bimabk commited on
Commit
7c03cdd
·
verified ·
1 Parent(s): 20aed0b

Upload task output 503ed8fa-75ce-4c8d-b91c-bf02ce892c47

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128009,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 24,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128004,
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": "bfloat16",
33
+ "transformers_version": "4.51.3",
34
+ "unsloth_fixed": true,
35
+ "use_cache": false,
36
+ "vocab_size": 128256
37
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "max_length": 131072,
10
+ "pad_token_id": 128004,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.51.3"
14
+ }
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 1830,0.3913484513759613
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da6df7709e7f1b7f23649e48c3059bef2cb24d24895d65cf311a680a1280d79
3
+ size 4965799096
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40033b8cc2646d3b3626c3a20fd36fcff79a1d778823541a0ba1c0f428c51635
3
+ size 1459729952
model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6425499648
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.norm.weight": "model-00002-of-00002.safetensors"
260
+ }
261
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 +1,2067 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|finetune_right_pad_id|>",
2064
+ "padding_side": "left",
2065
+ "tokenizer_class": "PreTrainedTokenizer",
2066
+ "unk_token": null
2067
+ }
trainer_state.json ADDED
@@ -0,0 +1,2652 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.9950900163666123,
6
+ "eval_steps": 500,
7
+ "global_step": 1830,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008183306055646482,
14
+ "grad_norm": 2.34375,
15
+ "learning_rate": 1.142857142857143e-06,
16
+ "loss": 0.6534,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.016366612111292964,
21
+ "grad_norm": 2.15625,
22
+ "learning_rate": 2.571428571428571e-06,
23
+ "loss": 0.6508,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.024549918166939442,
28
+ "grad_norm": 1.84375,
29
+ "learning_rate": 4.000000000000001e-06,
30
+ "loss": 0.6493,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.03273322422258593,
35
+ "grad_norm": 1.4453125,
36
+ "learning_rate": 5.428571428571429e-06,
37
+ "loss": 0.6052,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.04091653027823241,
42
+ "grad_norm": 1.0625,
43
+ "learning_rate": 6.857142857142858e-06,
44
+ "loss": 0.5644,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.049099836333878884,
49
+ "grad_norm": 0.76953125,
50
+ "learning_rate": 8.285714285714287e-06,
51
+ "loss": 0.5195,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.057283142389525366,
56
+ "grad_norm": 0.63671875,
57
+ "learning_rate": 9.714285714285715e-06,
58
+ "loss": 0.5033,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.06546644844517185,
63
+ "grad_norm": 0.59375,
64
+ "learning_rate": 9.99990841172964e-06,
65
+ "loss": 0.4931,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.07364975450081833,
70
+ "grad_norm": 0.56640625,
71
+ "learning_rate": 9.999536342048818e-06,
72
+ "loss": 0.4682,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.08183306055646482,
77
+ "grad_norm": 0.60546875,
78
+ "learning_rate": 9.998878095066407e-06,
79
+ "loss": 0.4627,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.09001636661211129,
84
+ "grad_norm": 0.53125,
85
+ "learning_rate": 9.997933721022044e-06,
86
+ "loss": 0.4458,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.09819967266775777,
91
+ "grad_norm": 0.55078125,
92
+ "learning_rate": 9.996703291993557e-06,
93
+ "loss": 0.4567,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.10638297872340426,
98
+ "grad_norm": 0.52734375,
99
+ "learning_rate": 9.995186901891448e-06,
100
+ "loss": 0.4644,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.11456628477905073,
105
+ "grad_norm": 0.53515625,
106
+ "learning_rate": 9.993384666451743e-06,
107
+ "loss": 0.4547,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.12274959083469722,
112
+ "grad_norm": 0.55859375,
113
+ "learning_rate": 9.991296723227148e-06,
114
+ "loss": 0.4546,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.1309328968903437,
119
+ "grad_norm": 0.5234375,
120
+ "learning_rate": 9.988923231576558e-06,
121
+ "loss": 0.4334,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.13911620294599017,
126
+ "grad_norm": 0.5078125,
127
+ "learning_rate": 9.986264372652883e-06,
128
+ "loss": 0.4419,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.14729950900163666,
133
+ "grad_norm": 0.53125,
134
+ "learning_rate": 9.983320349389237e-06,
135
+ "loss": 0.4409,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.15548281505728315,
140
+ "grad_norm": 0.51953125,
141
+ "learning_rate": 9.980091386483434e-06,
142
+ "loss": 0.4618,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.16366612111292964,
147
+ "grad_norm": 0.515625,
148
+ "learning_rate": 9.976577730380855e-06,
149
+ "loss": 0.4488,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.1718494271685761,
154
+ "grad_norm": 0.515625,
155
+ "learning_rate": 9.972779649255617e-06,
156
+ "loss": 0.4408,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.18003273322422259,
161
+ "grad_norm": 0.5234375,
162
+ "learning_rate": 9.968697432990129e-06,
163
+ "loss": 0.4423,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.18821603927986907,
168
+ "grad_norm": 0.5078125,
169
+ "learning_rate": 9.964331393152947e-06,
170
+ "loss": 0.4503,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.19639934533551553,
175
+ "grad_norm": 0.51171875,
176
+ "learning_rate": 9.959681862975007e-06,
177
+ "loss": 0.4282,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.20458265139116202,
182
+ "grad_norm": 0.51171875,
183
+ "learning_rate": 9.954749197324184e-06,
184
+ "loss": 0.4336,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.2127659574468085,
189
+ "grad_norm": 0.51953125,
190
+ "learning_rate": 9.949533772678215e-06,
191
+ "loss": 0.4337,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.220949263502455,
196
+ "grad_norm": 0.5234375,
197
+ "learning_rate": 9.944035987095955e-06,
198
+ "loss": 0.4365,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.22913256955810146,
203
+ "grad_norm": 0.51953125,
204
+ "learning_rate": 9.938256260187002e-06,
205
+ "loss": 0.4259,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.23731587561374795,
210
+ "grad_norm": 0.51171875,
211
+ "learning_rate": 9.932195033079677e-06,
212
+ "loss": 0.4291,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.24549918166939444,
217
+ "grad_norm": 0.515625,
218
+ "learning_rate": 9.925852768387337e-06,
219
+ "loss": 0.4362,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.25368248772504093,
224
+ "grad_norm": 0.5390625,
225
+ "learning_rate": 9.919229950173089e-06,
226
+ "loss": 0.4434,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.2618657937806874,
231
+ "grad_norm": 0.51953125,
232
+ "learning_rate": 9.912327083912825e-06,
233
+ "loss": 0.4278,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.2700490998363339,
238
+ "grad_norm": 0.53515625,
239
+ "learning_rate": 9.905144696456664e-06,
240
+ "loss": 0.4324,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.27823240589198034,
245
+ "grad_norm": 0.51953125,
246
+ "learning_rate": 9.897683335988714e-06,
247
+ "loss": 0.4505,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.2864157119476268,
