Anwaarma commited on
Commit
e2dd5c7
·
verified ·
1 Parent(s): 0e045de

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  run-0/checkpoint-12917/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  run-0/checkpoint-12917/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ run-0/checkpoint-2153/tokenizer.json filter=lfs diff=lfs merge=lfs -text
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fcbda655fa3b38e69010b100913398dff23ed086086397096a8cb589bf4f005
3
  size 4943290800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b20a78ea3a31bb1c09e578266cd0558034831cccfd22ae6e02dd5071e422c3
3
  size 4943290800
run-0/checkpoint-2153/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 64,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 16,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 128009,
25
+ "pretraining_tp": 1,
26
+ "problem_type": "single_label_classification",
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": {
29
+ "factor": 32.0,
30
+ "high_freq_factor": 4.0,
31
+ "low_freq_factor": 1.0,
32
+ "original_max_position_embeddings": 8192,
33
+ "rope_type": "llama3"
34
+ },
35
+ "rope_theta": 500000.0,
36
+ "tie_word_embeddings": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.51.3",
39
+ "use_cache": true,
40
+ "vocab_size": 128256
41
+ }
run-0/checkpoint-2153/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b20a78ea3a31bb1c09e578266cd0558034831cccfd22ae6e02dd5071e422c3
3
+ size 4943290800
run-0/checkpoint-2153/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98e67b6967bf65a4262cd2504e3551d371ca6d4ad6b4916e4579e9d4ce943bb
3
+ size 9886675962
run-0/checkpoint-2153/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ae1b361f0fce6d8e385e172a63c0261c23666e81c841f3b4ed4f240cfd0496
3
+ size 14244
run-0/checkpoint-2153/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c10cefc0a39ad044a13ef36542ecc644e67abff158e307d5fc769036080d1b3e
3
+ size 988
run-0/checkpoint-2153/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de624e2b1ceb379062807b91936a8473dd169de8c52c85109e95f826aff8fce
3
+ size 1064
run-0/checkpoint-2153/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
+ }
run-0/checkpoint-2153/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe07b35a61be0ec850f12e9379be8ca47b4ef845b20f0d146a8a2bfdb0e7e3e
3
+ size 17210195
run-0/checkpoint-2153/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": "PreTrainedTokenizer"
2064
+ }
run-0/checkpoint-2153/trainer_state.json ADDED
@@ -0,0 +1,1562 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2153,
3
+ "best_metric": 0.7269367449311068,
4
+ "best_model_checkpoint": "./llama-en/run-0/checkpoint-2153",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2153,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.004644681839294009,
14
+ "grad_norm": 211.72206115722656,
15
+ "learning_rate": 2.1452088429984463e-05,
16
+ "loss": 3.3072,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.009289363678588018,
21
+ "grad_norm": 35.370540618896484,
22
+ "learning_rate": 2.1402223045442423e-05,
23
+ "loss": 1.4348,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.013934045517882025,
28
+ "grad_norm": 24.980289459228516,
29
+ "learning_rate": 2.1352357660900386e-05,
30
+ "loss": 0.6679,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.018578727357176035,
35
+ "grad_norm": 65.78897857666016,
36
+ "learning_rate": 2.130249227635835e-05,
37
+ "loss": 0.8143,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.023223409196470042,
42
+ "grad_norm": 75.61241149902344,
43
+ "learning_rate": 2.1252626891816313e-05,
44
+ "loss": 1.1707,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.02786809103576405,
49
+ "grad_norm": 36.94132614135742,
50
+ "learning_rate": 2.1202761507274276e-05,
51
+ "loss": 1.2288,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.032512772875058056,
56
+ "grad_norm": 19.907167434692383,
57
+ "learning_rate": 2.1152896122732236e-05,
58
+ "loss": 0.7936,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.03715745471435207,
63
+ "grad_norm": 37.62481689453125,
64
+ "learning_rate": 2.11030307381902e-05,
65
+ "loss": 0.6593,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.04180213655364608,
70
+ "grad_norm": 63.50526809692383,
71
+ "learning_rate": 2.1053165353648163e-05,
72
+ "loss": 0.785,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.046446818392940084,
77
+ "grad_norm": 12.145021438598633,
78
+ "learning_rate": 2.1003299969106126e-05,
79
+ "loss": 0.9091,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.05109150023223409,
84
+ "grad_norm": 21.99431037902832,
85
+ "learning_rate": 2.095343458456409e-05,
86
+ "loss": 0.6404,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.0557361820715281,
91
+ "grad_norm": 50.777015686035156,
92
+ "learning_rate": 2.090356920002205e-05,
93
+ "loss": 0.7184,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.06038086391082211,
98
+ "grad_norm": 15.046972274780273,
99
+ "learning_rate": 2.0853703815480013e-05,
100
+ "loss": 0.7755,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.06502554575011611,
105
+ "grad_norm": 13.137744903564453,
106
+ "learning_rate": 2.0803838430937976e-05,
107
+ "loss": 0.5799,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.06967022758941012,
112
+ "grad_norm": 35.85881042480469,
113
+ "learning_rate": 2.075397304639594e-05,
114
