anindya64 commited on
Commit
c53a29a
·
verified ·
1 Parent(s): 6772c27

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/anindya/Submission/text2sql/text2sql/output_llama3.2_v0.0.2/checkpoint-3200",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.44.0",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.0"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3d31418de374b6a3d743843d97ff99440b658852c9aca068f12e71e3d70e58
3
+ size 4943274328
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77402f13c43c422c311054be881ce8d4ab442fcbaab4fcf49ec422cfa1738215
3
+ size 9886605026
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed4e19e1880ef435bf564c012b2b8809695c9df96579df0f75ddd8d4fd35483
3
+ size 14960
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051b16cbfce04c19dc1513df04edc6e177f0436509d1a5688acda053c7e7dbae
3
+ size 14960
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6943db2429497d298c96aaa0581a5996a793175c9cde03b1693bcab67c058cbf
3
+ size 14960
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dacb97007d00a52c325bf624a4a28f7fb5876966267ec188ab58aa6997e68437
3
+ size 14960
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf13c7e98fac3176f054c9620ff65ebb3414084a4213e969dde97e2ca4eaf81
3
+ size 1064
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 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
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
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,1168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.7407407407407407,
5
+ "eval_steps": 500,
6
+ "global_step": 1600,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004629629629629629,
13
+ "grad_norm": 1.9547569751739502,
14
+ "learning_rate": 5.205622071837585e-08,
15
+ "loss": 0.213,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.009259259259259259,
20
+ "grad_norm": 2.578005313873291,
21
+ "learning_rate": 1.041124414367517e-07,
22
+ "loss": 0.2008,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.013888888888888888,
27
+ "grad_norm": 2.6108486652374268,
28
+ "learning_rate": 1.5616866215512754e-07,
29
+ "loss": 0.2183,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.018518518518518517,
34
+ "grad_norm": 2.8388636112213135,
35
+ "learning_rate": 2.082248828735034e-07,
36
+ "loss": 0.1992,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.023148148148148147,
41
+ "grad_norm": 3.057955026626587,
42
+ "learning_rate": 2.6028110359187923e-07,
43
+ "loss": 0.191,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.027777777777777776,
48
+ "grad_norm": 3.562337875366211,
49
+ "learning_rate": 3.123373243102551e-07,
50
+ "loss": 0.2146,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.032407407407407406,
55
+ "grad_norm": 2.5107476711273193,
56
+ "learning_rate": 3.643935450286309e-07,
57
+ "loss": 0.1965,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.037037037037037035,
62
+ "grad_norm": 3.556824207305908,
63
+ "learning_rate": 4.164497657470068e-07,
64
+ "loss": 0.2066,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.041666666666666664,
69
+ "grad_norm": 2.4915523529052734,
70
+ "learning_rate": 4.633003643935451e-07,
71
+ "loss": 0.1732,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.046296296296296294,
76
+ "grad_norm": 2.685553789138794,
77
+ "learning_rate": 5.153565851119209e-07,
78
+ "loss": 0.171,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.05092592592592592,
83
+ "grad_norm": 2.201007127761841,
84
+ "learning_rate": 5.674128058302968e-07,
85
+ "loss": 0.1896,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.05555555555555555,
90
+ "grad_norm": 2.432368040084839,
91
+ "learning_rate": 6.194690265486726e-07,
92
+ "loss": 0.1754,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.06018518518518518,
97
+ "grad_norm": 2.5078160762786865,
98
+ "learning_rate": 6.715252472670485e-07,
99