252
+ "grad_norm": 0.515625,
253
+ "learning_rate": 9.889943571985258e-06,
254
+ "loss": 0.4329,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.2945990180032733,
259
+ "grad_norm": 0.5234375,
260
+ "learning_rate": 9.881925995171272e-06,
261
+ "loss": 0.4439,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.3027823240589198,
266
+ "grad_norm": 0.53125,
267
+ "learning_rate": 9.873631217475355e-06,
268
+ "loss": 0.4452,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.3109656301145663,
273
+ "grad_norm": 0.55078125,
274
+ "learning_rate": 9.865059871983003e-06,
275
+ "loss": 0.4329,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.3191489361702128,
280
+ "grad_norm": 0.515625,
281
+ "learning_rate": 9.856212612888312e-06,
282
+ "loss": 0.4224,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.32733224222585927,
287
+ "grad_norm": 0.54296875,
288
+ "learning_rate": 9.847090115444032e-06,
289
+ "loss": 0.4186,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.3355155482815057,
294
+ "grad_norm": 0.515625,
295
+ "learning_rate": 9.837693075910037e-06,
296
+ "loss": 0.4178,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.3436988543371522,
301
+ "grad_norm": 0.53125,
302
+ "learning_rate": 9.828022211500183e-06,
303
+ "loss": 0.441,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.3518821603927987,
308
+ "grad_norm": 0.54296875,
309
+ "learning_rate": 9.81807826032757e-06,
310
+ "loss": 0.4261,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.36006546644844517,
315
+ "grad_norm": 0.515625,
316
+ "learning_rate": 9.807861981348196e-06,
317
+ "loss": 0.422,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.36824877250409166,
322
+ "grad_norm": 0.498046875,
323
+ "learning_rate": 9.797374154303048e-06,
324
+ "loss": 0.4346,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.37643207855973815,
329
+ "grad_norm": 0.53515625,
330
+ "learning_rate": 9.786615579658571e-06,
331
+ "loss": 0.4226,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.38461538461538464,
336
+ "grad_norm": 0.53125,
337
+ "learning_rate": 9.77558707854559e-06,
338
+ "loss": 0.4136,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.39279869067103107,
343
+ "grad_norm": 0.52734375,
344
+ "learning_rate": 9.764289492696628e-06,
345
+ "loss": 0.4292,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.40098199672667756,
350
+ "grad_norm": 0.53125,
351
+ "learning_rate": 9.752723684381666e-06,
352
+ "loss": 0.4127,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.40916530278232405,
357
+ "grad_norm": 0.52734375,
358
+ "learning_rate": 9.740890536342336e-06,
359
+ "loss": 0.4383,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.41734860883797054,
364
+ "grad_norm": 0.51953125,
365
+ "learning_rate": 9.728790951724532e-06,
366
+ "loss": 0.4216,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.425531914893617,
371
+ "grad_norm": 0.5,
372
+ "learning_rate": 9.716425854009501e-06,
373
+ "loss": 0.4117,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.4337152209492635,
378
+ "grad_norm": 0.515625,
379
+ "learning_rate": 9.70379618694334e-06,
380
+ "loss": 0.427,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.44189852700491,
385
+ "grad_norm": 0.51171875,
386
+ "learning_rate": 9.690902914464977e-06,
387
+ "loss": 0.4267,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.4500818330605565,
392
+ "grad_norm": 0.5078125,
393
+ "learning_rate": 9.677747020632595e-06,
394
+ "loss": 0.4178,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.4582651391162029,
399
+ "grad_norm": 0.50390625,
400
+ "learning_rate": 9.664329509548534e-06,
401
+ "loss": 0.4094,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.4664484451718494,
406
+ "grad_norm": 0.50390625,
407
+ "learning_rate": 9.650651405282638e-06,
408
+ "loss": 0.402,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.4746317512274959,
413
+ "grad_norm": 0.5078125,
414
+ "learning_rate": 9.63671375179411e-06,
415
+ "loss": 0.4147,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.4828150572831424,
420
+ "grad_norm": 0.494140625,
421
+ "learning_rate": 9.622517612851832e-06,
422
+ "loss": 0.4107,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.4909983633387889,
427
+ "grad_norm": 0.5078125,
428
+ "learning_rate": 9.608064071953162e-06,
429
+ "loss": 0.4152,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.49918166939443537,
434
+ "grad_norm": 0.5234375,
435
+ "learning_rate": 9.593354232241251e-06,
436
+ "loss": 0.4308,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.5073649754500819,
441
+ "grad_norm": 0.51171875,
442
+ "learning_rate": 9.578389216420844e-06,
443
+ "loss": 0.4145,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.5155482815057283,
448
+ "grad_norm": 0.515625,
449
+ "learning_rate": 9.563170166672585e-06,
450
+ "loss": 0.4062,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.5237315875613748,
455
+ "grad_norm": 0.51953125,
456
+ "learning_rate": 9.547698244565855e-06,
457
+ "loss": 0.419,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.5319148936170213,
462
+ "grad_norm": 0.5234375,
463
+ "learning_rate": 9.5319746309701e-06,
464
+ "loss": 0.413,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.5400981996726678,
469
+ "grad_norm": 0.515625,
470
+ "learning_rate": 9.516000525964716e-06,
471
+ "loss": 0.4404,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 0.5482815057283142,
476
+ "grad_norm": 0.51171875,
477
+ "learning_rate": 9.499777148747455e-06,
478
+ "loss": 0.4185,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 0.5564648117839607,
483
+ "grad_norm": 0.5,
484
+ "learning_rate": 9.48330573754136e-06,
485
+ "loss": 0.4134,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 0.5646481178396072,
490
+ "grad_norm": 0.5234375,
491
+ "learning_rate": 9.466587549500274e-06,
492
+ "loss": 0.4305,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 0.5728314238952537,
497
+ "grad_norm": 0.50390625,
498
+ "learning_rate": 9.449623860612879e-06,
499
+ "loss": 0.4108,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 0.5810147299509002,
504
+ "grad_norm": 0.50390625,
505
+ "learning_rate": 9.432415965605318e-06,
506
+ "loss": 0.4086,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 0.5891980360065466,
511
+ "grad_norm": 0.5234375,
512
+ "learning_rate": 9.414965177842361e-06,
513
+ "loss": 0.4025,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 0.5973813420621932,
518
+ "grad_norm": 0.51953125,
519
+ "learning_rate": 9.397272829227187e-06,
520
+ "loss": 0.4191,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 0.6055646481178396,
525
+ "grad_norm": 0.51171875,
526
+ "learning_rate": 9.379340270099708e-06,
527
+ "loss": 0.4117,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 0.613747954173486,
532
+ "grad_norm": 0.515625,
533
+ "learning_rate": 9.361168869133516e-06,
534
+ "loss": 0.418,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 0.6219312602291326,
539
+ "grad_norm": 0.515625,
540
+ "learning_rate": 9.342760013231429e-06,
541
+ "loss": 0.4197,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 0.630114566284779,
546
+ "grad_norm": 0.51953125,
547
+ "learning_rate": 9.324115107419616e-06,
548
+ "loss": 0.4173,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 0.6382978723404256,
553
+ "grad_norm": 0.5078125,
554
+ "learning_rate": 9.305235574740386e-06,
555