+ "loss": 0.6626,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.07431490942870414,
119
+ "grad_norm": 21.24566650390625,
120
+ "learning_rate": 2.0704107661853903e-05,
121
+ "loss": 0.6553,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.07895959126799815,
126
+ "grad_norm": 24.310070037841797,
127
+ "learning_rate": 2.0654242277311863e-05,
128
+ "loss": 0.819,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.08360427310729215,
133
+ "grad_norm": 33.82474899291992,
134
+ "learning_rate": 2.0604376892769826e-05,
135
+ "loss": 0.5822,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.08824895494658616,
140
+ "grad_norm": 36.930877685546875,
141
+ "learning_rate": 2.055451150822779e-05,
142
+ "loss": 0.8236,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.09289363678588017,
147
+ "grad_norm": 32.972572326660156,
148
+ "learning_rate": 2.0504646123685753e-05,
149
+ "loss": 0.6895,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.09753831862517418,
154
+ "grad_norm": 37.615421295166016,
155
+ "learning_rate": 2.0454780739143716e-05,
156
+ "loss": 0.7972,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.10218300046446818,
161
+ "grad_norm": 40.067115783691406,
162
+ "learning_rate": 2.0404915354601676e-05,
163
+ "loss": 0.6308,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.10682768230376219,
168
+ "grad_norm": 12.833575248718262,
169
+ "learning_rate": 2.035504997005964e-05,
170
+ "loss": 0.6524,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.1114723641430562,
175
+ "grad_norm": 18.700349807739258,
176
+ "learning_rate": 2.0305184585517603e-05,
177
+ "loss": 0.8317,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.1161170459823502,
182
+ "grad_norm": 29.2730770111084,
183
+ "learning_rate": 2.0255319200975566e-05,
184
+ "loss": 0.6525,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.12076172782164422,
189
+ "grad_norm": 17.582622528076172,
190
+ "learning_rate": 2.020545381643353e-05,
191
+ "loss": 0.5362,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.12540640966093822,
196
+ "grad_norm": 23.002281188964844,
197
+ "learning_rate": 2.015558843189149e-05,
198
+ "loss": 0.6031,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.13005109150023222,
203
+ "grad_norm": 56.693634033203125,
204
+ "learning_rate": 2.0105723047349453e-05,
205
+ "loss": 0.5942,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.13469577333952623,
210
+ "grad_norm": 34.477684020996094,
211
+ "learning_rate": 2.0055857662807416e-05,
212
+ "loss": 0.6535,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.13934045517882024,
217
+ "grad_norm": 29.715768814086914,
218
+ "learning_rate": 2.000599227826538e-05,
219
+ "loss": 0.5852,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.14398513701811425,
224
+ "grad_norm": 17.289409637451172,
225
+ "learning_rate": 1.9956126893723343e-05,
226
+ "loss": 0.6004,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.14862981885740828,
231
+ "grad_norm": 7.364201068878174,
232
+ "learning_rate": 1.9906261509181306e-05,
233
+ "loss": 0.6761,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.1532745006967023,
238
+ "grad_norm": 21.19795799255371,
239
+ "learning_rate": 1.9856396124639266e-05,
240
+ "loss": 0.6105,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.1579191825359963,
245
+ "grad_norm": 15.903705596923828,
246
+ "learning_rate": 1.980653074009723e-05,
247
+ "loss": 0.6528,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.1625638643752903,
252
+ "grad_norm": 16.267425537109375,
253
+ "learning_rate": 1.9756665355555193e-05,
254
+ "loss": 0.5598,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.1672085462145843,
259
+ "grad_norm": 10.669220924377441,
260
+ "learning_rate": 1.9706799971013156e-05,
261
+ "loss": 1.3583,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.17185322805387832,
266
+ "grad_norm": 12.351362228393555,
267
+ "learning_rate": 1.965693458647112e-05,
268
+ "loss": 0.497,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.17649790989317232,
273
+ "grad_norm": 40.42892837524414,
274
+ "learning_rate": 1.960706920192908e-05,
275
+ "loss": 0.6024,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.18114259173246633,
280
+ "grad_norm": 14.722101211547852,
281
+ "learning_rate": 1.9557203817387043e-05,
282
+ "loss": 0.7695,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.18578727357176034,
287
+ "grad_norm": 30.782245635986328,
288
+ "learning_rate": 1.9507338432845006e-05,
289
+ "loss": 0.7731,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.19043195541105434,
294
+ "grad_norm": 11.219614028930664,
295
+ "learning_rate": 1.945747304830297e-05,
296
+ "loss": 0.7396,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.19507663725034835,
301
+ "grad_norm": 10.30286979675293,
302
+ "learning_rate": 1.9407607663760933e-05,
303
+ "loss": 0.6506,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.19972131908964236,
308
+ "grad_norm": 12.239933967590332,
309
+ "learning_rate": 1.9357742279218893e-05,
310
+ "loss": 0.6578,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.20436600092893636,
315
+ "grad_norm": 35.0018196105957,
316
+ "learning_rate": 1.9307876894676856e-05,
317
+ "loss": 0.6483,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.20901068276823037,
322
+ "grad_norm": 14.58996295928955,
323
+ "learning_rate": 1.925801151013482e-05,
324