+ "loss": 0.1696,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.06481481481481481,
104
+ "grad_norm": 2.8419947624206543,
105
+ "learning_rate": 7.235814679854243e-07,
106
+ "loss": 0.171,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.06944444444444445,
111
+ "grad_norm": 1.7001116275787354,
112
+ "learning_rate": 7.756376887038002e-07,
113
+ "loss": 0.1851,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.07407407407407407,
118
+ "grad_norm": 2.28574275970459,
119
+ "learning_rate": 8.27693909422176e-07,
120
+ "loss": 0.1787,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.0787037037037037,
125
+ "grad_norm": 2.0533792972564697,
126
+ "learning_rate": 8.797501301405519e-07,
127
+ "loss": 0.1851,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.08333333333333333,
132
+ "grad_norm": 1.8994508981704712,
133
+ "learning_rate": 9.318063508589277e-07,
134
+ "loss": 0.1759,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.08796296296296297,
139
+ "grad_norm": 2.1839489936828613,
140
+ "learning_rate": 9.838625715773036e-07,
141
+ "loss": 0.1733,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.09259259259259259,
146
+ "grad_norm": 2.344303607940674,
147
+ "learning_rate": 1.0359187922956794e-06,
148
+ "loss": 0.1612,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.09722222222222222,
153
+ "grad_norm": 2.48638916015625,
154
+ "learning_rate": 1.0879750130140553e-06,
155
+ "loss": 0.1672,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.10185185185185185,
160
+ "grad_norm": 2.793229579925537,
161
+ "learning_rate": 1.140031233732431e-06,
162
+ "loss": 0.1726,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.10648148148148148,
167
+ "grad_norm": 2.6986732482910156,
168
+ "learning_rate": 1.192087454450807e-06,
169
+ "loss": 0.1652,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.1111111111111111,
174
+ "grad_norm": 2.5542423725128174,
175
+ "learning_rate": 1.2441436751691828e-06,
176
+ "loss": 0.1816,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.11574074074074074,
181
+ "grad_norm": 2.154715061187744,
182
+ "learning_rate": 1.2961998958875587e-06,
183
+ "loss": 0.1653,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.12037037037037036,
188
+ "grad_norm": 2.007305383682251,
189
+ "learning_rate": 1.3482561166059347e-06,
190
+ "loss": 0.1763,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.125,
195
+ "grad_norm": 1.7739317417144775,
196
+ "learning_rate": 1.4003123373243104e-06,
197
+ "loss": 0.1534,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.12962962962962962,
202
+ "grad_norm": 2.1357200145721436,
203
+ "learning_rate": 1.4523685580426864e-06,
204
+ "loss": 0.1734,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.13425925925925927,
209
+ "grad_norm": 2.1542086601257324,
210
+ "learning_rate": 1.5044247787610621e-06,
211
+ "loss": 0.1671,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.1388888888888889,
216
+ "grad_norm": 2.20986008644104,
217
+ "learning_rate": 1.556480999479438e-06,
218
+ "loss": 0.1615,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.14351851851851852,
223
+ "grad_norm": 2.262831211090088,
224
+ "learning_rate": 1.6085372201978138e-06,
225
+ "loss": 0.1453,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.14814814814814814,
230
+ "grad_norm": 1.9716724157333374,
231
+ "learning_rate": 1.6605934409161898e-06,
232
+ "loss": 0.1688,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.1527777777777778,
237
+ "grad_norm": 2.058307647705078,
238
+ "learning_rate": 1.7126496616345655e-06,
239
+ "loss": 0.1494,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.1574074074074074,
244
+ "grad_norm": 2.354652166366577,
245
+ "learning_rate": 1.7647058823529414e-06,
246
+ "loss": 0.1641,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.16203703703703703,
251
+ "grad_norm": 2.8483664989471436,
252
+ "learning_rate": 1.8167621030713172e-06,
253