+ "loss": 0.4133,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 0.646481178396072,
560
+ "grad_norm": 0.53515625,
561
+ "learning_rate": 9.286122856143555e-06,
562
+ "loss": 0.4223,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 0.6546644844517185,
567
+ "grad_norm": 0.494140625,
568
+ "learning_rate": 9.266778410376484e-06,
569
+ "loss": 0.4045,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 0.662847790507365,
574
+ "grad_norm": 0.51171875,
575
+ "learning_rate": 9.247203713872732e-06,
576
+ "loss": 0.4196,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 0.6710310965630114,
581
+ "grad_norm": 0.5234375,
582
+ "learning_rate": 9.227400260639374e-06,
583
+ "loss": 0.3995,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 0.679214402618658,
588
+ "grad_norm": 0.53515625,
589
+ "learning_rate": 9.207369562142975e-06,
590
+ "loss": 0.4154,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 0.6873977086743044,
595
+ "grad_norm": 0.5234375,
596
+ "learning_rate": 9.187113147194222e-06,
597
+ "loss": 0.4077,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 0.6955810147299509,
602
+ "grad_norm": 0.5078125,
603
+ "learning_rate": 9.166632561831252e-06,
604
+ "loss": 0.4012,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 0.7037643207855974,
609
+ "grad_norm": 0.53515625,
610
+ "learning_rate": 9.145929369201646e-06,
611
+ "loss": 0.4007,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 0.7119476268412439,
616
+ "grad_norm": 0.494140625,
617
+ "learning_rate": 9.125005149443117e-06,
618
+ "loss": 0.412,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 0.7201309328968903,
623
+ "grad_norm": 0.56640625,
624
+ "learning_rate": 9.103861499562925e-06,
625
+ "loss": 0.4165,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 0.7283142389525368,
630
+ "grad_norm": 0.5,
631
+ "learning_rate": 9.082500033315976e-06,
632
+ "loss": 0.4114,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 0.7364975450081833,
637
+ "grad_norm": 0.515625,
638
+ "learning_rate": 9.060922381081658e-06,
639
+ "loss": 0.419,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 0.7446808510638298,
644
+ "grad_norm": 0.5234375,
645
+ "learning_rate": 9.039130189739405e-06,
646
+ "loss": 0.4209,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 0.7528641571194763,
651
+ "grad_norm": 0.546875,
652
+ "learning_rate": 9.017125122543006e-06,
653
+ "loss": 0.4359,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 0.7610474631751227,
658
+ "grad_norm": 0.5546875,
659
+ "learning_rate": 8.994908858993647e-06,
660
+ "loss": 0.4162,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 0.7692307692307693,
665
+ "grad_norm": 0.515625,
666
+ "learning_rate": 8.97248309471174e-06,
667
+ "loss": 0.3991,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 0.7774140752864157,
672
+ "grad_norm": 0.498046875,
673
+ "learning_rate": 8.949849541307505e-06,
674
+ "loss": 0.4087,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 0.7855973813420621,
679
+ "grad_norm": 0.51953125,
680
+ "learning_rate": 8.927009926250324e-06,
681
+ "loss": 0.4053,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 0.7937806873977087,
686
+ "grad_norm": 0.53125,
687
+ "learning_rate": 8.903965992736903e-06,
688
+ "loss": 0.4016,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 0.8019639934533551,
693
+ "grad_norm": 0.53515625,
694
+ "learning_rate": 8.880719499558226e-06,
695
+ "loss": 0.4128,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 0.8101472995090017,
700
+ "grad_norm": 0.51171875,
701
+ "learning_rate": 8.85727222096532e-06,
702
+ "loss": 0.4146,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 0.8183306055646481,
707
+ "grad_norm": 0.486328125,
708
+ "learning_rate": 8.833625946533826e-06,
709
+ "loss": 0.407,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 0.8183306055646481,
714
+ "eval_loss": 0.40063852071762085,
715
+ "eval_runtime": 5.182,
716
+ "eval_samples_per_second": 16.017,
717
+ "eval_steps_per_second": 16.017,
718
+ "step": 500
719
+ },
720
+ {
721
+ "epoch": 0.8265139116202946,
722
+ "grad_norm": 0.51953125,
723
+ "learning_rate": 8.809782481027425e-06,
724
+ "loss": 0.4279,
725
+ "step": 505
726
+ },
727
+ {
728
+ "epoch": 0.8346972176759411,
729
+ "grad_norm": 0.5234375,
730
+ "learning_rate": 8.785743644260087e-06,
731
+ "loss": 0.4123,
732
+ "step": 510
733
+ },
734
+ {
735
+ "epoch": 0.8428805237315876,
736
+ "grad_norm": 0.50390625,
737
+ "learning_rate": 8.761511270957179e-06,
738
+ "loss": 0.3964,
739
+ "step": 515
740
+ },
741
+ {
742
+ "epoch": 0.851063829787234,
743
+ "grad_norm": 0.5390625,
744
+ "learning_rate": 8.737087210615434e-06,
745
+ "loss": 0.4143,
746
+ "step": 520
747
+ },
748
+ {
749
+ "epoch": 0.8592471358428805,
750
+ "grad_norm": 0.50390625,
751
+ "learning_rate": 8.71247332736178e-06,
752
+ "loss": 0.4108,
753
+ "step": 525
754
+ },
755
+ {
756
+ "epoch": 0.867430441898527,
757
+ "grad_norm": 0.5,
758
+ "learning_rate": 8.687671499811083e-06,
759
+ "loss": 0.4157,
760
+ "step": 530
761
+ },
762
+ {
763
+ "epoch": 0.8756137479541735,
764
+ "grad_norm": 0.4921875,
765
+ "learning_rate": 8.662683620922743e-06,
766
+ "loss": 0.4068,
767
+ "step": 535
768
+ },
769
+ {
770
+ "epoch": 0.88379705400982,
771
+ "grad_norm": 0.5078125,
772
+ "learning_rate": 8.637511597856234e-06,
773
+ "loss": 0.4154,
774
+ "step": 540
775
+ },
776
+ {
777
+ "epoch": 0.8919803600654664,
778
+ "grad_norm": 0.4921875,
779
+ "learning_rate": 8.612157351825536e-06,
780
+ "loss": 0.3982,
781
+ "step": 545
782
+ },
783
+ {
784
+ "epoch": 0.900163666121113,
785
+ "grad_norm": 0.515625,
786
+ "learning_rate": 8.586622817952504e-06,
787
+ "loss": 0.4016,
788
+ "step": 550
789
+ },
790
+ {
791
+ "epoch": 0.9083469721767594,
792
+ "grad_norm": 0.5,
793
+ "learning_rate": 8.560909945119162e-06,
794
+ "loss": 0.405,
795
+ "step": 555
796
+ },
797
+ {
798
+ "epoch": 0.9165302782324058,
799
+ "grad_norm": 0.53515625,
800
+ "learning_rate": 8.53502069581898e-06,
801
+ "loss": 0.4107,
802
+ "step": 560
803
+ },
804
+ {
805
+ "epoch": 0.9247135842880524,
806
+ "grad_norm": 0.4921875,
807
+ "learning_rate": 8.50895704600707e-06,
808
+ "loss": 0.398,
809
+ "step": 565
810
+ },
811
+ {
812
+ "epoch": 0.9328968903436988,
813
+ "grad_norm": 0.50390625,
814
+ "learning_rate": 8.48272098494938e-06,
815
+ "loss": 0.3961,
816
+ "step": 570
817
+ },
818
+ {
819
+ "epoch": 0.9410801963993454,
820
+ "grad_norm": 0.49609375,
821
+ "learning_rate": 8.45631451507087e-06,
822
+ "loss": 0.4021,
823
+ "step": 575
824
+ },
825
+ {
826
+ "epoch": 0.9492635024549918,
827
+ "grad_norm": 0.51953125,
828
+ "learning_rate": 8.429739651802676e-06,
829
+ "loss": 0.4104,
830
+ "step": 580
831
+ },
832
+ {
833
+ "epoch": 0.9574468085106383,
834
+ "grad_norm": 0.498046875,
835
+ "learning_rate": 8.402998423428291e-06,
836
+ "loss": 0.411,
837
+ "step": 585
838
+ },
839
+ {
840
+ "epoch": 0.9656301145662848,
841
+ "grad_norm": 0.51953125,
842
+ "learning_rate": 8.376092870928752e-06,
843
+ "loss": 0.4266,
844
+ "step": 590
845
+ },
846
+ {
847
+ "epoch": 0.9738134206219312,
848
+ "grad_norm": 0.50390625,
849
+ "learning_rate": 8.349025047826873e-06,
850
+ "loss": 0.4103,
851
+ "step": 595
852
+ },
853
+ {
854
+ "epoch": 0.9819967266775778,
855
+ "grad_norm": 0.498046875,
856
+ "learning_rate": 8.321797020030504e-06,
857
+ "loss": 0.4233,
858
+ "step": 600
859
+ },
860
+ {
861
+ "epoch": 0.9901800327332242,
