Matt300209 commited on
Commit
d73081c
·
verified ·
1 Parent(s): f03d909

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
+ checkpoint-2286/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-4570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-2286/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 32.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.48.1",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
checkpoint-2286/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.48.1"
9
+ }
checkpoint-2286/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0acb6ca3480bb502c67cb621355ab508da0de16c44aaf87c72261c22e16b23f0
3
+ size 4980379440
checkpoint-2286/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7dcb30264e4d462f9627497f20b317f5542fce02a799a9d537d4564c2d2b349
3
+ size 1144267912
checkpoint-2286/model.safetensors.index.json ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6124593152
4
+ },
5
+ "weight_map": {
6
+ "lm_head.A": "model-00002-of-00002.safetensors",
7
+ "lm_head.B": "model-00002-of-00002.safetensors",
8
+ "lm_head.scales": "model-00002-of-00002.safetensors",
9
+ "lm_head.weight": "model-00002-of-00002.safetensors",
10
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.down_proj.A": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.down_proj.B": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.mlp.up_proj.A": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.mlp.up_proj.B": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
30
+ "model.layers.0.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
31
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
32
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.0.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
34
+ "model.layers.0.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
35
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
36
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.0.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
38
+ "model.layers.0.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
39
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
40
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.down_proj.A": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.down_proj.B": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.mlp.up_proj.A": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.mlp.up_proj.B": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
53
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.1.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
56
+ "model.layers.1.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
57
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
58
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.1.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
60
+ "model.layers.1.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
61
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
62
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.1.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
64
+ "model.layers.1.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
65
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
66
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.1.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
68
+ "model.layers.1.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
69
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
70
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.10.mlp.down_proj.A": "model-00001-of-00002.safetensors",
73
+ "model.layers.10.mlp.down_proj.B": "model-00001-of-00002.safetensors",
74
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
75
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.10.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
77
+ "model.layers.10.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
78
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
79
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.10.mlp.up_proj.A": "model-00001-of-00002.safetensors",
81
+ "model.layers.10.mlp.up_proj.B": "model-00001-of-00002.safetensors",
82
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
83
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.10.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
86
+ "model.layers.10.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
87
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
88
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.10.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
90
+ "model.layers.10.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
91
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
92
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.10.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
94
+ "model.layers.10.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
95
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
96
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.10.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
98
+ "model.layers.10.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
99
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
100
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.11.mlp.down_proj.A": "model-00001-of-00002.safetensors",
103
+ "model.layers.11.mlp.down_proj.B": "model-00001-of-00002.safetensors",
104
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
105
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.11.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
107
+ "model.layers.11.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
108
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
109
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.11.mlp.up_proj.A": "model-00001-of-00002.safetensors",
111
+ "model.layers.11.mlp.up_proj.B": "model-00001-of-00002.safetensors",
112
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
113
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.11.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
116
+ "model.layers.11.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
117
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
118
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.11.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
120
+ "model.layers.11.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
121
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
122
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.11.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
124
+ "model.layers.11.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
125
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
126
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.11.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
128
+ "model.layers.11.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
129
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
130
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.12.mlp.down_proj.A": "model-00001-of-00002.safetensors",
133
+ "model.layers.12.mlp.down_proj.B": "model-00001-of-00002.safetensors",
134
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
135
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.12.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
137
+ "model.layers.12.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
138
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
139
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.12.mlp.up_proj.A": "model-00001-of-00002.safetensors",
141
+ "model.layers.12.mlp.up_proj.B": "model-00001-of-00002.safetensors",
142
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
143
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.12.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
146
+ "model.layers.12.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
147
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
148
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.12.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
150
+ "model.layers.12.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
151
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
152
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.12.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
154
+ "model.layers.12.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
155
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
156
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.12.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
158
+ "model.layers.12.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
159
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
160
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.13.mlp.down_proj.A": "model-00001-of-00002.safetensors",
163
+ "model.layers.13.mlp.down_proj.B": "model-00001-of-00002.safetensors",
164
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
165
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.13.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
167
+ "model.layers.13.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
168
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
169
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.13.mlp.up_proj.A": "model-00001-of-00002.safetensors",
171
+ "model.layers.13.mlp.up_proj.B": "model-00001-of-00002.safetensors",
172
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
173
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.13.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
176
+ "model.layers.13.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
177
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
178
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.13.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
180
+ "model.layers.13.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
181
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
182
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.13.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
184
+ "model.layers.13.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
185
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
186
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.13.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
188
+ "model.layers.13.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
189
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
190
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.14.mlp.down_proj.A": "model-00001-of-00002.safetensors",
193
+ "model.layers.14.mlp.down_proj.B": "model-00001-of-00002.safetensors",
194
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
195
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.14.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
197
+ "model.layers.14.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
198
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
199
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.14.mlp.up_proj.A": "model-00001-of-00002.safetensors",
201
+ "model.layers.14.mlp.up_proj.B": "model-00001-of-00002.safetensors",
202
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
203
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.14.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
206
+ "model.layers.14.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
207
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
208
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.14.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
210
+ "model.layers.14.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
211
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
212
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.14.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
214
+ "model.layers.14.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
215
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
216
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.14.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
218
+ "model.layers.14.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
219
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
220
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.15.mlp.down_proj.A": "model-00002-of-00002.safetensors",
223
+ "model.layers.15.mlp.down_proj.B": "model-00002-of-00002.safetensors",
224
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
225
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.15.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
227
+ "model.layers.15.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
228
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
229
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.15.mlp.up_proj.A": "model-00001-of-00002.safetensors",
231
+ "model.layers.15.mlp.up_proj.B": "model-00001-of-00002.safetensors",
232
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
233
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.15.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
236
+ "model.layers.15.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
237
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
238
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.15.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
240
+ "model.layers.15.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
241
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
242
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.15.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
244
+ "model.layers.15.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
245
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
246
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.15.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
248
+ "model.layers.15.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
249
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
250
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.2.mlp.down_proj.A": "model-00001-of-00002.safetensors",
253
+ "model.layers.2.mlp.down_proj.B": "model-00001-of-00002.safetensors",
254
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
255
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.2.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
257
+ "model.layers.2.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
258
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
259
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.2.mlp.up_proj.A": "model-00001-of-00002.safetensors",
261
+ "model.layers.2.mlp.up_proj.B": "model-00001-of-00002.safetensors",
262
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
263
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.2.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
266
+ "model.layers.2.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
267
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
268
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.2.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
270
+ "model.layers.2.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
271
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
272
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.2.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
274
+ "model.layers.2.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
275
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
276
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.2.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
278
+ "model.layers.2.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
279
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
280
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.3.mlp.down_proj.A": "model-00001-of-00002.safetensors",
283
+ "model.layers.3.mlp.down_proj.B": "model-00001-of-00002.safetensors",
284
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.mlp.up_proj.A": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.mlp.up_proj.B": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
296
+ "model.layers.3.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
297
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
298
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.3.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
300
+ "model.layers.3.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
301
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
302
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.3.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
304
+ "model.layers.3.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
305
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
306
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.3.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
308
+ "model.layers.3.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
309
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
310
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.4.mlp.down_proj.A": "model-00001-of-00002.safetensors",
313
+ "model.layers.4.mlp.down_proj.B": "model-00001-of-00002.safetensors",
314
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.4.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
317
+ "model.layers.4.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
318
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
319
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.4.mlp.up_proj.A": "model-00001-of-00002.safetensors",
321
+ "model.layers.4.mlp.up_proj.B": "model-00001-of-00002.safetensors",
322
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
323
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.4.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
326
+ "model.layers.4.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
327
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
328
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.4.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
330
+ "model.layers.4.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
331
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
332
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.4.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
334
+ "model.layers.4.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
335
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
336
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.4.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
338
+ "model.layers.4.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
339
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.5.mlp.down_proj.A": "model-00001-of-00002.safetensors",
343
+ "model.layers.5.mlp.down_proj.B": "model-00001-of-00002.safetensors",
344
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
345
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.5.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
347
+ "model.layers.5.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
348
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
349
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.mlp.up_proj.A": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.up_proj.B": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.5.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
360
+ "model.layers.5.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
361
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
362
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.5.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
364
+ "model.layers.5.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
365
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
366
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.5.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
368
+ "model.layers.5.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
369
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
370
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.6.mlp.down_proj.A": "model-00001-of-00002.safetensors",
373
+ "model.layers.6.mlp.down_proj.B": "model-00001-of-00002.safetensors",
374
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
375
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.6.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
377
+ "model.layers.6.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
378
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
379
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.6.mlp.up_proj.A": "model-00001-of-00002.safetensors",
381
+ "model.layers.6.mlp.up_proj.B": "model-00001-of-00002.safetensors",
382
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
383
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.6.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
386
+ "model.layers.6.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
387
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
388
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.6.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
390
+ "model.layers.6.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
391
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.7.mlp.down_proj.A": "model-00001-of-00002.safetensors",
403
+ "model.layers.7.mlp.down_proj.B": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.mlp.up_proj.A": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.mlp.up_proj.B": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
416
+ "model.layers.7.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.7.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
428
+ "model.layers.7.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
429
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
430
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.mlp.down_proj.A": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.down_proj.B": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.mlp.up_proj.A": "model-00001-of-00002.safetensors",
441
+ "model.layers.8.mlp.up_proj.B": "model-00001-of-00002.safetensors",
442
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
443
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.8.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
446
+ "model.layers.8.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
447
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
448
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.8.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
450
+ "model.layers.8.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
451
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
452
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.8.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
454
+ "model.layers.8.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
455
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
456
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.8.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
458
+ "model.layers.8.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
459
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
460
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
462
+ "model.layers.9.mlp.down_proj.A": "model-00001-of-00002.safetensors",
463
+ "model.layers.9.mlp.down_proj.B": "model-00001-of-00002.safetensors",
464
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
465
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.9.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
467
+ "model.layers.9.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
468
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
469
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.9.mlp.up_proj.A": "model-00001-of-00002.safetensors",
471
+ "model.layers.9.mlp.up_proj.B": "model-00001-of-00002.safetensors",
472
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
473
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
474
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.9.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
476
+ "model.layers.9.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
477
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
478
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.9.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
480
+ "model.layers.9.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
481
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
482
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
483
+ "model.layers.9.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
484
+ "model.layers.9.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
485
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
486
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.layers.9.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
488
+ "model.layers.9.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
489
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
490
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.norm.weight": "model-00002-of-00002.safetensors"
492
+ }
493
+ }
checkpoint-2286/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a32a1e78c7bfac1b7d76162d6db0714e4f21996722e714d7ef61837116340a1
3
+ size 107615371
checkpoint-2286/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de69a2834426ff9ef8199d077e00892579278af31d8969d77f98235b5cfc010a
3
+ size 14645
checkpoint-2286/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f4d03cdedfe7d54728969153d7472d1c0e823abdc76bae70b2348d32fe4c73
3
+ size 1465
checkpoint-2286/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
