Vira21 commited on
Commit
a176bf6
·
verified ·
1 Parent(s): 23d6ff5

Upload 10 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "k_proj",
29
+ "o_proj",
30
+ "gate_proj",
31
+ "v_proj",
32
+ "down_proj",
33
+ "up_proj",
34
+ "q_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c650eb40642ced79e7a8054a6c74d7e40c5c1f2eb5a0a57ffca781a707236cf2
3
+ size 194563400
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3bf1096adbec58045ae73e3c446b4e8a6e31ada5cde9e2fd518fb7176b4373
3
+ size 389352298
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05c7ab158fdc98c1715ee6b1c45c1f7af33d7a79a90dcf2e67b74df334903d9
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d1296eb10a6bf828e418437064f6fc3edff1fc57764995179cf3ce30aff249
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051830f2f6c06d23b79bfeb1cb00c36ab32a29c2905e80e0b8e22148b654ec8b
3
+ size 17210197
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
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|eot_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,3458 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5130746364593506,
3
+ "best_model_checkpoint": "models/khmer-llama32-qa/checkpoint-9000",
4
+ "epoch": 3.0,
5
+ "eval_steps": 1000,
6
+ "global_step": 9591,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.006255864873318737,
13
+ "grad_norm": 3.055704355239868,
14
+ "learning_rate": 4.1666666666666667e-07,
15
+ "loss": 3.599,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.012511729746637473,
20
+ "grad_norm": 3.5084385871887207,
21
+ "learning_rate": 8.333333333333333e-07,
22
+ "loss": 3.6639,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.01876759461995621,
27
+ "grad_norm": 3.2163877487182617,
28
+ "learning_rate": 1.25e-06,
29
+ "loss": 3.6221,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.025023459493274947,
34
+ "grad_norm": 2.483070135116577,
35
+ "learning_rate": 1.6666666666666667e-06,
36
+ "loss": 3.5293,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.03127932436659368,
41
+ "grad_norm": 2.087958335876465,
42
+ "learning_rate": 2.0833333333333334e-06,
43
+ "loss": 3.486,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.03753518923991242,
48
+ "grad_norm": 1.9473289251327515,
49
+ "learning_rate": 2.5e-06,
50
+ "loss": 3.3948,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.043791054113231156,
55
+ "grad_norm": 1.4656407833099365,
56
+ "learning_rate": 2.916666666666667e-06,
57
+ "loss": 3.1533,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.05004691898654989,
62
+ "grad_norm": 1.4900797605514526,
63
+ "learning_rate": 3.3333333333333333e-06,
64
+ "loss": 2.9367,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.05630278385986863,
69
+ "grad_norm": 1.2561100721359253,
70
+ "learning_rate": 3.7500000000000005e-06,
71
+ "loss": 2.8441,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.06255864873318737,
76
+ "grad_norm": 1.502004623413086,
77
+ "learning_rate": 4.166666666666667e-06,
78
+ "loss": 2.6692,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.0688145136065061,
83
+ "grad_norm": 1.1987361907958984,
84
+ "learning_rate": 4.583333333333333e-06,
85
+ "loss": 2.618,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.07507037847982484,
90
+ "grad_norm": 1.2664542198181152,
91
+ "learning_rate": 5e-06,
92
+ "loss": 2.5955,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.08132624335314358,
97
+ "grad_norm": 1.4493029117584229,
98
+ "learning_rate": 5.416666666666667e-06,
99
+ "loss": 2.5506,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.08758210822646231,
104
+ "grad_norm": 1.3738720417022705,
105
+ "learning_rate": 5.833333333333334e-06,
106
+ "loss": 2.5202,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.09383797309978105,
111
+ "grad_norm": 1.5998780727386475,
112
+ "learning_rate": 6.25e-06,
113
+ "loss": 2.4909,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.10009383797309979,
118
+ "grad_norm": 1.4477788209915161,
119
+ "learning_rate": 6.666666666666667e-06,
120
+ "loss": 2.4929,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.10634970284641852,
125
+ "grad_norm": 1.4700181484222412,
126
+ "learning_rate": 7.083333333333335e-06,
127
+ "loss": 2.4574,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.11260556771973726,
132
+ "grad_norm": 1.9266761541366577,
133
+ "learning_rate": 7.500000000000001e-06,
134
+ "loss": 2.4146,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.118861432593056,
139
+ "grad_norm": 2.079688787460327,
140
+ "learning_rate": 7.916666666666667e-06,
141
+ "loss": 2.3837,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.12511729746637473,
146
+ "grad_norm": 1.6938954591751099,
147
+ "learning_rate": 8.333333333333334e-06,
148
+ "loss": 2.3659,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.13137316233969346,
153
+ "grad_norm": 1.6853476762771606,
154
+ "learning_rate": 8.750000000000001e-06,
155
+ "loss": 2.3636,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.1376290272130122,
160
+ "grad_norm": 1.5365005731582642,
161
+ "learning_rate": 9.166666666666666e-06,
162
+ "loss": 2.3139,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.14388489208633093,
167
+ "grad_norm": 1.6722062826156616,
168
+ "learning_rate": 9.583333333333335e-06,
169
+ "loss": 2.3738,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.15014075695964968,
174
+ "grad_norm": 1.6911437511444092,
175
+ "learning_rate": 1e-05,
176
+ "loss": 2.246,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.1563966218329684,
181
+ "grad_norm": 1.9284753799438477,
182
+ "learning_rate": 1.0416666666666668e-05,
183
+ "loss": 2.2457,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.16265248670628715,
188
+ "grad_norm": 1.870841145515442,
189
+ "learning_rate": 1.0833333333333334e-05,
190
+ "loss": 2.1937,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.16890835157960588,
195
+ "grad_norm": 2.1168696880340576,
196
+ "learning_rate": 1.125e-05,
197
+ "loss": 2.2104,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.17516421645292463,
202
+ "grad_norm": 2.3863697052001953,
203
+ "learning_rate": 1.1666666666666668e-05,
204
+ "loss": 2.1708,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.18142008132624335,
209
+ "grad_norm": 2.1332266330718994,
210
+ "learning_rate": 1.2083333333333333e-05,
211
+ "loss": 2.1147,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.1876759461995621,
216
+ "grad_norm": 2.657927989959717,
217
+ "learning_rate": 1.25e-05,
218
+ "loss": 2.1468,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.19393181107288082,
223
+ "grad_norm": 2.723944664001465,
224
+ "learning_rate": 1.2916666666666668e-05,
225
+ "loss": 2.1126,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.20018767594619957,
230
+ "grad_norm": 2.2403364181518555,
231
+ "learning_rate": 1.3333333333333333e-05,
232
+ "loss": 2.132,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.2064435408195183,
237
+ "grad_norm": 2.1621572971343994,
238
+ "learning_rate": 1.375e-05,
239
+ "loss": 2.0652,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 0.21269940569283705,
244
+ "grad_norm": 2.283856153488159,
245
+ "learning_rate": 1.416666666666667e-05,
246
+ "loss": 2.0652,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 0.21895527056615577,
251
+ "grad_norm": 2.3808491230010986,
252
+ "learning_rate": 1.4583333333333333e-05,
253
+ "loss": 2.0647,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 0.22521113543947452,
258
+ "grad_norm": 2.655351400375366,
259
+ "learning_rate": 1.5000000000000002e-05,
260
+ "loss": 2.0804,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 0.23146700031279324,
265
+ "grad_norm": 2.5698490142822266,
266
+ "learning_rate": 1.5416666666666668e-05,
267
+ "loss": 2.0677,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 0.237722865186112,
272
+ "grad_norm": 3.3763697147369385,
273
+ "learning_rate": 1.5833333333333333e-05,
274
+ "loss": 2.0432,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 0.24397873005943072,
279
+ "grad_norm": 2.749903917312622,
280
+ "learning_rate": 1.6250000000000002e-05,
281
+ "loss": 2.0451,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 0.25023459493274947,
286
+ "grad_norm": 3.3386733531951904,
287
+ "learning_rate": 1.6666666666666667e-05,
288
+ "loss": 2.0461,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 0.2564904598060682,
293
+ "grad_norm": 2.211704730987549,
294
+ "learning_rate": 1.7083333333333333e-05,
295
+ "loss": 2.0056,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 0.2627463246793869,
300
+ "grad_norm": 2.886216640472412,
301
+ "learning_rate": 1.7500000000000002e-05,
302
+ "loss": 1.9902,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 0.26900218955270566,
307
+ "grad_norm": 2.8164501190185547,
308
+ "learning_rate": 1.7916666666666667e-05,
309
+ "loss": 2.0382,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 0.2752580544260244,
314
+ "grad_norm": 3.3984410762786865,
315
+ "learning_rate": 1.8333333333333333e-05,
316
+ "loss": 2.0245,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 0.2815139192993431,
321
+ "grad_norm": 2.9318149089813232,
322
+ "learning_rate": 1.8750000000000002e-05,
323
+ "loss": 1.981,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 0.28776978417266186,
328
+ "grad_norm": 2.9568192958831787,
329
+ "learning_rate": 1.916666666666667e-05,
330
+ "loss": 1.981,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 0.2940256490459806,
335
+ "grad_norm": 3.3105645179748535,
336
+ "learning_rate": 1.9583333333333333e-05,
337
+ "loss": 1.9575,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 0.30028151391929936,
342
+ "grad_norm": 3.094958782196045,
343
+ "learning_rate": 2e-05,
344
+ "loss": 2.0318,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 0.30653737879261805,
349
+ "grad_norm": 2.9924981594085693,
350
+ "learning_rate": 1.9953655428107984e-05,
351
+ "loss": 1.9318,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 0.3127932436659368,
356
+ "grad_norm": 3.0640549659729004,
357
+ "learning_rate": 1.9907310856215966e-05,
358
+ "loss": 1.9675,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 0.3127932436659368,
363
+ "eval_loss": 0.6163395643234253,
364
+ "eval_runtime": 30.1355,
365
+ "eval_samples_per_second": 16.061,
366
+ "eval_steps_per_second": 4.015,
367
+ "step": 1000
368
+ },
369
+ {
370
+ "epoch": 0.31904910853925555,
371
+ "grad_norm": 3.016735076904297,
372
+ "learning_rate": 1.986096628432395e-05,
373
+ "loss": 1.9317,
374
+ "step": 1020
375
+ },
376
+ {
377
+ "epoch": 0.3253049734125743,
378
+ "grad_norm": 3.159961462020874,
379
+ "learning_rate": 1.9814621712431933e-05,
380
+ "loss": 1.9003,
381
+ "step": 1040
382
+ },
383
+ {
384
+ "epoch": 0.331560838285893,
385
+ "grad_norm": 3.248335123062134,
386
+ "learning_rate": 1.9768277140539916e-05,
387
+ "loss": 1.9733,
388
+ "step": 1060
389
+ },
390
+ {
391
+ "epoch": 0.33781670315921175,
392
+ "grad_norm": 3.2077865600585938,
393
+ "learning_rate": 1.9721932568647898e-05,
394
+ "loss": 1.8866,
395
+ "step": 1080
396
+ },
397
+ {
398
+ "epoch": 0.3440725680325305,
399
+ "grad_norm": 3.3022334575653076,
400
+ "learning_rate": 1.967558799675588e-05,
401
+ "loss": 1.9616,
402
+ "step": 1100
403
+ },
404
+ {
405
+ "epoch": 0.35032843290584925,
406
+ "grad_norm": 3.258803606033325,
407
+ "learning_rate": 1.9629243424863865e-05,
408
+ "loss": 1.9183,
409
+ "step": 1120
410
+ },
411
+ {
412
+ "epoch": 0.35658429777916795,
