yuzhounie commited on
Commit
22fa0a5
·
verified ·
1 Parent(s): 2273679

Training in progress, step 400

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
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": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.51.3",
37
+ "use_cache": false,
38
+ "vocab_size": 128256
39
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb2ee8bb31a7b48322043b9fb34d4ca3634f663009929a3ac843e5994001253
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a233d5e3e309d83c68ded365c4034096c95a6ea3b6328441511ba22604000b
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6caea4359e3e86c55f8a8fac6ccf10a2653f57645ac0588c782f736ba5f1f2c
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfab848c635dbd51553c38eda3ffd4ce10b8f8c259c287e877828ebba36e8dd7
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|eot_id|>",
4
+ "<|eom_id|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|begin_of_text|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|eot_id|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|eot_id|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2070 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
2053
+ "<|eot_id|>",
2054
+ "<|eom_id|>"
2055
+ ],
2056
+ "bos_token": "<|begin_of_text|>",
2057
+ "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 {%- set date_string = \"26 Jul 2024\" %}\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 + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\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 {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\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",
2058
+ "clean_up_tokenization_spaces": true,
2059
+ "eos_token": "<|eot_id|>",
2060
+ "extra_special_tokens": {},
2061
+ "model_input_names": [
2062
+ "input_ids",
2063
+ "attention_mask"
2064
+ ],
2065
+ "model_max_length": 131072,
2066
+ "pad_token": "<|eot_id|>",
2067
+ "padding_side": "right",
2068
+ "split_special_tokens": false,
2069
+ "tokenizer_class": "PreTrainedTokenizer"
2070
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 891, "loss": 1.1094, "lr": 0.0, "epoch": 0.003357582540570789, "percentage": 0.11, "elapsed_time": "0:00:09", "remaining_time": "2:22:06"}
2
+ {"current_steps": 2, "total_steps": 891, "loss": 1.2127, "lr": 1.1111111111111112e-07, "epoch": 0.006715165081141578, "percentage": 0.22, "elapsed_time": "0:00:22", "remaining_time": "2:43:20"}
3
+ {"current_steps": 3, "total_steps": 891, "loss": 1.1671, "lr": 2.2222222222222224e-07, "epoch": 0.010072747621712367, "percentage": 0.34, "elapsed_time": "0:00:28", "remaining_time": "2:22:36"}
4
+ {"current_steps": 4, "total_steps": 891, "loss": 1.1785, "lr": 3.3333333333333335e-07, "epoch": 0.013430330162283156, "percentage": 0.45, "elapsed_time": "0:00:36", "remaining_time": "2:14:58"}
5
+ {"current_steps": 5, "total_steps": 891, "loss": 1.1263, "lr": 4.444444444444445e-07, "epoch": 0.016787912702853944, "percentage": 0.56, "elapsed_time": "0:00:51", "remaining_time": "2:30:38"}
6
+ {"current_steps": 6, "total_steps": 891, "loss": 1.1748, "lr": 5.555555555555555e-07, "epoch": 0.020145495243424735, "percentage": 0.67, "elapsed_time": "0:01:00", "remaining_time": "2:29:02"}
7
+ {"current_steps": 7, "total_steps": 891, "loss": 1.1657, "lr": 6.666666666666667e-07, "epoch": 0.023503077783995522, "percentage": 0.79, "elapsed_time": "0:01:16", "remaining_time": "2:41:43"}
8
+ {"current_steps": 8, "total_steps": 891, "loss": 1.2313, "lr": 7.777777777777779e-07, "epoch": 0.026860660324566313, "percentage": 0.9, "elapsed_time": "0:01:27", "remaining_time": "2:40:38"}
9
+ {"current_steps": 9, "total_steps": 891, "loss": 1.1465, "lr": 8.88888888888889e-07, "epoch": 0.0302182428651371, "percentage": 1.01, "elapsed_time": "0:01:34", "remaining_time": "2:34:31"}
10
+ {"current_steps": 10, "total_steps": 891, "loss": 1.1103, "lr": 1.0000000000000002e-06, "epoch": 0.03357582540570789, "percentage": 1.12, "elapsed_time": "0:01:47", "remaining_time": "2:38:02"}
11
+ {"current_steps": 11, "total_steps": 891, "loss": 1.0456, "lr": 1.111111111111111e-06, "epoch": 0.03693340794627868, "percentage": 1.23, "elapsed_time": "0:02:01", "remaining_time": "2:41:49"}
12
+ {"current_steps": 12, "total_steps": 891, "loss": 1.0994, "lr": 1.2222222222222223e-06, "epoch": 0.04029099048684947, "percentage": 1.35, "elapsed_time": "0:02:11", "remaining_time": "2:41:03"}
13
+ {"current_steps": 13, "total_steps": 891, "loss": 0.9192, "lr": 1.3333333333333334e-06, "epoch": 0.04364857302742026, "percentage": 1.46, "elapsed_time": "0:02:24", "remaining_time": "2:42:34"}
14
+ {"current_steps": 14, "total_steps": 891, "loss": 0.9019, "lr": 1.4444444444444445e-06, "epoch": 0.047006155567991044, "percentage": 1.57, "elapsed_time": "0:02:34", "remaining_time": "2:41:43"}
15
+ {"current_steps": 15, "total_steps": 891, "loss": 0.932, "lr": 1.5555555555555558e-06, "epoch": 0.05036373810856184, "percentage": 1.68, "elapsed_time": "0:02:44", "remaining_time": "2:39:42"}
16
+ {"current_steps": 16, "total_steps": 891, "loss": 0.9504, "lr": 1.6666666666666667e-06, "epoch": 0.053721320649132626, "percentage": 1.8, "elapsed_time": "0:02:55", "remaining_time": "2:40:07"}
17
+ {"current_steps": 17, "total_steps": 891, "loss": 0.8997, "lr": 1.777777777777778e-06, "epoch": 0.05707890318970341, "percentage": 1.91, "elapsed_time": "0:03:11", "remaining_time": "2:43:59"}
18
+ {"current_steps": 18, "total_steps": 891, "loss": 0.9135, "lr": 1.888888888888889e-06, "epoch": 0.0604364857302742, "percentage": 2.02, "elapsed_time": "0:03:24", "remaining_time": "2:44:59"}
19
+ {"current_steps": 19, "total_steps": 891, "loss": 0.895, "lr": 2.0000000000000003e-06, "epoch": 0.063794068270845, "percentage": 2.13, "elapsed_time": "0:03:34", "remaining_time": "2:43:44"}
20
+ {"current_steps": 20, "total_steps": 891, "loss": 0.9178, "lr": 2.1111111111111114e-06, "epoch": 0.06715165081141578, "percentage": 2.24, "elapsed_time": "0:03:44", "remaining_time": "2:43:07"}
21
+ {"current_steps": 21, "total_steps": 891, "loss": 0.9436, "lr": 2.222222222222222e-06, "epoch": 0.07050923335198657, "percentage": 2.36, "elapsed_time": "0:03:52", "remaining_time": "2:40:11"}
22
+ {"current_steps": 22, "total_steps": 891, "loss": 0.8577, "lr": 2.3333333333333336e-06, "epoch": 0.07386681589255736, "percentage": 2.47, "elapsed_time": "0:04:02", "remaining_time": "2:39:51"}
23
+ {"current_steps": 23, "total_steps": 891, "loss": 0.849, "lr": 2.4444444444444447e-06, "epoch": 0.07722439843312814, "percentage": 2.58, "elapsed_time": "0:04:12", "remaining_time": "2:38:55"}
24
+ {"current_steps": 24, "total_steps": 891, "loss": 0.8684, "lr": 2.5555555555555557e-06, "epoch": 0.08058198097369894, "percentage": 2.69, "elapsed_time": "0:04:21", "remaining_time": "2:37:30"}
25
+ {"current_steps": 25, "total_steps": 891, "loss": 0.9139, "lr": 2.666666666666667e-06, "epoch": 0.08393956351426973, "percentage": 2.81, "elapsed_time": "0:04:29", "remaining_time": "2:35:32"}
26
+ {"current_steps": 26, "total_steps": 891, "loss": 0.825, "lr": 2.7777777777777783e-06, "epoch": 0.08729714605484051, "percentage": 2.92, "elapsed_time": "0:04:38", "remaining_time": "2:34:30"}
27
+ {"current_steps": 27, "total_steps": 891, "loss": 0.7743, "lr": 2.888888888888889e-06, "epoch": 0.09065472859541131, "percentage": 3.03, "elapsed_time": "0:04:47", "remaining_time": "2:33:26"}
28
+ {"current_steps": 28, "total_steps": 891, "loss": 0.8325, "lr": 3e-06, "epoch": 0.09401231113598209, "percentage": 3.14, "elapsed_time": "0:04:55", "remaining_time": "2:32:01"}
29
+ {"current_steps": 29, "total_steps": 891, "loss": 0.8181, "lr": 3.1111111111111116e-06, "epoch": 0.09736989367655288, "percentage": 3.25, "elapsed_time": "0:05:06", "remaining_time": "2:31:53"}
30
+ {"current_steps": 30, "total_steps": 891, "loss": 0.8839, "lr": 3.2222222222222227e-06, "epoch": 0.10072747621712368, "percentage": 3.37, "elapsed_time": "0:05:17", "remaining_time": "2:31:54"}
31
+ {"current_steps": 31, "total_steps": 891, "loss": 0.803, "lr": 3.3333333333333333e-06, "epoch": 0.10408505875769446, "percentage": 3.48, "elapsed_time": "0:05:25", "remaining_time": "2:30:21"}
32
+ {"current_steps": 32, "total_steps": 891, "loss": 0.7857, "lr": 3.444444444444445e-06, "epoch": 0.10744264129826525, "percentage": 3.59, "elapsed_time": "0:05:37", "remaining_time": "2:31:06"}
33
+ {"current_steps": 33, "total_steps": 891, "loss": 0.8166, "lr": 3.555555555555556e-06, "epoch": 0.11080022383883603, "percentage": 3.7, "elapsed_time": "0:05:45", "remaining_time": "2:29:33"}
34
+ {"current_steps": 34, "total_steps": 891, "loss": 0.7488, "lr": 3.6666666666666666e-06, "epoch": 0.11415780637940683, "percentage": 3.82, "elapsed_time": "0:05:51", "remaining_time": "2:27:52"}
35
+ {"current_steps": 35, "total_steps": 891, "loss": 0.7965, "lr": 3.777777777777778e-06, "epoch": 0.11751538891997762, "percentage": 3.93, "elapsed_time": "0:05:59", "remaining_time": "2:26:40"}
36
+ {"current_steps": 36, "total_steps": 891, "loss": 0.8154, "lr": 3.88888888888889e-06, "epoch": 0.1208729714605484, "percentage": 4.04, "elapsed_time": "0:06:07", "remaining_time": "2:25:20"}
37
+ {"current_steps": 37, "total_steps": 891, "loss": 0.8126, "lr": 4.000000000000001e-06, "epoch": 0.1242305540011192, "percentage": 4.15, "elapsed_time": "0:06:14", "remaining_time": "2:23:53"}
38
+ {"current_steps": 38, "total_steps": 891, "loss": 0.8001, "lr": 4.111111111111111e-06, "epoch": 0.12758813654169, "percentage": 4.26, "elapsed_time": "0:06:22", "remaining_time": "2:23:12"}
39
+ {"current_steps": 39, "total_steps": 891, "loss": 0.8286, "lr": 4.222222222222223e-06, "epoch": 0.13094571908226077, "percentage": 4.38, "elapsed_time": "0:06:31", "remaining_time": "2:22:28"}
40
+ {"current_steps": 40, "total_steps": 891, "loss": 0.8294, "lr": 4.333333333333334e-06, "epoch": 0.13430330162283155, "percentage": 4.49, "elapsed_time": "0:06:40", "remaining_time": "2:21:59"}
41
+ {"current_steps": 41, "total_steps": 891, "loss": 0.8057, "lr": 4.444444444444444e-06, "epoch": 0.13766088416340236, "percentage": 4.6, "elapsed_time": "0:06:47", "remaining_time": "2:20:50"}
42
+ {"current_steps": 42, "total_steps": 891, "loss": 0.7816, "lr": 4.555555555555556e-06, "epoch": 0.14101846670397314, "percentage": 4.71, "elapsed_time": "0:06:59", "remaining_time": "2:21:15"}
43