+ "loss": 0.1545,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.16666666666666666,
258
+ "grad_norm": 3.0298044681549072,
259
+ "learning_rate": 1.8688183237896931e-06,
260
+ "loss": 0.1463,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.1712962962962963,
265
+ "grad_norm": 2.6635050773620605,
266
+ "learning_rate": 1.920874544508069e-06,
267
+ "loss": 0.1483,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.17592592592592593,
272
+ "grad_norm": 2.1750943660736084,
273
+ "learning_rate": 1.972930765226445e-06,
274
+ "loss": 0.1539,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.18055555555555555,
279
+ "grad_norm": 3.222320318222046,
280
+ "learning_rate": 2.0249869859448206e-06,
281
+ "loss": 0.1677,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.18518518518518517,
286
+ "grad_norm": 2.517885684967041,
287
+ "learning_rate": 2.0770432066631967e-06,
288
+ "loss": 0.1719,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.18981481481481483,
293
+ "grad_norm": 2.2146666049957275,
294
+ "learning_rate": 2.1290994273815725e-06,
295
+ "loss": 0.1445,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.19444444444444445,
300
+ "grad_norm": 1.9601733684539795,
301
+ "learning_rate": 2.1811556480999482e-06,
302
+ "loss": 0.1664,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.19907407407407407,
307
+ "grad_norm": 2.468904733657837,
308
+ "learning_rate": 2.233211868818324e-06,
309
+ "loss": 0.1486,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.2037037037037037,
314
+ "grad_norm": 1.9706175327301025,
315
+ "learning_rate": 2.2852680895367e-06,
316
+ "loss": 0.1408,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.20833333333333334,
321
+ "grad_norm": 1.9512994289398193,
322
+ "learning_rate": 2.337324310255076e-06,
323
+ "loss": 0.1659,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.21296296296296297,
328
+ "grad_norm": 2.83563494682312,
329
+ "learning_rate": 2.3893805309734516e-06,
330
+ "loss": 0.1686,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.2175925925925926,
335
+ "grad_norm": 3.0552988052368164,
336
+ "learning_rate": 2.4414367516918273e-06,
337
+ "loss": 0.1576,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.2222222222222222,
342
+ "grad_norm": 2.7302849292755127,
343
+ "learning_rate": 2.4934929724102035e-06,
344
+ "loss": 0.1447,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.22685185185185186,
349
+ "grad_norm": 2.417853593826294,
350
+ "learning_rate": 2.5455491931285792e-06,
351
+ "loss": 0.1581,
352
+ "step": 490
353
+ },
354
+ {
355
+ "execution_accuracy": 46.0,
356
+ "selected_difficulty": "overall",
357
+ "step": 500
358
+ },
359
+ {
360
+ "epoch": 0.23148148148148148,
361
+ "grad_norm": 2.8662281036376953,
362
+ "learning_rate": 2.5976054138469546e-06,
363
+ "loss": 0.1617,
364
+ "step": 500
365
+ },
366
+ {
367
+ "epoch": 0.2361111111111111,
368
+ "grad_norm": 2.442883014678955,
369
+ "learning_rate": 2.6496616345653307e-06,
370
+ "loss": 0.1608,
371
+ "step": 510
372
+ },
373
+ {
374
+ "epoch": 0.24074074074074073,
375
+ "grad_norm": 2.1168131828308105,
376
+ "learning_rate": 2.7017178552837065e-06,
377
+ "loss": 0.1438,
378
+ "step": 520
379
+ },
380
+ {
381
+ "epoch": 0.24537037037037038,
382
+ "grad_norm": 3.455186605453491,
383
+ "learning_rate": 2.7537740760020826e-06,
384
+ "loss": 0.1661,
385
+ "step": 530
386
+ },
387
+ {
388
+ "epoch": 0.25,
389
+ "grad_norm": 2.615549325942993,
390
+ "learning_rate": 2.805830296720458e-06,
391
+ "loss": 0.1584,
392
+ "step": 540
393
+ },
394
+ {
395
+ "epoch": 0.25462962962962965,
396
+ "grad_norm": 1.9767112731933594,
397
+ "learning_rate": 2.857886517438834e-06,
398
+ "loss": 0.1299,
399
+ "step": 550
400
+ },
401
+ {
402
+ "epoch": 0.25925925925925924,
403
+ "grad_norm": 2.0110256671905518,
404
+ "learning_rate": 2.90994273815721e-06,
405
+ "loss": 0.1436,
406
+ "step": 560
407
+ },
408
+ {
409