413
+ "grad_norm": 3.348259687423706,
414
+ "learning_rate": 1.9582898852971847e-05,
415
+ "loss": 1.8972,
416
+ "step": 1140
417
+ },
418
+ {
419
+ "epoch": 0.3628401626524867,
420
+ "grad_norm": 2.9948360919952393,
421
+ "learning_rate": 1.953655428107983e-05,
422
+ "loss": 1.8953,
423
+ "step": 1160
424
+ },
425
+ {
426
+ "epoch": 0.36909602752580545,
427
+ "grad_norm": 3.072226047515869,
428
+ "learning_rate": 1.949020970918781e-05,
429
+ "loss": 1.909,
430
+ "step": 1180
431
+ },
432
+ {
433
+ "epoch": 0.3753518923991242,
434
+ "grad_norm": 2.7837533950805664,
435
+ "learning_rate": 1.9443865137295797e-05,
436
+ "loss": 1.9396,
437
+ "step": 1200
438
+ },
439
+ {
440
+ "epoch": 0.3816077572724429,
441
+ "grad_norm": 3.2200827598571777,
442
+ "learning_rate": 1.939752056540378e-05,
443
+ "loss": 1.8605,
444
+ "step": 1220
445
+ },
446
+ {
447
+ "epoch": 0.38786362214576164,
448
+ "grad_norm": 2.9632668495178223,
449
+ "learning_rate": 1.935117599351176e-05,
450
+ "loss": 1.8823,
451
+ "step": 1240
452
+ },
453
+ {
454
+ "epoch": 0.3941194870190804,
455
+ "grad_norm": 3.762718915939331,
456
+ "learning_rate": 1.9304831421619747e-05,
457
+ "loss": 1.861,
458
+ "step": 1260
459
+ },
460
+ {
461
+ "epoch": 0.40037535189239915,
462
+ "grad_norm": 3.123317003250122,
463
+ "learning_rate": 1.9258486849727725e-05,
464
+ "loss": 1.8385,
465
+ "step": 1280
466
+ },
467
+ {
468
+ "epoch": 0.40663121676571784,
469
+ "grad_norm": 3.2393641471862793,
470
+ "learning_rate": 1.921214227783571e-05,
471
+ "loss": 1.8507,
472
+ "step": 1300
473
+ },
474
+ {
475
+ "epoch": 0.4128870816390366,
476
+ "grad_norm": 3.06451153755188,
477
+ "learning_rate": 1.9165797705943693e-05,
478
+ "loss": 1.8872,
479
+ "step": 1320
480
+ },
481
+ {
482
+ "epoch": 0.41914294651235534,
483
+ "grad_norm": 3.2108166217803955,
484
+ "learning_rate": 1.9119453134051675e-05,
485
+ "loss": 1.9376,
486
+ "step": 1340
487
+ },
488
+ {
489
+ "epoch": 0.4253988113856741,
490
+ "grad_norm": 3.1738028526306152,
491
+ "learning_rate": 1.907310856215966e-05,
492
+ "loss": 1.8453,
493
+ "step": 1360
494
+ },
495
+ {
496
+ "epoch": 0.4316546762589928,
497
+ "grad_norm": 3.297335147857666,
498
+ "learning_rate": 1.902676399026764e-05,
499
+ "loss": 1.8411,
500
+ "step": 1380
501
+ },
502
+ {
503
+ "epoch": 0.43791054113231154,
504
+ "grad_norm": 3.6973254680633545,
505
+ "learning_rate": 1.8980419418375625e-05,
506
+ "loss": 1.8655,
507
+ "step": 1400
508
+ },
509
+ {
510
+ "epoch": 0.4441664060056303,
511
+ "grad_norm": 3.067793846130371,
512
+ "learning_rate": 1.8934074846483607e-05,
513
+ "loss": 1.8269,
514
+ "step": 1420
515
+ },
516
+ {
517
+ "epoch": 0.45042227087894904,
518
+ "grad_norm": 3.414215564727783,
519
+ "learning_rate": 1.888773027459159e-05,
520
+ "loss": 1.8114,
521
+ "step": 1440
522
+ },
523
+ {
524
+ "epoch": 0.45667813575226773,
525
+ "grad_norm": 3.223034620285034,
526
+ "learning_rate": 1.8841385702699574e-05,
527
+ "loss": 1.8345,
528
+ "step": 1460
529
+ },
530
+ {
531
+ "epoch": 0.4629340006255865,
532
+ "grad_norm": 3.184588670730591,
533
+ "learning_rate": 1.8795041130807557e-05,
534
+ "loss": 1.8334,
535
+ "step": 1480
536
+ },
537
+ {
538
+ "epoch": 0.46918986549890523,
539
+ "grad_norm": 3.343078374862671,
540
+ "learning_rate": 1.874869655891554e-05,
541
+ "loss": 1.7791,
542
+ "step": 1500
543
+ },
544
+ {
545
+ "epoch": 0.475445730372224,
546
+ "grad_norm": 3.3436670303344727,
547
+ "learning_rate": 1.870235198702352e-05,
548
+ "loss": 1.8317,
549
+ "step": 1520
550
+ },
551
+ {
552
+ "epoch": 0.4817015952455427,
553
+ "grad_norm": 3.7679710388183594,
554
+ "learning_rate": 1.8656007415131506e-05,
555
+ "loss": 1.8179,
556
+ "step": 1540
557
+ },
558
+ {
559
+ "epoch": 0.48795746011886143,
560
+ "grad_norm": 3.780228614807129,
561
+ "learning_rate": 1.8609662843239485e-05,
562
+ "loss": 1.8051,
563
+ "step": 1560
564
+ },
565
+ {
566
+ "epoch": 0.4942133249921802,
567
+ "grad_norm": 3.061527729034424,
568
+ "learning_rate": 1.856331827134747e-05,
569
+ "loss": 1.8413,
570
+ "step": 1580
571
+ },
572
+ {
573
+ "epoch": 0.5004691898654989,
574
+ "grad_norm": 3.53220796585083,
575
+ "learning_rate": 1.8516973699455452e-05,
576
+ "loss": 1.8018,
577
+ "step": 1600
578
+ },
579
+ {
580
+ "epoch": 0.5067250547388177,
581
+ "grad_norm": 3.7156918048858643,
582
+ "learning_rate": 1.8470629127563435e-05,
583
+ "loss": 1.771,
584
+ "step": 1620
585
+ },
586
+ {
587
+ "epoch": 0.5129809196121364,
588
+ "grad_norm": 3.174913167953491,
589
+ "learning_rate": 1.842428455567142e-05,
590
+ "loss": 1.792,
591
+ "step": 1640
592
+ },
593
+ {
594
+ "epoch": 0.5192367844854551,
595
+ "grad_norm": 3.3128390312194824,
596
+ "learning_rate": 1.83779399837794e-05,
597
+ "loss": 1.7571,
598
+ "step": 1660
599
+ },
600
+ {
601
+ "epoch": 0.5254926493587738,
602
+ "grad_norm": 3.163397789001465,
603
+ "learning_rate": 1.8331595411887384e-05,
604
+ "loss": 1.8294,
605
+ "step": 1680
606
+ },
607
+ {
608
+ "epoch": 0.5317485142320926,
609
+ "grad_norm": 3.1041367053985596,
610
+ "learning_rate": 1.8285250839995366e-05,
611
+ "loss": 1.7722,
612
+ "step": 1700
613
+ },
614
+ {
615
+ "epoch": 0.5380043791054113,
616
+ "grad_norm": 3.4675991535186768,
617
+ "learning_rate": 1.823890626810335e-05,
618
+ "loss": 1.7617,
619
+ "step": 1720
620
+ },
621
+ {
622
+ "epoch": 0.5442602439787301,
623
+ "grad_norm": 3.572848081588745,
624
+ "learning_rate": 1.8192561696211334e-05,
625
+ "loss": 1.7121,
626
+ "step": 1740
627
+ },
628
+ {
629
+ "epoch": 0.5505161088520488,
630
+ "grad_norm": 3.1788299083709717,
631
+ "learning_rate": 1.8146217124319316e-05,
632
+ "loss": 1.7865,
633
+ "step": 1760
634
+ },
635
+ {
636
+ "epoch": 0.5567719737253676,
637
+ "grad_norm": 3.3534226417541504,
638
+ "learning_rate": 1.8099872552427298e-05,
639
+ "loss": 1.8233,
640
+ "step": 1780
641
+ },
642
+ {
643
+ "epoch": 0.5630278385986862,
644
+ "grad_norm": 3.2126591205596924,
645
+ "learning_rate": 1.805352798053528e-05,
646
+ "loss": 1.7321,
647
+ "step": 1800
648
+ },
649
+ {
650
+ "epoch": 0.569283703472005,
651
+ "grad_norm": 3.1480772495269775,
652
+ "learning_rate": 1.8007183408643266e-05,
653
+ "loss": 1.8045,
654
+ "step": 1820
655
+ },
656
+ {
657
+ "epoch": 0.5755395683453237,
658
+ "grad_norm": 3.242344617843628,
659
+ "learning_rate": 1.7960838836751248e-05,
660
+ "loss": 1.7182,
661
+ "step": 1840
662
+ },
663
+ {
664
+ "epoch": 0.5817954332186425,
665
+ "grad_norm": 3.085733413696289,
666
+ "learning_rate": 1.791449426485923e-05,
667
+ "loss": 1.8152,
668
+ "step": 1860
669
+ },
670
+ {
671
+ "epoch": 0.5880512980919612,
672
+ "grad_norm": 3.510521173477173,
673
+ "learning_rate": 1.7868149692967212e-05,
674
+ "loss": 1.7413,
675
+ "step": 1880
676
+ },
677
+ {
678
+ "epoch": 0.59430716296528,
679
+ "grad_norm": 3.4337544441223145,
680
+ "learning_rate": 1.7821805121075194e-05,
681
+ "loss": 1.8148,
682
+ "step": 1900
683
+ },
684
+ {
685
+ "epoch": 0.6005630278385987,
686
+ "grad_norm": 2.888315200805664,
687
+ "learning_rate": 1.777546054918318e-05,
688
+ "loss": 1.7372,
689
+ "step": 1920
690
+ },
691
+ {
692
+ "epoch": 0.6068188927119175,
693
+ "grad_norm": 3.148432970046997,
694
+ "learning_rate": 1.7729115977291162e-05,
695
+ "loss": 1.8036,
696
+ "step": 1940
697
+ },
698
+ {
699
+ "epoch": 0.6130747575852361,
700
+ "grad_norm": 3.4758594036102295,
701
+ "learning_rate": 1.7682771405399144e-05,
702
+ "loss": 1.7447,
703
+ "step": 1960
704
+ },
705
+ {
706
+ "epoch": 0.6193306224585549,
707
+ "grad_norm": 3.720221519470215,
708
+ "learning_rate": 1.763642683350713e-05,
709
+ "loss": 1.6979,
710
+ "step": 1980
711
+ },
712
+ {
713
+ "epoch": 0.6255864873318736,
714
+ "grad_norm": 3.6428353786468506,
715
+ "learning_rate": 1.7590082261615108e-05,
716
+ "loss": 1.7339,
717
+ "step": 2000
718
+ },
719
+ {
720
+ "epoch": 0.6255864873318736,
721
+ "eval_loss": 0.5785377621650696,
722
+ "eval_runtime": 30.1197,
723
+ "eval_samples_per_second": 16.069,
724
+ "eval_steps_per_second": 4.017,
725
+ "step": 2000
726
+ },
727
+ {
728
+ "epoch": 0.6318423522051924,
729
+ "grad_norm": 3.3335535526275635,
730
+ "learning_rate": 1.7543737689723093e-05,
731
+ "loss": 1.7016,
732
+ "step": 2020
733
+ },
734
+ {
735
+ "epoch": 0.6380982170785111,
736
+ "grad_norm": 2.9847285747528076,
737
+ "learning_rate": 1.7497393117831076e-05,
738
+ "loss": 1.6967,
739
+ "step": 2040
740
+ },
741
+ {
742
+ "epoch": 0.6443540819518299,
743
+ "grad_norm": 3.235311269760132,
744
+ "learning_rate": 1.7451048545939058e-05,
745
+ "loss": 1.733,
746
+ "step": 2060
747
+ },
748
+ {
749
+ "epoch": 0.6506099468251486,
750
+ "grad_norm": 3.2147135734558105,
751
+ "learning_rate": 1.740470397404704e-05,
752
+ "loss": 1.7548,
753
+ "step": 2080
754
+ },
755
+ {
756
+ "epoch": 0.6568658116984674,
757
+ "grad_norm": 3.2119052410125732,
758
+ "learning_rate": 1.7358359402155025e-05,
759
+ "loss": 1.6748,
760
+ "step": 2100
761
+ },
762
+ {
763
+ "epoch": 0.663121676571786,
764
+ "grad_norm": 3.278869390487671,
765
+ "learning_rate": 1.7312014830263007e-05,
766
+ "loss": 1.7599,
767
+ "step": 2120
768
+ },
769
+ {
770
+ "epoch": 0.6693775414451048,
771
+ "grad_norm": 3.781015396118164,
772
+ "learning_rate": 1.726567025837099e-05,
773
+ "loss": 1.7298,
774
+ "step": 2140
775
+ },
776
+ {
777
+ "epoch": 0.6756334063184235,
778
+ "grad_norm": 3.6497671604156494,
779
+ "learning_rate": 1.721932568647897e-05,
780
+ "loss": 1.7324,
781
+ "step": 2160
782
+ },
783
+ {
784
+ "epoch": 0.6818892711917423,
785
+ "grad_norm": 3.0687382221221924,
786
+ "learning_rate": 1.7172981114586954e-05,
787
+ "loss": 1.6643,
788
+ "step": 2180
789
+ },
790
+ {
791
+ "epoch": 0.688145136065061,
792
+ "grad_norm": 3.9177842140197754,
793
+ "learning_rate": 1.712663654269494e-05,
794
+ "loss": 1.6868,
795
+ "step": 2200
796
+ },
797
+ {
798
+ "epoch": 0.6944010009383798,
799
+ "grad_norm": 3.525784969329834,
800
+ "learning_rate": 1.708029197080292e-05,
801
+ "loss": 1.7393,
802
+ "step": 2220
803
+ },
804
+ {
805
+ "epoch": 0.7006568658116985,
806
+ "grad_norm": 3.3422930240631104,
807
+ "learning_rate": 1.7033947398910903e-05,
808
+ "loss": 1.6745,
809
+ "step": 2240
810
+ },
811
+ {
812
+ "epoch": 0.7069127306850173,
813
+ "grad_norm": 3.4408421516418457,
814
+ "learning_rate": 1.698760282701889e-05,
815
+ "loss": 1.7166,
816
+ "step": 2260
817
+ },
818
+ {
819
+ "epoch": 0.7131685955583359,
820
+ "grad_norm": 3.9245855808258057,
821
+ "learning_rate": 1.6941258255126868e-05,
822
+ "loss": 1.7218,
823
+ "step": 2280
824
+ },
825
+ {
826
+ "epoch": 0.7194244604316546,
827
+ "grad_norm": 3.502345561981201,
828
+ "learning_rate": 1.6894913683234853e-05,
829
+ "loss": 1.7191,
830
+ "step": 2300
831
+ },
832
+ {
833
+ "epoch": 0.7256803253049734,
834
+ "grad_norm": 3.451737642288208,
835
+ "learning_rate": 1.6848569111342835e-05,
836
+ "loss": 1.726,
837
+ "step": 2320
838
+ },
839
+ {
840
+ "epoch": 0.7319361901782921,
841
+ "grad_norm": 3.112499952316284,
842
+ "learning_rate": 1.6802224539450817e-05,
843
+ "loss": 1.6989,
844
+ "step": 2340
845
+ },
846
+ {
847
+ "epoch": 0.7381920550516109,
848
+ "grad_norm": 4.081657409667969,
849
+ "learning_rate": 1.6755879967558803e-05,
850
+ "loss": 1.7184,
851
+ "step": 2360
852
+ },
853
+ {
854
+ "epoch": 0.7444479199249296,
855
+ "grad_norm": 3.0992517471313477,
856
+ "learning_rate": 1.6709535395666785e-05,
857
+ "loss": 1.6656,
858
+ "step": 2380
859
+ },
860
+ {