+ {"current_steps": 43, "total_steps": 891, "loss": 0.7406, "lr": 4.666666666666667e-06, "epoch": 0.14437604924454392, "percentage": 4.83, "elapsed_time": "0:07:05", "remaining_time": "2:19:55"}
44
+ {"current_steps": 44, "total_steps": 891, "loss": 0.7836, "lr": 4.777777777777778e-06, "epoch": 0.14773363178511473, "percentage": 4.94, "elapsed_time": "0:07:16", "remaining_time": "2:20:08"}
45
+ {"current_steps": 45, "total_steps": 891, "loss": 0.7905, "lr": 4.888888888888889e-06, "epoch": 0.1510912143256855, "percentage": 5.05, "elapsed_time": "0:07:26", "remaining_time": "2:19:51"}
46
+ {"current_steps": 46, "total_steps": 891, "loss": 0.77, "lr": 5e-06, "epoch": 0.1544487968662563, "percentage": 5.16, "elapsed_time": "0:07:33", "remaining_time": "2:18:51"}
47
+ {"current_steps": 47, "total_steps": 891, "loss": 0.8096, "lr": 5.1111111111111115e-06, "epoch": 0.1578063794068271, "percentage": 5.27, "elapsed_time": "0:07:43", "remaining_time": "2:18:43"}
48
+ {"current_steps": 48, "total_steps": 891, "loss": 0.8085, "lr": 5.2222222222222226e-06, "epoch": 0.16116396194739788, "percentage": 5.39, "elapsed_time": "0:07:51", "remaining_time": "2:18:05"}
49
+ {"current_steps": 49, "total_steps": 891, "loss": 0.7634, "lr": 5.333333333333334e-06, "epoch": 0.16452154448796866, "percentage": 5.5, "elapsed_time": "0:08:06", "remaining_time": "2:19:17"}
50
+ {"current_steps": 50, "total_steps": 891, "loss": 0.7764, "lr": 5.444444444444445e-06, "epoch": 0.16787912702853947, "percentage": 5.61, "elapsed_time": "0:08:12", "remaining_time": "2:18:07"}
51
+ {"current_steps": 51, "total_steps": 891, "loss": 0.7637, "lr": 5.555555555555557e-06, "epoch": 0.17123670956911025, "percentage": 5.72, "elapsed_time": "0:08:19", "remaining_time": "2:17:04"}
52
+ {"current_steps": 52, "total_steps": 891, "loss": 0.8304, "lr": 5.666666666666667e-06, "epoch": 0.17459429210968103, "percentage": 5.84, "elapsed_time": "0:08:28", "remaining_time": "2:16:41"}
53
+ {"current_steps": 53, "total_steps": 891, "loss": 0.8054, "lr": 5.777777777777778e-06, "epoch": 0.1779518746502518, "percentage": 5.95, "elapsed_time": "0:08:41", "remaining_time": "2:17:30"}
54
+ {"current_steps": 54, "total_steps": 891, "loss": 0.7767, "lr": 5.88888888888889e-06, "epoch": 0.18130945719082261, "percentage": 6.06, "elapsed_time": "0:08:59", "remaining_time": "2:19:21"}
55
+ {"current_steps": 55, "total_steps": 891, "loss": 0.7446, "lr": 6e-06, "epoch": 0.1846670397313934, "percentage": 6.17, "elapsed_time": "0:09:05", "remaining_time": "2:18:13"}
56
+ {"current_steps": 56, "total_steps": 891, "loss": 0.8216, "lr": 6.111111111111112e-06, "epoch": 0.18802462227196418, "percentage": 6.29, "elapsed_time": "0:09:13", "remaining_time": "2:17:26"}
57
+ {"current_steps": 57, "total_steps": 891, "loss": 0.7516, "lr": 6.222222222222223e-06, "epoch": 0.19138220481253498, "percentage": 6.4, "elapsed_time": "0:09:27", "remaining_time": "2:18:18"}
58
+ {"current_steps": 58, "total_steps": 891, "loss": 0.7809, "lr": 6.333333333333333e-06, "epoch": 0.19473978735310576, "percentage": 6.51, "elapsed_time": "0:09:36", "remaining_time": "2:18:01"}
59
+ {"current_steps": 59, "total_steps": 891, "loss": 0.7734, "lr": 6.444444444444445e-06, "epoch": 0.19809736989367654, "percentage": 6.62, "elapsed_time": "0:09:44", "remaining_time": "2:17:29"}
60
+ {"current_steps": 60, "total_steps": 891, "loss": 0.7763, "lr": 6.555555555555556e-06, "epoch": 0.20145495243424735, "percentage": 6.73, "elapsed_time": "0:09:53", "remaining_time": "2:17:00"}
61
+ {"current_steps": 61, "total_steps": 891, "loss": 0.7742, "lr": 6.666666666666667e-06, "epoch": 0.20481253497481813, "percentage": 6.85, "elapsed_time": "0:10:02", "remaining_time": "2:16:31"}
62
+ {"current_steps": 62, "total_steps": 891, "loss": 0.7388, "lr": 6.777777777777779e-06, "epoch": 0.2081701175153889, "percentage": 6.96, "elapsed_time": "0:10:14", "remaining_time": "2:16:59"}
63
+ {"current_steps": 63, "total_steps": 891, "loss": 0.8117, "lr": 6.88888888888889e-06, "epoch": 0.21152770005595972, "percentage": 7.07, "elapsed_time": "0:10:25", "remaining_time": "2:17:07"}
64
+ {"current_steps": 64, "total_steps": 891, "loss": 0.874, "lr": 7e-06, "epoch": 0.2148852825965305, "percentage": 7.18, "elapsed_time": "0:10:37", "remaining_time": "2:17:23"}
65
+ {"current_steps": 65, "total_steps": 891, "loss": 0.7753, "lr": 7.111111111111112e-06, "epoch": 0.21824286513710128, "percentage": 7.3, "elapsed_time": "0:10:46", "remaining_time": "2:16:55"}
66
+ {"current_steps": 66, "total_steps": 891, "loss": 0.7364, "lr": 7.222222222222223e-06, "epoch": 0.22160044767767206, "percentage": 7.41, "elapsed_time": "0:10:53", "remaining_time": "2:16:10"}
67
+ {"current_steps": 67, "total_steps": 891, "loss": 0.7828, "lr": 7.333333333333333e-06, "epoch": 0.22495803021824287, "percentage": 7.52, "elapsed_time": "0:11:01", "remaining_time": "2:15:39"}
68
+ {"current_steps": 68, "total_steps": 891, "loss": 0.7061, "lr": 7.444444444444445e-06, "epoch": 0.22831561275881365, "percentage": 7.63, "elapsed_time": "0:11:12", "remaining_time": "2:15:42"}
69
+ {"current_steps": 69, "total_steps": 891, "loss": 0.7717, "lr": 7.555555555555556e-06, "epoch": 0.23167319529938443, "percentage": 7.74, "elapsed_time": "0:11:21", "remaining_time": "2:15:14"}
70
+ {"current_steps": 70, "total_steps": 891, "loss": 0.7771, "lr": 7.666666666666667e-06, "epoch": 0.23503077783995524, "percentage": 7.86, "elapsed_time": "0:11:27", "remaining_time": "2:14:28"}
71
+ {"current_steps": 71, "total_steps": 891, "loss": 0.8112, "lr": 7.77777777777778e-06, "epoch": 0.23838836038052602, "percentage": 7.97, "elapsed_time": "0:11:38", "remaining_time": "2:14:29"}
72
+ {"current_steps": 72, "total_steps": 891, "loss": 0.7739, "lr": 7.88888888888889e-06, "epoch": 0.2417459429210968, "percentage": 8.08, "elapsed_time": "0:11:45", "remaining_time": "2:13:45"}
73
+ {"current_steps": 73, "total_steps": 891, "loss": 0.8008, "lr": 8.000000000000001e-06, "epoch": 0.2451035254616676, "percentage": 8.19, "elapsed_time": "0:11:52", "remaining_time": "2:13:07"}
74
+ {"current_steps": 74, "total_steps": 891, "loss": 0.8011, "lr": 8.111111111111112e-06, "epoch": 0.2484611080022384, "percentage": 8.31, "elapsed_time": "0:12:01", "remaining_time": "2:12:42"}
75
+ {"current_steps": 75, "total_steps": 891, "loss": 0.7438, "lr": 8.222222222222222e-06, "epoch": 0.2518186905428092, "percentage": 8.42, "elapsed_time": "0:12:12", "remaining_time": "2:12:45"}
76
+ {"current_steps": 76, "total_steps": 891, "loss": 0.8015, "lr": 8.333333333333334e-06, "epoch": 0.25517627308338, "percentage": 8.53, "elapsed_time": "0:12:19", "remaining_time": "2:12:06"}
77
+ {"current_steps": 77, "total_steps": 891, "loss": 0.7927, "lr": 8.444444444444446e-06, "epoch": 0.25853385562395076, "percentage": 8.64, "elapsed_time": "0:12:28", "remaining_time": "2:11:54"}
78
+ {"current_steps": 78, "total_steps": 891, "loss": 0.7832, "lr": 8.555555555555556e-06, "epoch": 0.26189143816452154, "percentage": 8.75, "elapsed_time": "0:12:40", "remaining_time": "2:12:08"}
79
+ {"current_steps": 79, "total_steps": 891, "loss": 0.7475, "lr": 8.666666666666668e-06, "epoch": 0.2652490207050923, "percentage": 8.87, "elapsed_time": "0:12:52", "remaining_time": "2:12:22"}
80
+ {"current_steps": 80, "total_steps": 891, "loss": 0.8269, "lr": 8.777777777777778e-06, "epoch": 0.2686066032456631, "percentage": 8.98, "elapsed_time": "0:13:05", "remaining_time": "2:12:47"}
81
+ {"current_steps": 81, "total_steps": 891, "loss": 0.7924, "lr": 8.888888888888888e-06, "epoch": 0.27196418578623394, "percentage": 9.09, "elapsed_time": "0:13:13", "remaining_time": "2:12:16"}
82
+ {"current_steps": 82, "total_steps": 891, "loss": 0.8096, "lr": 9e-06, "epoch": 0.2753217683268047, "percentage": 9.2, "elapsed_time": "0:13:33", "remaining_time": "2:13:46"}
83
+ {"current_steps": 83, "total_steps": 891, "loss": 0.7586, "lr": 9.111111111111112e-06, "epoch": 0.2786793508673755, "percentage": 9.32, "elapsed_time": "0:13:46", "remaining_time": "2:14:05"}
84
+ {"current_steps": 84, "total_steps": 891, "loss": 0.7741, "lr": 9.222222222222224e-06, "epoch": 0.2820369334079463, "percentage": 9.43, "elapsed_time": "0:13:57", "remaining_time": "2:14:01"}
85
+ {"current_steps": 85, "total_steps": 891, "loss": 0.7718, "lr": 9.333333333333334e-06, "epoch": 0.28539451594851706, "percentage": 9.54, "elapsed_time": "0:14:03", "remaining_time": "2:13:15"}
86
+ {"current_steps": 86, "total_steps": 891, "loss": 0.7687, "lr": 9.444444444444445e-06, "epoch": 0.28875209848908784, "percentage": 9.65, "elapsed_time": "0:14:15", "remaining_time": "2:13:28"}
87
+ {"current_steps": 87, "total_steps": 891, "loss": 0.7694, "lr": 9.555555555555556e-06, "epoch": 0.2921096810296586, "percentage": 9.76, "elapsed_time": "0:14:34", "remaining_time": "2:14:40"}
88
+ {"current_steps": 88, "total_steps": 891, "loss": 0.8077, "lr": 9.666666666666667e-06, "epoch": 0.29546726357022945, "percentage": 9.88, "elapsed_time": "0:14:41", "remaining_time": "2:14:07"}
89
+ {"current_steps": 89, "total_steps": 891, "loss": 0.8218, "lr": 9.777777777777779e-06, "epoch": 0.29882484611080024, "percentage": 9.99, "elapsed_time": "0:14:48", "remaining_time": "2:13:22"}
90
+ {"current_steps": 90, "total_steps": 891, "loss": 0.7613, "lr": 9.88888888888889e-06, "epoch": 0.302182428651371, "percentage": 10.1, "elapsed_time": "0:14:54", "remaining_time": "2:12:40"}
91
+ {"current_steps": 91, "total_steps": 891, "loss": 0.7597, "lr": 1e-05, "epoch": 0.3055400111919418, "percentage": 10.21, "elapsed_time": "0:15:02", "remaining_time": "2:12:12"}
92
+ {"current_steps": 92, "total_steps": 891, "loss": 0.7757, "lr": 9.999961543109546e-06, "epoch": 0.3088975937325126, "percentage": 10.33, "elapsed_time": "0:15:09", "remaining_time": "2:11:42"}
93
+ {"current_steps": 93, "total_steps": 891, "loss": 0.7865, "lr": 9.999846173029752e-06, "epoch": 0.31225517627308336, "percentage": 10.44, "elapsed_time": "0:15:15", "remaining_time": "2:10:57"}
94
+ {"current_steps": 94, "total_steps": 891, "loss": 0.7405, "lr": 9.99965389153533e-06, "epoch": 0.3156127588136542, "percentage": 10.55, "elapsed_time": "0:15:22", "remaining_time": "2:10:19"}
95
+ {"current_steps": 95, "total_steps": 891, "loss": 0.7605, "lr": 9.999384701584098e-06, "epoch": 0.318970341354225, "percentage": 10.66, "elapsed_time": "0:15:33", "remaining_time": "2:10:21"}