862
+ "grad_norm": 0.515625,
863
+ "learning_rate": 8.294410865674864e-06,
864
+ "loss": 0.4273,
865
+ "step": 605
866
+ },
867
+ {
868
+ "epoch": 0.9983633387888707,
869
+ "grad_norm": 0.51171875,
870
+ "learning_rate": 8.266868674963924e-06,
871
+ "loss": 0.4179,
872
+ "step": 610
873
+ },
874
+ {
875
+ "epoch": 0.9983633387888707,
876
+ "eval_loss": 0.39774245023727417,
877
+ "eval_runtime": 5.08,
878
+ "eval_samples_per_second": 16.338,
879
+ "eval_steps_per_second": 16.338,
880
+ "step": 610
881
+ },
882
+ {
883
+ "epoch": 1.0065466448445173,
884
+ "grad_norm": 0.5,
885
+ "learning_rate": 8.23917255001088e-06,
886
+ "loss": 0.381,
887
+ "step": 615
888
+ },
889
+ {
890
+ "epoch": 1.0147299509001637,
891
+ "grad_norm": 0.498046875,
892
+ "learning_rate": 8.211324604677711e-06,
893
+ "loss": 0.4149,
894
+ "step": 620
895
+ },
896
+ {
897
+ "epoch": 1.0229132569558101,
898
+ "grad_norm": 0.51171875,
899
+ "learning_rate": 8.183326964413832e-06,
900
+ "loss": 0.4204,
901
+ "step": 625
902
+ },
903
+ {
904
+ "epoch": 1.0310965630114566,
905
+ "grad_norm": 0.51953125,
906
+ "learning_rate": 8.155181766093893e-06,
907
+ "loss": 0.4049,
908
+ "step": 630
909
+ },
910
+ {
911
+ "epoch": 1.039279869067103,
912
+ "grad_norm": 0.53515625,
913
+ "learning_rate": 8.12689115785467e-06,
914
+ "loss": 0.3967,
915
+ "step": 635
916
+ },
917
+ {
918
+ "epoch": 1.0474631751227497,
919
+ "grad_norm": 0.515625,
920
+ "learning_rate": 8.098457298931113e-06,
921
+ "loss": 0.3976,
922
+ "step": 640
923
+ },
924
+ {
925
+ "epoch": 1.055646481178396,
926
+ "grad_norm": 0.5234375,
927
+ "learning_rate": 8.069882359491555e-06,
928
+ "loss": 0.4098,
929
+ "step": 645
930
+ },
931
+ {
932
+ "epoch": 1.0638297872340425,
933
+ "grad_norm": 0.546875,
934
+ "learning_rate": 8.041168520472065e-06,
935
+ "loss": 0.3955,
936
+ "step": 650
937
+ },
938
+ {
939
+ "epoch": 1.072013093289689,
940
+ "grad_norm": 0.50390625,
941
+ "learning_rate": 8.012317973410001e-06,
942
+ "loss": 0.3852,
943
+ "step": 655
944
+ },
945
+ {
946
+ "epoch": 1.0801963993453354,
947
+ "grad_norm": 0.515625,
948
+ "learning_rate": 7.983332920276745e-06,
949
+ "loss": 0.4018,
950
+ "step": 660
951
+ },
952
+ {
953
+ "epoch": 1.088379705400982,
954
+ "grad_norm": 0.546875,
955
+ "learning_rate": 7.95421557330963e-06,
956
+ "loss": 0.3948,
957
+ "step": 665
958
+ },
959
+ {
960
+ "epoch": 1.0965630114566285,
961
+ "grad_norm": 0.50390625,
962
+ "learning_rate": 7.924968154843108e-06,
963
+ "loss": 0.3918,
964
+ "step": 670
965
+ },
966
+ {
967
+ "epoch": 1.104746317512275,
968
+ "grad_norm": 0.5625,
969
+ "learning_rate": 7.895592897139128e-06,
970
+ "loss": 0.4182,
971
+ "step": 675
972
+ },
973
+ {
974
+ "epoch": 1.1129296235679214,
975
+ "grad_norm": 0.51953125,
976
+ "learning_rate": 7.866092042216755e-06,
977
+ "loss": 0.3837,
978
+ "step": 680
979
+ },
980
+ {
981
+ "epoch": 1.121112929623568,
982
+ "grad_norm": 0.50390625,
983
+ "learning_rate": 7.836467841681066e-06,
984
+ "loss": 0.4191,
985
+ "step": 685
986
+ },
987
+ {
988
+ "epoch": 1.1292962356792144,
989
+ "grad_norm": 0.5234375,
990
+ "learning_rate": 7.806722556551292e-06,
991
+ "loss": 0.4124,
992
+ "step": 690
993
+ },
994
+ {
995
+ "epoch": 1.1374795417348609,
996
+ "grad_norm": 0.51171875,
997
+ "learning_rate": 7.776858457088249e-06,
998
+ "loss": 0.4093,
999
+ "step": 695
1000
+ },
1001
+ {
1002
+ "epoch": 1.1456628477905073,
1003
+ "grad_norm": 0.50390625,
1004
+ "learning_rate": 7.746877822621059e-06,
1005
+ "loss": 0.4067,
1006
+ "step": 700
1007
+ },
1008
+ {
1009
+ "epoch": 1.1538461538461537,
1010
+ "grad_norm": 0.5078125,
1011
+ "learning_rate": 7.716782941373201e-06,
1012
+ "loss": 0.4061,
1013
+ "step": 705
1014
+ },
1015
+ {
1016
+ "epoch": 1.1620294599018004,
1017
+ "grad_norm": 0.51953125,
1018
+ "learning_rate": 7.68657611028785e-06,
1019
+ "loss": 0.3947,
1020
+ "step": 710
1021
+ },
1022
+ {
1023
+ "epoch": 1.1702127659574468,
1024
+ "grad_norm": 0.546875,
1025
+ "learning_rate": 7.656259634852566e-06,
1026
+ "loss": 0.4099,
1027
+ "step": 715
1028
+ },
1029
+ {
1030
+ "epoch": 1.1783960720130933,
1031
+ "grad_norm": 0.515625,
1032
+ "learning_rate": 7.625835828923344e-06,
1033
+ "loss": 0.3978,
1034
+ "step": 720
1035
+ },
1036
+ {
1037
+ "epoch": 1.1865793780687397,
1038
+ "grad_norm": 0.515625,
1039
+ "learning_rate": 7.595307014548e-06,
1040
+ "loss": 0.4063,
1041
+ "step": 725
1042
+ },
1043
+ {
1044
+ "epoch": 1.1947626841243864,
1045
+ "grad_norm": 0.51953125,
1046
+ "learning_rate": 7.5646755217889555e-06,
1047
+ "loss": 0.3915,
1048
+ "step": 730
1049
+ },
1050
+ {
1051
+ "epoch": 1.2029459901800328,
1052
+ "grad_norm": 0.5234375,
1053
+ "learning_rate": 7.533943688545391e-06,
1054
+ "loss": 0.4024,
1055
+ "step": 735
1056
+ },
1057
+ {
1058
+ "epoch": 1.2111292962356792,
1059
+ "grad_norm": 0.51171875,
1060
+ "learning_rate": 7.503113860374813e-06,
1061
+ "loss": 0.4142,
1062
+ "step": 740
1063
+ },
1064
+ {
1065
+ "epoch": 1.2193126022913257,
1066
+ "grad_norm": 0.53125,
1067
+ "learning_rate": 7.472188390314029e-06,
1068
+ "loss": 0.3906,
1069
+ "step": 745
1070
+ },
1071
+ {
1072
+ "epoch": 1.227495908346972,
1073
+ "grad_norm": 0.54296875,
1074
+ "learning_rate": 7.441169638699565e-06,
1075
+ "loss": 0.3984,
1076
+ "step": 750
1077
+ },
1078
+ {
1079
+ "epoch": 1.2356792144026187,
1080
+ "grad_norm": 0.51171875,
1081
+ "learning_rate": 7.4100599729875045e-06,
1082
+ "loss": 0.3901,
1083
+ "step": 755
1084
+ },
1085
+ {
1086
+ "epoch": 1.2405891980360066,
1087
+ "eval_loss": 0.39578545093536377,
1088
+ "eval_runtime": 5.0485,
1089
+ "eval_samples_per_second": 16.441,
1090
+ "eval_steps_per_second": 16.441,
1091
+ "step": 758
1092
+ },
1093
+ {
1094
+ "epoch": 1.2438625204582652,
1095
+ "grad_norm": 0.53515625,
1096
+ "learning_rate": 7.378861767572808e-06,
1097
+ "loss": 0.3995,
1098
+ "step": 760
1099
+ },
1100
+ {
1101
+ "epoch": 1.2520458265139116,
1102
+ "grad_norm": 0.54296875,
1103
+ "learning_rate": 7.347577403608084e-06,
1104
+ "loss": 0.3964,
1105
+ "step": 765
1106
+ },
1107
+ {
1108
+ "epoch": 1.260229132569558,
1109
+ "grad_norm": 0.53515625,
1110
+ "learning_rate": 7.316209268821852e-06,
1111
+ "loss": 0.3901,
1112
+ "step": 770
1113
+ },
1114
+ {
1115
+ "epoch": 1.2684124386252047,
1116
+ "grad_norm": 0.5546875,
1117
+ "learning_rate": 7.284759757336304e-06,
1118
+ "loss": 0.3886,
1119
+ "step": 775
1120
+ },
1121
+ {
1122
+ "epoch": 1.2765957446808511,
1123
+ "grad_norm": 0.51171875,
1124
+ "learning_rate": 7.25323126948458e-06,
1125
+ "loss": 0.4042,
1126
+ "step": 780
1127
+ },
1128
+ {
1129
+ "epoch": 1.2847790507364976,
1130
+ "grad_norm": 0.5234375,
1131
+ "learning_rate": 7.221626211627557e-06,
1132
+ "loss": 0.3994,
1133
+ "step": 785
1134
+ },
1135
+ {
1136
+ "epoch": 1.292962356792144,
1137
+ "grad_norm": 0.53125,
1138
+ "learning_rate": 7.1899469959702024e-06,
1139
+ "loss": 0.3935,
1140
+ "step": 790
1141
+ },
1142
+ {
1143
+ "epoch": 1.3011456628477904,
1144
+ "grad_norm": 0.50390625,
1145
+ "learning_rate": 7.158196040377452e-06,
1146
+ "loss": 0.3902,
1147
+ "step": 795
1148
+ },
1149
+ {
1150
+ "epoch": 1.3093289689034369,
1151
+ "grad_norm": 0.5,
1152
+ "learning_rate": 7.12637576818968e-06,
1153
+ "loss": 0.3938,
1154
+ "step": 800
1155
+ },
1156
+ {
1157
+ "epoch": 1.3175122749590835,
1158
+ "grad_norm": 0.5078125,
1159
+ "learning_rate": 7.094488608037731e-06,
1160
+ "loss": 0.3892,
1161