+ "loss": 0.5272,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.21365536460752438,
329
+ "grad_norm": 41.34626770019531,
330
+ "learning_rate": 1.9208146125592783e-05,
331
+ "loss": 0.6509,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.21830004644681839,
336
+ "grad_norm": 10.75104808807373,
337
+ "learning_rate": 1.9158280741050746e-05,
338
+ "loss": 0.6296,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.2229447282861124,
343
+ "grad_norm": 92.5117416381836,
344
+ "learning_rate": 1.9108415356508706e-05,
345
+ "loss": 0.6245,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.2275894101254064,
350
+ "grad_norm": 53.16917419433594,
351
+ "learning_rate": 1.905854997196667e-05,
352
+ "loss": 0.4873,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.2322340919647004,
357
+ "grad_norm": 27.867658615112305,
358
+ "learning_rate": 1.9008684587424633e-05,
359
+ "loss": 0.966,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.2368787738039944,
364
+ "grad_norm": 21.71831703186035,
365
+ "learning_rate": 1.8958819202882596e-05,
366
+ "loss": 0.7467,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.24152345564328845,
371
+ "grad_norm": 34.49421310424805,
372
+ "learning_rate": 1.890895381834056e-05,
373
+ "loss": 0.4829,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.24616813748258246,
378
+ "grad_norm": 65.69181823730469,
379
+ "learning_rate": 1.885908843379852e-05,
380
+ "loss": 0.6355,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.25081281932187643,
385
+ "grad_norm": 19.390453338623047,
386
+ "learning_rate": 1.8809223049256483e-05,
387
+ "loss": 0.6824,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.25545750116117044,
392
+ "grad_norm": 6.086198806762695,
393
+ "learning_rate": 1.8759357664714446e-05,
394
+ "loss": 0.4233,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.26010218300046445,
399
+ "grad_norm": 36.49763870239258,
400
+ "learning_rate": 1.870949228017241e-05,
401
+ "loss": 0.7479,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.26474686483975846,
406
+ "grad_norm": 44.0486946105957,
407
+ "learning_rate": 1.8659626895630373e-05,
408
+ "loss": 0.5992,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.26939154667905246,
413
+ "grad_norm": 56.75907897949219,
414
+ "learning_rate": 1.8609761511088333e-05,
415
+ "loss": 0.8668,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.27403622851834647,
420
+ "grad_norm": 14.17831802368164,
421
+ "learning_rate": 1.8559896126546296e-05,
422
+ "loss": 0.4972,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.2786809103576405,
427
+ "grad_norm": 24.53505516052246,
428
+ "learning_rate": 1.851003074200426e-05,
429
+ "loss": 0.5039,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.2833255921969345,
434
+ "grad_norm": 16.249000549316406,
435
+ "learning_rate": 1.8460165357462223e-05,
436
+ "loss": 0.6435,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.2879702740362285,
441
+ "grad_norm": 22.719852447509766,
442
+ "learning_rate": 1.8410299972920186e-05,
443
+ "loss": 0.5606,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.29261495587552255,
448
+ "grad_norm": 21.95683479309082,
449
+ "learning_rate": 1.8360434588378146e-05,
450
+ "loss": 0.6237,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.29725963771481656,
455
+ "grad_norm": 17.5963077545166,
456
+ "learning_rate": 1.831056920383611e-05,
457
+ "loss": 0.5549,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.30190431955411057,
462
+ "grad_norm": 22.68503761291504,
463
+ "learning_rate": 1.8260703819294073e-05,
464
+ "loss": 0.5519,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.3065490013934046,
469
+ "grad_norm": 23.33054542541504,
470
+ "learning_rate": 1.8210838434752036e-05,
471
+ "loss": 0.7282,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.3111936832326986,
476
+ "grad_norm": 14.123784065246582,
477
+ "learning_rate": 1.816097305021e-05,
478
+ "loss": 0.5398,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.3158383650719926,
483
+ "grad_norm": 25.707509994506836,
484
+ "learning_rate": 1.811110766566796e-05,
485
+ "loss": 0.4855,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.3204830469112866,
490
+ "grad_norm": 11.704025268554688,
491
+ "learning_rate": 1.8061242281125923e-05,
492
+ "loss": 0.587,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.3251277287505806,
497
+ "grad_norm": 55.51290512084961,
498
+ "learning_rate": 1.8011376896583886e-05,
499
+ "loss": 0.6107,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.3297724105898746,
504
+ "grad_norm": 16.0389461517334,
505
+ "learning_rate": 1.796151151204185e-05,
506
+ "loss": 0.558,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.3344170924291686,
511
+ "grad_norm": 70.73486328125,
512
+ "learning_rate": 1.7911646127499813e-05,
513
+ "loss": 0.6595,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.3390617742684626,
518
+ "grad_norm": 24.04580307006836,
519
+ "learning_rate": 1.7861780742957773e-05,
520
+ "loss": 0.6235,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.34370645610775663,
525
+ "grad_norm": 17.440170288085938,
526
+ "learning_rate": 1.7811915358415736e-05,
527
+ "loss": 0.5414,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.34835113794705064,
532
+ "grad_norm": 25.72278594970703,
533
+ "learning_rate": 1.77620499738737e-05,
534
