53.51, "elapsed_time": "5:11:56", "remaining_time": "4:30:59", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 1450, "total_steps": 2691, "loss": 0.1574, "learning_rate": 5.197838831979352e-06, "epoch": 1.6164994425863992, "percentage": 53.88, "elapsed_time": "5:14:01", "remaining_time": "4:28:45", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 1460, "total_steps": 2691, "loss": 0.1569, "learning_rate": 5.132992676419704e-06, "epoch": 1.6276477146042363, "percentage": 54.25, "elapsed_time": "5:16:06", "remaining_time": "4:26:31", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 1470, "total_steps": 2691, "loss": 0.157, "learning_rate": 5.068124126853633e-06, "epoch": 1.6387959866220736, "percentage": 54.63, "elapsed_time": "5:18:19", "remaining_time": "4:24:24", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 1480, "total_steps": 2691, "loss": 0.1569, "learning_rate": 5.0032441061887345e-06, "epoch": 1.649944258639911, "percentage": 55.0, "elapsed_time": "5:20:19", "remaining_time": "4:22:06", "throughput": "0.00", "total_tokens": 0}
151
+ {"current_steps": 1490, "total_steps": 2691, "loss": 0.1571, "learning_rate": 4.938363539264175e-06, "epoch": 1.661092530657748, "percentage": 55.37, "elapsed_time": "5:22:25", "remaining_time": "4:19:53", "throughput": "0.00", "total_tokens": 0}
152
+ {"current_steps": 1500, "total_steps": 2691, "loss": 0.1547, "learning_rate": 4.87349335101109e-06, "epoch": 1.6722408026755853, "percentage": 55.74, "elapsed_time": "5:24:34", "remaining_time": "4:17:42", "throughput": "0.00", "total_tokens": 0}
153
+ {"current_steps": 1500, "total_steps": 2691, "eval_loss": 0.19943761825561523, "epoch": 1.6722408026755853, "percentage": 55.74, "elapsed_time": "5:24:40", "remaining_time": "4:17:47", "throughput": "0.00", "total_tokens": 0}
154
+ {"current_steps": 1510, "total_steps": 2691, "loss": 0.1562, "learning_rate": 4.808644464613015e-06, "epoch": 1.6833890746934226, "percentage": 56.11, "elapsed_time": "5:27:13", "remaining_time": "4:15:55", "throughput": "0.00", "total_tokens": 0}
155
+ {"current_steps": 1520, "total_steps": 2691, "loss": 0.1547, "learning_rate": 4.743827799666555e-06, "epoch": 1.6945373467112597, "percentage": 56.48, "elapsed_time": "5:29:16", "remaining_time": "4:13:39", "throughput": "0.00", "total_tokens": 0}
156
+ {"current_steps": 1530, "total_steps": 2691, "loss": 0.1563, "learning_rate": 4.679054270342703e-06, "epoch": 1.705685618729097, "percentage": 56.86, "elapsed_time": "5:31:25", "remaining_time": "4:11:29", "throughput": "0.00", "total_tokens": 0}
157
+ {"current_steps": 1540, "total_steps": 2691, "loss": 0.1538, "learning_rate": 4.614334783549049e-06, "epoch": 1.7168338907469343, "percentage": 57.23, "elapsed_time": "5:33:38", "remaining_time": "4:09:22", "throughput": "0.00", "total_tokens": 0}
158
+ {"current_steps": 1550, "total_steps": 2691, "loss": 0.1571, "learning_rate": 4.549680237093215e-06, "epoch": 1.7279821627647713, "percentage": 57.6, "elapsed_time": "5:35:42", "remaining_time": "4:07:07", "throughput": "0.00", "total_tokens": 0}
159
+ {"current_steps": 1560, "total_steps": 2691, "loss": 0.1561, "learning_rate": 4.485101517847831e-06, "epoch": 1.7391304347826086, "percentage": 57.97, "elapsed_time": "5:37:43", "remaining_time": "4:04:51", "throughput": "0.00", "total_tokens": 0}
160
+ {"current_steps": 1570, "total_steps": 2691, "loss": 0.1555, "learning_rate": 4.420609499917337e-06, "epoch": 1.750278706800446, "percentage": 58.34, "elapsed_time": "5:39:46", "remaining_time": "4:02:36", "throughput": "0.00", "total_tokens": 0}
161
+ {"current_steps": 1580, "total_steps": 2691, "loss": 0.1545, "learning_rate": 4.3562150428069565e-06, "epoch": 1.761426978818283, "percentage": 58.71, "elapsed_time": "5:41:45", "remaining_time": "4:00:18", "throughput": "0.00", "total_tokens": 0}
162
+ {"current_steps": 1590, "total_steps": 2691, "loss": 0.1547, "learning_rate": 4.291928989594102e-06, "epoch": 1.7725752508361206, "percentage": 59.09, "elapsed_time": "5:43:51", "remaining_time": "3:58:06", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1600, "total_steps": 2691, "loss": 0.1548, "learning_rate": 4.2277621651025734e-06, "epoch": 1.7837235228539576, "percentage": 59.46, "elapsed_time": "5:45:59", "remaining_time": "3:55:55", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1610, "total_steps": 2691, "loss": 0.1559, "learning_rate": 4.163725374079808e-06, "epoch": 1.7948717948717947, "percentage": 59.83, "elapsed_time": "5:48:29", "remaining_time": "3:53:59", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1620, "total_steps": 2691, "loss": 0.1527, "learning_rate": 4.099829399377524e-06, "epoch": 1.8060200668896322, "percentage": 60.2, "elapsed_time": "5:50:32", "remaining_time": "3:51:45", "throughput": "0.00", "total_tokens": 0}
166
+ {"current_steps": 1630, "total_steps": 2691, "loss": 0.1562, "learning_rate": 4.036085000136046e-06, "epoch": 1.8171683389074693, "percentage": 60.57, "elapsed_time": "5:52:31", "remaining_time": "3:49:27", "throughput": "0.00", "total_tokens": 0}
167
+ {"current_steps": 1640, "total_steps": 2691, "loss": 0.1546, "learning_rate": 3.972502909972628e-06, "epoch": 1.8283166109253066, "percentage": 60.94, "elapsed_time": "5:54:44", "remaining_time": "3:47:20", "throughput": "0.00", "total_tokens": 0}
168
+ {"current_steps": 1650, "total_steps": 2691, "loss": 0.1547, "learning_rate": 3.909093835174066e-06, "epoch": 1.839464882943144, "percentage": 61.32, "elapsed_time": "5:56:56", "remaining_time": "3:45:12", "throughput": "0.00", "total_tokens": 0}
169
+ {"current_steps": 1660, "total_steps": 2691, "loss": 0.1546, "learning_rate": 3.845868452893919e-06, "epoch": 1.850613154960981, "percentage": 61.69, "elapsed_time": "5:59:09", "remaining_time": "3:43:03", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1670, "total_steps": 2691, "loss": 0.1526, "learning_rate": 3.7828374093546303e-06, "epoch": 1.8617614269788183, "percentage": 62.06, "elapsed_time": "6:01:20", "remaining_time": "3:40:55", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1680, "total_steps": 2691, "loss": 0.1542, "learning_rate": 3.720011318054871e-06, "epoch": 1.8729096989966556, "percentage": 62.43, "elapsed_time": "6:03:29", "remaining_time": "3:38:44", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1690, "total_steps": 2691, "loss": 0.1543, "learning_rate": 3.657400757982367e-06, "epoch": 1.8840579710144927, "percentage": 62.8, "elapsed_time": "6:05:32", "remaining_time": "3:36:30", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1700, "total_steps": 2691, "loss": 0.1531, "learning_rate": 3.595016271832572e-06, "epoch": 1.89520624303233, "percentage": 63.17, "elapsed_time": "6:07:37", "remaining_time": "3:34:18", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1710, "total_steps": 2691, "loss": 0.1541, "learning_rate": 3.532868364233416e-06, "epoch": 1.9063545150501673, "percentage": 63.55, "elapsed_time": "6:10:03", "remaining_time": "3:32:18", "throughput": "0.00", "total_tokens": 0}
175
+ {"current_steps": 1720, "total_steps": 2691, "loss": 0.1552, "learning_rate": 3.470967499976492e-06, "epoch": 1.9175027870680044, "percentage": 63.92, "elapsed_time": "6:12:15", "remaining_time": "3:30:08", "throughput": "0.00", "total_tokens": 0}
176
+ {"current_steps": 1730, "total_steps": 2691, "loss": 0.1521, "learning_rate": 3.4093241022549316e-06, "epoch": 1.9286510590858417, "percentage": 64.29, "elapsed_time": "6:14:29", "remaining_time": "3:28:01", "throughput": "0.00", "total_tokens": 0}
177
+ {"current_steps": 1740, "total_steps": 2691, "loss": 0.1536, "learning_rate": 3.347948550908303e-06, "epoch": 1.939799331103679, "percentage": 64.66, "elapsed_time": "6:16:35", "remaining_time": "3:25:49", "throughput": "0.00", "total_tokens": 0}
178
+ {"current_steps": 1750, "total_steps": 2691, "loss": 0.1524, "learning_rate": 3.286851180674788e-06, "epoch": 1.950947603121516, "percentage": 65.03, "elapsed_time": "6:18:42", "remaining_time": "3:23:38", "throughput": "0.00", "total_tokens": 0}
179
+ {"current_steps": 1760, "total_steps": 2691, "loss": 0.1527, "learning_rate": 3.2260422794509704e-06, "epoch": 1.9620958751393534, "percentage": 65.4, "elapsed_time": "6:20:56", "remaining_time": "3:21:30", "throughput": "0.00", "total_tokens": 0}
180
+ {"current_steps": 1770, "total_steps": 2691, "loss": 0.1523, "learning_rate": 3.165532086559504e-06, "epoch": 1.9732441471571907, "percentage": 65.77, "elapsed_time": "6:23:16", "remaining_time": "3:19:26", "throughput": "0.00", "total_tokens": 0}
181
+ {"current_steps": 1780, "total_steps": 2691, "loss": 0.1528, "learning_rate": 3.105330791024965e-06, "epoch": 1.9843924191750277, "percentage": 66.15, "elapsed_time": "6:25:19", "remaining_time": "3:17:12", "throughput": "0.00", "total_tokens": 0}
182
+ {"current_steps": 1790, "total_steps": 2691, "loss": 0.1523, "learning_rate": 3.045448529858165e-06, "epoch": 1.9955406911928653, "percentage": 66.52, "elapsed_time": "6:27:25", "remaining_time": "3:15:00", "throughput": "0.00", "total_tokens": 0}
183
+ {"current_steps": 1800, "total_steps": 2691, "loss": 0.1257, "learning_rate": 2.9858953863492334e-06, "epoch": 2.0066889632107023, "percentage": 66.89, "elapsed_time": "6:29:38", "remaining_time": "3:12:52", "throughput": "0.00", "total_tokens": 0}
184
+ {"current_steps": 1810, "total_steps": 2691, "loss": 0.111, "learning_rate": 2.9266813883697342e-06, "epoch": 2.0178372352285394, "percentage": 67.26, "elapsed_time": "6:32:13", "remaining_time": "3:10:54", "throughput": "0.00", "total_tokens": 0}
185
+ {"current_steps": 1820, "total_steps": 2691, "loss": 0.1125, "learning_rate": 2.867816506684126e-06, "epoch": 2.028985507246377, "percentage": 67.63, "elapsed_time": "6:34:21", "remaining_time": "3:08:43", "throughput": "0.00", "total_tokens": 0}
186
+ {"current_steps": 1830, "total_steps": 2691, "loss": 0.1113, "learning_rate": 2.809310653270825e-06, "epoch": 2.040133779264214, "percentage": 68.0, "elapsed_time": "6:36:24", "remaining_time": "3:06:30", "throughput": "0.00", "total_tokens": 0}
187
+ {"current_steps": 1840, "total_steps": 2691, "loss": 0.1101, "learning_rate": 2.751173679653184e-06, "epoch": 2.051282051282051, "percentage": 68.38, "elapsed_time": "6:38:31", "remaining_time": "3:04:19", "throughput": "0.00", "total_tokens": 0}
188
+ {"current_steps": 1850, "total_steps": 2691, "loss": 0.1099, "learning_rate": 2.693415375240629e-06, "epoch": 2.0624303232998886, "percentage": 68.75, "elapsed_time": "6:40:38", "remaining_time": "3:02:07", "throughput": "0.00", "total_tokens": 0}