96
+ {"current_steps": 96, "total_steps": 891, "loss": 0.8139, "lr": 9.999038607316942e-06, "epoch": 0.32232792389479575, "percentage": 10.77, "elapsed_time": "0:15:46", "remaining_time": "2:10:40"}
97
+ {"current_steps": 97, "total_steps": 891, "loss": 0.7782, "lr": 9.998615614057743e-06, "epoch": 0.32568550643536653, "percentage": 10.89, "elapsed_time": "0:15:55", "remaining_time": "2:10:24"}
98
+ {"current_steps": 98, "total_steps": 891, "loss": 0.7628, "lr": 9.998115728313305e-06, "epoch": 0.3290430889759373, "percentage": 11.0, "elapsed_time": "0:16:03", "remaining_time": "2:09:57"}
99
+ {"current_steps": 99, "total_steps": 891, "loss": 0.773, "lr": 9.997538957773248e-06, "epoch": 0.3324006715165081, "percentage": 11.11, "elapsed_time": "0:16:17", "remaining_time": "2:10:16"}
100
+ {"current_steps": 100, "total_steps": 891, "loss": 0.8015, "lr": 9.996885311309892e-06, "epoch": 0.33575825405707893, "percentage": 11.22, "elapsed_time": "0:16:23", "remaining_time": "2:09:42"}
101
+ {"current_steps": 101, "total_steps": 891, "loss": 0.759, "lr": 9.996154798978122e-06, "epoch": 0.3391158365976497, "percentage": 11.34, "elapsed_time": "0:16:33", "remaining_time": "2:09:27"}
102
+ {"current_steps": 102, "total_steps": 891, "loss": 0.7828, "lr": 9.99534743201523e-06, "epoch": 0.3424734191382205, "percentage": 11.45, "elapsed_time": "0:16:45", "remaining_time": "2:09:38"}
103
+ {"current_steps": 103, "total_steps": 891, "loss": 0.7518, "lr": 9.994463222840748e-06, "epoch": 0.34583100167879127, "percentage": 11.56, "elapsed_time": "0:16:53", "remaining_time": "2:09:13"}
104
+ {"current_steps": 104, "total_steps": 891, "loss": 0.7541, "lr": 9.993502185056244e-06, "epoch": 0.34918858421936205, "percentage": 11.67, "elapsed_time": "0:17:05", "remaining_time": "2:09:19"}
105
+ {"current_steps": 105, "total_steps": 891, "loss": 0.6949, "lr": 9.992464333445134e-06, "epoch": 0.35254616675993283, "percentage": 11.78, "elapsed_time": "0:17:16", "remaining_time": "2:09:21"}
106
+ {"current_steps": 106, "total_steps": 891, "loss": 0.7731, "lr": 9.991349683972435e-06, "epoch": 0.3559037493005036, "percentage": 11.9, "elapsed_time": "0:17:23", "remaining_time": "2:08:50"}
107
+ {"current_steps": 107, "total_steps": 891, "loss": 0.7746, "lr": 9.990158253784525e-06, "epoch": 0.35926133184107445, "percentage": 12.01, "elapsed_time": "0:17:30", "remaining_time": "2:08:15"}
108
+ {"current_steps": 108, "total_steps": 891, "loss": 0.757, "lr": 9.988890061208889e-06, "epoch": 0.36261891438164523, "percentage": 12.12, "elapsed_time": "0:17:40", "remaining_time": "2:08:05"}
109
+ {"current_steps": 109, "total_steps": 891, "loss": 0.8101, "lr": 9.987545125753818e-06, "epoch": 0.365976496922216, "percentage": 12.23, "elapsed_time": "0:17:51", "remaining_time": "2:08:04"}
110
+ {"current_steps": 110, "total_steps": 891, "loss": 0.7716, "lr": 9.986123468108134e-06, "epoch": 0.3693340794627868, "percentage": 12.35, "elapsed_time": "0:17:56", "remaining_time": "2:07:26"}
111
+ {"current_steps": 111, "total_steps": 891, "loss": 0.7842, "lr": 9.984625110140844e-06, "epoch": 0.37269166200335757, "percentage": 12.46, "elapsed_time": "0:18:08", "remaining_time": "2:07:25"}
112
+ {"current_steps": 112, "total_steps": 891, "loss": 0.7452, "lr": 9.983050074900824e-06, "epoch": 0.37604924454392835, "percentage": 12.57, "elapsed_time": "0:18:14", "remaining_time": "2:06:51"}
113
+ {"current_steps": 113, "total_steps": 891, "loss": 0.7502, "lr": 9.98139838661646e-06, "epoch": 0.3794068270844992, "percentage": 12.68, "elapsed_time": "0:18:20", "remaining_time": "2:06:19"}
114
+ {"current_steps": 114, "total_steps": 891, "loss": 0.7708, "lr": 9.979670070695265e-06, "epoch": 0.38276440962506997, "percentage": 12.79, "elapsed_time": "0:18:31", "remaining_time": "2:06:16"}
115
+ {"current_steps": 115, "total_steps": 891, "loss": 0.784, "lr": 9.977865153723508e-06, "epoch": 0.38612199216564075, "percentage": 12.91, "elapsed_time": "0:18:38", "remaining_time": "2:05:47"}
116
+ {"current_steps": 116, "total_steps": 891, "loss": 0.7534, "lr": 9.97598366346578e-06, "epoch": 0.38947957470621153, "percentage": 13.02, "elapsed_time": "0:18:47", "remaining_time": "2:05:30"}
117
+ {"current_steps": 117, "total_steps": 891, "loss": 0.7388, "lr": 9.974025628864592e-06, "epoch": 0.3928371572467823, "percentage": 13.13, "elapsed_time": "0:19:01", "remaining_time": "2:05:51"}
118
+ {"current_steps": 118, "total_steps": 891, "loss": 0.763, "lr": 9.971991080039912e-06, "epoch": 0.3961947397873531, "percentage": 13.24, "elapsed_time": "0:19:11", "remaining_time": "2:05:42"}
119
+ {"current_steps": 119, "total_steps": 891, "loss": 0.8042, "lr": 9.969880048288704e-06, "epoch": 0.39955232232792387, "percentage": 13.36, "elapsed_time": "0:19:18", "remaining_time": "2:05:16"}
120
+ {"current_steps": 120, "total_steps": 891, "loss": 0.7267, "lr": 9.96769256608446e-06, "epoch": 0.4029099048684947, "percentage": 13.47, "elapsed_time": "0:19:25", "remaining_time": "2:04:50"}
121
+ {"current_steps": 121, "total_steps": 891, "loss": 0.7642, "lr": 9.965428667076687e-06, "epoch": 0.4062674874090655, "percentage": 13.58, "elapsed_time": "0:19:45", "remaining_time": "2:05:43"}
122
+ {"current_steps": 122, "total_steps": 891, "loss": 0.7688, "lr": 9.963088386090386e-06, "epoch": 0.40962506994963627, "percentage": 13.69, "elapsed_time": "0:19:59", "remaining_time": "2:06:02"}
123
+ {"current_steps": 123, "total_steps": 891, "loss": 0.7909, "lr": 9.960671759125529e-06, "epoch": 0.41298265249020705, "percentage": 13.8, "elapsed_time": "0:20:08", "remaining_time": "2:05:42"}
124
+ {"current_steps": 124, "total_steps": 891, "loss": 0.7525, "lr": 9.958178823356503e-06, "epoch": 0.4163402350307778, "percentage": 13.92, "elapsed_time": "0:20:16", "remaining_time": "2:05:27"}
125
+ {"current_steps": 125, "total_steps": 891, "loss": 0.8311, "lr": 9.95560961713153e-06, "epoch": 0.4196978175713486, "percentage": 14.03, "elapsed_time": "0:20:28", "remaining_time": "2:05:28"}
126
+ {"current_steps": 126, "total_steps": 891, "loss": 0.7679, "lr": 9.95296417997208e-06, "epoch": 0.42305540011191944, "percentage": 14.14, "elapsed_time": "0:20:34", "remaining_time": "2:04:57"}
127
+ {"current_steps": 127, "total_steps": 891, "loss": 0.783, "lr": 9.950242552572272e-06, "epoch": 0.4264129826524902, "percentage": 14.25, "elapsed_time": "0:20:45", "remaining_time": "2:04:55"}
128
+ {"current_steps": 128, "total_steps": 891, "loss": 0.7213, "lr": 9.947444776798235e-06, "epoch": 0.429770565193061, "percentage": 14.37, "elapsed_time": "0:20:53", "remaining_time": "2:04:31"}
129
+ {"current_steps": 129, "total_steps": 891, "loss": 0.7832, "lr": 9.944570895687471e-06, "epoch": 0.4331281477336318, "percentage": 14.48, "elapsed_time": "0:21:04", "remaining_time": "2:04:28"}
130
+ {"current_steps": 130, "total_steps": 891, "loss": 0.7984, "lr": 9.941620953448195e-06, "epoch": 0.43648573027420257, "percentage": 14.59, "elapsed_time": "0:21:19", "remaining_time": "2:04:50"}
131
+ {"current_steps": 131, "total_steps": 891, "loss": 0.7794, "lr": 9.938594995458644e-06, "epoch": 0.43984331281477335, "percentage": 14.7, "elapsed_time": "0:21:26", "remaining_time": "2:04:24"}
132
+ {"current_steps": 132, "total_steps": 891, "loss": 0.7876, "lr": 9.935493068266396e-06, "epoch": 0.4432008953553441, "percentage": 14.81, "elapsed_time": "0:21:38", "remaining_time": "2:04:27"}
133
+ {"current_steps": 133, "total_steps": 891, "loss": 0.7665, "lr": 9.932315219587641e-06, "epoch": 0.44655847789591496, "percentage": 14.93, "elapsed_time": "0:21:45", "remaining_time": "2:04:02"}
134
+ {"current_steps": 134, "total_steps": 891, "loss": 0.7985, "lr": 9.929061498306448e-06, "epoch": 0.44991606043648574, "percentage": 15.04, "elapsed_time": "0:21:54", "remaining_time": "2:03:45"}
135
+ {"current_steps": 135, "total_steps": 891, "loss": 0.8119, "lr": 9.92573195447402e-06, "epoch": 0.4532736429770565, "percentage": 15.15, "elapsed_time": "0:22:07", "remaining_time": "2:03:54"}
136
+ {"current_steps": 136, "total_steps": 891, "loss": 0.753, "lr": 9.922326639307918e-06, "epoch": 0.4566312255176273, "percentage": 15.26, "elapsed_time": "0:22:20", "remaining_time": "2:03:58"}
137
+ {"current_steps": 137, "total_steps": 891, "loss": 0.792, "lr": 9.918845605191274e-06, "epoch": 0.4599888080581981, "percentage": 15.38, "elapsed_time": "0:22:31", "remaining_time": "2:03:56"}
138
+ {"current_steps": 138, "total_steps": 891, "loss": 0.7924, "lr": 9.915288905671986e-06, "epoch": 0.46334639059876886, "percentage": 15.49, "elapsed_time": "0:22:42", "remaining_time": "2:03:57"}
139
+ {"current_steps": 139, "total_steps": 891, "loss": 0.7287, "lr": 9.911656595461899e-06, "epoch": 0.4667039731393397, "percentage": 15.6, "elapsed_time": "0:22:56", "remaining_time": "2:04:06"}
140
+ {"current_steps": 140, "total_steps": 891, "loss": 0.783, "lr": 9.90794873043595e-06, "epoch": 0.4700615556799105, "percentage": 15.71, "elapsed_time": "0:23:08", "remaining_time": "2:04:09"}
141
+ {"current_steps": 141, "total_steps": 891, "loss": 0.7682, "lr": 9.904165367631329e-06, "epoch": 0.47341913822048126, "percentage": 15.82, "elapsed_time": "0:23:15", "remaining_time": "2:03:43"}
142
+ {"current_steps": 142, "total_steps": 891, "loss": 0.757, "lr": 9.900306565246579e-06, "epoch": 0.47677672076105204, "percentage": 15.94, "elapsed_time": "0:23:27", "remaining_time": "2:03:44"}
143
+ {"current_steps": 143, "total_steps": 891, "loss": 0.7691, "lr": 9.896372382640718e-06, "epoch": 0.4801343033016228, "percentage": 16.05, "elapsed_time": "0:23:38", "remaining_time": "2:03:40"}
144
+ {"current_steps": 144, "total_steps": 891, "loss": 0.7383, "lr": 9.892362880332316e-06, "epoch": 0.4834918858421936, "percentage": 16.16, "elapsed_time": "0:23:48", "remaining_time": "2:03:30"}
145
+ {"current_steps": 145, "total_steps": 891, "loss": 0.807, "lr": 9.888278119998573e-06, "epoch": 0.4868494683827644, "percentage": 16.27, "elapsed_time": "0:24:02", "remaining_time": "2:03:39"}
146
+ {"current_steps": 146, "total_steps": 891, "loss": 0.7899, "lr": 9.884118164474359e-06, "epoch": 0.4902070509233352, "percentage": 16.39, "elapsed_time": "0:24:13", "remaining_time": "2:03:35"}
147
+ {"current_steps": 147, "total_steps": 891, "loss": 0.7425, "lr": 9.879883077751255e-06, "epoch": 0.493564633463906, "percentage": 16.5, "elapsed_time": "0:24:21", "remaining_time": "2:03:17"}