+ "loss": 0.6179,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.35299581978634464,
539
+ "grad_norm": 25.754533767700195,
540
+ "learning_rate": 1.7712184589331663e-05,
541
+ "loss": 0.6862,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.35764050162563865,
546
+ "grad_norm": 17.074621200561523,
547
+ "learning_rate": 1.7662319204789626e-05,
548
+ "loss": 0.4386,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.36228518346493266,
553
+ "grad_norm": 25.758764266967773,
554
+ "learning_rate": 1.7612453820247586e-05,
555
+ "loss": 0.5667,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.36692986530422667,
560
+ "grad_norm": 74.62012481689453,
561
+ "learning_rate": 1.756258843570555e-05,
562
+ "loss": 0.7956,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.3715745471435207,
567
+ "grad_norm": 22.15366554260254,
568
+ "learning_rate": 1.7512723051163513e-05,
569
+ "loss": 0.6652,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.3762192289828147,
574
+ "grad_norm": 22.554166793823242,
575
+ "learning_rate": 1.7462857666621476e-05,
576
+ "loss": 0.7547,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.3808639108221087,
581
+ "grad_norm": 3.1268579959869385,
582
+ "learning_rate": 1.741299228207944e-05,
583
+ "loss": 0.6936,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.3855085926614027,
588
+ "grad_norm": 16.36742401123047,
589
+ "learning_rate": 1.73631268975374e-05,
590
+ "loss": 0.4024,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.3901532745006967,
595
+ "grad_norm": 35.942108154296875,
596
+ "learning_rate": 1.7313261512995363e-05,
597
+ "loss": 0.9718,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.3947979563399907,
602
+ "grad_norm": 32.59349060058594,
603
+ "learning_rate": 1.7263396128453326e-05,
604
+ "loss": 0.4242,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.3994426381792847,
609
+ "grad_norm": 14.402030944824219,
610
+ "learning_rate": 1.721353074391129e-05,
611
+ "loss": 0.4503,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.4040873200185787,
616
+ "grad_norm": 22.52005386352539,
617
+ "learning_rate": 1.7163665359369253e-05,
618
+ "loss": 0.7052,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.40873200185787273,
623
+ "grad_norm": 14.834693908691406,
624
+ "learning_rate": 1.7113799974827213e-05,
625
+ "loss": 0.5847,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.41337668369716674,
630
+ "grad_norm": 10.242630958557129,
631
+ "learning_rate": 1.7063934590285176e-05,
632
+ "loss": 0.6775,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.41802136553646074,
637
+ "grad_norm": 19.234588623046875,
638
+ "learning_rate": 1.701406920574314e-05,
639
+ "loss": 0.5771,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.42266604737575475,
644
+ "grad_norm": 26.22275161743164,
645
+ "learning_rate": 1.6964203821201103e-05,
646
+ "loss": 0.6148,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.42731072921504876,
651
+ "grad_norm": 41.367008209228516,
652
+ "learning_rate": 1.6914338436659066e-05,
653
+ "loss": 0.6231,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.43195541105434276,
658
+ "grad_norm": 20.041852951049805,
659
+ "learning_rate": 1.6864473052117026e-05,
660
+ "loss": 0.4405,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.43660009289363677,
665
+ "grad_norm": 58.10574722290039,
666
+ "learning_rate": 1.681460766757499e-05,
667
+ "loss": 0.5475,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.4412447747329308,
672
+ "grad_norm": 39.26423645019531,
673
+ "learning_rate": 1.6764742283032953e-05,
674
+ "loss": 0.51,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.4458894565722248,
679
+ "grad_norm": 23.290077209472656,
680
+ "learning_rate": 1.6714876898490916e-05,
681
+ "loss": 0.6312,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.4505341384115188,
686
+ "grad_norm": 13.668265342712402,
687
+ "learning_rate": 1.666501151394888e-05,
688
+ "loss": 0.5317,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.4551788202508128,
693
+ "grad_norm": 53.51641082763672,
694
+ "learning_rate": 1.661514612940684e-05,
695
+ "loss": 0.6003,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.4598235020901068,
700
+ "grad_norm": 41.4106330871582,
701
+ "learning_rate": 1.6565280744864803e-05,
702
+ "loss": 0.4173,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.4644681839294008,
707
+ "grad_norm": 14.340582847595215,
708
+ "learning_rate": 1.6515415360322766e-05,
709
+ "loss": 0.8924,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.4691128657686948,
714
+ "grad_norm": 14.345767974853516,
715
+ "learning_rate": 1.646554997578073e-05,
716
+ "loss": 0.6567,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.4737575476079888,
721
+ "grad_norm": 7.988738059997559,
722
+ "learning_rate": 1.6415684591238693e-05,
723
+ "loss": 0.5343,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.47840222944728283,
728
+ "grad_norm": 17.18528938293457,
729
+ "learning_rate": 1.6365819206696653e-05,
730
+ "loss": 0.5373,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.4830469112865769,
735
+ "grad_norm": 3.3986854553222656,
736
+ "learning_rate": 1.6315953822154616e-05,
737
+ "loss": 0.4882,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.4876915931258709,
742
+ "grad_norm": 26.01762580871582,
743
+ "learning_rate": 1.626608843761258e-05,
744