checkpoint-2286/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-2286/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "\n {{- bos_token }}\n {%- for message in messages %}\n {%- if message['role'] == 'assistant' %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '\n' }}\n {%- generation %}\n {{- message['content'] + '<|eot_id|>' }}\n {%- endgeneration %}\n {{- '\n' }}\n {%- else %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '\n' + message['content'] + '<|eot_id|>' + '\n' }}\n {%- endif %}\n {%- endfor %}\n {%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n' }}\n {%- endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-2286/trainer_state.json ADDED
@@ -0,0 +1,1644 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2286,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "eval_loss": 2.3424127101898193,
14
+ "eval_runtime": 1.1989,
15
+ "eval_samples_per_second": 16.682,
16
+ "eval_steps_per_second": 4.171,
17
+ "step": 0
18
+ },
19
+ {
20
+ "epoch": 0.0004375410194705754,
21
+ "grad_norm": 11.591988563537598,
22
+ "learning_rate": 3.6231884057971015e-07,
23
+ "loss": 1.7217,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.004375410194705754,
28
+ "grad_norm": 7.750391006469727,
29
+ "learning_rate": 3.6231884057971017e-06,
30
+ "loss": 1.6447,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.008750820389411508,
35
+ "grad_norm": 4.005843162536621,
36
+ "learning_rate": 7.246376811594203e-06,
37
+ "loss": 1.5732,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.01312623058411726,
42
+ "grad_norm": 2.8733792304992676,
43
+ "learning_rate": 1.0869565217391305e-05,
44
+ "loss": 1.4077,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.017501640778823015,
49
+ "grad_norm": 2.6543965339660645,
50
+ "learning_rate": 1.4492753623188407e-05,
51
+ "loss": 1.3353,
52
+ "step": 40
53
+ },
54
+ {
55
+ "epoch": 0.021877050973528767,
56
+ "grad_norm": 2.3828840255737305,
57
+ "learning_rate": 1.8115942028985507e-05,
58
+ "loss": 1.2485,
59
+ "step": 50
60
+ },
61
+ {
62
+ "epoch": 0.02625246116823452,
63
+ "grad_norm": 2.1744871139526367,
64
+ "learning_rate": 2.173913043478261e-05,
65
+ "loss": 1.2685,
66
+ "step": 60
67
+ },
68
+ {
69
+ "epoch": 0.030627871362940276,
70
+ "grad_norm": 2.292287588119507,
71
+ "learning_rate": 2.5362318840579714e-05,
72
+ "loss": 1.1884,
73
+ "step": 70
74
+ },
75
+ {
76
+ "epoch": 0.03500328155764603,
77
+ "grad_norm": 2.3060696125030518,
78
+ "learning_rate": 2.8985507246376814e-05,
79
+ "loss": 1.2874,
80
+ "step": 80
81
+ },
82
+ {
83
+ "epoch": 0.039378691752351785,
84
+ "grad_norm": 2.0335893630981445,
85
+ "learning_rate": 3.260869565217392e-05,
86
+ "loss": 1.2227,
87
+ "step": 90
88
+ },
89
+ {
90
+ "epoch": 0.04375410194705753,
91
+ "grad_norm": 2.4152441024780273,
92
+ "learning_rate": 3.6231884057971014e-05,
93
+ "loss": 1.192,
94
+ "step": 100
95
+ },
96
+ {
97
+ "epoch": 0.04812951214176329,
98
+ "grad_norm": 2.216953992843628,
99
+ "learning_rate": 3.985507246376812e-05,
100
+ "loss": 1.1883,
101
+ "step": 110
102
+ },
103
+ {
104
+ "epoch": 0.05250492233646904,
105
+ "grad_norm": 2.3724114894866943,
106
+ "learning_rate": 4.347826086956522e-05,
107
+ "loss": 1.1811,
108
+ "step": 120
109
+ },
110
+ {
111
+ "epoch": 0.0568803325311748,
112
+ "grad_norm": 2.238722801208496,
113
+ "learning_rate": 4.710144927536232e-05,
114
+ "loss": 1.168,
115
+ "step": 130
116
+ },
117
+ {
118
+ "epoch": 0.06125574272588055,
119
+ "grad_norm": 2.2097883224487305,
120
+ "learning_rate": 4.999997487707664e-05,
121
+ "loss": 1.1848,
122
+ "step": 140
123
+ },
124
+ {
125
+ "epoch": 0.0656311529205863,
126
+ "grad_norm": 2.2063302993774414,
127
+ "learning_rate": 4.999909558006067e-05,
128
+ "loss": 1.2155,
129
+ "step": 150
130
+ },
131
+ {
132
+ "epoch": 0.07000656311529206,
133
+ "grad_norm": 1.8397595882415771,
134
+ "learning_rate": 4.9996960187368994e-05,
135
+ "loss": 1.1507,
136
+ "step": 160
137
+ },
138
+ {
139
+ "epoch": 0.07438197330999781,
140
+ "grad_norm": 1.8552066087722778,
141
+ "learning_rate": 4.9993568806295786e-05,
142
+ "loss": 1.2109,
143
+ "step": 170
144
+ },
145
+ {
146
+ "epoch": 0.07875738350470357,
147
+ "grad_norm": 2.173321485519409,
148
+ "learning_rate": 4.998892160724318e-05,
149
+ "loss": 1.1784,
150
+ "step": 180
151
+ },
152
+ {
153
+ "epoch": 0.08313279369940932,
154
+ "grad_norm": 2.0949854850769043,
155
+ "learning_rate": 4.998301882371268e-05,
156
+ "loss": 1.1967,
157
+ "step": 190
158
+ },
159
+ {
160
+ "epoch": 0.08750820389411507,
161
+ "grad_norm": 1.8619498014450073,
162
+ "learning_rate": 4.997586075229346e-05,
163
+ "loss": 1.1761,
164
+ "step": 200
165
+ },
166
+ {
167
+ "epoch": 0.09188361408882083,
168
+ "grad_norm": 1.9095852375030518,
169
+ "learning_rate": 4.996744775264743e-05,
170
+ "loss": 1.15,
171
+ "step": 210
172
+ },
173
+ {
174
+ "epoch": 0.09625902428352658,
175
+ "grad_norm": 2.0714683532714844,
176
+ "learning_rate": 4.995778024749118e-05,
177
+ "loss": 1.1477,
178
+ "step": 220
179
+ },
180
+ {
181
+ "epoch": 0.10063443447823234,
182
+ "grad_norm": 1.9555009603500366,
183
+ "learning_rate": 4.9946858722574743e-05,
184
+ "loss": 1.1602,
185
+ "step": 230
186
+ },
187
+ {
188
+ "epoch": 0.10500984467293809,
189
+ "grad_norm": 1.9120110273361206,
190
+ "learning_rate": 4.993468372665718e-05,
191
+ "loss": 1.1516,
192
+ "step": 240
193
+ },
194
+ {
195
+ "epoch": 0.10938525486764385,
196
+ "grad_norm": 1.8210362195968628,
197
+ "learning_rate": 4.9921255871479e-05,
198
+ "loss": 1.1404,
199
+ "step": 250
200
+ },
201
+ {
202
+ "epoch": 0.1137606650623496,
203
+ "grad_norm": 1.8263871669769287,
204
+ "learning_rate": 4.990657583173146e-05,
205
+ "loss": 1.1629,
206
+ "step": 260
207
+ },
208
+ {
209
+ "epoch": 0.11813607525705534,
210
+ "grad_norm": 1.906760811805725,
211
+ "learning_rate": 4.989064434502262e-05,
212
+ "loss": 1.1364,
213
+ "step": 270
214
+ },
215
+ {
216
+ "epoch": 0.1225114854517611,
217
+ "grad_norm": 1.7693920135498047,
218
+ "learning_rate": 4.9873462211840296e-05,
219
+ "loss": 1.1396,
220
+ "step": 280
221
+ },
222
+ {
223
+ "epoch": 0.12688689564646685,
224
+ "grad_norm": 1.8662511110305786,
225
+ "learning_rate": 4.985503029551184e-05,
226
+ "loss": 1.1859,
227
+ "step": 290
228
+ },
229
+ {
230
+ "epoch": 0.1312623058411726,
231
+ "grad_norm": 1.7560139894485474,
232
+ "learning_rate": 4.983534952216079e-05,
233
+ "loss": 1.1419,
234
+ "step": 300
235
+ },
236
+ {
237
+ "epoch": 0.13563771603587838,
238
+ "grad_norm": 1.8666057586669922,
239
+ "learning_rate": 4.981442088066029e-05,
240
+ "loss": 1.1686,
241
+ "step": 310
242
+ },
243
+ {
244
+ "epoch": 0.14001312623058412,
245
+ "grad_norm": 1.7406998872756958,
246
+ "learning_rate": 4.9792245422583406e-05,
247
+ "loss": 1.1275,
248
+ "step": 320
249
+ },
250
+ {
251
+ "epoch": 0.14438853642528987,
252
+ "grad_norm": 1.717785120010376,
253
+ "learning_rate": 4.9768824262150344e-05,
254
+ "loss": 1.1236,
255
+ "step": 330
256
+ },
257
+ {
258
+ "epoch": 0.14876394661999562,
259
+ "grad_norm": 1.7829722166061401,
260
+ "learning_rate": 4.9744158576172406e-05,
261
+ "loss": 1.1297,
262
+ "step": 340
263
+ },
264
+ {
265
+ "epoch": 0.15313935681470137,
266
+ "grad_norm": 1.8614799976348877,
267
+ "learning_rate": 4.971824960399289e-05,
268
+ "loss": 1.2018,
269
+ "step": 350
270
+ },
271
+ {
272
+ "epoch": 0.15751476700940714,
273
+ "grad_norm": 1.9301059246063232,
274
+ "learning_rate": 4.9691098647424806e-05,
275
+ "loss": 1.1491,
276
+ "step": 360
277
+ },
278
+ {
279
+ "epoch": 0.1618901772041129,
280
+ "grad_norm": 1.7714897394180298,
281
+ "learning_rate": 4.9662707070685476e-05,
282
+ "loss": 1.1393,
283
+ "step": 370
284
+ },
285
+ {
286
+ "epoch": 0.16626558739881864,
287
+ "grad_norm": 1.7732449769973755,
288
+ "learning_rate": 4.963307630032797e-05,
289
+ "loss": 1.1029,
290
+ "step": 380
291
+ },
292
+ {
293
+ "epoch": 0.17064099759352439,
294
+ "grad_norm": 1.6674808263778687,
295
+ "learning_rate": 4.960220782516946e-05,
296
+ "loss": 1.1385,
297
+ "step": 390
298
+ },
299
+ {
300
+ "epoch": 0.17501640778823013,
301
+ "grad_norm": 1.8136391639709473,
302
+ "learning_rate": 4.957010319621638e-05,
303
+ "loss": 1.0898,
304
+ "step": 400
305
+ },
306
+ {
307
+ "epoch": 0.1793918179829359,
308
+ "grad_norm": 1.7509042024612427,
309
+ "learning_rate": 4.95367640265865e-05,
310
+ "loss": 1.1914,
311
+ "step": 410
312
+ },
313
+ {
314
+ "epoch": 0.18376722817764166,
315
+ "grad_norm": 1.7148741483688354,
316
+ "learning_rate": 4.950219199142791e-05,
317
+ "loss": 1.1228,
318
+ "step": 420
319
+ },
320
+ {
321
+ "epoch": 0.1881426383723474,
322
+ "grad_norm": 1.8227111101150513,
323
+ "learning_rate": 4.9466388827834795e-05,
324
+ "loss": 1.1556,
325
+ "step": 430
326
+ },
327
+ {
328
+ "epoch": 0.19251804856705315,
329
+ "grad_norm": 1.6873571872711182,
330
+ "learning_rate": 4.9429356334760205e-05,
331
+ "loss": 1.1551,
332
+ "step": 440
333
+ },
334
+ {
335
+ "epoch": 0.19689345876175893,
336
+ "grad_norm": 1.6948832273483276,
337
+ "learning_rate": 4.9391096372925626e-05,
338
+ "loss": 1.1085,
339
+ "step": 450
340
+ },
341
+ {
342
+ "epoch": 0.20126886895646467,
343
+ "grad_norm": 1.7749884128570557,
344
+ "learning_rate": 4.9351610864727504e-05,
345
+ "loss": 1.1421,
346
+ "step": 460
347
+ },
348
+ {
349
+ "epoch": 0.20564427915117042,
350
+ "grad_norm": 1.607061743736267,
351
+ "learning_rate": 4.9310901794140665e-05,
352
+ "loss": 1.155,
353
+ "step": 470
354
+ },
355
+ {
356
+ "epoch": 0.21001968934587617,
357
+ "grad_norm": 1.6496872901916504,
358
+ "learning_rate": 4.92689712066186e-05,
359
+ "loss": 1.1552,
360
+ "step": 480
361
+ },
362
+ {
363
+ "epoch": 0.21439509954058192,
364
+ "grad_norm": 1.5627405643463135,
365
+ "learning_rate": 4.922582120899072e-05,
366
+ "loss": 1.1419,
367
+ "step": 490
368
+ },
369
+ {
370
+ "epoch": 0.2187705097352877,
371
+ "grad_norm": 1.7042529582977295,
372
+ "learning_rate": 4.918145396935648e-05,
373
+ "loss": 1.1652,
374
+ "step": 500
375
+ },
376
+ {
377
+ "epoch": 0.22314591992999344,
378
+ "grad_norm": 1.5909007787704468,
379
+ "learning_rate": 4.913587171697643e-05,
380
+ "loss": 1.1294,
381
+ "step": 510
382
+ },
383
+ {
384
+ "epoch": 0.2275213301246992,
385
+ "grad_norm": 1.7357898950576782,
386
+ "learning_rate": 4.908907674216023e-05,
387
+ "loss": 1.1119,
388
+ "step": 520
389
+ },
390
+ {
391
+ "epoch": 0.23189674031940494,
392
+ "grad_norm": 1.6394789218902588,
393
+ "learning_rate": 4.9041071396151585e-05,
394
+ "loss": 1.1626,
395
+ "step": 530
396
+ },
397
+ {
398
+ "epoch": 0.23627215051411068,
399
+ "grad_norm": 1.5801527500152588,
400
+ "learning_rate": 4.899185809101003e-05,
401
+ "loss": 1.1211,
402
+ "step": 540
403
+ },
404
+ {
405
+ "epoch": 0.24064756070881646,
406
+ "grad_norm": 1.8420217037200928,
407
+ "learning_rate": 4.894143929948982e-05,
408
+ "loss": 1.1103,
409
+ "step": 550
410
+ },
411
+ {
412
+ "epoch": 0.2450229709035222,
413
+ "grad_norm": 1.671028971672058,
414
+ "learning_rate": 4.8889817554915645e-05,
415
+ "loss": 1.1461,
416
+ "step": 560
417
+ },
418
+ {
419
+ "epoch": 0.24939838109822796,
420
+ "grad_norm": 1.6634349822998047,
421
+ "learning_rate": 4.8836995451055344e-05,
422
+ "loss": 1.1562,
423
+ "step": 570
424
+ },
425
+ {
426
+ "epoch": 0.2537737912929337,
427
+ "grad_norm": 1.5025454759597778,
428
+ "learning_rate": 4.878297564198959e-05,
429
+ "loss": 1.0946,
430
+ "step": 580
431
+ },
432
+ {
433
+ "epoch": 0.2581492014876395,
434
+ "grad_norm": 1.7138441801071167,
435
+ "learning_rate": 4.872776084197851e-05,
436
+ "loss": 1.1093,
437
+ "step": 590
438
+ },
439
+ {
440
+ "epoch": 0.2625246116823452,
441
+ "grad_norm": 1.668101191520691,
442
+ "learning_rate": 4.867135382532533e-05,
443
+ "loss": 1.153,
444
+ "step": 600
445
+ },
446
+ {
447
+ "epoch": 0.266900021877051,
448
+ "grad_norm": 1.706669569015503,
449
+ "learning_rate": 4.861375742623697e-05,
450
+ "loss": 1.1281,
451
+ "step": 610
452
+ },
453
+ {
454
+ "epoch": 0.27127543207175675,
455
+ "grad_norm": 2.0017876625061035,
456
+ "learning_rate": 4.855497453868164e-05,
457
+ "loss": 1.1056,
458
+ "step": 620
459
+ },
460
+ {
461
+ "epoch": 0.27565084226646247,
462
+ "grad_norm": 1.611232042312622,
463
+ "learning_rate": 4.849500811624343e-05,
464
+ "loss": 1.1271,
465
+ "step": 630
466
+ },
467
+ {
468
+ "epoch": 0.28002625246116825,
469
+ "grad_norm": 1.463722586631775,
470
+ "learning_rate": 4.8433861171973896e-05,
471
+ "loss": 1.1402,
472
+ "step": 640
473
+ },
474
+ {
475
+ "epoch": 0.28440166265587397,
476
+ "grad_norm": 1.5447578430175781,
477
+ "learning_rate": 4.837153677824067e-05,
478
+ "loss": 1.1493,
479
+ "step": 650
480
+ },
481
+ {
482
+ "epoch": 0.28877707285057974,
483
+ "grad_norm": 1.496686339378357,
484
+ "learning_rate": 4.830803806657311e-05,
485
+ "loss": 1.1333,
486
+ "step": 660
487
+ },
488
+ {
489
+ "epoch": 0.2931524830452855,
490
+ "grad_norm": 1.6186118125915527,
491
+ "learning_rate": 4.8243368227504924e-05,
492
+ "loss": 1.1545,
493
+ "step": 670
494
+ },
495
+ {
496
+ "epoch": 0.29752789323999124,
497
+ "grad_norm": 1.5591745376586914,
498
+ "learning_rate": 4.817753051041387e-05,
499
+ "loss": 1.1189,
500
+ "step": 680
501
+ },
502
+ {
503
+ "epoch": 0.301903303434697,
504
+ "grad_norm": 1.8602070808410645,
505
+ "learning_rate": 4.811052822335849e-05,
506
+ "loss": 1.1486,
507
+ "step": 690
508
+ },
509
+ {
510
+ "epoch": 0.30627871362940273,
511
+ "grad_norm": 1.5043679475784302,
512
+ "learning_rate": 4.80423647329119e-05,
513
+ "loss": 1.0961,
514
+ "step": 700
515
+ },
516
+ {
517
+ "epoch": 0.3106541238241085,
518
+ "grad_norm": 1.6095219850540161,
519
+ "learning_rate": 4.797304346399263e-05,
520
+ "loss": 1.141,
521
+ "step": 710
522
+ },
523
+ {
524
+ "epoch": 0.3150295340188143,
525
+ "grad_norm": 1.628132939338684,
526
+ "learning_rate": 4.790256789969252e-05,
527
+ "loss": 1.1784,
528
+ "step": 720
529
+ },
530
+ {
531
+ "epoch": 0.31940494421352,
532
+ "grad_norm": 1.5121166706085205,
533
+ "learning_rate": 4.783094158110174e-05,
534
+ "loss": 1.1193,
535
+ "step": 730
536
+ },
537
+ {
538
+ "epoch": 0.3237803544082258,
539
+ "grad_norm": 1.5826560258865356,
540
+ "learning_rate": 4.775816810713086e-05,
541
+ "loss": 1.1206,
542
+ "step": 740
543
+ },
544
+ {
545
+ "epoch": 0.3281557646029315,
546
+ "grad_norm": 1.5174522399902344,
547
+ "learning_rate": 4.768425113433e-05,
548
+ "loss": 1.1566,
549
+ "step": 750
550
+ },
551
+ {
552
+ "epoch": 0.3325311747976373,
553
+ "grad_norm": 1.6296701431274414,
554
+ "learning_rate": 4.7609194376705105e-05,
555
+ "loss": 1.1388,
556
+ "step": 760
557
+ },
558
+ {
559
+ "epoch": 0.33690658499234305,
560
+ "grad_norm": 1.798865556716919,
561
+ "learning_rate": 4.753300160553136e-05,
562
+ "loss": 1.1889,
563
+ "step": 770
564
+ },
565
+ {
566
+ "epoch": 0.34128199518704877,
567
+ "grad_norm": 1.6122382879257202,
568
+ "learning_rate": 4.745567664916368e-05,
569
+ "loss": 1.125,
570
+ "step": 780
571
+ },
572
+ {
573
+ "epoch": 0.34565740538175455,
574
+ "grad_norm": 1.6329957246780396,
575
+ "learning_rate": 4.737722339284436e-05,
576
+ "loss": 1.121,
577
+ "step": 790
578
+ },
579
+ {
580
+ "epoch": 0.35003281557646027,
581
+ "grad_norm": 1.697094440460205,
582
+ "learning_rate": 4.7297645778507835e-05,
583
+ "loss": 1.0644,
584
+ "step": 800
585
+ },
586
+ {
587
+ "epoch": 0.35440822577116604,
588
+ "grad_norm": 1.6578021049499512,
589
+ "learning_rate": 4.721694780458266e-05,
590
+ "loss": 1.1579,
591
+ "step": 810
592
+ },
593
+ {
594
+ "epoch": 0.3587836359658718,
595
+ "grad_norm": 1.478832483291626,
596
+ "learning_rate": 4.7135133525790544e-05,
597
+ "loss": 1.1512,
598
+ "step": 820
599
+ },
600
+ {
601
+ "epoch": 0.36315904616057754,
602
+ "grad_norm": 1.513938546180725,
603
+ "learning_rate": 4.7052207052942685e-05,
604
+ "loss": 1.0791,
605
+ "step": 830
606
+ },
607
+ {
608
+ "epoch": 0.3675344563552833,
609
+ "grad_norm": 1.5836193561553955,
610
+ "learning_rate": 4.6968172552733185e-05,
611
+ "loss": 1.1259,
612
+ "step": 840
613
+ },
614
+ {
615
+ "epoch": 0.3719098665499891,
616
+ "grad_norm": 1.617882490158081,
617
+ "learning_rate": 4.688303424752969e-05,
618
+ "loss": 1.1001,
619
+ "step": 850
620
+ },
621
+ {
622
+ "epoch": 0.3762852767446948,
623
+ "grad_norm": 1.4709640741348267,
624
+ "learning_rate": 4.679679641516122e-05,
625
+ "loss": 1.1085,
626
+ "step": 860
627
+ },
628
+ {
629
+ "epoch": 0.3806606869394006,
630
+ "grad_norm": 1.4871046543121338,
631
+ "learning_rate": 4.670946338870329e-05,
632
+ "loss": 1.0863,
633
+ "step": 870
634
+ },
635
+ {
636
+ "epoch": 0.3850360971341063,
637
+ "grad_norm": 1.5609277486801147,
638
+ "learning_rate": 4.6621039556260095e-05,
639
+ "loss": 1.1255,
640
+ "step": 880
641
+ },
642
+ {
643
+ "epoch": 0.3894115073288121,
644
+ "grad_norm": 1.513523817062378,
645
+ "learning_rate": 4.653152936074413e-05,
646
+ "loss": 1.1101,
647
+ "step": 890
648
+ },
649
+ {
650
+ "epoch": 0.39378691752351785,
651
+ "grad_norm": 1.6045000553131104,
652
+ "learning_rate": 4.644093729965287e-05,
653
+ "loss": 1.1041,
654
+ "step": 900
655
+ },
656
+ {
657
+ "epoch": 0.3981623277182236,
658
+ "grad_norm": 1.5579705238342285,
659
+ "learning_rate": 4.634926792484284e-05,
660
+ "loss": 1.1592,
661
+ "step": 910
662
+ },
663
+ {
664
+ "epoch": 0.40253773791292935,
665
+ "grad_norm": 1.4306694269180298,
666
+ "learning_rate": 4.625652584230089e-05,
667
+ "loss": 1.1465,
668
+ "step": 920
669
+ },
670
+ {
671
+ "epoch": 0.40691314810763507,
672
+ "grad_norm": 1.3425192832946777,
673
+ "learning_rate": 4.616271571191273e-05,
674
+ "loss": 1.1555,
675
+ "step": 930
676
+ },
677
+ {
678
+ "epoch": 0.41128855830234085,
679
+ "grad_norm": 1.5686333179473877,
680
+ "learning_rate": 4.606784224722887e-05,
681
+ "loss": 1.1394,
682
+ "step": 940
683
+ },
684
+ {
685
+ "epoch": 0.4156639684970466,
686
+ "grad_norm": 1.4096781015396118,
687
+ "learning_rate": 4.5971910215227684e-05,
688
+ "loss": 1.0751,
689
+ "step": 950
690
+ },
691
+ {
692
+ "epoch": 0.42003937869175234,
693
+ "grad_norm": 1.3961308002471924,
694
+ "learning_rate": 4.5874924436075996e-05,
695
+ "loss": 1.1281,
696
+ "step": 960
697
+ },
698
+ {
699
+ "epoch": 0.4244147888864581,
700
+ "grad_norm": 1.4717061519622803,
701
+ "learning_rate": 4.577688978288681e-05,
702
+ "loss": 1.1441,
703
+ "step": 970
704
+ },
705
+ {
706
+ "epoch": 0.42879019908116384,
707
+ "grad_norm": 1.4169813394546509,
708
+ "learning_rate": 4.567781118147448e-05,
709
+ "loss": 1.1381,
710
+ "step": 980
711
+ },
712
+ {
713
+ "epoch": 0.4331656092758696,
714
+ "grad_norm": 1.4888379573822021,
715
+ "learning_rate": 4.557769361010721e-05,
716
+ "loss": 1.0826,
717
+ "step": 990
718
+ },
719
+ {
720
+ "epoch": 0.4375410194705754,
721
+ "grad_norm": 1.572547435760498,
722
+ "learning_rate": 4.547654209925693e-05,
723
+ "loss": 1.1131,
724
+ "step": 1000
725
+ },
726
+ {
727
+ "epoch": 0.4419164296652811,
728
+ "grad_norm": 1.5723587274551392,
729
+ "learning_rate": 4.5374361731346526e-05,
730
+ "loss": 1.1088,
731
+ "step": 1010
732
+ },
733
+ {
734
+ "epoch": 0.4462918398599869,
735
+ "grad_norm": 1.5646806955337524,
736
+ "learning_rate": 4.5271157640494456e-05,
737
+ "loss": 1.1313,
738
+ "step": 1020
739
+ },
740
+ {
741
+ "epoch": 0.4506672500546926,
742
+ "grad_norm": 1.6168869733810425,
743
+ "learning_rate": 4.51669350122568e-05,
744
+ "loss": 1.1452,
745
+ "step": 1030
746
+ },
747
+ {
748
+ "epoch": 0.4550426602493984,
749
+ "grad_norm": 1.565577745437622,
750
+ "learning_rate": 4.506169908336673e-05,
751
+ "loss": 1.1473,
752
+ "step": 1040
753
+ },
754
+ {
755
+ "epoch": 0.45941807044410415,
756
+ "grad_norm": 1.6016472578048706,
757
+ "learning_rate": 4.495545514147134e-05,
758
+ "loss": 1.1006,
759
+ "step": 1050
760
+ },
761
+ {
762
+ "epoch": 0.4637934806388099,
763
+ "grad_norm": 1.628869891166687,
764
+ "learning_rate": 4.484820852486598e-05,
765
+ "loss": 1.1327,
766
+ "step": 1060
767
+ },
768
+ {
769
+ "epoch": 0.46816889083351565,
770
+ "grad_norm": 1.4887852668762207,
771
+ "learning_rate": 4.473996462222606e-05,
772
+ "loss": 1.1011,
773
+ "step": 1070
774
+ },
775
+ {
776
+ "epoch": 0.47254430102822137,
777
+ "grad_norm": 1.6507240533828735,
778
+ "learning_rate": 4.463072887233625e-05,
779
+ "loss": 1.15,
780
+ "step": 1080
781
+ },
782
+ {
783
+ "epoch": 0.47691971122292715,
784
+ "grad_norm": 1.5163503885269165,
785
+ "learning_rate": 4.452050676381725e-05,
786
+ "loss": 1.1598,
787
+ "step": 1090
788
+ },
789
+ {
790
+ "epoch": 0.4812951214176329,
791
+ "grad_norm": 1.6033108234405518,
792
+ "learning_rate": 4.440930383484995e-05,
793
+ "loss": 1.118,
794
+ "step": 1100
795
+ },
796
+ {
797
+ "epoch": 0.48567053161233864,
798
+ "grad_norm": 1.4987646341323853,
799
+ "learning_rate": 4.429712567289722e-05,
800
+ "loss": 1.1352,
801
+ "step": 1110
802
+ },
803
+ {
804
+ "epoch": 0.4900459418070444,
805
+ "grad_norm": 1.51768159866333,
806
+ "learning_rate": 4.418397791442314e-05,
807
+ "loss": 1.1433,
808
+ "step": 1120
809
+ },
810
+ {
811
+ "epoch": 0.4944213520017502,
812
+ "grad_norm": 1.3354873657226562,
813
+ "learning_rate": 4.406986624460979e-05,
814
+ "loss": 1.147,
815
+ "step": 1130
816
+ },
817
+ {
818
+ "epoch": 0.4987967621964559,
819
+ "grad_norm": 1.5693355798721313,
820
+ "learning_rate": 4.395479639707158e-05,
821
+ "loss": 1.0808,
822
+ "step": 1140
823
+ },
824
+ {
825
+ "epoch": 0.5031721723911616,
826
+ "grad_norm": 1.5598881244659424,
827
+ "learning_rate": 4.3838774153567195e-05,
828
+ "loss": 1.1247,
829
+ "step": 1150
830
+ },
831
+ {
832
+ "epoch": 0.5075475825858674,
833
+ "grad_norm": 1.4272862672805786,
834
+ "learning_rate": 4.372180534370908e-05,
835
+ "loss": 1.1122,
836
+ "step": 1160
837
+ },
838
+ {
839
+ "epoch": 0.5119229927805732,
840
+ "grad_norm": 1.5112720727920532,
841
+ "learning_rate": 4.3603895844670495e-05,
842
+ "loss": 1.102,
843
+ "step": 1170
844
+ },
845
+ {
846
+ "epoch": 0.516298402975279,
847
+ "grad_norm": 1.589198350906372,
848
+ "learning_rate": 4.3485051580890236e-05,
849
+ "loss": 1.1435,
850
+ "step": 1180
851
+ },
852
+ {
853
+ "epoch": 0.5206738131699847,
854
+ "grad_norm": 1.4863295555114746,
855
+ "learning_rate": 4.336527852377497e-05,
856
+ "loss": 1.1374,
857
+ "step": 1190
858
+ },
859
+ {
860
+ "epoch": 0.5250492233646904,
861
+ "grad_norm": 1.4931763410568237,
862
+ "learning_rate": 4.324458269139916e-05,
863
+ "loss": 1.111,
864
+ "step": 1200
865
+ },
866
+ {
867
+ "epoch": 0.5294246335593962,
868
+ "grad_norm": 1.5186004638671875,
869
+ "learning_rate": 4.3122970148202744e-05,
870
+ "loss": 1.1213,
871
+ "step": 1210
872
+ },
873
+ {
874
+ "epoch": 0.533800043754102,
875
+ "grad_norm": 1.4999425411224365,
876
+ "learning_rate": 4.300044700468635e-05,
877
+ "loss": 1.1388,
878
+ "step": 1220
879
+ },
880
+ {
881
+ "epoch": 0.5381754539488077,
882
+ "grad_norm": 1.5555874109268188,
883
+ "learning_rate": 4.2877019417104334e-05,
884
+ "loss": 1.1028,
885
+ "step": 1230
886
+ },
887
+ {
888
+ "epoch": 0.5425508641435135,
889
+ "grad_norm": 1.4953700304031372,
890
+ "learning_rate": 4.27526935871554e-05,
891
+ "loss": 1.1342,
892
+ "step": 1240
893
+ },
894
+ {
895
+ "epoch": 0.5469262743382192,
896
+ "grad_norm": 1.4581255912780762,
897
+ "learning_rate": 4.262747576167106e-05,
898
+ "loss": 1.0921,
899
+ "step": 1250
900
+ },
901
+ {
902
+ "epoch": 0.5513016845329249,
903
+ "grad_norm": 1.552866816520691,
904
+ "learning_rate": 4.250137223230165e-05,
905
+ "loss": 1.1089,
906
+ "step": 1260
907
+ },
908
+ {
909
+ "epoch": 0.5556770947276307,
910
+ "grad_norm": 1.5412286520004272,
911
+ "learning_rate": 4.2374389335200335e-05,
912
+ "loss": 1.1261,
913
+ "step": 1270
914
+ },
915
+ {
916
+ "epoch": 0.5600525049223365,
917
+ "grad_norm": 1.64509117603302,
918
+ "learning_rate": 4.224653345070466e-05,
919
+ "loss": 1.0668,
920
+ "step": 1280
921
+ },
922
+ {
923
+ "epoch": 0.5644279151170423,
924
+ "grad_norm": 1.4940526485443115,
925
+ "learning_rate": 4.211781100301596e-05,
926
+ "loss": 1.1372,
927
+ "step": 1290
928
+ },
929
+ {
930
+ "epoch": 0.5688033253117479,
931
+ "grad_norm": 1.4879716634750366,
932
+ "learning_rate": 4.198822845987661e-05,
933
+ "loss": 1.1166,
934
+ "step": 1300
935
+ },
936
+ {
937
+ "epoch": 0.5731787355064537,
938
+ "grad_norm": 1.5581066608428955,
939
+ "learning_rate": 4.185779233224506e-05,
940
+ "loss": 1.0663,
941
+ "step": 1310
942
+ },
943
+ {
944
+ "epoch": 0.5775541457011595,
945
+ "grad_norm": 1.5502949953079224,
946
+ "learning_rate": 4.172650917396863e-05,
947
+ "loss": 1.165,
948
+ "step": 1320
949
+ },
950
+ {
951
+ "epoch": 0.5819295558958653,
952
+ "grad_norm": 1.4957443475723267,
953
+ "learning_rate": 4.1594385581454245e-05,
954
+ "loss": 1.1723,
955
+ "step": 1330
956
+ },
957
+ {
958
+ "epoch": 0.586304966090571,
959
+ "grad_norm": 1.4180186986923218,
960
+ "learning_rate": 4.146142819333702e-05,
961
+ "loss": 1.1181,
962
+ "step": 1340
963
+ },
964
+ {
965
+ "epoch": 0.5906803762852767,
966
+ "grad_norm": 1.5630731582641602,
967
+ "learning_rate": 4.132764369014662e-05,
968
+ "loss": 1.1731,
969
+ "step": 1350
970
+ },
971
+ {
972
+ "epoch": 0.5950557864799825,
973
+ "grad_norm": 1.5089911222457886,
974
+ "learning_rate": 4.119303879397169e-05,
975
+ "loss": 1.1199,
976
+ "step": 1360
977
+ },
978
+ {
979
+ "epoch": 0.5994311966746882,
980
+ "grad_norm": 1.4724007844924927,
981
+ "learning_rate": 4.1057620268122004e-05,
982
+ "loss": 1.1108,
983
+ "step": 1370
984
+ },
985
+ {
986
+ "epoch": 0.603806606869394,
987
+ "grad_norm": 1.6644493341445923,
988
+ "learning_rate": 4.092139491678873e-05,
989
+ "loss": 1.0948,
990
+ "step": 1380
991
+ },