148
+ {"current_steps": 148, "total_steps": 891, "loss": 0.7857, "lr": 9.875572924976568e-06, "epoch": 0.4969222160044768, "percentage": 16.61, "elapsed_time": "0:24:32", "remaining_time": "2:03:12"}
149
+ {"current_steps": 149, "total_steps": 891, "loss": 0.7932, "lr": 9.871187772452327e-06, "epoch": 0.5002797985450476, "percentage": 16.72, "elapsed_time": "0:24:47", "remaining_time": "2:03:26"}
150
+ {"current_steps": 150, "total_steps": 891, "loss": 0.7613, "lr": 9.866727687634266e-06, "epoch": 0.5036373810856184, "percentage": 16.84, "elapsed_time": "0:24:57", "remaining_time": "2:03:18"}
151
+ {"current_steps": 151, "total_steps": 891, "loss": 0.7728, "lr": 9.86219273913078e-06, "epoch": 0.5069949636261891, "percentage": 16.95, "elapsed_time": "0:25:09", "remaining_time": "2:03:16"}
152
+ {"current_steps": 152, "total_steps": 891, "loss": 0.7613, "lr": 9.857582996701878e-06, "epoch": 0.51035254616676, "percentage": 17.06, "elapsed_time": "0:25:22", "remaining_time": "2:03:23"}
153
+ {"current_steps": 153, "total_steps": 891, "loss": 0.7538, "lr": 9.852898531258102e-06, "epoch": 0.5137101287073307, "percentage": 17.17, "elapsed_time": "0:25:30", "remaining_time": "2:03:03"}
154
+ {"current_steps": 154, "total_steps": 891, "loss": 0.7518, "lr": 9.848139414859441e-06, "epoch": 0.5170677112479015, "percentage": 17.28, "elapsed_time": "0:25:38", "remaining_time": "2:02:41"}
155
+ {"current_steps": 155, "total_steps": 891, "loss": 0.758, "lr": 9.843305720714227e-06, "epoch": 0.5204252937884724, "percentage": 17.4, "elapsed_time": "0:25:48", "remaining_time": "2:02:34"}
156
+ {"current_steps": 156, "total_steps": 891, "loss": 0.7508, "lr": 9.838397523177993e-06, "epoch": 0.5237828763290431, "percentage": 17.51, "elapsed_time": "0:25:54", "remaining_time": "2:02:03"}
157
+ {"current_steps": 157, "total_steps": 891, "loss": 0.7595, "lr": 9.833414897752346e-06, "epoch": 0.5271404588696139, "percentage": 17.62, "elapsed_time": "0:26:00", "remaining_time": "2:01:36"}
158
+ {"current_steps": 158, "total_steps": 891, "loss": 0.7734, "lr": 9.828357921083803e-06, "epoch": 0.5304980414101846, "percentage": 17.73, "elapsed_time": "0:26:11", "remaining_time": "2:01:31"}
159
+ {"current_steps": 159, "total_steps": 891, "loss": 0.821, "lr": 9.823226670962598e-06, "epoch": 0.5338556239507555, "percentage": 17.85, "elapsed_time": "0:26:21", "remaining_time": "2:01:21"}
160
+ {"current_steps": 160, "total_steps": 891, "loss": 0.8161, "lr": 9.818021226321502e-06, "epoch": 0.5372132064913262, "percentage": 17.96, "elapsed_time": "0:26:28", "remaining_time": "2:00:56"}
161
+ {"current_steps": 161, "total_steps": 891, "loss": 0.7693, "lr": 9.812741667234599e-06, "epoch": 0.540570789031897, "percentage": 18.07, "elapsed_time": "0:26:36", "remaining_time": "2:00:37"}
162
+ {"current_steps": 162, "total_steps": 891, "loss": 0.759, "lr": 9.807388074916064e-06, "epoch": 0.5439283715724679, "percentage": 18.18, "elapsed_time": "0:26:50", "remaining_time": "2:00:47"}
163
+ {"current_steps": 163, "total_steps": 891, "loss": 0.7605, "lr": 9.801960531718898e-06, "epoch": 0.5472859541130386, "percentage": 18.29, "elapsed_time": "0:26:56", "remaining_time": "2:00:21"}
164
+ {"current_steps": 164, "total_steps": 891, "loss": 0.8167, "lr": 9.796459121133675e-06, "epoch": 0.5506435366536094, "percentage": 18.41, "elapsed_time": "0:27:02", "remaining_time": "1:59:51"}
165
+ {"current_steps": 165, "total_steps": 891, "loss": 0.7771, "lr": 9.790883927787254e-06, "epoch": 0.5540011191941802, "percentage": 18.52, "elapsed_time": "0:27:19", "remaining_time": "2:00:13"}
166
+ {"current_steps": 166, "total_steps": 891, "loss": 0.7749, "lr": 9.785235037441473e-06, "epoch": 0.557358701734751, "percentage": 18.63, "elapsed_time": "0:27:28", "remaining_time": "1:59:58"}
167
+ {"current_steps": 167, "total_steps": 891, "loss": 0.7186, "lr": 9.779512536991839e-06, "epoch": 0.5607162842753217, "percentage": 18.74, "elapsed_time": "0:27:45", "remaining_time": "2:00:21"}
168
+ {"current_steps": 168, "total_steps": 891, "loss": 0.7092, "lr": 9.773716514466179e-06, "epoch": 0.5640738668158926, "percentage": 18.86, "elapsed_time": "0:27:59", "remaining_time": "2:00:26"}
169
+ {"current_steps": 169, "total_steps": 891, "loss": 0.7561, "lr": 9.767847059023292e-06, "epoch": 0.5674314493564634, "percentage": 18.97, "elapsed_time": "0:28:07", "remaining_time": "2:00:09"}
170
+ {"current_steps": 170, "total_steps": 891, "loss": 0.7802, "lr": 9.761904260951583e-06, "epoch": 0.5707890318970341, "percentage": 19.08, "elapsed_time": "0:28:19", "remaining_time": "2:00:08"}
171
+ {"current_steps": 171, "total_steps": 891, "loss": 0.7301, "lr": 9.755888211667663e-06, "epoch": 0.574146614437605, "percentage": 19.19, "elapsed_time": "0:28:30", "remaining_time": "2:00:01"}
172
+ {"current_steps": 172, "total_steps": 891, "loss": 0.7799, "lr": 9.749799003714954e-06, "epoch": 0.5775041969781757, "percentage": 19.3, "elapsed_time": "0:28:38", "remaining_time": "1:59:43"}
173
+ {"current_steps": 173, "total_steps": 891, "loss": 0.7827, "lr": 9.743636730762259e-06, "epoch": 0.5808617795187465, "percentage": 19.42, "elapsed_time": "0:28:50", "remaining_time": "1:59:40"}
174
+ {"current_steps": 174, "total_steps": 891, "loss": 0.7267, "lr": 9.737401487602314e-06, "epoch": 0.5842193620593172, "percentage": 19.53, "elapsed_time": "0:28:57", "remaining_time": "1:59:19"}
175
+ {"current_steps": 175, "total_steps": 891, "loss": 0.7456, "lr": 9.731093370150349e-06, "epoch": 0.5875769445998881, "percentage": 19.64, "elapsed_time": "0:29:05", "remaining_time": "1:59:03"}
176
+ {"current_steps": 176, "total_steps": 891, "loss": 0.7703, "lr": 9.724712475442597e-06, "epoch": 0.5909345271404589, "percentage": 19.75, "elapsed_time": "0:29:18", "remaining_time": "1:59:04"}
177
+ {"current_steps": 177, "total_steps": 891, "loss": 0.7102, "lr": 9.718258901634802e-06, "epoch": 0.5942921096810296, "percentage": 19.87, "elapsed_time": "0:29:26", "remaining_time": "1:58:47"}
178
+ {"current_steps": 178, "total_steps": 891, "loss": 0.7432, "lr": 9.71173274800072e-06, "epoch": 0.5976496922216005, "percentage": 19.98, "elapsed_time": "0:29:38", "remaining_time": "1:58:43"}
179
+ {"current_steps": 179, "total_steps": 891, "loss": 0.7298, "lr": 9.70513411493058e-06, "epoch": 0.6010072747621712, "percentage": 20.09, "elapsed_time": "0:29:45", "remaining_time": "1:58:22"}
180
+ {"current_steps": 180, "total_steps": 891, "loss": 0.7627, "lr": 9.698463103929542e-06, "epoch": 0.604364857302742, "percentage": 20.2, "elapsed_time": "0:29:54", "remaining_time": "1:58:06"}
181
+ {"current_steps": 181, "total_steps": 891, "loss": 0.747, "lr": 9.691719817616148e-06, "epoch": 0.6077224398433129, "percentage": 20.31, "elapsed_time": "0:30:03", "remaining_time": "1:57:53"}
182
+ {"current_steps": 182, "total_steps": 891, "loss": 0.7338, "lr": 9.684904359720724e-06, "epoch": 0.6110800223838836, "percentage": 20.43, "elapsed_time": "0:30:14", "remaining_time": "1:57:46"}
183
+ {"current_steps": 183, "total_steps": 891, "loss": 0.7535, "lr": 9.678016835083798e-06, "epoch": 0.6144376049244544, "percentage": 20.54, "elapsed_time": "0:30:24", "remaining_time": "1:57:39"}
184
+ {"current_steps": 184, "total_steps": 891, "loss": 0.8249, "lr": 9.671057349654481e-06, "epoch": 0.6177951874650252, "percentage": 20.65, "elapsed_time": "0:30:34", "remaining_time": "1:57:27"}
185
+ {"current_steps": 185, "total_steps": 891, "loss": 0.7565, "lr": 9.66402601048884e-06, "epoch": 0.621152770005596, "percentage": 20.76, "elapsed_time": "0:30:42", "remaining_time": "1:57:13"}
186
+ {"current_steps": 186, "total_steps": 891, "loss": 0.779, "lr": 9.656922925748254e-06, "epoch": 0.6245103525461667, "percentage": 20.88, "elapsed_time": "0:30:57", "remaining_time": "1:57:18"}
187
+ {"current_steps": 187, "total_steps": 891, "loss": 0.7111, "lr": 9.649748204697741e-06, "epoch": 0.6278679350867375, "percentage": 20.99, "elapsed_time": "0:31:03", "remaining_time": "1:56:54"}
188
+ {"current_steps": 188, "total_steps": 891, "loss": 0.7737, "lr": 9.642501957704287e-06, "epoch": 0.6312255176273084, "percentage": 21.1, "elapsed_time": "0:31:13", "remaining_time": "1:56:43"}
189
+ {"current_steps": 189, "total_steps": 891, "loss": 0.7678, "lr": 9.63518429623514e-06, "epoch": 0.6345831001678791, "percentage": 21.21, "elapsed_time": "0:31:20", "remaining_time": "1:56:23"}
190
+ {"current_steps": 190, "total_steps": 891, "loss": 0.7765, "lr": 9.627795332856107e-06, "epoch": 0.63794068270845, "percentage": 21.32, "elapsed_time": "0:31:30", "remaining_time": "1:56:16"}
191
+ {"current_steps": 191, "total_steps": 891, "loss": 0.7583, "lr": 9.620335181229805e-06, "epoch": 0.6412982652490207, "percentage": 21.44, "elapsed_time": "0:31:38", "remaining_time": "1:55:58"}
192
+ {"current_steps": 192, "total_steps": 891, "loss": 0.7755, "lr": 9.612803956113932e-06, "epoch": 0.6446558477895915, "percentage": 21.55, "elapsed_time": "0:31:46", "remaining_time": "1:55:42"}
193
+ {"current_steps": 193, "total_steps": 891, "loss": 0.7125, "lr": 9.605201773359485e-06, "epoch": 0.6480134303301622, "percentage": 21.66, "elapsed_time": "0:32:00", "remaining_time": "1:55:47"}
194
+ {"current_steps": 194, "total_steps": 891, "loss": 0.72, "lr": 9.59752874990899e-06, "epoch": 0.6513710128707331, "percentage": 21.77, "elapsed_time": "0:32:09", "remaining_time": "1:55:33"}
195
+ {"current_steps": 195, "total_steps": 891, "loss": 0.741, "lr": 9.589785003794692e-06, "epoch": 0.6547285954113039, "percentage": 21.89, "elapsed_time": "0:32:22", "remaining_time": "1:55:34"}
196
+ {"current_steps": 196, "total_steps": 891, "loss": 0.7723, "lr": 9.581970654136752e-06, "epoch": 0.6580861779518746, "percentage": 22.0, "elapsed_time": "0:32:32", "remaining_time": "1:55:22"}
197
+ {"current_steps": 197, "total_steps": 891, "loss": 0.754, "lr": 9.574085821141406e-06, "epoch": 0.6614437604924455, "percentage": 22.11, "elapsed_time": "0:32:45", "remaining_time": "1:55:25"}
198
+ {"current_steps": 198, "total_steps": 891, "loss": 0.7738, "lr": 9.566130626099118e-06, "epoch": 0.6648013430330162, "percentage": 22.22, "elapsed_time": "0:32:55", "remaining_time": "1:55:14"}
199