189
+ {"current_steps": 1860, "total_steps": 2691, "loss": 0.1098, "learning_rate": 2.636045465680282e-06, "epoch": 2.0735785953177257, "percentage": 69.12, "elapsed_time": "6:42:38", "remaining_time": "2:59:53", "throughput": "0.00", "total_tokens": 0}
190
+ {"current_steps": 1870, "total_steps": 2691, "loss": 0.1094, "learning_rate": 2.5790736112192893e-06, "epoch": 2.084726867335563, "percentage": 69.49, "elapsed_time": "6:44:50", "remaining_time": "2:57:44", "throughput": "0.00", "total_tokens": 0}
191
+ {"current_steps": 1880, "total_steps": 2691, "loss": 0.1105, "learning_rate": 2.522509405078187e-06, "epoch": 2.0958751393534003, "percentage": 69.86, "elapsed_time": "6:46:58", "remaining_time": "2:55:33", "throughput": "0.00", "total_tokens": 0}
192
+ {"current_steps": 1890, "total_steps": 2691, "loss": 0.1102, "learning_rate": 2.4663623718355444e-06, "epoch": 2.1070234113712374, "percentage": 70.23, "elapsed_time": "6:49:07", "remaining_time": "2:53:23", "throughput": "0.00", "total_tokens": 0}
193
+ {"current_steps": 1900, "total_steps": 2691, "loss": 0.1089, "learning_rate": 2.410641965824166e-06, "epoch": 2.1181716833890745, "percentage": 70.61, "elapsed_time": "6:51:15", "remaining_time": "2:51:12", "throughput": "0.00", "total_tokens": 0}
194
+ {"current_steps": 1910, "total_steps": 2691, "loss": 0.1119, "learning_rate": 2.355357569539114e-06, "epoch": 2.129319955406912, "percentage": 70.98, "elapsed_time": "6:53:49", "remaining_time": "2:49:12", "throughput": "0.00", "total_tokens": 0}
195
+ {"current_steps": 1920, "total_steps": 2691, "loss": 0.114, "learning_rate": 2.300518492057842e-06, "epoch": 2.140468227424749, "percentage": 71.35, "elapsed_time": "6:55:59", "remaining_time": "2:47:02", "throughput": "0.00", "total_tokens": 0}
196
+ {"current_steps": 1930, "total_steps": 2691, "loss": 0.1102, "learning_rate": 2.2461339674726804e-06, "epoch": 2.1516164994425866, "percentage": 71.72, "elapsed_time": "6:58:03", "remaining_time": "2:44:50", "throughput": "0.00", "total_tokens": 0}
197
+ {"current_steps": 1940, "total_steps": 2691, "loss": 0.1109, "learning_rate": 2.192213153335953e-06, "epoch": 2.1627647714604237, "percentage": 72.09, "elapsed_time": "7:00:09", "remaining_time": "2:42:38", "throughput": "0.00", "total_tokens": 0}
198
+ {"current_steps": 1950, "total_steps": 2691, "loss": 0.1106, "learning_rate": 2.1387651291179775e-06, "epoch": 2.1739130434782608, "percentage": 72.46, "elapsed_time": "7:02:11", "remaining_time": "2:40:25", "throughput": "0.00", "total_tokens": 0}
199
+ {"current_steps": 1960, "total_steps": 2691, "loss": 0.1089, "learning_rate": 2.085798894678217e-06, "epoch": 2.1850613154960983, "percentage": 72.84, "elapsed_time": "7:04:23", "remaining_time": "2:38:16", "throughput": "0.00", "total_tokens": 0}
200
+ {"current_steps": 1970, "total_steps": 2691, "loss": 0.1094, "learning_rate": 2.0333233687498433e-06, "epoch": 2.1962095875139354, "percentage": 73.21, "elapsed_time": "7:06:30", "remaining_time": "2:36:05", "throughput": "0.00", "total_tokens": 0}
201
+ {"current_steps": 1980, "total_steps": 2691, "loss": 0.1105, "learning_rate": 1.98134738743794e-06, "epoch": 2.2073578595317724, "percentage": 73.58, "elapsed_time": "7:08:33", "remaining_time": "2:33:53", "throughput": "0.00", "total_tokens": 0}
202
+ {"current_steps": 1990, "total_steps": 2691, "loss": 0.1088, "learning_rate": 1.9298797027316474e-06, "epoch": 2.21850613154961, "percentage": 73.95, "elapsed_time": "7:10:29", "remaining_time": "2:31:38", "throughput": "0.00", "total_tokens": 0}
203
+ {"current_steps": 2000, "total_steps": 2691, "loss": 0.1092, "learning_rate": 1.878928981030445e-06, "epoch": 2.229654403567447, "percentage": 74.32, "elapsed_time": "7:12:28", "remaining_time": "2:29:25", "throughput": "0.00", "total_tokens": 0}
204
+ {"current_steps": 2000, "total_steps": 2691, "eval_loss": 0.20725835859775543, "epoch": 2.229654403567447, "percentage": 74.32, "elapsed_time": "7:12:33", "remaining_time": "2:29:27", "throughput": "0.00", "total_tokens": 0}
205
+ {"current_steps": 2010, "total_steps": 2691, "loss": 0.1098, "learning_rate": 1.828503801684864e-06, "epoch": 2.240802675585284, "percentage": 74.69, "elapsed_time": "7:15:00", "remaining_time": "2:27:22", "throughput": "0.00", "total_tokens": 0}
206
+ {"current_steps": 2020, "total_steps": 2691, "loss": 0.1093, "learning_rate": 1.7786126555518484e-06, "epoch": 2.2519509476031216, "percentage": 75.07, "elapsed_time": "7:17:11", "remaining_time": "2:25:13", "throughput": "0.00", "total_tokens": 0}
207
+ {"current_steps": 2030, "total_steps": 2691, "loss": 0.1088, "learning_rate": 1.729263943565022e-06, "epoch": 2.2630992196209587, "percentage": 75.44, "elapsed_time": "7:19:24", "remaining_time": "2:23:04", "throughput": "0.00", "total_tokens": 0}
208
+ {"current_steps": 2040, "total_steps": 2691, "loss": 0.1101, "learning_rate": 1.6804659753200925e-06, "epoch": 2.274247491638796, "percentage": 75.81, "elapsed_time": "7:21:24", "remaining_time": "2:20:51", "throughput": "0.00", "total_tokens": 0}
209
+ {"current_steps": 2050, "total_steps": 2691, "loss": 0.1096, "learning_rate": 1.6322269676756402e-06, "epoch": 2.2853957636566333, "percentage": 76.18, "elapsed_time": "7:23:28", "remaining_time": "2:18:40", "throughput": "0.00", "total_tokens": 0}
210
+ {"current_steps": 2060, "total_steps": 2691, "loss": 0.109, "learning_rate": 1.5845550433695172e-06, "epoch": 2.2965440356744704, "percentage": 76.55, "elapsed_time": "7:25:36", "remaining_time": "2:16:29", "throughput": "0.00", "total_tokens": 0}
211
+ {"current_steps": 2070, "total_steps": 2691, "loss": 0.1097, "learning_rate": 1.5374582296511054e-06, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "7:27:40", "remaining_time": "2:14:18", "throughput": "0.00", "total_tokens": 0}
212
+ {"current_steps": 2080, "total_steps": 2691, "loss": 0.1084, "learning_rate": 1.4909444569296334e-06, "epoch": 2.318840579710145, "percentage": 77.29, "elapsed_time": "7:29:37", "remaining_time": "2:12:04", "throughput": "0.00", "total_tokens": 0}
213
+ {"current_steps": 2090, "total_steps": 2691, "loss": 0.1094, "learning_rate": 1.4450215574388265e-06, "epoch": 2.329988851727982, "percentage": 77.67, "elapsed_time": "7:31:37", "remaining_time": "2:09:52", "throughput": "0.00", "total_tokens": 0}
214
+ {"current_steps": 2100, "total_steps": 2691, "loss": 0.1086, "learning_rate": 1.3996972639180645e-06, "epoch": 2.3411371237458196, "percentage": 78.04, "elapsed_time": "7:33:43", "remaining_time": "2:07:41", "throughput": "0.00", "total_tokens": 0}
215
+ {"current_steps": 2110, "total_steps": 2691, "loss": 0.1079, "learning_rate": 1.3549792083103037e-06, "epoch": 2.3522853957636567, "percentage": 78.41, "elapsed_time": "7:36:27", "remaining_time": "2:05:41", "throughput": "0.00", "total_tokens": 0}
216
+ {"current_steps": 2120, "total_steps": 2691, "loss": 0.1093, "learning_rate": 1.3108749204769732e-06, "epoch": 2.3634336677814938, "percentage": 78.78, "elapsed_time": "7:38:36", "remaining_time": "2:03:31", "throughput": "0.00", "total_tokens": 0}
217
+ {"current_steps": 2130, "total_steps": 2691, "loss": 0.109, "learning_rate": 1.2673918269300557e-06, "epoch": 2.374581939799331, "percentage": 79.15, "elapsed_time": "7:40:36", "remaining_time": "2:01:18", "throughput": "0.00", "total_tokens": 0}
218
+ {"current_steps": 2140, "total_steps": 2691, "loss": 0.1086, "learning_rate": 1.2245372495815726e-06, "epoch": 2.3857302118171684, "percentage": 79.52, "elapsed_time": "7:42:41", "remaining_time": "1:59:08", "throughput": "0.00", "total_tokens": 0}
219
+ {"current_steps": 2150, "total_steps": 2691, "loss": 0.1088, "learning_rate": 1.1823184045106816e-06, "epoch": 2.3968784838350055, "percentage": 79.9, "elapsed_time": "7:44:55", "remaining_time": "1:56:59", "throughput": "0.00", "total_tokens": 0}
220
+ {"current_steps": 2160, "total_steps": 2691, "loss": 0.1085, "learning_rate": 1.140742400748593e-06, "epoch": 2.408026755852843, "percentage": 80.27, "elapsed_time": "7:47:02", "remaining_time": "1:54:48", "throughput": "0.00", "total_tokens": 0}
221
+ {"current_steps": 2170, "total_steps": 2691, "loss": 0.1084, "learning_rate": 1.099816239081521e-06, "epoch": 2.41917502787068, "percentage": 80.64, "elapsed_time": "7:49:08", "remaining_time": "1:52:38", "throughput": "0.00", "total_tokens": 0}
222
+ {"current_steps": 2180, "total_steps": 2691, "loss": 0.1089, "learning_rate": 1.0595468108718448e-06, "epoch": 2.430323299888517, "percentage": 81.01, "elapsed_time": "7:51:17", "remaining_time": "1:50:28", "throughput": "0.00", "total_tokens": 0}
223
+ {"current_steps": 2190, "total_steps": 2691, "loss": 0.1087, "learning_rate": 1.0199408968977138e-06, "epoch": 2.4414715719063547, "percentage": 81.38, "elapsed_time": "7:53:19", "remaining_time": "1:48:16", "throughput": "0.00", "total_tokens": 0}
224
+ {"current_steps": 2200, "total_steps": 2691, "loss": 0.108, "learning_rate": 9.810051662112558e-07, "epoch": 2.4526198439241917, "percentage": 81.75, "elapsed_time": "7:55:21", "remaining_time": "1:46:05", "throughput": "0.00", "total_tokens": 0}
225
+ {"current_steps": 2210, "total_steps": 2691, "loss": 0.1096, "learning_rate": 9.427461750156142e-07, "epoch": 2.463768115942029, "percentage": 82.13, "elapsed_time": "7:57:54", "remaining_time": "1:44:00", "throughput": "0.00", "total_tokens": 0}
226
+ {"current_steps": 2220, "total_steps": 2691, "loss": 0.1089, "learning_rate": 9.051703655609762e-07, "epoch": 2.4749163879598663, "percentage": 82.5, "elapsed_time": "8:00:02", "remaining_time": "1:41:50", "throughput": "0.00", "total_tokens": 0}
227
+ {"current_steps": 2230, "total_steps": 2691, "loss": 0.1095, "learning_rate": 8.68284065059794e-07, "epoch": 2.4860646599777034, "percentage": 82.87, "elapsed_time": "8:02:13", "remaining_time": "1:39:41", "throughput": "0.00", "total_tokens": 0}
228
+ {"current_steps": 2240, "total_steps": 2691, "loss": 0.1082, "learning_rate": 8.320934846213746e-07, "epoch": 2.4972129319955405, "percentage": 83.24, "elapsed_time": "8:04:22", "remaining_time": "1:37:31", "throughput": "0.00", "total_tokens": 0}
229
+ {"current_steps": 2250, "total_steps": 2691, "loss": 0.1083, "learning_rate": 7.966047182060226e-07, "epoch": 2.508361204013378, "percentage": 83.61, "elapsed_time": "8:06:27", "remaining_time": "1:35:20", "throughput": "0.00", "total_tokens": 0}