+ "epoch": 0.2638888888888889,
410
+ "grad_norm": 2.232252836227417,
411
+ "learning_rate": 2.961998958875586e-06,
412
+ "loss": 0.1476,
413
+ "step": 570
414
+ },
415
+ {
416
+ "epoch": 0.26851851851851855,
417
+ "grad_norm": 2.556427240371704,
418
+ "learning_rate": 3.0140551795939618e-06,
419
+ "loss": 0.1411,
420
+ "step": 580
421
+ },
422
+ {
423
+ "epoch": 0.27314814814814814,
424
+ "grad_norm": 1.7226930856704712,
425
+ "learning_rate": 3.0661114003123375e-06,
426
+ "loss": 0.1421,
427
+ "step": 590
428
+ },
429
+ {
430
+ "epoch": 0.2777777777777778,
431
+ "grad_norm": 1.7159005403518677,
432
+ "learning_rate": 3.1181676210307132e-06,
433
+ "loss": 0.1451,
434
+ "step": 600
435
+ },
436
+ {
437
+ "epoch": 0.2824074074074074,
438
+ "grad_norm": 2.398245334625244,
439
+ "learning_rate": 3.1702238417490894e-06,
440
+ "loss": 0.1537,
441
+ "step": 610
442
+ },
443
+ {
444
+ "epoch": 0.28703703703703703,
445
+ "grad_norm": 2.5853817462921143,
446
+ "learning_rate": 3.222280062467465e-06,
447
+ "loss": 0.1506,
448
+ "step": 620
449
+ },
450
+ {
451
+ "epoch": 0.2916666666666667,
452
+ "grad_norm": 2.438486337661743,
453
+ "learning_rate": 3.274336283185841e-06,
454
+ "loss": 0.1512,
455
+ "step": 630
456
+ },
457
+ {
458
+ "epoch": 0.2962962962962963,
459
+ "grad_norm": 2.3523032665252686,
460
+ "learning_rate": 3.3263925039042166e-06,
461
+ "loss": 0.1489,
462
+ "step": 640
463
+ },
464
+ {
465
+ "epoch": 0.30092592592592593,
466
+ "grad_norm": 2.763634443283081,
467
+ "learning_rate": 3.3784487246225928e-06,
468
+ "loss": 0.1518,
469
+ "step": 650
470
+ },
471
+ {
472
+ "epoch": 0.3055555555555556,
473
+ "grad_norm": 2.588419198989868,
474
+ "learning_rate": 3.4305049453409685e-06,
475
+ "loss": 0.138,
476
+ "step": 660
477
+ },
478
+ {
479
+ "epoch": 0.3101851851851852,
480
+ "grad_norm": 1.9856290817260742,
481
+ "learning_rate": 3.4825611660593443e-06,
482
+ "loss": 0.1549,
483
+ "step": 670
484
+ },
485
+ {
486
+ "epoch": 0.3148148148148148,
487
+ "grad_norm": 1.7812482118606567,
488
+ "learning_rate": 3.53461738677772e-06,
489
+ "loss": 0.1288,
490
+ "step": 680
491
+ },
492
+ {
493
+ "epoch": 0.3194444444444444,
494
+ "grad_norm": 2.1843719482421875,
495
+ "learning_rate": 3.586673607496096e-06,
496
+ "loss": 0.1311,
497
+ "step": 690
498
+ },
499
+ {
500
+ "epoch": 0.32407407407407407,
501
+ "grad_norm": 2.653047561645508,
502
+ "learning_rate": 3.638729828214472e-06,
503
+ "loss": 0.1612,
504
+ "step": 700
505
+ },
506
+ {
507
+ "epoch": 0.3287037037037037,
508
+ "grad_norm": 2.5062875747680664,
509
+ "learning_rate": 3.690786048932848e-06,
510
+ "loss": 0.1437,
511
+ "step": 710
512
+ },
513
+ {
514
+ "epoch": 0.3333333333333333,
515
+ "grad_norm": 1.8424952030181885,
516
+ "learning_rate": 3.7428422696512234e-06,
517
+ "loss": 0.1368,
518
+ "step": 720
519
+ },
520
+ {
521
+ "epoch": 0.33796296296296297,
522
+ "grad_norm": 2.2268905639648438,
523
+ "learning_rate": 3.7948984903695995e-06,
524
+ "loss": 0.1442,
525
+ "step": 730
526
+ },
527
+ {
528
+ "epoch": 0.3425925925925926,
529
+ "grad_norm": 2.2701923847198486,
530
+ "learning_rate": 3.846954711087975e-06,
531
+ "loss": 0.1359,
532
+ "step": 740
533
+ },
534
+ {
535
+ "epoch": 0.3472222222222222,
536
+ "grad_norm": 1.805020809173584,
537
+ "learning_rate": 3.899010931806351e-06,
538
+ "loss": 0.1414,
539
+ "step": 750
540
+ },
541
+ {
542
+ "epoch": 0.35185185185185186,
543
+ "grad_norm": 2.4810807704925537,
544
+ "learning_rate": 3.951067152524727e-06,
545
+ "loss": 0.1504,
546
+ "step": 760
547
+ },
548
+ {
549
+ "epoch": 0.35648148148148145,
550
+ "grad_norm": 2.313380002975464,
551
+ "learning_rate": 4.003123373243103e-06,
552
+ "loss": 0.1417,
553
+ "step": 770
554
+ },
555
+ {
556
+ "epoch": 0.3611111111111111,
557
+ "grad_norm": 2.2919764518737793,
558
+ "learning_rate": 4.055179593961479e-06,
559
+ "loss": 0.1402,
560
+ "step": 780
561
+ },
562