+ "loss": 0.6547,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.4923362749651649,
749
+ "grad_norm": 54.30781936645508,
750
+ "learning_rate": 1.6216223053070543e-05,
751
+ "loss": 0.8929,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.4969809568044589,
756
+ "grad_norm": 23.58662223815918,
757
+ "learning_rate": 1.6166357668528506e-05,
758
+ "loss": 0.6557,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.5016256386437529,
763
+ "grad_norm": 18.75876808166504,
764
+ "learning_rate": 1.6116492283986466e-05,
765
+ "loss": 0.7164,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.5062703204830469,
770
+ "grad_norm": 31.582334518432617,
771
+ "learning_rate": 1.606662689944443e-05,
772
+ "loss": 0.6538,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.5109150023223409,
777
+ "grad_norm": 11.017553329467773,
778
+ "learning_rate": 1.6016761514902393e-05,
779
+ "loss": 0.6416,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.5155596841616349,
784
+ "grad_norm": 16.78295135498047,
785
+ "learning_rate": 1.5966896130360356e-05,
786
+ "loss": 0.5108,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.5202043660009289,
791
+ "grad_norm": 12.465627670288086,
792
+ "learning_rate": 1.591703074581832e-05,
793
+ "loss": 0.6153,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.5248490478402229,
798
+ "grad_norm": 17.042451858520508,
799
+ "learning_rate": 1.586716536127628e-05,
800
+ "loss": 0.6711,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.5294937296795169,
805
+ "grad_norm": 10.192228317260742,
806
+ "learning_rate": 1.5817299976734243e-05,
807
+ "loss": 0.4773,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.5341384115188109,
812
+ "grad_norm": 57.02873611450195,
813
+ "learning_rate": 1.5767434592192206e-05,
814
+ "loss": 0.6164,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.5387830933581049,
819
+ "grad_norm": 18.456907272338867,
820
+ "learning_rate": 1.571756920765017e-05,
821
+ "loss": 0.5722,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.5434277751973989,
826
+ "grad_norm": 14.433390617370605,
827
+ "learning_rate": 1.5667703823108133e-05,
828
+ "loss": 0.4521,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.5480724570366929,
833
+ "grad_norm": 9.868057250976562,
834
+ "learning_rate": 1.5617838438566093e-05,
835
+ "loss": 0.5333,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.552717138875987,
840
+ "grad_norm": 10.04655647277832,
841
+ "learning_rate": 1.5567973054024056e-05,
842
+ "loss": 0.6211,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.557361820715281,
847
+ "grad_norm": 3.9764537811279297,
848
+ "learning_rate": 1.551810766948202e-05,
849
+ "loss": 0.5288,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.562006502554575,
854
+ "grad_norm": 75.85688018798828,
855
+ "learning_rate": 1.5468242284939983e-05,
856
+ "loss": 0.5062,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.566651184393869,
861
+ "grad_norm": 58.41361999511719,
862
+ "learning_rate": 1.5418376900397946e-05,
863
+ "loss": 0.6781,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.571295866233163,
868
+ "grad_norm": 21.685863494873047,
869
+ "learning_rate": 1.536851151585591e-05,
870
+ "loss": 0.6229,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.575940548072457,
875
+ "grad_norm": 56.589420318603516,
876
+ "learning_rate": 1.531864613131387e-05,
877
+ "loss": 0.6928,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.5805852299117511,
882
+ "grad_norm": 135.11924743652344,
883
+ "learning_rate": 1.527376728522604e-05,
884
+ "loss": 0.871,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.5852299117510451,
889
+ "grad_norm": 17.793853759765625,
890
+ "learning_rate": 1.5223901900684e-05,
891
+ "loss": 0.6875,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.5898745935903391,
896
+ "grad_norm": 184.71627807617188,
897
+ "learning_rate": 1.5174036516141963e-05,
898
+ "loss": 0.4991,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.5945192754296331,
903
+ "grad_norm": 9.668450355529785,
904
+ "learning_rate": 1.5124171131599925e-05,
905
+ "loss": 0.7237,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.5991639572689271,
910
+ "grad_norm": 23.586933135986328,
911
+ "learning_rate": 1.5074305747057888e-05,
912
+ "loss": 0.5921,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.6038086391082211,
917
+ "grad_norm": 33.03472137451172,
918
+ "learning_rate": 1.502444036251585e-05,
919
+ "loss": 0.5426,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.6084533209475151,
924
+ "grad_norm": 11.148355484008789,
925
+ "learning_rate": 1.4974574977973813e-05,
926
+ "loss": 0.6081,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.6130980027868091,
931
+ "grad_norm": 17.641267776489258,
932
+ "learning_rate": 1.4924709593431777e-05,
933
+ "loss": 0.5492,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.6177426846261032,
938
+ "grad_norm": 11.775382041931152,
939
+ "learning_rate": 1.4874844208889738e-05,
940
+ "loss": 0.5168,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.6223873664653972,
945
+ "grad_norm": 13.548938751220703,
946
+ "learning_rate": 1.4824978824347698e-05,
947
+ "loss": 0.6428,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.6270320483046912,
952
+ "grad_norm": 38.070335388183594,
953
+ "learning_rate": 1.4775113439805662e-05,
954
+ "loss": 0.4728,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.6316767301439852,