992
+ {
993
+ "epoch": 0.6081820170640998,
994
+ "grad_norm": 1.598973035812378,
995
+ "learning_rate": 4.078436958470244e-05,
996
+ "loss": 1.0948,
997
+ "step": 1390
998
+ },
999
+ {
1000
+ "epoch": 0.6125574272588055,
1001
+ "grad_norm": 1.4203752279281616,
1002
+ "learning_rate": 4.064655115678933e-05,
1003
+ "loss": 1.0704,
1004
+ "step": 1400
1005
+ },
1006
+ {
1007
+ "epoch": 0.6169328374535112,
1008
+ "grad_norm": 1.367942214012146,
1009
+ "learning_rate": 4.050794655782515e-05,
1010
+ "loss": 1.0958,
1011
+ "step": 1410
1012
+ },
1013
+ {
1014
+ "epoch": 0.621308247648217,
1015
+ "grad_norm": 1.553614616394043,
1016
+ "learning_rate": 4.036856275208736e-05,
1017
+ "loss": 1.0756,
1018
+ "step": 1420
1019
+ },
1020
+ {
1021
+ "epoch": 0.6256836578429228,
1022
+ "grad_norm": 1.4172255992889404,
1023
+ "learning_rate": 4.022840674300512e-05,
1024
+ "loss": 1.1166,
1025
+ "step": 1430
1026
+ },
1027
+ {
1028
+ "epoch": 0.6300590680376286,
1029
+ "grad_norm": 1.6529884338378906,
1030
+ "learning_rate": 4.0087485572807485e-05,
1031
+ "loss": 1.069,
1032
+ "step": 1440
1033
+ },
1034
+ {
1035
+ "epoch": 0.6344344782323342,
1036
+ "grad_norm": 1.5031507015228271,
1037
+ "learning_rate": 3.994580632216952e-05,
1038
+ "loss": 1.1368,
1039
+ "step": 1450
1040
+ },
1041
+ {
1042
+ "epoch": 0.63880988842704,
1043
+ "grad_norm": 1.6318256855010986,
1044
+ "learning_rate": 3.980337610985651e-05,
1045
+ "loss": 1.1184,
1046
+ "step": 1460
1047
+ },
1048
+ {
1049
+ "epoch": 0.6431852986217458,
1050
+ "grad_norm": 1.5290026664733887,
1051
+ "learning_rate": 3.9660202092366316e-05,
1052
+ "loss": 1.1252,
1053
+ "step": 1470
1054
+ },
1055
+ {
1056
+ "epoch": 0.6475607088164516,
1057
+ "grad_norm": 1.4681955575942993,
1058
+ "learning_rate": 3.951629146356975e-05,
1059
+ "loss": 1.0866,
1060
+ "step": 1480
1061
+ },
1062
+ {
1063
+ "epoch": 0.6519361190111573,
1064
+ "grad_norm": 1.4883171319961548,
1065
+ "learning_rate": 3.937165145434914e-05,
1066
+ "loss": 1.1292,
1067
+ "step": 1490
1068
+ },
1069
+ {
1070
+ "epoch": 0.656311529205863,
1071
+ "grad_norm": 1.5238957405090332,
1072
+ "learning_rate": 3.922628933223502e-05,
1073
+ "loss": 1.1547,
1074
+ "step": 1500
1075
+ },
1076
+ {
1077
+ "epoch": 0.6606869394005688,
1078
+ "grad_norm": 1.5324879884719849,
1079
+ "learning_rate": 3.9080212401040914e-05,
1080
+ "loss": 1.0668,
1081
+ "step": 1510
1082
+ },
1083
+ {
1084
+ "epoch": 0.6650623495952745,
1085
+ "grad_norm": 1.4942597150802612,
1086
+ "learning_rate": 3.8933428000496455e-05,
1087
+ "loss": 1.1394,
1088
+ "step": 1520
1089
+ },
1090
+ {
1091
+ "epoch": 0.6694377597899803,
1092
+ "grad_norm": 1.5268304347991943,
1093
+ "learning_rate": 3.878594350587844e-05,
1094
+ "loss": 1.0647,
1095
+ "step": 1530
1096
+ },
1097
+ {
1098
+ "epoch": 0.6738131699846861,
1099
+ "grad_norm": 1.5157787799835205,
1100
+ "learning_rate": 3.863776632764043e-05,
1101
+ "loss": 1.1521,
1102
+ "step": 1540
1103
+ },
1104
+ {
1105
+ "epoch": 0.6781885801793918,
1106
+ "grad_norm": 1.5063765048980713,
1107
+ "learning_rate": 3.848890391104028e-05,
1108
+ "loss": 1.0954,
1109
+ "step": 1550
1110
+ },
1111
+ {
1112
+ "epoch": 0.6825639903740975,
1113
+ "grad_norm": 1.4812955856323242,
1114
+ "learning_rate": 3.833936373576606e-05,
1115
+ "loss": 1.1054,
1116
+ "step": 1560
1117
+ },
1118
+ {
1119
+ "epoch": 0.6869394005688033,
1120
+ "grad_norm": 1.4586228132247925,
1121
+ "learning_rate": 3.8189153315560324e-05,
1122
+ "loss": 1.1125,
1123
+ "step": 1570
1124
+ },
1125
+ {
1126
+ "epoch": 0.6913148107635091,
1127
+ "grad_norm": 1.3584743738174438,
1128
+ "learning_rate": 3.803828019784248e-05,
1129
+ "loss": 1.103,
1130
+ "step": 1580
1131
+ },
1132
+ {
1133
+ "epoch": 0.6956902209582149,
1134
+ "grad_norm": 1.5196596384048462,
1135
+ "learning_rate": 3.788675196332959e-05,
1136
+ "loss": 1.1642,
1137
+ "step": 1590
1138
+ },
1139
+ {
1140
+ "epoch": 0.7000656311529205,
1141
+ "grad_norm": 1.5605676174163818,
1142
+ "learning_rate": 3.7734576225655504e-05,
1143
+ "loss": 1.1656,
1144
+ "step": 1600
1145
+ },
1146
+ {
1147
+ "epoch": 0.7044410413476263,
1148
+ "grad_norm": 1.4787431955337524,
1149
+ "learning_rate": 3.758176063098829e-05,
1150
+ "loss": 1.0855,
1151
+ "step": 1610
1152
+ },
1153
+ {
1154
+ "epoch": 0.7088164515423321,
1155
+ "grad_norm": 1.4558417797088623,
1156
+ "learning_rate": 3.742831285764602e-05,
1157
+ "loss": 1.0855,
1158
+ "step": 1620
1159
+ },
1160
+ {
1161
+ "epoch": 0.7131918617370379,
1162
+ "grad_norm": 1.552485466003418,
1163
+ "learning_rate": 3.7274240615710986e-05,
1164
+ "loss": 1.0949,
1165
+ "step": 1630
1166
+ },
1167
+ {
1168
+ "epoch": 0.7175672719317436,
1169
+ "grad_norm": 1.5539509057998657,
1170
+ "learning_rate": 3.711955164664235e-05,
1171
+ "loss": 1.1285,
1172
+ "step": 1640
1173
+ },
1174
+ {
1175
+ "epoch": 0.7219426821264494,
1176
+ "grad_norm": 1.4706348180770874,
1177
+ "learning_rate": 3.6964253722887075e-05,
1178
+ "loss": 1.1041,
1179
+ "step": 1650
1180
+ },
1181
+ {
1182
+ "epoch": 0.7263180923211551,
1183
+ "grad_norm": 1.460062861442566,
1184
+ "learning_rate": 3.680835464748949e-05,
1185
+ "loss": 1.0845,
1186
+ "step": 1660
1187
+ },
1188
+ {
1189
+ "epoch": 0.7306935025158608,
1190
+ "grad_norm": 1.4356744289398193,
1191
+ "learning_rate": 3.6651862253699144e-05,
1192
+ "loss": 1.0716,
1193
+ "step": 1670
1194
+ },
1195
+ {
1196
+ "epoch": 0.7350689127105666,
1197
+ "grad_norm": 1.6479544639587402,
1198
+ "learning_rate": 3.649478440457726e-05,
1199
+ "loss": 1.1017,
1200
+ "step": 1680
1201
+ },
1202
+ {
1203
+ "epoch": 0.7394443229052724,
1204
+ "grad_norm": 1.4607200622558594,
1205
+ "learning_rate": 3.633712899260166e-05,
1206
+ "loss": 1.0853,
1207
+ "step": 1690
1208
+ },
1209
+ {
1210
+ "epoch": 0.7438197330999782,
1211
+ "grad_norm": 1.5237467288970947,
1212
+ "learning_rate": 3.617890393927015e-05,
1213
+ "loss": 1.1646,
1214
+ "step": 1700
1215
+ },
1216
+ {
1217
+ "epoch": 0.7481951432946838,
1218
+ "grad_norm": 1.464272379875183,
1219
+ "learning_rate": 3.6020117194702555e-05,
1220
+ "loss": 1.0863,
1221
+ "step": 1710
1222
+ },
1223
+ {
1224
+ "epoch": 0.7525705534893896,
1225
+ "grad_norm": 1.440658688545227,
1226
+ "learning_rate": 3.586077673724124e-05,
1227
+ "loss": 1.128,
1228
+ "step": 1720
1229
+ },
1230
+ {
1231
+ "epoch": 0.7569459636840954,
1232
+ "grad_norm": 1.5667482614517212,
1233
+ "learning_rate": 3.570089057305022e-05,
1234
+ "loss": 1.1441,
1235
+ "step": 1730
1236
+ },
1237
+ {
1238
+ "epoch": 0.7613213738788012,
1239
+ "grad_norm": 1.4171441793441772,
1240
+ "learning_rate": 3.5540466735712906e-05,
1241
+ "loss": 1.1002,
1242
+ "step": 1740
1243
+ },
1244
+ {
1245
+ "epoch": 0.7656967840735069,
1246
+ "grad_norm": 1.412792444229126,
1247
+ "learning_rate": 3.5379513285828433e-05,
1248
+ "loss": 1.0983,
1249
+ "step": 1750
1250
+ },
1251
+ {
1252
+ "epoch": 0.7700721942682126,
1253
+ "grad_norm": 1.468995213508606,
1254
+ "learning_rate": 3.521803831060668e-05,
1255
+ "loss": 1.0736,
1256
+ "step": 1760
1257
+ },
1258
+ {
1259
+ "epoch": 0.7744476044629184,
1260
+ "grad_norm": 1.570688247680664,
1261
+ "learning_rate": 3.505604992346187e-05,
1262
+ "loss": 1.0935,
1263
+ "step": 1770
1264
+ },
1265
+ {
1266
+ "epoch": 0.7788230146576242,
1267
+ "grad_norm": 1.4552085399627686,
1268
+ "learning_rate": 3.489355626360497e-05,
1269
+ "loss": 1.1388,
1270
+ "step": 1780
1271
+ },
1272
+ {
1273
+ "epoch": 0.7831984248523299,
1274
+ "grad_norm": 1.6429483890533447,
1275
+ "learning_rate": 3.473056549563469e-05,
1276
+ "loss": 1.1082,
1277
+ "step": 1790
1278
+ },
1279
+ {
1280
+ "epoch": 0.7875738350470357,
1281
+ "grad_norm": 1.6186859607696533,
1282
+ "learning_rate": 3.456708580912725e-05,
1283
+ "loss": 1.1182,
1284
+ "step": 1800
1285
+ },
1286
+ {
1287
+ "epoch": 0.7919492452417414,
1288
+ "grad_norm": 1.3440533876419067,
1289
+ "learning_rate": 3.44031254182249e-05,
1290
+ "loss": 1.0769,
1291
+ "step": 1810
1292
+ },
1293
+ {
1294
+ "epoch": 0.7963246554364471,
1295
+ "grad_norm": 1.3511815071105957,
1296
+ "learning_rate": 3.42386925612232e-05,
1297
+ "loss": 1.0761,
1298
+ "step": 1820
1299
+ },
1300
+ {
1301
+ "epoch": 0.8007000656311529,
1302
+ "grad_norm": 1.4499377012252808,
1303
+ "learning_rate": 3.407379550015707e-05,
1304
+ "loss": 1.1344,
1305
+ "step": 1830
1306
+ },
1307
+ {
1308
+ "epoch": 0.8050754758258587,
1309
+ "grad_norm": 1.4759228229522705,
1310
+ "learning_rate": 3.390844252038565e-05,
1311
+ "loss": 1.0874,
1312
+ "step": 1840
1313
+ },
1314
+ {
1315
+ "epoch": 0.8094508860205645,
1316
+ "grad_norm": 1.4827808141708374,
1317
+ "learning_rate": 3.3742641930176045e-05,
1318
+ "loss": 1.0313,
1319
+ "step": 1850
1320
+ },
1321
+ {
1322
+ "epoch": 0.8138262962152701,
1323
+ "grad_norm": 1.6069589853286743,
1324
+ "learning_rate": 3.3576402060285786e-05,
1325
+ "loss": 1.1089,
1326
+ "step": 1860
1327
+ },
1328
+ {
1329
+ "epoch": 0.8182017064099759,
1330
+ "grad_norm": 1.4358799457550049,
1331
+ "learning_rate": 3.3409731263544345e-05,
1332
+ "loss": 1.0682,
1333
+ "step": 1870
1334
+ },
1335
+ {
1336
+ "epoch": 0.8225771166046817,
1337
+ "grad_norm": 1.4865995645523071,
1338
+ "learning_rate": 3.324263791443333e-05,
1339
+ "loss": 1.0924,
1340
+ "step": 1880
1341
+ },
1342
+ {
1343
+ "epoch": 0.8269525267993875,
1344
+ "grad_norm": 1.4410614967346191,
1345
+ "learning_rate": 3.307513040866584e-05,
1346
+ "loss": 1.0754,
1347
+ "step": 1890
1348
+ },
1349
+ {
1350
+ "epoch": 0.8313279369940932,
1351
+ "grad_norm": 1.3776915073394775,
1352
+ "learning_rate": 3.290721716276448e-05,
1353
+ "loss": 1.097,
1354
+ "step": 1900
1355
+ },
1356
+ {
1357
+ "epoch": 0.8357033471887989,
1358
+ "grad_norm": 1.5188299417495728,
1359
+ "learning_rate": 3.273890661363855e-05,
1360
+ "loss": 1.1616,
1361
+ "step": 1910
1362
+ },
1363
+ {
1364
+ "epoch": 0.8400787573835047,
1365
+ "grad_norm": 1.5575170516967773,
1366
+ "learning_rate": 3.257020721816013e-05,
1367
+ "loss": 1.1246,
1368
+ "step": 1920
1369
+ },
1370
+ {
1371
+ "epoch": 0.8444541675782105,
1372
+ "grad_norm": 1.5193071365356445,
1373
+ "learning_rate": 3.240112745273911e-05,
1374
+ "loss": 1.1162,
1375
+ "step": 1930
1376
+ },
1377
+ {
1378
+ "epoch": 0.8488295777729162,
1379
+ "grad_norm": 1.451002836227417,
1380
+ "learning_rate": 3.223167581289729e-05,
1381
+ "loss": 1.1106,
1382
+ "step": 1940
1383
+ },
1384
+ {
1385
+ "epoch": 0.853204987967622,
1386
+ "grad_norm": 1.54093599319458,
1387
+ "learning_rate": 3.206186081284161e-05,
1388
+ "loss": 1.071,
1389
+ "step": 1950
1390
+ },
1391
+ {
1392
+ "epoch": 0.8575803981623277,
1393
+ "grad_norm": 1.5598371028900146,
1394
+ "learning_rate": 3.1891690985036215e-05,
1395
+ "loss": 1.0986,
1396
+ "step": 1960
1397
+ },
1398
+ {
1399
+ "epoch": 0.8619558083570334,
1400
+ "grad_norm": 1.4229456186294556,
1401
+ "learning_rate": 3.1721174879773826e-05,
1402
+ "loss": 1.0839,
1403
+ "step": 1970
1404
+ },
1405
+ {
1406
+ "epoch": 0.8663312185517392,
1407
+ "grad_norm": 1.5579663515090942,
1408
+ "learning_rate": 3.1550321064746086e-05,
1409
+ "loss": 1.0854,
1410
+ "step": 1980
1411
+ },
1412
+ {
1413
+ "epoch": 0.870706628746445,
1414
+ "grad_norm": 1.4583122730255127,
1415
+ "learning_rate": 3.1379138124613105e-05,
1416
+ "loss": 1.0916,
1417
+ "step": 1990
1418
+ },
1419
+ {
1420
+ "epoch": 0.8750820389411508,
1421
+ "grad_norm": 1.577874779701233,
1422
+ "learning_rate": 3.120763466057206e-05,
1423
+ "loss": 1.061,
1424
+ "step": 2000
1425
+ },
1426
+ {
1427
+ "epoch": 0.8794574491358564,
1428
+ "grad_norm": 1.5133827924728394,
1429
+ "learning_rate": 3.10358192899251e-05,
1430
+ "loss": 1.1227,
1431
+ "step": 2010
1432
+ },
1433
+ {
1434
+ "epoch": 0.8838328593305622,
1435
+ "grad_norm": 1.4519861936569214,
1436
+ "learning_rate": 3.086370064564629e-05,
1437
+ "loss": 1.086,
1438
+ "step": 2020
1439
+ },
1440
+ {
1441
+ "epoch": 0.888208269525268,
1442
+ "grad_norm": 1.6563777923583984,
1443
+ "learning_rate": 3.069128737594789e-05,
1444
+ "loss": 1.1102,
1445
+ "step": 2030
1446
+ },
1447
+ {
1448
+ "epoch": 0.8925836797199738,
1449
+ "grad_norm": 1.3476353883743286,
1450
+ "learning_rate": 3.051858814384581e-05,
1451
+ "loss": 1.0804,
1452
+ "step": 2040
1453
+ },
1454
+ {
1455
+ "epoch": 0.8969590899146795,
1456
+ "grad_norm": 1.501389503479004,
1457
+ "learning_rate": 3.0345611626724285e-05,
1458
+ "loss": 1.1101,
1459
+ "step": 2050
1460
+ },
1461
+ {
1462
+ "epoch": 0.9013345001093852,
1463
+ "grad_norm": 1.483244776725769,
1464
+ "learning_rate": 3.0172366515899982e-05,
1465
+ "loss": 1.0964,
1466
+ "step": 2060
1467
+ },
1468
+ {
1469
+ "epoch": 0.905709910304091,
1470
+ "grad_norm": 1.4610023498535156,
1471
+ "learning_rate": 2.9998861516185173e-05,
1472
+ "loss": 1.0953,
1473
+ "step": 2070
1474
+ },
1475
+ {
1476
+ "epoch": 0.9100853204987968,
1477
+ "grad_norm": 1.4304044246673584,
1478
+ "learning_rate": 2.982510534545043e-05,
1479
+ "loss": 1.0687,
1480
+ "step": 2080
1481
+ },
1482
+ {
1483
+ "epoch": 0.9144607306935025,
1484
+ "grad_norm": 1.461287498474121,
1485
+ "learning_rate": 2.9651106734186618e-05,
1486
+ "loss": 1.0875,
1487
+ "step": 2090
1488
+ },
1489
+ {
1490
+ "epoch": 0.9188361408882083,
1491
+ "grad_norm": 1.484709620475769,
1492
+ "learning_rate": 2.9476874425066105e-05,
1493
+ "loss": 1.1122,
1494
+ "step": 2100
1495
+ },
1496
+ {
1497
+ "epoch": 0.923211551082914,
1498
+ "grad_norm": 1.4673666954040527,
1499
+ "learning_rate": 2.9302417172503622e-05,
1500
+ "loss": 1.1506,
1501
+ "step": 2110
1502
+ },
1503
+ {
1504
+ "epoch": 0.9275869612776197,
1505
+ "grad_norm": 1.456113576889038,
1506
+ "learning_rate": 2.9127743742216303e-05,
1507
+ "loss": 1.0851,
1508
+ "step": 2120
1509
+ },
1510
+ {
1511
+ "epoch": 0.9319623714723255,
1512
+ "grad_norm": 1.524404525756836,
1513
+ "learning_rate": 2.8952862910783267e-05,
1514
+ "loss": 1.1047,
1515
+ "step": 2130
1516
+ },
1517
+ {
1518
+ "epoch": 0.9363377816670313,
1519
+ "grad_norm": 1.3824920654296875,
1520
+ "learning_rate": 2.877778346520466e-05,
1521
+ "loss": 1.069,
1522
+ "step": 2140
1523
+ },
1524
+ {
1525
+ "epoch": 0.9407131918617371,
1526
+ "grad_norm": 1.3911488056182861,
1527
+ "learning_rate": 2.860251420246009e-05,
1528
+ "loss": 1.1128,
1529
+ "step": 2150
1530
+ },
1531
+ {
1532
+ "epoch": 0.9450886020564427,
1533
+ "grad_norm": 1.6120619773864746,
1534
+ "learning_rate": 2.842706392906669e-05,
1535
+ "loss": 1.1468,
1536
+ "step": 2160
1537
+ },
1538
+ {
1539
+ "epoch": 0.9494640122511485,
1540
+ "grad_norm": 1.4727811813354492,
1541
+ "learning_rate": 2.825144146063654e-05,
1542
+ "loss": 1.1405,
1543
+ "step": 2170
1544
+ },
1545
+ {
1546
+ "epoch": 0.9538394224458543,
1547
+ "grad_norm": 1.4946926832199097,
1548
+ "learning_rate": 2.8075655621433826e-05,
1549
+ "loss": 1.0887,
1550
+ "step": 2180
1551
+ },
1552
+ {
1553
+ "epoch": 0.9582148326405601,
1554
+ "grad_norm": 1.575395107269287,
1555
+ "learning_rate": 2.7899715243931375e-05,
1556
+ "loss": 1.077,
1557
+ "step": 2190
1558
+ },
1559
+ {
1560
+ "epoch": 0.9625902428352658,
1561
+ "grad_norm": 1.483463168144226,
1562
+ "learning_rate": 2.7723629168366883e-05,
1563
+ "loss": 1.1137,
1564
+ "step": 2200
1565
+ },
1566
+ {
1567
+ "epoch": 0.9669656530299715,
1568
+ "grad_norm": 1.5409109592437744,
1569
+ "learning_rate": 2.754740624229875e-05,
1570
+ "loss": 1.0749,
1571
+ "step": 2210
1572
+ },
1573
+ {
1574
+ "epoch": 0.9713410632246773,
1575
+ "grad_norm": 1.4951428174972534,
1576
+ "learning_rate": 2.737105532016152e-05,
1577
+ "loss": 1.0779,
1578
+ "step": 2220
1579
+ },
1580
+ {
1581
+ "epoch": 0.9757164734193831,
1582
+ "grad_norm": 1.6109696626663208,
1583
+ "learning_rate": 2.719458526282099e-05,
1584
+ "loss": 1.1006,
1585
+ "step": 2230
1586
+ },
1587
+ {
1588
+ "epoch": 0.9800918836140888,
1589
+ "grad_norm": 1.4150285720825195,
1590
+ "learning_rate": 2.7018004937128937e-05,
1591
+ "loss": 1.0498,
1592
+ "step": 2240
1593
+ },
1594
+ {
1595
+ "epoch": 0.9844672938087946,
1596
+ "grad_norm": 1.5306379795074463,
1597
+ "learning_rate": 2.6841323215477714e-05,
1598
+ "loss": 1.0943,
1599
+ "step": 2250
1600
+ },
1601
+ {
1602
+ "epoch": 0.9888427040035004,
1603
+ "grad_norm": 1.3424153327941895,
1604
+ "learning_rate": 2.6664548975354332e-05,
1605
+ "loss": 1.079,
1606
+ "step": 2260
1607
+ },
1608
+ {
1609
+ "epoch": 0.993218114198206,
1610
+ "grad_norm": 1.4553660154342651,
1611
+ "learning_rate": 2.6487691098894447e-05,
1612
+ "loss": 1.0663,
1613
+ "step": 2270
1614
+ },
1615
+ {
1616
+ "epoch": 0.9975935243929118,
1617
+ "grad_norm": 1.5150882005691528,
1618
+ "learning_rate": 2.6310758472436103e-05,
1619
+ "loss": 1.0449,
1620
+ "step": 2280
1621
+ }
1622
+ ],
1623
+ "logging_steps": 10,
1624
+ "max_steps": 4570,
1625
+ "num_input_tokens_seen": 0,
1626
+ "num_train_epochs": 2,
1627
+ "save_steps": 500.0,
1628
+ "stateful_callbacks": {
1629
+ "TrainerControl": {
1630
+ "args": {
1631
+ "should_epoch_stop": false,
1632
+ "should_evaluate": false,
1633
+ "should_log": false,
1634
+ "should_save": true,
1635
+ "should_training_stop": false
1636
+ },
1637
+ "attributes": {}
1638
+ }
1639
+ },
1640
+ "total_flos": 9.493158922149888e+17,
1641
+ "train_batch_size": 4,
1642
+ "trial_name": null,
1643
+ "trial_params": null
1644
+ }
checkpoint-2286/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c85d66f583d263a717810314b9c2c8bcc0a0f818cd568e1c7709ffaa2e23b63
3
+ size 6353
checkpoint-4570/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 32.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.48.1",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
checkpoint-4570/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.48.1"
9
+ }
checkpoint-4570/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f296664d96f41adb9939ca047de15c4b74e6100ae2a470975179b31c72ffc2
3
+ size 4980379440
checkpoint-4570/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8e1d82bf5bb601c40dd0ca17abd29f3d599d0bbb5e70c3de2945bbf9c8238c
3
+ size 1144267912
checkpoint-4570/model.safetensors.index.json ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6124593152
4
+ },
5
+ "weight_map": {
6
+ "lm_head.A": "model-00002-of-00002.safetensors",
7
+ "lm_head.B": "model-00002-of-00002.safetensors",
8
+ "lm_head.scales": "model-00002-of-00002.safetensors",
9
+ "lm_head.weight": "model-00002-of-00002.safetensors",
10
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.down_proj.A": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.down_proj.B": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.mlp.up_proj.A": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.mlp.up_proj.B": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
30
+ "model.layers.0.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
31
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
32
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.0.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
34
+ "model.layers.0.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
35
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
36
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.0.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
38
+ "model.layers.0.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
39
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
40
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.down_proj.A": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.down_proj.B": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.mlp.up_proj.A": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.mlp.up_proj.B": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
53
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.1.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
56
+ "model.layers.1.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
57
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
58
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.1.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
60
+ "model.layers.1.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
61
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
62
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.1.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
64
+ "model.layers.1.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
65
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
66
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.1.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
68
+ "model.layers.1.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
69
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
70
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.10.mlp.down_proj.A": "model-00001-of-00002.safetensors",
73
+ "model.layers.10.mlp.down_proj.B": "model-00001-of-00002.safetensors",
74
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
75
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.10.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
77
+ "model.layers.10.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
78
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
79
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.10.mlp.up_proj.A": "model-00001-of-00002.safetensors",
81
+ "model.layers.10.mlp.up_proj.B": "model-00001-of-00002.safetensors",
82
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
83
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.10.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
86
+ "model.layers.10.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
87
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
88
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.10.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
90
+ "model.layers.10.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
91
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
92
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.10.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
94
+ "model.layers.10.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
95
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
96
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.10.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
98
+ "model.layers.10.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
99
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
100
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.11.mlp.down_proj.A": "model-00001-of-00002.safetensors",
103
+ "model.layers.11.mlp.down_proj.B": "model-00001-of-00002.safetensors",
104
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
105
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.11.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
107
+ "model.layers.11.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
108
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
109
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.11.mlp.up_proj.A": "model-00001-of-00002.safetensors",
111
+ "model.layers.11.mlp.up_proj.B": "model-00001-of-00002.safetensors",
112
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
113
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.11.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
116
+ "model.layers.11.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
117
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
118
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.11.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
120
+ "model.layers.11.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
121
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
122
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.11.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
124
+ "model.layers.11.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
125
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
126
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.11.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
128
+ "model.layers.11.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
129
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
130
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.12.mlp.down_proj.A": "model-00001-of-00002.safetensors",
133
+ "model.layers.12.mlp.down_proj.B": "model-00001-of-00002.safetensors",
134
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
135
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.12.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
137
+ "model.layers.12.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
138
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
139
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.12.mlp.up_proj.A": "model-00001-of-00002.safetensors",
141
+ "model.layers.12.mlp.up_proj.B": "model-00001-of-00002.safetensors",
142
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
143
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.12.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
146
+ "model.layers.12.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
147
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
148
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.12.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
150
+ "model.layers.12.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
151
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
152
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.12.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
154
+ "model.layers.12.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
155
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
156