+ "step": 805
1162
+ },
1163
+ {
1164
+ "epoch": 1.32569558101473,
1165
+ "grad_norm": 0.51171875,
1166
+ "learning_rate": 7.062536993657574e-06,
1167
+ "loss": 0.3957,
1168
+ "step": 810
1169
+ },
1170
+ {
1171
+ "epoch": 1.3338788870703764,
1172
+ "grad_norm": 0.52734375,
1173
+ "learning_rate": 7.0305233637045375e-06,
1174
+ "loss": 0.4083,
1175
+ "step": 815
1176
+ },
1177
+ {
1178
+ "epoch": 1.342062193126023,
1179
+ "grad_norm": 0.50390625,
1180
+ "learning_rate": 6.998450161567189e-06,
1181
+ "loss": 0.3917,
1182
+ "step": 820
1183
+ },
1184
+ {
1185
+ "epoch": 1.3502454991816695,
1186
+ "grad_norm": 0.53125,
1187
+ "learning_rate": 6.966319835180849e-06,
1188
+ "loss": 0.3878,
1189
+ "step": 825
1190
+ },
1191
+ {
1192
+ "epoch": 1.358428805237316,
1193
+ "grad_norm": 0.53125,
1194
+ "learning_rate": 6.9341348368407505e-06,
1195
+ "loss": 0.4083,
1196
+ "step": 830
1197
+ },
1198
+ {
1199
+ "epoch": 1.3666121112929623,
1200
+ "grad_norm": 0.515625,
1201
+ "learning_rate": 6.901897623014877e-06,
1202
+ "loss": 0.3942,
1203
+ "step": 835
1204
+ },
1205
+ {
1206
+ "epoch": 1.3747954173486088,
1207
+ "grad_norm": 0.5078125,
1208
+ "learning_rate": 6.869610654156476e-06,
1209
+ "loss": 0.3856,
1210
+ "step": 840
1211
+ },
1212
+ {
1213
+ "epoch": 1.3829787234042552,
1214
+ "grad_norm": 0.51953125,
1215
+ "learning_rate": 6.837276394516264e-06,
1216
+ "loss": 0.4077,
1217
+ "step": 845
1218
+ },
1219
+ {
1220
+ "epoch": 1.3911620294599019,
1221
+ "grad_norm": 0.52734375,
1222
+ "learning_rate": 6.804897311954354e-06,
1223
+ "loss": 0.3987,
1224
+ "step": 850
1225
+ },
1226
+ {
1227
+ "epoch": 1.3993453355155483,
1228
+ "grad_norm": 0.53125,
1229
+ "learning_rate": 6.77247587775189e-06,
1230
+ "loss": 0.4003,
1231
+ "step": 855
1232
+ },
1233
+ {
1234
+ "epoch": 1.4075286415711947,
1235
+ "grad_norm": 0.52734375,
1236
+ "learning_rate": 6.7400145664224445e-06,
1237
+ "loss": 0.4041,
1238
+ "step": 860
1239
+ },
1240
+ {
1241
+ "epoch": 1.4157119476268412,
1242
+ "grad_norm": 0.5234375,
1243
+ "learning_rate": 6.707515855523141e-06,
1244
+ "loss": 0.4082,
1245
+ "step": 865
1246
+ },
1247
+ {
1248
+ "epoch": 1.4238952536824878,
1249
+ "grad_norm": 0.5,
1250
+ "learning_rate": 6.674982225465568e-06,
1251
+ "loss": 0.3739,
1252
+ "step": 870
1253
+ },
1254
+ {
1255
+ "epoch": 1.4320785597381342,
1256
+ "grad_norm": 0.5,
1257
+ "learning_rate": 6.642416159326462e-06,
1258
+ "loss": 0.3866,
1259
+ "step": 875
1260
+ },
1261
+ {
1262
+ "epoch": 1.4402618657937807,
1263
+ "grad_norm": 0.5234375,
1264
+ "learning_rate": 6.609820142658186e-06,
1265
+ "loss": 0.4101,
1266
+ "step": 880
1267
+ },
1268
+ {
1269
+ "epoch": 1.4484451718494271,
1270
+ "grad_norm": 0.5234375,
1271
+ "learning_rate": 6.577196663299039e-06,
1272
+ "loss": 0.3888,
1273
+ "step": 885
1274
+ },
1275
+ {
1276
+ "epoch": 1.4566284779050735,
1277
+ "grad_norm": 0.50390625,
1278
+ "learning_rate": 6.544548211183355e-06,
1279
+ "loss": 0.3937,
1280
+ "step": 890
1281
+ },
1282
+ {
1283
+ "epoch": 1.4648117839607202,
1284
+ "grad_norm": 0.53125,
1285
+ "learning_rate": 6.511877278151479e-06,
1286
+ "loss": 0.3989,
1287
+ "step": 895
1288
+ },
1289
+ {
1290
+ "epoch": 1.4729950900163666,
1291
+ "grad_norm": 0.5078125,
1292
+ "learning_rate": 6.479186357759575e-06,
1293
+ "loss": 0.4157,
1294
+ "step": 900
1295
+ },
1296
+ {
1297
+ "epoch": 1.481178396072013,
1298
+ "grad_norm": 0.52734375,
1299
+ "learning_rate": 6.4464779450893086e-06,
1300
+ "loss": 0.388,
1301
+ "step": 905
1302
+ },
1303
+ {
1304
+ "epoch": 1.4893617021276595,
1305
+ "grad_norm": 0.50390625,
1306
+ "learning_rate": 6.413754536557416e-06,
1307
+ "loss": 0.3916,
1308
+ "step": 910
1309
+ },
1310
+ {
1311
+ "epoch": 1.4975450081833062,
1312
+ "grad_norm": 0.52734375,
1313
+ "learning_rate": 6.381018629725169e-06,
1314
+ "loss": 0.4073,
1315
+ "step": 915
1316
+ },
1317
+ {
1318
+ "epoch": 1.5057283142389526,
1319
+ "grad_norm": 0.53125,
1320
+ "learning_rate": 6.34827272310775e-06,
1321
+ "loss": 0.401,
1322
+ "step": 920
1323
+ },
1324
+ {
1325
+ "epoch": 1.513911620294599,
1326
+ "grad_norm": 0.515625,
1327
+ "learning_rate": 6.315519315983562e-06,
1328
+ "loss": 0.3859,
1329
+ "step": 925
1330
+ },
1331
+ {
1332
+ "epoch": 1.5220949263502455,
1333
+ "grad_norm": 0.51171875,
1334
+ "learning_rate": 6.282760908203467e-06,
1335
+ "loss": 0.3952,
1336
+ "step": 930
1337
+ },
1338
+ {
1339
+ "epoch": 1.530278232405892,
1340
+ "grad_norm": 0.50390625,
1341
+ "learning_rate": 6.25e-06,
1342
+ "loss": 0.384,
1343
+ "step": 935
1344
+ },
1345
+ {
1346
+ "epoch": 1.5384615384615383,
1347
+ "grad_norm": 0.53125,
1348
+ "learning_rate": 6.2172390917965345e-06,
1349
+ "loss": 0.3937,
1350
+ "step": 940
1351
+ },
1352
+ {
1353
+ "epoch": 1.546644844517185,
1354
+ "grad_norm": 0.490234375,
1355
+ "learning_rate": 6.18448068401644e-06,
1356
+ "loss": 0.3811,
1357
+ "step": 945
1358
+ },
1359
+ {
1360
+ "epoch": 1.5548281505728314,
1361
+ "grad_norm": 0.54296875,
1362
+ "learning_rate": 6.151727276892252e-06,
1363
+ "loss": 0.3966,
1364
+ "step": 950
1365
+ },
1366
+ {
1367
+ "epoch": 1.563011456628478,
1368
+ "grad_norm": 0.53125,
1369
+ "learning_rate": 6.118981370274833e-06,
1370
+ "loss": 0.4045,
1371
+ "step": 955
1372
+ },
1373
+ {
1374
+ "epoch": 1.5711947626841245,
1375
+ "grad_norm": 0.53125,
1376
+ "learning_rate": 6.086245463442586e-06,
1377
+ "loss": 0.3798,
1378
+ "step": 960
1379
+ },
1380
+ {
1381
+ "epoch": 1.579378068739771,
1382
+ "grad_norm": 0.53515625,
1383
+ "learning_rate": 6.0535220549106946e-06,
1384
+ "loss": 0.4011,
1385
+ "step": 965
1386
+ },
1387
+ {
1388
+ "epoch": 1.5875613747954174,
1389
+ "grad_norm": 0.53125,
1390
+ "learning_rate": 6.020813642240426e-06,
1391
+ "loss": 0.3887,
1392
+ "step": 970
1393
+ },
1394
+ {
1395
+ "epoch": 1.5957446808510638,
1396
+ "grad_norm": 0.52734375,
1397
+ "learning_rate": 5.988122721848521e-06,
1398
+ "loss": 0.4012,
1399
+ "step": 975
1400
+ },
1401
+ {
1402
+ "epoch": 1.6039279869067102,
1403
+ "grad_norm": 0.52734375,
1404
+ "learning_rate": 5.955451788816645e-06,
1405
+ "loss": 0.403,
1406
+ "step": 980
1407
+ },
1408
+ {
1409
+ "epoch": 1.6121112929623567,
1410
+ "grad_norm": 0.52734375,
1411
+ "learning_rate": 5.922803336700962e-06,
1412
+ "loss": 0.3879,
1413
+ "step": 985
1414
+ },
1415
+ {
1416
+ "epoch": 1.6202945990180033,
1417
+ "grad_norm": 0.55859375,
1418
+ "learning_rate": 5.890179857341814e-06,
1419
+ "loss": 0.4001,
1420
+ "step": 990
1421
+ },
1422
+ {
1423
+ "epoch": 1.6284779050736498,
1424
+ "grad_norm": 0.51953125,
1425
+ "learning_rate": 5.85758384067354e-06,
1426
+ "loss": 0.4184,
1427
+ "step": 995
1428
+ },
1429
+ {
1430
+ "epoch": 1.6366612111292962,
1431
+ "grad_norm": 0.51953125,
1432
+ "learning_rate": 5.825017774534434e-06,
1433
+ "loss": 0.4192,
1434
+ "step": 1000
1435
+ },
1436
+ {
1437
+ "epoch": 1.6366612111292962,
1438
+ "eval_loss": 0.3935750126838684,
1439
+ "eval_runtime": 5.036,
1440
+ "eval_samples_per_second": 16.481,
1441
+ "eval_steps_per_second": 16.481,
1442
+ "step": 1000
1443
+ },
1444
+ {
1445
+ "epoch": 1.6448445171849428,
1446
+ "grad_norm": 0.53125,
1447
+ "learning_rate": 5.7924841444768585e-06,
1448
+ "loss": 0.3859,
1449
+ "step": 1005
1450
+ },
1451
+ {
1452
+ "epoch": 1.6530278232405893,
1453
+ "grad_norm": 0.51171875,
1454
+ "learning_rate": 5.759985433577557e-06,
1455
+ "loss": 0.3973,
1456
+ "step": 1010
1457
+ },
1458