959
+ "grad_norm": 19.39068031311035,
960
+ "learning_rate": 1.4725248055263625e-05,
961
+ "loss": 0.4786,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.6363214119832792,
966
+ "grad_norm": 22.63104248046875,
967
+ "learning_rate": 1.4675382670721587e-05,
968
+ "loss": 0.565,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.6409660938225732,
973
+ "grad_norm": 37.99357986450195,
974
+ "learning_rate": 1.462551728617955e-05,
975
+ "loss": 0.3932,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.6456107756618672,
980
+ "grad_norm": 2.9193620681762695,
981
+ "learning_rate": 1.4575651901637512e-05,
982
+ "loss": 0.3625,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.6502554575011612,
987
+ "grad_norm": 46.6943473815918,
988
+ "learning_rate": 1.4525786517095475e-05,
989
+ "loss": 0.886,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.6549001393404552,
994
+ "grad_norm": 22.397979736328125,
995
+ "learning_rate": 1.4475921132553438e-05,
996
+ "loss": 0.7012,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.6595448211797492,
1001
+ "grad_norm": 9.515957832336426,
1002
+ "learning_rate": 1.44260557480114e-05,
1003
+ "loss": 0.6053,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.6641895030190432,
1008
+ "grad_norm": 12.916342735290527,
1009
+ "learning_rate": 1.4376190363469363e-05,
1010
+ "loss": 0.5694,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.6688341848583372,
1015
+ "grad_norm": 37.17584991455078,
1016
+ "learning_rate": 1.4326324978927325e-05,
1017
+ "loss": 0.5905,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.6734788666976312,
1022
+ "grad_norm": 37.41575622558594,
1023
+ "learning_rate": 1.4276459594385288e-05,
1024
+ "loss": 0.5446,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.6781235485369252,
1029
+ "grad_norm": 16.848384857177734,
1030
+ "learning_rate": 1.4226594209843252e-05,
1031
+ "loss": 0.5074,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.6827682303762193,
1036
+ "grad_norm": 6.8437323570251465,
1037
+ "learning_rate": 1.4176728825301213e-05,
1038
+ "loss": 0.378,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.6874129122155133,
1043
+ "grad_norm": 17.651676177978516,
1044
+ "learning_rate": 1.4126863440759177e-05,
1045
+ "loss": 0.4868,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.6920575940548073,
1050
+ "grad_norm": 5.8376336097717285,
1051
+ "learning_rate": 1.407699805621714e-05,
1052
+ "loss": 0.6628,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.6967022758941013,
1057
+ "grad_norm": 12.156155586242676,
1058
+ "learning_rate": 1.4027132671675102e-05,
1059
+ "loss": 0.7202,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.7013469577333953,
1064
+ "grad_norm": 27.546836853027344,
1065
+ "learning_rate": 1.3977267287133065e-05,
1066
+ "loss": 0.5407,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.7059916395726893,
1071
+ "grad_norm": 10.75734806060791,
1072
+ "learning_rate": 1.3927401902591027e-05,
1073
+ "loss": 0.5132,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.7106363214119833,
1078
+ "grad_norm": 6.772491931915283,
1079
+ "learning_rate": 1.387753651804899e-05,
1080
+ "loss": 0.6341,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.7152810032512773,
1085
+ "grad_norm": 15.500252723693848,
1086
+ "learning_rate": 1.3827671133506953e-05,
1087
+ "loss": 0.5976,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.7199256850905713,
1092
+ "grad_norm": 2.9452760219573975,
1093
+ "learning_rate": 1.3777805748964915e-05,
1094
+ "loss": 0.4807,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.7245703669298653,
1099
+ "grad_norm": 11.288049697875977,
1100
+ "learning_rate": 1.3727940364422878e-05,
1101
+ "loss": 0.4815,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.7292150487691593,
1106
+ "grad_norm": 7.9401726722717285,
1107
+ "learning_rate": 1.367807497988084e-05,
1108
+ "loss": 0.4613,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.7338597306084533,
1113
+ "grad_norm": 17.873010635375977,
1114
+ "learning_rate": 1.3628209595338803e-05,
1115
+ "loss": 0.6516,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.7385044124477473,
1120
+ "grad_norm": 24.160341262817383,
1121
+ "learning_rate": 1.3578344210796767e-05,
1122
+ "loss": 0.55,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.7431490942870413,
1127
+ "grad_norm": 7.697661876678467,
1128
+ "learning_rate": 1.3528478826254728e-05,
1129
+ "loss": 0.4278,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.7477937761263354,
1134
+ "grad_norm": 32.532779693603516,
1135
+ "learning_rate": 1.3478613441712692e-05,
1136
+ "loss": 0.5394,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.7524384579656294,
1141
+ "grad_norm": 11.085630416870117,
1142
+ "learning_rate": 1.3428748057170653e-05,
1143
+ "loss": 0.4398,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.7570831398049234,
1148
+ "grad_norm": 13.244244575500488,
1149
+ "learning_rate": 1.3378882672628617e-05,
1150
+ "loss": 0.7832,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.7617278216442174,
1155
+ "grad_norm": 12.643896102905273,
1156
+ "learning_rate": 1.332901728808658e-05,
1157
+ "loss": 0.6907,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.7663725034835114,
1162
+ "grad_norm": 14.135263442993164,
1163
+ "learning_rate": 1.3279151903544542e-05,