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.12.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
158
+ "model.layers.12.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
159
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
160
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.13.mlp.down_proj.A": "model-00001-of-00002.safetensors",
163
+ "model.layers.13.mlp.down_proj.B": "model-00001-of-00002.safetensors",
164
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
165
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.13.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
167
+ "model.layers.13.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
168
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
169
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.13.mlp.up_proj.A": "model-00001-of-00002.safetensors",
171
+ "model.layers.13.mlp.up_proj.B": "model-00001-of-00002.safetensors",
172
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
173
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.13.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
176
+ "model.layers.13.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
177
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
178
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.13.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
180
+ "model.layers.13.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
181
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
182
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.13.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
184
+ "model.layers.13.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
185
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
186
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.13.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
188
+ "model.layers.13.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
189
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
190
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.14.mlp.down_proj.A": "model-00001-of-00002.safetensors",
193
+ "model.layers.14.mlp.down_proj.B": "model-00001-of-00002.safetensors",
194
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
195
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.14.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
197
+ "model.layers.14.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
198
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
199
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.14.mlp.up_proj.A": "model-00001-of-00002.safetensors",
201
+ "model.layers.14.mlp.up_proj.B": "model-00001-of-00002.safetensors",
202
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
203
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.14.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
206
+ "model.layers.14.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
207
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
208
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.14.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
210
+ "model.layers.14.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
211
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
212
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.14.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
214
+ "model.layers.14.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
215
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
216
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.14.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
218
+ "model.layers.14.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
219
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
220
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.15.mlp.down_proj.A": "model-00002-of-00002.safetensors",
223
+ "model.layers.15.mlp.down_proj.B": "model-00002-of-00002.safetensors",
224
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
225
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.15.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
227
+ "model.layers.15.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
228
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
229
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.15.mlp.up_proj.A": "model-00001-of-00002.safetensors",
231
+ "model.layers.15.mlp.up_proj.B": "model-00001-of-00002.safetensors",
232
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
233
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.15.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
236
+ "model.layers.15.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
237
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
238
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.15.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
240
+ "model.layers.15.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
241
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
242
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.15.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
244
+ "model.layers.15.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
245
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
246
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.15.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
248
+ "model.layers.15.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
249
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
250
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.2.mlp.down_proj.A": "model-00001-of-00002.safetensors",
253
+ "model.layers.2.mlp.down_proj.B": "model-00001-of-00002.safetensors",
254
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
255
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.2.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
257
+ "model.layers.2.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
258
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
259
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.2.mlp.up_proj.A": "model-00001-of-00002.safetensors",
261
+ "model.layers.2.mlp.up_proj.B": "model-00001-of-00002.safetensors",
262
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
263
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.2.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
266
+ "model.layers.2.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
267
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
268
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.2.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
270
+ "model.layers.2.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
271
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
272
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.2.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
274
+ "model.layers.2.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
275
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
276
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.2.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
278
+ "model.layers.2.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
279
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
280
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.3.mlp.down_proj.A": "model-00001-of-00002.safetensors",
283
+ "model.layers.3.mlp.down_proj.B": "model-00001-of-00002.safetensors",
284
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.mlp.up_proj.A": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.mlp.up_proj.B": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
296
+ "model.layers.3.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
297
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
298
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.3.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
300
+ "model.layers.3.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
301
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
302
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.3.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
304
+ "model.layers.3.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
305
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
306
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.3.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
308
+ "model.layers.3.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
309
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
310
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.4.mlp.down_proj.A": "model-00001-of-00002.safetensors",
313
+ "model.layers.4.mlp.down_proj.B": "model-00001-of-00002.safetensors",
314
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.4.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
317
+ "model.layers.4.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
318
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
319
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.4.mlp.up_proj.A": "model-00001-of-00002.safetensors",
321
+ "model.layers.4.mlp.up_proj.B": "model-00001-of-00002.safetensors",
322
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
323
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.4.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
326
+ "model.layers.4.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
327
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
328
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.4.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
330
+ "model.layers.4.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
331
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
332
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.4.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
334
+ "model.layers.4.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
335
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
336
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.4.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
338
+ "model.layers.4.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
339
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.5.mlp.down_proj.A": "model-00001-of-00002.safetensors",
343
+ "model.layers.5.mlp.down_proj.B": "model-00001-of-00002.safetensors",
344
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
345
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.5.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
347
+ "model.layers.5.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
348
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
349
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.mlp.up_proj.A": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.up_proj.B": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.5.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
360
+ "model.layers.5.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
361
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
362
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.5.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
364
+ "model.layers.5.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
365
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
366
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.5.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
368
+ "model.layers.5.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
369
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
370
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.6.mlp.down_proj.A": "model-00001-of-00002.safetensors",
373
+ "model.layers.6.mlp.down_proj.B": "model-00001-of-00002.safetensors",
374
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
375
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.6.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
377
+ "model.layers.6.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
378
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
379
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.6.mlp.up_proj.A": "model-00001-of-00002.safetensors",
381
+ "model.layers.6.mlp.up_proj.B": "model-00001-of-00002.safetensors",
382
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
383
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.6.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
386
+ "model.layers.6.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
387
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
388
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.6.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
390
+ "model.layers.6.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
391
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.7.mlp.down_proj.A": "model-00001-of-00002.safetensors",
403
+ "model.layers.7.mlp.down_proj.B": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.mlp.up_proj.A": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.mlp.up_proj.B": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
416
+ "model.layers.7.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.7.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
428
+ "model.layers.7.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
429
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
430
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.mlp.down_proj.A": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.down_proj.B": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.mlp.up_proj.A": "model-00001-of-00002.safetensors",
441
+ "model.layers.8.mlp.up_proj.B": "model-00001-of-00002.safetensors",
442
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
443
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.8.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
446
+ "model.layers.8.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
447
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
448
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.8.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
450
+ "model.layers.8.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
451
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
452
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.8.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
454
+ "model.layers.8.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
455
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
456
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.8.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
458
+ "model.layers.8.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
459
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
460
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
462
+ "model.layers.9.mlp.down_proj.A": "model-00001-of-00002.safetensors",
463
+ "model.layers.9.mlp.down_proj.B": "model-00001-of-00002.safetensors",
464
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
465
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.9.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
467
+ "model.layers.9.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
468
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
469
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.9.mlp.up_proj.A": "model-00001-of-00002.safetensors",
471
+ "model.layers.9.mlp.up_proj.B": "model-00001-of-00002.safetensors",
472
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
473
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
474
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.9.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
476
+ "model.layers.9.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
477
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
478
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.9.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
480
+ "model.layers.9.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
481
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
482
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
483
+ "model.layers.9.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
484
+ "model.layers.9.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
485
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
486
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.layers.9.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
488
+ "model.layers.9.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
489
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
490
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.norm.weight": "model-00002-of-00002.safetensors"
492
+ }
493
+ }
checkpoint-4570/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f1e51b761dcb31c8b4176f157a45fe0328d0b1089107482681d827101a8a15
3
+ size 107615371
checkpoint-4570/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2534e434cd5abbb8f7668d3eab0549db0ef95d6a797a3efa86b712e8e32266a7
3
+ size 14645
checkpoint-4570/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f7aec684da28e981a5da3b1d95cc415e11cf523b59b047e5ef6ee887b24633
3
+ size 1465
checkpoint-4570/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
checkpoint-4570/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-4570/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "\n {{- bos_token }}\n {%- for message in messages %}\n {%- if message['role'] == 'assistant' %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '\n' }}\n {%- generation %}\n {{- message['content'] + '<|eot_id|>' }}\n {%- endgeneration %}\n {{- '\n' }}\n {%- else %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '\n' + message['content'] + '<|eot_id|>' + '\n' }}\n {%- endif %}\n {%- endfor %}\n {%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n' }}\n {%- endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-4570/trainer_state.json ADDED
@@ -0,0 +1,3247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9993436884707942,
5
+ "eval_steps": 500,
6
+ "global_step": 4570,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "eval_loss": 2.3424127101898193,
14
+ "eval_runtime": 1.1989,
15
+ "eval_samples_per_second": 16.682,
16
+ "eval_steps_per_second": 4.171,
17
+ "step": 0
18
+ },
19
+ {
20
+ "epoch": 0.0004375410194705754,
21
+ "grad_norm": 11.591988563537598,
22
+ "learning_rate": 3.6231884057971015e-07,
23
+ "loss": 1.7217,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.004375410194705754,
28
+ "grad_norm": 7.750391006469727,
29
+ "learning_rate": 3.6231884057971017e-06,
30
+ "loss": 1.6447,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.008750820389411508,
35
+ "grad_norm": 4.005843162536621,
36
+ "learning_rate": 7.246376811594203e-06,
37
+ "loss": 1.5732,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.01312623058411726,
42
+ "grad_norm": 2.8733792304992676,
43
+ "learning_rate": 1.0869565217391305e-05,
44
+ "loss": 1.4077,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.017501640778823015,
49
+ "grad_norm": 2.6543965339660645,
50
+ "learning_rate": 1.4492753623188407e-05,
51
+ "loss": 1.3353,
52
+ "step": 40
53
+ },
54
+ {
55
+ "epoch": 0.021877050973528767,
56
+ "grad_norm": 2.3828840255737305,
57
+ "learning_rate": 1.8115942028985507e-05,
58
+ "loss": 1.2485,
59
+ "step": 50
60
+ },
61
+ {
62
+ "epoch": 0.02625246116823452,
63
+ "grad_norm": 2.1744871139526367,
64
+ "learning_rate": 2.173913043478261e-05,
65
+ "loss": 1.2685,
66
+ "step": 60
67
+ },
68
+ {
69
+ "epoch": 0.030627871362940276,
70
+ "grad_norm": 2.292287588119507,
71
+ "learning_rate": 2.5362318840579714e-05,
72
+ "loss": 1.1884,
73
+ "step": 70
74
+ },
75
+ {
76
+ "epoch": 0.03500328155764603,
77
+ "grad_norm": 2.3060696125030518,
78
+ "learning_rate": 2.8985507246376814e-05,
79
+ "loss": 1.2874,
80
+ "step": 80
81
+ },
82
+ {
83
+ "epoch": 0.039378691752351785,
84
+ "grad_norm": 2.0335893630981445,
85
+ "learning_rate": 3.260869565217392e-05,
86
+ "loss": 1.2227,
87
+ "step": 90
88
+ },
89
+ {
90
+ "epoch": 0.04375410194705753,
91
+ "grad_norm": 2.4152441024780273,
92
+ "learning_rate": 3.6231884057971014e-05,
93
+ "loss": 1.192,
94
+ "step": 100
95
+ },
96
+ {
97
+ "epoch": 0.04812951214176329,
98
+ "grad_norm": 2.216953992843628,
99
+ "learning_rate": 3.985507246376812e-05,
100
+ "loss": 1.1883,
101
+ "step": 110
102
+ },
103
+ {
104
+ "epoch": 0.05250492233646904,
105
+ "grad_norm": 2.3724114894866943,
106
+ "learning_rate": 4.347826086956522e-05,
107
+ "loss": 1.1811,
108
+ "step": 120
109
+ },
110
+ {
111
+ "epoch": 0.0568803325311748,
112
+ "grad_norm": 2.238722801208496,
113
+ "learning_rate": 4.710144927536232e-05,
114
+ "loss": 1.168,
115
+ "step": 130
116
+ },
117
+ {
118
+ "epoch": 0.06125574272588055,
119
+ "grad_norm": 2.2097883224487305,
120
+ "learning_rate": 4.999997487707664e-05,
121
+ "loss": 1.1848,
122
+ "step": 140
123
+ },
124
+ {
125
+ "epoch": 0.0656311529205863,
126
+ "grad_norm": 2.2063302993774414,
127
+ "learning_rate": 4.999909558006067e-05,
128
+ "loss": 1.2155,
129
+ "step": 150
130
+ },
131
+ {
132
+ "epoch": 0.07000656311529206,
133
+ "grad_norm": 1.8397595882415771,
134
+ "learning_rate": 4.9996960187368994e-05,
135
+ "loss": 1.1507,
136
+ "step": 160
137
+ },
138
+ {
139
+ "epoch": 0.07438197330999781,
140
+ "grad_norm": 1.8552066087722778,
141
+ "learning_rate": 4.9993568806295786e-05,
142
+ "loss": 1.2109,
143
+ "step": 170
144
+ },
145
+ {
146
+ "epoch": 0.07875738350470357,
147
+ "grad_norm": 2.173321485519409,
148
+ "learning_rate": 4.998892160724318e-05,
149
+ "loss": 1.1784,
150
+ "step": 180
151
+ },
152
+ {
153
+ "epoch": 0.08313279369940932,
154
+ "grad_norm": 2.0949854850769043,
155
+ "learning_rate": 4.998301882371268e-05,
156
+ "loss": 1.1967,
157
+ "step": 190
158
+ },
159
+ {
160
+ "epoch": 0.08750820389411507,
161
+ "grad_norm": 1.8619498014450073,
162
+ "learning_rate": 4.997586075229346e-05,
163
+ "loss": 1.1761,
164
+ "step": 200
165
+ },
166
+ {
167
+ "epoch": 0.09188361408882083,
168
+ "grad_norm": 1.9095852375030518,
169
+ "learning_rate": 4.996744775264743e-05,
170
+ "loss": 1.15,
171
+ "step": 210
172
+ },
173
+ {
174
+ "epoch": 0.09625902428352658,
175
+ "grad_norm": 2.0714683532714844,
176
+ "learning_rate": 4.995778024749118e-05,
177
+ "loss": 1.1477,
178
+ "step": 220
179
+ },
180
+ {
181
+ "epoch": 0.10063443447823234,
182
+ "grad_norm": 1.9555009603500366,
183
+ "learning_rate": 4.9946858722574743e-05,
184
+ "loss": 1.1602,
185
+ "step": 230
186
+ },
187
+ {
188
+ "epoch": 0.10500984467293809,
189
+ "grad_norm": 1.9120110273361206,
190
+ "learning_rate": 4.993468372665718e-05,
191
+ "loss": 1.1516,
192
+ "step": 240
193
+ },
194
+ {
195
+ "epoch": 0.10938525486764385,
196
+ "grad_norm": 1.8210362195968628,
197
+ "learning_rate": 4.9921255871479e-05,
198
+ "loss": 1.1404,
199
+ "step": 250
200
+ },
201
+ {
202
+ "epoch": 0.1137606650623496,
203
+ "grad_norm": 1.8263871669769287,
204
+ "learning_rate": 4.990657583173146e-05,
205
+ "loss": 1.1629,
206
+ "step": 260
207
+ },
208
+ {
209
+ "epoch": 0.11813607525705534,
210
+ "grad_norm": 1.906760811805725,
211
+ "learning_rate": 4.989064434502262e-05,
212
+ "loss": 1.1364,
213
+ "step": 270
214
+ },
215
+ {
216
+ "epoch": 0.1225114854517611,
217
+ "grad_norm": 1.7693920135498047,
218
+ "learning_rate": 4.9873462211840296e-05,
219
+ "loss": 1.1396,
220
+ "step": 280
221
+ },
222
+ {
223
+ "epoch": 0.12688689564646685,
224
+ "grad_norm": 1.8662511110305786,
225
+ "learning_rate": 4.985503029551184e-05,
226
+ "loss": 1.1859,
227
+ "step": 290
228
+ },
229
+ {
230
+ "epoch": 0.1312623058411726,
231
+ "grad_norm": 1.7560139894485474,
232
+ "learning_rate": 4.983534952216079e-05,
233
+ "loss": 1.1419,
234
+ "step": 300
235
+ },
236
+ {
237
+ "epoch": 0.13563771603587838,
238
+ "grad_norm": 1.8666057586669922,
239
+ "learning_rate": 4.981442088066029e-05,
240
+ "loss": 1.1686,
241
+ "step": 310
242
+ },
243
+ {
244
+ "epoch": 0.14001312623058412,
245
+ "grad_norm": 1.7406998872756958,
246
+ "learning_rate": 4.9792245422583406e-05,
247
+ "loss": 1.1275,
248
+ "step": 320
249
+ },
250
+ {
251
+ "epoch": 0.14438853642528987,
252
+ "grad_norm": 1.717785120010376,
253
+ "learning_rate": 4.9768824262150344e-05,
254
+ "loss": 1.1236,
255
+ "step": 330
256
+ },
257
+ {
258
+ "epoch": 0.14876394661999562,
259
+ "grad_norm": 1.7829722166061401,
260
+ "learning_rate": 4.9744158576172406e-05,
261
+ "loss": 1.1297,
262
+ "step": 340
263
+ },
264
+ {
265
+ "epoch": 0.15313935681470137,
266
+ "grad_norm": 1.8614799976348877,
267
+ "learning_rate": 4.971824960399289e-05,
268
+ "loss": 1.2018,
269
+ "step": 350
270
+ },
271
+ {
272
+ "epoch": 0.15751476700940714,
273
+ "grad_norm": 1.9301059246063232,
274
+ "learning_rate": 4.9691098647424806e-05,
275
+ "loss": 1.1491,
276
+ "step": 360
277
+ },
278
+ {
279
+ "epoch": 0.1618901772041129,
280
+ "grad_norm": 1.7714897394180298,
281
+ "learning_rate": 4.9662707070685476e-05,
282
+ "loss": 1.1393,
283
+ "step": 370
284
+ },
285
+ {
286
+ "epoch": 0.16626558739881864,
287
+ "grad_norm": 1.7732449769973755,
288
+ "learning_rate": 4.963307630032797e-05,
289
+ "loss": 1.1029,
290
+ "step": 380
291
+ },
292
+ {
293
+ "epoch": 0.17064099759352439,
294
+ "grad_norm": 1.6674808263778687,
295
+ "learning_rate": 4.960220782516946e-05,
296
+ "loss": 1.1385,
297
+ "step": 390
298
+ },
299
+ {
300
+ "epoch": 0.17501640778823013,
301
+ "grad_norm": 1.8136391639709473,
302
+ "learning_rate": 4.957010319621638e-05,
303
+ "loss": 1.0898,
304
+ "step": 400
305
+ },
306
+ {
307
+ "epoch": 0.1793918179829359,
308
+ "grad_norm": 1.7509042024612427,
309
+ "learning_rate": 4.95367640265865e-05,
310
+ "loss": 1.1914,
311
+ "step": 410
312
+ },
313
+ {
314
+ "epoch": 0.18376722817764166,
315