+ {"current_steps": 199, "total_steps": 891, "loss": 0.781, "lr": 9.55810519138271e-06, "epoch": 0.668158925573587, "percentage": 22.33, "elapsed_time": "0:33:12", "remaining_time": "1:55:30"}
200
+ {"current_steps": 200, "total_steps": 891, "loss": 0.7606, "lr": 9.550009640445492e-06, "epoch": 0.6715165081141579, "percentage": 22.45, "elapsed_time": "0:33:19", "remaining_time": "1:55:09"}
201
+ {"current_steps": 201, "total_steps": 891, "loss": 0.7535, "lr": 9.541844097819347e-06, "epoch": 0.6748740906547286, "percentage": 22.56, "elapsed_time": "0:33:27", "remaining_time": "1:54:51"}
202
+ {"current_steps": 202, "total_steps": 891, "loss": 0.7559, "lr": 9.533608689112827e-06, "epoch": 0.6782316731952994, "percentage": 22.67, "elapsed_time": "0:33:34", "remaining_time": "1:54:30"}
203
+ {"current_steps": 203, "total_steps": 891, "loss": 0.6754, "lr": 9.525303541009218e-06, "epoch": 0.6815892557358701, "percentage": 22.78, "elapsed_time": "0:33:40", "remaining_time": "1:54:08"}
204
+ {"current_steps": 204, "total_steps": 891, "loss": 0.7431, "lr": 9.516928781264588e-06, "epoch": 0.684946838276441, "percentage": 22.9, "elapsed_time": "0:33:54", "remaining_time": "1:54:10"}
205
+ {"current_steps": 205, "total_steps": 891, "loss": 0.7649, "lr": 9.508484538705823e-06, "epoch": 0.6883044208170117, "percentage": 23.01, "elapsed_time": "0:34:02", "remaining_time": "1:53:54"}
206
+ {"current_steps": 206, "total_steps": 891, "loss": 0.7218, "lr": 9.499970943228646e-06, "epoch": 0.6916620033575825, "percentage": 23.12, "elapsed_time": "0:34:11", "remaining_time": "1:53:41"}
207
+ {"current_steps": 207, "total_steps": 891, "loss": 0.7104, "lr": 9.491388125795623e-06, "epoch": 0.6950195858981534, "percentage": 23.23, "elapsed_time": "0:34:17", "remaining_time": "1:53:20"}
208
+ {"current_steps": 208, "total_steps": 891, "loss": 0.7477, "lr": 9.482736218434144e-06, "epoch": 0.6983771684387241, "percentage": 23.34, "elapsed_time": "0:34:25", "remaining_time": "1:53:02"}
209
+ {"current_steps": 209, "total_steps": 891, "loss": 0.7587, "lr": 9.474015354234385e-06, "epoch": 0.7017347509792949, "percentage": 23.46, "elapsed_time": "0:34:33", "remaining_time": "1:52:45"}
210
+ {"current_steps": 210, "total_steps": 891, "loss": 0.7292, "lr": 9.465225667347275e-06, "epoch": 0.7050923335198657, "percentage": 23.57, "elapsed_time": "0:34:44", "remaining_time": "1:52:38"}
211
+ {"current_steps": 211, "total_steps": 891, "loss": 0.7241, "lr": 9.45636729298243e-06, "epoch": 0.7084499160604365, "percentage": 23.68, "elapsed_time": "0:34:52", "remaining_time": "1:52:23"}
212
+ {"current_steps": 212, "total_steps": 891, "loss": 0.7458, "lr": 9.447440367406053e-06, "epoch": 0.7118074986010072, "percentage": 23.79, "elapsed_time": "0:34:59", "remaining_time": "1:52:05"}
213
+ {"current_steps": 213, "total_steps": 891, "loss": 0.76, "lr": 9.438445027938873e-06, "epoch": 0.7151650811415781, "percentage": 23.91, "elapsed_time": "0:35:08", "remaining_time": "1:51:52"}
214
+ {"current_steps": 214, "total_steps": 891, "loss": 0.7463, "lr": 9.429381412954e-06, "epoch": 0.7185226636821489, "percentage": 24.02, "elapsed_time": "0:35:15", "remaining_time": "1:51:32"}
215
+ {"current_steps": 215, "total_steps": 891, "loss": 0.7562, "lr": 9.420249661874812e-06, "epoch": 0.7218802462227196, "percentage": 24.13, "elapsed_time": "0:35:25", "remaining_time": "1:51:24"}
216
+ {"current_steps": 216, "total_steps": 891, "loss": 0.719, "lr": 9.41104991517281e-06, "epoch": 0.7252378287632905, "percentage": 24.24, "elapsed_time": "0:35:31", "remaining_time": "1:51:01"}
217
+ {"current_steps": 217, "total_steps": 891, "loss": 0.7611, "lr": 9.401782314365458e-06, "epoch": 0.7285954113038612, "percentage": 24.35, "elapsed_time": "0:35:42", "remaining_time": "1:50:53"}
218
+ {"current_steps": 218, "total_steps": 891, "loss": 0.7241, "lr": 9.392447002013996e-06, "epoch": 0.731952993844432, "percentage": 24.47, "elapsed_time": "0:35:48", "remaining_time": "1:50:33"}
219
+ {"current_steps": 219, "total_steps": 891, "loss": 0.7413, "lr": 9.383044121721257e-06, "epoch": 0.7353105763850027, "percentage": 24.58, "elapsed_time": "0:35:58", "remaining_time": "1:50:22"}
220
+ {"current_steps": 220, "total_steps": 891, "loss": 0.7479, "lr": 9.37357381812946e-06, "epoch": 0.7386681589255736, "percentage": 24.69, "elapsed_time": "0:36:03", "remaining_time": "1:49:58"}
221
+ {"current_steps": 221, "total_steps": 891, "loss": 0.6834, "lr": 9.364036236917972e-06, "epoch": 0.7420257414661444, "percentage": 24.8, "elapsed_time": "0:36:13", "remaining_time": "1:49:50"}
222
+ {"current_steps": 222, "total_steps": 891, "loss": 0.7512, "lr": 9.354431524801082e-06, "epoch": 0.7453833240067151, "percentage": 24.92, "elapsed_time": "0:36:22", "remaining_time": "1:49:36"}
223
+ {"current_steps": 223, "total_steps": 891, "loss": 0.7138, "lr": 9.344759829525734e-06, "epoch": 0.748740906547286, "percentage": 25.03, "elapsed_time": "0:36:29", "remaining_time": "1:49:17"}
224
+ {"current_steps": 224, "total_steps": 891, "loss": 0.7382, "lr": 9.335021299869256e-06, "epoch": 0.7520984890878567, "percentage": 25.14, "elapsed_time": "0:36:43", "remaining_time": "1:49:20"}
225
+ {"current_steps": 225, "total_steps": 891, "loss": 0.7436, "lr": 9.32521608563708e-06, "epoch": 0.7554560716284275, "percentage": 25.25, "elapsed_time": "0:36:49", "remaining_time": "1:48:59"}
226
+ {"current_steps": 226, "total_steps": 891, "loss": 0.7364, "lr": 9.315344337660422e-06, "epoch": 0.7588136541689984, "percentage": 25.36, "elapsed_time": "0:36:56", "remaining_time": "1:48:42"}
227
+ {"current_steps": 227, "total_steps": 891, "loss": 0.7225, "lr": 9.305406207793974e-06, "epoch": 0.7621712367095691, "percentage": 25.48, "elapsed_time": "0:37:07", "remaining_time": "1:48:36"}
228
+ {"current_steps": 228, "total_steps": 891, "loss": 0.7458, "lr": 9.295401848913569e-06, "epoch": 0.7655288192501399, "percentage": 25.59, "elapsed_time": "0:37:14", "remaining_time": "1:48:18"}
229
+ {"current_steps": 229, "total_steps": 891, "loss": 0.6967, "lr": 9.285331414913816e-06, "epoch": 0.7688864017907107, "percentage": 25.7, "elapsed_time": "0:37:20", "remaining_time": "1:47:57"}
230
+ {"current_steps": 230, "total_steps": 891, "loss": 0.7501, "lr": 9.275195060705749e-06, "epoch": 0.7722439843312815, "percentage": 25.81, "elapsed_time": "0:37:30", "remaining_time": "1:47:48"}
231
+ {"current_steps": 231, "total_steps": 891, "loss": 0.7236, "lr": 9.264992942214427e-06, "epoch": 0.7756015668718522, "percentage": 25.93, "elapsed_time": "0:37:40", "remaining_time": "1:47:38"}
232
+ {"current_steps": 232, "total_steps": 891, "loss": 0.7666, "lr": 9.254725216376562e-06, "epoch": 0.7789591494124231, "percentage": 26.04, "elapsed_time": "0:37:55", "remaining_time": "1:47:43"}
233
+ {"current_steps": 233, "total_steps": 891, "loss": 0.7449, "lr": 9.244392041138068e-06, "epoch": 0.7823167319529939, "percentage": 26.15, "elapsed_time": "0:38:04", "remaining_time": "1:47:30"}
234
+ {"current_steps": 234, "total_steps": 891, "loss": 0.7052, "lr": 9.233993575451663e-06, "epoch": 0.7856743144935646, "percentage": 26.26, "elapsed_time": "0:38:17", "remaining_time": "1:47:31"}
235
+ {"current_steps": 235, "total_steps": 891, "loss": 0.7166, "lr": 9.223529979274411e-06, "epoch": 0.7890318970341355, "percentage": 26.37, "elapsed_time": "0:38:28", "remaining_time": "1:47:23"}
236
+ {"current_steps": 236, "total_steps": 891, "loss": 0.7614, "lr": 9.213001413565259e-06, "epoch": 0.7923894795747062, "percentage": 26.49, "elapsed_time": "0:38:38", "remaining_time": "1:47:15"}
237
+ {"current_steps": 237, "total_steps": 891, "loss": 0.7407, "lr": 9.202408040282567e-06, "epoch": 0.795747062115277, "percentage": 26.6, "elapsed_time": "0:38:48", "remaining_time": "1:47:05"}
238
+ {"current_steps": 238, "total_steps": 891, "loss": 0.76, "lr": 9.191750022381613e-06, "epoch": 0.7991046446558477, "percentage": 26.71, "elapsed_time": "0:38:56", "remaining_time": "1:46:49"}
239
+ {"current_steps": 239, "total_steps": 891, "loss": 0.6906, "lr": 9.181027523812088e-06, "epoch": 0.8024622271964186, "percentage": 26.82, "elapsed_time": "0:39:06", "remaining_time": "1:46:40"}
240
+ {"current_steps": 240, "total_steps": 891, "loss": 0.7492, "lr": 9.170240709515573e-06, "epoch": 0.8058198097369894, "percentage": 26.94, "elapsed_time": "0:39:14", "remaining_time": "1:46:26"}
241
+ {"current_steps": 241, "total_steps": 891, "loss": 0.753, "lr": 9.159389745423003e-06, "epoch": 0.8091773922775601, "percentage": 27.05, "elapsed_time": "0:39:22", "remaining_time": "1:46:12"}
242
+ {"current_steps": 242, "total_steps": 891, "loss": 0.7687, "lr": 9.14847479845211e-06, "epoch": 0.812534974818131, "percentage": 27.16, "elapsed_time": "0:39:31", "remaining_time": "1:46:00"}
243
+ {"current_steps": 243, "total_steps": 891, "loss": 0.7236, "lr": 9.137496036504868e-06, "epoch": 0.8158925573587017, "percentage": 27.27, "elapsed_time": "0:39:40", "remaining_time": "1:45:48"}
244
+ {"current_steps": 244, "total_steps": 891, "loss": 0.7513, "lr": 9.126453628464889e-06, "epoch": 0.8192501398992725, "percentage": 27.38, "elapsed_time": "0:39:54", "remaining_time": "1:45:48"}
245
+ {"current_steps": 245, "total_steps": 891, "loss": 0.7117, "lr": 9.115347744194844e-06, "epoch": 0.8226077224398433, "percentage": 27.5, "elapsed_time": "0:40:05", "remaining_time": "1:45:43"}
246
+ {"current_steps": 246, "total_steps": 891, "loss": 0.7421, "lr": 9.10417855453385e-06, "epoch": 0.8259653049804141, "percentage": 27.61, "elapsed_time": "0:40:19", "remaining_time": "1:45:45"}
247
+ {"current_steps": 247, "total_steps": 891, "loss": 0.7683, "lr": 9.09294623129482e-06, "epoch": 0.8293228875209849, "percentage": 27.72, "elapsed_time": "0:40:27", "remaining_time": "1:45:30"}
248
+ {"current_steps": 248, "total_steps": 891, "loss": 0.7454, "lr": 9.081650947261847e-06, "epoch": 0.8326804700615557, "percentage": 27.83, "elapsed_time": "0:40:40", "remaining_time": "1:45:26"}
249
+ {"current_steps": 249, "total_steps": 891, "loss": 0.7511, "lr": 9.070292876187532e-06, "epoch": 0.8360380526021265, "percentage": 27.95, "elapsed_time": "0:40:49", "remaining_time": "1:45:15"}
250
+ {"current_steps": 250, "total_steps": 891, "loss": 0.7594, "lr": 9.058872192790314e-06, "epoch": 0.8393956351426972, "percentage": 28.06, "elapsed_time": "0:40:56", "remaining_time": "1:44:59"}
251