+ {
1459
+ "epoch": 1.6612111292962357,
1460
+ "grad_norm": 0.52734375,
1461
+ "learning_rate": 5.727524122248112e-06,
1462
+ "loss": 0.4077,
1463
+ "step": 1015
1464
+ },
1465
+ {
1466
+ "epoch": 1.6693944353518821,
1467
+ "grad_norm": 0.51171875,
1468
+ "learning_rate": 5.695102688045649e-06,
1469
+ "loss": 0.3916,
1470
+ "step": 1020
1471
+ },
1472
+ {
1473
+ "epoch": 1.6775777414075286,
1474
+ "grad_norm": 0.50390625,
1475
+ "learning_rate": 5.662723605483738e-06,
1476
+ "loss": 0.3852,
1477
+ "step": 1025
1478
+ },
1479
+ {
1480
+ "epoch": 1.685761047463175,
1481
+ "grad_norm": 0.546875,
1482
+ "learning_rate": 5.6303893458435255e-06,
1483
+ "loss": 0.4055,
1484
+ "step": 1030
1485
+ },
1486
+ {
1487
+ "epoch": 1.6939443535188214,
1488
+ "grad_norm": 0.5390625,
1489
+ "learning_rate": 5.598102376985124e-06,
1490
+ "loss": 0.4046,
1491
+ "step": 1035
1492
+ },
1493
+ {
1494
+ "epoch": 1.702127659574468,
1495
+ "grad_norm": 0.53515625,
1496
+ "learning_rate": 5.565865163159252e-06,
1497
+ "loss": 0.3868,
1498
+ "step": 1040
1499
+ },
1500
+ {
1501
+ "epoch": 1.7103109656301145,
1502
+ "grad_norm": 0.51171875,
1503
+ "learning_rate": 5.5336801648191525e-06,
1504
+ "loss": 0.3929,
1505
+ "step": 1045
1506
+ },
1507
+ {
1508
+ "epoch": 1.7184942716857612,
1509
+ "grad_norm": 0.52734375,
1510
+ "learning_rate": 5.501549838432812e-06,
1511
+ "loss": 0.4018,
1512
+ "step": 1050
1513
+ },
1514
+ {
1515
+ "epoch": 1.7266775777414076,
1516
+ "grad_norm": 0.52734375,
1517
+ "learning_rate": 5.469476636295463e-06,
1518
+ "loss": 0.4009,
1519
+ "step": 1055
1520
+ },
1521
+ {
1522
+ "epoch": 1.734860883797054,
1523
+ "grad_norm": 0.5390625,
1524
+ "learning_rate": 5.437463006342427e-06,
1525
+ "loss": 0.3959,
1526
+ "step": 1060
1527
+ },
1528
+ {
1529
+ "epoch": 1.7430441898527005,
1530
+ "grad_norm": 0.51953125,
1531
+ "learning_rate": 5.4055113919622714e-06,
1532
+ "loss": 0.3921,
1533
+ "step": 1065
1534
+ },
1535
+ {
1536
+ "epoch": 1.751227495908347,
1537
+ "grad_norm": 0.53125,
1538
+ "learning_rate": 5.373624231810322e-06,
1539
+ "loss": 0.3869,
1540
+ "step": 1070
1541
+ },
1542
+ {
1543
+ "epoch": 1.7594108019639934,
1544
+ "grad_norm": 0.52734375,
1545
+ "learning_rate": 5.341803959622549e-06,
1546
+ "loss": 0.3866,
1547
+ "step": 1075
1548
+ },
1549
+ {
1550
+ "epoch": 1.7675941080196398,
1551
+ "grad_norm": 0.52734375,
1552
+ "learning_rate": 5.310053004029798e-06,
1553
+ "loss": 0.3853,
1554
+ "step": 1080
1555
+ },
1556
+ {
1557
+ "epoch": 1.7757774140752864,
1558
+ "grad_norm": 0.54296875,
1559
+ "learning_rate": 5.278373788372444e-06,
1560
+ "loss": 0.4065,
1561
+ "step": 1085
1562
+ },
1563
+ {
1564
+ "epoch": 1.7839607201309329,
1565
+ "grad_norm": 0.49609375,
1566
+ "learning_rate": 5.246768730515424e-06,
1567
+ "loss": 0.3839,
1568
+ "step": 1090
1569
+ },
1570
+ {
1571
+ "epoch": 1.7921440261865795,
1572
+ "grad_norm": 0.515625,
1573
+ "learning_rate": 5.2152402426636975e-06,
1574
+ "loss": 0.3914,
1575
+ "step": 1095
1576
+ },
1577
+ {
1578
+ "epoch": 1.800327332242226,
1579
+ "grad_norm": 0.53125,
1580
+ "learning_rate": 5.183790731178151e-06,
1581
+ "loss": 0.3846,
1582
+ "step": 1100
1583
+ },
1584
+ {
1585
+ "epoch": 1.8085106382978724,
1586
+ "grad_norm": 0.51171875,
1587
+ "learning_rate": 5.152422596391917e-06,
1588
+ "loss": 0.3841,
1589
+ "step": 1105
1590
+ },
1591
+ {
1592
+ "epoch": 1.8166939443535188,
1593
+ "grad_norm": 0.5078125,
1594
+ "learning_rate": 5.121138232427193e-06,
1595
+ "loss": 0.3932,
1596
+ "step": 1110
1597
+ },
1598
+ {
1599
+ "epoch": 1.8248772504091653,
1600
+ "grad_norm": 0.52734375,
1601
+ "learning_rate": 5.089940027012498e-06,
1602
+ "loss": 0.4066,
1603
+ "step": 1115
1604
+ },
1605
+ {
1606
+ "epoch": 1.8330605564648117,
1607
+ "grad_norm": 0.53515625,
1608
+ "learning_rate": 5.058830361300437e-06,
1609
+ "loss": 0.3977,
1610
+ "step": 1120
1611
+ },
1612
+ {
1613
+ "epoch": 1.8412438625204581,
1614
+ "grad_norm": 0.54296875,
1615
+ "learning_rate": 5.027811609685972e-06,
1616
+ "loss": 0.4038,
1617
+ "step": 1125
1618
+ },
1619
+ {
1620
+ "epoch": 1.8494271685761048,
1621
+ "grad_norm": 0.51953125,
1622
+ "learning_rate": 4.9968861396251884e-06,
1623
+ "loss": 0.3984,
1624
+ "step": 1130
1625
+ },
1626
+ {
1627
+ "epoch": 1.8576104746317512,
1628
+ "grad_norm": 0.5390625,
1629
+ "learning_rate": 4.96605631145461e-06,
1630
+ "loss": 0.3976,
1631
+ "step": 1135
1632
+ },
1633
+ {
1634
+ "epoch": 1.8657937806873979,
1635
+ "grad_norm": 0.53515625,
1636
+ "learning_rate": 4.935324478211047e-06,
1637
+ "loss": 0.4076,
1638
+ "step": 1140
1639
+ },
1640
+ {
1641
+ "epoch": 1.8739770867430443,
1642
+ "grad_norm": 0.5234375,
1643
+ "learning_rate": 4.9046929854520014e-06,
1644
+ "loss": 0.3916,
1645
+ "step": 1145
1646
+ },
1647
+ {
1648
+ "epoch": 1.8821603927986907,
1649
+ "grad_norm": 0.51171875,
1650
+ "learning_rate": 4.8741641710766595e-06,
1651
+ "loss": 0.3976,
1652
+ "step": 1150
1653
+ },
1654
+ {
1655
+ "epoch": 1.8903436988543372,
1656
+ "grad_norm": 0.54296875,
1657
+ "learning_rate": 4.843740365147435e-06,
1658
+ "loss": 0.4034,
1659
+ "step": 1155
1660
+ },
1661
+ {
1662
+ "epoch": 1.8985270049099836,
1663
+ "grad_norm": 0.5,
1664
+ "learning_rate": 4.8134238897121515e-06,
1665
+ "loss": 0.4105,
1666
+ "step": 1160
1667
+ },
1668
+ {
1669
+ "epoch": 1.90671031096563,
1670
+ "grad_norm": 0.55078125,
1671
+ "learning_rate": 4.783217058626799e-06,
1672
+ "loss": 0.4022,
1673
+ "step": 1165
1674
+ },
1675
+ {
1676
+ "epoch": 1.9148936170212765,
1677
+ "grad_norm": 0.5625,
1678
+ "learning_rate": 4.753122177378941e-06,
1679
+ "loss": 0.3885,
1680
+ "step": 1170
1681
+ },
1682
+ {
1683
+ "epoch": 1.9230769230769231,
1684
+ "grad_norm": 0.5234375,
1685
+ "learning_rate": 4.723141542911755e-06,
1686
+ "loss": 0.4192,
1687
+ "step": 1175
1688
+ },
1689
+ {
1690
+ "epoch": 1.9312602291325696,
1691
+ "grad_norm": 0.5,
1692
+ "learning_rate": 4.693277443448709e-06,
1693
+ "loss": 0.3854,
1694
+ "step": 1180
1695
+ },
1696
+ {
1697
+ "epoch": 1.939443535188216,
1698
+ "grad_norm": 0.5546875,
1699
+ "learning_rate": 4.663532158318936e-06,
1700
+ "loss": 0.4069,
1701
+ "step": 1185
1702
+ },
1703
+ {
1704
+ "epoch": 1.9476268412438626,
1705
+ "grad_norm": 0.5078125,
1706
+ "learning_rate": 4.633907957783249e-06,
1707
+ "loss": 0.4069,
1708
+ "step": 1190
1709
+ },
1710
+ {
1711
+ "epoch": 1.955810147299509,
1712
+ "grad_norm": 0.5546875,
1713
+ "learning_rate": 4.604407102860875e-06,
1714
+ "loss": 0.4052,
1715
+ "step": 1195
1716
+ },
1717
+ {
1718
+ "epoch": 1.9639934533551555,
1719
+ "grad_norm": 0.54296875,
1720
+ "learning_rate": 4.575031845156893e-06,
1721
+ "loss": 0.4004,
1722
+ "step": 1200
1723
+ },
1724
+ {
1725
+ "epoch": 1.972176759410802,
1726
+ "grad_norm": 0.51953125,
1727
+ "learning_rate": 4.545784426690371e-06,
1728
+ "loss": 0.3926,
1729
+ "step": 1205
1730
+ },
1731
+ {
1732
+ "epoch": 1.9803600654664484,
1733
+ "grad_norm": 0.5078125,
1734
+ "learning_rate": 4.516667079723257e-06,
1735
+ "loss": 0.3958,
1736
+ "step": 1210
1737
+ },
1738
+ {
1739
+ "epoch": 1.9885433715220948,
1740
+ "grad_norm": 0.515625,
1741
+ "learning_rate": 4.48768202659e-06,
1742
+ "loss": 0.401,
1743
+ "step": 1215
1744
+ },
1745
+ {
1746
+ "epoch": 1.9967266775777412,
1747
+ "grad_norm": 0.53125,
1748
+ "learning_rate": 4.458831479527936e-06,
1749
+ "loss": 0.392,
1750
+ "step": 1220
1751
+ },
1752
+ {
1753