+ "grad_norm": 1.7148741483688354,
316
+ "learning_rate": 4.950219199142791e-05,
317
+ "loss": 1.1228,
318
+ "step": 420
319
+ },
320
+ {
321
+ "epoch": 0.1881426383723474,
322
+ "grad_norm": 1.8227111101150513,
323
+ "learning_rate": 4.9466388827834795e-05,
324
+ "loss": 1.1556,
325
+ "step": 430
326
+ },
327
+ {
328
+ "epoch": 0.19251804856705315,
329
+ "grad_norm": 1.6873571872711182,
330
+ "learning_rate": 4.9429356334760205e-05,
331
+ "loss": 1.1551,
332
+ "step": 440
333
+ },
334
+ {
335
+ "epoch": 0.19689345876175893,
336
+ "grad_norm": 1.6948832273483276,
337
+ "learning_rate": 4.9391096372925626e-05,
338
+ "loss": 1.1085,
339
+ "step": 450
340
+ },
341
+ {
342
+ "epoch": 0.20126886895646467,
343
+ "grad_norm": 1.7749884128570557,
344
+ "learning_rate": 4.9351610864727504e-05,
345
+ "loss": 1.1421,
346
+ "step": 460
347
+ },
348
+ {
349
+ "epoch": 0.20564427915117042,
350
+ "grad_norm": 1.607061743736267,
351
+ "learning_rate": 4.9310901794140665e-05,
352
+ "loss": 1.155,
353
+ "step": 470
354
+ },
355
+ {
356
+ "epoch": 0.21001968934587617,
357
+ "grad_norm": 1.6496872901916504,
358
+ "learning_rate": 4.92689712066186e-05,
359
+ "loss": 1.1552,
360
+ "step": 480
361
+ },
362
+ {
363
+ "epoch": 0.21439509954058192,
364
+ "grad_norm": 1.5627405643463135,
365
+ "learning_rate": 4.922582120899072e-05,
366
+ "loss": 1.1419,
367
+ "step": 490
368
+ },
369
+ {
370
+ "epoch": 0.2187705097352877,
371
+ "grad_norm": 1.7042529582977295,
372
+ "learning_rate": 4.918145396935648e-05,
373
+ "loss": 1.1652,
374
+ "step": 500
375
+ },
376
+ {
377
+ "epoch": 0.22314591992999344,
378
+ "grad_norm": 1.5909007787704468,
379
+ "learning_rate": 4.913587171697643e-05,
380
+ "loss": 1.1294,
381
+ "step": 510
382
+ },
383
+ {
384
+ "epoch": 0.2275213301246992,
385
+ "grad_norm": 1.7357898950576782,
386
+ "learning_rate": 4.908907674216023e-05,
387
+ "loss": 1.1119,
388
+ "step": 520
389
+ },
390
+ {
391
+ "epoch": 0.23189674031940494,
392
+ "grad_norm": 1.6394789218902588,
393
+ "learning_rate": 4.9041071396151585e-05,
394
+ "loss": 1.1626,
395
+ "step": 530
396
+ },
397
+ {
398
+ "epoch": 0.23627215051411068,
399
+ "grad_norm": 1.5801527500152588,
400
+ "learning_rate": 4.899185809101003e-05,
401
+ "loss": 1.1211,
402
+ "step": 540
403
+ },
404
+ {
405
+ "epoch": 0.24064756070881646,
406
+ "grad_norm": 1.8420217037200928,
407
+ "learning_rate": 4.894143929948982e-05,
408
+ "loss": 1.1103,
409
+ "step": 550
410
+ },
411
+ {
412
+ "epoch": 0.2450229709035222,
413
+ "grad_norm": 1.671028971672058,
414
+ "learning_rate": 4.8889817554915645e-05,
415
+ "loss": 1.1461,
416
+ "step": 560
417
+ },
418
+ {
419
+ "epoch": 0.24939838109822796,
420
+ "grad_norm": 1.6634349822998047,
421
+ "learning_rate": 4.8836995451055344e-05,
422
+ "loss": 1.1562,
423
+ "step": 570
424
+ },
425
+ {
426
+ "epoch": 0.2537737912929337,
427
+ "grad_norm": 1.5025454759597778,
428
+ "learning_rate": 4.878297564198959e-05,
429
+ "loss": 1.0946,
430
+ "step": 580
431
+ },
432
+ {
433
+ "epoch": 0.2581492014876395,
434
+ "grad_norm": 1.7138441801071167,
435
+ "learning_rate": 4.872776084197851e-05,
436
+ "loss": 1.1093,
437
+ "step": 590
438
+ },
439
+ {
440
+ "epoch": 0.2625246116823452,
441
+ "grad_norm": 1.668101191520691,
442
+ "learning_rate": 4.867135382532533e-05,
443
+ "loss": 1.153,
444
+ "step": 600
445
+ },
446
+ {
447
+ "epoch": 0.266900021877051,
448
+ "grad_norm": 1.706669569015503,
449
+ "learning_rate": 4.861375742623697e-05,
450
+ "loss": 1.1281,
451
+ "step": 610
452
+ },
453
+ {
454
+ "epoch": 0.27127543207175675,
455
+ "grad_norm": 2.0017876625061035,
456
+ "learning_rate": 4.855497453868164e-05,
457
+ "loss": 1.1056,
458
+ "step": 620
459
+ },
460
+ {
461
+ "epoch": 0.27565084226646247,
462
+ "grad_norm": 1.611232042312622,
463
+ "learning_rate": 4.849500811624343e-05,
464
+ "loss": 1.1271,
465
+ "step": 630
466
+ },
467
+ {
468
+ "epoch": 0.28002625246116825,
469
+ "grad_norm": 1.463722586631775,
470
+ "learning_rate": 4.8433861171973896e-05,
471
+ "loss": 1.1402,
472
+ "step": 640
473
+ },
474
+ {
475
+ "epoch": 0.28440166265587397,
476
+ "grad_norm": 1.5447578430175781,
477
+ "learning_rate": 4.837153677824067e-05,
478
+ "loss": 1.1493,
479
+ "step": 650
480
+ },
481
+ {
482
+ "epoch": 0.28877707285057974,
483
+ "grad_norm": 1.496686339378357,
484
+ "learning_rate": 4.830803806657311e-05,
485
+ "loss": 1.1333,
486
+ "step": 660
487
+ },
488
+ {
489
+ "epoch": 0.2931524830452855,
490
+ "grad_norm": 1.6186118125915527,
491
+ "learning_rate": 4.8243368227504924e-05,
492
+ "loss": 1.1545,
493
+ "step": 670
494
+ },
495
+ {
496
+ "epoch": 0.29752789323999124,
497
+ "grad_norm": 1.5591745376586914,
498
+ "learning_rate": 4.817753051041387e-05,
499
+ "loss": 1.1189,
500
+ "step": 680
501
+ },
502
+ {
503
+ "epoch": 0.301903303434697,
504
+ "grad_norm": 1.8602070808410645,
505
+ "learning_rate": 4.811052822335849e-05,
506
+ "loss": 1.1486,
507
+ "step": 690
508
+ },
509
+ {
510
+ "epoch": 0.30627871362940273,
511
+ "grad_norm": 1.5043679475784302,
512
+ "learning_rate": 4.80423647329119e-05,
513
+ "loss": 1.0961,
514
+ "step": 700
515
+ },
516
+ {
517
+ "epoch": 0.3106541238241085,
518
+ "grad_norm": 1.6095219850540161,
519
+ "learning_rate": 4.797304346399263e-05,
520
+ "loss": 1.141,
521
+ "step": 710
522
+ },
523
+ {
524
+ "epoch": 0.3150295340188143,
525
+ "grad_norm": 1.628132939338684,
526
+ "learning_rate": 4.790256789969252e-05,
527
+ "loss": 1.1784,
528
+ "step": 720
529
+ },
530
+ {
531
+ "epoch": 0.31940494421352,
532
+ "grad_norm": 1.5121166706085205,
533
+ "learning_rate": 4.783094158110174e-05,
534
+ "loss": 1.1193,
535
+ "step": 730
536
+ },
537
+ {
538
+ "epoch": 0.3237803544082258,
539
+ "grad_norm": 1.5826560258865356,
540
+ "learning_rate": 4.775816810713086e-05,
541
+ "loss": 1.1206,
542
+ "step": 740
543
+ },
544
+ {
545
+ "epoch": 0.3281557646029315,
546
+ "grad_norm": 1.5174522399902344,
547
+ "learning_rate": 4.768425113433e-05,
548
+ "loss": 1.1566,
549
+ "step": 750
550
+ },
551
+ {
552
+ "epoch": 0.3325311747976373,
553
+ "grad_norm": 1.6296701431274414,
554
+ "learning_rate": 4.7609194376705105e-05,
555
+ "loss": 1.1388,
556
+ "step": 760
557
+ },
558
+ {
559
+ "epoch": 0.33690658499234305,
560
+ "grad_norm": 1.798865556716919,
561
+ "learning_rate": 4.753300160553136e-05,
562
+ "loss": 1.1889,
563
+ "step": 770
564
+ },
565
+ {
566
+ "epoch": 0.34128199518704877,
567
+ "grad_norm": 1.6122382879257202,
568
+ "learning_rate": 4.745567664916368e-05,
569
+ "loss": 1.125,
570
+ "step": 780
571
+ },
572
+ {
573
+ "epoch": 0.34565740538175455,
574
+ "grad_norm": 1.6329957246780396,
575
+ "learning_rate": 4.737722339284436e-05,
576
+ "loss": 1.121,
577
+ "step": 790
578
+ },
579
+ {
580
+ "epoch": 0.35003281557646027,
581
+ "grad_norm": 1.697094440460205,
582
+ "learning_rate": 4.7297645778507835e-05,
583
+ "loss": 1.0644,
584
+ "step": 800
585
+ },
586
+ {
587
+ "epoch": 0.35440822577116604,
588
+ "grad_norm": 1.6578021049499512,
589
+ "learning_rate": 4.721694780458266e-05,
590
+ "loss": 1.1579,
591
+ "step": 810
592
+ },
593
+ {
594
+ "epoch": 0.3587836359658718,
595
+ "grad_norm": 1.478832483291626,
596
+ "learning_rate": 4.7135133525790544e-05,
597
+ "loss": 1.1512,
598
+ "step": 820
599
+ },
600
+ {
601
+ "epoch": 0.36315904616057754,
602
+ "grad_norm": 1.513938546180725,
603
+ "learning_rate": 4.7052207052942685e-05,
604
+ "loss": 1.0791,
605
+ "step": 830
606
+ },
607
+ {
608
+ "epoch": 0.3675344563552833,
609
+ "grad_norm": 1.5836193561553955,
610
+ "learning_rate": 4.6968172552733185e-05,
611
+ "loss": 1.1259,
612
+ "step": 840
613
+ },
614
+ {
615
+ "epoch": 0.3719098665499891,
616
+ "grad_norm": 1.617882490158081,
617
+ "learning_rate": 4.688303424752969e-05,
618
+ "loss": 1.1001,
619
+ "step": 850
620
+ },
621
+ {
622
+ "epoch": 0.3762852767446948,
623
+ "grad_norm": 1.4709640741348267,
624
+ "learning_rate": 4.679679641516122e-05,
625
+ "loss": 1.1085,
626
+ "step": 860
627
+ },
628
+ {
629
+ "epoch": 0.3806606869394006,
630
+ "grad_norm": 1.4871046543121338,
631
+ "learning_rate": 4.670946338870329e-05,
632
+ "loss": 1.0863,
633
+ "step": 870
634
+ },
635
+ {
636
+ "epoch": 0.3850360971341063,
637
+ "grad_norm": 1.5609277486801147,
638
+ "learning_rate": 4.6621039556260095e-05,
639
+ "loss": 1.1255,
640
+ "step": 880
641
+ },
642
+ {
643
+ "epoch": 0.3894115073288121,
644
+ "grad_norm": 1.513523817062378,
645
+ "learning_rate": 4.653152936074413e-05,
646
+ "loss": 1.1101,
647
+ "step": 890
648
+ },
649
+ {
650
+ "epoch": 0.39378691752351785,
651
+ "grad_norm": 1.6045000553131104,
652
+ "learning_rate": 4.644093729965287e-05,
653
+ "loss": 1.1041,
654
+ "step": 900
655
+ },
656
+ {
657
+ "epoch": 0.3981623277182236,
658
+ "grad_norm": 1.5579705238342285,
659
+ "learning_rate": 4.634926792484284e-05,
660
+ "loss": 1.1592,
661
+ "step": 910
662
+ },
663
+ {
664
+ "epoch": 0.40253773791292935,
665
+ "grad_norm": 1.4306694269180298,
666
+ "learning_rate": 4.625652584230089e-05,
667
+ "loss": 1.1465,
668
+ "step": 920
669
+ },
670
+ {
671
+ "epoch": 0.40691314810763507,
672
+ "grad_norm": 1.3425192832946777,
673
+ "learning_rate": 4.616271571191273e-05,
674
+ "loss": 1.1555,
675
+ "step": 930
676
+ },
677
+ {
678
+ "epoch": 0.41128855830234085,
679
+ "grad_norm": 1.5686333179473877,
680
+ "learning_rate": 4.606784224722887e-05,
681
+ "loss": 1.1394,
682
+ "step": 940
683
+ },
684
+ {
685
+ "epoch": 0.4156639684970466,
686
+ "grad_norm": 1.4096781015396118,
687
+ "learning_rate": 4.5971910215227684e-05,
688
+ "loss": 1.0751,
689
+ "step": 950
690
+ },
691
+ {
692
+ "epoch": 0.42003937869175234,
693
+ "grad_norm": 1.3961308002471924,
694
+ "learning_rate": 4.5874924436075996e-05,
695
+ "loss": 1.1281,
696
+ "step": 960
697
+ },
698
+ {
699
+ "epoch": 0.4244147888864581,
700
+ "grad_norm": 1.4717061519622803,
701
+ "learning_rate": 4.577688978288681e-05,
702
+ "loss": 1.1441,
703
+ "step": 970
704
+ },
705
+ {
706
+ "epoch": 0.42879019908116384,
707
+ "grad_norm": 1.4169813394546509,
708
+ "learning_rate": 4.567781118147448e-05,
709
+ "loss": 1.1381,
710
+ "step": 980
711
+ },
712
+ {
713
+ "epoch": 0.4331656092758696,
714
+ "grad_norm": 1.4888379573822021,
715
+ "learning_rate": 4.557769361010721e-05,
716
+ "loss": 1.0826,
717
+ "step": 990
718
+ },
719
+ {
720
+ "epoch": 0.4375410194705754,
721
+ "grad_norm": 1.572547435760498,
722
+ "learning_rate": 4.547654209925693e-05,
723
+ "loss": 1.1131,
724
+ "step": 1000
725
+ },
726
+ {
727
+ "epoch": 0.4419164296652811,
728
+ "grad_norm": 1.5723587274551392,
729
+ "learning_rate": 4.5374361731346526e-05,
730
+ "loss": 1.1088,
731
+ "step": 1010
732
+ },
733
+ {
734
+ "epoch": 0.4462918398599869,
735
+ "grad_norm": 1.5646806955337524,
736
+ "learning_rate": 4.5271157640494456e-05,
737
+ "loss": 1.1313,
738
+ "step": 1020
739
+ },
740
+ {
741
+ "epoch": 0.4506672500546926,
742
+ "grad_norm": 1.6168869733810425,
743
+ "learning_rate": 4.51669350122568e-05,
744
+ "loss": 1.1452,
745
+ "step": 1030
746
+ },
747
+ {
748
+ "epoch": 0.4550426602493984,
749
+ "grad_norm": 1.565577745437622,
750
+ "learning_rate": 4.506169908336673e-05,
751
+ "loss": 1.1473,
752
+ "step": 1040
753
+ },
754
+ {
755
+ "epoch": 0.45941807044410415,
756
+ "grad_norm": 1.6016472578048706,
757
+ "learning_rate": 4.495545514147134e-05,
758
+ "loss": 1.1006,
759
+ "step": 1050
760
+ },
761
+ {
762
+ "epoch": 0.4637934806388099,
763
+ "grad_norm": 1.628869891166687,
764
+ "learning_rate": 4.484820852486598e-05,
765
+ "loss": 1.1327,
766
+ "step": 1060
767
+ },
768
+ {
769
+ "epoch": 0.46816889083351565,
770
+ "grad_norm": 1.4887852668762207,
771
+ "learning_rate": 4.473996462222606e-05,
772
+ "loss": 1.1011,
773
+ "step": 1070
774
+ },
775
+ {
776
+ "epoch": 0.47254430102822137,
777
+ "grad_norm": 1.6507240533828735,
778
+ "learning_rate": 4.463072887233625e-05,
779
+ "loss": 1.15,
780
+ "step": 1080
781
+ },
782
+ {
783
+ "epoch": 0.47691971122292715,
784
+ "grad_norm": 1.5163503885269165,
785
+ "learning_rate": 4.452050676381725e-05,
786
+ "loss": 1.1598,
787
+ "step": 1090
788
+ },
789
+ {
790
+ "epoch": 0.4812951214176329,
791
+ "grad_norm": 1.6033108234405518,
792
+ "learning_rate": 4.440930383484995e-05,
793
+ "loss": 1.118,
794
+ "step": 1100
795
+ },
796
+ {
797
+ "epoch": 0.48567053161233864,
798
+ "grad_norm": 1.4987646341323853,
799
+ "learning_rate": 4.429712567289722e-05,
800
+ "loss": 1.1352,
801
+ "step": 1110
802
+ },
803
+ {
804
+ "epoch": 0.4900459418070444,
805
+ "grad_norm": 1.51768159866333,
806
+ "learning_rate": 4.418397791442314e-05,
807
+ "loss": 1.1433,
808
+ "step": 1120
809
+ },
810
+ {
811
+ "epoch": 0.4944213520017502,
812
+ "grad_norm": 1.3354873657226562,
813
+ "learning_rate": 4.406986624460979e-05,
814
+ "loss": 1.147,
815
+ "step": 1130
816
+ },
817
+ {
818
+ "epoch": 0.4987967621964559,
819
+ "grad_norm": 1.5693355798721313,
820
+ "learning_rate": 4.395479639707158e-05,
821
+ "loss": 1.0808,
822
+ "step": 1140
823
+ },
824
+ {
825
+ "epoch": 0.5031721723911616,
826
+ "grad_norm": 1.5598881244659424,
827
+ "learning_rate": 4.3838774153567195e-05,
828
+ "loss": 1.1247,
829
+ "step": 1150
830
+ },
831
+ {
832
+ "epoch": 0.5075475825858674,
833
+ "grad_norm": 1.4272862672805786,
834
+ "learning_rate": 4.372180534370908e-05,
835
+ "loss": 1.1122,
836
+ "step": 1160
837
+ },
838
+ {
839
+ "epoch": 0.5119229927805732,
840
+ "grad_norm": 1.5112720727920532,
841
+ "learning_rate": 4.3603895844670495e-05,
842
+ "loss": 1.102,
843
+ "step": 1170
844
+ },
845
+ {
846
+ "epoch": 0.516298402975279,
847
+ "grad_norm": 1.589198350906372,
848
+ "learning_rate": 4.3485051580890236e-05,
849
+ "loss": 1.1435,
850
+ "step": 1180
851
+ },
852
+ {
853
+ "epoch": 0.5206738131699847,
854
+ "grad_norm": 1.4863295555114746,
855
+ "learning_rate": 4.336527852377497e-05,
856
+ "loss": 1.1374,
857
+ "step": 1190
858
+ },
859
+ {
860
+ "epoch": 0.5250492233646904,
861
+ "grad_norm": 1.4931763410568237,
862
+ "learning_rate": 4.324458269139916e-05,
863
+ "loss": 1.111,
864
+ "step": 1200
865
+ },
866
+ {
867
+ "epoch": 0.5294246335593962,
868
+ "grad_norm": 1.5186004638671875,
869
+ "learning_rate": 4.3122970148202744e-05,
870
+ "loss": 1.1213,
871
+ "step": 1210
872
+ },
873
+ {
874
+ "epoch": 0.533800043754102,
875
+ "grad_norm": 1.4999425411224365,
876
+ "learning_rate": 4.300044700468635e-05,
877
+ "loss": 1.1388,
878
+ "step": 1220
879
+ },
880
+ {
881
+ "epoch": 0.5381754539488077,
882
+ "grad_norm": 1.5555874109268188,
883
+ "learning_rate": 4.2877019417104334e-05,
884
+ "loss": 1.1028,
885
+ "step": 1230
886
+ },
887
+ {
888
+ "epoch": 0.5425508641435135,
889
+ "grad_norm": 1.4953700304031372,
890
+ "learning_rate": 4.27526935871554e-05,
891
+ "loss": 1.1342,
892
+ "step": 1240
893
+ },
894
+ {
895
+ "epoch": 0.5469262743382192,
896
+ "grad_norm": 1.4581255912780762,
897
+ "learning_rate": 4.262747576167106e-05,
898
+ "loss": 1.0921,
899
+ "step": 1250
900
+ },
901
+ {
902
+ "epoch": 0.5513016845329249,
903
+ "grad_norm": 1.552866816520691,
904
+ "learning_rate": 4.250137223230165e-05,
905
+ "loss": 1.1089,
906
+ "step": 1260
907
+ },
908
+ {
909
+ "epoch": 0.5556770947276307,
910
+ "grad_norm": 1.5412286520004272,
911
+ "learning_rate": 4.2374389335200335e-05,
912
+ "loss": 1.1261,
913
+ "step": 1270
914
+ },
915
+ {
916
+ "epoch": 0.5600525049223365,
917
+ "grad_norm": 1.64509117603302,
918
+ "learning_rate": 4.224653345070466e-05,
919
+ "loss": 1.0668,
920
+ "step": 1280
921
+ },
922
+ {
923
+ "epoch": 0.5644279151170423,
924
+ "grad_norm": 1.4940526485443115,
925
+ "learning_rate": 4.211781100301596e-05,
926
+ "loss": 1.1372,
927
+ "step": 1290
928
+ },
929
+ {
930
+ "epoch": 0.5688033253117479,
931
+ "grad_norm": 1.4879716634750366,
932
+ "learning_rate": 4.198822845987661e-05,
933
+ "loss": 1.1166,
934
+ "step": 1300
935
+ },
936
+ {
937
+ "epoch": 0.5731787355064537,
938
+ "grad_norm": 1.5581066608428955,
939
+ "learning_rate": 4.185779233224506e-05,
940
+ "loss": 1.0663,
941
+ "step": 1310
942
+ },
943
+ {
944
+ "epoch": 0.5775541457011595,
945
+ "grad_norm": 1.5502949953079224,
946
+ "learning_rate": 4.172650917396863e-05,
947
+ "loss": 1.165,
948
+ "step": 1320
949
+ },
950
+ {
951
+ "epoch": 0.5819295558958653,
952
+ "grad_norm": 1.4957443475723267,
953
+ "learning_rate": 4.1594385581454245e-05,
954
+ "loss": 1.1723,
955
+ "step": 1330
956
+ },
957
+ {
958
+ "epoch": 0.586304966090571,
959
+ "grad_norm": 1.4180186986923218,
960
+ "learning_rate": 4.146142819333702e-05,
961
+ "loss": 1.1181,
962
+ "step": 1340
963
+ },
964
+ {
965
+ "epoch": 0.5906803762852767,
966
+ "grad_norm": 1.5630731582641602,
967
+ "learning_rate": 4.132764369014662e-05,
968
+ "loss": 1.1731,
969
+ "step": 1350
970
+ },
971
+ {
972
+ "epoch": 0.5950557864799825,
973
+ "grad_norm": 1.5089911222457886,
974
+ "learning_rate": 4.119303879397169e-05,
975
+ "loss": 1.1199,
976
+ "step": 1360
977
+ },
978
+ {
979
+ "epoch": 0.5994311966746882,
980
+ "grad_norm": 1.4724007844924927,
981
+ "learning_rate": 4.1057620268122004e-05,
982
+ "loss": 1.1108,
983
+ "step": 1370
984
+ },
985
+ {
986
+ "epoch": 0.603806606869394,
987
+ "grad_norm": 1.6644493341445923,
988
+ "learning_rate": 4.092139491678873e-05,
989
+ "loss": 1.0948,
990
+ "step": 1380
991
+ },
992
+ {
993
+ "epoch": 0.6081820170640998,
994
+ "grad_norm": 1.598973035812378,
995
+ "learning_rate": 4.078436958470244e-05,
996
+ "loss": 1.0948,
997
+ "step": 1390
998
+ },
999
+ {
1000
+ "epoch": 0.6125574272588055,
1001
+ "grad_norm": 1.4203752279281616,
1002
+ "learning_rate": 4.064655115678933e-05,
1003
+ "loss": 1.0704,
1004
+ "step": 1400
1005
+ },
1006
+ {
1007
+ "epoch": 0.6169328374535112,
1008
+ "grad_norm": 1.367942214012146,
1009
+ "learning_rate": 4.050794655782515e-05,
1010
+ "loss": 1.0958,
1011
+ "step": 1410
1012
+ },
1013
+ {
1014
+ "epoch": 0.621308247648217,
1015
+ "grad_norm": 1.553614616394043,
1016
+ "learning_rate": 4.036856275208736e-05,
1017
+ "loss": 1.0756,
1018
+ "step": 1420
1019
+ },
1020
+ {
1021
+ "epoch": 0.6256836578429228,
1022
+ "grad_norm": 1.4172255992889404,
1023
+ "learning_rate": 4.022840674300512e-05,
1024
+ "loss": 1.1166,
1025
+ "step": 1430
1026
+ },
1027
+ {
1028
+ "epoch": 0.6300590680376286,
1029
+ "grad_norm": 1.6529884338378906,
1030
+ "learning_rate": 4.0087485572807485e-05,
1031
+ "loss": 1.069,
1032
+ "step": 1440
1033
+ },
1034
+ {
1035
+ "epoch": 0.6344344782323342,
1036
+ "grad_norm": 1.5031507015228271,
1037
+ "learning_rate": 3.994580632216952e-05,
1038
+ "loss": 1.1368,
1039
+ "step": 1450
1040
+ },
1041
+ {
1042
+ "epoch": 0.63880988842704,
1043
+ "grad_norm": 1.6318256855010986,
1044
+ "learning_rate": 3.980337610985651e-05,
1045
+ "loss": 1.1184,
1046
+ "step": 1460
1047
+ },
1048
+ {
1049
+ "epoch": 0.6431852986217458,
1050
+ "grad_norm": 1.5290026664733887,
1051
+ "learning_rate": 3.9660202092366316e-05,
1052
+ "loss": 1.1252,
1053
+ "step": 1470
1054
+ },
1055
+ {
1056
+ "epoch": 0.6475607088164516,
1057
+ "grad_norm": 1.4681955575942993,
1058
+ "learning_rate": 3.951629146356975e-05,
1059
+ "loss": 1.0866,
1060
+ "step": 1480
1061
+ },
1062
+ {
1063
+ "epoch": 0.6519361190111573,
1064
+ "grad_norm": 1.4883171319961548,
1065
+ "learning_rate": 3.937165145434914e-05,
1066
+ "loss": 1.1292,
1067
+ "step": 1490
1068
+ },
1069
+ {
1070
+ "epoch": 0.656311529205863,
1071
+ "grad_norm": 1.5238957405090332,
1072
+ "learning_rate": 3.922628933223502e-05,
1073
+ "loss": 1.1547,
1074
+ "step": 1500
1075
+ },
1076
+ {
1077
+ "epoch": 0.6606869394005688,
1078
+ "grad_norm": 1.5324879884719849,
1079
+ "learning_rate": 3.9080212401040914e-05,
1080
+ "loss": 1.0668,
1081
+ "step": 1510
1082
+ },
1083
+ {
1084
+ "epoch": 0.6650623495952745,
1085
+ "grad_norm": 1.4942597150802612,
1086
+ "learning_rate": 3.8933428000496455e-05,
1087
+ "loss": 1.1394,
1088
+ "step": 1520
1089
+ },
1090
+ {
1091
+ "epoch": 0.6694377597899803,
1092
+ "grad_norm": 1.5268304347991943,
1093
+ "learning_rate": 3.878594350587844e-05,
1094
+ "loss": 1.0647,
1095
+ "step": 1530
1096
+ },
1097
+ {
1098
+ "epoch": 0.6738131699846861,
1099
+ "grad_norm": 1.5157787799835205,
1100
+ "learning_rate": 3.863776632764043e-05,
1101
+ "loss": 1.1521,
1102
+ "step": 1540
1103
+ },
1104
+ {
1105
+ "epoch": 0.6781885801793918,
1106
+ "grad_norm": 1.5063765048980713,
1107
+ "learning_rate": 3.848890391104028e-05,
1108
+ "loss": 1.0954,
1109
+ "step": 1550
1110
+ },
1111
+ {
1112
+ "epoch": 0.6825639903740975,
1113
+ "grad_norm": 1.4812955856323242,
1114
+ "learning_rate": 3.833936373576606e-05,
1115
+ "loss": 1.1054,
1116
+ "step": 1560
1117
+ },
1118
+ {
1119
+ "epoch": 0.6869394005688033,
1120
+ "grad_norm": 1.4586228132247925,
1121
+ "learning_rate": 3.8189153315560324e-05,
1122
+ "loss": 1.1125,
1123
+ "step": 1570
1124
+ },
1125
+ {
1126
+ "epoch": 0.6913148107635091,
1127
+ "grad_norm": 1.3584743738174438,
1128
+ "learning_rate": 3.803828019784248e-05,
1129
+ "loss": 1.103,
1130
+ "step": 1580
1131
+ },
1132
+ {
1133
+ "epoch": 0.6956902209582149,
1134
+ "grad_norm": 1.5196596384048462,
1135
+ "learning_rate": 3.788675196332959e-05,
1136
+ "loss": 1.1642,
1137
+ "step": 1590
1138
+ },
1139
+ {
1140
+ "epoch": 0.7000656311529205,
1141
+ "grad_norm": 1.5605676174163818,
1142
+ "learning_rate": 3.7734576225655504e-05,
1143
+ "loss": 1.1656,
1144
+ "step": 1600
1145
+ },
1146
+ {
1147
+ "epoch": 0.7044410413476263,
1148
+ "grad_norm": 1.4787431955337524,
1149
+ "learning_rate": 3.758176063098829e-05,
1150
+ "loss": 1.0855,
1151
+ "step": 1610
1152
+ },
1153
+ {
1154
+ "epoch": 0.7088164515423321,
1155
+ "grad_norm": 1.4558417797088623,
1156
+ "learning_rate": 3.742831285764602e-05,
1157
+ "loss": 1.0855,
1158
+ "step": 1620
1159
+ },
1160
+ {
1161
+ "epoch": 0.7131918617370379,
1162
+ "grad_norm": 1.552485466003418,
1163
+ "learning_rate": 3.7274240615710986e-05,
1164
+ "loss": 1.0949,
1165
+ "step": 1630
1166
+ },
1167
+ {
1168
+ "epoch": 0.7175672719317436,
1169
+ "grad_norm": 1.5539509057998657,
1170
+ "learning_rate": 3.711955164664235e-05,
1171
+ "loss": 1.1285,
1172
+ "step": 1640
1173
+ },
1174
+ {
1175
+ "epoch": 0.7219426821264494,
1176
+ "grad_norm": 1.4706348180770874,
1177
+ "learning_rate": 3.6964253722887075e-05,
1178
+ "loss": 1.1041,
1179
+ "step": 1650
1180
+ },
1181
+ {
1182
+ "epoch": 0.7263180923211551,
1183
+ "grad_norm": 1.460062861442566,
1184
+ "learning_rate": 3.680835464748949e-05,
1185
+ "loss": 1.0845,
1186
+ "step": 1660
1187
+ },
1188
+ {
1189
+ "epoch": 0.7306935025158608,
1190
+ "grad_norm": 1.4356744289398193,
1191
+ "learning_rate": 3.6651862253699144e-05,
1192
+ "loss": 1.0716,
1193
+ "step": 1670
1194
+ },
1195
+ {
1196
+ "epoch": 0.7350689127105666,
1197
+ "grad_norm": 1.6479544639587402,
1198
+ "learning_rate": 3.649478440457726e-05,
1199
+ "loss": 1.1017,
1200
+ "step": 1680
1201
+ },
1202
+ {
1203
+ "epoch": 0.7394443229052724,
1204
+ "grad_norm": 1.4607200622558594,
1205
+ "learning_rate": 3.633712899260166e-05,
1206
+ "loss": 1.0853,
1207
+ "step": 1690
1208
+ },
1209
+ {
1210
+ "epoch": 0.7438197330999782,
1211
+ "grad_norm": 1.5237467288970947,
1212
+ "learning_rate": 3.617890393927015e-05,
1213
+ "loss": 1.1646,
1214
+ "step": 1700
1215
+ },
1216
+ {
1217
+ "epoch": 0.7481951432946838,
1218
+ "grad_norm": 1.464272379875183,
1219
+ "learning_rate": 3.6020117194702555e-05,
1220
+ "loss": 1.0863,
1221
+ "step": 1710
1222
+ },
1223
+ {
1224
+ "epoch": 0.7525705534893896,
1225
+ "grad_norm": 1.440658688545227,
1226
+ "learning_rate": 3.586077673724124e-05,
1227
+ "loss": 1.128,
1228
+ "step": 1720
1229
+ },
1230
+ {
1231
+ "epoch": 0.7569459636840954,
1232
+ "grad_norm": 1.5667482614517212,
1233
+ "learning_rate": 3.570089057305022e-05,
1234
+ "loss": 1.1441,
1235
+ "step": 1730
1236
+ },
1237
+ {
1238
+ "epoch": 0.7613213738788012,
1239
+ "grad_norm": 1.4171441793441772,
1240
+ "learning_rate": 3.5540466735712906e-05,
1241
+ "loss": 1.1002,
1242
+ "step": 1740
1243
+ },
1244
+ {
1245
+ "epoch": 0.7656967840735069,
1246
+ "grad_norm": 1.412792444229126,
1247
+ "learning_rate": 3.5379513285828433e-05,
1248
+ "loss": 1.0983,
1249
+ "step": 1750
1250
+ },
1251
+ {
1252
+ "epoch": 0.7700721942682126,
1253
+ "grad_norm": 1.468995213508606,
1254
+ "learning_rate": 3.521803831060668e-05,
1255
+ "loss": 1.0736,
1256
+ "step": 1760
1257
+ },
1258
+ {
1259
+ "epoch": 0.7744476044629184,
1260
+ "grad_norm": 1.570688247680664,
1261
+ "learning_rate": 3.505604992346187e-05,
1262
+ "loss": 1.0935,
1263
+ "step": 1770
1264
+ },
1265
+ {
1266
+ "epoch": 0.7788230146576242,
1267
+ "grad_norm": 1.4552085399627686,
1268
+ "learning_rate": 3.489355626360497e-05,
1269
+ "loss": 1.1388,
1270
+ "step": 1780
1271
+ },
1272
+ {
1273
+ "epoch": 0.7831984248523299,
1274
+ "grad_norm": 1.6429483890533447,
1275
+ "learning_rate": 3.473056549563469e-05,
1276
+ "loss": 1.1082,
1277
+ "step": 1790
1278
+ },
1279
+ {
1280
+ "epoch": 0.7875738350470357,
1281
+ "grad_norm": 1.6186859607696533,
1282
+ "learning_rate": 3.456708580912725e-05,
1283
+ "loss": 1.1182,
1284
+ "step": 1800
1285
+ },
1286
+ {
1287
+ "epoch": 0.7919492452417414,
1288
+ "grad_norm": 1.3440533876419067,
1289
+ "learning_rate": 3.44031254182249e-05,
1290
+ "loss": 1.0769,
1291
+ "step": 1810
1292
+ },
1293
+ {
1294
+ "epoch": 0.7963246554364471,
1295
+ "grad_norm": 1.3511815071105957,
1296
+ "learning_rate": 3.42386925612232e-05,
1297
+ "loss": 1.0761,
1298
+ "step": 1820
1299
+ },
1300
+ {
1301
+ "epoch": 0.8007000656311529,
1302
+ "grad_norm": 1.4499377012252808,
1303
+ "learning_rate": 3.407379550015707e-05,
1304
+ "loss": 1.1344,
1305
+ "step": 1830
1306
+ },
1307
+ {
1308
+ "epoch": 0.8050754758258587,
1309
+ "grad_norm": 1.4759228229522705,