+ {
563
+ "epoch": 0.36574074074074076,
564
+ "grad_norm": 2.7147014141082764,
565
+ "learning_rate": 4.107235814679855e-06,
566
+ "loss": 0.1305,
567
+ "step": 790
568
+ },
569
+ {
570
+ "epoch": 0.37037037037037035,
571
+ "grad_norm": 2.1526637077331543,
572
+ "learning_rate": 4.15929203539823e-06,
573
+ "loss": 0.1371,
574
+ "step": 800
575
+ },
576
+ {
577
+ "epoch": 0.375,
578
+ "grad_norm": 2.168653726577759,
579
+ "learning_rate": 4.211348256116606e-06,
580
+ "loss": 0.1261,
581
+ "step": 810
582
+ },
583
+ {
584
+ "epoch": 0.37962962962962965,
585
+ "grad_norm": 1.9278998374938965,
586
+ "learning_rate": 4.263404476834982e-06,
587
+ "loss": 0.1371,
588
+ "step": 820
589
+ },
590
+ {
591
+ "epoch": 0.38425925925925924,
592
+ "grad_norm": 2.528472423553467,
593
+ "learning_rate": 4.315460697553358e-06,
594
+ "loss": 0.1343,
595
+ "step": 830
596
+ },
597
+ {
598
+ "epoch": 0.3888888888888889,
599
+ "grad_norm": 1.9146366119384766,
600
+ "learning_rate": 4.367516918271734e-06,
601
+ "loss": 0.1287,
602
+ "step": 840
603
+ },
604
+ {
605
+ "epoch": 0.39351851851851855,
606
+ "grad_norm": 2.0333926677703857,
607
+ "learning_rate": 4.41957313899011e-06,
608
+ "loss": 0.1226,
609
+ "step": 850
610
+ },
611
+ {
612
+ "epoch": 0.39814814814814814,
613
+ "grad_norm": 1.8780897855758667,
614
+ "learning_rate": 4.4716293597084854e-06,
615
+ "loss": 0.1358,
616
+ "step": 860
617
+ },
618
+ {
619
+ "epoch": 0.4027777777777778,
620
+ "grad_norm": 2.3289811611175537,
621
+ "learning_rate": 4.523685580426862e-06,
622
+ "loss": 0.1361,
623
+ "step": 870
624
+ },
625
+ {
626
+ "epoch": 0.4074074074074074,
627
+ "grad_norm": 2.307506799697876,
628
+ "learning_rate": 4.575741801145237e-06,
629
+ "loss": 0.1347,
630
+ "step": 880
631
+ },
632
+ {
633
+ "epoch": 0.41203703703703703,
634
+ "grad_norm": 2.4301393032073975,
635
+ "learning_rate": 4.627798021863613e-06,
636
+ "loss": 0.1407,
637
+ "step": 890
638
+ },
639
+ {
640
+ "epoch": 0.4166666666666667,
641
+ "grad_norm": 2.1248655319213867,
642
+ "learning_rate": 4.679854242581988e-06,
643
+ "loss": 0.1359,
644
+ "step": 900
645
+ },
646
+ {
647
+ "epoch": 0.4212962962962963,
648
+ "grad_norm": 2.7919039726257324,
649
+ "learning_rate": 4.7319104633003646e-06,
650
+ "loss": 0.1404,
651
+ "step": 910
652
+ },
653
+ {
654
+ "epoch": 0.42592592592592593,
655
+ "grad_norm": 2.627920627593994,
656
+ "learning_rate": 4.783966684018741e-06,
657
+ "loss": 0.1347,
658
+ "step": 920
659
+ },
660
+ {
661
+ "epoch": 0.4305555555555556,
662
+ "grad_norm": 1.7436546087265015,
663
+ "learning_rate": 4.836022904737117e-06,
664
+ "loss": 0.135,
665
+ "step": 930
666
+ },
667
+ {
668
+ "epoch": 0.4351851851851852,
669
+ "grad_norm": 2.3651235103607178,
670
+ "learning_rate": 4.888079125455492e-06,
671
+ "loss": 0.1165,
672
+ "step": 940
673
+ },
674
+ {
675
+ "epoch": 0.4398148148148148,
676
+ "grad_norm": 3.688002586364746,
677
+ "learning_rate": 4.940135346173868e-06,
678
+ "loss": 0.1289,
679
+ "step": 950
680
+ },
681
+ {
682
+ "epoch": 0.4444444444444444,
683
+ "grad_norm": 2.553744077682495,
684
+ "learning_rate": 4.992191566892244e-06,
685
+ "loss": 0.1399,
686
+ "step": 960
687
+ },
688
+ {
689
+ "epoch": 0.44907407407407407,
690
+ "grad_norm": 2.997828722000122,
691
+ "learning_rate": 5.04424778761062e-06,
692
+ "loss": 0.1115,
693
+ "step": 970
694
+ },
695
+ {
696
+ "epoch": 0.4537037037037037,
697
+ "grad_norm": 1.8085178136825562,
698
+ "learning_rate": 5.096304008328996e-06,
699
+ "loss": 0.1144,
700
+ "step": 980
701
+ },
702
+ {
703
+ "epoch": 0.4583333333333333,
704
+ "grad_norm": 3.0211071968078613,
705
+ "learning_rate": 5.148360229047371e-06,
706
+ "loss": 0.1432,
707
+ "step": 990
708
+ },
709
+ {
710
+ "execution_accuracy": 46.0,
711
+ "selected_difficulty": "overall",
712
+ "step": 1000
713
+ },
714
+ {
715
+ "epoch": 0.46296296296296297,
716
+ "grad_norm": 2.11688232421875,
717