1164
+ "loss": 0.4552,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.7710171853228054,
1169
+ "grad_norm": 40.20560073852539,
1170
+ "learning_rate": 1.3229286519002505e-05,
1171
+ "loss": 0.6304,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.7756618671620994,
1176
+ "grad_norm": 4.1568522453308105,
1177
+ "learning_rate": 1.3179421134460467e-05,
1178
+ "loss": 0.4987,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.7803065490013934,
1183
+ "grad_norm": 49.13134765625,
1184
+ "learning_rate": 1.312955574991843e-05,
1185
+ "loss": 0.4316,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.7849512308406874,
1190
+ "grad_norm": 24.75063705444336,
1191
+ "learning_rate": 1.3079690365376393e-05,
1192
+ "loss": 0.5864,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.7895959126799814,
1197
+ "grad_norm": 40.39198303222656,
1198
+ "learning_rate": 1.3029824980834355e-05,
1199
+ "loss": 0.6909,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.7942405945192754,
1204
+ "grad_norm": 29.39513397216797,
1205
+ "learning_rate": 1.2979959596292318e-05,
1206
+ "loss": 0.4545,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.7988852763585694,
1211
+ "grad_norm": 14.731855392456055,
1212
+ "learning_rate": 1.293009421175028e-05,
1213
+ "loss": 0.4467,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.8035299581978634,
1218
+ "grad_norm": 23.611068725585938,
1219
+ "learning_rate": 1.2880228827208243e-05,
1220
+ "loss": 0.5262,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.8081746400371574,
1225
+ "grad_norm": 6.023813247680664,
1226
+ "learning_rate": 1.2830363442666207e-05,
1227
+ "loss": 0.5964,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.8128193218764515,
1232
+ "grad_norm": 9.401269912719727,
1233
+ "learning_rate": 1.2780498058124168e-05,
1234
+ "loss": 0.5461,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.8174640037157455,
1239
+ "grad_norm": 54.0169792175293,
1240
+ "learning_rate": 1.2730632673582132e-05,
1241
+ "loss": 0.4554,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.8221086855550395,
1246
+ "grad_norm": 47.7166862487793,
1247
+ "learning_rate": 1.2680767289040093e-05,
1248
+ "loss": 0.4399,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.8267533673943335,
1253
+ "grad_norm": 9.918916702270508,
1254
+ "learning_rate": 1.2630901904498057e-05,
1255
+ "loss": 0.6007,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.8313980492336275,
1260
+ "grad_norm": 14.748363494873047,
1261
+ "learning_rate": 1.258103651995602e-05,
1262
+ "loss": 0.5345,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.8360427310729215,
1267
+ "grad_norm": 10.884316444396973,
1268
+ "learning_rate": 1.2531171135413982e-05,
1269
+ "loss": 0.5876,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.8406874129122155,
1274
+ "grad_norm": 21.72517204284668,
1275
+ "learning_rate": 1.2481305750871945e-05,
1276
+ "loss": 0.52,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.8453320947515095,
1281
+ "grad_norm": 16.430513381958008,
1282
+ "learning_rate": 1.2431440366329907e-05,
1283
+ "loss": 0.5887,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.8499767765908035,
1288
+ "grad_norm": 11.547590255737305,
1289
+ "learning_rate": 1.238157498178787e-05,
1290
+ "loss": 0.5356,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.8546214584300975,
1295
+ "grad_norm": 5.6605963706970215,
1296
+ "learning_rate": 1.2331709597245834e-05,
1297
+ "loss": 0.6289,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.8592661402693915,
1302
+ "grad_norm": 6.220414161682129,
1303
+ "learning_rate": 1.2281844212703795e-05,
1304
+ "loss": 0.4977,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.8639108221086855,
1309
+ "grad_norm": 11.676337242126465,
1310
+ "learning_rate": 1.2231978828161759e-05,
1311
+ "loss": 0.7576,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.8685555039479795,
1316
+ "grad_norm": 8.973514556884766,
1317
+ "learning_rate": 1.218211344361972e-05,
1318
+ "loss": 0.687,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.8732001857872735,
1323
+ "grad_norm": 2.6711742877960205,
1324
+ "learning_rate": 1.2132248059077684e-05,
1325
+ "loss": 0.5245,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.8778448676265675,
1330
+ "grad_norm": 28.208005905151367,
1331
+ "learning_rate": 1.2082382674535647e-05,
1332
+ "loss": 0.4551,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.8824895494658616,
1337
+ "grad_norm": 23.71241569519043,
1338
+ "learning_rate": 1.2032517289993609e-05,
1339
+ "loss": 0.529,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.8871342313051556,
1344
+ "grad_norm": 21.452486038208008,
1345
+ "learning_rate": 1.1982651905451572e-05,
1346
+ "loss": 0.5877,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.8917789131444496,
1351
+ "grad_norm": 9.46278190612793,
1352
+ "learning_rate": 1.1932786520909534e-05,
1353
+ "loss": 0.4907,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.8964235949837436,
1358
+ "grad_norm": 37.1279296875,
1359
+ "learning_rate": 1.1882921136367497e-05,
1360
+ "loss": 0.5092,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.9010682768230376,
1365
+ "grad_norm": 11.245513916015625,
1366
+ "learning_rate": 1.183305575182546e-05,
1367
+ "loss": 0.4723,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.9057129586623316,
1372
+ "grad_norm": 22.38329315185547,