+ "epoch": 1.9967266775777412,
1754
+ "eval_loss": 0.3923807144165039,
1755
+ "eval_runtime": 5.0473,
1756
+ "eval_samples_per_second": 16.445,
1757
+ "eval_steps_per_second": 16.445,
1758
+ "step": 1220
1759
+ },
1760
+ {
1761
+ "epoch": 2.0049099836333877,
1762
+ "grad_norm": 0.49609375,
1763
+ "learning_rate": 4.430117640508447e-06,
1764
+ "loss": 0.3889,
1765
+ "step": 1225
1766
+ },
1767
+ {
1768
+ "epoch": 2.0130932896890346,
1769
+ "grad_norm": 0.53125,
1770
+ "learning_rate": 4.401542701068887e-06,
1771
+ "loss": 0.3813,
1772
+ "step": 1230
1773
+ },
1774
+ {
1775
+ "epoch": 2.021276595744681,
1776
+ "grad_norm": 0.51171875,
1777
+ "learning_rate": 4.373108842145332e-06,
1778
+ "loss": 0.3885,
1779
+ "step": 1235
1780
+ },
1781
+ {
1782
+ "epoch": 2.0294599018003274,
1783
+ "grad_norm": 0.49609375,
1784
+ "learning_rate": 4.344818233906108e-06,
1785
+ "loss": 0.388,
1786
+ "step": 1240
1787
+ },
1788
+ {
1789
+ "epoch": 2.037643207855974,
1790
+ "grad_norm": 0.49609375,
1791
+ "learning_rate": 4.316673035586168e-06,
1792
+ "loss": 0.3848,
1793
+ "step": 1245
1794
+ },
1795
+ {
1796
+ "epoch": 2.0458265139116203,
1797
+ "grad_norm": 0.5078125,
1798
+ "learning_rate": 4.288675395322291e-06,
1799
+ "loss": 0.3885,
1800
+ "step": 1250
1801
+ },
1802
+ {
1803
+ "epoch": 2.0540098199672667,
1804
+ "grad_norm": 0.5546875,
1805
+ "learning_rate": 4.26082744998912e-06,
1806
+ "loss": 0.382,
1807
+ "step": 1255
1808
+ },
1809
+ {
1810
+ "epoch": 2.062193126022913,
1811
+ "grad_norm": 0.5234375,
1812
+ "learning_rate": 4.233131325036077e-06,
1813
+ "loss": 0.38,
1814
+ "step": 1260
1815
+ },
1816
+ {
1817
+ "epoch": 2.0703764320785596,
1818
+ "grad_norm": 0.5234375,
1819
+ "learning_rate": 4.205589134325138e-06,
1820
+ "loss": 0.3926,
1821
+ "step": 1265
1822
+ },
1823
+ {
1824
+ "epoch": 2.078559738134206,
1825
+ "grad_norm": 0.515625,
1826
+ "learning_rate": 4.178202979969499e-06,
1827
+ "loss": 0.3936,
1828
+ "step": 1270
1829
+ },
1830
+ {
1831
+ "epoch": 2.086743044189853,
1832
+ "grad_norm": 0.53125,
1833
+ "learning_rate": 4.15097495217313e-06,
1834
+ "loss": 0.3862,
1835
+ "step": 1275
1836
+ },
1837
+ {
1838
+ "epoch": 2.0949263502454993,
1839
+ "grad_norm": 0.5546875,
1840
+ "learning_rate": 4.1239071290712485e-06,
1841
+ "loss": 0.3968,
1842
+ "step": 1280
1843
+ },
1844
+ {
1845
+ "epoch": 2.1031096563011458,
1846
+ "grad_norm": 0.52734375,
1847
+ "learning_rate": 4.0970015765717105e-06,
1848
+ "loss": 0.4087,
1849
+ "step": 1285
1850
+ },
1851
+ {
1852
+ "epoch": 2.111292962356792,
1853
+ "grad_norm": 0.5078125,
1854
+ "learning_rate": 4.070260348197324e-06,
1855
+ "loss": 0.3784,
1856
+ "step": 1290
1857
+ },
1858
+ {
1859
+ "epoch": 2.1194762684124386,
1860
+ "grad_norm": 0.51953125,
1861
+ "learning_rate": 4.043685484929132e-06,
1862
+ "loss": 0.3852,
1863
+ "step": 1295
1864
+ },
1865
+ {
1866
+ "epoch": 2.127659574468085,
1867
+ "grad_norm": 0.50390625,
1868
+ "learning_rate": 4.0172790150506215e-06,
1869
+ "loss": 0.3756,
1870
+ "step": 1300
1871
+ },
1872
+ {
1873
+ "epoch": 2.1358428805237315,
1874
+ "grad_norm": 0.5234375,
1875
+ "learning_rate": 3.991042953992931e-06,
1876
+ "loss": 0.3841,
1877
+ "step": 1305
1878
+ },
1879
+ {
1880
+ "epoch": 2.144026186579378,
1881
+ "grad_norm": 0.52734375,
1882
+ "learning_rate": 3.96497930418102e-06,
1883
+ "loss": 0.3847,
1884
+ "step": 1310
1885
+ },
1886
+ {
1887
+ "epoch": 2.1522094926350244,
1888
+ "grad_norm": 0.515625,
1889
+ "learning_rate": 3.939090054880839e-06,
1890
+ "loss": 0.3826,
1891
+ "step": 1315
1892
+ },
1893
+ {
1894
+ "epoch": 2.160392798690671,
1895
+ "grad_norm": 0.5078125,
1896
+ "learning_rate": 3.913377182047498e-06,
1897
+ "loss": 0.3882,
1898
+ "step": 1320
1899
+ },
1900
+ {
1901
+ "epoch": 2.1685761047463177,
1902
+ "grad_norm": 0.53515625,
1903
+ "learning_rate": 3.887842648174465e-06,
1904
+ "loss": 0.3998,
1905
+ "step": 1325
1906
+ },
1907
+ {
1908
+ "epoch": 2.176759410801964,
1909
+ "grad_norm": 0.51171875,
1910
+ "learning_rate": 3.862488402143767e-06,
1911
+ "loss": 0.3782,
1912
+ "step": 1330
1913
+ },
1914
+ {
1915
+ "epoch": 2.1849427168576105,
1916
+ "grad_norm": 0.53125,
1917
+ "learning_rate": 3.8373163790772595e-06,
1918
+ "loss": 0.3937,
1919
+ "step": 1335
1920
+ },
1921
+ {
1922
+ "epoch": 2.193126022913257,
1923
+ "grad_norm": 0.51953125,
1924
+ "learning_rate": 3.812328500188919e-06,
1925
+ "loss": 0.3967,
1926
+ "step": 1340
1927
+ },
1928
+ {
1929
+ "epoch": 2.2013093289689034,
1930
+ "grad_norm": 0.54296875,
1931
+ "learning_rate": 3.78752667263822e-06,
1932
+ "loss": 0.3856,
1933
+ "step": 1345
1934
+ },
1935
+ {
1936
+ "epoch": 2.20949263502455,
1937
+ "grad_norm": 0.5078125,
1938
+ "learning_rate": 3.762912789384568e-06,
1939
+ "loss": 0.377,
1940
+ "step": 1350
1941
+ },
1942
+ {
1943
+ "epoch": 2.2176759410801963,
1944
+ "grad_norm": 0.53125,
1945
+ "learning_rate": 3.738488729042821e-06,
1946
+ "loss": 0.3853,
1947
+ "step": 1355
1948
+ },
1949
+ {
1950
+ "epoch": 2.2258592471358427,
1951
+ "grad_norm": 0.5234375,
1952
+ "learning_rate": 3.7142563557399145e-06,
1953
+ "loss": 0.386,
1954
+ "step": 1360
1955
+ },
1956
+ {
1957
+ "epoch": 2.2340425531914896,
1958
+ "grad_norm": 0.51953125,
1959
+ "learning_rate": 3.6902175189725764e-06,
1960
+ "loss": 0.3881,
1961
+ "step": 1365
1962
+ },
1963
+ {
1964
+ "epoch": 2.242225859247136,
1965
+ "grad_norm": 0.51953125,
1966
+ "learning_rate": 3.666374053466175e-06,
1967
+ "loss": 0.3934,
1968
+ "step": 1370
1969
+ },
1970
+ {
1971
+ "epoch": 2.2504091653027825,
1972
+ "grad_norm": 0.53515625,
1973
+ "learning_rate": 3.642727779034681e-06,
1974
+ "loss": 0.391,
1975
+ "step": 1375
1976
+ },
1977
+ {
1978
+ "epoch": 2.258592471358429,
1979
+ "grad_norm": 0.5078125,
1980
+ "learning_rate": 3.6192805004417732e-06,
1981
+ "loss": 0.3818,
1982
+ "step": 1380
1983
+ },
1984
+ {
1985
+ "epoch": 2.2667757774140753,
1986
+ "grad_norm": 0.498046875,
1987
+ "learning_rate": 3.5960340072630984e-06,
1988
+ "loss": 0.3861,
1989
+ "step": 1385
1990
+ },
1991
+ {
1992
+ "epoch": 2.2749590834697218,
1993
+ "grad_norm": 0.51171875,
1994
+ "learning_rate": 3.572990073749678e-06,
1995
+ "loss": 0.3989,
1996
+ "step": 1390
1997
+ },
1998
+ {
1999
+ "epoch": 2.283142389525368,
2000
+ "grad_norm": 0.51171875,
2001
+ "learning_rate": 3.550150458692497e-06,
2002
+ "loss": 0.3973,
2003
+ "step": 1395
2004
+ },
2005
+ {
2006
+ "epoch": 2.2913256955810146,
2007
+ "grad_norm": 0.51171875,
2008
+ "learning_rate": 3.527516905288261e-06,
2009
+ "loss": 0.3724,
2010
+ "step": 1400
2011
+ },
2012
+ {
2013
+ "epoch": 2.299509001636661,
2014
+ "grad_norm": 0.51953125,
2015
+ "learning_rate": 3.505091141006354e-06,
2016
+ "loss": 0.3882,
2017
+ "step": 1405
2018
+ },
2019
+ {
2020
+ "epoch": 2.3076923076923075,
2021
+ "grad_norm": 0.5234375,
2022
+ "learning_rate": 3.4828748774569967e-06,
2023
+ "loss": 0.3945,
2024
+ "step": 1410
2025
+ },
2026
+ {
2027
+ "epoch": 2.3158756137479544,
2028
+ "grad_norm": 0.55078125,
2029
+ "learning_rate": 3.460869810260595e-06,
2030
+ "loss": 0.3919,
2031
+ "step": 1415
2032
+ },
2033
+ {
2034
+ "epoch": 2.324058919803601,
2035
+ "grad_norm": 0.52734375,
2036
+ "learning_rate": 3.4390776189183435e-06,
2037
+ "loss": 0.3875,
2038
+ "step": 1420
2039
+ },
2040
+ {
2041
+ "epoch": 2.3322422258592472,
2042
+ "grad_norm": 0.52734375,
2043
+ "learning_rate": 3.4174999666840257e-06,
2044
+ "loss": 0.3817,
2045