+ {"current_steps": 251, "total_steps": 891, "loss": 0.7164, "lr": 9.047389072751777e-06, "epoch": 0.842753217683268, "percentage": 28.17, "elapsed_time": "0:41:05", "remaining_time": "1:44:45"}
252
+ {"current_steps": 252, "total_steps": 891, "loss": 0.7256, "lr": 9.035843692713961e-06, "epoch": 0.8461108002238389, "percentage": 28.28, "elapsed_time": "0:41:13", "remaining_time": "1:44:31"}
253
+ {"current_steps": 253, "total_steps": 891, "loss": 0.7307, "lr": 9.02423623027663e-06, "epoch": 0.8494683827644096, "percentage": 28.4, "elapsed_time": "0:41:30", "remaining_time": "1:44:39"}
254
+ {"current_steps": 254, "total_steps": 891, "loss": 0.7434, "lr": 9.012566863994548e-06, "epoch": 0.8528259653049804, "percentage": 28.51, "elapsed_time": "0:41:38", "remaining_time": "1:44:25"}
255
+ {"current_steps": 255, "total_steps": 891, "loss": 0.7454, "lr": 9.000835773374733e-06, "epoch": 0.8561835478455512, "percentage": 28.62, "elapsed_time": "0:41:47", "remaining_time": "1:44:13"}
256
+ {"current_steps": 256, "total_steps": 891, "loss": 0.7057, "lr": 8.98904313887369e-06, "epoch": 0.859541130386122, "percentage": 28.73, "elapsed_time": "0:41:54", "remaining_time": "1:43:57"}
257
+ {"current_steps": 257, "total_steps": 891, "loss": 0.7711, "lr": 8.977189141894645e-06, "epoch": 0.8628987129266927, "percentage": 28.84, "elapsed_time": "0:42:01", "remaining_time": "1:43:40"}
258
+ {"current_steps": 258, "total_steps": 891, "loss": 0.6948, "lr": 8.965273964784735e-06, "epoch": 0.8662562954672636, "percentage": 28.96, "elapsed_time": "0:42:09", "remaining_time": "1:43:25"}
259
+ {"current_steps": 259, "total_steps": 891, "loss": 0.7545, "lr": 8.953297790832231e-06, "epoch": 0.8696138780078344, "percentage": 29.07, "elapsed_time": "0:42:17", "remaining_time": "1:43:12"}
260
+ {"current_steps": 260, "total_steps": 891, "loss": 0.7427, "lr": 8.941260804263697e-06, "epoch": 0.8729714605484051, "percentage": 29.18, "elapsed_time": "0:42:29", "remaining_time": "1:43:08"}
261
+ {"current_steps": 261, "total_steps": 891, "loss": 0.7129, "lr": 8.929163190241157e-06, "epoch": 0.876329043088976, "percentage": 29.29, "elapsed_time": "0:42:41", "remaining_time": "1:43:03"}
262
+ {"current_steps": 262, "total_steps": 891, "loss": 0.6766, "lr": 8.917005134859263e-06, "epoch": 0.8796866256295467, "percentage": 29.41, "elapsed_time": "0:42:53", "remaining_time": "1:42:57"}
263
+ {"current_steps": 263, "total_steps": 891, "loss": 0.7312, "lr": 8.904786825142416e-06, "epoch": 0.8830442081701175, "percentage": 29.52, "elapsed_time": "0:43:04", "remaining_time": "1:42:51"}
264
+ {"current_steps": 264, "total_steps": 891, "loss": 0.752, "lr": 8.892508449041893e-06, "epoch": 0.8864017907106883, "percentage": 29.63, "elapsed_time": "0:43:13", "remaining_time": "1:42:39"}
265
+ {"current_steps": 265, "total_steps": 891, "loss": 0.741, "lr": 8.88017019543296e-06, "epoch": 0.8897593732512591, "percentage": 29.74, "elapsed_time": "0:43:26", "remaining_time": "1:42:36"}
266
+ {"current_steps": 266, "total_steps": 891, "loss": 0.7121, "lr": 8.867772254111966e-06, "epoch": 0.8931169557918299, "percentage": 29.85, "elapsed_time": "0:43:33", "remaining_time": "1:42:21"}
267
+ {"current_steps": 267, "total_steps": 891, "loss": 0.7259, "lr": 8.85531481579342e-06, "epoch": 0.8964745383324007, "percentage": 29.97, "elapsed_time": "0:43:46", "remaining_time": "1:42:18"}
268
+ {"current_steps": 268, "total_steps": 891, "loss": 0.8211, "lr": 8.842798072107055e-06, "epoch": 0.8998321208729715, "percentage": 30.08, "elapsed_time": "0:44:07", "remaining_time": "1:42:35"}
269
+ {"current_steps": 269, "total_steps": 891, "loss": 0.7545, "lr": 8.83022221559489e-06, "epoch": 0.9031897034135422, "percentage": 30.19, "elapsed_time": "0:44:14", "remaining_time": "1:42:18"}
270
+ {"current_steps": 270, "total_steps": 891, "loss": 0.7097, "lr": 8.81758743970826e-06, "epoch": 0.906547285954113, "percentage": 30.3, "elapsed_time": "0:44:23", "remaining_time": "1:42:05"}
271
+ {"current_steps": 271, "total_steps": 891, "loss": 0.7085, "lr": 8.804893938804839e-06, "epoch": 0.9099048684946839, "percentage": 30.42, "elapsed_time": "0:44:30", "remaining_time": "1:41:50"}
272
+ {"current_steps": 272, "total_steps": 891, "loss": 0.749, "lr": 8.79214190814566e-06, "epoch": 0.9132624510352546, "percentage": 30.53, "elapsed_time": "0:44:44", "remaining_time": "1:41:48"}
273
+ {"current_steps": 273, "total_steps": 891, "loss": 0.7437, "lr": 8.779331543892097e-06, "epoch": 0.9166200335758254, "percentage": 30.64, "elapsed_time": "0:44:50", "remaining_time": "1:41:30"}
274
+ {"current_steps": 274, "total_steps": 891, "loss": 0.7405, "lr": 8.766463043102864e-06, "epoch": 0.9199776161163962, "percentage": 30.75, "elapsed_time": "0:45:01", "remaining_time": "1:41:22"}
275
+ {"current_steps": 275, "total_steps": 891, "loss": 0.7099, "lr": 8.75353660373097e-06, "epoch": 0.923335198656967, "percentage": 30.86, "elapsed_time": "0:45:08", "remaining_time": "1:41:05"}
276
+ {"current_steps": 276, "total_steps": 891, "loss": 0.6971, "lr": 8.740552424620679e-06, "epoch": 0.9266927811975377, "percentage": 30.98, "elapsed_time": "0:45:19", "remaining_time": "1:40:59"}
277
+ {"current_steps": 277, "total_steps": 891, "loss": 0.7293, "lr": 8.727510705504453e-06, "epoch": 0.9300503637381086, "percentage": 31.09, "elapsed_time": "0:45:28", "remaining_time": "1:40:47"}
278
+ {"current_steps": 278, "total_steps": 891, "loss": 0.7741, "lr": 8.714411646999878e-06, "epoch": 0.9334079462786794, "percentage": 31.2, "elapsed_time": "0:45:39", "remaining_time": "1:40:39"}
279
+ {"current_steps": 279, "total_steps": 891, "loss": 0.7643, "lr": 8.701255450606579e-06, "epoch": 0.9367655288192501, "percentage": 31.31, "elapsed_time": "0:45:48", "remaining_time": "1:40:27"}
280
+ {"current_steps": 280, "total_steps": 891, "loss": 0.7464, "lr": 8.688042318703111e-06, "epoch": 0.940123111359821, "percentage": 31.43, "elapsed_time": "0:45:58", "remaining_time": "1:40:18"}
281
+ {"current_steps": 281, "total_steps": 891, "loss": 0.7103, "lr": 8.674772454543869e-06, "epoch": 0.9434806939003917, "percentage": 31.54, "elapsed_time": "0:46:07", "remaining_time": "1:40:07"}
282
+ {"current_steps": 282, "total_steps": 891, "loss": 0.6947, "lr": 8.661446062255931e-06, "epoch": 0.9468382764409625, "percentage": 31.65, "elapsed_time": "0:46:15", "remaining_time": "1:39:53"}
283
+ {"current_steps": 283, "total_steps": 891, "loss": 0.726, "lr": 8.648063346835943e-06, "epoch": 0.9501958589815332, "percentage": 31.76, "elapsed_time": "0:46:29", "remaining_time": "1:39:53"}
284
+ {"current_steps": 284, "total_steps": 891, "loss": 0.7353, "lr": 8.634624514146954e-06, "epoch": 0.9535534415221041, "percentage": 31.87, "elapsed_time": "0:46:44", "remaining_time": "1:39:53"}
285
+ {"current_steps": 285, "total_steps": 891, "loss": 0.7712, "lr": 8.621129770915248e-06, "epoch": 0.9569110240626749, "percentage": 31.99, "elapsed_time": "0:46:54", "remaining_time": "1:39:44"}
286
+ {"current_steps": 286, "total_steps": 891, "loss": 0.7472, "lr": 8.607579324727175e-06, "epoch": 0.9602686066032456, "percentage": 32.1, "elapsed_time": "0:47:07", "remaining_time": "1:39:41"}
287
+ {"current_steps": 287, "total_steps": 891, "loss": 0.7502, "lr": 8.59397338402594e-06, "epoch": 0.9636261891438165, "percentage": 32.21, "elapsed_time": "0:47:17", "remaining_time": "1:39:32"}
288
+ {"current_steps": 288, "total_steps": 891, "loss": 0.7464, "lr": 8.580312158108413e-06, "epoch": 0.9669837716843872, "percentage": 32.32, "elapsed_time": "0:47:25", "remaining_time": "1:39:18"}
289
+ {"current_steps": 289, "total_steps": 891, "loss": 0.7099, "lr": 8.566595857121902e-06, "epoch": 0.970341354224958, "percentage": 32.44, "elapsed_time": "0:47:36", "remaining_time": "1:39:09"}
290
+ {"current_steps": 290, "total_steps": 891, "loss": 0.7299, "lr": 8.55282469206092e-06, "epoch": 0.9736989367655288, "percentage": 32.55, "elapsed_time": "0:47:57", "remaining_time": "1:39:22"}
291
+ {"current_steps": 291, "total_steps": 891, "loss": 0.7639, "lr": 8.538998874763942e-06, "epoch": 0.9770565193060996, "percentage": 32.66, "elapsed_time": "0:48:06", "remaining_time": "1:39:11"}
292
+ {"current_steps": 292, "total_steps": 891, "loss": 0.7547, "lr": 8.525118617910144e-06, "epoch": 0.9804141018466704, "percentage": 32.77, "elapsed_time": "0:48:21", "remaining_time": "1:39:12"}
293
+ {"current_steps": 293, "total_steps": 891, "loss": 0.7309, "lr": 8.511184135016134e-06, "epoch": 0.9837716843872412, "percentage": 32.88, "elapsed_time": "0:48:34", "remaining_time": "1:39:07"}
294
+ {"current_steps": 294, "total_steps": 891, "loss": 0.7261, "lr": 8.497195640432664e-06, "epoch": 0.987129266927812, "percentage": 33.0, "elapsed_time": "0:48:45", "remaining_time": "1:39:00"}
295
+ {"current_steps": 295, "total_steps": 891, "loss": 0.7166, "lr": 8.483153349341336e-06, "epoch": 0.9904868494683827, "percentage": 33.11, "elapsed_time": "0:48:59", "remaining_time": "1:38:59"}
296
+ {"current_steps": 296, "total_steps": 891, "loss": 0.6816, "lr": 8.46905747775129e-06, "epoch": 0.9938444320089536, "percentage": 33.22, "elapsed_time": "0:49:06", "remaining_time": "1:38:43"}
297
+ {"current_steps": 297, "total_steps": 891, "loss": 0.7147, "lr": 8.45490824249588e-06, "epoch": 0.9972020145495244, "percentage": 33.33, "elapsed_time": "0:49:14", "remaining_time": "1:38:28"}
298
+ {"current_steps": 298, "total_steps": 891, "loss": 1.2836, "lr": 8.440705861229344e-06, "epoch": 1.0033575825405707, "percentage": 33.45, "elapsed_time": "0:49:22", "remaining_time": "1:38:15"}
299
+ {"current_steps": 299, "total_steps": 891, "loss": 0.5247, "lr": 8.426450552423451e-06, "epoch": 1.0067151650811417, "percentage": 33.56, "elapsed_time": "0:49:29", "remaining_time": "1:38:00"}
300
+ {"current_steps": 300, "total_steps": 891, "loss": 0.5023, "lr": 8.412142535364139e-06, "epoch": 1.0100727476217124, "percentage": 33.67, "elapsed_time": "0:49:38", "remaining_time": "1:37:46"}
301
+ {"current_steps": 301, "total_steps": 891, "loss": 0.5212, "lr": 8.397782030148147e-06, "epoch": 1.0134303301622831, "percentage": 33.78, "elapsed_time": "0:49:48", "remaining_time": "1:37:37"}
302
+ {"current_steps": 302, "total_steps": 891, "loss": 0.5258, "lr": 8.383369257679625e-06, "epoch": 1.0167879127028538, "percentage": 33.89, "elapsed_time": "0:49:56", "remaining_time": "1:37:23"}
303