861
+ "epoch": 0.7507037847982484,
862
+ "grad_norm": 3.080566644668579,
863
+ "learning_rate": 1.6663190823774767e-05,
864
+ "loss": 1.6727,
865
+ "step": 2400
866
+ },
867
+ {
868
+ "epoch": 0.7569596496715671,
869
+ "grad_norm": 2.938995361328125,
870
+ "learning_rate": 1.661684625188275e-05,
871
+ "loss": 1.6483,
872
+ "step": 2420
873
+ },
874
+ {
875
+ "epoch": 0.7632155145448858,
876
+ "grad_norm": 3.2587146759033203,
877
+ "learning_rate": 1.657050167999073e-05,
878
+ "loss": 1.6965,
879
+ "step": 2440
880
+ },
881
+ {
882
+ "epoch": 0.7694713794182045,
883
+ "grad_norm": 3.5692856311798096,
884
+ "learning_rate": 1.6524157108098717e-05,
885
+ "loss": 1.7098,
886
+ "step": 2460
887
+ },
888
+ {
889
+ "epoch": 0.7757272442915233,
890
+ "grad_norm": 3.1614418029785156,
891
+ "learning_rate": 1.64778125362067e-05,
892
+ "loss": 1.6576,
893
+ "step": 2480
894
+ },
895
+ {
896
+ "epoch": 0.781983109164842,
897
+ "grad_norm": 3.1559157371520996,
898
+ "learning_rate": 1.643146796431468e-05,
899
+ "loss": 1.6498,
900
+ "step": 2500
901
+ },
902
+ {
903
+ "epoch": 0.7882389740381608,
904
+ "grad_norm": 3.6744728088378906,
905
+ "learning_rate": 1.6385123392422663e-05,
906
+ "loss": 1.6789,
907
+ "step": 2520
908
+ },
909
+ {
910
+ "epoch": 0.7944948389114795,
911
+ "grad_norm": 3.6650450229644775,
912
+ "learning_rate": 1.633877882053065e-05,
913
+ "loss": 1.6372,
914
+ "step": 2540
915
+ },
916
+ {
917
+ "epoch": 0.8007507037847983,
918
+ "grad_norm": 3.7447121143341064,
919
+ "learning_rate": 1.629243424863863e-05,
920
+ "loss": 1.7067,
921
+ "step": 2560
922
+ },
923
+ {
924
+ "epoch": 0.8070065686581169,
925
+ "grad_norm": 3.40779972076416,
926
+ "learning_rate": 1.6246089676746613e-05,
927
+ "loss": 1.6942,
928
+ "step": 2580
929
+ },
930
+ {
931
+ "epoch": 0.8132624335314357,
932
+ "grad_norm": 4.096377849578857,
933
+ "learning_rate": 1.6199745104854595e-05,
934
+ "loss": 1.6124,
935
+ "step": 2600
936
+ },
937
+ {
938
+ "epoch": 0.8195182984047544,
939
+ "grad_norm": 3.5456223487854004,
940
+ "learning_rate": 1.6153400532962577e-05,
941
+ "loss": 1.6957,
942
+ "step": 2620
943
+ },
944
+ {
945
+ "epoch": 0.8257741632780732,
946
+ "grad_norm": 4.157273292541504,
947
+ "learning_rate": 1.6107055961070562e-05,
948
+ "loss": 1.6718,
949
+ "step": 2640
950
+ },
951
+ {
952
+ "epoch": 0.8320300281513919,
953
+ "grad_norm": 3.7936980724334717,
954
+ "learning_rate": 1.6060711389178544e-05,
955
+ "loss": 1.6235,
956
+ "step": 2660
957
+ },
958
+ {
959
+ "epoch": 0.8382858930247107,
960
+ "grad_norm": 3.590808629989624,
961
+ "learning_rate": 1.6014366817286526e-05,
962
+ "loss": 1.6704,
963
+ "step": 2680
964
+ },
965
+ {
966
+ "epoch": 0.8445417578980294,
967
+ "grad_norm": 3.088557243347168,
968
+ "learning_rate": 1.596802224539451e-05,
969
+ "loss": 1.6886,
970
+ "step": 2700
971
+ },
972
+ {
973
+ "epoch": 0.8507976227713482,
974
+ "grad_norm": 3.6176650524139404,
975
+ "learning_rate": 1.592167767350249e-05,
976
+ "loss": 1.6178,
977
+ "step": 2720
978
+ },
979
+ {
980
+ "epoch": 0.8570534876446668,
981
+ "grad_norm": 3.519657611846924,
982
+ "learning_rate": 1.5875333101610476e-05,
983
+ "loss": 1.6596,
984
+ "step": 2740
985
+ },
986
+ {
987
+ "epoch": 0.8633093525179856,
988
+ "grad_norm": 3.0401337146759033,
989
+ "learning_rate": 1.5828988529718458e-05,
990
+ "loss": 1.6518,
991
+ "step": 2760
992
+ },
993
+ {
994
+ "epoch": 0.8695652173913043,
995
+ "grad_norm": 3.584986925125122,
996
+ "learning_rate": 1.578264395782644e-05,
997
+ "loss": 1.6248,
998
+ "step": 2780
999
+ },
1000
+ {
1001
+ "epoch": 0.8758210822646231,
1002
+ "grad_norm": 3.4703197479248047,
1003
+ "learning_rate": 1.5736299385934422e-05,
1004
+ "loss": 1.6753,
1005
+ "step": 2800
1006
+ },
1007
+ {
1008
+ "epoch": 0.8820769471379418,
1009
+ "grad_norm": 3.361783266067505,
1010
+ "learning_rate": 1.5689954814042408e-05,
1011
+ "loss": 1.6769,
1012
+ "step": 2820
1013
+ },
1014
+ {
1015
+ "epoch": 0.8883328120112606,
1016
+ "grad_norm": 3.613750696182251,
1017
+ "learning_rate": 1.564361024215039e-05,
1018
+ "loss": 1.7109,
1019
+ "step": 2840
1020
+ },
1021
+ {
1022
+ "epoch": 0.8945886768845793,
1023
+ "grad_norm": 3.510986566543579,
1024
+ "learning_rate": 1.5597265670258372e-05,
1025
+ "loss": 1.6455,
1026
+ "step": 2860
1027
+ },
1028
+ {
1029
+ "epoch": 0.9008445417578981,
1030
+ "grad_norm": 3.334446668624878,
1031
+ "learning_rate": 1.5550921098366358e-05,
1032
+ "loss": 1.6255,
1033
+ "step": 2880
1034
+ },
1035
+ {
1036
+ "epoch": 0.9071004066312167,
1037
+ "grad_norm": 3.8680272102355957,
1038
+ "learning_rate": 1.5504576526474336e-05,
1039
+ "loss": 1.6302,
1040
+ "step": 2900
1041
+ },
1042
+ {
1043
+ "epoch": 0.9133562715045355,
1044
+ "grad_norm": 3.6026196479797363,
1045
+ "learning_rate": 1.5458231954582322e-05,
1046
+ "loss": 1.6466,
1047
+ "step": 2920
1048
+ },
1049
+ {
1050
+ "epoch": 0.9196121363778542,
1051
+ "grad_norm": 3.609692096710205,
1052
+ "learning_rate": 1.5411887382690304e-05,
1053
+ "loss": 1.633,
1054
+ "step": 2940
1055
+ },
1056
+ {
1057
+ "epoch": 0.925868001251173,
1058
+ "grad_norm": 3.4523870944976807,
1059
+ "learning_rate": 1.5365542810798286e-05,
1060
+ "loss": 1.6967,
1061
+ "step": 2960
1062
+ },
1063
+ {
1064
+ "epoch": 0.9321238661244917,
1065
+ "grad_norm": 3.257688283920288,
1066
+ "learning_rate": 1.531919823890627e-05,
1067
+ "loss": 1.6019,
1068
+ "step": 2980
1069
+ },
1070
+ {
1071
+ "epoch": 0.9383797309978105,
1072
+ "grad_norm": 3.10917067527771,
1073
+ "learning_rate": 1.527285366701425e-05,
1074
+ "loss": 1.6436,
1075
+ "step": 3000
1076
+ },
1077
+ {
1078
+ "epoch": 0.9383797309978105,
1079
+ "eval_loss": 0.5556857585906982,
1080
+ "eval_runtime": 30.1131,
1081
+ "eval_samples_per_second": 16.073,
1082
+ "eval_steps_per_second": 4.018,
1083
+ "step": 3000
1084
+ },
1085
+ {
1086
+ "epoch": 0.9446355958711292,
1087
+ "grad_norm": 3.7206368446350098,
1088
+ "learning_rate": 1.5226509095122236e-05,
1089
+ "loss": 1.6323,
1090
+ "step": 3020
1091
+ },
1092
+ {
1093
+ "epoch": 0.950891460744448,
1094
+ "grad_norm": 3.273854970932007,
1095
+ "learning_rate": 1.518016452323022e-05,
1096
+ "loss": 1.6645,
1097
+ "step": 3040
1098
+ },
1099
+ {
1100
+ "epoch": 0.9571473256177666,
1101
+ "grad_norm": 3.4478001594543457,
1102
+ "learning_rate": 1.51338199513382e-05,
1103
+ "loss": 1.6323,
1104
+ "step": 3060
1105
+ },
1106
+ {
1107
+ "epoch": 0.9634031904910854,
1108
+ "grad_norm": 3.5107407569885254,
1109
+ "learning_rate": 1.5087475379446184e-05,
1110
+ "loss": 1.6106,
1111
+ "step": 3080
1112
+ },
1113
+ {
1114
+ "epoch": 0.9696590553644041,
1115
+ "grad_norm": 3.4260244369506836,
1116
+ "learning_rate": 1.5041130807554167e-05,
1117
+ "loss": 1.6129,
1118
+ "step": 3100
1119
+ },
1120
+ {
1121
+ "epoch": 0.9759149202377229,
1122
+ "grad_norm": 3.3112871646881104,
1123
+ "learning_rate": 1.499478623566215e-05,
1124
+ "loss": 1.6468,
1125
+ "step": 3120
1126
+ },
1127
+ {
1128
+ "epoch": 0.9821707851110416,
1129
+ "grad_norm": 3.370237112045288,
1130
+ "learning_rate": 1.4948441663770132e-05,
1131
+ "loss": 1.6002,
1132
+ "step": 3140
1133
+ },
1134
+ {
1135
+ "epoch": 0.9884266499843604,
1136
+ "grad_norm": 2.750504732131958,
1137
+ "learning_rate": 1.4902097091878115e-05,
1138
+ "loss": 1.6065,
1139
+ "step": 3160
1140
+ },
1141
+ {
1142
+ "epoch": 0.9946825148576791,
1143
+ "grad_norm": 4.291706085205078,
1144
+ "learning_rate": 1.4855752519986097e-05,
1145
+ "loss": 1.5884,
1146
+ "step": 3180
1147
+ },
1148
+ {
1149
+ "epoch": 1.0009383797309979,
1150
+ "grad_norm": 3.447493553161621,
1151
+ "learning_rate": 1.4809407948094081e-05,
1152
+ "loss": 1.6045,
1153
+ "step": 3200
1154
+ },
1155
+ {
1156
+ "epoch": 1.0071942446043165,
1157
+ "grad_norm": 3.561293125152588,
1158
+ "learning_rate": 1.4763063376202062e-05,
1159
+ "loss": 1.601,
1160
+ "step": 3220
1161
+ },
1162
+ {
1163
+ "epoch": 1.0134501094776354,
1164
+ "grad_norm": 3.4609010219573975,
1165
+ "learning_rate": 1.4716718804310045e-05,
1166
+ "loss": 1.5634,
1167
+ "step": 3240
1168
+ },
1169
+ {
1170
+ "epoch": 1.019705974350954,
1171
+ "grad_norm": 3.336390733718872,
1172
+ "learning_rate": 1.467037423241803e-05,
1173
+ "loss": 1.6336,
1174
+ "step": 3260
1175
+ },
1176
+ {
1177
+ "epoch": 1.0259618392242729,
1178
+ "grad_norm": 3.7268803119659424,
1179
+ "learning_rate": 1.4624029660526011e-05,
1180
+ "loss": 1.5949,
1181
+ "step": 3280
1182
+ },
1183
+ {
1184
+ "epoch": 1.0322177040975915,
1185
+ "grad_norm": 3.0219619274139404,
1186
+ "learning_rate": 1.4577685088633995e-05,
1187
+ "loss": 1.5786,
1188
+ "step": 3300
1189
+ },
1190
+ {
1191
+ "epoch": 1.0384735689709101,
1192
+ "grad_norm": 3.6862988471984863,
1193
+ "learning_rate": 1.4531340516741979e-05,
1194
+ "loss": 1.5208,
1195
+ "step": 3320
1196
+ },
1197
+ {
1198
+ "epoch": 1.044729433844229,
1199
+ "grad_norm": 3.8871073722839355,
1200
+ "learning_rate": 1.448499594484996e-05,
1201
+ "loss": 1.594,
1202
+ "step": 3340
1203
+ },
1204
+ {
1205
+ "epoch": 1.0509852987175476,
1206
+ "grad_norm": 3.6962697505950928,
1207
+ "learning_rate": 1.4438651372957943e-05,
1208
+ "loss": 1.5132,
1209
+ "step": 3360
1210
+ },
1211
+ {
1212
+ "epoch": 1.0572411635908665,
1213
+ "grad_norm": 3.7267775535583496,
1214
+ "learning_rate": 1.4392306801065927e-05,
1215
+ "loss": 1.5618,
1216
+ "step": 3380
1217
+ },
1218
+ {
1219
+ "epoch": 1.0634970284641851,
1220
+ "grad_norm": 3.993413209915161,
1221
+ "learning_rate": 1.4345962229173909e-05,
1222
+ "loss": 1.5639,
1223
+ "step": 3400
1224
+ },
1225
+ {
1226
+ "epoch": 1.069752893337504,
1227
+ "grad_norm": 3.4021973609924316,
1228
+ "learning_rate": 1.4299617657281893e-05,
1229
+ "loss": 1.591,
1230
+ "step": 3420
1231
+ },
1232
+ {
1233
+ "epoch": 1.0760087582108226,
1234
+ "grad_norm": 3.457179307937622,
1235
+ "learning_rate": 1.4253273085389877e-05,
1236
+ "loss": 1.5748,
1237
+ "step": 3440
1238
+ },
1239
+ {
1240
+ "epoch": 1.0822646230841413,
1241
+ "grad_norm": 3.792189836502075,
1242
+ "learning_rate": 1.4206928513497857e-05,
1243
+ "loss": 1.5604,
1244
+ "step": 3460
1245
+ },
1246
+ {
1247
+ "epoch": 1.0885204879574601,
1248
+ "grad_norm": 3.5839691162109375,
1249
+ "learning_rate": 1.416058394160584e-05,
1250
+ "loss": 1.5709,
1251
+ "step": 3480
1252
+ },
1253
+ {
1254
+ "epoch": 1.0947763528307788,
1255
+ "grad_norm": 3.1503920555114746,
1256
+ "learning_rate": 1.4114239369713823e-05,
1257
+ "loss": 1.6201,
1258
+ "step": 3500
1259
+ },
1260
+ {
1261
+ "epoch": 1.1010322177040976,
1262
+ "grad_norm": 3.971402645111084,
1263
+ "learning_rate": 1.4067894797821807e-05,
1264
+ "loss": 1.6339,
1265
+ "step": 3520
1266
+ },
1267
+ {
1268
+ "epoch": 1.1072880825774163,
1269
+ "grad_norm": 2.93398118019104,
1270
+ "learning_rate": 1.402155022592979e-05,
1271
+ "loss": 1.6061,
1272
+ "step": 3540
1273
+ },
1274
+ {
1275
+ "epoch": 1.1135439474507351,
1276
+ "grad_norm": 3.298301935195923,
1277
+ "learning_rate": 1.3975205654037771e-05,
1278
+ "loss": 1.5666,
1279
+ "step": 3560
1280
+ },
1281
+ {
1282
+ "epoch": 1.1197998123240538,
1283
+ "grad_norm": 3.154184341430664,
1284
+ "learning_rate": 1.3928861082145755e-05,
1285
+ "loss": 1.5712,
1286
+ "step": 3580
1287
+ },
1288
+ {
1289
+ "epoch": 1.1260556771973724,
1290
+ "grad_norm": 4.005284309387207,
1291
+ "learning_rate": 1.3882516510253738e-05,
1292
+ "loss": 1.5215,
1293
+ "step": 3600
1294
+ },
1295
+ {
1296
+ "epoch": 1.1323115420706913,
1297