1310
+ "learning_rate": 3.390844252038565e-05,
1311
+ "loss": 1.0874,
1312
+ "step": 1840
1313
+ },
1314
+ {
1315
+ "epoch": 0.8094508860205645,
1316
+ "grad_norm": 1.4827808141708374,
1317
+ "learning_rate": 3.3742641930176045e-05,
1318
+ "loss": 1.0313,
1319
+ "step": 1850
1320
+ },
1321
+ {
1322
+ "epoch": 0.8138262962152701,
1323
+ "grad_norm": 1.6069589853286743,
1324
+ "learning_rate": 3.3576402060285786e-05,
1325
+ "loss": 1.1089,
1326
+ "step": 1860
1327
+ },
1328
+ {
1329
+ "epoch": 0.8182017064099759,
1330
+ "grad_norm": 1.4358799457550049,
1331
+ "learning_rate": 3.3409731263544345e-05,
1332
+ "loss": 1.0682,
1333
+ "step": 1870
1334
+ },
1335
+ {
1336
+ "epoch": 0.8225771166046817,
1337
+ "grad_norm": 1.4865995645523071,
1338
+ "learning_rate": 3.324263791443333e-05,
1339
+ "loss": 1.0924,
1340
+ "step": 1880
1341
+ },
1342
+ {
1343
+ "epoch": 0.8269525267993875,
1344
+ "grad_norm": 1.4410614967346191,
1345
+ "learning_rate": 3.307513040866584e-05,
1346
+ "loss": 1.0754,
1347
+ "step": 1890
1348
+ },
1349
+ {
1350
+ "epoch": 0.8313279369940932,
1351
+ "grad_norm": 1.3776915073394775,
1352
+ "learning_rate": 3.290721716276448e-05,
1353
+ "loss": 1.097,
1354
+ "step": 1900
1355
+ },
1356
+ {
1357
+ "epoch": 0.8357033471887989,
1358
+ "grad_norm": 1.5188299417495728,
1359
+ "learning_rate": 3.273890661363855e-05,
1360
+ "loss": 1.1616,
1361
+ "step": 1910
1362
+ },
1363
+ {
1364
+ "epoch": 0.8400787573835047,
1365
+ "grad_norm": 1.5575170516967773,
1366
+ "learning_rate": 3.257020721816013e-05,
1367
+ "loss": 1.1246,
1368
+ "step": 1920
1369
+ },
1370
+ {
1371
+ "epoch": 0.8444541675782105,
1372
+ "grad_norm": 1.5193071365356445,
1373
+ "learning_rate": 3.240112745273911e-05,
1374
+ "loss": 1.1162,
1375
+ "step": 1930
1376
+ },
1377
+ {
1378
+ "epoch": 0.8488295777729162,
1379
+ "grad_norm": 1.451002836227417,
1380
+ "learning_rate": 3.223167581289729e-05,
1381
+ "loss": 1.1106,
1382
+ "step": 1940
1383
+ },
1384
+ {
1385
+ "epoch": 0.853204987967622,
1386
+ "grad_norm": 1.54093599319458,
1387
+ "learning_rate": 3.206186081284161e-05,
1388
+ "loss": 1.071,
1389
+ "step": 1950
1390
+ },
1391
+ {
1392
+ "epoch": 0.8575803981623277,
1393
+ "grad_norm": 1.5598371028900146,
1394
+ "learning_rate": 3.1891690985036215e-05,
1395
+ "loss": 1.0986,
1396
+ "step": 1960
1397
+ },
1398
+ {
1399
+ "epoch": 0.8619558083570334,
1400
+ "grad_norm": 1.4229456186294556,
1401
+ "learning_rate": 3.1721174879773826e-05,
1402
+ "loss": 1.0839,
1403
+ "step": 1970
1404
+ },
1405
+ {
1406
+ "epoch": 0.8663312185517392,
1407
+ "grad_norm": 1.5579663515090942,
1408
+ "learning_rate": 3.1550321064746086e-05,
1409
+ "loss": 1.0854,
1410
+ "step": 1980
1411
+ },
1412
+ {
1413
+ "epoch": 0.870706628746445,
1414
+ "grad_norm": 1.4583122730255127,
1415
+ "learning_rate": 3.1379138124613105e-05,
1416
+ "loss": 1.0916,
1417
+ "step": 1990
1418
+ },
1419
+ {
1420
+ "epoch": 0.8750820389411508,
1421
+ "grad_norm": 1.577874779701233,
1422
+ "learning_rate": 3.120763466057206e-05,
1423
+ "loss": 1.061,
1424
+ "step": 2000
1425
+ },
1426
+ {
1427
+ "epoch": 0.8794574491358564,
1428
+ "grad_norm": 1.5133827924728394,
1429
+ "learning_rate": 3.10358192899251e-05,
1430
+ "loss": 1.1227,
1431
+ "step": 2010
1432
+ },
1433
+ {
1434
+ "epoch": 0.8838328593305622,
1435
+ "grad_norm": 1.4519861936569214,
1436
+ "learning_rate": 3.086370064564629e-05,
1437
+ "loss": 1.086,
1438
+ "step": 2020
1439
+ },
1440
+ {
1441
+ "epoch": 0.888208269525268,
1442
+ "grad_norm": 1.6563777923583984,
1443
+ "learning_rate": 3.069128737594789e-05,
1444
+ "loss": 1.1102,
1445
+ "step": 2030
1446
+ },
1447
+ {
1448
+ "epoch": 0.8925836797199738,
1449
+ "grad_norm": 1.3476353883743286,
1450
+ "learning_rate": 3.051858814384581e-05,
1451
+ "loss": 1.0804,
1452
+ "step": 2040
1453
+ },
1454
+ {
1455
+ "epoch": 0.8969590899146795,
1456
+ "grad_norm": 1.501389503479004,
1457
+ "learning_rate": 3.0345611626724285e-05,
1458
+ "loss": 1.1101,
1459
+ "step": 2050
1460
+ },
1461
+ {
1462
+ "epoch": 0.9013345001093852,
1463
+ "grad_norm": 1.483244776725769,
1464
+ "learning_rate": 3.0172366515899982e-05,
1465
+ "loss": 1.0964,
1466
+ "step": 2060
1467
+ },
1468
+ {
1469
+ "epoch": 0.905709910304091,
1470
+ "grad_norm": 1.4610023498535156,
1471
+ "learning_rate": 2.9998861516185173e-05,
1472
+ "loss": 1.0953,
1473
+ "step": 2070
1474
+ },
1475
+ {
1476
+ "epoch": 0.9100853204987968,
1477
+ "grad_norm": 1.4304044246673584,
1478
+ "learning_rate": 2.982510534545043e-05,
1479
+ "loss": 1.0687,
1480
+ "step": 2080
1481
+ },
1482
+ {
1483
+ "epoch": 0.9144607306935025,
1484
+ "grad_norm": 1.461287498474121,
1485
+ "learning_rate": 2.9651106734186618e-05,
1486
+ "loss": 1.0875,
1487
+ "step": 2090
1488
+ },
1489
+ {
1490
+ "epoch": 0.9188361408882083,
1491
+ "grad_norm": 1.484709620475769,
1492
+ "learning_rate": 2.9476874425066105e-05,
1493
+ "loss": 1.1122,
1494
+ "step": 2100
1495
+ },
1496
+ {
1497
+ "epoch": 0.923211551082914,
1498
+ "grad_norm": 1.4673666954040527,
1499
+ "learning_rate": 2.9302417172503622e-05,
1500
+ "loss": 1.1506,
1501
+ "step": 2110
1502
+ },
1503
+ {
1504
+ "epoch": 0.9275869612776197,
1505
+ "grad_norm": 1.456113576889038,
1506
+ "learning_rate": 2.9127743742216303e-05,
1507
+ "loss": 1.0851,
1508
+ "step": 2120
1509
+ },
1510
+ {
1511
+ "epoch": 0.9319623714723255,
1512
+ "grad_norm": 1.524404525756836,
1513
+ "learning_rate": 2.8952862910783267e-05,
1514
+ "loss": 1.1047,
1515
+ "step": 2130
1516
+ },
1517
+ {
1518
+ "epoch": 0.9363377816670313,
1519
+ "grad_norm": 1.3824920654296875,
1520
+ "learning_rate": 2.877778346520466e-05,
1521
+ "loss": 1.069,
1522
+ "step": 2140
1523
+ },
1524
+ {
1525
+ "epoch": 0.9407131918617371,
1526
+ "grad_norm": 1.3911488056182861,
1527
+ "learning_rate": 2.860251420246009e-05,
1528
+ "loss": 1.1128,
1529
+ "step": 2150
1530
+ },
1531
+ {
1532
+ "epoch": 0.9450886020564427,
1533
+ "grad_norm": 1.6120619773864746,
1534
+ "learning_rate": 2.842706392906669e-05,
1535
+ "loss": 1.1468,
1536
+ "step": 2160
1537
+ },
1538
+ {
1539
+ "epoch": 0.9494640122511485,
1540
+ "grad_norm": 1.4727811813354492,
1541
+ "learning_rate": 2.825144146063654e-05,
1542
+ "loss": 1.1405,
1543
+ "step": 2170
1544
+ },
1545
+ {
1546
+ "epoch": 0.9538394224458543,
1547
+ "grad_norm": 1.4946926832199097,
1548
+ "learning_rate": 2.8075655621433826e-05,
1549
+ "loss": 1.0887,
1550
+ "step": 2180
1551
+ },
1552
+ {
1553
+ "epoch": 0.9582148326405601,
1554
+ "grad_norm": 1.575395107269287,
1555
+ "learning_rate": 2.7899715243931375e-05,
1556
+ "loss": 1.077,
1557
+ "step": 2190
1558
+ },
1559
+ {
1560
+ "epoch": 0.9625902428352658,
1561
+ "grad_norm": 1.483463168144226,
1562
+ "learning_rate": 2.7723629168366883e-05,
1563
+ "loss": 1.1137,
1564
+ "step": 2200
1565
+ },
1566
+ {
1567
+ "epoch": 0.9669656530299715,
1568
+ "grad_norm": 1.5409109592437744,
1569
+ "learning_rate": 2.754740624229875e-05,
1570
+ "loss": 1.0749,
1571
+ "step": 2210
1572
+ },
1573
+ {
1574
+ "epoch": 0.9713410632246773,
1575
+ "grad_norm": 1.4951428174972534,
1576
+ "learning_rate": 2.737105532016152e-05,
1577
+ "loss": 1.0779,
1578
+ "step": 2220
1579
+ },
1580
+ {
1581
+ "epoch": 0.9757164734193831,
1582
+ "grad_norm": 1.6109696626663208,
1583
+ "learning_rate": 2.719458526282099e-05,
1584
+ "loss": 1.1006,
1585
+ "step": 2230
1586
+ },
1587
+ {
1588
+ "epoch": 0.9800918836140888,
1589
+ "grad_norm": 1.4150285720825195,
1590
+ "learning_rate": 2.7018004937128937e-05,
1591
+ "loss": 1.0498,
1592
+ "step": 2240
1593
+ },
1594
+ {
1595
+ "epoch": 0.9844672938087946,
1596
+ "grad_norm": 1.5306379795074463,
1597
+ "learning_rate": 2.6841323215477714e-05,
1598
+ "loss": 1.0943,
1599
+ "step": 2250
1600
+ },
1601
+ {
1602
+ "epoch": 0.9888427040035004,
1603
+ "grad_norm": 1.3424153327941895,
1604
+ "learning_rate": 2.6664548975354332e-05,
1605
+ "loss": 1.079,
1606
+ "step": 2260
1607
+ },
1608
+ {
1609
+ "epoch": 0.993218114198206,
1610
+ "grad_norm": 1.4553660154342651,
1611
+ "learning_rate": 2.6487691098894447e-05,
1612
+ "loss": 1.0663,
1613
+ "step": 2270
1614
+ },
1615
+ {
1616
+ "epoch": 0.9975935243929118,
1617
+ "grad_norm": 1.5150882005691528,
1618
+ "learning_rate": 2.6310758472436103e-05,
1619
+ "loss": 1.0449,
1620
+ "step": 2280
1621
+ },
1622
+ {
1623
+ "epoch": 1.0017501640778823,
1624
+ "grad_norm": 1.4436382055282593,
1625
+ "learning_rate": 2.6133759986073197e-05,
1626
+ "loss": 1.1167,
1627
+ "step": 2290
1628
+ },
1629
+ {
1630
+ "epoch": 1.006125574272588,
1631
+ "grad_norm": 1.6366405487060547,
1632
+ "learning_rate": 2.595670453320879e-05,
1633
+ "loss": 1.0539,
1634
+ "step": 2300
1635
+ },
1636
+ {
1637
+ "epoch": 1.0105009844672939,
1638
+ "grad_norm": 1.5061817169189453,
1639
+ "learning_rate": 2.5779601010108273e-05,
1640
+ "loss": 1.0694,
1641
+ "step": 2310
1642
+ },
1643
+ {
1644
+ "epoch": 1.0148763946619996,
1645
+ "grad_norm": 1.5583983659744263,
1646
+ "learning_rate": 2.5602458315452355e-05,
1647
+ "loss": 1.0598,
1648
+ "step": 2320
1649
+ },
1650
+ {
1651
+ "epoch": 1.0192518048567054,
1652
+ "grad_norm": 1.4948369264602661,
1653
+ "learning_rate": 2.5425285349889938e-05,
1654
+ "loss": 1.0323,
1655
+ "step": 2330
1656
+ },
1657
+ {
1658
+ "epoch": 1.023627215051411,
1659
+ "grad_norm": 1.4352792501449585,
1660
+ "learning_rate": 2.5248091015590907e-05,
1661
+ "loss": 1.0418,
1662
+ "step": 2340
1663
+ },
1664
+ {
1665
+ "epoch": 1.0280026252461167,
1666
+ "grad_norm": 1.5330169200897217,
1667
+ "learning_rate": 2.507088421579884e-05,
1668
+ "loss": 1.0375,
1669
+ "step": 2350
1670
+ },
1671
+ {
1672
+ "epoch": 1.0323780354408225,
1673
+ "grad_norm": 1.4603830575942993,
1674
+ "learning_rate": 2.489367385438365e-05,
1675
+ "loss": 1.1019,
1676
+ "step": 2360
1677
+ },
1678
+ {
1679
+ "epoch": 1.0367534456355283,
1680
+ "grad_norm": 1.3922033309936523,
1681
+ "learning_rate": 2.4716468835394195e-05,
1682
+ "loss": 1.0636,
1683
+ "step": 2370
1684
+ },
1685
+ {
1686
+ "epoch": 1.041128855830234,
1687
+ "grad_norm": 1.389041543006897,
1688
+ "learning_rate": 2.4539278062610928e-05,
1689
+ "loss": 1.0634,
1690
+ "step": 2380
1691
+ },
1692
+ {
1693
+ "epoch": 1.0455042660249398,
1694
+ "grad_norm": 1.577828049659729,
1695
+ "learning_rate": 2.4362110439098443e-05,
1696
+ "loss": 1.0551,
1697
+ "step": 2390
1698
+ },
1699
+ {
1700
+ "epoch": 1.0498796762196456,
1701
+ "grad_norm": 1.4485417604446411,
1702
+ "learning_rate": 2.4184974866758232e-05,
1703
+ "loss": 1.0447,
1704
+ "step": 2400
1705
+ },
1706
+ {
1707
+ "epoch": 1.0542550864143514,
1708
+ "grad_norm": 1.3846266269683838,
1709
+ "learning_rate": 2.400788024588134e-05,
1710
+ "loss": 1.0129,
1711
+ "step": 2410
1712
+ },
1713
+ {
1714
+ "epoch": 1.0586304966090572,
1715
+ "grad_norm": 1.612506628036499,
1716
+ "learning_rate": 2.3830835474701158e-05,
1717
+ "loss": 1.0622,
1718
+ "step": 2420
1719
+ },
1720
+ {
1721
+ "epoch": 1.063005906803763,
1722
+ "grad_norm": 1.3812724351882935,
1723
+ "learning_rate": 2.365384944894638e-05,
1724
+ "loss": 1.024,
1725
+ "step": 2430
1726
+ },
1727
+ {
1728
+ "epoch": 1.0673813169984685,
1729
+ "grad_norm": 1.5689557790756226,
1730
+ "learning_rate": 2.3476931061393968e-05,
1731
+ "loss": 1.0753,
1732
+ "step": 2440
1733
+ },
1734
+ {
1735
+ "epoch": 1.0717567271931743,
1736
+ "grad_norm": 1.5560890436172485,
1737
+ "learning_rate": 2.33000892014224e-05,
1738
+ "loss": 1.0436,
1739
+ "step": 2450
1740
+ },
1741
+ {
1742
+ "epoch": 1.07613213738788,
1743
+ "grad_norm": 1.625240445137024,
1744
+ "learning_rate": 2.312333275456492e-05,
1745
+ "loss": 1.0584,
1746
+ "step": 2460
1747
+ },
1748
+ {
1749
+ "epoch": 1.0805075475825858,
1750
+ "grad_norm": 1.5473369359970093,
1751
+ "learning_rate": 2.2946670602063175e-05,
1752
+ "loss": 1.0547,
1753
+ "step": 2470
1754
+ },
1755
+ {
1756
+ "epoch": 1.0848829577772916,
1757
+ "grad_norm": 1.529844045639038,
1758
+ "learning_rate": 2.2770111620420935e-05,
1759
+ "loss": 1.0644,
1760
+ "step": 2480
1761
+ },
1762
+ {
1763
+ "epoch": 1.0892583679719974,
1764
+ "grad_norm": 1.512666940689087,
1765
+ "learning_rate": 2.2593664680958045e-05,
1766
+ "loss": 1.0301,
1767
+ "step": 2490
1768
+ },
1769
+ {
1770
+ "epoch": 1.0936337781667032,
1771
+ "grad_norm": 1.5139986276626587,
1772
+ "learning_rate": 2.2417338649364765e-05,
1773
+ "loss": 1.0677,
1774
+ "step": 2500
1775
+ },
1776
+ {
1777
+ "epoch": 1.098009188361409,
1778
+ "grad_norm": 1.4566220045089722,
1779
+ "learning_rate": 2.2241142385256237e-05,
1780
+ "loss": 1.0807,
1781
+ "step": 2510
1782
+ },
1783
+ {
1784
+ "epoch": 1.1023845985561147,
1785
+ "grad_norm": 1.644047737121582,
1786
+ "learning_rate": 2.2065084741727337e-05,
1787
+ "loss": 1.0405,
1788
+ "step": 2520
1789
+ },
1790
+ {
1791
+ "epoch": 1.1067600087508205,
1792
+ "grad_norm": 1.5637203454971313,
1793
+ "learning_rate": 2.1889174564907898e-05,
1794
+ "loss": 1.0686,
1795
+ "step": 2530
1796
+ },
1797
+ {
1798
+ "epoch": 1.1111354189455263,
1799
+ "grad_norm": 1.4541386365890503,
1800
+ "learning_rate": 2.1713420693518155e-05,
1801
+ "loss": 1.0723,
1802
+ "step": 2540
1803
+ },
1804
+ {
1805
+ "epoch": 1.1155108291402318,
1806
+ "grad_norm": 1.5103000402450562,
1807
+ "learning_rate": 2.153783195842472e-05,
1808
+ "loss": 1.0749,
1809
+ "step": 2550
1810
+ },
1811
+ {
1812
+ "epoch": 1.1198862393349376,
1813
+ "grad_norm": 1.3568867444992065,
1814
+ "learning_rate": 2.136241718219677e-05,
1815
+ "loss": 1.0348,
1816
+ "step": 2560
1817
+ },
1818
+ {
1819
+ "epoch": 1.1242616495296434,
1820
+ "grad_norm": 1.4986484050750732,
1821
+ "learning_rate": 2.118718517866286e-05,
1822
+ "loss": 1.0317,
1823
+ "step": 2570
1824
+ },
1825
+ {
1826
+ "epoch": 1.1286370597243491,
1827
+ "grad_norm": 1.5433015823364258,
1828
+ "learning_rate": 2.101214475246798e-05,
1829
+ "loss": 1.0577,
1830
+ "step": 2580
1831
+ },
1832
+ {
1833
+ "epoch": 1.133012469919055,
1834
+ "grad_norm": 1.5786523818969727,
1835
+ "learning_rate": 2.0837304698631195e-05,
1836
+ "loss": 1.0226,
1837
+ "step": 2590
1838
+ },
1839
+ {
1840
+ "epoch": 1.1373878801137607,
1841
+ "grad_norm": 1.6050409078598022,
1842
+ "learning_rate": 2.066267380210375e-05,
1843
+ "loss": 1.08,
1844
+ "step": 2600
1845
+ },
1846
+ {
1847
+ "epoch": 1.1417632903084665,
1848
+ "grad_norm": 1.551988959312439,
1849
+ "learning_rate": 2.0488260837327626e-05,
1850
+ "loss": 1.0365,
1851
+ "step": 2610
1852
+ },
1853
+ {
1854
+ "epoch": 1.1461387005031722,
1855
+ "grad_norm": 1.4551851749420166,
1856
+ "learning_rate": 2.0314074567794704e-05,
1857
+ "loss": 1.0489,
1858
+ "step": 2620
1859
+ },
1860
+ {
1861
+ "epoch": 1.150514110697878,
1862
+ "grad_norm": 1.579973816871643,
1863
+ "learning_rate": 2.0140123745606397e-05,
1864
+ "loss": 1.0423,
1865
+ "step": 2630
1866
+ },
1867
+ {
1868
+ "epoch": 1.1548895208925836,
1869
+ "grad_norm": 1.5528831481933594,
1870
+ "learning_rate": 1.9966417111033913e-05,
1871
+ "loss": 1.013,
1872
+ "step": 2640
1873
+ },
1874
+ {
1875
+ "epoch": 1.1592649310872893,
1876
+ "grad_norm": 1.410082459449768,
1877
+ "learning_rate": 1.979296339207912e-05,
1878
+ "loss": 1.0464,
1879
+ "step": 2650
1880
+ },
1881
+ {
1882
+ "epoch": 1.1636403412819951,
1883
+ "grad_norm": 1.5580497980117798,
1884
+ "learning_rate": 1.961977130403595e-05,
1885
+ "loss": 1.0405,
1886
+ "step": 2660
1887
+ },
1888
+ {
1889
+ "epoch": 1.168015751476701,
1890
+ "grad_norm": 1.6045440435409546,
1891
+ "learning_rate": 1.9446849549052542e-05,
1892
+ "loss": 1.0094,
1893
+ "step": 2670
1894
+ },
1895
+ {
1896
+ "epoch": 1.1723911616714067,
1897
+ "grad_norm": 1.4971415996551514,
1898
+ "learning_rate": 1.9274206815693957e-05,
1899
+ "loss": 1.0706,
1900
+ "step": 2680
1901
+ },
1902
+ {
1903
+ "epoch": 1.1767665718661124,
1904
+ "grad_norm": 1.5157324075698853,
1905
+ "learning_rate": 1.9101851778505664e-05,
1906
+ "loss": 1.0354,
1907
+ "step": 2690
1908
+ },
1909
+ {
1910
+ "epoch": 1.1811419820608182,
1911
+ "grad_norm": 1.4750152826309204,
1912
+ "learning_rate": 1.8929793097577613e-05,
1913
+ "loss": 1.0663,
1914
+ "step": 2700
1915
+ },
1916
+ {
1917
+ "epoch": 1.185517392255524,
1918
+ "grad_norm": 1.6027971506118774,
1919
+ "learning_rate": 1.8758039418109167e-05,
1920
+ "loss": 1.0404,
1921
+ "step": 2710
1922
+ },
1923
+ {
1924
+ "epoch": 1.1898928024502298,
1925
+ "grad_norm": 1.4709988832473755,
1926
+ "learning_rate": 1.85865993699747e-05,
1927
+ "loss": 0.996,
1928
+ "step": 2720
1929
+ },
1930
+ {
1931
+ "epoch": 1.1942682126449355,
1932
+ "grad_norm": 1.4839427471160889,
1933
+ "learning_rate": 1.8415481567289954e-05,
1934
+ "loss": 1.0368,
1935
+ "step": 2730
1936
+ },
1937
+ {
1938
+ "epoch": 1.1986436228396413,
1939
+ "grad_norm": 1.5311963558197021,
1940
+ "learning_rate": 1.8244694607979265e-05,
1941
+ "loss": 1.0569,
1942
+ "step": 2740
1943
+ },
1944
+ {
1945
+ "epoch": 1.2030190330343469,
1946
+ "grad_norm": 1.4894174337387085,
1947
+ "learning_rate": 1.8074247073343508e-05,
1948
+ "loss": 1.0441,
1949
+ "step": 2750
1950
+ },
1951
+ {
1952
+ "epoch": 1.2073944432290526,
1953
+ "grad_norm": 1.5051078796386719,
1954
+ "learning_rate": 1.7904147527628978e-05,
1955
+ "loss": 1.0631,
1956
+ "step": 2760
1957
+ },
1958
+ {
1959
+ "epoch": 1.2117698534237584,
1960
+ "grad_norm": 1.6134063005447388,
1961
+ "learning_rate": 1.7734404517597004e-05,
1962
+ "loss": 1.0481,
1963
+ "step": 2770
1964
+ },
1965
+ {
1966
+ "epoch": 1.2161452636184642,
1967
+ "grad_norm": 1.4523193836212158,
1968
+ "learning_rate": 1.7565026572094563e-05,
1969
+ "loss": 1.0614,
1970
+ "step": 2780
1971
+ },
1972
+ {
1973
+ "epoch": 1.22052067381317,
1974
+ "grad_norm": 1.3861931562423706,
1975
+ "learning_rate": 1.7396022201625755e-05,
1976
+ "loss": 1.062,
1977
+ "step": 2790
1978
+ },
1979
+ {
1980
+ "epoch": 1.2248960840078758,
1981
+ "grad_norm": 1.4329195022583008,
1982
+ "learning_rate": 1.7227399897924128e-05,
1983
+ "loss": 1.0014,
1984
+ "step": 2800
1985
+ },
1986
+ {
1987
+ "epoch": 1.2292714942025815,
1988
+ "grad_norm": 1.4674146175384521,
1989
+ "learning_rate": 1.7059168133526043e-05,
1990
+ "loss": 1.0915,
1991
+ "step": 2810
1992
+ },
1993
+ {
1994
+ "epoch": 1.2336469043972873,
1995
+ "grad_norm": 1.4468815326690674,
1996
+ "learning_rate": 1.6891335361344978e-05,
1997
+ "loss": 1.0788,
1998
+ "step": 2820
1999
+ },
2000
+ {
2001
+ "epoch": 1.238022314591993,
2002
+ "grad_norm": 1.3832966089248657,
2003
+ "learning_rate": 1.6723910014246798e-05,
2004
+ "loss": 1.0282,
2005
+ "step": 2830
2006
+ },
2007
+ {
2008
+ "epoch": 1.2423977247866986,
2009
+ "grad_norm": 1.4221124649047852,
2010
+ "learning_rate": 1.6556900504625998e-05,
2011
+ "loss": 1.0688,
2012
+ "step": 2840
2013
+ },
2014
+ {
2015
+ "epoch": 1.2467731349814044,
2016
+ "grad_norm": 1.5301196575164795,
2017
+ "learning_rate": 1.6390315223983066e-05,
2018
+ "loss": 1.0247,
2019
+ "step": 2850
2020
+ },
2021
+ {
2022
+ "epoch": 1.2511485451761102,
2023
+ "grad_norm": 1.434435248374939,
2024
+ "learning_rate": 1.6224162542502857e-05,
2025
+ "loss": 1.0071,
2026
+ "step": 2860
2027
+ },
2028
+ {
2029
+ "epoch": 1.255523955370816,
2030
+ "grad_norm": 1.5031973123550415,
2031
+ "learning_rate": 1.6058450808633958e-05,
2032
+ "loss": 1.0898,
2033
+ "step": 2870
2034
+ },
2035
+ {
2036
+ "epoch": 1.2598993655655217,
2037
+ "grad_norm": 1.5583535432815552,
2038
+ "learning_rate": 1.589318834866928e-05,
2039
+ "loss": 1.0726,
2040
+ "step": 2880
2041
+ },
2042
+ {
2043
+ "epoch": 1.2642747757602275,
2044
+ "grad_norm": 1.5489450693130493,
2045
+ "learning_rate": 1.5728383466327684e-05,
2046
+ "loss": 1.0498,
2047
+ "step": 2890
2048
+ },
2049
+ {
2050
+ "epoch": 1.2686501859549333,
2051
+ "grad_norm": 1.3748371601104736,
2052
+ "learning_rate": 1.5564044442336755e-05,
2053
+ "loss": 1.0071,
2054
+ "step": 2900
2055
+ },
2056
+ {
2057
+ "epoch": 1.273025596149639,
2058
+ "grad_norm": 1.581483006477356,
2059
+ "learning_rate": 1.54001795340167e-05,
2060
+ "loss": 0.9992,
2061
+ "step": 2910
2062
+ },
2063
+ {
2064
+ "epoch": 1.2774010063443448,
2065
+ "grad_norm": 1.5674552917480469,
2066
+ "learning_rate": 1.5236796974865481e-05,
2067
+ "loss": 1.0497,
2068
+ "step": 2920
2069
+ },
2070
+ {
2071
+ "epoch": 1.2817764165390506,
2072
+ "grad_norm": 1.5625611543655396,
2073
+ "learning_rate": 1.5073904974145144e-05,
2074
+ "loss": 0.997,
2075
+ "step": 2930
2076
+ },
2077
+ {
2078
+ "epoch": 1.2861518267337564,
2079
+ "grad_norm": 1.625352382659912,
2080
+ "learning_rate": 1.4911511716469279e-05,
2081
+ "loss": 1.026,
2082
+ "step": 2940
2083
+ },
2084
+ {
2085
+ "epoch": 1.2905272369284622,
2086
+ "grad_norm": 1.4870202541351318,
2087
+ "learning_rate": 1.4749625361391815e-05,
2088
+ "loss": 1.0561,
2089
+ "step": 2950
2090
+ },
2091
+ {
2092
+ "epoch": 1.2949026471231677,
2093
+ "grad_norm": 1.551835060119629,
2094
+ "learning_rate": 1.4588254042997057e-05,
2095
+ "loss": 1.0484,
2096
+ "step": 2960
2097
+ },
2098
+ {
2099
+ "epoch": 1.2992780573178735,
2100
+ "grad_norm": 1.4249804019927979,
2101
+ "learning_rate": 1.4427405869490923e-05,
2102
+ "loss": 1.068,
2103
+ "step": 2970
2104
+ },
2105
+ {
2106
+ "epoch": 1.3036534675125793,
2107
+ "grad_norm": 1.5101299285888672,
2108
+ "learning_rate": 1.4267088922793615e-05,
2109
+ "loss": 1.0761,
2110
+ "step": 2980
2111
+ },
2112
+ {
2113
+ "epoch": 1.308028877707285,
2114
+ "grad_norm": 1.5725096464157104,
2115
+ "learning_rate": 1.4107311258133485e-05,
2116
+ "loss": 1.0459,
2117
+ "step": 2990
2118
+ },
2119
+ {
2120
+ "epoch": 1.3124042879019908,
2121
+ "grad_norm": 1.4517625570297241,
2122
+ "learning_rate": 1.3948080903642307e-05,
2123
+ "loss": 1.0429,
2124
+ "step": 3000
2125
+ },
2126
+ {
2127
+ "epoch": 1.3167796980966966,
2128
+ "grad_norm": 1.750517725944519,
2129
+ "learning_rate": 1.3789405859951893e-05,
2130
+ "loss": 1.0646,
2131
+ "step": 3010
2132
+ },
2133
+ {
2134
+ "epoch": 1.3211551082914024,
2135
+ "grad_norm": 1.3727548122406006,
2136
+ "learning_rate": 1.3631294099792136e-05,
2137
+ "loss": 1.0217,
2138
+ "step": 3020
2139
+ },
2140
+ {
2141
+ "epoch": 1.3255305184861081,
2142
+ "grad_norm": 1.5657787322998047,
2143
+ "learning_rate": 1.3473753567590372e-05,
2144
+ "loss": 1.0441,
2145
+ "step": 3030
2146
+ },
2147
+ {
2148
+ "epoch": 1.3299059286808137,
2149
+ "grad_norm": 1.4173895120620728,
2150
+ "learning_rate": 1.3316792179072202e-05,
2151
+ "loss": 1.0571,
2152
+ "step": 3040
2153
+ },
2154
+ {
2155
+ "epoch": 1.3342813388755195,
2156
+ "grad_norm": 1.4876666069030762,
2157
+ "learning_rate": 1.3160417820863807e-05,
2158
+ "loss": 1.1207,
2159
+ "step": 3050
2160
+ },
2161
+ {
2162
+ "epoch": 1.3386567490702252,
2163
+ "grad_norm": 1.635214924812317,
2164
+ "learning_rate": 1.3004638350095627e-05,
2165
+ "loss": 1.0501,
2166
+ "step": 3060
2167
+ },
2168
+ {
2169
+ "epoch": 1.343032159264931,
2170
+ "grad_norm": 1.4365153312683105,
2171
+ "learning_rate": 1.2849461594007622e-05,
2172
+ "loss": 1.0522,
2173
+ "step": 3070
2174
+ },
2175
+ {
2176
+ "epoch": 1.3474075694596368,
2177
+ "grad_norm": 1.570642352104187,
2178
+ "learning_rate": 1.2694895349555938e-05,
2179
+ "loss": 1.1029,
2180
+ "step": 3080
2181
+ },
2182
+ {
2183
+ "epoch": 1.3517829796543426,
2184
+ "grad_norm": 1.5404038429260254,
2185
+ "learning_rate": 1.2540947383021196e-05,
2186
+ "loss": 1.0097,
2187
+ "step": 3090
2188
+ },
2189
+ {
2190
+ "epoch": 1.3561583898490484,
2191
+ "grad_norm": 1.4297966957092285,
2192
+ "learning_rate": 1.2387625429618235e-05,
2193
+ "loss": 1.0823,
2194
+ "step": 3100
2195
+ },
2196
+ {
2197
+ "epoch": 1.3605338000437541,
2198
+ "grad_norm": 1.5374993085861206,
2199
+ "learning_rate": 1.2234937193107449e-05,
2200
+ "loss": 1.0511,
2201
+ "step": 3110
2202
+ },
2203
+ {
2204
+ "epoch": 1.36490921023846,
2205
+ "grad_norm": 1.418187141418457,
2206
+ "learning_rate": 1.208289034540774e-05,
2207
+ "loss": 1.0097,
2208
+ "step": 3120
2209
+ },
2210
+ {
2211
+ "epoch": 1.3692846204331657,
2212
+ "grad_norm": 1.599236249923706,
2213
+ "learning_rate": 1.1931492526210988e-05,
2214
+ "loss": 1.0431,
2215
+ "step": 3130
2216
+ },
2217
+ {
2218
+ "epoch": 1.3736600306278715,
2219
+ "grad_norm": 1.4665392637252808,
2220
+ "learning_rate": 1.1780751342598254e-05,
2221
+ "loss": 1.0091,
2222
+ "step": 3140
2223
+ },
2224
+ {
2225
+ "epoch": 1.3780354408225772,
2226
+ "grad_norm": 1.475703239440918,
2227
+ "learning_rate": 1.1630674368657476e-05,
2228
+ "loss": 1.0821,
2229
+ "step": 3150
2230
+ },
2231
+ {
2232
+ "epoch": 1.382410851017283,
2233
+ "grad_norm": 1.515609622001648,
2234
+ "learning_rate": 1.1481269145102985e-05,
2235
+ "loss": 1.0217,
2236
+ "step": 3160
2237
+ },
2238
+ {
2239
+ "epoch": 1.3867862612119886,
2240
+ "grad_norm": 1.577500820159912,
2241
+ "learning_rate": 1.1332543178896577e-05,
2242
+ "loss": 1.0153,
2243
+ "step": 3170
2244
+ },
2245
+ {
2246
+ "epoch": 1.3911616714066943,
2247
+ "grad_norm": 1.5948362350463867,
2248
+ "learning_rate": 1.1184503942870295e-05,
2249
+ "loss": 1.0654,
2250
+ "step": 3180
2251
+ },
2252
+ {
2253
+ "epoch": 1.3955370816014,
2254
+ "grad_norm": 1.543228268623352,
2255
+ "learning_rate": 1.1037158875351026e-05,
2256
+ "loss": 1.0484,
2257
+ "step": 3190
2258
+ },
2259
+ {
2260
+ "epoch": 1.3999124917961059,
2261
+ "grad_norm": 1.5313066244125366,
2262
+ "learning_rate": 1.0890515379786664e-05,
2263
+ "loss": 1.0771,
2264
+ "step": 3200
2265
+ },
2266
+ {
2267
+ "epoch": 1.4042879019908117,
2268
+ "grad_norm": 1.5253814458847046,
2269
+ "learning_rate": 1.0744580824374217e-05,
2270
+ "loss": 1.0013,
2271
+ "step": 3210
2272
+ },
2273
+ {
2274
+ "epoch": 1.4086633121855174,
2275
+ "grad_norm": 1.5002059936523438,
2276