230
+ {"current_steps": 2260, "total_steps": 2691, "loss": 0.1083, "learning_rate": 7.618237415989032e-07, "epoch": 2.519509476031215, "percentage": 83.98, "elapsed_time": "8:08:30", "remaining_time": "1:33:09", "throughput": "0.00", "total_tokens": 0}
231
+ {"current_steps": 2270, "total_steps": 2691, "loss": 0.1082, "learning_rate": 7.277564114038149e-07, "epoch": 2.5306577480490526, "percentage": 84.36, "elapsed_time": "8:10:26", "remaining_time": "1:30:57", "throughput": "0.00", "total_tokens": 0}
232
+ {"current_steps": 2280, "total_steps": 2691, "loss": 0.1072, "learning_rate": 6.944084640570142e-07, "epoch": 2.5418060200668897, "percentage": 84.73, "elapsed_time": "8:12:40", "remaining_time": "1:28:48", "throughput": "0.00", "total_tokens": 0}
233
+ {"current_steps": 2290, "total_steps": 2691, "loss": 0.1071, "learning_rate": 6.617855148612945e-07, "epoch": 2.552954292084727, "percentage": 85.1, "elapsed_time": "8:14:58", "remaining_time": "1:26:40", "throughput": "0.00", "total_tokens": 0}
234
+ {"current_steps": 2300, "total_steps": 2691, "loss": 0.1087, "learning_rate": 6.298930570404432e-07, "epoch": 2.564102564102564, "percentage": 85.47, "elapsed_time": "8:17:00", "remaining_time": "1:24:29", "throughput": "0.00", "total_tokens": 0}
235
+ {"current_steps": 2310, "total_steps": 2691, "loss": 0.1076, "learning_rate": 5.987364608142693e-07, "epoch": 2.5752508361204014, "percentage": 85.84, "elapsed_time": "8:19:34", "remaining_time": "1:22:23", "throughput": "0.00", "total_tokens": 0}
236
+ {"current_steps": 2320, "total_steps": 2691, "loss": 0.109, "learning_rate": 5.683209724943344e-07, "epoch": 2.5863991081382385, "percentage": 86.21, "elapsed_time": "8:21:39", "remaining_time": "1:20:13", "throughput": "0.00", "total_tokens": 0}
237
+ {"current_steps": 2330, "total_steps": 2691, "loss": 0.1081, "learning_rate": 5.386517136005543e-07, "epoch": 2.597547380156076, "percentage": 86.58, "elapsed_time": "8:23:38", "remaining_time": "1:18:01", "throughput": "0.00", "total_tokens": 0}
238
+ {"current_steps": 2340, "total_steps": 2691, "loss": 0.1079, "learning_rate": 5.097336799988067e-07, "epoch": 2.608695652173913, "percentage": 86.96, "elapsed_time": "8:25:47", "remaining_time": "1:15:52", "throughput": "0.00", "total_tokens": 0}
239
+ {"current_steps": 2350, "total_steps": 2691, "loss": 0.1081, "learning_rate": 4.815717410597042e-07, "epoch": 2.61984392419175, "percentage": 87.33, "elapsed_time": "8:27:59", "remaining_time": "1:13:42", "throughput": "0.00", "total_tokens": 0}
240
+ {"current_steps": 2360, "total_steps": 2691, "loss": 0.1086, "learning_rate": 4.541706388386624e-07, "epoch": 2.6309921962095872, "percentage": 87.7, "elapsed_time": "8:30:19", "remaining_time": "1:11:34", "throughput": "0.00", "total_tokens": 0}
241
+ {"current_steps": 2370, "total_steps": 2691, "loss": 0.1073, "learning_rate": 4.275349872774098e-07, "epoch": 2.6421404682274248, "percentage": 88.07, "elapsed_time": "8:32:30", "remaining_time": "1:09:24", "throughput": "0.00", "total_tokens": 0}
242
+ {"current_steps": 2380, "total_steps": 2691, "loss": 0.1076, "learning_rate": 4.0166927142706313e-07, "epoch": 2.653288740245262, "percentage": 88.44, "elapsed_time": "8:34:38", "remaining_time": "1:07:14", "throughput": "0.00", "total_tokens": 0}
243
+ {"current_steps": 2390, "total_steps": 2691, "loss": 0.1066, "learning_rate": 3.765778466929182e-07, "epoch": 2.6644370122630994, "percentage": 88.81, "elapsed_time": "8:36:50", "remaining_time": "1:05:05", "throughput": "0.00", "total_tokens": 0}
244
+ {"current_steps": 2400, "total_steps": 2691, "loss": 0.1081, "learning_rate": 3.5226493810105624e-07, "epoch": 2.6755852842809364, "percentage": 89.19, "elapsed_time": "8:39:04", "remaining_time": "1:02:56", "throughput": "0.00", "total_tokens": 0}
245
+ {"current_steps": 2410, "total_steps": 2691, "loss": 0.108, "learning_rate": 3.2873463958691675e-07, "epoch": 2.6867335562987735, "percentage": 89.56, "elapsed_time": "8:41:33", "remaining_time": "1:00:48", "throughput": "0.00", "total_tokens": 0}
246
+ {"current_steps": 2420, "total_steps": 2691, "loss": 0.1077, "learning_rate": 3.05990913305938e-07, "epoch": 2.697881828316611, "percentage": 89.93, "elapsed_time": "8:43:41", "remaining_time": "0:58:38", "throughput": "0.00", "total_tokens": 0}
247
+ {"current_steps": 2430, "total_steps": 2691, "loss": 0.106, "learning_rate": 2.840375889663871e-07, "epoch": 2.709030100334448, "percentage": 90.3, "elapsed_time": "8:45:46", "remaining_time": "0:56:28", "throughput": "0.00", "total_tokens": 0}
248
+ {"current_steps": 2440, "total_steps": 2691, "loss": 0.107, "learning_rate": 2.62878363184495e-07, "epoch": 2.7201783723522857, "percentage": 90.67, "elapsed_time": "8:47:55", "remaining_time": "0:54:18", "throughput": "0.00", "total_tokens": 0}
249
+ {"current_steps": 2450, "total_steps": 2691, "loss": 0.1078, "learning_rate": 2.425167988620014e-07, "epoch": 2.7313266443701227, "percentage": 91.04, "elapsed_time": "8:50:04", "remaining_time": "0:52:08", "throughput": "0.00", "total_tokens": 0}
250
+ {"current_steps": 2460, "total_steps": 2691, "loss": 0.1076, "learning_rate": 2.2295632458621097e-07, "epoch": 2.74247491638796, "percentage": 91.42, "elapsed_time": "8:52:08", "remaining_time": "0:49:58", "throughput": "0.00", "total_tokens": 0}
251
+ {"current_steps": 2470, "total_steps": 2691, "loss": 0.1076, "learning_rate": 2.0420023405267663e-07, "epoch": 2.753623188405797, "percentage": 91.79, "elapsed_time": "8:54:15", "remaining_time": "0:47:48", "throughput": "0.00", "total_tokens": 0}
252
+ {"current_steps": 2480, "total_steps": 2691, "loss": 0.1071, "learning_rate": 1.8625168551058115e-07, "epoch": 2.7647714604236344, "percentage": 92.16, "elapsed_time": "8:56:28", "remaining_time": "0:45:38", "throughput": "0.00", "total_tokens": 0}
253
+ {"current_steps": 2490, "total_steps": 2691, "loss": 0.1081, "learning_rate": 1.6911370123094238e-07, "epoch": 2.7759197324414715, "percentage": 92.53, "elapsed_time": "8:58:31", "remaining_time": "0:43:28", "throughput": "0.00", "total_tokens": 0}
254
+ {"current_steps": 2500, "total_steps": 2691, "loss": 0.1073, "learning_rate": 1.5278916699770163e-07, "epoch": 2.787068004459309, "percentage": 92.9, "elapsed_time": "9:00:45", "remaining_time": "0:41:18", "throughput": "0.00", "total_tokens": 0}
255
+ {"current_steps": 2500, "total_steps": 2691, "eval_loss": 0.20636913180351257, "epoch": 2.787068004459309, "percentage": 92.9, "elapsed_time": "9:00:51", "remaining_time": "0:41:19", "throughput": "0.00", "total_tokens": 0}
256
+ {"current_steps": 2510, "total_steps": 2691, "loss": 0.1075, "learning_rate": 1.3728083162180384e-07, "epoch": 2.798216276477146, "percentage": 93.27, "elapsed_time": "9:03:27", "remaining_time": "0:39:11", "throughput": "0.00", "total_tokens": 0}
257
+ {"current_steps": 2520, "total_steps": 2691, "loss": 0.1065, "learning_rate": 1.2259130647833627e-07, "epoch": 2.809364548494983, "percentage": 93.65, "elapsed_time": "9:05:33", "remaining_time": "0:37:01", "throughput": "0.00", "total_tokens": 0}
258
+ {"current_steps": 2530, "total_steps": 2691, "loss": 0.1079, "learning_rate": 1.0872306506681251e-07, "epoch": 2.8205128205128203, "percentage": 94.02, "elapsed_time": "9:07:42", "remaining_time": "0:34:51", "throughput": "0.00", "total_tokens": 0}
259
+ {"current_steps": 2540, "total_steps": 2691, "loss": 0.1083, "learning_rate": 9.567844259467051e-08, "epoch": 2.831661092530658, "percentage": 94.39, "elapsed_time": "9:09:48", "remaining_time": "0:32:41", "throughput": "0.00", "total_tokens": 0}
260
+ {"current_steps": 2550, "total_steps": 2691, "loss": 0.1079, "learning_rate": 8.345963558406001e-08, "epoch": 2.842809364548495, "percentage": 94.76, "elapsed_time": "9:12:00", "remaining_time": "0:30:31", "throughput": "0.00", "total_tokens": 0}
261
+ {"current_steps": 2560, "total_steps": 2691, "loss": 0.107, "learning_rate": 7.206870150197831e-08, "epoch": 2.8539576365663324, "percentage": 95.13, "elapsed_time": "9:14:02", "remaining_time": "0:28:21", "throughput": "0.00", "total_tokens": 0}
262
+ {"current_steps": 2570, "total_steps": 2691, "loss": 0.1067, "learning_rate": 6.150755841382527e-08, "epoch": 2.8651059085841695, "percentage": 95.5, "elapsed_time": "9:16:09", "remaining_time": "0:26:11", "throughput": "0.00", "total_tokens": 0}
263
+ {"current_steps": 2580, "total_steps": 2691, "loss": 0.1078, "learning_rate": 5.177798466042716e-08, "epoch": 2.8762541806020065, "percentage": 95.88, "elapsed_time": "9:18:13", "remaining_time": "0:24:01", "throughput": "0.00", "total_tokens": 0}
264
+ {"current_steps": 2590, "total_steps": 2691, "loss": 0.109, "learning_rate": 4.2881618558592855e-08, "epoch": 2.887402452619844, "percentage": 96.25, "elapsed_time": "9:20:23", "remaining_time": "0:21:51", "throughput": "0.00", "total_tokens": 0}
265
+ {"current_steps": 2600, "total_steps": 2691, "loss": 0.1064, "learning_rate": 3.481995812524286e-08, "epoch": 2.898550724637681, "percentage": 96.62, "elapsed_time": "9:22:27", "remaining_time": "0:19:41", "throughput": "0.00", "total_tokens": 0}
266
+ {"current_steps": 2610, "total_steps": 2691, "loss": 0.107, "learning_rate": 2.7594360825166644e-08, "epoch": 2.9096989966555182, "percentage": 96.99, "elapsed_time": "9:24:59", "remaining_time": "0:17:32", "throughput": "0.00", "total_tokens": 0}
267
+ {"current_steps": 2620, "total_steps": 2691, "loss": 0.1067, "learning_rate": 2.120604334244547e-08, "epoch": 2.9208472686733558, "percentage": 97.36, "elapsed_time": "9:27:09", "remaining_time": "0:15:22", "throughput": "0.00", "total_tokens": 0}
268
+ {"current_steps": 2630, "total_steps": 2691, "loss": 0.1063, "learning_rate": 1.565608137558128e-08, "epoch": 2.931995540691193, "percentage": 97.73, "elapsed_time": "9:29:16", "remaining_time": "0:13:12", "throughput": "0.00", "total_tokens": 0}
269
+ {"current_steps": 2640, "total_steps": 2691, "loss": 0.1075, "learning_rate": 1.0945409456364353e-08, "epoch": 2.94314381270903, "percentage": 98.1, "elapsed_time": "9:31:17", "remaining_time": "0:11:02", "throughput": "0.00", "total_tokens": 0}
270
+ {"current_steps": 2650, "total_steps": 2691, "loss": 0.1075, "learning_rate": 7.0748207925103176e-09, "epoch": 2.9542920847268674, "percentage": 98.48, "elapsed_time": "9:33:26", "remaining_time": "0:08:52", "throughput": "0.00", "total_tokens": 0}
271