1373
+ "learning_rate": 1.1783190367283422e-05,
1374
+ "loss": 0.5213,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.9103576405016256,
1379
+ "grad_norm": 9.722599029541016,
1380
+ "learning_rate": 1.1733324982741385e-05,
1381
+ "loss": 0.4407,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.9150023223409196,
1386
+ "grad_norm": 42.44827651977539,
1387
+ "learning_rate": 1.1683459598199349e-05,
1388
+ "loss": 0.5251,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.9196470041802136,
1393
+ "grad_norm": 18.725831985473633,
1394
+ "learning_rate": 1.163359421365731e-05,
1395
+ "loss": 0.5138,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.9242916860195076,
1400
+ "grad_norm": 11.360920906066895,
1401
+ "learning_rate": 1.1583728829115274e-05,
1402
+ "loss": 0.551,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.9289363678588016,
1407
+ "grad_norm": 29.606061935424805,
1408
+ "learning_rate": 1.1533863444573235e-05,
1409
+ "loss": 0.6572,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.9335810496980956,
1414
+ "grad_norm": 44.13784408569336,
1415
+ "learning_rate": 1.1483998060031199e-05,
1416
+ "loss": 0.4724,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.9382257315373896,
1421
+ "grad_norm": 37.983055114746094,
1422
+ "learning_rate": 1.1434132675489162e-05,
1423
+ "loss": 0.5225,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.9428704133766836,
1428
+ "grad_norm": 15.249692916870117,
1429
+ "learning_rate": 1.1384267290947124e-05,
1430
+ "loss": 0.4439,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.9475150952159777,
1435
+ "grad_norm": 41.946937561035156,
1436
+ "learning_rate": 1.1334401906405087e-05,
1437
+ "loss": 0.6557,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.9521597770552717,
1442
+ "grad_norm": 14.351404190063477,
1443
+ "learning_rate": 1.1284536521863049e-05,
1444
+ "loss": 0.5077,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.9568044588945657,
1449
+ "grad_norm": 11.345954895019531,
1450
+ "learning_rate": 1.1234671137321012e-05,
1451
+ "loss": 0.4649,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.9614491407338597,
1456
+ "grad_norm": 10.129472732543945,
1457
+ "learning_rate": 1.1184805752778975e-05,
1458
+ "loss": 0.4637,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.9660938225731538,
1463
+ "grad_norm": 17.96135711669922,
1464
+ "learning_rate": 1.1134940368236937e-05,
1465
+ "loss": 0.5942,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.9707385044124478,
1470
+ "grad_norm": 26.003862380981445,
1471
+ "learning_rate": 1.10850749836949e-05,
1472
+ "loss": 0.6214,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.9753831862517418,
1477
+ "grad_norm": 6.638750076293945,
1478
+ "learning_rate": 1.1035209599152862e-05,
1479
+ "loss": 0.4563,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.9800278680910358,
1484
+ "grad_norm": 11.93756103515625,
1485
+ "learning_rate": 1.0985344214610825e-05,
1486
+ "loss": 0.3787,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.9846725499303298,
1491
+ "grad_norm": 40.54302215576172,
1492
+ "learning_rate": 1.0935478830068789e-05,
1493
+ "loss": 0.6483,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.9893172317696238,
1498
+ "grad_norm": 7.869910717010498,
1499
+ "learning_rate": 1.088561344552675e-05,
1500
+ "loss": 0.429,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.9939619136089178,
1505
+ "grad_norm": 31.836936950683594,
1506
+ "learning_rate": 1.0835748060984714e-05,
1507
+ "loss": 0.7914,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.9986065954482118,
1512
+ "grad_norm": 5.69075345993042,
1513
+ "learning_rate": 1.0785882676442675e-05,
1514
+ "loss": 0.5178,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 1.0,
1519
+ "eval_f1": 0.7269367449311068,
1520
+ "eval_loss": 0.5655010342597961,
1521
+ "eval_runtime": 23.3278,
1522
+ "eval_samples_per_second": 224.367,
1523
+ "eval_steps_per_second": 37.423,
1524
+ "step": 2153
1525
+ }
1526
+ ],
1527
+ "logging_steps": 10,
1528
+ "max_steps": 4306,
1529
+ "num_input_tokens_seen": 0,
1530
+ "num_train_epochs": 2,
1531
+ "save_steps": 500,
1532
+ "stateful_callbacks": {
1533
+ "EarlyStoppingCallback": {
1534
+ "args": {
1535
+ "early_stopping_patience": 2,
1536
+ "early_stopping_threshold": 0.0
1537
+ },
1538
+ "attributes": {
1539
+ "early_stopping_patience_counter": 0
1540
+ }
1541
+ },
1542
+ "TrainerControl": {
1543
+ "args": {
1544
+ "should_epoch_stop": false,
1545
+ "should_evaluate": false,
1546
+ "should_log": false,
1547
+ "should_save": true,
1548
+ "should_training_stop": false
1549
+ },
1550
+ "attributes": {}
1551
+ }
1552
+ },
1553
+ "total_flos": 9641193740697600.0,
1554
+ "train_batch_size": 6,
1555
+ "trial_name": null,
1556
+ "trial_params": {
1557
+ "learning_rate": 2.1472034583801277e-05,
1558
+ "num_train_epochs": 2,
1559
+ "per_device_train_batch_size": 6,
1560
+ "weight_decay": 0.054058229046701475
1561
+ }
1562
+ }
run-0/checkpoint-2153/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f21d5c8f6bb5577579729be6f8849358729141000cd8a775701a8cdd187f3d4
3
+ size 5368
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21ccd6598c3d2f9042342ed5581f206efdbe38e7f413005fbee271ade0d5b118
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f21d5c8f6bb5577579729be6f8849358729141000cd8a775701a8cdd187f3d4
3
+ size 5368