+ "grad_norm": 4.161669731140137,
1298
+ "learning_rate": 1.383617193836172e-05,
1299
+ "loss": 1.5316,
1300
+ "step": 3620
1301
+ },
1302
+ {
1303
+ "epoch": 1.13856740694401,
1304
+ "grad_norm": 3.5575239658355713,
1305
+ "learning_rate": 1.3789827366469704e-05,
1306
+ "loss": 1.5181,
1307
+ "step": 3640
1308
+ },
1309
+ {
1310
+ "epoch": 1.1448232718173288,
1311
+ "grad_norm": 3.849310874938965,
1312
+ "learning_rate": 1.3743482794577686e-05,
1313
+ "loss": 1.553,
1314
+ "step": 3660
1315
+ },
1316
+ {
1317
+ "epoch": 1.1510791366906474,
1318
+ "grad_norm": 4.078603744506836,
1319
+ "learning_rate": 1.3697138222685669e-05,
1320
+ "loss": 1.6065,
1321
+ "step": 3680
1322
+ },
1323
+ {
1324
+ "epoch": 1.1573350015639663,
1325
+ "grad_norm": 3.6123812198638916,
1326
+ "learning_rate": 1.3650793650793652e-05,
1327
+ "loss": 1.6441,
1328
+ "step": 3700
1329
+ },
1330
+ {
1331
+ "epoch": 1.163590866437285,
1332
+ "grad_norm": 4.202884674072266,
1333
+ "learning_rate": 1.3604449078901634e-05,
1334
+ "loss": 1.5529,
1335
+ "step": 3720
1336
+ },
1337
+ {
1338
+ "epoch": 1.1698467313106038,
1339
+ "grad_norm": 3.2778208255767822,
1340
+ "learning_rate": 1.3558104507009617e-05,
1341
+ "loss": 1.5742,
1342
+ "step": 3740
1343
+ },
1344
+ {
1345
+ "epoch": 1.1761025961839224,
1346
+ "grad_norm": 4.048972129821777,
1347
+ "learning_rate": 1.35117599351176e-05,
1348
+ "loss": 1.5131,
1349
+ "step": 3760
1350
+ },
1351
+ {
1352
+ "epoch": 1.182358461057241,
1353
+ "grad_norm": 3.4141221046447754,
1354
+ "learning_rate": 1.3465415363225582e-05,
1355
+ "loss": 1.5249,
1356
+ "step": 3780
1357
+ },
1358
+ {
1359
+ "epoch": 1.18861432593056,
1360
+ "grad_norm": 4.267421722412109,
1361
+ "learning_rate": 1.3419070791333566e-05,
1362
+ "loss": 1.5395,
1363
+ "step": 3800
1364
+ },
1365
+ {
1366
+ "epoch": 1.1948701908038786,
1367
+ "grad_norm": 3.1491217613220215,
1368
+ "learning_rate": 1.337272621944155e-05,
1369
+ "loss": 1.5512,
1370
+ "step": 3820
1371
+ },
1372
+ {
1373
+ "epoch": 1.2011260556771974,
1374
+ "grad_norm": 3.626814365386963,
1375
+ "learning_rate": 1.332638164754953e-05,
1376
+ "loss": 1.5097,
1377
+ "step": 3840
1378
+ },
1379
+ {
1380
+ "epoch": 1.207381920550516,
1381
+ "grad_norm": 3.499701738357544,
1382
+ "learning_rate": 1.3280037075657514e-05,
1383
+ "loss": 1.5498,
1384
+ "step": 3860
1385
+ },
1386
+ {
1387
+ "epoch": 1.213637785423835,
1388
+ "grad_norm": 3.646066188812256,
1389
+ "learning_rate": 1.3233692503765498e-05,
1390
+ "loss": 1.5804,
1391
+ "step": 3880
1392
+ },
1393
+ {
1394
+ "epoch": 1.2198936502971536,
1395
+ "grad_norm": 3.6452980041503906,
1396
+ "learning_rate": 1.318734793187348e-05,
1397
+ "loss": 1.6128,
1398
+ "step": 3900
1399
+ },
1400
+ {
1401
+ "epoch": 1.2261495151704724,
1402
+ "grad_norm": 3.4716873168945312,
1403
+ "learning_rate": 1.3141003359981464e-05,
1404
+ "loss": 1.5725,
1405
+ "step": 3920
1406
+ },
1407
+ {
1408
+ "epoch": 1.232405380043791,
1409
+ "grad_norm": 3.3494322299957275,
1410
+ "learning_rate": 1.3094658788089448e-05,
1411
+ "loss": 1.539,
1412
+ "step": 3940
1413
+ },
1414
+ {
1415
+ "epoch": 1.2386612449171097,
1416
+ "grad_norm": 3.9730496406555176,
1417
+ "learning_rate": 1.3048314216197428e-05,
1418
+ "loss": 1.5518,
1419
+ "step": 3960
1420
+ },
1421
+ {
1422
+ "epoch": 1.2449171097904286,
1423
+ "grad_norm": 3.71327805519104,
1424
+ "learning_rate": 1.3001969644305412e-05,
1425
+ "loss": 1.5592,
1426
+ "step": 3980
1427
+ },
1428
+ {
1429
+ "epoch": 1.2511729746637472,
1430
+ "grad_norm": 3.4022958278656006,
1431
+ "learning_rate": 1.2955625072413394e-05,
1432
+ "loss": 1.5271,
1433
+ "step": 4000
1434
+ },
1435
+ {
1436
+ "epoch": 1.2511729746637472,
1437
+ "eval_loss": 0.5431435704231262,
1438
+ "eval_runtime": 30.1654,
1439
+ "eval_samples_per_second": 16.045,
1440
+ "eval_steps_per_second": 4.011,
1441
+ "step": 4000
1442
+ },
1443
+ {
1444
+ "epoch": 1.257428839537066,
1445
+ "grad_norm": 4.227381229400635,
1446
+ "learning_rate": 1.2909280500521378e-05,
1447
+ "loss": 1.4989,
1448
+ "step": 4020
1449
+ },
1450
+ {
1451
+ "epoch": 1.2636847044103847,
1452
+ "grad_norm": 3.459625720977783,
1453
+ "learning_rate": 1.2862935928629362e-05,
1454
+ "loss": 1.5381,
1455
+ "step": 4040
1456
+ },
1457
+ {
1458
+ "epoch": 1.2699405692837034,
1459
+ "grad_norm": 3.8662827014923096,
1460
+ "learning_rate": 1.2816591356737342e-05,
1461
+ "loss": 1.5592,
1462
+ "step": 4060
1463
+ },
1464
+ {
1465
+ "epoch": 1.2761964341570222,
1466
+ "grad_norm": 3.6900293827056885,
1467
+ "learning_rate": 1.2770246784845326e-05,
1468
+ "loss": 1.542,
1469
+ "step": 4080
1470
+ },
1471
+ {
1472
+ "epoch": 1.282452299030341,
1473
+ "grad_norm": 3.6139461994171143,
1474
+ "learning_rate": 1.272390221295331e-05,
1475
+ "loss": 1.5312,
1476
+ "step": 4100
1477
+ },
1478
+ {
1479
+ "epoch": 1.2887081639036597,
1480
+ "grad_norm": 4.2868332862854,
1481
+ "learning_rate": 1.2677557641061292e-05,
1482
+ "loss": 1.5769,
1483
+ "step": 4120
1484
+ },
1485
+ {
1486
+ "epoch": 1.2949640287769784,
1487
+ "grad_norm": 3.5073251724243164,
1488
+ "learning_rate": 1.2631213069169275e-05,
1489
+ "loss": 1.5122,
1490
+ "step": 4140
1491
+ },
1492
+ {
1493
+ "epoch": 1.3012198936502972,
1494
+ "grad_norm": 3.2796294689178467,
1495
+ "learning_rate": 1.2584868497277258e-05,
1496
+ "loss": 1.5677,
1497
+ "step": 4160
1498
+ },
1499
+ {
1500
+ "epoch": 1.3074757585236159,
1501
+ "grad_norm": 4.9055376052856445,
1502
+ "learning_rate": 1.253852392538524e-05,
1503
+ "loss": 1.5355,
1504
+ "step": 4180
1505
+ },
1506
+ {
1507
+ "epoch": 1.3137316233969347,
1508
+ "grad_norm": 3.3482460975646973,
1509
+ "learning_rate": 1.2492179353493223e-05,
1510
+ "loss": 1.5339,
1511
+ "step": 4200
1512
+ },
1513
+ {
1514
+ "epoch": 1.3199874882702534,
1515
+ "grad_norm": 3.3556487560272217,
1516
+ "learning_rate": 1.2445834781601207e-05,
1517
+ "loss": 1.5132,
1518
+ "step": 4220
1519
+ },
1520
+ {
1521
+ "epoch": 1.326243353143572,
1522
+ "grad_norm": 3.3929593563079834,
1523
+ "learning_rate": 1.2399490209709188e-05,
1524
+ "loss": 1.5163,
1525
+ "step": 4240
1526
+ },
1527
+ {
1528
+ "epoch": 1.3324992180168909,
1529
+ "grad_norm": 3.4471447467803955,
1530
+ "learning_rate": 1.2353145637817171e-05,
1531
+ "loss": 1.5829,
1532
+ "step": 4260
1533
+ },
1534
+ {
1535
+ "epoch": 1.3387550828902095,
1536
+ "grad_norm": 4.140485763549805,
1537
+ "learning_rate": 1.2306801065925154e-05,
1538
+ "loss": 1.4735,
1539
+ "step": 4280
1540
+ },
1541
+ {
1542
+ "epoch": 1.3450109477635284,
1543
+ "grad_norm": 3.6784679889678955,
1544
+ "learning_rate": 1.2260456494033137e-05,
1545
+ "loss": 1.5415,
1546
+ "step": 4300
1547
+ },
1548
+ {
1549
+ "epoch": 1.351266812636847,
1550
+ "grad_norm": 3.488356113433838,
1551
+ "learning_rate": 1.2214111922141121e-05,
1552
+ "loss": 1.5178,
1553
+ "step": 4320
1554
+ },
1555
+ {
1556
+ "epoch": 1.3575226775101656,
1557
+ "grad_norm": 3.4582056999206543,
1558
+ "learning_rate": 1.2167767350249102e-05,
1559
+ "loss": 1.5464,
1560
+ "step": 4340
1561
+ },
1562
+ {
1563
+ "epoch": 1.3637785423834845,
1564
+ "grad_norm": 3.233997344970703,
1565
+ "learning_rate": 1.2121422778357085e-05,
1566
+ "loss": 1.5184,
1567
+ "step": 4360
1568
+ },
1569
+ {
1570
+ "epoch": 1.3700344072568034,
1571
+ "grad_norm": 4.5231547355651855,
1572
+ "learning_rate": 1.2075078206465069e-05,
1573
+ "loss": 1.5492,
1574
+ "step": 4380
1575
+ },
1576
+ {
1577
+ "epoch": 1.376290272130122,
1578
+ "grad_norm": 3.368537425994873,
1579
+ "learning_rate": 1.2028733634573051e-05,
1580
+ "loss": 1.5519,
1581
+ "step": 4400
1582
+ },
1583
+ {
1584
+ "epoch": 1.3825461370034406,
1585
+ "grad_norm": 3.618436336517334,
1586
+ "learning_rate": 1.1982389062681035e-05,
1587
+ "loss": 1.5166,
1588
+ "step": 4420
1589
+ },
1590
+ {
1591
+ "epoch": 1.3888020018767595,
1592
+ "grad_norm": 3.74650502204895,
1593
+ "learning_rate": 1.1936044490789019e-05,
1594
+ "loss": 1.5313,
1595
+ "step": 4440
1596
+ },
1597
+ {
1598
+ "epoch": 1.3950578667500781,
1599
+ "grad_norm": 3.186457395553589,
1600
+ "learning_rate": 1.1889699918897e-05,
1601
+ "loss": 1.502,
1602
+ "step": 4460
1603
+ },
1604
+ {
1605
+ "epoch": 1.401313731623397,
1606
+ "grad_norm": 3.0362093448638916,
1607
+ "learning_rate": 1.1843355347004983e-05,
1608
+ "loss": 1.507,
1609
+ "step": 4480
1610
+ },
1611
+ {
1612
+ "epoch": 1.4075695964967156,
1613
+ "grad_norm": 3.121917486190796,
1614
+ "learning_rate": 1.1797010775112965e-05,
1615
+ "loss": 1.5148,
1616
+ "step": 4500
1617
+ },
1618
+ {
1619
+ "epoch": 1.4138254613700343,
1620
+ "grad_norm": 3.965427875518799,
1621
+ "learning_rate": 1.1750666203220949e-05,
1622
+ "loss": 1.5764,
1623
+ "step": 4520
1624
+ },
1625
+ {
1626
+ "epoch": 1.4200813262433531,
1627
+ "grad_norm": 4.197850227355957,
1628
+ "learning_rate": 1.1704321631328933e-05,
1629
+ "loss": 1.5838,
1630
+ "step": 4540
1631
+ },
1632
+ {
1633
+ "epoch": 1.426337191116672,
1634
+ "grad_norm": 3.8980863094329834,
1635
+ "learning_rate": 1.1657977059436913e-05,
1636
+ "loss": 1.5039,
1637
+ "step": 4560
1638
+ },
1639
+ {
1640
+ "epoch": 1.4325930559899906,
1641
+ "grad_norm": 3.8204169273376465,
1642
+ "learning_rate": 1.1611632487544897e-05,
1643
+ "loss": 1.5211,
1644
+ "step": 4580
1645
+ },
1646
+ {
1647
+ "epoch": 1.4388489208633093,
1648
+ "grad_norm": 4.281759262084961,
1649
+ "learning_rate": 1.156528791565288e-05,
1650
+ "loss": 1.5597,
1651
+ "step": 4600
1652
+ },
1653
+ {
1654
+ "epoch": 1.4451047857366282,
1655
+ "grad_norm": 3.467996835708618,
1656
+ "learning_rate": 1.1518943343760863e-05,
1657
+ "loss": 1.4983,
1658
+ "step": 4620
1659
+ },
1660
+ {
1661
+ "epoch": 1.4513606506099468,
1662
+ "grad_norm": 3.524231195449829,
1663
+ "learning_rate": 1.1472598771868847e-05,
1664
+ "loss": 1.488,
1665
+ "step": 4640
1666
+ },
1667
+ {
1668
+ "epoch": 1.4576165154832657,
1669
+ "grad_norm": 3.9286301136016846,
1670
+ "learning_rate": 1.142625419997683e-05,
1671
+ "loss": 1.5314,
1672
+ "step": 4660
1673
+ },
1674
+ {
1675
+ "epoch": 1.4638723803565843,
1676
+ "grad_norm": 3.6402275562286377,
1677
+ "learning_rate": 1.137990962808481e-05,
1678
+ "loss": 1.4996,
1679
+ "step": 4680
1680
+ },
1681
+ {
1682
+ "epoch": 1.470128245229903,
1683
+ "grad_norm": 3.587326765060425,
1684
+ "learning_rate": 1.1333565056192795e-05,
1685
+ "loss": 1.5019,
1686
+ "step": 4700
1687
+ },
1688
+ {
1689
+ "epoch": 1.4763841101032218,
1690
+ "grad_norm": 3.7835605144500732,
1691
+ "learning_rate": 1.1287220484300778e-05,
1692
+ "loss": 1.5088,
1693
+ "step": 4720
1694
+ },
1695
+ {
1696
+ "epoch": 1.4826399749765404,
1697
+ "grad_norm": 3.7514798641204834,
1698
+ "learning_rate": 1.124087591240876e-05,
1699
+ "loss": 1.5111,
1700
+ "step": 4740
1701
+ },
1702
+ {
1703
+ "epoch": 1.4888958398498593,
1704
+ "grad_norm": 3.885326623916626,
1705
+ "learning_rate": 1.1194531340516743e-05,
1706
+ "loss": 1.5366,
1707
+ "step": 4760
1708
+ },
1709
+ {
1710
+ "epoch": 1.495151704723178,
1711
+ "grad_norm": 3.762674331665039,
1712
+ "learning_rate": 1.1148186768624725e-05,
1713
+ "loss": 1.5278,
1714
+ "step": 4780
1715
+ },
1716
+ {
1717
+ "epoch": 1.5014075695964966,
1718
+ "grad_norm": 4.042783260345459,
1719
+ "learning_rate": 1.1101842196732708e-05,
1720
+ "loss": 1.5166,
1721
+ "step": 4800
1722
+ },
1723
+ {
1724
+ "epoch": 1.5076634344698154,
1725
+ "grad_norm": 4.318854331970215,
1726
+ "learning_rate": 1.1055497624840692e-05,
1727
+ "loss": 1.4609,