+ {"current_steps": 2660, "total_steps": 2691, "loss": 0.1079, "learning_rate": 4.044967134099187e-09, "epoch": 2.9654403567447045, "percentage": 98.85, "elapsed_time": "9:35:38", "remaining_time": "0:06:42", "throughput": "0.00", "total_tokens": 0}
272
+ {"current_steps": 2670, "total_steps": 2691, "loss": 0.1064, "learning_rate": 1.8563586638281617e-09, "epoch": 2.976588628762542, "percentage": 99.22, "elapsed_time": "9:37:46", "remaining_time": "0:04:32", "throughput": "0.00", "total_tokens": 0}
273
+ {"current_steps": 2680, "total_steps": 2691, "loss": 0.1071, "learning_rate": 5.093639111025673e-10, "epoch": 2.987736900780379, "percentage": 99.59, "elapsed_time": "9:39:55", "remaining_time": "0:02:22", "throughput": "0.00", "total_tokens": 0}
274
+ {"current_steps": 2690, "total_steps": 2691, "loss": 0.1079, "learning_rate": 4.2096899854904285e-12, "epoch": 2.998885172798216, "percentage": 99.96, "elapsed_time": "9:42:00", "remaining_time": "0:00:12", "throughput": "0.00", "total_tokens": 0}
275
+ {"current_steps": 2691, "total_steps": 2691, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "9:42:37", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
trainer_state.json ADDED
@@ -0,0 +1,1970 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2691,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.011148272017837236,
13
+ "grad_norm": 3.7741404834185763,
14
+ "learning_rate": 3.7037037037037036e-07,
15
+ "loss": 0.3679,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.022296544035674472,
20
+ "grad_norm": 1.8040349271595875,
21
+ "learning_rate": 7.407407407407407e-07,
22
+ "loss": 0.3385,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.033444816053511704,
27
+ "grad_norm": 1.1311364667628296,
28
+ "learning_rate": 1.111111111111111e-06,
29
+ "loss": 0.3008,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.044593088071348944,
34
+ "grad_norm": 1.096280133534896,
35
+ "learning_rate": 1.4814814814814815e-06,
36
+ "loss": 0.2689,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.055741360089186176,
41
+ "grad_norm": 0.7223895222097435,
42
+ "learning_rate": 1.8518518518518519e-06,
43
+ "loss": 0.2506,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.06688963210702341,
48
+ "grad_norm": 0.6507379554846837,
49
+ "learning_rate": 2.222222222222222e-06,
50
+ "loss": 0.24,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.07803790412486064,
55
+ "grad_norm": 0.5228577418159993,
56
+ "learning_rate": 2.5925925925925925e-06,
57
+ "loss": 0.2374,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.08918617614269789,
62
+ "grad_norm": 0.5725671090349675,
63
+ "learning_rate": 2.962962962962963e-06,
64
+ "loss": 0.2343,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.10033444816053512,
69
+ "grad_norm": 0.575895692421762,
70
+ "learning_rate": 3.3333333333333333e-06,
71
+ "loss": 0.2279,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.11148272017837235,
76
+ "grad_norm": 0.5723674270595959,
77
+ "learning_rate": 3.7037037037037037e-06,
78
+ "loss": 0.2263,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.12263099219620958,
83
+ "grad_norm": 0.6264644346158856,
84
+ "learning_rate": 4.074074074074074e-06,
85
+ "loss": 0.2239,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.13377926421404682,
90
+ "grad_norm": 0.7124762074512575,
91
+ "learning_rate": 4.444444444444444e-06,
92
+ "loss": 0.2232,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.14492753623188406,
97
+ "grad_norm": 0.5878673377883962,
98
+ "learning_rate": 4.814814814814815e-06,
99
+ "loss": 0.2231,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.15607580824972128,
104
+ "grad_norm": 0.821524645221957,
105
+ "learning_rate": 5.185185185185185e-06,
106
+ "loss": 0.2215,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.16722408026755853,
111
+ "grad_norm": 0.6626631852309735,
112
+ "learning_rate": 5.555555555555557e-06,
113
+ "loss": 0.2203,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.17837235228539577,
118
+ "grad_norm": 0.7549263527576757,
119
+ "learning_rate": 5.925925925925926e-06,
120
+ "loss": 0.2186,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.189520624303233,
125
+ "grad_norm": 0.695178742046847,
126
+ "learning_rate": 6.296296296296297e-06,
127
+ "loss": 0.2184,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.20066889632107024,
132
+ "grad_norm": 0.7460261830067356,
133
+ "learning_rate": 6.666666666666667e-06,
134
+ "loss": 0.22,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.21181716833890746,
139
+ "grad_norm": 0.7489258972164311,
140
+ "learning_rate": 7.0370370370370375e-06,
141
+ "loss": 0.2181,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2229654403567447,
146
+ "grad_norm": 0.7563607766637321,
147
+ "learning_rate": 7.4074074074074075e-06,
148
+ "loss": 0.221,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.23411371237458195,
153
+ "grad_norm": 0.6786891318993898,
154
+ "learning_rate": 7.77777777777778e-06,
155
+ "loss": 0.2188,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.24526198439241917,
160
+ "grad_norm": 0.718723752297412,
161
+ "learning_rate": 8.148148148148148e-06,
162
+ "loss": 0.2191,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.2564102564102564,
167
+ "grad_norm": 0.79515342774086,
168
+ "learning_rate": 8.518518518518519e-06,
169
+ "loss": 0.222,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.26755852842809363,
174
+ "grad_norm": 0.6773955348554602,
175
+ "learning_rate": 8.888888888888888e-06,
176
+ "loss": 0.2189,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.2787068004459309,
181
+ "grad_norm": 0.6019195042882624,
182
+ "learning_rate": 9.25925925925926e-06,
183
+ "loss": 0.2177,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.2898550724637681,
188
+ "grad_norm": 0.6564030437537817,
189
+ "learning_rate": 9.62962962962963e-06,
190
+ "loss": 0.2202,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3010033444816054,
195
+ "grad_norm": 0.6392190084647338,
196
+ "learning_rate": 1e-05,
197
+ "loss": 0.217,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.31215161649944256,
202
+ "grad_norm": 0.6409199129954214,
203
+ "learning_rate": 9.999579036849509e-06,
204
+ "loss": 0.2184,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.3232998885172798,
209
+ "grad_norm": 0.6213419108722281,
210
+ "learning_rate": 9.998316218282025e-06,
211
+ "loss": 0.2165,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.33444816053511706,
216
+ "grad_norm": 0.6837626955419673,
217
+ "learning_rate": 9.996211756937579e-06,
218
+ "loss": 0.2153,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.3455964325529543,
223
+ "grad_norm": 0.6153911123312514,
224
+ "learning_rate": 9.993266007176446e-06,
225
+ "loss": 0.2183,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.35674470457079155,
230
+ "grad_norm": 0.6491533849083898,
231
+ "learning_rate": 9.989479465019462e-06,
232
+ "loss": 0.2168,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.36789297658862874,
237
+ "grad_norm": 0.6331404269468602,
238
+ "learning_rate": 9.984852768064516e-06,
239
+ "loss": 0.2164,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.379041248606466,
244
+ "grad_norm": 0.6066866794436855,
245
+ "learning_rate": 9.979386695379179e-06,
246
+ "loss": 0.2157,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.39018952062430323,
251
+ "grad_norm": 0.6283882559447943,
252
+ "learning_rate": 9.973082167369521e-06,
253
+ "loss": 0.2144,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.4013377926421405,
258
+ "grad_norm": 0.620915432947406,
259
+ "learning_rate": 9.965940245625131e-06,
260
+ "loss": 0.2109,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.4124860646599777,
265
+ "grad_norm": 0.5581175223325301,
266
+ "learning_rate": 9.95796213274036e-06,
267
+ "loss": 0.2159,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.4236343366778149,
272
+ "grad_norm": 0.7003333387574542,
273
+ "learning_rate": 9.949149172111825e-06,
274
+ "loss": 0.2154,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.43478260869565216,
279
+ "grad_norm": 0.6965889831011358,
280
+ "learning_rate": 9.93950284771219e-06,
281
+ "loss": 0.215,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.4459308807134894,
286
+ "grad_norm": 0.6783561953012276,
287
+ "learning_rate": 9.929024783840302e-06,
288
+ "loss": 0.2156,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.45707915273132665,
293
+ "grad_norm": 0.6133815858556971,
294
+ "learning_rate": 9.917716744847674e-06,
295
+ "loss": 0.2135,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.4682274247491639,
300
+ "grad_norm": 0.5517297679124203,
301
+ "learning_rate": 9.905580634841388e-06,
302
+ "loss": 0.2127,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.4793756967670011,
307
+ "grad_norm": 0.5672097715363509,
308
+ "learning_rate": 9.892618497363491e-06,
309
+ "loss": 0.2152,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.49052396878483834,
314
+ "grad_norm": 0.7373862211696988,
315
+ "learning_rate": 9.878832515046873e-06,
316
+ "loss": 0.2121,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.5016722408026756,
321
+ "grad_norm": 0.5683396526691493,
322
+ "learning_rate": 9.864225009247753e-06,
323
+ "loss": 0.2124,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.5128205128205128,
328
+ "grad_norm": 0.5991852837643047,
329
+ "learning_rate": 9.848798439654797e-06,
330
+ "loss": 0.2116,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.5239687848383501,
335
+ "grad_norm": 0.5945184596013314,
336
+ "learning_rate": 9.832555403874937e-06,
337
+ "loss": 0.2107,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.5351170568561873,
342
+ "grad_norm": 0.5308451359275891,
343
+ "learning_rate": 9.815498636995982e-06,
344
+ "loss": 0.2092,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.5462653288740246,
349
+ "grad_norm": 0.5709398866928973,
350
+ "learning_rate": 9.797631011126061e-06,
351
+ "loss": 0.2098,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.5574136008918618,
356
+ "grad_norm": 0.570042268652287,
357
+ "learning_rate": 9.778955534910004e-06,
358
+ "loss": 0.2107,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.5574136008918618,
363
+ "eval_accuracy": 0.9207988997610126,
364
+ "eval_loss": 0.21421977877616882,
365
+ "eval_runtime": 5.3128,
366
+ "eval_samples_per_second": 43.292,
367
+ "eval_steps_per_second": 1.506,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 0.568561872909699,
372
+ "grad_norm": 0.6073438181861355,
373
+ "learning_rate": 9.759475353022735e-06,