+ {"current_steps": 303, "total_steps": 891, "loss": 0.4882, "lr": 8.368904439666739e-06, "epoch": 1.0201454952434248, "percentage": 34.01, "elapsed_time": "0:50:06", "remaining_time": "1:37:13"}
304
+ {"current_steps": 304, "total_steps": 891, "loss": 0.5222, "lr": 8.354387798618254e-06, "epoch": 1.0235030777839955, "percentage": 34.12, "elapsed_time": "0:50:13", "remaining_time": "1:36:57"}
305
+ {"current_steps": 305, "total_steps": 891, "loss": 0.4725, "lr": 8.339819557840124e-06, "epoch": 1.0268606603245662, "percentage": 34.23, "elapsed_time": "0:50:22", "remaining_time": "1:36:46"}
306
+ {"current_steps": 306, "total_steps": 891, "loss": 0.5223, "lr": 8.32519994143204e-06, "epoch": 1.0302182428651372, "percentage": 34.34, "elapsed_time": "0:50:31", "remaining_time": "1:36:34"}
307
+ {"current_steps": 307, "total_steps": 891, "loss": 0.5291, "lr": 8.310529174284004e-06, "epoch": 1.033575825405708, "percentage": 34.46, "elapsed_time": "0:50:40", "remaining_time": "1:36:24"}
308
+ {"current_steps": 308, "total_steps": 891, "loss": 0.5197, "lr": 8.295807482072842e-06, "epoch": 1.0369334079462786, "percentage": 34.57, "elapsed_time": "0:50:50", "remaining_time": "1:36:13"}
309
+ {"current_steps": 309, "total_steps": 891, "loss": 0.4758, "lr": 8.281035091258762e-06, "epoch": 1.0402909904868494, "percentage": 34.68, "elapsed_time": "0:50:59", "remaining_time": "1:36:03"}
310
+ {"current_steps": 310, "total_steps": 891, "loss": 0.4927, "lr": 8.266212229081846e-06, "epoch": 1.0436485730274203, "percentage": 34.79, "elapsed_time": "0:51:09", "remaining_time": "1:35:53"}
311
+ {"current_steps": 311, "total_steps": 891, "loss": 0.4897, "lr": 8.251339123558573e-06, "epoch": 1.047006155567991, "percentage": 34.9, "elapsed_time": "0:51:23", "remaining_time": "1:35:50"}
312
+ {"current_steps": 312, "total_steps": 891, "loss": 0.4794, "lr": 8.236416003478295e-06, "epoch": 1.0503637381085618, "percentage": 35.02, "elapsed_time": "0:51:31", "remaining_time": "1:35:36"}
313
+ {"current_steps": 313, "total_steps": 891, "loss": 0.4872, "lr": 8.221443098399733e-06, "epoch": 1.0537213206491327, "percentage": 35.13, "elapsed_time": "0:51:39", "remaining_time": "1:35:24"}
314
+ {"current_steps": 314, "total_steps": 891, "loss": 0.4945, "lr": 8.206420638647433e-06, "epoch": 1.0570789031897034, "percentage": 35.24, "elapsed_time": "0:51:47", "remaining_time": "1:35:10"}
315
+ {"current_steps": 315, "total_steps": 891, "loss": 0.4766, "lr": 8.191348855308229e-06, "epoch": 1.0604364857302742, "percentage": 35.35, "elapsed_time": "0:52:01", "remaining_time": "1:35:07"}
316
+ {"current_steps": 316, "total_steps": 891, "loss": 0.4723, "lr": 8.176227980227693e-06, "epoch": 1.063794068270845, "percentage": 35.47, "elapsed_time": "0:52:12", "remaining_time": "1:35:00"}
317
+ {"current_steps": 317, "total_steps": 891, "loss": 0.5207, "lr": 8.161058246006558e-06, "epoch": 1.0671516508114158, "percentage": 35.58, "elapsed_time": "0:52:25", "remaining_time": "1:34:54"}
318
+ {"current_steps": 318, "total_steps": 891, "loss": 0.4906, "lr": 8.145839885997146e-06, "epoch": 1.0705092333519866, "percentage": 35.69, "elapsed_time": "0:52:40", "remaining_time": "1:34:54"}
319
+ {"current_steps": 319, "total_steps": 891, "loss": 0.4918, "lr": 8.130573134299782e-06, "epoch": 1.0738668158925573, "percentage": 35.8, "elapsed_time": "0:52:46", "remaining_time": "1:34:38"}
320
+ {"current_steps": 320, "total_steps": 891, "loss": 0.4515, "lr": 8.11525822575918e-06, "epoch": 1.0772243984331282, "percentage": 35.91, "elapsed_time": "0:52:55", "remaining_time": "1:34:25"}
321
+ {"current_steps": 321, "total_steps": 891, "loss": 0.5124, "lr": 8.099895395960847e-06, "epoch": 1.080581980973699, "percentage": 36.03, "elapsed_time": "0:53:09", "remaining_time": "1:34:23"}
322
+ {"current_steps": 322, "total_steps": 891, "loss": 0.4867, "lr": 8.084484881227449e-06, "epoch": 1.0839395635142697, "percentage": 36.14, "elapsed_time": "0:53:17", "remaining_time": "1:34:09"}
323
+ {"current_steps": 323, "total_steps": 891, "loss": 0.4901, "lr": 8.069026918615173e-06, "epoch": 1.0872971460548406, "percentage": 36.25, "elapsed_time": "0:53:25", "remaining_time": "1:33:56"}
324
+ {"current_steps": 324, "total_steps": 891, "loss": 0.5072, "lr": 8.05352174591009e-06, "epoch": 1.0906547285954113, "percentage": 36.36, "elapsed_time": "0:53:41", "remaining_time": "1:33:57"}
325
+ {"current_steps": 325, "total_steps": 891, "loss": 0.5104, "lr": 8.037969601624495e-06, "epoch": 1.094012311135982, "percentage": 36.48, "elapsed_time": "0:53:50", "remaining_time": "1:33:46"}
326
+ {"current_steps": 326, "total_steps": 891, "loss": 0.4585, "lr": 8.022370724993229e-06, "epoch": 1.0973698936765528, "percentage": 36.59, "elapsed_time": "0:53:57", "remaining_time": "1:33:30"}
327
+ {"current_steps": 327, "total_steps": 891, "loss": 0.4979, "lr": 8.006725355970008e-06, "epoch": 1.1007274762171237, "percentage": 36.7, "elapsed_time": "0:54:12", "remaining_time": "1:33:30"}
328
+ {"current_steps": 328, "total_steps": 891, "loss": 0.4929, "lr": 7.99103373522373e-06, "epoch": 1.1040850587576945, "percentage": 36.81, "elapsed_time": "0:54:20", "remaining_time": "1:33:16"}
329
+ {"current_steps": 329, "total_steps": 891, "loss": 0.4891, "lr": 7.975296104134768e-06, "epoch": 1.1074426412982652, "percentage": 36.92, "elapsed_time": "0:54:31", "remaining_time": "1:33:07"}
330
+ {"current_steps": 330, "total_steps": 891, "loss": 0.4957, "lr": 7.959512704791269e-06, "epoch": 1.1108002238388361, "percentage": 37.04, "elapsed_time": "0:54:43", "remaining_time": "1:33:02"}
331
+ {"current_steps": 331, "total_steps": 891, "loss": 0.4891, "lr": 7.943683779985412e-06, "epoch": 1.1141578063794069, "percentage": 37.15, "elapsed_time": "0:54:54", "remaining_time": "1:32:54"}
332
+ {"current_steps": 332, "total_steps": 891, "loss": 0.4667, "lr": 7.927809573209691e-06, "epoch": 1.1175153889199776, "percentage": 37.26, "elapsed_time": "0:55:08", "remaining_time": "1:32:51"}
333
+ {"current_steps": 333, "total_steps": 891, "loss": 0.4485, "lr": 7.911890328653156e-06, "epoch": 1.1208729714605483, "percentage": 37.37, "elapsed_time": "0:55:15", "remaining_time": "1:32:36"}
334
+ {"current_steps": 334, "total_steps": 891, "loss": 0.4817, "lr": 7.895926291197667e-06, "epoch": 1.1242305540011193, "percentage": 37.49, "elapsed_time": "0:55:24", "remaining_time": "1:32:23"}
335
+ {"current_steps": 335, "total_steps": 891, "loss": 0.5305, "lr": 7.87991770641412e-06, "epoch": 1.12758813654169, "percentage": 37.6, "elapsed_time": "0:55:35", "remaining_time": "1:32:15"}
336
+ {"current_steps": 336, "total_steps": 891, "loss": 0.5083, "lr": 7.863864820558669e-06, "epoch": 1.1309457190822607, "percentage": 37.71, "elapsed_time": "0:55:45", "remaining_time": "1:32:05"}
337
+ {"current_steps": 337, "total_steps": 891, "loss": 0.4588, "lr": 7.847767880568944e-06, "epoch": 1.1343033016228317, "percentage": 37.82, "elapsed_time": "0:55:54", "remaining_time": "1:31:54"}
338
+ {"current_steps": 338, "total_steps": 891, "loss": 0.4846, "lr": 7.831627134060249e-06, "epoch": 1.1376608841634024, "percentage": 37.93, "elapsed_time": "0:56:04", "remaining_time": "1:31:45"}
339
+ {"current_steps": 339, "total_steps": 891, "loss": 0.483, "lr": 7.815442829321754e-06, "epoch": 1.141018466703973, "percentage": 38.05, "elapsed_time": "0:56:19", "remaining_time": "1:31:42"}
340
+ {"current_steps": 340, "total_steps": 891, "loss": 0.4579, "lr": 7.799215215312667e-06, "epoch": 1.1443760492445438, "percentage": 38.16, "elapsed_time": "0:56:26", "remaining_time": "1:31:27"}
341
+ {"current_steps": 341, "total_steps": 891, "loss": 0.5117, "lr": 7.782944541658423e-06, "epoch": 1.1477336317851148, "percentage": 38.27, "elapsed_time": "0:56:35", "remaining_time": "1:31:16"}
342
+ {"current_steps": 342, "total_steps": 891, "loss": 0.4622, "lr": 7.766631058646826e-06, "epoch": 1.1510912143256855, "percentage": 38.38, "elapsed_time": "0:56:46", "remaining_time": "1:31:08"}
343
+ {"current_steps": 343, "total_steps": 891, "loss": 0.4724, "lr": 7.750275017224208e-06, "epoch": 1.1544487968662562, "percentage": 38.5, "elapsed_time": "0:56:57", "remaining_time": "1:30:59"}
344
+ {"current_steps": 344, "total_steps": 891, "loss": 0.4924, "lr": 7.733876668991565e-06, "epoch": 1.1578063794068272, "percentage": 38.61, "elapsed_time": "0:57:06", "remaining_time": "1:30:48"}
345
+ {"current_steps": 345, "total_steps": 891, "loss": 0.517, "lr": 7.71743626620069e-06, "epoch": 1.161163961947398, "percentage": 38.72, "elapsed_time": "0:57:13", "remaining_time": "1:30:33"}
346
+ {"current_steps": 346, "total_steps": 891, "loss": 0.487, "lr": 7.700954061750295e-06, "epoch": 1.1645215444879686, "percentage": 38.83, "elapsed_time": "0:57:19", "remaining_time": "1:30:17"}
347
+ {"current_steps": 347, "total_steps": 891, "loss": 0.4709, "lr": 7.684430309182106e-06, "epoch": 1.1678791270285394, "percentage": 38.95, "elapsed_time": "0:57:27", "remaining_time": "1:30:04"}
348
+ {"current_steps": 348, "total_steps": 891, "loss": 0.489, "lr": 7.667865262676981e-06, "epoch": 1.1712367095691103, "percentage": 39.06, "elapsed_time": "0:57:34", "remaining_time": "1:29:50"}
349
+ {"current_steps": 349, "total_steps": 891, "loss": 0.5033, "lr": 7.651259177050996e-06, "epoch": 1.174594292109681, "percentage": 39.17, "elapsed_time": "0:57:44", "remaining_time": "1:29:39"}
350
+ {"current_steps": 350, "total_steps": 891, "loss": 0.45, "lr": 7.634612307751513e-06, "epoch": 1.1779518746502518, "percentage": 39.28, "elapsed_time": "0:57:55", "remaining_time": "1:29:31"}
351
+ {"current_steps": 351, "total_steps": 891, "loss": 0.5108, "lr": 7.617924910853266e-06, "epoch": 1.1813094571908227, "percentage": 39.39, "elapsed_time": "0:58:01", "remaining_time": "1:29:16"}
352
+ {"current_steps": 352, "total_steps": 891, "loss": 0.4998, "lr": 7.601197243054411e-06, "epoch": 1.1846670397313934, "percentage": 39.51, "elapsed_time": "0:58:14", "remaining_time": "1:29:10"}
353
+ {"current_steps": 353, "total_steps": 891, "loss": 0.4822, "lr": 7.584429561672586e-06, "epoch": 1.1880246222719641, "percentage": 39.62, "elapsed_time": "0:58:26", "remaining_time": "1:29:04"}
354
+ {"current_steps": 354, "total_steps": 891, "loss": 0.4824, "lr": 7.567622124640942e-06, "epoch": 1.1913822048125349, "percentage": 39.73, "elapsed_time": "0:58:33", "remaining_time": "1:28:49"}