1728
+ "step": 4820
1729
+ },
1730
+ {
1731
+ "epoch": 1.5139192993431343,
1732
+ "grad_norm": 3.423506498336792,
1733
+ "learning_rate": 1.1009153052948673e-05,
1734
+ "loss": 1.5034,
1735
+ "step": 4840
1736
+ },
1737
+ {
1738
+ "epoch": 1.520175164216453,
1739
+ "grad_norm": 3.9718987941741943,
1740
+ "learning_rate": 1.0962808481056656e-05,
1741
+ "loss": 1.4938,
1742
+ "step": 4860
1743
+ },
1744
+ {
1745
+ "epoch": 1.5264310290897716,
1746
+ "grad_norm": 3.8156068325042725,
1747
+ "learning_rate": 1.091646390916464e-05,
1748
+ "loss": 1.5344,
1749
+ "step": 4880
1750
+ },
1751
+ {
1752
+ "epoch": 1.5326868939630904,
1753
+ "grad_norm": 3.734156370162964,
1754
+ "learning_rate": 1.0870119337272622e-05,
1755
+ "loss": 1.4922,
1756
+ "step": 4900
1757
+ },
1758
+ {
1759
+ "epoch": 1.5389427588364093,
1760
+ "grad_norm": 3.59214186668396,
1761
+ "learning_rate": 1.0823774765380606e-05,
1762
+ "loss": 1.5005,
1763
+ "step": 4920
1764
+ },
1765
+ {
1766
+ "epoch": 1.545198623709728,
1767
+ "grad_norm": 3.830472946166992,
1768
+ "learning_rate": 1.077743019348859e-05,
1769
+ "loss": 1.435,
1770
+ "step": 4940
1771
+ },
1772
+ {
1773
+ "epoch": 1.5514544885830466,
1774
+ "grad_norm": 3.512565851211548,
1775
+ "learning_rate": 1.073108562159657e-05,
1776
+ "loss": 1.5366,
1777
+ "step": 4960
1778
+ },
1779
+ {
1780
+ "epoch": 1.5577103534563652,
1781
+ "grad_norm": 4.332693576812744,
1782
+ "learning_rate": 1.0684741049704554e-05,
1783
+ "loss": 1.5388,
1784
+ "step": 4980
1785
+ },
1786
+ {
1787
+ "epoch": 1.563966218329684,
1788
+ "grad_norm": 4.484791278839111,
1789
+ "learning_rate": 1.0638396477812538e-05,
1790
+ "loss": 1.4778,
1791
+ "step": 5000
1792
+ },
1793
+ {
1794
+ "epoch": 1.563966218329684,
1795
+ "eval_loss": 0.5325935482978821,
1796
+ "eval_runtime": 30.2979,
1797
+ "eval_samples_per_second": 15.975,
1798
+ "eval_steps_per_second": 3.994,
1799
+ "step": 5000
1800
+ },
1801
+ {
1802
+ "epoch": 1.570222083203003,
1803
+ "grad_norm": 3.519361972808838,
1804
+ "learning_rate": 1.059205190592052e-05,
1805
+ "loss": 1.5333,
1806
+ "step": 5020
1807
+ },
1808
+ {
1809
+ "epoch": 1.5764779480763216,
1810
+ "grad_norm": 4.101566791534424,
1811
+ "learning_rate": 1.0545707334028504e-05,
1812
+ "loss": 1.4594,
1813
+ "step": 5040
1814
+ },
1815
+ {
1816
+ "epoch": 1.5827338129496402,
1817
+ "grad_norm": 3.4529476165771484,
1818
+ "learning_rate": 1.0499362762136484e-05,
1819
+ "loss": 1.5263,
1820
+ "step": 5060
1821
+ },
1822
+ {
1823
+ "epoch": 1.588989677822959,
1824
+ "grad_norm": 3.918497085571289,
1825
+ "learning_rate": 1.0453018190244468e-05,
1826
+ "loss": 1.5055,
1827
+ "step": 5080
1828
+ },
1829
+ {
1830
+ "epoch": 1.5952455426962777,
1831
+ "grad_norm": 4.017299175262451,
1832
+ "learning_rate": 1.0406673618352452e-05,
1833
+ "loss": 1.5578,
1834
+ "step": 5100
1835
+ },
1836
+ {
1837
+ "epoch": 1.6015014075695966,
1838
+ "grad_norm": 3.6538748741149902,
1839
+ "learning_rate": 1.0360329046460434e-05,
1840
+ "loss": 1.4732,
1841
+ "step": 5120
1842
+ },
1843
+ {
1844
+ "epoch": 1.6077572724429152,
1845
+ "grad_norm": 3.3641505241394043,
1846
+ "learning_rate": 1.0313984474568418e-05,
1847
+ "loss": 1.5595,
1848
+ "step": 5140
1849
+ },
1850
+ {
1851
+ "epoch": 1.6140131373162339,
1852
+ "grad_norm": 4.010868549346924,
1853
+ "learning_rate": 1.0267639902676401e-05,
1854
+ "loss": 1.4979,
1855
+ "step": 5160
1856
+ },
1857
+ {
1858
+ "epoch": 1.6202690021895527,
1859
+ "grad_norm": 3.882277488708496,
1860
+ "learning_rate": 1.0221295330784382e-05,
1861
+ "loss": 1.4327,
1862
+ "step": 5180
1863
+ },
1864
+ {
1865
+ "epoch": 1.6265248670628716,
1866
+ "grad_norm": 3.3188819885253906,
1867
+ "learning_rate": 1.0174950758892366e-05,
1868
+ "loss": 1.499,
1869
+ "step": 5200
1870
+ },
1871
+ {
1872
+ "epoch": 1.6327807319361902,
1873
+ "grad_norm": 3.892775058746338,
1874
+ "learning_rate": 1.012860618700035e-05,
1875
+ "loss": 1.4713,
1876
+ "step": 5220
1877
+ },
1878
+ {
1879
+ "epoch": 1.6390365968095089,
1880
+ "grad_norm": 4.000039100646973,
1881
+ "learning_rate": 1.0082261615108331e-05,
1882
+ "loss": 1.4392,
1883
+ "step": 5240
1884
+ },
1885
+ {
1886
+ "epoch": 1.6452924616828275,
1887
+ "grad_norm": 3.8597168922424316,
1888
+ "learning_rate": 1.0035917043216314e-05,
1889
+ "loss": 1.5019,
1890
+ "step": 5260
1891
+ },
1892
+ {
1893
+ "epoch": 1.6515483265561464,
1894
+ "grad_norm": 3.5325751304626465,
1895
+ "learning_rate": 9.989572471324297e-06,
1896
+ "loss": 1.5157,
1897
+ "step": 5280
1898
+ },
1899
+ {
1900
+ "epoch": 1.6578041914294652,
1901
+ "grad_norm": 3.6834187507629395,
1902
+ "learning_rate": 9.94322789943228e-06,
1903
+ "loss": 1.4627,
1904
+ "step": 5300
1905
+ },
1906
+ {
1907
+ "epoch": 1.6640600563027839,
1908
+ "grad_norm": 3.7806499004364014,
1909
+ "learning_rate": 9.896883327540263e-06,
1910
+ "loss": 1.4858,
1911
+ "step": 5320
1912
+ },
1913
+ {
1914
+ "epoch": 1.6703159211761025,
1915
+ "grad_norm": 4.8793044090271,
1916
+ "learning_rate": 9.850538755648245e-06,
1917
+ "loss": 1.5186,
1918
+ "step": 5340
1919
+ },
1920
+ {
1921
+ "epoch": 1.6765717860494214,
1922
+ "grad_norm": 3.3358120918273926,
1923
+ "learning_rate": 9.804194183756227e-06,
1924
+ "loss": 1.476,
1925
+ "step": 5360
1926
+ },
1927
+ {
1928
+ "epoch": 1.6828276509227402,
1929
+ "grad_norm": 3.562429904937744,
1930
+ "learning_rate": 9.757849611864211e-06,
1931
+ "loss": 1.4551,
1932
+ "step": 5380
1933
+ },
1934
+ {
1935
+ "epoch": 1.6890835157960589,
1936
+ "grad_norm": 3.358164072036743,
1937
+ "learning_rate": 9.711505039972195e-06,
1938
+ "loss": 1.4587,
1939
+ "step": 5400
1940
+ },
1941
+ {
1942
+ "epoch": 1.6953393806693775,
1943
+ "grad_norm": 3.7120015621185303,
1944
+ "learning_rate": 9.665160468080177e-06,
1945
+ "loss": 1.509,
1946
+ "step": 5420
1947
+ },
1948
+ {
1949
+ "epoch": 1.7015952455426961,
1950
+ "grad_norm": 3.393617868423462,
1951
+ "learning_rate": 9.61881589618816e-06,
1952
+ "loss": 1.4466,
1953
+ "step": 5440
1954
+ },
1955
+ {
1956
+ "epoch": 1.707851110416015,
1957
+ "grad_norm": 3.6086132526397705,
1958
+ "learning_rate": 9.572471324296143e-06,
1959
+ "loss": 1.5047,
1960
+ "step": 5460
1961
+ },
1962
+ {
1963
+ "epoch": 1.7141069752893339,
1964
+ "grad_norm": 3.6902570724487305,
1965
+ "learning_rate": 9.526126752404125e-06,
1966
+ "loss": 1.4928,
1967
+ "step": 5480
1968
+ },
1969
+ {
1970
+ "epoch": 1.7203628401626525,
1971
+ "grad_norm": 3.3542566299438477,
1972
+ "learning_rate": 9.479782180512109e-06,
1973
+ "loss": 1.516,
1974
+ "step": 5500
1975
+ },
1976
+ {
1977
+ "epoch": 1.7266187050359711,
1978
+ "grad_norm": 3.9466335773468018,
1979
+ "learning_rate": 9.433437608620091e-06,
1980
+ "loss": 1.5194,
1981
+ "step": 5520
1982
+ },
1983
+ {
1984
+ "epoch": 1.73287456990929,
1985
+ "grad_norm": 3.526545286178589,
1986
+ "learning_rate": 9.387093036728075e-06,
1987
+ "loss": 1.469,
1988
+ "step": 5540
1989
+ },
1990
+ {
1991
+ "epoch": 1.7391304347826086,
1992
+ "grad_norm": 3.920001745223999,
1993
+ "learning_rate": 9.340748464836057e-06,
1994
+ "loss": 1.4877,
1995
+ "step": 5560
1996
+ },
1997
+ {
1998
+ "epoch": 1.7453862996559275,
1999
+ "grad_norm": 3.415998935699463,
2000
+ "learning_rate": 9.294403892944039e-06,
2001
+ "loss": 1.477,
2002
+ "step": 5580
2003
+ },
2004
+ {
2005
+ "epoch": 1.7516421645292461,
2006
+ "grad_norm": 4.152552127838135,
2007
+ "learning_rate": 9.248059321052023e-06,
2008
+ "loss": 1.4598,
2009
+ "step": 5600
2010
+ },
2011
+ {
2012
+ "epoch": 1.7578980294025648,
2013
+ "grad_norm": 4.323616027832031,
2014
+ "learning_rate": 9.201714749160005e-06,
2015
+ "loss": 1.4412,
2016
+ "step": 5620
2017
+ },
2018
+ {
2019
+ "epoch": 1.7641538942758836,
2020
+ "grad_norm": 4.302744388580322,
2021
+ "learning_rate": 9.155370177267989e-06,
2022
+ "loss": 1.4885,
2023
+ "step": 5640
2024
+ },
2025
+ {
2026
+ "epoch": 1.7704097591492025,
2027
+ "grad_norm": 3.2638041973114014,
2028
+ "learning_rate": 9.10902560537597e-06,
2029
+ "loss": 1.4948,
2030
+ "step": 5660
2031
+ },
2032
+ {
2033
+ "epoch": 1.7766656240225212,
2034
+ "grad_norm": 3.4382920265197754,
2035
+ "learning_rate": 9.062681033483955e-06,
2036
+ "loss": 1.4491,
2037
+ "step": 5680
2038
+ },
2039
+ {
2040
+ "epoch": 1.7829214888958398,
2041
+ "grad_norm": 3.907999038696289,
2042
+ "learning_rate": 9.016336461591937e-06,
2043
+ "loss": 1.4573,
2044
+ "step": 5700
2045
+ },
2046
+ {
2047
+ "epoch": 1.7891773537691584,
2048
+ "grad_norm": 4.269818305969238,
2049
+ "learning_rate": 8.969991889699919e-06,
2050
+ "loss": 1.4932,
2051
+ "step": 5720
2052
+ },
2053
+ {
2054
+ "epoch": 1.7954332186424773,
2055
+ "grad_norm": 4.269619941711426,
2056
+ "learning_rate": 8.923647317807903e-06,
2057
+ "loss": 1.4468,
2058
+ "step": 5740
2059
+ },
2060
+ {
2061
+ "epoch": 1.8016890835157962,
2062
+ "grad_norm": 3.4848062992095947,
2063
+ "learning_rate": 8.877302745915886e-06,
2064
+ "loss": 1.4679,
2065
+ "step": 5760
2066
+ },
2067
+ {
2068
+ "epoch": 1.8079449483891148,
2069
+ "grad_norm": 3.567715644836426,
2070
+ "learning_rate": 8.830958174023868e-06,
2071
+ "loss": 1.4974,
2072
+ "step": 5780
2073
+ },
2074
+ {
2075
+ "epoch": 1.8142008132624334,
2076
+ "grad_norm": 4.031379222869873,
2077
+ "learning_rate": 8.78461360213185e-06,
2078
+ "loss": 1.4192,
2079
+ "step": 5800
2080
+ },
2081
+ {
2082
+ "epoch": 1.8204566781357523,
2083
+ "grad_norm": 3.2717881202697754,
2084
+ "learning_rate": 8.738269030239834e-06,
2085
+ "loss": 1.4905,
2086
+ "step": 5820
2087
+ },
2088
+ {
2089
+ "epoch": 1.8267125430090712,
2090
+ "grad_norm": 3.7909555435180664,
2091
+ "learning_rate": 8.691924458347816e-06,
2092
+ "loss": 1.4595,
2093
+ "step": 5840
2094
+ },
2095
+ {
2096
+ "epoch": 1.8329684078823898,
2097
+ "grad_norm": 3.242023468017578,
2098
+ "learning_rate": 8.645579886455799e-06,
2099
+ "loss": 1.4484,
2100
+ "step": 5860
2101
+ },
2102
+ {
2103
+ "epoch": 1.8392242727557084,
2104
+ "grad_norm": 3.605093240737915,
2105
+ "learning_rate": 8.599235314563782e-06,
2106
+ "loss": 1.4915,
2107
+ "step": 5880
2108
+ },
2109
+ {
2110
+ "epoch": 1.845480137629027,
2111
+ "grad_norm": 3.832170248031616,
2112
+ "learning_rate": 8.552890742671766e-06,
2113
+ "loss": 1.476,
2114
+ "step": 5900
2115
+ },
2116
+ {
2117
+ "epoch": 1.851736002502346,
2118
+ "grad_norm": 3.6190032958984375,
2119
+ "learning_rate": 8.506546170779748e-06,
2120
+ "loss": 1.4179,
2121
+ "step": 5920
2122
+ },
2123
+ {
2124
+ "epoch": 1.8579918673756648,
2125
+ "grad_norm": 4.795033931732178,
2126
+ "learning_rate": 8.46020159888773e-06,
2127
+ "loss": 1.4823,
2128
+ "step": 5940
2129
+ },
2130
+ {
2131
+ "epoch": 1.8642477322489834,
2132
+ "grad_norm": 4.25372314453125,
2133
+ "learning_rate": 8.413857026995714e-06,
2134
+ "loss": 1.4547,
2135
+ "step": 5960
2136
+ },
2137
+ {
2138
+ "epoch": 1.870503597122302,
2139
+ "grad_norm": 3.29866099357605,
2140
+ "learning_rate": 8.367512455103696e-06,
2141
+ "loss": 1.4366,
2142
+ "step": 5980
2143
+ },
2144
+ {
2145
+ "epoch": 1.876759461995621,
2146
+ "grad_norm": 3.771183967590332,
2147
+ "learning_rate": 8.32116788321168e-06,
2148
+ "loss": 1.5107,
2149
+ "step": 6000
2150
+ },
2151
+ {
2152
+ "epoch": 1.876759461995621,
2153
+ "eval_loss": 0.5249506831169128,
2154
+ "eval_runtime": 30.3312,
2155
+ "eval_samples_per_second": 15.957,
2156
+ "eval_steps_per_second": 3.989,
2157
+ "step": 6000
2158
+ },
2159
+ {
2160
+ "epoch": 1.8830153268689396,
2161
+ "grad_norm": 3.4355130195617676,