374
+ "loss": 0.2096,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 0.5797101449275363,
379
+ "grad_norm": 0.5805559872103752,
380
+ "learning_rate": 9.739193745639745e-06,
381
+ "loss": 0.2088,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 0.5908584169453734,
386
+ "grad_norm": 0.569674689944485,
387
+ "learning_rate": 9.718114127884774e-06,
388
+ "loss": 0.2079,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 0.6020066889632107,
393
+ "grad_norm": 0.6479348013496814,
394
+ "learning_rate": 9.696240049254744e-06,
395
+ "loss": 0.2095,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 0.6131549609810479,
400
+ "grad_norm": 0.6837993590888451,
401
+ "learning_rate": 9.673575193022073e-06,
402
+ "loss": 0.2103,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 0.6243032329988851,
407
+ "grad_norm": 0.5658586658235949,
408
+ "learning_rate": 9.650123375614477e-06,
409
+ "loss": 0.209,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 0.6354515050167224,
414
+ "grad_norm": 0.525804021378744,
415
+ "learning_rate": 9.625888545972333e-06,
416
+ "loss": 0.2109,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 0.6465997770345596,
421
+ "grad_norm": 0.5027074127285335,
422
+ "learning_rate": 9.600874784883736e-06,
423
+ "loss": 0.2072,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 0.6577480490523969,
428
+ "grad_norm": 0.5503527245541562,
429
+ "learning_rate": 9.575086304297351e-06,
430
+ "loss": 0.2068,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 0.6688963210702341,
435
+ "grad_norm": 0.5786235649699455,
436
+ "learning_rate": 9.548527446613198e-06,
437
+ "loss": 0.2088,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 0.6800445930880713,
442
+ "grad_norm": 0.5963491322528846,
443
+ "learning_rate": 9.521202683951436e-06,
444
+ "loss": 0.2079,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 0.6911928651059086,
449
+ "grad_norm": 0.5483351877002366,
450
+ "learning_rate": 9.493116617399333e-06,
451
+ "loss": 0.2086,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 0.7023411371237458,
456
+ "grad_norm": 0.5231384119737766,
457
+ "learning_rate": 9.464273976236518e-06,
458
+ "loss": 0.2079,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 0.7134894091415831,
463
+ "grad_norm": 0.5728914844384684,
464
+ "learning_rate": 9.434679617138624e-06,
465
+ "loss": 0.207,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 0.7246376811594203,
470
+ "grad_norm": 0.6056684783613336,
471
+ "learning_rate": 9.404338523359511e-06,
472
+ "loss": 0.2072,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 0.7357859531772575,
477
+ "grad_norm": 0.48483746742809725,
478
+ "learning_rate": 9.373255803892149e-06,
479
+ "loss": 0.2043,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 0.7469342251950948,
484
+ "grad_norm": 0.5052853090283119,
485
+ "learning_rate": 9.341436692608341e-06,
486
+ "loss": 0.2059,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 0.758082497212932,
491
+ "grad_norm": 0.5013961896834831,
492
+ "learning_rate": 9.30888654737742e-06,
493
+ "loss": 0.2045,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 0.7692307692307693,
498
+ "grad_norm": 0.6136168534682885,
499
+ "learning_rate": 9.275610849164066e-06,
500
+ "loss": 0.2037,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 0.7803790412486065,
505
+ "grad_norm": 0.5454932461837725,
506
+ "learning_rate": 9.241615201105372e-06,
507
+ "loss": 0.2055,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 0.7915273132664437,
512
+ "grad_norm": 0.630054882059704,
513
+ "learning_rate": 9.206905327567385e-06,
514
+ "loss": 0.2084,
515
+ "step": 710
516
+ },
517
+ {
518
+ "epoch": 0.802675585284281,
519
+ "grad_norm": 0.5115790207210278,
520
+ "learning_rate": 9.171487073181198e-06,
521
+ "loss": 0.2054,
522
+ "step": 720
523
+ },
524
+ {
525
+ "epoch": 0.8138238573021181,
526
+ "grad_norm": 0.522185957547097,
527
+ "learning_rate": 9.135366401858782e-06,
528
+ "loss": 0.2073,
529
+ "step": 730
530
+ },
531
+ {
532
+ "epoch": 0.8249721293199554,
533
+ "grad_norm": 0.5370558619096407,
534
+ "learning_rate": 9.098549395788784e-06,
535
+ "loss": 0.2073,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 0.8361204013377926,
540
+ "grad_norm": 0.5143052735973912,
541
+ "learning_rate": 9.061042254412346e-06,
542
+ "loss": 0.2039,
543
+ "step": 750
544
+ },
545
+ {
546
+ "epoch": 0.8472686733556298,
547
+ "grad_norm": 0.5271311850347303,
548
+ "learning_rate": 9.022851293379232e-06,
549
+ "loss": 0.2053,
550
+ "step": 760
551
+ },
552
+ {
553
+ "epoch": 0.8584169453734671,
554
+ "grad_norm": 0.54232371019945,
555
+ "learning_rate": 8.983982943484348e-06,
556
+ "loss": 0.2023,
557
+ "step": 770
558
+ },
559
+ {
560
+ "epoch": 0.8695652173913043,
561
+ "grad_norm": 0.5365286519965239,
562
+ "learning_rate": 8.944443749584908e-06,
563
+ "loss": 0.2043,
564
+ "step": 780
565
+ },
566
+ {
567
+ "epoch": 0.8807134894091416,
568
+ "grad_norm": 0.49203900940366796,
569
+ "learning_rate": 8.904240369498363e-06,
570
+ "loss": 0.2013,
571
+ "step": 790
572
+ },
573
+ {
574
+ "epoch": 0.8918617614269788,
575
+ "grad_norm": 0.6067905351468151,
576
+ "learning_rate": 8.863379572881328e-06,
577
+ "loss": 0.2038,
578
+ "step": 800
579
+ },
580
+ {
581
+ "epoch": 0.903010033444816,
582
+ "grad_norm": 0.5687299547717642,
583
+ "learning_rate": 8.821868240089676e-06,
584
+ "loss": 0.2044,
585
+ "step": 810
586
+ },
587
+ {
588
+ "epoch": 0.9141583054626533,
589
+ "grad_norm": 0.5124900416142478,
590
+ "learning_rate": 8.779713361019983e-06,
591
+ "loss": 0.2068,
592
+ "step": 820
593
+ },
594
+ {
595
+ "epoch": 0.9253065774804905,
596
+ "grad_norm": 0.48310445826631493,
597
+ "learning_rate": 8.736922033932522e-06,
598
+ "loss": 0.2022,
599
+ "step": 830
600
+ },
601
+ {
602
+ "epoch": 0.9364548494983278,
603
+ "grad_norm": 0.5272157184999492,
604
+ "learning_rate": 8.693501464256046e-06,
605
+ "loss": 0.2027,
606
+ "step": 840
607
+ },
608
+ {
609
+ "epoch": 0.947603121516165,
610
+ "grad_norm": 0.5270482869515378,
611
+ "learning_rate": 8.649458963374474e-06,
612
+ "loss": 0.2032,
613
+ "step": 850
614
+ },
615
+ {
616
+ "epoch": 0.9587513935340022,
617
+ "grad_norm": 0.5738980238907102,
618
+ "learning_rate": 8.604801947395776e-06,
619
+ "loss": 0.2,
620
+ "step": 860
621
+ },
622
+ {
623
+ "epoch": 0.9698996655518395,
624
+ "grad_norm": 0.4603491880478103,
625
+ "learning_rate": 8.55953793590321e-06,
626
+ "loss": 0.2021,
627
+ "step": 870
628
+ },
629
+ {
630
+ "epoch": 0.9810479375696767,
631
+ "grad_norm": 0.548549890115731,
632
+ "learning_rate": 8.513674550689128e-06,
633
+ "loss": 0.2002,
634
+ "step": 880
635
+ },
636
+ {
637
+ "epoch": 0.992196209587514,
638
+ "grad_norm": 0.49756226702185397,
639
+ "learning_rate": 8.46721951447158e-06,
640
+ "loss": 0.2024,
641
+ "step": 890
642
+ },
643
+ {
644
+ "epoch": 1.0033444816053512,
645
+ "grad_norm": 0.6472920299598118,
646
+ "learning_rate": 8.42018064959393e-06,
647
+ "loss": 0.1903,
648
+ "step": 900
649
+ },
650
+ {
651
+ "epoch": 1.0144927536231885,
652
+ "grad_norm": 0.5997372944954878,
653
+ "learning_rate": 8.37256587670768e-06,
654
+ "loss": 0.1599,
655
+ "step": 910
656
+ },
657
+ {
658
+ "epoch": 1.0256410256410255,
659
+ "grad_norm": 0.6661365745997817,
660
+ "learning_rate": 8.32438321343875e-06,
661
+ "loss": 0.1578,
662
+ "step": 920
663
+ },
664
+ {
665
+ "epoch": 1.0367892976588629,
666
+ "grad_norm": 0.5526716468068121,
667
+ "learning_rate": 8.275640773037432e-06,
668
+ "loss": 0.1584,
669
+ "step": 930
670
+ },
671
+ {
672
+ "epoch": 1.0479375696767002,
673
+ "grad_norm": 0.5311689895480008,
674
+ "learning_rate": 8.226346763012234e-06,
675
+ "loss": 0.1591,
676
+ "step": 940
677
+ },
678
+ {
679
+ "epoch": 1.0590858416945372,
680
+ "grad_norm": 0.6216949836162623,
681
+ "learning_rate": 8.176509483747863e-06,
682
+ "loss": 0.1587,
683
+ "step": 950
684
+ },
685
+ {
686
+ "epoch": 1.0702341137123745,
687
+ "grad_norm": 0.5643715674767006,
688
+ "learning_rate": 8.126137327107556e-06,
689
+ "loss": 0.1559,
690
+ "step": 960
691
+ },
692
+ {
693
+ "epoch": 1.0813823857302118,
694
+ "grad_norm": 0.528226825221165,
695
+ "learning_rate": 8.075238775020011e-06,
696
+ "loss": 0.1582,
697
+ "step": 970
698
+ },
699
+ {
700
+ "epoch": 1.0925306577480491,
701
+ "grad_norm": 0.5303123877825515,
702
+ "learning_rate": 8.023822398051168e-06,
703
+ "loss": 0.1588,
704
+ "step": 980
705
+ },
706
+ {
707
+ "epoch": 1.1036789297658862,
708
+ "grad_norm": 0.5437405641707471,
709
+ "learning_rate": 7.971896853961043e-06,
710
+ "loss": 0.1576,
711
+ "step": 990
712
+ },
713
+ {
714
+ "epoch": 1.1148272017837235,
715
+ "grad_norm": 0.5691619401154729,
716
+ "learning_rate": 7.919470886245886e-06,
717
+ "loss": 0.1561,
718
+ "step": 1000
719
+ },
720
+ {
721
+ "epoch": 1.1148272017837235,
722
+ "eval_accuracy": 0.9239298004895466,
723
+ "eval_loss": 0.20845723152160645,
724
+ "eval_runtime": 4.947,
725
+ "eval_samples_per_second": 46.493,
726
+ "eval_steps_per_second": 1.617,
727
+ "step": 1000
728
+ },
729
+ {
730
+ "epoch": 1.1259754738015608,
731
+ "grad_norm": 0.47581750607341355,
732
+ "learning_rate": 7.86655332266591e-06,
733
+ "loss": 0.1586,
734
+ "step": 1010
735
+ },
736
+ {
737
+ "epoch": 1.137123745819398,
738
+ "grad_norm": 0.6353712929162172,
739
+ "learning_rate": 7.813153073758833e-06,
740
+ "loss": 0.1582,
741
+ "step": 1020
742
+ },
743
+ {
744
+ "epoch": 1.1482720178372352,
745
+ "grad_norm": 0.5419698538850736,
746
+ "learning_rate": 7.759279131339455e-06,
747
+ "loss": 0.1579,
748
+ "step": 1030
749
+ },
750
+ {
751
+ "epoch": 1.1594202898550725,
752
+ "grad_norm": 0.5730038786065867,
753
+ "learning_rate": 7.704940566985592e-06,
754
+ "loss": 0.163,
755
+ "step": 1040
756
+ },
757
+ {
758
+ "epoch": 1.1705685618729098,
759
+ "grad_norm": 0.5280364919184873,
760
+ "learning_rate": 7.650146530510542e-06,
761
+ "loss": 0.1617,
762
+ "step": 1050
763
+ },
764
+ {
765
+ "epoch": 1.1817168338907469,
766
+ "grad_norm": 0.544836252028228,
767
+ "learning_rate": 7.594906248422392e-06,
768
+ "loss": 0.1596,
769
+ "step": 1060
770
+ },
771
+ {
772
+ "epoch": 1.1928651059085842,
773
+ "grad_norm": 0.5378141986574141,
774
+ "learning_rate": 7.539229022370418e-06,
775
+ "loss": 0.1603,
776
+ "step": 1070
777
+ },
778
+ {
779
+ "epoch": 1.2040133779264215,
780
+ "grad_norm": 0.5500474096682983,
781
+ "learning_rate": 7.483124227578811e-06,
782
+ "loss": 0.1579,
783
+ "step": 1080
784
+ },
785
+ {
786