+ "learning_rate": 1.0599362541689493e-05,
2277
+ "loss": 1.0223,
2278
+ "step": 3220
2279
+ },
2280
+ {
2281
+ "epoch": 1.4130387223802232,
2282
+ "grad_norm": 1.4917947053909302,
2283
+ "learning_rate": 1.0454867828318742e-05,
2284
+ "loss": 1.0595,
2285
+ "step": 3230
2286
+ },
2287
+ {
2288
+ "epoch": 1.4174141325749288,
2289
+ "grad_norm": 1.52601158618927,
2290
+ "learning_rate": 1.0311103944492015e-05,
2291
+ "loss": 1.0335,
2292
+ "step": 3240
2293
+ },
2294
+ {
2295
+ "epoch": 1.4217895427696345,
2296
+ "grad_norm": 1.5720328092575073,
2297
+ "learning_rate": 1.0168078113718327e-05,
2298
+ "loss": 1.0451,
2299
+ "step": 3250
2300
+ },
2301
+ {
2302
+ "epoch": 1.4261649529643403,
2303
+ "grad_norm": 1.5480356216430664,
2304
+ "learning_rate": 1.0025797522422778e-05,
2305
+ "loss": 1.021,
2306
+ "step": 3260
2307
+ },
2308
+ {
2309
+ "epoch": 1.430540363159046,
2310
+ "grad_norm": 1.5697144269943237,
2311
+ "learning_rate": 9.884269319585402e-06,
2312
+ "loss": 1.0263,
2313
+ "step": 3270
2314
+ },
2315
+ {
2316
+ "epoch": 1.4349157733537519,
2317
+ "grad_norm": 1.5155223608016968,
2318
+ "learning_rate": 9.743500616382012e-06,
2319
+ "loss": 1.0562,
2320
+ "step": 3280
2321
+ },
2322
+ {
2323
+ "epoch": 1.4392911835484576,
2324
+ "grad_norm": 1.5573937892913818,
2325
+ "learning_rate": 9.603498485826848e-06,
2326
+ "loss": 1.0509,
2327
+ "step": 3290
2328
+ },
2329
+ {
2330
+ "epoch": 1.4436665937431634,
2331
+ "grad_norm": 1.3795148134231567,
2332
+ "learning_rate": 9.464269962417233e-06,
2333
+ "loss": 1.0498,
2334
+ "step": 3300
2335
+ },
2336
+ {
2337
+ "epoch": 1.4480420039378692,
2338
+ "grad_norm": 1.496437430381775,
2339
+ "learning_rate": 9.325822041780105e-06,
2340
+ "loss": 1.0061,
2341
+ "step": 3310
2342
+ },
2343
+ {
2344
+ "epoch": 1.452417414132575,
2345
+ "grad_norm": 1.526340126991272,
2346
+ "learning_rate": 9.188161680320486e-06,
2347
+ "loss": 1.0291,
2348
+ "step": 3320
2349
+ },
2350
+ {
2351
+ "epoch": 1.4567928243272807,
2352
+ "grad_norm": 1.4637991189956665,
2353
+ "learning_rate": 9.051295794872008e-06,
2354
+ "loss": 1.0587,
2355
+ "step": 3330
2356
+ },
2357
+ {
2358
+ "epoch": 1.4611682345219865,
2359
+ "grad_norm": 1.5240123271942139,
2360
+ "learning_rate": 8.915231262349316e-06,
2361
+ "loss": 1.0013,
2362
+ "step": 3340
2363
+ },
2364
+ {
2365
+ "epoch": 1.4655436447166923,
2366
+ "grad_norm": 1.3594683408737183,
2367
+ "learning_rate": 8.77997491940259e-06,
2368
+ "loss": 0.9967,
2369
+ "step": 3350
2370
+ },
2371
+ {
2372
+ "epoch": 1.469919054911398,
2373
+ "grad_norm": 1.6217098236083984,
2374
+ "learning_rate": 8.645533562073971e-06,
2375
+ "loss": 1.0683,
2376
+ "step": 3360
2377
+ },
2378
+ {
2379
+ "epoch": 1.4742944651061036,
2380
+ "grad_norm": 1.5475493669509888,
2381
+ "learning_rate": 8.51191394545615e-06,
2382
+ "loss": 1.0166,
2383
+ "step": 3370
2384
+ },
2385
+ {
2386
+ "epoch": 1.4786698753008094,
2387
+ "grad_norm": 1.4708356857299805,
2388
+ "learning_rate": 8.379122783352927e-06,
2389
+ "loss": 1.0105,
2390
+ "step": 3380
2391
+ },
2392
+ {
2393
+ "epoch": 1.4830452854955152,
2394
+ "grad_norm": 1.5092549324035645,
2395
+ "learning_rate": 8.247166747941846e-06,
2396
+ "loss": 1.0416,
2397
+ "step": 3390
2398
+ },
2399
+ {
2400
+ "epoch": 1.487420695690221,
2401
+ "grad_norm": 1.5428940057754517,
2402
+ "learning_rate": 8.116052469438979e-06,
2403
+ "loss": 1.0268,
2404
+ "step": 3400
2405
+ },
2406
+ {
2407
+ "epoch": 1.4917961058849267,
2408
+ "grad_norm": 1.4949884414672852,
2409
+ "learning_rate": 7.985786535765794e-06,
2410
+ "loss": 1.037,
2411
+ "step": 3410
2412
+ },
2413
+ {
2414
+ "epoch": 1.4961715160796325,
2415
+ "grad_norm": 1.4505797624588013,
2416
+ "learning_rate": 7.856375492218127e-06,
2417
+ "loss": 1.0374,
2418
+ "step": 3420
2419
+ },
2420
+ {
2421
+ "epoch": 1.500546926274338,
2422
+ "grad_norm": 1.6311450004577637,
2423
+ "learning_rate": 7.727825841137282e-06,
2424
+ "loss": 1.0337,
2425
+ "step": 3430
2426
+ },
2427
+ {
2428
+ "epoch": 1.5049223364690438,
2429
+ "grad_norm": 1.4141907691955566,
2430
+ "learning_rate": 7.6001440415833705e-06,
2431
+ "loss": 0.9676,
2432
+ "step": 3440
2433
+ },
2434
+ {
2435
+ "epoch": 1.5092977466637496,
2436
+ "grad_norm": 1.499178171157837,
2437
+ "learning_rate": 7.473336509010742e-06,
2438
+ "loss": 1.0763,
2439
+ "step": 3450
2440
+ },
2441
+ {
2442
+ "epoch": 1.5136731568584554,
2443
+ "grad_norm": 1.3310422897338867,
2444
+ "learning_rate": 7.347409614945621e-06,
2445
+ "loss": 0.9934,
2446
+ "step": 3460
2447
+ },
2448
+ {
2449
+ "epoch": 1.5180485670531612,
2450
+ "grad_norm": 1.5936180353164673,
2451
+ "learning_rate": 7.2223696866659865e-06,
2452
+ "loss": 1.0169,
2453
+ "step": 3470
2454
+ },
2455
+ {
2456
+ "epoch": 1.522423977247867,
2457
+ "grad_norm": 1.4071223735809326,
2458
+ "learning_rate": 7.098223006883667e-06,
2459
+ "loss": 1.0532,
2460
+ "step": 3480
2461
+ },
2462
+ {
2463
+ "epoch": 1.5267993874425727,
2464
+ "grad_norm": 1.381949543952942,
2465
+ "learning_rate": 6.974975813428622e-06,
2466
+ "loss": 0.949,
2467
+ "step": 3490
2468
+ },
2469
+ {
2470
+ "epoch": 1.5311747976372785,
2471
+ "grad_norm": 1.548047661781311,
2472
+ "learning_rate": 6.852634298935554e-06,
2473
+ "loss": 1.0571,
2474
+ "step": 3500
2475
+ },
2476
+ {
2477
+ "epoch": 1.5355502078319843,
2478
+ "grad_norm": 1.6835612058639526,
2479
+ "learning_rate": 6.73120461053274e-06,
2480
+ "loss": 1.0665,
2481
+ "step": 3510
2482
+ },
2483
+ {
2484
+ "epoch": 1.53992561802669,
2485
+ "grad_norm": 1.5767420530319214,
2486
+ "learning_rate": 6.610692849533176e-06,
2487
+ "loss": 1.0711,
2488
+ "step": 3520
2489
+ },
2490
+ {
2491
+ "epoch": 1.5443010282213958,
2492
+ "grad_norm": 1.6286526918411255,
2493
+ "learning_rate": 6.491105071127984e-06,
2494
+ "loss": 1.0837,
2495
+ "step": 3530
2496
+ },
2497
+ {
2498
+ "epoch": 1.5486764384161016,
2499
+ "grad_norm": 1.5266960859298706,
2500
+ "learning_rate": 6.372447284082186e-06,
2501
+ "loss": 1.0329,
2502
+ "step": 3540
2503
+ },
2504
+ {
2505
+ "epoch": 1.5530518486108074,
2506
+ "grad_norm": 1.5030903816223145,
2507
+ "learning_rate": 6.254725450432819e-06,
2508
+ "loss": 1.0385,
2509
+ "step": 3550
2510
+ },
2511
+ {
2512
+ "epoch": 1.5574272588055131,
2513
+ "grad_norm": 1.542777419090271,
2514
+ "learning_rate": 6.137945485189292e-06,
2515
+ "loss": 1.0784,
2516
+ "step": 3560
2517
+ },
2518
+ {
2519
+ "epoch": 1.561802669000219,
2520
+ "grad_norm": 1.48823082447052,
2521
+ "learning_rate": 6.022113256036268e-06,
2522
+ "loss": 1.0194,
2523
+ "step": 3570
2524
+ },
2525
+ {
2526
+ "epoch": 1.5661780791949247,
2527
+ "grad_norm": 1.651016116142273,
2528
+ "learning_rate": 5.907234583038781e-06,
2529
+ "loss": 1.0996,
2530
+ "step": 3580
2531
+ },
2532
+ {
2533
+ "epoch": 1.5705534893896302,
2534
+ "grad_norm": 1.4115656614303589,
2535
+ "learning_rate": 5.793315238349834e-06,
2536
+ "loss": 1.0681,
2537
+ "step": 3590
2538
+ },
2539
+ {
2540
+ "epoch": 1.574928899584336,
2541
+ "grad_norm": 1.5791130065917969,
2542
+ "learning_rate": 5.68036094592034e-06,
2543
+ "loss": 1.048,
2544
+ "step": 3600
2545
+ },
2546
+ {
2547
+ "epoch": 1.5793043097790418,
2548
+ "grad_norm": 1.6106353998184204,
2549
+ "learning_rate": 5.568377381211548e-06,
2550
+ "loss": 1.0411,
2551
+ "step": 3610
2552
+ },
2553
+ {
2554
+ "epoch": 1.5836797199737476,
2555
+ "grad_norm": 1.461083173751831,
2556
+ "learning_rate": 5.457370170909878e-06,
2557
+ "loss": 1.0249,
2558
+ "step": 3620
2559
+ },
2560
+ {
2561
+ "epoch": 1.5880551301684533,
2562
+ "grad_norm": 1.4923583269119263,
2563
+ "learning_rate": 5.347344892644171e-06,
2564
+ "loss": 1.0462,
2565
+ "step": 3630
2566
+ },
2567
+ {
2568
+ "epoch": 1.592430540363159,
2569
+ "grad_norm": 1.4730093479156494,
2570
+ "learning_rate": 5.238307074705481e-06,
2571
+ "loss": 0.9946,
2572
+ "step": 3640
2573
+ },
2574
+ {
2575
+ "epoch": 1.5968059505578647,
2576
+ "grad_norm": 1.626094937324524,
2577
+ "learning_rate": 5.130262195769273e-06,
2578
+ "loss": 1.0611,
2579
+ "step": 3650
2580
+ },
2581
+ {
2582
+ "epoch": 1.6011813607525704,
2583
+ "grad_norm": 1.3962546586990356,
2584
+ "learning_rate": 5.023215684620159e-06,
2585
+ "loss": 1.0505,
2586
+ "step": 3660
2587
+ },
2588
+ {
2589
+ "epoch": 1.6055567709472762,
2590
+ "grad_norm": 1.587723970413208,
2591
+ "learning_rate": 4.917172919879098e-06,
2592
+ "loss": 0.9735,
2593
+ "step": 3670
2594
+ },
2595
+ {
2596
+ "epoch": 1.609932181141982,
2597
+ "grad_norm": 1.5360171794891357,
2598
+ "learning_rate": 4.812139229733179e-06,
2599
+ "loss": 1.0593,
2600
+ "step": 3680
2601
+ },
2602
+ {
2603
+ "epoch": 1.6143075913366878,
2604
+ "grad_norm": 1.462829351425171,
2605
+ "learning_rate": 4.708119891667892e-06,
2606
+ "loss": 1.0435,
2607
+ "step": 3690
2608
+ },
2609
+ {
2610
+ "epoch": 1.6186830015313936,
2611
+ "grad_norm": 1.5362554788589478,
2612
+ "learning_rate": 4.605120132201932e-06,
2613
+ "loss": 1.0653,
2614
+ "step": 3700
2615
+ },
2616
+ {
2617
+ "epoch": 1.6230584117260993,
2618
+ "grad_norm": 1.4747408628463745,
2619
+ "learning_rate": 4.503145126624631e-06,
2620
+ "loss": 1.0539,
2621
+ "step": 3710
2622
+ },
2623
+ {
2624
+ "epoch": 1.627433821920805,
2625
+ "grad_norm": 1.511655330657959,
2626
+ "learning_rate": 4.402199998735896e-06,
2627
+ "loss": 1.0921,
2628
+ "step": 3720
2629
+ },
2630
+ {
2631
+ "epoch": 1.6318092321155109,
2632
+ "grad_norm": 1.5355191230773926,
2633
+ "learning_rate": 4.302289820588762e-06,
2634
+ "loss": 1.0182,
2635
+ "step": 3730
2636
+ },
2637
+ {
2638
+ "epoch": 1.6361846423102167,
2639
+ "grad_norm": 1.3255157470703125,
2640
+ "learning_rate": 4.203419612234536e-06,
2641
+ "loss": 1.0586,
2642
+ "step": 3740
2643
+ },
2644
+ {
2645
+ "epoch": 1.6405600525049224,
2646
+ "grad_norm": 1.4897997379302979,
2647
+ "learning_rate": 4.105594341470592e-06,
2648
+ "loss": 1.0022,
2649
+ "step": 3750
2650
+ },
2651
+ {
2652
+ "epoch": 1.6449354626996282,
2653
+ "grad_norm": 1.5675077438354492,
2654
+ "learning_rate": 4.00881892359074e-06,
2655
+ "loss": 1.0394,
2656
+ "step": 3760
2657
+ },
2658
+ {
2659
+ "epoch": 1.649310872894334,
2660
+ "grad_norm": 1.46114182472229,
2661
+ "learning_rate": 3.913098221138237e-06,
2662
+ "loss": 1.0464,
2663
+ "step": 3770
2664
+ },
2665
+ {
2666
+ "epoch": 1.6536862830890398,
2667
+ "grad_norm": 1.4704811573028564,
2668
+ "learning_rate": 3.818437043661497e-06,
2669
+ "loss": 1.0428,
2670
+ "step": 3780
2671
+ },
2672
+ {
2673
+ "epoch": 1.6580616932837453,
2674
+ "grad_norm": 1.493815302848816,
2675
+ "learning_rate": 3.724840147472422e-06,
2676
+ "loss": 1.0717,
2677
+ "step": 3790
2678
+ },
2679
+ {
2680
+ "epoch": 1.662437103478451,
2681
+ "grad_norm": 1.392871618270874,
2682
+ "learning_rate": 3.6323122354074033e-06,
2683
+ "loss": 0.9971,
2684
+ "step": 3800
2685
+ },
2686
+ {
2687
+ "epoch": 1.6668125136731569,
2688
+ "grad_norm": 1.5616687536239624,
2689
+ "learning_rate": 3.5408579565910344e-06,
2690
+ "loss": 1.0498,
2691
+ "step": 3810
2692
+ },
2693
+ {
2694
+ "epoch": 1.6711879238678626,
2695
+ "grad_norm": 1.5294009447097778,
2696
+ "learning_rate": 3.450481906202524e-06,
2697
+ "loss": 1.0721,
2698
+ "step": 3820
2699
+ },
2700
+ {
2701
+ "epoch": 1.6755633340625684,
2702
+ "grad_norm": 1.541881799697876,
2703
+ "learning_rate": 3.3611886252448017e-06,
2704
+ "loss": 1.0331,
2705
+ "step": 3830
2706
+ },
2707
+ {
2708
+ "epoch": 1.679938744257274,
2709
+ "grad_norm": 1.4998458623886108,
2710
+ "learning_rate": 3.2729826003163323e-06,
2711
+ "loss": 0.9996,
2712
+ "step": 3840
2713
+ },
2714
+ {
2715
+ "epoch": 1.6843141544519797,
2716
+ "grad_norm": 1.4179540872573853,
2717
+ "learning_rate": 3.1858682633857105e-06,
2718
+ "loss": 1.0467,
2719
+ "step": 3850
2720
+ },
2721
+ {
2722
+ "epoch": 1.6886895646466855,
2723
+ "grad_norm": 1.5790250301361084,
2724
+ "learning_rate": 3.0998499915689733e-06,
2725
+ "loss": 1.0415,
2726
+ "step": 3860
2727
+ },
2728
+ {
2729
+ "epoch": 1.6930649748413913,
2730
+ "grad_norm": 1.5594815015792847,
2731
+ "learning_rate": 3.0149321069096375e-06,
2732
+ "loss": 1.0491,
2733
+ "step": 3870
2734
+ },
2735
+ {
2736
+ "epoch": 1.697440385036097,
2737
+ "grad_norm": 1.5254184007644653,
2738
+ "learning_rate": 2.9311188761615703e-06,
2739
+ "loss": 1.0132,
2740
+ "step": 3880
2741
+ },
2742
+ {
2743
+ "epoch": 1.7018157952308028,
2744
+ "grad_norm": 1.5314863920211792,
2745
+ "learning_rate": 2.8484145105745903e-06,
2746
+ "loss": 1.0049,
2747
+ "step": 3890
2748
+ },
2749
+ {
2750
+ "epoch": 1.7061912054255086,
2751
+ "grad_norm": 1.608102798461914,
2752
+ "learning_rate": 2.7668231656828775e-06,
2753
+ "loss": 1.0627,
2754
+ "step": 3900
2755
+ },
2756
+ {
2757
+ "epoch": 1.7105666156202144,
2758
+ "grad_norm": 1.4776244163513184,
2759
+ "learning_rate": 2.6863489410961505e-06,
2760
+ "loss": 1.0374,
2761
+ "step": 3910
2762
+ },
2763
+ {
2764
+ "epoch": 1.7149420258149202,
2765
+ "grad_norm": 1.6031432151794434,
2766
+ "learning_rate": 2.606995880293717e-06,
2767
+ "loss": 1.1048,
2768
+ "step": 3920
2769
+ },
2770
+ {
2771
+ "epoch": 1.719317436009626,
2772
+ "grad_norm": 1.5214728116989136,
2773
+ "learning_rate": 2.5287679704212836e-06,
2774
+ "loss": 1.0272,
2775
+ "step": 3930
2776
+ },
2777
+ {
2778
+ "epoch": 1.7236928462043317,
2779
+ "grad_norm": 1.4273405075073242,
2780
+ "learning_rate": 2.451669142090615e-06,
2781
+ "loss": 1.0509,
2782
+ "step": 3940
2783
+ },
2784
+ {
2785
+ "epoch": 1.7280682563990375,
2786
+ "grad_norm": 1.5345888137817383,
2787
+ "learning_rate": 2.3757032691820476e-06,
2788
+ "loss": 1.0378,
2789
+ "step": 3950
2790
+ },
2791
+ {
2792
+ "epoch": 1.7324436665937433,
2793
+ "grad_norm": 1.635636329650879,
2794
+ "learning_rate": 2.3008741686498498e-06,
2795
+ "loss": 1.0308,
2796
+ "step": 3960
2797
+ },
2798
+ {
2799
+ "epoch": 1.736819076788449,
2800
+ "grad_norm": 1.5404716730117798,
2801
+ "learning_rate": 2.2271856003304253e-06,
2802
+ "loss": 1.054,
2803
+ "step": 3970
2804
+ },
2805
+ {
2806
+ "epoch": 1.7411944869831548,
2807
+ "grad_norm": 1.5047839879989624,
2808
+ "learning_rate": 2.154641266753393e-06,
2809
+ "loss": 1.0234,
2810
+ "step": 3980
2811
+ },
2812
+ {
2813
+ "epoch": 1.7455698971778604,
2814
+ "grad_norm": 1.4826009273529053,
2815
+ "learning_rate": 2.083244812955573e-06,
2816
+ "loss": 1.064,
2817
+ "step": 3990
2818
+ },
2819
+ {
2820
+ "epoch": 1.7499453073725662,
2821
+ "grad_norm": 1.5155521631240845,
2822
+ "learning_rate": 2.012999826297823e-06,
2823
+ "loss": 1.0188,
2824
+ "step": 4000
2825
+ },
2826
+ {
2827
+ "epoch": 1.754320717567272,
2828
+ "grad_norm": 1.5202479362487793,
2829
+ "learning_rate": 1.9439098362847825e-06,
2830
+ "loss": 1.0179,
2831
+ "step": 4010
2832
+ },
2833
+ {
2834
+ "epoch": 1.7586961277619777,
2835
+ "grad_norm": 1.3785141706466675,
2836
+ "learning_rate": 1.8759783143875443e-06,
2837
+ "loss": 1.0683,
2838
+ "step": 4020
2839
+ },
2840
+ {
2841
+ "epoch": 1.7630715379566835,
2842
+ "grad_norm": 1.4348698854446411,
2843
+ "learning_rate": 1.8092086738692282e-06,
2844
+ "loss": 1.0171,
2845
+ "step": 4030
2846
+ },
2847
+ {
2848
+ "epoch": 1.767446948151389,
2849
+ "grad_norm": 1.4248477220535278,
2850
+ "learning_rate": 1.7436042696134747e-06,
2851
+ "loss": 1.0062,
2852
+ "step": 4040
2853
+ },
2854
+ {
2855
+ "epoch": 1.7718223583460948,
2856
+ "grad_norm": 1.50611412525177,
2857
+ "learning_rate": 1.6791683979558686e-06,
2858
+ "loss": 1.0302,
2859
+ "step": 4050
2860
+ },
2861
+ {
2862
+ "epoch": 1.7761977685408006,
2863
+ "grad_norm": 1.5289087295532227,
2864
+ "learning_rate": 1.6159042965183335e-06,
2865
+ "loss": 1.006,
2866
+ "step": 4060
2867
+ },
2868
+ {
2869
+ "epoch": 1.7805731787355064,
2870
+ "grad_norm": 1.319069266319275,
2871
+ "learning_rate": 1.5538151440464332e-06,
2872
+ "loss": 0.9973,
2873
+ "step": 4070
2874
+ },
2875
+ {
2876
+ "epoch": 1.7849485889302121,
2877
+ "grad_norm": 1.4898905754089355,
2878
+ "learning_rate": 1.4929040602496586e-06,
2879
+ "loss": 1.047,
2880
+ "step": 4080
2881
+ },
2882
+ {
2883
+ "epoch": 1.789323999124918,
2884
+ "grad_norm": 1.5255054235458374,
2885
+ "learning_rate": 1.4331741056446968e-06,
2886
+ "loss": 1.0525,
2887
+ "step": 4090
2888
+ },
2889
+ {
2890
+ "epoch": 1.7936994093196237,
2891
+ "grad_norm": 1.536674976348877,
2892
+ "learning_rate": 1.3746282814016242e-06,
2893
+ "loss": 1.0171,
2894
+ "step": 4100
2895
+ },
2896
+ {
2897
+ "epoch": 1.7980748195143295,
2898
+ "grad_norm": 1.4357112646102905,
2899
+ "learning_rate": 1.3172695291931353e-06,
2900
+ "loss": 1.0532,
2901
+ "step": 4110
2902
+ },
2903
+ {
2904
+ "epoch": 1.8024502297090352,
2905
+ "grad_norm": 1.4620466232299805,
2906
+ "learning_rate": 1.2611007310467049e-06,
2907
+ "loss": 1.0177,
2908
+ "step": 4120
2909
+ },
2910
+ {
2911
+ "epoch": 1.806825639903741,
2912
+ "grad_norm": 1.5015560388565063,
2913
+ "learning_rate": 1.2061247091998211e-06,
2914
+ "loss": 1.0575,
2915
+ "step": 4130
2916
+ },
2917
+ {
2918
+ "epoch": 1.8112010500984468,
2919
+ "grad_norm": 1.4859633445739746,
2920
+ "learning_rate": 1.1523442259581435e-06,
2921
+ "loss": 1.0373,
2922
+ "step": 4140
2923
+ },
2924
+ {
2925
+ "epoch": 1.8155764602931526,
2926
+ "grad_norm": 1.6235337257385254,
2927
+ "learning_rate": 1.0997619835567241e-06,
2928
+ "loss": 1.0727,
2929
+ "step": 4150
2930
+ },
2931
+ {
2932
+ "epoch": 1.8199518704878583,
2933
+ "grad_norm": 1.6077338457107544,
2934
+ "learning_rate": 1.0483806240242366e-06,
2935
+ "loss": 1.0183,
2936
+ "step": 4160
2937
+ },
2938
+ {
2939
+ "epoch": 1.8243272806825641,
2940
+ "grad_norm": 1.5733646154403687,
2941
+ "learning_rate": 9.982027290502238e-07,
2942
+ "loss": 1.0867,
2943
+ "step": 4170
2944
+ },
2945
+ {
2946
+ "epoch": 1.8287026908772699,
2947
+ "grad_norm": 1.4715242385864258,
2948
+ "learning_rate": 9.492308198553707e-07,
2949
+ "loss": 1.0763,
2950
+ "step": 4180
2951
+ },
2952
+ {
2953
+ "epoch": 1.8330781010719757,
2954
+ "grad_norm": 1.5703119039535522,
2955
+ "learning_rate": 9.014673570648253e-07,
2956
+ "loss": 1.0661,
2957
+ "step": 4190
2958
+ },
2959
+ {
2960
+ "epoch": 1.8374535112666812,
2961
+ "grad_norm": 1.4015430212020874,
2962
+ "learning_rate": 8.549147405845781e-07,
2963
+ "loss": 1.0542,
2964
+ "step": 4200
2965
+ },
2966
+ {
2967
+ "epoch": 1.841828921461387,
2968
+ "grad_norm": 1.6461395025253296,
2969
+ "learning_rate": 8.095753094808506e-07,
2970
+ "loss": 1.0412,
2971
+ "step": 4210
2972
+ },
2973
+ {
2974
+ "epoch": 1.8462043316560928,
2975
+ "grad_norm": 1.4549918174743652,
2976
+ "learning_rate": 7.654513418625941e-07,
2977
+ "loss": 0.9894,
2978
+ "step": 4220
2979
+ },
2980
+ {
2981
+ "epoch": 1.8505797418507985,
2982
+ "grad_norm": 1.447482705116272,
2983
+ "learning_rate": 7.225450547670126e-07,
2984
+ "loss": 1.0665,
2985
+ "step": 4230
2986
+ },
2987
+ {
2988
+ "epoch": 1.8549551520455043,
2989
+ "grad_norm": 1.479117512702942,
2990
+ "learning_rate": 6.808586040481651e-07,
2991
+ "loss": 1.0133,
2992
+ "step": 4240
2993
+ },
2994
+ {
2995
+ "epoch": 1.8593305622402099,
2996
+ "grad_norm": 1.3185451030731201,
2997
+ "learning_rate": 6.403940842686474e-07,
2998
+ "loss": 1.0564,
2999
+ "step": 4250
3000
+ },
3001
+ {
3002
+ "epoch": 1.8637059724349156,
3003
+ "grad_norm": 1.5025280714035034,
3004
+ "learning_rate": 6.011535285943392e-07,
3005
+ "loss": 0.9987,
3006
+ "step": 4260
3007
+ },
3008
+ {
3009
+ "epoch": 1.8680813826296214,
3010
+ "grad_norm": 1.4831477403640747,
3011
+ "learning_rate": 5.631389086922678e-07,
3012
+ "loss": 1.055,
3013
+ "step": 4270
3014
+ },
3015
+ {
3016
+ "epoch": 1.8724567928243272,
3017
+ "grad_norm": 1.4341115951538086,
3018
+ "learning_rate": 5.263521346315192e-07,
3019
+ "loss": 1.0502,
3020
+ "step": 4280
3021
+ },
3022
+ {
3023
+ "epoch": 1.876832203019033,
3024
+ "grad_norm": 1.3913581371307373,
3025
+ "learning_rate": 4.907950547872686e-07,
3026
+ "loss": 1.0273,
3027
+ "step": 4290
3028
+ },
3029
+ {
3030
+ "epoch": 1.8812076132137387,
3031
+ "grad_norm": 1.5028200149536133,
3032
+ "learning_rate": 4.564694557479238e-07,
3033
+ "loss": 1.0131,
3034
+ "step": 4300
3035
+ },
3036
+ {
3037
+ "epoch": 1.8855830234084445,
3038
+ "grad_norm": 1.5376793146133423,
3039
+ "learning_rate": 4.2337706222533856e-07,
3040
+ "loss": 1.0292,
3041
+ "step": 4310
3042
+ },
3043
+ {
3044
+ "epoch": 1.8899584336031503,
3045
+ "grad_norm": 1.5637511014938354,
3046
+ "learning_rate": 3.915195369681629e-07,
3047
+ "loss": 1.0262,
3048
+ "step": 4320
3049
+ },
3050
+ {
3051
+ "epoch": 1.894333843797856,
3052
+ "grad_norm": 1.5448585748672485,
3053
+ "learning_rate": 3.608984806782928e-07,
3054
+ "loss": 1.0492,
3055
+ "step": 4330
3056
+ },
3057
+ {
3058
+ "epoch": 1.8987092539925619,
3059
+ "grad_norm": 1.4419684410095215,
3060
+ "learning_rate": 3.315154319304431e-07,
3061
+ "loss": 1.0724,
3062
+ "step": 4340
3063
+ },
3064
+ {
3065
+ "epoch": 1.9030846641872676,
3066
+ "grad_norm": 1.4939939975738525,
3067
+ "learning_rate": 3.033718670948482e-07,
3068
+ "loss": 1.0234,
3069
+ "step": 4350
3070
+ },
3071
+ {
3072
+ "epoch": 1.9074600743819734,
3073
+ "grad_norm": 1.4496331214904785,
3074
+ "learning_rate": 2.764692002630631e-07,
3075
+ "loss": 1.0371,
3076
+ "step": 4360
3077
+ },
3078
+ {
3079
+ "epoch": 1.9118354845766792,
3080
+ "grad_norm": 1.5224913358688354,
3081
+ "learning_rate": 2.5080878317693125e-07,
3082
+ "loss": 1.067,
3083
+ "step": 4370
3084
+ },
3085
+ {
3086
+ "epoch": 1.916210894771385,
3087
+ "grad_norm": 1.3078250885009766,
3088
+ "learning_rate": 2.2639190516065277e-07,
3089
+ "loss": 1.015,
3090
+ "step": 4380
3091
+ },
3092
+ {
3093
+ "epoch": 1.9205863049660907,
3094
+ "grad_norm": 1.5351719856262207,
3095
+ "learning_rate": 2.032197930560059e-07,
3096
+ "loss": 1.0435,
3097
+ "step": 4390
3098
+ },
3099
+ {
3100
+ "epoch": 1.9249617151607963,
3101
+ "grad_norm": 1.3579761981964111,
3102
+ "learning_rate": 1.812936111607072e-07,
3103
+ "loss": 0.9982,
3104
+ "step": 4400
3105
+ },
3106
+ {
3107
+ "epoch": 1.929337125355502,
3108
+ "grad_norm": 1.4030203819274902,
3109
+ "learning_rate": 1.6061446116990008e-07,
3110
+ "loss": 1.0374,
3111
+ "step": 4410
3112
+ },
3113
+ {
3114
+ "epoch": 1.9337125355502078,
3115
+ "grad_norm": 1.5246331691741943,
3116
+ "learning_rate": 1.4118338212081028e-07,
3117
+ "loss": 1.0612,
3118
+ "step": 4420
3119
+ },
3120
+ {
3121
+ "epoch": 1.9380879457449136,
3122
+ "grad_norm": 1.4720394611358643,
3123
+ "learning_rate": 1.2300135034052916e-07,
3124
+ "loss": 1.084,
3125
+ "step": 4430
3126
+ },
3127
+ {
3128
+ "epoch": 1.9424633559396194,
3129
+ "grad_norm": 1.529296875,
3130
+ "learning_rate": 1.0606927939696976e-07,
3131
+ "loss": 1.0421,
3132
+ "step": 4440
3133
+ },
3134
+ {
3135
+ "epoch": 1.946838766134325,
3136
+ "grad_norm": 1.4124305248260498,
3137
+ "learning_rate": 9.03880200529561e-08,
3138
+ "loss": 1.0183,
3139
+ "step": 4450
3140
+ },
3141
+ {
3142
+ "epoch": 1.9512141763290307,
3143
+ "grad_norm": 1.4209787845611572,
3144
+ "learning_rate": 7.59583602234687e-08,
3145
+ "loss": 1.0359,
3146
+ "step": 4460
3147
+ },
3148
+ {
3149
+ "epoch": 1.9555895865237365,
3150
+ "grad_norm": 1.4830424785614014,
3151
+ "learning_rate": 6.27810249360733e-08,
3152
+ "loss": 1.0425,
3153
+ "step": 4470
3154
+ },
3155
+ {
3156
+ "epoch": 1.9599649967184423,
3157
+ "grad_norm": 1.6016472578048706,
3158
+ "learning_rate": 5.08566762944751e-08,
3159
+ "loss": 1.0069,
3160
+ "step": 4480
3161
+ },
3162
+ {
3163
+ "epoch": 1.964340406913148,
3164
+ "grad_norm": 1.4748444557189941,
3165
+ "learning_rate": 4.018591344526479e-08,
3166
+ "loss": 0.9978,
3167
+ "step": 4490
3168
+ },
3169
+ {
3170
+ "epoch": 1.9687158171078538,
3171
+ "grad_norm": 1.462731122970581,
3172
+ "learning_rate": 3.076927254779538e-08,
3173
+ "loss": 1.0539,
3174
+ "step": 4500
3175
+ },
3176
+ {
3177
+ "epoch": 1.9730912273025596,
3178
+ "grad_norm": 1.4741415977478027,
3179
+ "learning_rate": 2.2607226747262122e-08,
3180
+ "loss": 1.0609,
3181
+ "step": 4510
3182
+ },
3183
+ {
3184
+ "epoch": 1.9774666374972654,
3185
+ "grad_norm": 1.4613292217254639,
3186
+ "learning_rate": 1.5700186150921503e-08,
3187
+ "loss": 1.0224,
3188
+ "step": 4520
3189
+ },
3190
+ {
3191
+ "epoch": 1.9818420476919711,
3192
+ "grad_norm": 1.4673250913619995,
3193
+ "learning_rate": 1.0048497807479963e-08,
3194
+ "loss": 1.0265,
3195
+ "step": 4530
3196
+ },
3197
+ {
3198
+ "epoch": 1.986217457886677,
3199
+ "grad_norm": 1.4706196784973145,
3200
+ "learning_rate": 5.652445689660613e-09,
3201
+ "loss": 1.0217,
3202
+ "step": 4540
3203
+ },
3204
+ {
3205
+ "epoch": 1.9905928680813827,
3206
+ "grad_norm": 1.5136979818344116,
3207
+ "learning_rate": 2.512250679939654e-09,
3208
+ "loss": 1.0589,
3209
+ "step": 4550
3210
+ },
3211
+ {
3212
+ "epoch": 1.9949682782760885,
3213
+ "grad_norm": 1.4204763174057007,
3214
+ "learning_rate": 6.280705594385871e-10,
3215
+ "loss": 1.0342,
3216
+ "step": 4560
3217
+ },
3218
+ {
3219
+ "epoch": 1.9993436884707942,
3220
+ "grad_norm": 1.3786492347717285,
3221
+ "learning_rate": 0.0,
3222
+ "loss": 1.0299,
3223
+ "step": 4570
3224
+ }
3225
+ ],
3226
+ "logging_steps": 10,
3227
+ "max_steps": 4570,
3228
+ "num_input_tokens_seen": 0,
3229
+ "num_train_epochs": 2,
3230
+ "save_steps": 500.0,
3231
+ "stateful_callbacks": {
3232
+ "TrainerControl": {
3233
+ "args": {
3234
+ "should_epoch_stop": false,
3235
+ "should_evaluate": false,
3236
+ "should_log": false,
3237
+ "should_save": true,
3238
+ "should_training_stop": true
3239
+ },
3240
+ "attributes": {}
3241
+ }
3242
+ },
3243
+ "total_flos": 1.8983281907294208e+18,
3244
+ "train_batch_size": 4,
3245
+ "trial_name": null,
3246
+ "trial_params": null