2162
+ "learning_rate": 8.274823311319662e-06,
2163
+ "loss": 1.4839,
2164
+ "step": 6020
2165
+ },
2166
+ {
2167
+ "epoch": 1.8892711917422584,
2168
+ "grad_norm": 3.5628068447113037,
2169
+ "learning_rate": 8.228478739427646e-06,
2170
+ "loss": 1.5049,
2171
+ "step": 6040
2172
+ },
2173
+ {
2174
+ "epoch": 1.895527056615577,
2175
+ "grad_norm": 3.52653169631958,
2176
+ "learning_rate": 8.182134167535628e-06,
2177
+ "loss": 1.4729,
2178
+ "step": 6060
2179
+ },
2180
+ {
2181
+ "epoch": 1.9017829214888957,
2182
+ "grad_norm": 4.024752140045166,
2183
+ "learning_rate": 8.13578959564361e-06,
2184
+ "loss": 1.4413,
2185
+ "step": 6080
2186
+ },
2187
+ {
2188
+ "epoch": 1.9080387863622146,
2189
+ "grad_norm": 4.114953994750977,
2190
+ "learning_rate": 8.089445023751594e-06,
2191
+ "loss": 1.4517,
2192
+ "step": 6100
2193
+ },
2194
+ {
2195
+ "epoch": 1.9142946512355334,
2196
+ "grad_norm": 3.832791328430176,
2197
+ "learning_rate": 8.043100451859576e-06,
2198
+ "loss": 1.4576,
2199
+ "step": 6120
2200
+ },
2201
+ {
2202
+ "epoch": 1.920550516108852,
2203
+ "grad_norm": 3.5607106685638428,
2204
+ "learning_rate": 7.99675587996756e-06,
2205
+ "loss": 1.4813,
2206
+ "step": 6140
2207
+ },
2208
+ {
2209
+ "epoch": 1.9268063809821707,
2210
+ "grad_norm": 3.79740309715271,
2211
+ "learning_rate": 7.950411308075542e-06,
2212
+ "loss": 1.4886,
2213
+ "step": 6160
2214
+ },
2215
+ {
2216
+ "epoch": 1.9330622458554894,
2217
+ "grad_norm": 3.8134922981262207,
2218
+ "learning_rate": 7.904066736183526e-06,
2219
+ "loss": 1.425,
2220
+ "step": 6180
2221
+ },
2222
+ {
2223
+ "epoch": 1.9393181107288082,
2224
+ "grad_norm": 4.097330570220947,
2225
+ "learning_rate": 7.857722164291508e-06,
2226
+ "loss": 1.5026,
2227
+ "step": 6200
2228
+ },
2229
+ {
2230
+ "epoch": 1.945573975602127,
2231
+ "grad_norm": 3.597710609436035,
2232
+ "learning_rate": 7.81137759239949e-06,
2233
+ "loss": 1.4355,
2234
+ "step": 6220
2235
+ },
2236
+ {
2237
+ "epoch": 1.9518298404754457,
2238
+ "grad_norm": 4.481216907501221,
2239
+ "learning_rate": 7.765033020507474e-06,
2240
+ "loss": 1.4761,
2241
+ "step": 6240
2242
+ },
2243
+ {
2244
+ "epoch": 1.9580857053487644,
2245
+ "grad_norm": 3.9572675228118896,
2246
+ "learning_rate": 7.718688448615457e-06,
2247
+ "loss": 1.4684,
2248
+ "step": 6260
2249
+ },
2250
+ {
2251
+ "epoch": 1.9643415702220832,
2252
+ "grad_norm": 3.0749871730804443,
2253
+ "learning_rate": 7.67234387672344e-06,
2254
+ "loss": 1.4369,
2255
+ "step": 6280
2256
+ },
2257
+ {
2258
+ "epoch": 1.970597435095402,
2259
+ "grad_norm": 4.008276462554932,
2260
+ "learning_rate": 7.625999304831422e-06,
2261
+ "loss": 1.4414,
2262
+ "step": 6300
2263
+ },
2264
+ {
2265
+ "epoch": 1.9768532999687207,
2266
+ "grad_norm": 3.3780014514923096,
2267
+ "learning_rate": 7.5796547329394054e-06,
2268
+ "loss": 1.4795,
2269
+ "step": 6320
2270
+ },
2271
+ {
2272
+ "epoch": 1.9831091648420394,
2273
+ "grad_norm": 3.802067756652832,
2274
+ "learning_rate": 7.533310161047388e-06,
2275
+ "loss": 1.4506,
2276
+ "step": 6340
2277
+ },
2278
+ {
2279
+ "epoch": 1.989365029715358,
2280
+ "grad_norm": 3.7218985557556152,
2281
+ "learning_rate": 7.4869655891553705e-06,
2282
+ "loss": 1.4379,
2283
+ "step": 6360
2284
+ },
2285
+ {
2286
+ "epoch": 1.9956208945886769,
2287
+ "grad_norm": 3.222632646560669,
2288
+ "learning_rate": 7.440621017263354e-06,
2289
+ "loss": 1.4354,
2290
+ "step": 6380
2291
+ },
2292
+ {
2293
+ "epoch": 2.0018767594619957,
2294
+ "grad_norm": 3.8669259548187256,
2295
+ "learning_rate": 7.394276445371336e-06,
2296
+ "loss": 1.4626,
2297
+ "step": 6400
2298
+ },
2299
+ {
2300
+ "epoch": 2.0081326243353144,
2301
+ "grad_norm": 3.748908281326294,
2302
+ "learning_rate": 7.347931873479319e-06,
2303
+ "loss": 1.4119,
2304
+ "step": 6420
2305
+ },
2306
+ {
2307
+ "epoch": 2.014388489208633,
2308
+ "grad_norm": 3.8527488708496094,
2309
+ "learning_rate": 7.301587301587301e-06,
2310
+ "loss": 1.468,
2311
+ "step": 6440
2312
+ },
2313
+ {
2314
+ "epoch": 2.0206443540819516,
2315
+ "grad_norm": 4.265289783477783,
2316
+ "learning_rate": 7.255242729695285e-06,
2317
+ "loss": 1.411,
2318
+ "step": 6460
2319
+ },
2320
+ {
2321
+ "epoch": 2.0269002189552707,
2322
+ "grad_norm": 3.580428123474121,
2323
+ "learning_rate": 7.208898157803268e-06,
2324
+ "loss": 1.4447,
2325
+ "step": 6480
2326
+ },
2327
+ {
2328
+ "epoch": 2.0331560838285894,
2329
+ "grad_norm": 3.5705726146698,
2330
+ "learning_rate": 7.16255358591125e-06,
2331
+ "loss": 1.4475,
2332
+ "step": 6500
2333
+ },
2334
+ {
2335
+ "epoch": 2.039411948701908,
2336
+ "grad_norm": 4.200178146362305,
2337
+ "learning_rate": 7.116209014019233e-06,
2338
+ "loss": 1.4493,
2339
+ "step": 6520
2340
+ },
2341
+ {
2342
+ "epoch": 2.0456678135752266,
2343
+ "grad_norm": 3.9091575145721436,
2344
+ "learning_rate": 7.069864442127217e-06,
2345
+ "loss": 1.4842,
2346
+ "step": 6540
2347
+ },
2348
+ {
2349
+ "epoch": 2.0519236784485457,
2350
+ "grad_norm": 4.206997394561768,
2351
+ "learning_rate": 7.023519870235199e-06,
2352
+ "loss": 1.4528,
2353
+ "step": 6560
2354
+ },
2355
+ {
2356
+ "epoch": 2.0581795433218644,
2357
+ "grad_norm": 3.746002435684204,
2358
+ "learning_rate": 6.977175298343182e-06,
2359
+ "loss": 1.4081,
2360
+ "step": 6580
2361
+ },
2362
+ {
2363
+ "epoch": 2.064435408195183,
2364
+ "grad_norm": 4.167978286743164,
2365
+ "learning_rate": 6.930830726451166e-06,
2366
+ "loss": 1.4367,
2367
+ "step": 6600
2368
+ },
2369
+ {
2370
+ "epoch": 2.0706912730685016,
2371
+ "grad_norm": 3.922278881072998,
2372
+ "learning_rate": 6.884486154559148e-06,
2373
+ "loss": 1.4745,
2374
+ "step": 6620
2375
+ },
2376
+ {
2377
+ "epoch": 2.0769471379418203,
2378
+ "grad_norm": 4.390613555908203,
2379
+ "learning_rate": 6.838141582667131e-06,
2380
+ "loss": 1.4456,
2381
+ "step": 6640
2382
+ },
2383
+ {
2384
+ "epoch": 2.0832030028151394,
2385
+ "grad_norm": 3.3324151039123535,
2386
+ "learning_rate": 6.791797010775113e-06,
2387
+ "loss": 1.4202,
2388
+ "step": 6660
2389
+ },
2390
+ {
2391
+ "epoch": 2.089458867688458,
2392
+ "grad_norm": 3.823288917541504,
2393
+ "learning_rate": 6.745452438883097e-06,
2394
+ "loss": 1.4624,
2395
+ "step": 6680
2396
+ },
2397
+ {
2398
+ "epoch": 2.0957147325617766,
2399
+ "grad_norm": 3.162973403930664,
2400
+ "learning_rate": 6.699107866991079e-06,
2401
+ "loss": 1.4481,
2402
+ "step": 6700
2403
+ },
2404
+ {
2405
+ "epoch": 2.1019705974350953,
2406
+ "grad_norm": 3.888578176498413,
2407
+ "learning_rate": 6.652763295099062e-06,
2408
+ "loss": 1.3965,
2409
+ "step": 6720
2410
+ },
2411
+ {
2412
+ "epoch": 2.108226462308414,
2413
+ "grad_norm": 3.485076665878296,
2414
+ "learning_rate": 6.606418723207046e-06,
2415
+ "loss": 1.4791,
2416
+ "step": 6740
2417
+ },
2418
+ {
2419
+ "epoch": 2.114482327181733,
2420
+ "grad_norm": 4.454657554626465,
2421
+ "learning_rate": 6.560074151315028e-06,
2422
+ "loss": 1.4502,
2423
+ "step": 6760
2424
+ },
2425
+ {
2426
+ "epoch": 2.1207381920550517,
2427
+ "grad_norm": 4.14171838760376,
2428
+ "learning_rate": 6.513729579423011e-06,
2429
+ "loss": 1.4569,
2430
+ "step": 6780
2431
+ },
2432
+ {
2433
+ "epoch": 2.1269940569283703,
2434
+ "grad_norm": 3.889117956161499,
2435
+ "learning_rate": 6.467385007530993e-06,
2436
+ "loss": 1.4173,
2437
+ "step": 6800
2438
+ },
2439
+ {
2440
+ "epoch": 2.133249921801689,
2441
+ "grad_norm": 4.004756927490234,
2442
+ "learning_rate": 6.4210404356389765e-06,
2443
+ "loss": 1.4278,
2444
+ "step": 6820
2445
+ },
2446
+ {
2447
+ "epoch": 2.139505786675008,
2448
+ "grad_norm": 3.7619662284851074,
2449
+ "learning_rate": 6.3746958637469595e-06,
2450
+ "loss": 1.4279,
2451
+ "step": 6840
2452
+ },
2453
+ {
2454
+ "epoch": 2.1457616515483267,
2455
+ "grad_norm": 4.004810333251953,
2456
+ "learning_rate": 6.3283512918549416e-06,
2457
+ "loss": 1.4657,
2458
+ "step": 6860
2459
+ },
2460
+ {
2461
+ "epoch": 2.1520175164216453,
2462
+ "grad_norm": 5.289163112640381,
2463
+ "learning_rate": 6.282006719962925e-06,
2464
+ "loss": 1.4271,
2465
+ "step": 6880
2466
+ },
2467
+ {
2468
+ "epoch": 2.158273381294964,
2469
+ "grad_norm": 3.6333744525909424,
2470
+ "learning_rate": 6.2356621480709074e-06,
2471
+ "loss": 1.4337,
2472
+ "step": 6900
2473
+ },
2474
+ {
2475
+ "epoch": 2.1645292461682826,
2476
+ "grad_norm": 4.031957626342773,
2477
+ "learning_rate": 6.18931757617889e-06,
2478
+ "loss": 1.4133,
2479
+ "step": 6920
2480
+ },
2481
+ {
2482
+ "epoch": 2.1707851110416017,
2483
+ "grad_norm": 3.917013168334961,
2484
+ "learning_rate": 6.142973004286873e-06,
2485
+ "loss": 1.4533,
2486
+ "step": 6940
2487
+ },
2488
+ {
2489
+ "epoch": 2.1770409759149203,
2490
+ "grad_norm": 3.9864284992218018,
2491
+ "learning_rate": 6.096628432394856e-06,
2492
+ "loss": 1.4549,
2493
+ "step": 6960
2494
+ },
2495
+ {
2496
+ "epoch": 2.183296840788239,
2497
+ "grad_norm": 3.6606876850128174,
2498
+ "learning_rate": 6.050283860502839e-06,
2499
+ "loss": 1.4091,
2500
+ "step": 6980
2501
+ },
2502
+ {
2503
+ "epoch": 2.1895527056615576,
2504
+ "grad_norm": 4.302699565887451,
2505
+ "learning_rate": 6.003939288610821e-06,
2506
+ "loss": 1.4914,
2507
+ "step": 7000
2508
+ },
2509
+ {
2510
+ "epoch": 2.1895527056615576,
2511
+ "eval_loss": 0.5183842778205872,
2512
+ "eval_runtime": 30.127,
2513
+ "eval_samples_per_second": 16.065,
2514
+ "eval_steps_per_second": 4.016,
2515
+ "step": 7000
2516
+ },
2517
+ {
2518
+ "epoch": 2.1958085705348767,
2519
+ "grad_norm": 4.072482109069824,
2520
+ "learning_rate": 5.957594716718805e-06,
2521
+ "loss": 1.4146,
2522
+ "step": 7020
2523
+ },
2524
+ {
2525
+ "epoch": 2.2020644354081953,
2526
+ "grad_norm": 3.948002815246582,
2527
+ "learning_rate": 5.911250144826788e-06,
2528
+ "loss": 1.4575,
2529
+ "step": 7040
2530
+ },
2531
+ {
2532
+ "epoch": 2.208320300281514,
2533
+ "grad_norm": 3.2207224369049072,
2534
+ "learning_rate": 5.86490557293477e-06,
2535
+ "loss": 1.3987,
2536
+ "step": 7060
2537
+ },
2538
+ {
2539
+ "epoch": 2.2145761651548326,
2540
+ "grad_norm": 3.5877556800842285,
2541
+ "learning_rate": 5.818561001042753e-06,
2542
+ "loss": 1.4113,
2543
+ "step": 7080
2544
+ },
2545
+ {
2546
+ "epoch": 2.220832030028151,
2547
+ "grad_norm": 4.221316337585449,
2548
+ "learning_rate": 5.772216429150737e-06,
2549
+ "loss": 1.4649,
2550
+ "step": 7100
2551
+ },
2552
+ {
2553
+ "epoch": 2.2270878949014703,
2554
+ "grad_norm": 3.4622902870178223,
2555
+ "learning_rate": 5.725871857258719e-06,
2556
+ "loss": 1.4291,
2557
+ "step": 7120
2558
+ },
2559
+ {
2560
+ "epoch": 2.233343759774789,
2561
+ "grad_norm": 3.8495419025421143,
2562
+ "learning_rate": 5.679527285366702e-06,
2563
+ "loss": 1.4492,
2564
+ "step": 7140
2565
+ },
2566
+ {
2567
+ "epoch": 2.2395996246481076,
2568
+ "grad_norm": 4.676374912261963,
2569
+ "learning_rate": 5.633182713474685e-06,
2570
+ "loss": 1.4219,
2571
+ "step": 7160
2572
+ },
2573
+ {
2574
+ "epoch": 2.245855489521426,
2575
+ "grad_norm": 5.073587894439697,
2576
+ "learning_rate": 5.586838141582668e-06,
2577
+ "loss": 1.4784,
2578
+ "step": 7180
2579
+ },
2580
+ {
2581
+ "epoch": 2.252111354394745,
2582
+ "grad_norm": 3.6623458862304688,
2583
+ "learning_rate": 5.54049356969065e-06,
2584
+ "loss": 1.4654,
2585
+ "step": 7200
2586
+ },
2587
+ {
2588
+ "epoch": 2.258367219268064,
2589
+ "grad_norm": 3.8176751136779785,
2590
+ "learning_rate": 5.494148997798633e-06,
2591
+ "loss": 1.384,
2592
+ "step": 7220
2593
+ },
2594
+ {
2595
+ "epoch": 2.2646230841413826,