+ "epoch": 1.2151616499442586,
787
+ "grad_norm": 0.5018225238945918,
788
+ "learning_rate": 7.426601311268043e-06,
789
+ "loss": 0.16,
790
+ "step": 1090
791
+ },
792
+ {
793
+ "epoch": 1.2263099219620959,
794
+ "grad_norm": 0.575725285027047,
795
+ "learning_rate": 7.369669791064085e-06,
796
+ "loss": 0.1596,
797
+ "step": 1100
798
+ },
799
+ {
800
+ "epoch": 1.2374581939799332,
801
+ "grad_norm": 0.47947733030163836,
802
+ "learning_rate": 7.312339253395778e-06,
803
+ "loss": 0.1582,
804
+ "step": 1110
805
+ },
806
+ {
807
+ "epoch": 1.2486064659977703,
808
+ "grad_norm": 0.4980356373309633,
809
+ "learning_rate": 7.254619351880625e-06,
810
+ "loss": 0.1581,
811
+ "step": 1120
812
+ },
813
+ {
814
+ "epoch": 1.2597547380156076,
815
+ "grad_norm": 0.578756138117811,
816
+ "learning_rate": 7.1965198056992615e-06,
817
+ "loss": 0.1592,
818
+ "step": 1130
819
+ },
820
+ {
821
+ "epoch": 1.2709030100334449,
822
+ "grad_norm": 0.4635139388152137,
823
+ "learning_rate": 7.138050397958889e-06,
824
+ "loss": 0.1595,
825
+ "step": 1140
826
+ },
827
+ {
828
+ "epoch": 1.282051282051282,
829
+ "grad_norm": 0.49482297151736354,
830
+ "learning_rate": 7.079220974045941e-06,
831
+ "loss": 0.1584,
832
+ "step": 1150
833
+ },
834
+ {
835
+ "epoch": 1.2931995540691192,
836
+ "grad_norm": 0.5460979920247649,
837
+ "learning_rate": 7.0200414399682745e-06,
838
+ "loss": 0.1584,
839
+ "step": 1160
840
+ },
841
+ {
842
+ "epoch": 1.3043478260869565,
843
+ "grad_norm": 0.48148732576426634,
844
+ "learning_rate": 6.96052176068713e-06,
845
+ "loss": 0.1576,
846
+ "step": 1170
847
+ },
848
+ {
849
+ "epoch": 1.3154960981047936,
850
+ "grad_norm": 0.5821793738001766,
851
+ "learning_rate": 6.900671958439192e-06,
852
+ "loss": 0.1599,
853
+ "step": 1180
854
+ },
855
+ {
856
+ "epoch": 1.326644370122631,
857
+ "grad_norm": 0.48883238562313075,
858
+ "learning_rate": 6.840502111048982e-06,
859
+ "loss": 0.158,
860
+ "step": 1190
861
+ },
862
+ {
863
+ "epoch": 1.3377926421404682,
864
+ "grad_norm": 0.5974171958012616,
865
+ "learning_rate": 6.780022350231912e-06,
866
+ "loss": 0.1604,
867
+ "step": 1200
868
+ },
869
+ {
870
+ "epoch": 1.3489409141583055,
871
+ "grad_norm": 0.5659057198248688,
872
+ "learning_rate": 6.719242859888243e-06,
873
+ "loss": 0.1576,
874
+ "step": 1210
875
+ },
876
+ {
877
+ "epoch": 1.3600891861761428,
878
+ "grad_norm": 0.6417774138796649,
879
+ "learning_rate": 6.65817387438827e-06,
880
+ "loss": 0.1588,
881
+ "step": 1220
882
+ },
883
+ {
884
+ "epoch": 1.37123745819398,
885
+ "grad_norm": 0.5414201206440971,
886
+ "learning_rate": 6.596825676849006e-06,
887
+ "loss": 0.1581,
888
+ "step": 1230
889
+ },
890
+ {
891
+ "epoch": 1.3823857302118172,
892
+ "grad_norm": 0.513016285464973,
893
+ "learning_rate": 6.535208597402658e-06,
894
+ "loss": 0.1588,
895
+ "step": 1240
896
+ },
897
+ {
898
+ "epoch": 1.3935340022296545,
899
+ "grad_norm": 0.5513989056143007,
900
+ "learning_rate": 6.473333011457181e-06,
901
+ "loss": 0.1586,
902
+ "step": 1250
903
+ },
904
+ {
905
+ "epoch": 1.4046822742474916,
906
+ "grad_norm": 0.5049419184837916,
907
+ "learning_rate": 6.411209337949214e-06,
908
+ "loss": 0.1594,
909
+ "step": 1260
910
+ },
911
+ {
912
+ "epoch": 1.415830546265329,
913
+ "grad_norm": 0.5217098963627814,
914
+ "learning_rate": 6.348848037589683e-06,
915
+ "loss": 0.159,
916
+ "step": 1270
917
+ },
918
+ {
919
+ "epoch": 1.4269788182831662,
920
+ "grad_norm": 0.5169737196009081,
921
+ "learning_rate": 6.286259611102376e-06,
922
+ "loss": 0.1589,
923
+ "step": 1280
924
+ },
925
+ {
926
+ "epoch": 1.4381270903010033,
927
+ "grad_norm": 0.5747675813836013,
928
+ "learning_rate": 6.223454597455776e-06,
929
+ "loss": 0.1587,
930
+ "step": 1290
931
+ },
932
+ {
933
+ "epoch": 1.4492753623188406,
934
+ "grad_norm": 0.5345109793646367,
935
+ "learning_rate": 6.160443572088443e-06,
936
+ "loss": 0.1595,
937
+ "step": 1300
938
+ },
939
+ {
940
+ "epoch": 1.4604236343366779,
941
+ "grad_norm": 0.49324906218088477,
942
+ "learning_rate": 6.097237145128282e-06,
943
+ "loss": 0.1584,
944
+ "step": 1310
945
+ },
946
+ {
947
+ "epoch": 1.471571906354515,
948
+ "grad_norm": 0.5093141609186953,
949
+ "learning_rate": 6.0338459596059395e-06,
950
+ "loss": 0.1554,
951
+ "step": 1320
952
+ },
953
+ {
954
+ "epoch": 1.4827201783723523,
955
+ "grad_norm": 0.509538948244533,
956
+ "learning_rate": 5.9702806896626855e-06,
957
+ "loss": 0.1585,
958
+ "step": 1330
959
+ },
960
+ {
961
+ "epoch": 1.4938684503901896,
962
+ "grad_norm": 0.6369579950149653,
963
+ "learning_rate": 5.90655203875304e-06,
964
+ "loss": 0.159,
965
+ "step": 1340
966
+ },
967
+ {
968
+ "epoch": 1.5050167224080266,
969
+ "grad_norm": 0.47625480890424343,
970
+ "learning_rate": 5.8426707378424675e-06,
971
+ "loss": 0.1579,
972
+ "step": 1350
973
+ },
974
+ {
975
+ "epoch": 1.516164994425864,
976
+ "grad_norm": 0.5438272649779904,
977
+ "learning_rate": 5.778647543600443e-06,
978
+ "loss": 0.1564,
979
+ "step": 1360
980
+ },
981
+ {
982
+ "epoch": 1.5273132664437012,
983
+ "grad_norm": 0.5161276266998152,
984
+ "learning_rate": 5.714493236589187e-06,
985
+ "loss": 0.1545,
986
+ "step": 1370
987
+ },
988
+ {
989
+ "epoch": 1.5384615384615383,
990
+ "grad_norm": 0.5315157886776762,
991
+ "learning_rate": 5.650218619448379e-06,
992
+ "loss": 0.1552,
993
+ "step": 1380
994
+ },
995
+ {
996
+ "epoch": 1.5496098104793758,
997
+ "grad_norm": 0.5390188368744134,
998
+ "learning_rate": 5.5858345150761515e-06,
999
+ "loss": 0.1556,
1000
+ "step": 1390
1001
+ },
1002
+ {
1003
+ "epoch": 1.560758082497213,
1004
+ "grad_norm": 0.5357636181743068,
1005
+ "learning_rate": 5.521351764806672e-06,
1006
+ "loss": 0.1568,
1007
+ "step": 1400
1008
+ },
1009
+ {
1010
+ "epoch": 1.57190635451505,
1011
+ "grad_norm": 0.4874443181407851,
1012
+ "learning_rate": 5.456781226584621e-06,
1013
+ "loss": 0.158,
1014
+ "step": 1410
1015
+ },
1016
+ {
1017
+ "epoch": 1.5830546265328875,
1018
+ "grad_norm": 0.4563465609878918,
1019
+ "learning_rate": 5.392133773136877e-06,
1020
+ "loss": 0.1602,
1021
+ "step": 1420
1022
+ },
1023
+ {
1024
+ "epoch": 1.5942028985507246,
1025
+ "grad_norm": 0.493572716982426,
1026
+ "learning_rate": 5.327420290141712e-06,
1027
+ "loss": 0.1571,
1028
+ "step": 1430
1029
+ },
1030
+ {
1031
+ "epoch": 1.605351170568562,
1032
+ "grad_norm": 0.5297224295489479,
1033
+ "learning_rate": 5.262651674395799e-06,
1034
+ "loss": 0.1567,
1035
+ "step": 1440
1036
+ },
1037
+ {
1038
+ "epoch": 1.6164994425863992,
1039
+ "grad_norm": 0.4990830580335757,
1040
+ "learning_rate": 5.197838831979352e-06,
1041
+ "loss": 0.1574,
1042
+ "step": 1450
1043
+ },
1044
+ {
1045
+ "epoch": 1.6276477146042363,
1046
+ "grad_norm": 0.4877320539367503,
1047
+ "learning_rate": 5.132992676419704e-06,
1048
+ "loss": 0.1569,
1049
+ "step": 1460
1050
+ },
1051
+ {
1052
+ "epoch": 1.6387959866220736,
1053
+ "grad_norm": 0.546166024878597,
1054
+ "learning_rate": 5.068124126853633e-06,
1055
+ "loss": 0.157,
1056
+ "step": 1470
1057
+ },
1058
+ {
1059
+ "epoch": 1.649944258639911,
1060
+ "grad_norm": 0.4770361938111255,
1061
+ "learning_rate": 5.0032441061887345e-06,
1062
+ "loss": 0.1569,
1063
+ "step": 1480
1064
+ },
1065
+ {
1066
+ "epoch": 1.661092530657748,
1067
+ "grad_norm": 0.44557527525358764,
1068
+ "learning_rate": 4.938363539264175e-06,
1069
+ "loss": 0.1571,
1070
+ "step": 1490
1071
+ },
1072
+ {
1073
+ "epoch": 1.6722408026755853,
1074
+ "grad_norm": 0.48803538459110823,
1075
+ "learning_rate": 4.87349335101109e-06,
1076
+ "loss": 0.1547,
1077
+ "step": 1500
1078
+ },
1079
+ {
1080
+ "epoch": 1.6722408026755853,
1081
+ "eval_accuracy": 0.9265380200765034,
1082
+ "eval_loss": 0.19943761825561523,
1083
+ "eval_runtime": 5.3541,
1084
+ "eval_samples_per_second": 42.958,
1085
+ "eval_steps_per_second": 1.494,
1086
+ "step": 1500
1087
+ },
1088
+ {
1089
+ "epoch": 1.6833890746934226,
1090
+ "grad_norm": 0.5076348755331102,
1091
+ "learning_rate": 4.808644464613015e-06,
1092
+ "loss": 0.1562,
1093
+ "step": 1510
1094
+ },
1095
+ {
1096
+ "epoch": 1.6945373467112597,
1097
+ "grad_norm": 0.501612702783229,
1098
+ "learning_rate": 4.743827799666555e-06,
1099
+ "loss": 0.1547,
1100
+ "step": 1520
1101
+ },
1102
+ {
1103
+ "epoch": 1.705685618729097,
1104
+ "grad_norm": 0.4879807944214394,
1105
+ "learning_rate": 4.679054270342703e-06,
1106
+ "loss": 0.1563,
1107
+ "step": 1530
1108
+ },
1109
+ {
1110
+ "epoch": 1.7168338907469343,
1111
+ "grad_norm": 0.46616141709578995,
1112
+ "learning_rate": 4.614334783549049e-06,
1113
+ "loss": 0.1538,
1114
+ "step": 1540
1115
+ },
1116
+ {
1117
+ "epoch": 1.7279821627647713,
1118
+ "grad_norm": 0.5293473205445773,
1119
+ "learning_rate": 4.549680237093215e-06,
1120
+ "loss": 0.1571,
1121
+ "step": 1550
1122
+ },
1123
+ {
1124
+ "epoch": 1.7391304347826086,
1125
+ "grad_norm": 0.4768030365700139,
1126
+ "learning_rate": 4.485101517847831e-06,
1127
+ "loss": 0.1561,
1128
+ "step": 1560
1129
+ },
1130
+ {
1131
+ "epoch": 1.750278706800446,
1132
+ "grad_norm": 0.5395794005148075,
1133
+ "learning_rate": 4.420609499917337e-06,
1134
+ "loss": 0.1555,
1135
+ "step": 1570
1136
+ },
1137
+ {
1138
+ "epoch": 1.761426978818283,
1139
+ "grad_norm": 0.4879668723657388,
1140
+ "learning_rate": 4.3562150428069565e-06,
1141
+ "loss": 0.1545,
1142
+ "step": 1580
1143
+ },
1144
+ {
1145
+ "epoch": 1.7725752508361206,
1146
+ "grad_norm": 0.4939707212729394,
1147
+ "learning_rate": 4.291928989594102e-06,
1148
+ "loss": 0.1547,
1149
+ "step": 1590
1150
+ },
1151
+ {
1152
+ "epoch": 1.7837235228539576,
1153
+ "grad_norm": 0.4807444627751433,
1154
+ "learning_rate": 4.2277621651025734e-06,
1155
+ "loss": 0.1548,
1156
+ "step": 1600
1157
+ },
1158
+ {
1159
+ "epoch": 1.7948717948717947,
1160
+ "grad_norm": 0.49281674069166814,
1161
+ "learning_rate": 4.163725374079808e-06,
1162
+ "loss": 0.1559,
1163
+ "step": 1610
1164
+ },
1165
+ {
1166
+ "epoch": 1.8060200668896322,
1167
+ "grad_norm": 0.52027039374057,
1168
+ "learning_rate": 4.099829399377524e-06,
1169
+ "loss": 0.1527,
1170
+ "step": 1620
1171
+ },
1172
+ {
1173
+ "epoch": 1.8171683389074693,
1174
+ "grad_norm": 0.4693230544446258,
1175
+ "learning_rate": 4.036085000136046e-06,
1176
+ "loss": 0.1562,
1177
+ "step": 1630
1178
+ },
1179
+ {
1180
+ "epoch": 1.8283166109253066,
1181
+ "grad_norm": 0.5063480473756882,
1182
+ "learning_rate": 3.972502909972628e-06,
1183
+ "loss": 0.1546,
1184
+ "step": 1640
1185
+ },
1186
+ {
1187
+ "epoch": 1.839464882943144,
1188
+ "grad_norm": 0.4816499638368781,