355
+ {"current_steps": 355, "total_steps": 891, "loss": 0.5051, "lr": 7.5507751905041885e-06, "epoch": 1.1947397873531058, "percentage": 39.84, "elapsed_time": "0:58:43", "remaining_time": "1:28:40"}
356
+ {"current_steps": 356, "total_steps": 891, "loss": 0.4909, "lr": 7.533889018414602e-06, "epoch": 1.1980973698936765, "percentage": 39.96, "elapsed_time": "0:58:57", "remaining_time": "1:28:35"}
357
+ {"current_steps": 357, "total_steps": 891, "loss": 0.4975, "lr": 7.516963868128054e-06, "epoch": 1.2014549524342473, "percentage": 40.07, "elapsed_time": "0:59:06", "remaining_time": "1:28:25"}
358
+ {"current_steps": 358, "total_steps": 891, "loss": 0.5057, "lr": 7.500000000000001e-06, "epoch": 1.2048125349748182, "percentage": 40.18, "elapsed_time": "0:59:13", "remaining_time": "1:28:10"}
359
+ {"current_steps": 359, "total_steps": 891, "loss": 0.4958, "lr": 7.4829976749814935e-06, "epoch": 1.208170117515389, "percentage": 40.29, "elapsed_time": "0:59:24", "remaining_time": "1:28:02"}
360
+ {"current_steps": 360, "total_steps": 891, "loss": 0.51, "lr": 7.46595715461515e-06, "epoch": 1.2115277000559597, "percentage": 40.4, "elapsed_time": "0:59:37", "remaining_time": "1:27:56"}
361
+ {"current_steps": 361, "total_steps": 891, "loss": 0.4986, "lr": 7.4488787010311425e-06, "epoch": 1.2148852825965304, "percentage": 40.52, "elapsed_time": "0:59:45", "remaining_time": "1:27:44"}
362
+ {"current_steps": 362, "total_steps": 891, "loss": 0.5224, "lr": 7.431762576943157e-06, "epoch": 1.2182428651371013, "percentage": 40.63, "elapsed_time": "0:59:55", "remaining_time": "1:27:34"}
363
+ {"current_steps": 363, "total_steps": 891, "loss": 0.5036, "lr": 7.414609045644356e-06, "epoch": 1.221600447677672, "percentage": 40.74, "elapsed_time": "1:00:03", "remaining_time": "1:27:21"}
364
+ {"current_steps": 364, "total_steps": 891, "loss": 0.4985, "lr": 7.3974183710033334e-06, "epoch": 1.2249580302182428, "percentage": 40.85, "elapsed_time": "1:00:11", "remaining_time": "1:27:08"}
365
+ {"current_steps": 365, "total_steps": 891, "loss": 0.4826, "lr": 7.38019081746004e-06, "epoch": 1.2283156127588137, "percentage": 40.97, "elapsed_time": "1:00:20", "remaining_time": "1:26:57"}
366
+ {"current_steps": 366, "total_steps": 891, "loss": 0.4734, "lr": 7.362926650021736e-06, "epoch": 1.2316731952993845, "percentage": 41.08, "elapsed_time": "1:00:34", "remaining_time": "1:26:53"}
367
+ {"current_steps": 367, "total_steps": 891, "loss": 0.4707, "lr": 7.345626134258897e-06, "epoch": 1.2350307778399552, "percentage": 41.19, "elapsed_time": "1:00:40", "remaining_time": "1:26:37"}
368
+ {"current_steps": 368, "total_steps": 891, "loss": 0.4429, "lr": 7.3282895363011405e-06, "epoch": 1.238388360380526, "percentage": 41.3, "elapsed_time": "1:00:47", "remaining_time": "1:26:23"}
369
+ {"current_steps": 369, "total_steps": 891, "loss": 0.5123, "lr": 7.310917122833127e-06, "epoch": 1.2417459429210969, "percentage": 41.41, "elapsed_time": "1:00:56", "remaining_time": "1:26:12"}
370
+ {"current_steps": 370, "total_steps": 891, "loss": 0.4868, "lr": 7.293509161090453e-06, "epoch": 1.2451035254616676, "percentage": 41.53, "elapsed_time": "1:01:03", "remaining_time": "1:25:58"}
371
+ {"current_steps": 371, "total_steps": 891, "loss": 0.4917, "lr": 7.276065918855554e-06, "epoch": 1.2484611080022383, "percentage": 41.64, "elapsed_time": "1:01:13", "remaining_time": "1:25:49"}
372
+ {"current_steps": 372, "total_steps": 891, "loss": 0.4957, "lr": 7.2585876644535705e-06, "epoch": 1.2518186905428093, "percentage": 41.75, "elapsed_time": "1:01:26", "remaining_time": "1:25:43"}
373
+ {"current_steps": 373, "total_steps": 891, "loss": 0.5311, "lr": 7.241074666748228e-06, "epoch": 1.25517627308338, "percentage": 41.86, "elapsed_time": "1:01:35", "remaining_time": "1:25:31"}
374
+ {"current_steps": 374, "total_steps": 891, "loss": 0.5217, "lr": 7.2235271951377005e-06, "epoch": 1.2585338556239507, "percentage": 41.98, "elapsed_time": "1:01:42", "remaining_time": "1:25:17"}
375
+ {"current_steps": 375, "total_steps": 891, "loss": 0.4972, "lr": 7.205945519550467e-06, "epoch": 1.2618914381645214, "percentage": 42.09, "elapsed_time": "1:01:53", "remaining_time": "1:25:09"}
376
+ {"current_steps": 376, "total_steps": 891, "loss": 0.4715, "lr": 7.188329910441154e-06, "epoch": 1.2652490207050924, "percentage": 42.2, "elapsed_time": "1:02:01", "remaining_time": "1:24:56"}
377
+ {"current_steps": 377, "total_steps": 891, "loss": 0.4841, "lr": 7.170680638786383e-06, "epoch": 1.268606603245663, "percentage": 42.31, "elapsed_time": "1:02:13", "remaining_time": "1:24:50"}
378
+ {"current_steps": 378, "total_steps": 891, "loss": 0.5132, "lr": 7.1529979760805946e-06, "epoch": 1.271964185786234, "percentage": 42.42, "elapsed_time": "1:02:26", "remaining_time": "1:24:44"}
379
+ {"current_steps": 379, "total_steps": 891, "loss": 0.4916, "lr": 7.135282194331881e-06, "epoch": 1.2753217683268048, "percentage": 42.54, "elapsed_time": "1:02:38", "remaining_time": "1:24:36"}
380
+ {"current_steps": 380, "total_steps": 891, "loss": 0.4985, "lr": 7.1175335660577906e-06, "epoch": 1.2786793508673755, "percentage": 42.65, "elapsed_time": "1:02:45", "remaining_time": "1:24:23"}
381
+ {"current_steps": 381, "total_steps": 891, "loss": 0.4985, "lr": 7.099752364281147e-06, "epoch": 1.2820369334079462, "percentage": 42.76, "elapsed_time": "1:02:52", "remaining_time": "1:24:09"}
382
+ {"current_steps": 382, "total_steps": 891, "loss": 0.4648, "lr": 7.0819388625258385e-06, "epoch": 1.285394515948517, "percentage": 42.87, "elapsed_time": "1:03:01", "remaining_time": "1:23:58"}
383
+ {"current_steps": 383, "total_steps": 891, "loss": 0.5151, "lr": 7.0640933348126235e-06, "epoch": 1.288752098489088, "percentage": 42.99, "elapsed_time": "1:03:10", "remaining_time": "1:23:48"}
384
+ {"current_steps": 384, "total_steps": 891, "loss": 0.4853, "lr": 7.046216055654902e-06, "epoch": 1.2921096810296586, "percentage": 43.1, "elapsed_time": "1:03:16", "remaining_time": "1:23:33"}
385
+ {"current_steps": 385, "total_steps": 891, "loss": 0.5407, "lr": 7.028307300054499e-06, "epoch": 1.2954672635702296, "percentage": 43.21, "elapsed_time": "1:03:34", "remaining_time": "1:23:32"}
386
+ {"current_steps": 386, "total_steps": 891, "loss": 0.504, "lr": 7.0103673434974375e-06, "epoch": 1.2988248461108003, "percentage": 43.32, "elapsed_time": "1:03:44", "remaining_time": "1:23:23"}
387
+ {"current_steps": 387, "total_steps": 891, "loss": 0.4724, "lr": 6.992396461949693e-06, "epoch": 1.302182428651371, "percentage": 43.43, "elapsed_time": "1:03:53", "remaining_time": "1:23:12"}
388
+ {"current_steps": 388, "total_steps": 891, "loss": 0.4901, "lr": 6.974394931852957e-06, "epoch": 1.3055400111919417, "percentage": 43.55, "elapsed_time": "1:04:00", "remaining_time": "1:22:59"}
389
+ {"current_steps": 389, "total_steps": 891, "loss": 0.4779, "lr": 6.956363030120377e-06, "epoch": 1.3088975937325125, "percentage": 43.66, "elapsed_time": "1:04:07", "remaining_time": "1:22:45"}
390
+ {"current_steps": 390, "total_steps": 891, "loss": 0.4661, "lr": 6.9383010341323e-06, "epoch": 1.3122551762730834, "percentage": 43.77, "elapsed_time": "1:04:16", "remaining_time": "1:22:34"}
391
+ {"current_steps": 391, "total_steps": 891, "loss": 0.4814, "lr": 6.920209221732007e-06, "epoch": 1.3156127588136541, "percentage": 43.88, "elapsed_time": "1:04:29", "remaining_time": "1:22:28"}
392
+ {"current_steps": 392, "total_steps": 891, "loss": 0.498, "lr": 6.902087871221439e-06, "epoch": 1.318970341354225, "percentage": 44.0, "elapsed_time": "1:04:39", "remaining_time": "1:22:18"}
393
+ {"current_steps": 393, "total_steps": 891, "loss": 0.5079, "lr": 6.88393726135691e-06, "epoch": 1.3223279238947958, "percentage": 44.11, "elapsed_time": "1:04:48", "remaining_time": "1:22:07"}
394
+ {"current_steps": 394, "total_steps": 891, "loss": 0.4769, "lr": 6.865757671344827e-06, "epoch": 1.3256855064353665, "percentage": 44.22, "elapsed_time": "1:04:58", "remaining_time": "1:21:57"}
395
+ {"current_steps": 395, "total_steps": 891, "loss": 0.4766, "lr": 6.8475493808373895e-06, "epoch": 1.3290430889759373, "percentage": 44.33, "elapsed_time": "1:05:05", "remaining_time": "1:21:44"}
396
+ {"current_steps": 396, "total_steps": 891, "loss": 0.456, "lr": 6.829312669928293e-06, "epoch": 1.332400671516508, "percentage": 44.44, "elapsed_time": "1:05:21", "remaining_time": "1:21:41"}
397
+ {"current_steps": 397, "total_steps": 891, "loss": 0.4984, "lr": 6.811047819148413e-06, "epoch": 1.335758254057079, "percentage": 44.56, "elapsed_time": "1:05:26", "remaining_time": "1:21:26"}
398
+ {"current_steps": 398, "total_steps": 891, "loss": 0.4866, "lr": 6.792755109461498e-06, "epoch": 1.3391158365976497, "percentage": 44.67, "elapsed_time": "1:05:37", "remaining_time": "1:21:17"}
399
+ {"current_steps": 399, "total_steps": 891, "loss": 0.499, "lr": 6.7744348222598386e-06, "epoch": 1.3424734191382206, "percentage": 44.78, "elapsed_time": "1:05:45", "remaining_time": "1:21:05"}
400
+ {"current_steps": 400, "total_steps": 891, "loss": 0.493, "lr": 6.756087239359948e-06, "epoch": 1.3458310016787913, "percentage": 44.89, "elapsed_time": "1:05:56", "remaining_time": "1:20:56"}
401
+ {"current_steps": 401, "total_steps": 891, "loss": 0.5378, "lr": 6.737712642998219e-06, "epoch": 1.349188584219362, "percentage": 45.01, "elapsed_time": "1:06:57", "remaining_time": "1:21:49"}
402
+ {"current_steps": 402, "total_steps": 891, "loss": 0.4714, "lr": 6.719311315826589e-06, "epoch": 1.3525461667599328, "percentage": 45.12, "elapsed_time": "1:07:12", "remaining_time": "1:21:45"}
403
+ {"current_steps": 403, "total_steps": 891, "loss": 0.4872, "lr": 6.700883540908185e-06, "epoch": 1.3559037493005035, "percentage": 45.23, "elapsed_time": "1:07:21", "remaining_time": "1:21:34"}
404
+ {"current_steps": 404, "total_steps": 891, "loss": 0.4799, "lr": 6.682429601712976e-06, "epoch": 1.3592613318410744, "percentage": 45.34, "elapsed_time": "1:07:33", "remaining_time": "1:21:25"}
405
+ {"current_steps": 405, "total_steps": 891, "loss": 0.5166, "lr": 6.663949782113413e-06, "epoch": 1.3626189143816452, "percentage": 45.45, "elapsed_time": "1:07:44", "remaining_time": "1:21:17"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23477fc4d73b27ad2609e1f37eee9b972fa50ce3b3c2db3fbb3af3ac6fac2247
3
+ size 8312