2596
+ "grad_norm": 4.066217422485352,
2597
+ "learning_rate": 5.447804425906617e-06,
2598
+ "loss": 1.4125,
2599
+ "step": 7240
2600
+ },
2601
+ {
2602
+ "epoch": 2.270878949014701,
2603
+ "grad_norm": 3.977444887161255,
2604
+ "learning_rate": 5.401459854014599e-06,
2605
+ "loss": 1.4492,
2606
+ "step": 7260
2607
+ },
2608
+ {
2609
+ "epoch": 2.27713481388802,
2610
+ "grad_norm": 3.8999898433685303,
2611
+ "learning_rate": 5.355115282122582e-06,
2612
+ "loss": 1.3982,
2613
+ "step": 7280
2614
+ },
2615
+ {
2616
+ "epoch": 2.283390678761339,
2617
+ "grad_norm": 3.845292329788208,
2618
+ "learning_rate": 5.3087707102305655e-06,
2619
+ "loss": 1.4199,
2620
+ "step": 7300
2621
+ },
2622
+ {
2623
+ "epoch": 2.2896465436346576,
2624
+ "grad_norm": 4.052536964416504,
2625
+ "learning_rate": 5.262426138338548e-06,
2626
+ "loss": 1.4316,
2627
+ "step": 7320
2628
+ },
2629
+ {
2630
+ "epoch": 2.2959024085079762,
2631
+ "grad_norm": 5.119332790374756,
2632
+ "learning_rate": 5.2160815664465305e-06,
2633
+ "loss": 1.4084,
2634
+ "step": 7340
2635
+ },
2636
+ {
2637
+ "epoch": 2.302158273381295,
2638
+ "grad_norm": 4.279220104217529,
2639
+ "learning_rate": 5.169736994554513e-06,
2640
+ "loss": 1.4383,
2641
+ "step": 7360
2642
+ },
2643
+ {
2644
+ "epoch": 2.308414138254614,
2645
+ "grad_norm": 4.149873733520508,
2646
+ "learning_rate": 5.123392422662496e-06,
2647
+ "loss": 1.4221,
2648
+ "step": 7380
2649
+ },
2650
+ {
2651
+ "epoch": 2.3146700031279326,
2652
+ "grad_norm": 4.548859119415283,
2653
+ "learning_rate": 5.077047850770479e-06,
2654
+ "loss": 1.3936,
2655
+ "step": 7400
2656
+ },
2657
+ {
2658
+ "epoch": 2.3209258680012512,
2659
+ "grad_norm": 4.159961700439453,
2660
+ "learning_rate": 5.0307032788784615e-06,
2661
+ "loss": 1.4052,
2662
+ "step": 7420
2663
+ },
2664
+ {
2665
+ "epoch": 2.32718173287457,
2666
+ "grad_norm": 3.7540910243988037,
2667
+ "learning_rate": 4.984358706986444e-06,
2668
+ "loss": 1.416,
2669
+ "step": 7440
2670
+ },
2671
+ {
2672
+ "epoch": 2.3334375977478885,
2673
+ "grad_norm": 4.482418537139893,
2674
+ "learning_rate": 4.938014135094427e-06,
2675
+ "loss": 1.4299,
2676
+ "step": 7460
2677
+ },
2678
+ {
2679
+ "epoch": 2.3396934626212076,
2680
+ "grad_norm": 4.642965316772461,
2681
+ "learning_rate": 4.89166956320241e-06,
2682
+ "loss": 1.3794,
2683
+ "step": 7480
2684
+ },
2685
+ {
2686
+ "epoch": 2.3459493274945262,
2687
+ "grad_norm": 3.7981739044189453,
2688
+ "learning_rate": 4.845324991310393e-06,
2689
+ "loss": 1.4147,
2690
+ "step": 7500
2691
+ },
2692
+ {
2693
+ "epoch": 2.352205192367845,
2694
+ "grad_norm": 3.6449689865112305,
2695
+ "learning_rate": 4.798980419418376e-06,
2696
+ "loss": 1.3822,
2697
+ "step": 7520
2698
+ },
2699
+ {
2700
+ "epoch": 2.3584610572411635,
2701
+ "grad_norm": 4.532881736755371,
2702
+ "learning_rate": 4.752635847526359e-06,
2703
+ "loss": 1.4283,
2704
+ "step": 7540
2705
+ },
2706
+ {
2707
+ "epoch": 2.364716922114482,
2708
+ "grad_norm": 4.486178874969482,
2709
+ "learning_rate": 4.706291275634341e-06,
2710
+ "loss": 1.4043,
2711
+ "step": 7560
2712
+ },
2713
+ {
2714
+ "epoch": 2.3709727869878012,
2715
+ "grad_norm": 3.9950759410858154,
2716
+ "learning_rate": 4.659946703742325e-06,
2717
+ "loss": 1.4632,
2718
+ "step": 7580
2719
+ },
2720
+ {
2721
+ "epoch": 2.37722865186112,
2722
+ "grad_norm": 3.486673355102539,
2723
+ "learning_rate": 4.613602131850307e-06,
2724
+ "loss": 1.4193,
2725
+ "step": 7600
2726
+ },
2727
+ {
2728
+ "epoch": 2.3834845167344385,
2729
+ "grad_norm": 3.896305799484253,
2730
+ "learning_rate": 4.56725755995829e-06,
2731
+ "loss": 1.3879,
2732
+ "step": 7620
2733
+ },
2734
+ {
2735
+ "epoch": 2.389740381607757,
2736
+ "grad_norm": 3.072448492050171,
2737
+ "learning_rate": 4.520912988066273e-06,
2738
+ "loss": 1.4173,
2739
+ "step": 7640
2740
+ },
2741
+ {
2742
+ "epoch": 2.395996246481076,
2743
+ "grad_norm": 3.844083547592163,
2744
+ "learning_rate": 4.474568416174256e-06,
2745
+ "loss": 1.3865,
2746
+ "step": 7660
2747
+ },
2748
+ {
2749
+ "epoch": 2.402252111354395,
2750
+ "grad_norm": 4.288559436798096,
2751
+ "learning_rate": 4.428223844282239e-06,
2752
+ "loss": 1.4044,
2753
+ "step": 7680
2754
+ },
2755
+ {
2756
+ "epoch": 2.4085079762277135,
2757
+ "grad_norm": 3.5817108154296875,
2758
+ "learning_rate": 4.381879272390222e-06,
2759
+ "loss": 1.4128,
2760
+ "step": 7700
2761
+ },
2762
+ {
2763
+ "epoch": 2.414763841101032,
2764
+ "grad_norm": 4.0619282722473145,
2765
+ "learning_rate": 4.335534700498205e-06,
2766
+ "loss": 1.4721,
2767
+ "step": 7720
2768
+ },
2769
+ {
2770
+ "epoch": 2.421019705974351,
2771
+ "grad_norm": 3.2147204875946045,
2772
+ "learning_rate": 4.289190128606187e-06,
2773
+ "loss": 1.4621,
2774
+ "step": 7740
2775
+ },
2776
+ {
2777
+ "epoch": 2.42727557084767,
2778
+ "grad_norm": 3.896071195602417,
2779
+ "learning_rate": 4.24284555671417e-06,
2780
+ "loss": 1.4041,
2781
+ "step": 7760
2782
+ },
2783
+ {
2784
+ "epoch": 2.4335314357209885,
2785
+ "grad_norm": 3.7601754665374756,
2786
+ "learning_rate": 4.196500984822154e-06,
2787
+ "loss": 1.3929,
2788
+ "step": 7780
2789
+ },
2790
+ {
2791
+ "epoch": 2.439787300594307,
2792
+ "grad_norm": 3.753279685974121,
2793
+ "learning_rate": 4.150156412930136e-06,
2794
+ "loss": 1.4418,
2795
+ "step": 7800
2796
+ },
2797
+ {
2798
+ "epoch": 2.446043165467626,
2799
+ "grad_norm": 3.9221978187561035,
2800
+ "learning_rate": 4.103811841038119e-06,
2801
+ "loss": 1.3875,
2802
+ "step": 7820
2803
+ },
2804
+ {
2805
+ "epoch": 2.452299030340945,
2806
+ "grad_norm": 3.614114761352539,
2807
+ "learning_rate": 4.057467269146102e-06,
2808
+ "loss": 1.3828,
2809
+ "step": 7840
2810
+ },
2811
+ {
2812
+ "epoch": 2.4585548952142635,
2813
+ "grad_norm": 4.317903518676758,
2814
+ "learning_rate": 4.0111226972540846e-06,
2815
+ "loss": 1.4378,
2816
+ "step": 7860
2817
+ },
2818
+ {
2819
+ "epoch": 2.464810760087582,
2820
+ "grad_norm": 4.5976738929748535,
2821
+ "learning_rate": 3.964778125362067e-06,
2822
+ "loss": 1.3863,
2823
+ "step": 7880
2824
+ },
2825
+ {
2826
+ "epoch": 2.471066624960901,
2827
+ "grad_norm": 4.07506799697876,
2828
+ "learning_rate": 3.9184335534700504e-06,
2829
+ "loss": 1.3808,
2830
+ "step": 7900
2831
+ },
2832
+ {
2833
+ "epoch": 2.4773224898342194,
2834
+ "grad_norm": 4.548733711242676,
2835
+ "learning_rate": 3.872088981578033e-06,
2836
+ "loss": 1.4063,
2837
+ "step": 7920
2838
+ },
2839
+ {
2840
+ "epoch": 2.4835783547075385,
2841
+ "grad_norm": 4.166104316711426,
2842
+ "learning_rate": 3.8257444096860155e-06,
2843
+ "loss": 1.3962,
2844
+ "step": 7940
2845
+ },
2846
+ {
2847
+ "epoch": 2.489834219580857,
2848
+ "grad_norm": 3.7219245433807373,
2849
+ "learning_rate": 3.779399837793999e-06,
2850
+ "loss": 1.4458,
2851
+ "step": 7960
2852
+ },
2853
+ {
2854
+ "epoch": 2.496090084454176,
2855
+ "grad_norm": 4.242513179779053,
2856
+ "learning_rate": 3.7330552659019814e-06,
2857
+ "loss": 1.4342,
2858
+ "step": 7980
2859
+ },
2860
+ {
2861
+ "epoch": 2.5023459493274944,
2862
+ "grad_norm": 3.4067800045013428,
2863
+ "learning_rate": 3.6867106940099643e-06,
2864
+ "loss": 1.3884,
2865
+ "step": 8000
2866
+ },
2867
+ {
2868
+ "epoch": 2.5023459493274944,
2869
+ "eval_loss": 0.5156850814819336,
2870
+ "eval_runtime": 30.2,
2871
+ "eval_samples_per_second": 16.027,
2872
+ "eval_steps_per_second": 4.007,
2873
+ "step": 8000
2874
+ },
2875
+ {
2876
+ "epoch": 2.508601814200813,
2877
+ "grad_norm": 3.91298508644104,
2878
+ "learning_rate": 3.640366122117947e-06,
2879
+ "loss": 1.3653,
2880
+ "step": 8020
2881
+ },
2882
+ {
2883
+ "epoch": 2.514857679074132,
2884
+ "grad_norm": 3.830792188644409,
2885
+ "learning_rate": 3.5940215502259302e-06,
2886
+ "loss": 1.3945,
2887
+ "step": 8040
2888
+ },
2889
+ {
2890
+ "epoch": 2.521113543947451,
2891
+ "grad_norm": 3.802927017211914,
2892
+ "learning_rate": 3.5476769783339127e-06,
2893
+ "loss": 1.3996,
2894
+ "step": 8060
2895
+ },
2896
+ {
2897
+ "epoch": 2.5273694088207694,
2898
+ "grad_norm": 4.000018119812012,
2899
+ "learning_rate": 3.5013324064418957e-06,
2900
+ "loss": 1.4302,
2901
+ "step": 8080
2902
+ },
2903
+ {
2904
+ "epoch": 2.533625273694088,
2905
+ "grad_norm": 4.325403690338135,
2906
+ "learning_rate": 3.454987834549879e-06,
2907
+ "loss": 1.4083,
2908
+ "step": 8100
2909
+ },
2910
+ {
2911
+ "epoch": 2.5398811385674067,
2912
+ "grad_norm": 3.761460781097412,
2913
+ "learning_rate": 3.4086432626578616e-06,
2914
+ "loss": 1.3648,
2915
+ "step": 8120
2916
+ },
2917
+ {
2918
+ "epoch": 2.546137003440726,
2919
+ "grad_norm": 3.756761312484741,
2920
+ "learning_rate": 3.3622986907658445e-06,
2921
+ "loss": 1.3559,
2922
+ "step": 8140
2923
+ },
2924
+ {
2925
+ "epoch": 2.5523928683140444,
2926
+ "grad_norm": 3.938476085662842,
2927
+ "learning_rate": 3.315954118873827e-06,
2928
+ "loss": 1.4314,
2929
+ "step": 8160
2930
+ },
2931
+ {
2932
+ "epoch": 2.558648733187363,
2933
+ "grad_norm": 3.8850269317626953,
2934
+ "learning_rate": 3.26960954698181e-06,
2935
+ "loss": 1.4357,
2936
+ "step": 8180
2937
+ },
2938
+ {
2939
+ "epoch": 2.564904598060682,
2940
+ "grad_norm": 4.117141246795654,
2941
+ "learning_rate": 3.2232649750897925e-06,
2942
+ "loss": 1.3784,
2943
+ "step": 8200
2944
+ },
2945
+ {
2946
+ "epoch": 2.5711604629340004,
2947
+ "grad_norm": 3.2003445625305176,
2948
+ "learning_rate": 3.176920403197776e-06,
2949
+ "loss": 1.4187,
2950
+ "step": 8220
2951
+ },
2952
+ {
2953
+ "epoch": 2.5774163278073194,
2954
+ "grad_norm": 3.5441741943359375,
2955
+ "learning_rate": 3.130575831305759e-06,
2956
+ "loss": 1.3897,
2957
+ "step": 8240
2958
+ },
2959
+ {
2960
+ "epoch": 2.583672192680638,
2961
+ "grad_norm": 4.082095623016357,
2962
+ "learning_rate": 3.0842312594137413e-06,
2963
+ "loss": 1.3901,
2964
+ "step": 8260
2965
+ },
2966
+ {
2967
+ "epoch": 2.5899280575539567,
2968
+ "grad_norm": 3.878877878189087,
2969
+ "learning_rate": 3.0378866875217243e-06,
2970
+ "loss": 1.4273,
2971
+ "step": 8280
2972
+ },
2973
+ {
2974
+ "epoch": 2.596183922427276,
2975
+ "grad_norm": 4.063547134399414,
2976
+ "learning_rate": 2.991542115629707e-06,
2977
+ "loss": 1.4536,
2978
+ "step": 8300
2979
+ },
2980
+ {
2981
+ "epoch": 2.6024397873005944,
2982
+ "grad_norm": 5.6043596267700195,
2983
+ "learning_rate": 2.94519754373769e-06,
2984
+ "loss": 1.3799,
2985
+ "step": 8320
2986
+ },
2987
+ {
2988
+ "epoch": 2.608695652173913,
2989
+ "grad_norm": 3.9058849811553955,
2990
+ "learning_rate": 2.8988529718456727e-06,
2991
+ "loss": 1.4384,
2992
+ "step": 8340
2993
+ },
2994
+ {
2995
+ "epoch": 2.6149515170472317,
2996
+ "grad_norm": 4.544114112854004,
2997
+ "learning_rate": 2.8525083999536556e-06,
2998
+ "loss": 1.4154,
2999
+ "step": 8360
3000
+ },
3001
+ {
3002
+ "epoch": 2.6212073819205504,
3003
+ "grad_norm": 4.125789165496826,
3004
+ "learning_rate": 2.8061638280616386e-06,
3005
+ "loss": 1.348,
3006
+ "step": 8380
3007
+ },
3008
+ {
3009
+ "epoch": 2.6274632467938694,
3010
+ "grad_norm": 3.849442958831787,
3011
+ "learning_rate": 2.7598192561696215e-06,
3012
+ "loss": 1.3859,
3013
+ "step": 8400
3014
+ },
3015
+ {
3016
+ "epoch": 2.633719111667188,
3017
+ "grad_norm": 3.8428611755371094,
3018
+ "learning_rate": 2.7134746842776045e-06,
3019
+ "loss": 1.3743,
3020
+ "step": 8420
3021
+ },
3022
+ {
3023
+ "epoch": 2.6399749765405067,
3024
+ "grad_norm": 3.9532744884490967,
3025
+ "learning_rate": 2.667130112385587e-06,
3026
+ "loss": 1.3664,
3027
+ "step": 8440
3028
+ },
3029
+ {
3030