1189
+ "learning_rate": 3.909093835174066e-06,
1190
+ "loss": 0.1547,
1191
+ "step": 1650
1192
+ },
1193
+ {
1194
+ "epoch": 1.850613154960981,
1195
+ "grad_norm": 0.64084638347163,
1196
+ "learning_rate": 3.845868452893919e-06,
1197
+ "loss": 0.1546,
1198
+ "step": 1660
1199
+ },
1200
+ {
1201
+ "epoch": 1.8617614269788183,
1202
+ "grad_norm": 0.5316728198827755,
1203
+ "learning_rate": 3.7828374093546303e-06,
1204
+ "loss": 0.1526,
1205
+ "step": 1670
1206
+ },
1207
+ {
1208
+ "epoch": 1.8729096989966556,
1209
+ "grad_norm": 0.47782006941247335,
1210
+ "learning_rate": 3.720011318054871e-06,
1211
+ "loss": 0.1542,
1212
+ "step": 1680
1213
+ },
1214
+ {
1215
+ "epoch": 1.8840579710144927,
1216
+ "grad_norm": 0.4960856794921382,
1217
+ "learning_rate": 3.657400757982367e-06,
1218
+ "loss": 0.1543,
1219
+ "step": 1690
1220
+ },
1221
+ {
1222
+ "epoch": 1.89520624303233,
1223
+ "grad_norm": 0.5205359533145413,
1224
+ "learning_rate": 3.595016271832572e-06,
1225
+ "loss": 0.1531,
1226
+ "step": 1700
1227
+ },
1228
+ {
1229
+ "epoch": 1.9063545150501673,
1230
+ "grad_norm": 0.5250980924250916,
1231
+ "learning_rate": 3.532868364233416e-06,
1232
+ "loss": 0.1541,
1233
+ "step": 1710
1234
+ },
1235
+ {
1236
+ "epoch": 1.9175027870680044,
1237
+ "grad_norm": 0.4552911079184954,
1238
+ "learning_rate": 3.470967499976492e-06,
1239
+ "loss": 0.1552,
1240
+ "step": 1720
1241
+ },
1242
+ {
1243
+ "epoch": 1.9286510590858417,
1244
+ "grad_norm": 0.47374387614448155,
1245
+ "learning_rate": 3.4093241022549316e-06,
1246
+ "loss": 0.1521,
1247
+ "step": 1730
1248
+ },
1249
+ {
1250
+ "epoch": 1.939799331103679,
1251
+ "grad_norm": 0.4809046264515791,
1252
+ "learning_rate": 3.347948550908303e-06,
1253
+ "loss": 0.1536,
1254
+ "step": 1740
1255
+ },
1256
+ {
1257
+ "epoch": 1.950947603121516,
1258
+ "grad_norm": 0.4611916983834658,
1259
+ "learning_rate": 3.286851180674788e-06,
1260
+ "loss": 0.1524,
1261
+ "step": 1750
1262
+ },
1263
+ {
1264
+ "epoch": 1.9620958751393534,
1265
+ "grad_norm": 0.4496375299269273,
1266
+ "learning_rate": 3.2260422794509704e-06,
1267
+ "loss": 0.1527,
1268
+ "step": 1760
1269
+ },
1270
+ {
1271
+ "epoch": 1.9732441471571907,
1272
+ "grad_norm": 0.49594296693835754,
1273
+ "learning_rate": 3.165532086559504e-06,
1274
+ "loss": 0.1523,
1275
+ "step": 1770
1276
+ },
1277
+ {
1278
+ "epoch": 1.9843924191750277,
1279
+ "grad_norm": 0.4311413917530802,
1280
+ "learning_rate": 3.105330791024965e-06,
1281
+ "loss": 0.1528,
1282
+ "step": 1780
1283
+ },
1284
+ {
1285
+ "epoch": 1.9955406911928653,
1286
+ "grad_norm": 0.46002893870709255,
1287
+ "learning_rate": 3.045448529858165e-06,
1288
+ "loss": 0.1523,
1289
+ "step": 1790
1290
+ },
1291
+ {
1292
+ "epoch": 2.0066889632107023,
1293
+ "grad_norm": 0.6640864376769408,
1294
+ "learning_rate": 2.9858953863492334e-06,
1295
+ "loss": 0.1257,
1296
+ "step": 1800
1297
+ },
1298
+ {
1299
+ "epoch": 2.0178372352285394,
1300
+ "grad_norm": 0.5065513503070602,
1301
+ "learning_rate": 2.9266813883697342e-06,
1302
+ "loss": 0.111,
1303
+ "step": 1810
1304
+ },
1305
+ {
1306
+ "epoch": 2.028985507246377,
1307
+ "grad_norm": 0.5422041920978169,
1308
+ "learning_rate": 2.867816506684126e-06,
1309
+ "loss": 0.1125,
1310
+ "step": 1820
1311
+ },
1312
+ {
1313
+ "epoch": 2.040133779264214,
1314
+ "grad_norm": 0.5207289779266513,
1315
+ "learning_rate": 2.809310653270825e-06,
1316
+ "loss": 0.1113,
1317
+ "step": 1830
1318
+ },
1319
+ {
1320
+ "epoch": 2.051282051282051,
1321
+ "grad_norm": 0.4849357576510085,
1322
+ "learning_rate": 2.751173679653184e-06,
1323
+ "loss": 0.1101,
1324
+ "step": 1840
1325
+ },
1326
+ {
1327
+ "epoch": 2.0624303232998886,
1328
+ "grad_norm": 0.47414870888584787,
1329
+ "learning_rate": 2.693415375240629e-06,
1330
+ "loss": 0.1099,
1331
+ "step": 1850
1332
+ },
1333
+ {
1334
+ "epoch": 2.0735785953177257,
1335
+ "grad_norm": 0.47845407787457195,
1336
+ "learning_rate": 2.636045465680282e-06,
1337
+ "loss": 0.1098,
1338
+ "step": 1860
1339
+ },
1340
+ {
1341
+ "epoch": 2.084726867335563,
1342
+ "grad_norm": 0.5151744285005124,
1343
+ "learning_rate": 2.5790736112192893e-06,
1344
+ "loss": 0.1094,
1345
+ "step": 1870
1346
+ },
1347
+ {
1348
+ "epoch": 2.0958751393534003,
1349
+ "grad_norm": 0.44908780393249104,
1350
+ "learning_rate": 2.522509405078187e-06,
1351
+ "loss": 0.1105,
1352
+ "step": 1880
1353
+ },
1354
+ {
1355
+ "epoch": 2.1070234113712374,
1356
+ "grad_norm": 0.46168216362984565,
1357
+ "learning_rate": 2.4663623718355444e-06,
1358
+ "loss": 0.1102,
1359
+ "step": 1890
1360
+ },
1361
+ {
1362
+ "epoch": 2.1181716833890745,
1363
+ "grad_norm": 0.5003674108234805,
1364
+ "learning_rate": 2.410641965824166e-06,
1365
+ "loss": 0.1089,
1366
+ "step": 1900
1367
+ },
1368
+ {
1369
+ "epoch": 2.129319955406912,
1370
+ "grad_norm": 0.47533896359509586,
1371
+ "learning_rate": 2.355357569539114e-06,
1372
+ "loss": 0.1119,
1373
+ "step": 1910
1374
+ },
1375
+ {
1376
+ "epoch": 2.140468227424749,
1377
+ "grad_norm": 0.4874105883605131,
1378
+ "learning_rate": 2.300518492057842e-06,
1379
+ "loss": 0.114,
1380
+ "step": 1920
1381
+ },
1382
+ {
1383
+ "epoch": 2.1516164994425866,
1384
+ "grad_norm": 0.5034128167417606,
1385
+ "learning_rate": 2.2461339674726804e-06,
1386
+ "loss": 0.1102,
1387
+ "step": 1930
1388
+ },
1389
+ {
1390
+ "epoch": 2.1627647714604237,
1391
+ "grad_norm": 0.4772612798475211,
1392
+ "learning_rate": 2.192213153335953e-06,
1393
+ "loss": 0.1109,
1394
+ "step": 1940
1395
+ },
1396
+ {
1397
+ "epoch": 2.1739130434782608,
1398
+ "grad_norm": 0.4919335114976622,
1399
+ "learning_rate": 2.1387651291179775e-06,
1400
+ "loss": 0.1106,
1401
+ "step": 1950
1402
+ },
1403
+ {
1404
+ "epoch": 2.1850613154960983,
1405
+ "grad_norm": 0.4893367756986907,
1406
+ "learning_rate": 2.085798894678217e-06,
1407
+ "loss": 0.1089,
1408
+ "step": 1960
1409
+ },
1410
+ {
1411
+ "epoch": 2.1962095875139354,
1412
+ "grad_norm": 0.5106660638111142,
1413
+ "learning_rate": 2.0333233687498433e-06,
1414
+ "loss": 0.1094,
1415
+ "step": 1970
1416
+ },
1417
+ {
1418
+ "epoch": 2.2073578595317724,
1419
+ "grad_norm": 0.4698835768687655,
1420
+ "learning_rate": 1.98134738743794e-06,
1421
+ "loss": 0.1105,
1422
+ "step": 1980
1423
+ },
1424
+ {
1425
+ "epoch": 2.21850613154961,
1426
+ "grad_norm": 0.481190970836223,
1427
+ "learning_rate": 1.9298797027316474e-06,
1428
+ "loss": 0.1088,
1429
+ "step": 1990
1430
+ },
1431
+ {
1432
+ "epoch": 2.229654403567447,
1433
+ "grad_norm": 0.4828488140066944,
1434
+ "learning_rate": 1.878928981030445e-06,
1435
+ "loss": 0.1092,
1436
+ "step": 2000
1437
+ },
1438
+ {
1439
+ "epoch": 2.229654403567447,
1440
+ "eval_accuracy": 0.9278099495985295,
1441
+ "eval_loss": 0.20725835859775543,
1442
+ "eval_runtime": 4.9127,
1443
+ "eval_samples_per_second": 46.817,
1444
+ "eval_steps_per_second": 1.628,
1445
+ "step": 2000
1446
+ },
1447
+ {
1448
+ "epoch": 2.240802675585284,
1449
+ "grad_norm": 0.5445446664477709,
1450
+ "learning_rate": 1.828503801684864e-06,
1451
+ "loss": 0.1098,
1452
+ "step": 2010
1453
+ },
1454
+ {
1455
+ "epoch": 2.2519509476031216,
1456
+ "grad_norm": 0.4945888022659562,
1457
+ "learning_rate": 1.7786126555518484e-06,
1458
+ "loss": 0.1093,
1459
+ "step": 2020
1460
+ },
1461
+ {
1462
+ "epoch": 2.2630992196209587,
1463
+ "grad_norm": 0.4728964267184926,
1464
+ "learning_rate": 1.729263943565022e-06,
1465
+ "loss": 0.1088,
1466
+ "step": 2030
1467
+ },
1468
+ {
1469
+ "epoch": 2.274247491638796,
1470
+ "grad_norm": 0.46594045141875756,
1471
+ "learning_rate": 1.6804659753200925e-06,
1472
+ "loss": 0.1101,
1473
+ "step": 2040
1474
+ },
1475
+ {
1476
+ "epoch": 2.2853957636566333,
1477
+ "grad_norm": 0.4731193453792897,
1478
+ "learning_rate": 1.6322269676756402e-06,
1479
+ "loss": 0.1096,
1480
+ "step": 2050
1481
+ },
1482
+ {
1483
+ "epoch": 2.2965440356744704,
1484
+ "grad_norm": 0.46507870631813036,
1485
+ "learning_rate": 1.5845550433695172e-06,
1486
+ "loss": 0.109,
1487
+ "step": 2060
1488
+ },
1489
+ {
1490
+ "epoch": 2.3076923076923075,
1491
+ "grad_norm": 0.5041104454052192,
1492
+ "learning_rate": 1.5374582296511054e-06,
1493
+ "loss": 0.1097,
1494
+ "step": 2070
1495
+ },
1496
+ {
1497
+ "epoch": 2.318840579710145,
1498
+ "grad_norm": 0.4506495588973169,
1499
+ "learning_rate": 1.4909444569296334e-06,
1500
+ "loss": 0.1084,
1501
+ "step": 2080
1502
+ },
1503
+ {
1504
+ "epoch": 2.329988851727982,
1505
+ "grad_norm": 0.5081246384541027,
1506
+ "learning_rate": 1.4450215574388265e-06,
1507
+ "loss": 0.1094,
1508
+ "step": 2090
1509
+ },
1510
+ {
1511
+ "epoch": 2.3411371237458196,
1512
+ "grad_norm": 0.449952731509518,
1513
+ "learning_rate": 1.3996972639180645e-06,
1514
+ "loss": 0.1086,
1515
+ "step": 2100
1516
+ },
1517
+ {
1518
+ "epoch": 2.3522853957636567,
1519
+ "grad_norm": 0.5009677565037799,
1520
+ "learning_rate": 1.3549792083103037e-06,
1521
+ "loss": 0.1079,
1522
+ "step": 2110
1523
+ },
1524
+ {
1525
+ "epoch": 2.3634336677814938,
1526
+ "grad_norm": 0.4544414237147968,
1527
+ "learning_rate": 1.3108749204769732e-06,
1528
+ "loss": 0.1093,
1529
+ "step": 2120
1530
+ },
1531
+ {
1532
+ "epoch": 2.374581939799331,
1533
+ "grad_norm": 0.476556243372622,
1534
+ "learning_rate": 1.2673918269300557e-06,
1535
+ "loss": 0.109,
1536
+ "step": 2130
1537
+ },
1538
+ {
1539
+ "epoch": 2.3857302118171684,
1540
+ "grad_norm": 0.48618656512125896,
1541
+ "learning_rate": 1.2245372495815726e-06,
1542
+ "loss": 0.1086,
1543
+ "step": 2140
1544
+ },
1545
+ {
1546
+ "epoch": 2.3968784838350055,
1547
+ "grad_norm": 0.48915278085562003,
1548
+ "learning_rate": 1.1823184045106816e-06,
1549
+ "loss": 0.1088,
1550
+ "step": 2150
1551
+ },
1552
+ {
1553
+ "epoch": 2.408026755852843,
1554
+ "grad_norm": 0.4612765468912016,
1555
+ "learning_rate": 1.140742400748593e-06,
1556
+ "loss": 0.1085,
1557
+ "step": 2160
1558
+ },
1559
+ {
1560
+ "epoch": 2.41917502787068,
1561
+ "grad_norm": 0.49881271267886607,
1562
+ "learning_rate": 1.099816239081521e-06,
1563
+ "loss": 0.1084,
1564
+ "step": 2170
1565
+ },
1566
+ {
1567
+ "epoch": 2.430323299888517,
1568
+ "grad_norm": 0.47510269822553847,
1569
+ "learning_rate": 1.0595468108718448e-06,
1570
+ "loss": 0.1089,
1571
+ "step": 2180
1572
+ },
1573
+ {
1574
+ "epoch": 2.4414715719063547,
1575
+ "grad_norm": 0.47369643358112645,
1576
+ "learning_rate": 1.0199408968977138e-06,
1577
+ "loss": 0.1087,
1578
+ "step": 2190
1579
+ },
1580
+ {
1581
+ "epoch": 2.4526198439241917,
1582
+ "grad_norm": 0.47267131195325657,
1583