+ "learning_rate": 5.2004164497657475e-06,
718
+ "loss": 0.136,
719
+ "step": 1000
720
+ },
721
+ {
722
+ "epoch": 0.4675925925925926,
723
+ "grad_norm": 2.3399276733398438,
724
+ "learning_rate": 5.252472670484124e-06,
725
+ "loss": 0.1258,
726
+ "step": 1010
727
+ },
728
+ {
729
+ "epoch": 0.4722222222222222,
730
+ "grad_norm": 2.1700856685638428,
731
+ "learning_rate": 5.3045288912025e-06,
732
+ "loss": 0.1278,
733
+ "step": 1020
734
+ },
735
+ {
736
+ "epoch": 0.47685185185185186,
737
+ "grad_norm": 2.491363286972046,
738
+ "learning_rate": 5.356585111920874e-06,
739
+ "loss": 0.1278,
740
+ "step": 1030
741
+ },
742
+ {
743
+ "epoch": 0.48148148148148145,
744
+ "grad_norm": 2.147585868835449,
745
+ "learning_rate": 5.4086413326392505e-06,
746
+ "loss": 0.1263,
747
+ "step": 1040
748
+ },
749
+ {
750
+ "epoch": 0.4861111111111111,
751
+ "grad_norm": 2.3154337406158447,
752
+ "learning_rate": 5.460697553357627e-06,
753
+ "loss": 0.1231,
754
+ "step": 1050
755
+ },
756
+ {
757
+ "epoch": 0.49074074074074076,
758
+ "grad_norm": 2.23714280128479,
759
+ "learning_rate": 5.512753774076003e-06,
760
+ "loss": 0.1396,
761
+ "step": 1060
762
+ },
763
+ {
764
+ "epoch": 0.49537037037037035,
765
+ "grad_norm": 2.789081573486328,
766
+ "learning_rate": 5.564809994794378e-06,
767
+ "loss": 0.1505,
768
+ "step": 1070
769
+ },
770
+ {
771
+ "epoch": 0.5,
772
+ "grad_norm": 2.1684062480926514,
773
+ "learning_rate": 5.616866215512754e-06,
774
+ "loss": 0.128,
775
+ "step": 1080
776
+ },
777
+ {
778
+ "epoch": 0.5046296296296297,
779
+ "grad_norm": 2.603804588317871,
780
+ "learning_rate": 5.6689224362311304e-06,
781
+ "loss": 0.1269,
782
+ "step": 1090
783
+ },
784
+ {
785
+ "epoch": 0.5092592592592593,
786
+ "grad_norm": 1.6282514333724976,
787
+ "learning_rate": 5.720978656949507e-06,
788
+ "loss": 0.1201,
789
+ "step": 1100
790
+ },
791
+ {
792
+ "epoch": 0.5138888888888888,
793
+ "grad_norm": 2.267298460006714,
794
+ "learning_rate": 5.773034877667881e-06,
795
+ "loss": 0.1294,
796
+ "step": 1110
797
+ },
798
+ {
799
+ "epoch": 0.5185185185185185,
800
+ "grad_norm": 2.526259183883667,
801
+ "learning_rate": 5.825091098386257e-06,
802
+ "loss": 0.1263,
803
+ "step": 1120
804
+ },
805
+ {
806
+ "epoch": 0.5231481481481481,
807
+ "grad_norm": 2.38616943359375,
808
+ "learning_rate": 5.877147319104633e-06,
809
+ "loss": 0.1436,
810
+ "step": 1130
811
+ },
812
+ {
813
+ "epoch": 0.5277777777777778,
814
+ "grad_norm": 2.69435715675354,
815
+ "learning_rate": 5.9292035398230096e-06,
816
+ "loss": 0.1374,
817
+ "step": 1140
818
+ },
819
+ {
820
+ "epoch": 0.5324074074074074,
821
+ "grad_norm": 2.2402076721191406,
822
+ "learning_rate": 5.981259760541385e-06,
823
+ "loss": 0.1208,
824
+ "step": 1150
825
+ },
826
+ {
827
+ "epoch": 0.5370370370370371,
828
+ "grad_norm": 2.1587324142456055,
829
+ "learning_rate": 6.033315981259761e-06,
830
+ "loss": 0.1458,
831
+ "step": 1160
832
+ },
833
+ {
834
+ "epoch": 0.5416666666666666,
835
+ "grad_norm": 2.2141196727752686,
836
+ "learning_rate": 6.085372201978137e-06,
837
+ "loss": 0.1193,
838
+ "step": 1170
839
+ },
840
+ {
841
+ "epoch": 0.5462962962962963,
842
+ "grad_norm": 2.2879085540771484,
843
+ "learning_rate": 6.137428422696513e-06,
844
+ "loss": 0.1345,
845
+ "step": 1180
846
+ },
847
+ {
848
+ "epoch": 0.5509259259259259,
849
+ "grad_norm": 3.161435604095459,
850
+ "learning_rate": 6.189484643414888e-06,
851
+ "loss": 0.1319,
852
+ "step": 1190
853
+ },
854
+ {
855
+ "epoch": 0.5555555555555556,
856
+ "grad_norm": 4.313039779663086,
857
+ "learning_rate": 6.241540864133264e-06,
858
+ "loss": 0.1295,
859
+ "step": 1200
860
+ },
861
+ {
862
+ "epoch": 0.5601851851851852,
863
+ "grad_norm": 3.2827019691467285,
864
+ "learning_rate": 6.29359708485164e-06,
865
+ "loss": 0.1335,
866
+ "step": 1210
867
+ },
868
+ {
869
+ "epoch": 0.5648148148148148,
870
+ "grad_norm": 2.1369690895080566,
871