+ "epoch": 2.6462308414138254,
3031
+ "grad_norm": 4.1256232261657715,
3032
+ "learning_rate": 2.62078554049357e-06,
3033
+ "loss": 1.4149,
3034
+ "step": 8460
3035
+ },
3036
+ {
3037
+ "epoch": 2.652486706287144,
3038
+ "grad_norm": 4.687183856964111,
3039
+ "learning_rate": 2.5744409686015525e-06,
3040
+ "loss": 1.3974,
3041
+ "step": 8480
3042
+ },
3043
+ {
3044
+ "epoch": 2.658742571160463,
3045
+ "grad_norm": 4.005310535430908,
3046
+ "learning_rate": 2.528096396709536e-06,
3047
+ "loss": 1.3903,
3048
+ "step": 8500
3049
+ },
3050
+ {
3051
+ "epoch": 2.6649984360337817,
3052
+ "grad_norm": 3.9469504356384277,
3053
+ "learning_rate": 2.4817518248175183e-06,
3054
+ "loss": 1.3635,
3055
+ "step": 8520
3056
+ },
3057
+ {
3058
+ "epoch": 2.6712543009071004,
3059
+ "grad_norm": 3.4386444091796875,
3060
+ "learning_rate": 2.4354072529255013e-06,
3061
+ "loss": 1.4357,
3062
+ "step": 8540
3063
+ },
3064
+ {
3065
+ "epoch": 2.677510165780419,
3066
+ "grad_norm": 3.956700563430786,
3067
+ "learning_rate": 2.3890626810334842e-06,
3068
+ "loss": 1.3847,
3069
+ "step": 8560
3070
+ },
3071
+ {
3072
+ "epoch": 2.6837660306537376,
3073
+ "grad_norm": 3.6167428493499756,
3074
+ "learning_rate": 2.3427181091414668e-06,
3075
+ "loss": 1.3627,
3076
+ "step": 8580
3077
+ },
3078
+ {
3079
+ "epoch": 2.6900218955270567,
3080
+ "grad_norm": 4.528804779052734,
3081
+ "learning_rate": 2.2963735372494497e-06,
3082
+ "loss": 1.3817,
3083
+ "step": 8600
3084
+ },
3085
+ {
3086
+ "epoch": 2.6962777604003754,
3087
+ "grad_norm": 4.087806701660156,
3088
+ "learning_rate": 2.2500289653574326e-06,
3089
+ "loss": 1.4025,
3090
+ "step": 8620
3091
+ },
3092
+ {
3093
+ "epoch": 2.702533625273694,
3094
+ "grad_norm": 3.7826669216156006,
3095
+ "learning_rate": 2.2036843934654156e-06,
3096
+ "loss": 1.3574,
3097
+ "step": 8640
3098
+ },
3099
+ {
3100
+ "epoch": 2.708789490147013,
3101
+ "grad_norm": 3.944565534591675,
3102
+ "learning_rate": 2.1573398215733985e-06,
3103
+ "loss": 1.4142,
3104
+ "step": 8660
3105
+ },
3106
+ {
3107
+ "epoch": 2.7150453550203313,
3108
+ "grad_norm": 3.3899853229522705,
3109
+ "learning_rate": 2.110995249681381e-06,
3110
+ "loss": 1.41,
3111
+ "step": 8680
3112
+ },
3113
+ {
3114
+ "epoch": 2.7213012198936504,
3115
+ "grad_norm": 3.7669284343719482,
3116
+ "learning_rate": 2.064650677789364e-06,
3117
+ "loss": 1.434,
3118
+ "step": 8700
3119
+ },
3120
+ {
3121
+ "epoch": 2.727557084766969,
3122
+ "grad_norm": 4.533022880554199,
3123
+ "learning_rate": 2.018306105897347e-06,
3124
+ "loss": 1.4266,
3125
+ "step": 8720
3126
+ },
3127
+ {
3128
+ "epoch": 2.7338129496402876,
3129
+ "grad_norm": 4.264920711517334,
3130
+ "learning_rate": 1.97196153400533e-06,
3131
+ "loss": 1.3866,
3132
+ "step": 8740
3133
+ },
3134
+ {
3135
+ "epoch": 2.7400688145136067,
3136
+ "grad_norm": 3.9496846199035645,
3137
+ "learning_rate": 1.9256169621133124e-06,
3138
+ "loss": 1.3872,
3139
+ "step": 8760
3140
+ },
3141
+ {
3142
+ "epoch": 2.7463246793869254,
3143
+ "grad_norm": 3.966773271560669,
3144
+ "learning_rate": 1.8792723902212956e-06,
3145
+ "loss": 1.4064,
3146
+ "step": 8780
3147
+ },
3148
+ {
3149
+ "epoch": 2.752580544260244,
3150
+ "grad_norm": 3.9621760845184326,
3151
+ "learning_rate": 1.8329278183292783e-06,
3152
+ "loss": 1.372,
3153
+ "step": 8800
3154
+ },
3155
+ {
3156
+ "epoch": 2.7588364091335627,
3157
+ "grad_norm": 3.506624698638916,
3158
+ "learning_rate": 1.7865832464372612e-06,
3159
+ "loss": 1.355,
3160
+ "step": 8820
3161
+ },
3162
+ {
3163
+ "epoch": 2.7650922740068813,
3164
+ "grad_norm": 4.213022708892822,
3165
+ "learning_rate": 1.740238674545244e-06,
3166
+ "loss": 1.4216,
3167
+ "step": 8840
3168
+ },
3169
+ {
3170
+ "epoch": 2.7713481388802004,
3171
+ "grad_norm": 4.381209373474121,
3172
+ "learning_rate": 1.693894102653227e-06,
3173
+ "loss": 1.3929,
3174
+ "step": 8860
3175
+ },
3176
+ {
3177
+ "epoch": 2.777604003753519,
3178
+ "grad_norm": 3.455552101135254,
3179
+ "learning_rate": 1.6475495307612097e-06,
3180
+ "loss": 1.3575,
3181
+ "step": 8880
3182
+ },
3183
+ {
3184
+ "epoch": 2.7838598686268377,
3185
+ "grad_norm": 4.170933723449707,
3186
+ "learning_rate": 1.6012049588691924e-06,
3187
+ "loss": 1.3772,
3188
+ "step": 8900
3189
+ },
3190
+ {
3191
+ "epoch": 2.7901157335001563,
3192
+ "grad_norm": 3.778902292251587,
3193
+ "learning_rate": 1.5548603869771755e-06,
3194
+ "loss": 1.3941,
3195
+ "step": 8920
3196
+ },
3197
+ {
3198
+ "epoch": 2.796371598373475,
3199
+ "grad_norm": 3.5581791400909424,
3200
+ "learning_rate": 1.5085158150851583e-06,
3201
+ "loss": 1.3799,
3202
+ "step": 8940
3203
+ },
3204
+ {
3205
+ "epoch": 2.802627463246794,
3206
+ "grad_norm": 3.6567673683166504,
3207
+ "learning_rate": 1.4621712431931412e-06,
3208
+ "loss": 1.3902,
3209
+ "step": 8960
3210
+ },
3211
+ {
3212
+ "epoch": 2.8088833281201127,
3213
+ "grad_norm": 4.234646797180176,
3214
+ "learning_rate": 1.415826671301124e-06,
3215
+ "loss": 1.3859,
3216
+ "step": 8980
3217
+ },
3218
+ {
3219
+ "epoch": 2.8151391929934313,
3220
+ "grad_norm": 3.7421681880950928,
3221
+ "learning_rate": 1.369482099409107e-06,
3222
+ "loss": 1.357,
3223
+ "step": 9000
3224
+ },
3225
+ {
3226
+ "epoch": 2.8151391929934313,
3227
+ "eval_loss": 0.5130746364593506,
3228
+ "eval_runtime": 30.1582,
3229
+ "eval_samples_per_second": 16.049,
3230
+ "eval_steps_per_second": 4.012,
3231
+ "step": 9000
3232
+ },
3233
+ {
3234
+ "epoch": 2.82139505786675,
3235
+ "grad_norm": 4.607457160949707,
3236
+ "learning_rate": 1.3231375275170896e-06,
3237
+ "loss": 1.4083,
3238
+ "step": 9020
3239
+ },
3240
+ {
3241
+ "epoch": 2.8276509227400686,
3242
+ "grad_norm": 3.6216139793395996,
3243
+ "learning_rate": 1.2767929556250724e-06,
3244
+ "loss": 1.3613,
3245
+ "step": 9040
3246
+ },
3247
+ {
3248
+ "epoch": 2.8339067876133877,
3249
+ "grad_norm": 4.228906154632568,
3250
+ "learning_rate": 1.2304483837330553e-06,
3251
+ "loss": 1.4016,
3252
+ "step": 9060
3253
+ },
3254
+ {
3255
+ "epoch": 2.8401626524867063,
3256
+ "grad_norm": 4.767721652984619,
3257
+ "learning_rate": 1.1841038118410383e-06,
3258
+ "loss": 1.3985,
3259
+ "step": 9080
3260
+ },
3261
+ {
3262
+ "epoch": 2.846418517360025,
3263
+ "grad_norm": 3.784308671951294,
3264
+ "learning_rate": 1.137759239949021e-06,
3265
+ "loss": 1.3853,
3266
+ "step": 9100
3267
+ },
3268
+ {
3269
+ "epoch": 2.852674382233344,
3270
+ "grad_norm": 4.14461088180542,
3271
+ "learning_rate": 1.091414668057004e-06,
3272
+ "loss": 1.3303,
3273
+ "step": 9120
3274
+ },
3275
+ {
3276
+ "epoch": 2.8589302471066627,
3277
+ "grad_norm": 3.3787248134613037,
3278
+ "learning_rate": 1.0450700961649869e-06,
3279
+ "loss": 1.4045,
3280
+ "step": 9140
3281
+ },
3282
+ {
3283
+ "epoch": 2.8651861119799813,
3284
+ "grad_norm": 3.9108362197875977,
3285
+ "learning_rate": 9.987255242729696e-07,
3286
+ "loss": 1.3806,
3287
+ "step": 9160
3288
+ },
3289
+ {
3290
+ "epoch": 2.8714419768533,
3291
+ "grad_norm": 3.8654673099517822,
3292
+ "learning_rate": 9.523809523809525e-07,
3293
+ "loss": 1.367,
3294
+ "step": 9180
3295
+ },
3296
+ {
3297
+ "epoch": 2.8776978417266186,
3298
+ "grad_norm": 3.9487152099609375,
3299
+ "learning_rate": 9.060363804889354e-07,
3300
+ "loss": 1.4199,
3301
+ "step": 9200
3302
+ },
3303
+ {
3304
+ "epoch": 2.8839537065999377,
3305
+ "grad_norm": 3.804671049118042,
3306
+ "learning_rate": 8.596918085969181e-07,
3307
+ "loss": 1.4252,
3308
+ "step": 9220
3309
+ },
3310
+ {
3311
+ "epoch": 2.8902095714732563,
3312
+ "grad_norm": 3.471071243286133,
3313
+ "learning_rate": 8.13347236704901e-07,
3314
+ "loss": 1.4102,
3315
+ "step": 9240
3316
+ },
3317
+ {
3318
+ "epoch": 2.896465436346575,
3319
+ "grad_norm": 3.498152256011963,
3320
+ "learning_rate": 7.670026648128838e-07,
3321
+ "loss": 1.3805,
3322
+ "step": 9260
3323
+ },
3324
+ {
3325
+ "epoch": 2.9027213012198936,
3326
+ "grad_norm": 4.2036871910095215,
3327
+ "learning_rate": 7.206580929208668e-07,
3328
+ "loss": 1.3746,
3329
+ "step": 9280
3330
+ },
3331
+ {
3332
+ "epoch": 2.908977166093212,
3333
+ "grad_norm": 3.783219337463379,
3334
+ "learning_rate": 6.743135210288496e-07,
3335
+ "loss": 1.3919,
3336
+ "step": 9300
3337
+ },
3338
+ {
3339
+ "epoch": 2.9152330309665313,
3340
+ "grad_norm": 3.6748569011688232,
3341
+ "learning_rate": 6.279689491368323e-07,
3342
+ "loss": 1.3889,
3343
+ "step": 9320
3344
+ },
3345
+ {
3346
+ "epoch": 2.92148889583985,
3347
+ "grad_norm": 3.686070680618286,
3348
+ "learning_rate": 5.816243772448153e-07,
3349
+ "loss": 1.4083,
3350
+ "step": 9340
3351
+ },
3352
+ {
3353
+ "epoch": 2.9277447607131686,
3354
+ "grad_norm": 3.854691505432129,
3355
+ "learning_rate": 5.352798053527981e-07,
3356
+ "loss": 1.3814,
3357
+ "step": 9360
3358
+ },
3359
+ {
3360
+ "epoch": 2.934000625586487,
3361
+ "grad_norm": 4.229208946228027,
3362
+ "learning_rate": 4.88935233460781e-07,
3363
+ "loss": 1.3687,
3364
+ "step": 9380
3365
+ },
3366
+ {
3367
+ "epoch": 2.940256490459806,
3368
+ "grad_norm": 4.185445308685303,
3369
+ "learning_rate": 4.425906615687638e-07,
3370
+ "loss": 1.4074,
3371
+ "step": 9400
3372
+ },
3373
+ {
3374
+ "epoch": 2.946512355333125,
3375
+ "grad_norm": 4.26198673248291,
3376
+ "learning_rate": 3.9624608967674663e-07,
3377
+ "loss": 1.3865,
3378
+ "step": 9420
3379
+ },
3380
+ {
3381
+ "epoch": 2.9527682202064436,
3382
+ "grad_norm": 4.7634735107421875,
3383
+ "learning_rate": 3.4990151778472947e-07,
3384
+ "loss": 1.3857,
3385
+ "step": 9440
3386
+ },
3387
+ {
3388
+ "epoch": 2.9590240850797622,
3389
+ "grad_norm": 3.629460573196411,
3390
+ "learning_rate": 3.0355694589271236e-07,
3391
+ "loss": 1.4056,
3392
+ "step": 9460
3393
+ },
3394
+ {
3395
+ "epoch": 2.965279949953081,
3396
+ "grad_norm": 3.930769443511963,
3397
+ "learning_rate": 2.572123740006952e-07,
3398
+ "loss": 1.3554,
3399
+ "step": 9480
3400
+ },
3401
+ {
3402
+ "epoch": 2.9715358148263995,
3403
+ "grad_norm": 3.6116929054260254,
3404
+ "learning_rate": 2.1086780210867804e-07,
3405
+ "loss": 1.3699,
3406
+ "step": 9500
3407
+ },
3408
+ {
3409
+ "epoch": 2.9777916796997186,
3410
+ "grad_norm": 4.0823073387146,
3411
+ "learning_rate": 1.6452323021666087e-07,
3412
+ "loss": 1.4166,
3413
+ "step": 9520
3414
+ },
3415
+ {
3416
+ "epoch": 2.9840475445730372,
3417
+ "grad_norm": 3.9738993644714355,
3418
+ "learning_rate": 1.1817865832464373e-07,
3419
+ "loss": 1.3666,
3420
+ "step": 9540
3421
+ },
3422
+ {
3423
+ "epoch": 2.990303409446356,
3424
+ "grad_norm": 4.159948348999023,
3425
+ "learning_rate": 7.183408643262659e-08,
3426
+ "loss": 1.3622,
3427
+ "step": 9560
3428
+ },
3429
+ {
3430
+ "epoch": 2.996559274319675,
3431
+ "grad_norm": 3.861499309539795,
3432
+ "learning_rate": 2.5489514540609434e-08,
3433
+ "loss": 1.3759,
3434
+ "step": 9580
3435
+ }
3436
+ ],
3437
+ "logging_steps": 20,
3438
+ "max_steps": 9591,
3439
+ "num_input_tokens_seen": 0,
3440
+ "num_train_epochs": 3,
3441
+ "save_steps": 1000,
3442
+ "stateful_callbacks": {
3443
+ "TrainerControl": {
3444
+ "args": {
3445
+ "should_epoch_stop": false,
3446
+ "should_evaluate": false,
3447
+ "should_log": false,
3448
+ "should_save": true,
3449
+ "should_training_stop": true
3450
+ },
3451
+ "attributes": {}
3452
+ }
3453
+ },
3454
+ "total_flos": 5.406598441985901e+18,
3455
+ "train_batch_size": 4,
3456
+ "trial_name": null,
3457
+ "trial_params": null
3458
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57363124f6b43643594fbea7545c903dfa250faee074cef055372a897831ace
3
+ size 5368