+ "learning_rate": 9.810051662112558e-07,
1584
+ "loss": 0.108,
1585
+ "step": 2200
1586
+ },
1587
+ {
1588
+ "epoch": 2.463768115942029,
1589
+ "grad_norm": 0.45402353633897424,
1590
+ "learning_rate": 9.427461750156142e-07,
1591
+ "loss": 0.1096,
1592
+ "step": 2210
1593
+ },
1594
+ {
1595
+ "epoch": 2.4749163879598663,
1596
+ "grad_norm": 0.46683292783796754,
1597
+ "learning_rate": 9.051703655609762e-07,
1598
+ "loss": 0.1089,
1599
+ "step": 2220
1600
+ },
1601
+ {
1602
+ "epoch": 2.4860646599777034,
1603
+ "grad_norm": 0.4654495260542525,
1604
+ "learning_rate": 8.68284065059794e-07,
1605
+ "loss": 0.1095,
1606
+ "step": 2230
1607
+ },
1608
+ {
1609
+ "epoch": 2.4972129319955405,
1610
+ "grad_norm": 0.4819165766260374,
1611
+ "learning_rate": 8.320934846213746e-07,
1612
+ "loss": 0.1082,
1613
+ "step": 2240
1614
+ },
1615
+ {
1616
+ "epoch": 2.508361204013378,
1617
+ "grad_norm": 0.4582207481405345,
1618
+ "learning_rate": 7.966047182060226e-07,
1619
+ "loss": 0.1083,
1620
+ "step": 2250
1621
+ },
1622
+ {
1623
+ "epoch": 2.519509476031215,
1624
+ "grad_norm": 0.44176541619456144,
1625
+ "learning_rate": 7.618237415989032e-07,
1626
+ "loss": 0.1083,
1627
+ "step": 2260
1628
+ },
1629
+ {
1630
+ "epoch": 2.5306577480490526,
1631
+ "grad_norm": 0.45340706173810835,
1632
+ "learning_rate": 7.277564114038149e-07,
1633
+ "loss": 0.1082,
1634
+ "step": 2270
1635
+ },
1636
+ {
1637
+ "epoch": 2.5418060200668897,
1638
+ "grad_norm": 0.4607933599342553,
1639
+ "learning_rate": 6.944084640570142e-07,
1640
+ "loss": 0.1072,
1641
+ "step": 2280
1642
+ },
1643
+ {
1644
+ "epoch": 2.552954292084727,
1645
+ "grad_norm": 0.4613886801061754,
1646
+ "learning_rate": 6.617855148612945e-07,
1647
+ "loss": 0.1071,
1648
+ "step": 2290
1649
+ },
1650
+ {
1651
+ "epoch": 2.564102564102564,
1652
+ "grad_norm": 0.4490390133193121,
1653
+ "learning_rate": 6.298930570404432e-07,
1654
+ "loss": 0.1087,
1655
+ "step": 2300
1656
+ },
1657
+ {
1658
+ "epoch": 2.5752508361204014,
1659
+ "grad_norm": 0.4561285734622287,
1660
+ "learning_rate": 5.987364608142693e-07,
1661
+ "loss": 0.1076,
1662
+ "step": 2310
1663
+ },
1664
+ {
1665
+ "epoch": 2.5863991081382385,
1666
+ "grad_norm": 0.461278673680382,
1667
+ "learning_rate": 5.683209724943344e-07,
1668
+ "loss": 0.109,
1669
+ "step": 2320
1670
+ },
1671
+ {
1672
+ "epoch": 2.597547380156076,
1673
+ "grad_norm": 0.45105628731245295,
1674
+ "learning_rate": 5.386517136005543e-07,
1675
+ "loss": 0.1081,
1676
+ "step": 2330
1677
+ },
1678
+ {
1679
+ "epoch": 2.608695652173913,
1680
+ "grad_norm": 0.438445525307319,
1681
+ "learning_rate": 5.097336799988067e-07,
1682
+ "loss": 0.1079,
1683
+ "step": 2340
1684
+ },
1685
+ {
1686
+ "epoch": 2.61984392419175,
1687
+ "grad_norm": 0.4457791687565759,
1688
+ "learning_rate": 4.815717410597042e-07,
1689
+ "loss": 0.1081,
1690
+ "step": 2350
1691
+ },
1692
+ {
1693
+ "epoch": 2.6309921962095872,
1694
+ "grad_norm": 0.44606421814267033,
1695
+ "learning_rate": 4.541706388386624e-07,
1696
+ "loss": 0.1086,
1697
+ "step": 2360
1698
+ },
1699
+ {
1700
+ "epoch": 2.6421404682274248,
1701
+ "grad_norm": 0.4398808910735919,
1702
+ "learning_rate": 4.275349872774098e-07,
1703
+ "loss": 0.1073,
1704
+ "step": 2370
1705
+ },
1706
+ {
1707
+ "epoch": 2.653288740245262,
1708
+ "grad_norm": 0.4522695550459701,
1709
+ "learning_rate": 4.0166927142706313e-07,
1710
+ "loss": 0.1076,
1711
+ "step": 2380
1712
+ },
1713
+ {
1714
+ "epoch": 2.6644370122630994,
1715
+ "grad_norm": 0.4436224867256293,
1716
+ "learning_rate": 3.765778466929182e-07,
1717
+ "loss": 0.1066,
1718
+ "step": 2390
1719
+ },
1720
+ {
1721
+ "epoch": 2.6755852842809364,
1722
+ "grad_norm": 0.428940667218784,
1723
+ "learning_rate": 3.5226493810105624e-07,
1724
+ "loss": 0.1081,
1725
+ "step": 2400
1726
+ },
1727
+ {
1728
+ "epoch": 2.6867335562987735,
1729
+ "grad_norm": 0.45631649150745296,
1730
+ "learning_rate": 3.2873463958691675e-07,
1731
+ "loss": 0.108,
1732
+ "step": 2410
1733
+ },
1734
+ {
1735
+ "epoch": 2.697881828316611,
1736
+ "grad_norm": 0.4407463233212753,
1737
+ "learning_rate": 3.05990913305938e-07,
1738
+ "loss": 0.1077,
1739
+ "step": 2420
1740
+ },
1741
+ {
1742
+ "epoch": 2.709030100334448,
1743
+ "grad_norm": 0.45899753246408376,
1744
+ "learning_rate": 2.840375889663871e-07,
1745
+ "loss": 0.106,
1746
+ "step": 2430
1747
+ },
1748
+ {
1749
+ "epoch": 2.7201783723522857,
1750
+ "grad_norm": 0.4620830771843678,
1751
+ "learning_rate": 2.62878363184495e-07,
1752
+ "loss": 0.107,
1753
+ "step": 2440
1754
+ },
1755
+ {
1756
+ "epoch": 2.7313266443701227,
1757
+ "grad_norm": 0.4540560827599527,
1758
+ "learning_rate": 2.425167988620014e-07,
1759
+ "loss": 0.1078,
1760
+ "step": 2450
1761
+ },
1762
+ {
1763
+ "epoch": 2.74247491638796,
1764
+ "grad_norm": 0.4379908641559117,
1765
+ "learning_rate": 2.2295632458621097e-07,
1766
+ "loss": 0.1076,
1767
+ "step": 2460
1768
+ },
1769
+ {
1770
+ "epoch": 2.753623188405797,
1771
+ "grad_norm": 0.44868425706880766,
1772
+ "learning_rate": 2.0420023405267663e-07,
1773
+ "loss": 0.1076,
1774
+ "step": 2470
1775
+ },
1776
+ {
1777
+ "epoch": 2.7647714604236344,
1778
+ "grad_norm": 0.47473094706270963,
1779
+ "learning_rate": 1.8625168551058115e-07,
1780
+ "loss": 0.1071,
1781
+ "step": 2480
1782
+ },
1783
+ {
1784
+ "epoch": 2.7759197324414715,
1785
+ "grad_norm": 0.45861955063568105,
1786
+ "learning_rate": 1.6911370123094238e-07,
1787
+ "loss": 0.1081,
1788
+ "step": 2490
1789
+ },
1790
+ {
1791
+ "epoch": 2.787068004459309,
1792
+ "grad_norm": 0.45384731541579043,
1793
+ "learning_rate": 1.5278916699770163e-07,
1794
+ "loss": 0.1073,
1795
+ "step": 2500
1796
+ },
1797
+ {
1798
+ "epoch": 2.787068004459309,
1799
+ "eval_accuracy": 0.9283863306145088,
1800
+ "eval_loss": 0.20636913180351257,
1801
+ "eval_runtime": 5.1195,
1802
+ "eval_samples_per_second": 44.926,
1803
+ "eval_steps_per_second": 1.563,
1804
+ "step": 2500
1805
+ },
1806
+ {
1807
+ "epoch": 2.798216276477146,
1808
+ "grad_norm": 0.4773943035056343,
1809
+ "learning_rate": 1.3728083162180384e-07,
1810
+ "loss": 0.1075,
1811
+ "step": 2510
1812
+ },
1813
+ {
1814
+ "epoch": 2.809364548494983,
1815
+ "grad_norm": 0.428735968014936,
1816
+ "learning_rate": 1.2259130647833627e-07,
1817
+ "loss": 0.1065,
1818
+ "step": 2520
1819
+ },
1820
+ {
1821
+ "epoch": 2.8205128205128203,
1822
+ "grad_norm": 0.4385864949658292,
1823
+ "learning_rate": 1.0872306506681251e-07,
1824
+ "loss": 0.1079,
1825
+ "step": 2530
1826
+ },
1827
+ {
1828
+ "epoch": 2.831661092530658,
1829
+ "grad_norm": 0.4743582222874101,
1830
+ "learning_rate": 9.567844259467051e-08,
1831
+ "loss": 0.1083,
1832
+ "step": 2540
1833
+ },
1834
+ {
1835
+ "epoch": 2.842809364548495,
1836
+ "grad_norm": 0.45862196445217895,
1837
+ "learning_rate": 8.345963558406001e-08,
1838
+ "loss": 0.1079,
1839
+ "step": 2550
1840
+ },
1841
+ {
1842
+ "epoch": 2.8539576365663324,
1843
+ "grad_norm": 0.45558482700348846,
1844
+ "learning_rate": 7.206870150197831e-08,
1845
+ "loss": 0.107,
1846
+ "step": 2560
1847
+ },
1848
+ {
1849
+ "epoch": 2.8651059085841695,
1850
+ "grad_norm": 0.4458457370599944,
1851
+ "learning_rate": 6.150755841382527e-08,
1852
+ "loss": 0.1067,
1853
+ "step": 2570
1854
+ },
1855
+ {
1856
+ "epoch": 2.8762541806020065,
1857
+ "grad_norm": 0.44342362029660554,
1858
+ "learning_rate": 5.177798466042716e-08,
1859
+ "loss": 0.1078,
1860
+ "step": 2580
1861
+ },
1862
+ {
1863
+ "epoch": 2.887402452619844,
1864
+ "grad_norm": 0.4369582199234232,
1865
+ "learning_rate": 4.2881618558592855e-08,
1866
+ "loss": 0.109,
1867
+ "step": 2590
1868
+ },
1869
+ {
1870
+ "epoch": 2.898550724637681,
1871
+ "grad_norm": 0.4355601557089695,
1872
+ "learning_rate": 3.481995812524286e-08,
1873
+ "loss": 0.1064,
1874
+ "step": 2600
1875
+ },
1876
+ {
1877
+ "epoch": 2.9096989966555182,
1878
+ "grad_norm": 0.4377173417059771,
1879
+ "learning_rate": 2.7594360825166644e-08,
1880
+ "loss": 0.107,
1881
+ "step": 2610
1882
+ },
1883
+ {
1884
+ "epoch": 2.9208472686733558,
1885
+ "grad_norm": 0.4495055773584237,
1886
+ "learning_rate": 2.120604334244547e-08,
1887
+ "loss": 0.1067,
1888
+ "step": 2620
1889
+ },
1890
+ {
1891
+ "epoch": 2.931995540691193,
1892
+ "grad_norm": 0.44729903103488183,
1893
+ "learning_rate": 1.565608137558128e-08,
1894
+ "loss": 0.1063,
1895
+ "step": 2630
1896
+ },
1897
+ {
1898
+ "epoch": 2.94314381270903,
1899
+ "grad_norm": 0.44620730977493767,
1900
+ "learning_rate": 1.0945409456364353e-08,
1901
+ "loss": 0.1075,
1902
+ "step": 2640
1903
+ },
1904
+ {
1905
+ "epoch": 2.9542920847268674,
1906
+ "grad_norm": 0.46052917967733736,
1907
+ "learning_rate": 7.0748207925103176e-09,
1908
+ "loss": 0.1075,
1909
+ "step": 2650
1910
+ },
1911
+ {
1912
+ "epoch": 2.9654403567447045,
1913
+ "grad_norm": 0.4450651551983087,
1914
+ "learning_rate": 4.044967134099187e-09,
1915
+ "loss": 0.1079,
1916
+ "step": 2660
1917
+ },
1918
+ {
1919
+ "epoch": 2.976588628762542,
1920
+ "grad_norm": 0.4581682413498136,
1921
+ "learning_rate": 1.8563586638281617e-09,
1922
+ "loss": 0.1064,
1923
+ "step": 2670
1924
+ },
1925
+ {
1926
+ "epoch": 2.987736900780379,
1927
+ "grad_norm": 0.44561324878780834,
1928
+ "learning_rate": 5.093639111025673e-10,
1929
+ "loss": 0.1071,
1930
+ "step": 2680
1931
+ },
1932
+ {
1933
+ "epoch": 2.998885172798216,
1934
+ "grad_norm": 0.46042910026727557,
1935
+ "learning_rate": 4.2096899854904285e-12,
1936
+ "loss": 0.1079,
1937
+ "step": 2690
1938
+ },
1939
+ {
1940
+ "epoch": 3.0,
1941
+ "step": 2691,
1942
+ "total_flos": 2978959170994176.0,
1943
+ "train_loss": 0.161040273276637,
1944
+ "train_runtime": 34957.7462,
1945
+ "train_samples_per_second": 19.698,
1946
+ "train_steps_per_second": 0.077
1947
+ }
1948
+ ],
1949
+ "logging_steps": 10,
1950
+ "max_steps": 2691,
1951
+ "num_input_tokens_seen": 0,
1952
+ "num_train_epochs": 3,
1953
+ "save_steps": 100,
1954
+ "stateful_callbacks": {
1955
+ "TrainerControl": {
1956
+ "args": {
1957
+ "should_epoch_stop": false,
1958
+ "should_evaluate": false,
1959
+ "should_log": false,
1960
+ "should_save": true,
1961
+ "should_training_stop": true
1962
+ },
1963
+ "attributes": {}
1964
+ }
1965
+ },
1966
+ "total_flos": 2978959170994176.0,
1967
+ "train_batch_size": 4,
1968
+ "trial_name": null,
1969
+ "trial_params": null
1970
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f65e0c7540b029889ba1a34172c030237b5ce3656f22eb9c6e93d46be58cf30
3
+ size 7160
training_eval_accuracy.png ADDED
training_eval_loss.png ADDED
training_loss.png ADDED