+ "learning_rate": 6.345653305570016e-06,
872
+ "loss": 0.1123,
873
+ "step": 1220
874
+ },
875
+ {
876
+ "epoch": 0.5694444444444444,
877
+ "grad_norm": 2.3678247928619385,
878
+ "learning_rate": 6.397709526288392e-06,
879
+ "loss": 0.1271,
880
+ "step": 1230
881
+ },
882
+ {
883
+ "epoch": 0.5740740740740741,
884
+ "grad_norm": 2.282134771347046,
885
+ "learning_rate": 6.449765747006768e-06,
886
+ "loss": 0.1078,
887
+ "step": 1240
888
+ },
889
+ {
890
+ "epoch": 0.5787037037037037,
891
+ "grad_norm": 2.3011066913604736,
892
+ "learning_rate": 6.501821967725144e-06,
893
+ "loss": 0.1356,
894
+ "step": 1250
895
+ },
896
+ {
897
+ "epoch": 0.5833333333333334,
898
+ "grad_norm": 2.669616460800171,
899
+ "learning_rate": 6.55387818844352e-06,
900
+ "loss": 0.1175,
901
+ "step": 1260
902
+ },
903
+ {
904
+ "epoch": 0.5879629629629629,
905
+ "grad_norm": 2.568129777908325,
906
+ "learning_rate": 6.605934409161895e-06,
907
+ "loss": 0.1168,
908
+ "step": 1270
909
+ },
910
+ {
911
+ "epoch": 0.5925925925925926,
912
+ "grad_norm": 1.9154844284057617,
913
+ "learning_rate": 6.657990629880271e-06,
914
+ "loss": 0.1235,
915
+ "step": 1280
916
+ },
917
+ {
918
+ "epoch": 0.5972222222222222,
919
+ "grad_norm": 2.8254613876342773,
920
+ "learning_rate": 6.710046850598647e-06,
921
+ "loss": 0.1352,
922
+ "step": 1290
923
+ },
924
+ {
925
+ "epoch": 0.6018518518518519,
926
+ "grad_norm": 1.9419591426849365,
927
+ "learning_rate": 6.762103071317023e-06,
928
+ "loss": 0.1196,
929
+ "step": 1300
930
+ },
931
+ {
932
+ "epoch": 0.6064814814814815,
933
+ "grad_norm": 2.1100144386291504,
934
+ "learning_rate": 6.814159292035398e-06,
935
+ "loss": 0.1337,
936
+ "step": 1310
937
+ },
938
+ {
939
+ "epoch": 0.6111111111111112,
940
+ "grad_norm": 2.0183956623077393,
941
+ "learning_rate": 6.8662155127537746e-06,
942
+ "loss": 0.1166,
943
+ "step": 1320
944
+ },
945
+ {
946
+ "epoch": 0.6157407407407407,
947
+ "grad_norm": 2.0606720447540283,
948
+ "learning_rate": 6.918271733472151e-06,
949
+ "loss": 0.1265,
950
+ "step": 1330
951
+ },
952
+ {
953
+ "epoch": 0.6203703703703703,
954
+ "grad_norm": 2.4177541732788086,
955
+ "learning_rate": 6.970327954190527e-06,
956
+ "loss": 0.1276,
957
+ "step": 1340
958
+ },
959
+ {
960
+ "epoch": 0.625,
961
+ "grad_norm": 2.064150810241699,
962
+ "learning_rate": 7.022384174908901e-06,
963
+ "loss": 0.1262,
964
+ "step": 1350
965
+ },
966
+ {
967
+ "epoch": 0.6296296296296297,
968
+ "grad_norm": 1.9812283515930176,
969
+ "learning_rate": 7.0744403956272775e-06,
970
+ "loss": 0.1168,
971
+ "step": 1360
972
+ },
973
+ {
974
+ "epoch": 0.6342592592592593,
975
+ "grad_norm": 2.5228352546691895,
976
+ "learning_rate": 7.126496616345654e-06,
977
+ "loss": 0.126,
978
+ "step": 1370
979
+ },
980
+ {
981
+ "epoch": 0.6388888888888888,
982
+ "grad_norm": 2.5014448165893555,
983
+ "learning_rate": 7.17855283706403e-06,
984
+ "loss": 0.1275,
985
+ "step": 1380
986
+ },
987
+ {
988
+ "epoch": 0.6435185185185185,
989
+ "grad_norm": 2.343454122543335,
990
+ "learning_rate": 7.230609057782405e-06,
991
+ "loss": 0.1288,
992
+ "step": 1390
993
+ },
994
+ {
995
+ "epoch": 0.6481481481481481,
996
+ "grad_norm": 2.2527363300323486,
997
+ "learning_rate": 7.282665278500781e-06,
998
+ "loss": 0.1447,
999
+ "step": 1400
1000
+ },
1001
+ {
1002
+ "epoch": 0.6527777777777778,
1003
+ "grad_norm": 2.631322145462036,
1004
+ "learning_rate": 7.3347214992191575e-06,
1005
+ "loss": 0.1411,
1006
+ "step": 1410
1007
+ },
1008
+ {
1009
+ "epoch": 0.6574074074074074,
1010
+ "grad_norm": 2.194526433944702,
1011
+ "learning_rate": 7.386777719937534e-06,
1012
+ "loss": 0.1314,
1013
+ "step": 1420
1014
+ },
1015
+ {
1016
+ "epoch": 0.6620370370370371,
1017
+ "grad_norm": 1.7892805337905884,
1018
+ "learning_rate": 7.438833940655908e-06,
1019
+ "loss": 0.1237,
1020
+ "step": 1430
1021
+ },
1022
+ {
1023
+ "epoch": 0.6666666666666666,
1024