3247
+ }
checkpoint-4570/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c85d66f583d263a717810314b9c2c8bcc0a0f818cd568e1c7709ffaa2e23b63
3
+ size 6353
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 32.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.48.1",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.48.1"
9
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f296664d96f41adb9939ca047de15c4b74e6100ae2a470975179b31c72ffc2
3
+ size 4980379440
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8e1d82bf5bb601c40dd0ca17abd29f3d599d0bbb5e70c3de2945bbf9c8238c
3
+ size 1144267912
model.safetensors.index.json ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6124593152
4
+ },
5
+ "weight_map": {
6
+ "lm_head.A": "model-00002-of-00002.safetensors",
7
+ "lm_head.B": "model-00002-of-00002.safetensors",
8
+ "lm_head.scales": "model-00002-of-00002.safetensors",
9
+ "lm_head.weight": "model-00002-of-00002.safetensors",
10
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.down_proj.A": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.down_proj.B": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.mlp.up_proj.A": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.mlp.up_proj.B": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
30
+ "model.layers.0.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
31
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
32
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.0.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
34
+ "model.layers.0.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
35
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
36
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.0.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
38
+ "model.layers.0.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
39
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
40
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.down_proj.A": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.down_proj.B": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.mlp.up_proj.A": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.mlp.up_proj.B": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
53
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.1.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
56
+ "model.layers.1.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
57
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
58
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.1.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
60
+ "model.layers.1.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
61
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
62
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.1.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
64
+ "model.layers.1.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
65
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
66
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.1.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
68
+ "model.layers.1.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
69
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
70
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.10.mlp.down_proj.A": "model-00001-of-00002.safetensors",
73
+ "model.layers.10.mlp.down_proj.B": "model-00001-of-00002.safetensors",
74
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
75
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.10.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
77
+ "model.layers.10.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
78
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
79
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.10.mlp.up_proj.A": "model-00001-of-00002.safetensors",
81
+ "model.layers.10.mlp.up_proj.B": "model-00001-of-00002.safetensors",
82
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
83
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.10.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
86
+ "model.layers.10.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
87
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
88
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.10.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
90
+ "model.layers.10.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
91
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
92
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.10.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
94
+ "model.layers.10.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
95
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
96
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.10.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
98
+ "model.layers.10.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
99
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
100
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.11.mlp.down_proj.A": "model-00001-of-00002.safetensors",
103
+ "model.layers.11.mlp.down_proj.B": "model-00001-of-00002.safetensors",
104
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
105
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.11.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
107
+ "model.layers.11.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
108
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
109
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.11.mlp.up_proj.A": "model-00001-of-00002.safetensors",
111
+ "model.layers.11.mlp.up_proj.B": "model-00001-of-00002.safetensors",
112
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
113
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.11.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
116
+ "model.layers.11.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
117
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
118
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.11.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
120
+ "model.layers.11.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
121
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
122
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.11.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
124
+ "model.layers.11.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
125
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
126
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.11.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
128
+ "model.layers.11.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
129
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
130
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.12.mlp.down_proj.A": "model-00001-of-00002.safetensors",
133
+ "model.layers.12.mlp.down_proj.B": "model-00001-of-00002.safetensors",
134
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
135
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.12.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
137
+ "model.layers.12.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
138
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
139
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.12.mlp.up_proj.A": "model-00001-of-00002.safetensors",
141
+ "model.layers.12.mlp.up_proj.B": "model-00001-of-00002.safetensors",
142
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
143
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.12.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
146
+ "model.layers.12.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
147
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
148
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.12.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
150
+ "model.layers.12.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
151
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
152
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.12.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
154
+ "model.layers.12.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
155
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
156
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.12.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
158
+ "model.layers.12.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
159
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
160
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.13.mlp.down_proj.A": "model-00001-of-00002.safetensors",
163
+ "model.layers.13.mlp.down_proj.B": "model-00001-of-00002.safetensors",
164
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
165
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.13.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
167
+ "model.layers.13.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
168
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
169
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.13.mlp.up_proj.A": "model-00001-of-00002.safetensors",
171
+ "model.layers.13.mlp.up_proj.B": "model-00001-of-00002.safetensors",
172
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
173
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.13.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
176
+ "model.layers.13.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
177
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
178
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.13.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
180
+ "model.layers.13.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
181
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
182
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.13.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
184
+ "model.layers.13.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
185
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
186
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.13.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
188
+ "model.layers.13.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
189
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
190
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.14.mlp.down_proj.A": "model-00001-of-00002.safetensors",
193
+ "model.layers.14.mlp.down_proj.B": "model-00001-of-00002.safetensors",
194
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
195
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.14.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
197
+ "model.layers.14.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
198
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
199
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.14.mlp.up_proj.A": "model-00001-of-00002.safetensors",
201
+ "model.layers.14.mlp.up_proj.B": "model-00001-of-00002.safetensors",
202
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
203
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.14.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
206
+ "model.layers.14.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
207
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
208
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.14.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
210
+ "model.layers.14.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
211
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
212
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.14.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
214
+ "model.layers.14.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
215
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
216
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.14.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
218
+ "model.layers.14.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
219
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
220
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.15.mlp.down_proj.A": "model-00002-of-00002.safetensors",
223
+ "model.layers.15.mlp.down_proj.B": "model-00002-of-00002.safetensors",
224
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
225
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.15.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
227
+ "model.layers.15.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
228
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
229
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.15.mlp.up_proj.A": "model-00001-of-00002.safetensors",
231
+ "model.layers.15.mlp.up_proj.B": "model-00001-of-00002.safetensors",
232
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
233
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.15.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
236
+ "model.layers.15.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
237
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
238
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.15.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
240
+ "model.layers.15.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
241
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
242
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.15.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
244
+ "model.layers.15.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
245
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
246
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.15.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
248
+ "model.layers.15.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
249
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
250
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.2.mlp.down_proj.A": "model-00001-of-00002.safetensors",
253
+ "model.layers.2.mlp.down_proj.B": "model-00001-of-00002.safetensors",
254
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
255
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.2.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
257
+ "model.layers.2.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
258
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
259
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.2.mlp.up_proj.A": "model-00001-of-00002.safetensors",
261
+ "model.layers.2.mlp.up_proj.B": "model-00001-of-00002.safetensors",
262
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
263
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.2.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
266
+ "model.layers.2.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
267
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
268
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.2.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
270
+ "model.layers.2.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
271
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
272
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.2.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
274
+ "model.layers.2.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
275
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
276
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.2.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
278
+ "model.layers.2.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
279
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
280
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.3.mlp.down_proj.A": "model-00001-of-00002.safetensors",
283
+ "model.layers.3.mlp.down_proj.B": "model-00001-of-00002.safetensors",
284
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.mlp.up_proj.A": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.mlp.up_proj.B": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
296
+ "model.layers.3.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
297
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
298
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.3.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
300
+ "model.layers.3.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
301
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
302
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.3.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
304
+ "model.layers.3.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
305
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
306
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.3.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
308
+ "model.layers.3.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
309
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
310
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.4.mlp.down_proj.A": "model-00001-of-00002.safetensors",
313
+ "model.layers.4.mlp.down_proj.B": "model-00001-of-00002.safetensors",
314
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.4.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
317
+ "model.layers.4.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
318
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
319
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.4.mlp.up_proj.A": "model-00001-of-00002.safetensors",
321
+ "model.layers.4.mlp.up_proj.B": "model-00001-of-00002.safetensors",
322
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
323
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.4.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
326
+ "model.layers.4.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
327
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
328
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.4.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
330
+ "model.layers.4.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
331
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
332
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.4.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
334
+ "model.layers.4.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
335
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
336
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.4.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
338
+ "model.layers.4.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
339
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.5.mlp.down_proj.A": "model-00001-of-00002.safetensors",
343
+ "model.layers.5.mlp.down_proj.B": "model-00001-of-00002.safetensors",
344
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
345
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.5.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
347
+ "model.layers.5.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
348
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
349
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.mlp.up_proj.A": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.up_proj.B": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.5.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
360
+ "model.layers.5.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
361
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
362
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.5.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
364
+ "model.layers.5.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
365
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
366
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.5.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
368
+ "model.layers.5.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
369
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
370
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.6.mlp.down_proj.A": "model-00001-of-00002.safetensors",
373
+ "model.layers.6.mlp.down_proj.B": "model-00001-of-00002.safetensors",
374
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
375
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.6.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
377
+ "model.layers.6.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
378
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
379
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.6.mlp.up_proj.A": "model-00001-of-00002.safetensors",
381
+ "model.layers.6.mlp.up_proj.B": "model-00001-of-00002.safetensors",
382
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
383
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.6.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
386
+ "model.layers.6.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
387
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
388
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.6.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
390
+ "model.layers.6.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
391
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.7.mlp.down_proj.A": "model-00001-of-00002.safetensors",
403
+ "model.layers.7.mlp.down_proj.B": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.mlp.up_proj.A": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.mlp.up_proj.B": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
416
+ "model.layers.7.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.7.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
428
+ "model.layers.7.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
429
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
430
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.mlp.down_proj.A": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.down_proj.B": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.mlp.up_proj.A": "model-00001-of-00002.safetensors",
441
+ "model.layers.8.mlp.up_proj.B": "model-00001-of-00002.safetensors",
442
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
443
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.8.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
446
+ "model.layers.8.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
447
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
448
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.8.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
450
+ "model.layers.8.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
451
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
452
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.8.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
454
+ "model.layers.8.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
455
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
456
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.8.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
458
+ "model.layers.8.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
459
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
460
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
462
+ "model.layers.9.mlp.down_proj.A": "model-00001-of-00002.safetensors",
463
+ "model.layers.9.mlp.down_proj.B": "model-00001-of-00002.safetensors",
464
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
465
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.9.mlp.gate_proj.A": "model-00001-of-00002.safetensors",
467
+ "model.layers.9.mlp.gate_proj.B": "model-00001-of-00002.safetensors",
468
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
469
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.9.mlp.up_proj.A": "model-00001-of-00002.safetensors",
471
+ "model.layers.9.mlp.up_proj.B": "model-00001-of-00002.safetensors",
472
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
473
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
474
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.9.self_attn.k_proj.A": "model-00001-of-00002.safetensors",
476
+ "model.layers.9.self_attn.k_proj.B": "model-00001-of-00002.safetensors",
477
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
478
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.9.self_attn.o_proj.A": "model-00001-of-00002.safetensors",
480
+ "model.layers.9.self_attn.o_proj.B": "model-00001-of-00002.safetensors",
481
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
482
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
483
+ "model.layers.9.self_attn.q_proj.A": "model-00001-of-00002.safetensors",
484
+ "model.layers.9.self_attn.q_proj.B": "model-00001-of-00002.safetensors",
485
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
486
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.layers.9.self_attn.v_proj.A": "model-00001-of-00002.safetensors",
488
+ "model.layers.9.self_attn.v_proj.B": "model-00001-of-00002.safetensors",
489
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
490
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.norm.weight": "model-00002-of-00002.safetensors"
492
+ }
493
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
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 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "\n {{- bos_token }}\n {%- for message in messages %}\n {%- if message['role'] == 'assistant' %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '\n' }}\n {%- generation %}\n {{- message['content'] + '<|eot_id|>' }}\n {%- endgeneration %}\n {{- '\n' }}\n {%- else %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '\n' + message['content'] + '<|eot_id|>' + '\n' }}\n {%- endif %}\n {%- endfor %}\n {%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n' }}\n {%- endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c85d66f583d263a717810314b9c2c8bcc0a0f818cd568e1c7709ffaa2e23b63
3
+ size 6353