+ "grad_norm": 2.414116621017456,
1025
+ "learning_rate": 7.490890161374284e-06,
1026
+ "loss": 0.1218,
1027
+ "step": 1440
1028
+ },
1029
+ {
1030
+ "epoch": 0.6712962962962963,
1031
+ "grad_norm": 1.8819609880447388,
1032
+ "learning_rate": 7.5429463820926605e-06,
1033
+ "loss": 0.1196,
1034
+ "step": 1450
1035
+ },
1036
+ {
1037
+ "epoch": 0.6759259259259259,
1038
+ "grad_norm": 2.459386110305786,
1039
+ "learning_rate": 7.595002602811037e-06,
1040
+ "loss": 0.1222,
1041
+ "step": 1460
1042
+ },
1043
+ {
1044
+ "epoch": 0.6805555555555556,
1045
+ "grad_norm": 2.1400787830352783,
1046
+ "learning_rate": 7.647058823529411e-06,
1047
+ "loss": 0.1227,
1048
+ "step": 1470
1049
+ },
1050
+ {
1051
+ "epoch": 0.6851851851851852,
1052
+ "grad_norm": 2.4179768562316895,
1053
+ "learning_rate": 7.699115044247788e-06,
1054
+ "loss": 0.1392,
1055
+ "step": 1480
1056
+ },
1057
+ {
1058
+ "epoch": 0.6898148148148148,
1059
+ "grad_norm": 2.1421689987182617,
1060
+ "learning_rate": 7.751171264966163e-06,
1061
+ "loss": 0.1367,
1062
+ "step": 1490
1063
+ },
1064
+ {
1065
+ "execution_accuracy": 45.0,
1066
+ "selected_difficulty": "overall",
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 0.6944444444444444,
1071
+ "grad_norm": 2.1561977863311768,
1072
+ "learning_rate": 7.80322748568454e-06,
1073
+ "loss": 0.1308,
1074
+ "step": 1500
1075
+ },
1076
+ {
1077
+ "epoch": 0.6990740740740741,
1078
+ "grad_norm": 1.4436249732971191,
1079
+ "learning_rate": 7.855283706402916e-06,
1080
+ "loss": 0.1131,
1081
+ "step": 1510
1082
+ },
1083
+ {
1084
+ "epoch": 0.7037037037037037,
1085
+ "grad_norm": 2.2428104877471924,
1086
+ "learning_rate": 7.907339927121291e-06,
1087
+ "loss": 0.1187,
1088
+ "step": 1520
1089
+ },
1090
+ {
1091
+ "epoch": 0.7083333333333334,
1092
+ "grad_norm": 2.241523265838623,
1093
+ "learning_rate": 7.959396147839668e-06,
1094
+ "loss": 0.1129,
1095
+ "step": 1530
1096
+ },
1097
+ {
1098
+ "epoch": 0.7129629629629629,
1099
+ "grad_norm": 1.6972129344940186,
1100
+ "learning_rate": 8.011452368558043e-06,
1101
+ "loss": 0.1189,
1102
+ "step": 1540
1103
+ },
1104
+ {
1105
+ "epoch": 0.7175925925925926,
1106
+ "grad_norm": 2.174455165863037,
1107
+ "learning_rate": 8.063508589276419e-06,
1108
+ "loss": 0.1186,
1109
+ "step": 1550
1110
+ },
1111
+ {
1112
+ "epoch": 0.7222222222222222,
1113
+ "grad_norm": 2.057164430618286,
1114
+ "learning_rate": 8.115564809994794e-06,
1115
+ "loss": 0.1259,
1116
+ "step": 1560
1117
+ },
1118
+ {
1119
+ "epoch": 0.7268518518518519,
1120
+ "grad_norm": 2.4605278968811035,
1121
+ "learning_rate": 8.167621030713171e-06,
1122
+ "loss": 0.1237,
1123
+ "step": 1570
1124
+ },
1125
+ {
1126
+ "epoch": 0.7314814814814815,
1127
+ "grad_norm": 2.3143205642700195,
1128
+ "learning_rate": 8.219677251431546e-06,
1129
+ "loss": 0.1055,
1130
+ "step": 1580
1131
+ },
1132
+ {
1133
+ "epoch": 0.7361111111111112,
1134
+ "grad_norm": 2.437072992324829,
1135
+ "learning_rate": 8.271733472149922e-06,
1136
+ "loss": 0.1101,
1137
+ "step": 1590
1138
+ },
1139
+ {
1140
+ "epoch": 0.7407407407407407,
1141
+ "grad_norm": 2.146765947341919,
1142
+ "learning_rate": 8.323789692868299e-06,
1143
+ "loss": 0.1127,
1144
+ "step": 1600
1145
+ }
1146
+ ],
1147
+ "logging_steps": 10,
1148
+ "max_steps": 15068,
1149
+ "num_input_tokens_seen": 0,
1150
+ "num_train_epochs": 7,
1151
+ "save_steps": 200,
1152
+ "stateful_callbacks": {
1153
+ "TrainerControl": {
1154
+ "args": {
1155
+ "should_epoch_stop": false,
1156
+ "should_evaluate": false,
1157
+ "should_log": false,
1158
+ "should_save": true,
1159
+ "should_training_stop": false
1160
+ },
1161
+ "attributes": {}
1162
+ }
1163
+ },
1164
+ "total_flos": 6.821775221247181e+17,
1165
+ "train_batch_size": 3,
1166
+ "trial_name": null,
1167
+ "trial_params": null
1168
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58af5cd5c2e854fbf68c3cab2eee37c35425c02a2b7cb9a92b0b6bf6456444bd
3
+ size 5240