+ "step": 1425
2046
+ },
2047
+ {
2048
+ "epoch": 2.3404255319148937,
2049
+ "grad_norm": 0.51171875,
2050
+ "learning_rate": 3.396138500437076e-06,
2051
+ "loss": 0.392,
2052
+ "step": 1430
2053
+ },
2054
+ {
2055
+ "epoch": 2.34860883797054,
2056
+ "grad_norm": 0.5,
2057
+ "learning_rate": 3.374994850556884e-06,
2058
+ "loss": 0.3902,
2059
+ "step": 1435
2060
+ },
2061
+ {
2062
+ "epoch": 2.3567921440261865,
2063
+ "grad_norm": 0.53515625,
2064
+ "learning_rate": 3.354070630798355e-06,
2065
+ "loss": 0.3935,
2066
+ "step": 1440
2067
+ },
2068
+ {
2069
+ "epoch": 2.364975450081833,
2070
+ "grad_norm": 0.54296875,
2071
+ "learning_rate": 3.3333674381687476e-06,
2072
+ "loss": 0.3904,
2073
+ "step": 1445
2074
+ },
2075
+ {
2076
+ "epoch": 2.3731587561374794,
2077
+ "grad_norm": 0.53125,
2078
+ "learning_rate": 3.312886852805779e-06,
2079
+ "loss": 0.403,
2080
+ "step": 1450
2081
+ },
2082
+ {
2083
+ "epoch": 2.381342062193126,
2084
+ "grad_norm": 0.5234375,
2085
+ "learning_rate": 3.292630437857026e-06,
2086
+ "loss": 0.4007,
2087
+ "step": 1455
2088
+ },
2089
+ {
2090
+ "epoch": 2.3895253682487727,
2091
+ "grad_norm": 0.53515625,
2092
+ "learning_rate": 3.2725997393606266e-06,
2093
+ "loss": 0.3833,
2094
+ "step": 1460
2095
+ },
2096
+ {
2097
+ "epoch": 2.397708674304419,
2098
+ "grad_norm": 0.51953125,
2099
+ "learning_rate": 3.2527962861272695e-06,
2100
+ "loss": 0.3862,
2101
+ "step": 1465
2102
+ },
2103
+ {
2104
+ "epoch": 2.4058919803600656,
2105
+ "grad_norm": 0.5078125,
2106
+ "learning_rate": 3.2332215896235176e-06,
2107
+ "loss": 0.3923,
2108
+ "step": 1470
2109
+ },
2110
+ {
2111
+ "epoch": 2.414075286415712,
2112
+ "grad_norm": 0.50390625,
2113
+ "learning_rate": 3.2138771438564465e-06,
2114
+ "loss": 0.379,
2115
+ "step": 1475
2116
+ },
2117
+ {
2118
+ "epoch": 2.4222585924713584,
2119
+ "grad_norm": 0.546875,
2120
+ "learning_rate": 3.194764425259615e-06,
2121
+ "loss": 0.3766,
2122
+ "step": 1480
2123
+ },
2124
+ {
2125
+ "epoch": 2.430441898527005,
2126
+ "grad_norm": 0.50390625,
2127
+ "learning_rate": 3.1758848925803846e-06,
2128
+ "loss": 0.3904,
2129
+ "step": 1485
2130
+ },
2131
+ {
2132
+ "epoch": 2.4386252045826513,
2133
+ "grad_norm": 0.51953125,
2134
+ "learning_rate": 3.1572399867685727e-06,
2135
+ "loss": 0.3922,
2136
+ "step": 1490
2137
+ },
2138
+ {
2139
+ "epoch": 2.4468085106382977,
2140
+ "grad_norm": 0.5625,
2141
+ "learning_rate": 3.138831130866484e-06,
2142
+ "loss": 0.392,
2143
+ "step": 1495
2144
+ },
2145
+ {
2146
+ "epoch": 2.454991816693944,
2147
+ "grad_norm": 0.53125,
2148
+ "learning_rate": 3.1206597299002948e-06,
2149
+ "loss": 0.3825,
2150
+ "step": 1500
2151
+ },
2152
+ {
2153
+ "epoch": 2.454991816693944,
2154
+ "eval_loss": 0.39173567295074463,
2155
+ "eval_runtime": 5.0609,
2156
+ "eval_samples_per_second": 16.4,
2157
+ "eval_steps_per_second": 16.4,
2158
+ "step": 1500
2159
+ },
2160
+ {
2161
+ "epoch": 2.4631751227495906,
2162
+ "grad_norm": 0.53125,
2163
+ "learning_rate": 3.1027271707728147e-06,
2164
+ "loss": 0.3988,
2165
+ "step": 1505
2166
+ },
2167
+ {
2168
+ "epoch": 2.4713584288052375,
2169
+ "grad_norm": 0.53125,
2170
+ "learning_rate": 3.0850348221576405e-06,
2171
+ "loss": 0.3944,
2172
+ "step": 1510
2173
+ },
2174
+ {
2175
+ "epoch": 2.479541734860884,
2176
+ "grad_norm": 0.51953125,
2177
+ "learning_rate": 3.067584034394684e-06,
2178
+ "loss": 0.394,
2179
+ "step": 1515
2180
+ },
2181
+ {
2182
+ "epoch": 2.4877250409165304,
2183
+ "grad_norm": 0.51953125,
2184
+ "learning_rate": 3.050376139387121e-06,
2185
+ "loss": 0.3959,
2186
+ "step": 1520
2187
+ },
2188
+ {
2189
+ "epoch": 2.495908346972177,
2190
+ "grad_norm": 0.5078125,
2191
+ "learning_rate": 3.0334124504997275e-06,
2192
+ "loss": 0.384,
2193
+ "step": 1525
2194
+ },
2195
+ {
2196
+ "epoch": 2.504091653027823,
2197
+ "grad_norm": 0.53125,
2198
+ "learning_rate": 3.016694262458642e-06,
2199
+ "loss": 0.384,
2200
+ "step": 1530
2201
+ },
2202
+ {
2203
+ "epoch": 2.5122749590834696,
2204
+ "grad_norm": 0.50390625,
2205
+ "learning_rate": 3.0002228512525485e-06,
2206
+ "loss": 0.3892,
2207
+ "step": 1535
2208
+ },
2209
+ {
2210
+ "epoch": 2.520458265139116,
2211
+ "grad_norm": 0.51953125,
2212
+ "learning_rate": 2.983999474035285e-06,
2213
+ "loss": 0.3921,
2214
+ "step": 1540
2215
+ },
2216
+ {
2217
+ "epoch": 2.528641571194763,
2218
+ "grad_norm": 0.52734375,
2219
+ "learning_rate": 2.968025369029902e-06,
2220
+ "loss": 0.4082,
2221
+ "step": 1545
2222
+ },
2223
+ {
2224
+ "epoch": 2.5368248772504094,
2225
+ "grad_norm": 0.52734375,
2226
+ "learning_rate": 2.9523017554341465e-06,
2227
+ "loss": 0.3814,
2228
+ "step": 1550
2229
+ },
2230
+ {
2231
+ "epoch": 2.545008183306056,
2232
+ "grad_norm": 0.53125,
2233
+ "learning_rate": 2.9368298333274148e-06,
2234
+ "loss": 0.386,
2235
+ "step": 1555
2236
+ },
2237
+ {
2238
+ "epoch": 2.5531914893617023,
2239
+ "grad_norm": 0.51953125,
2240
+ "learning_rate": 2.921610783579157e-06,
2241
+ "loss": 0.3794,
2242
+ "step": 1560
2243
+ },
2244
+ {
2245
+ "epoch": 2.5613747954173487,
2246
+ "grad_norm": 0.5234375,
2247
+ "learning_rate": 2.9066457677587488e-06,
2248
+ "loss": 0.3805,
2249
+ "step": 1565
2250
+ },
2251
+ {
2252
+ "epoch": 2.569558101472995,
2253
+ "grad_norm": 0.53515625,
2254
+ "learning_rate": 2.891935928046839e-06,
2255
+ "loss": 0.4039,
2256
+ "step": 1570
2257
+ },
2258
+ {
2259
+ "epoch": 2.5777414075286416,
2260
+ "grad_norm": 0.5234375,
2261
+ "learning_rate": 2.8774823871481695e-06,
2262
+ "loss": 0.3814,
2263
+ "step": 1575
2264
+ },
2265
+ {
2266
+ "epoch": 2.585924713584288,
2267
+ "grad_norm": 0.53515625,
2268
+ "learning_rate": 2.86328624820589e-06,
2269
+ "loss": 0.3798,
2270
+ "step": 1580
2271
+ },
2272
+ {
2273
+ "epoch": 2.5941080196399344,
2274
+ "grad_norm": 0.54296875,
2275
+ "learning_rate": 2.8493485947173643e-06,
2276
+ "loss": 0.3909,
2277
+ "step": 1585
2278
+ },
2279
+ {
2280
+ "epoch": 2.602291325695581,
2281
+ "grad_norm": 0.53125,
2282
+ "learning_rate": 2.8356704904514683e-06,
2283
+ "loss": 0.3958,
2284
+ "step": 1590
2285
+ },
2286
+ {
2287
+ "epoch": 2.6104746317512273,
2288
+ "grad_norm": 0.54296875,
2289
+ "learning_rate": 2.8222529793674055e-06,
2290
+ "loss": 0.3929,
2291
+ "step": 1595
2292
+ },
2293
+ {
2294
+ "epoch": 2.6186579378068737,
2295
+ "grad_norm": 0.5234375,
2296
+ "learning_rate": 2.8090970855350252e-06,
2297
+ "loss": 0.4019,
2298
+ "step": 1600
2299
+ },
2300
+ {
2301
+ "epoch": 2.6268412438625206,
2302
+ "grad_norm": 0.51171875,
2303
+ "learning_rate": 2.7962038130566616e-06,
2304
+ "loss": 0.3837,
2305
+ "step": 1605
2306
+ },
2307
+ {
2308
+ "epoch": 2.635024549918167,
2309
+ "grad_norm": 0.51953125,
2310
+ "learning_rate": 2.783574145990501e-06,
2311
+ "loss": 0.4116,
2312
+ "step": 1610
2313
+ },
2314
+ {
2315
+ "epoch": 2.6432078559738135,
2316
+ "grad_norm": 0.51171875,
2317
+ "learning_rate": 2.7712090482754683e-06,
2318
+ "loss": 0.386,
2319
+ "step": 1615
2320
+ },
2321
+ {
2322
+ "epoch": 2.65139116202946,
2323
+ "grad_norm": 0.5234375,
2324
+ "learning_rate": 2.759109463657666e-06,
2325
+ "loss": 0.3837,
2326
+ "step": 1620
2327
+ },
2328
+ {
2329
+ "epoch": 2.6595744680851063,
2330
+ "grad_norm": 0.53515625,
2331
+ "learning_rate": 2.7472763156183346e-06,
2332
+ "loss": 0.4019,
2333
+ "step": 1625
2334
+ },
2335
+ {
2336
+ "epoch": 2.6677577741407528,
2337
+ "grad_norm": 0.50390625,
2338
+ "learning_rate": 2.735710507303374e-06,
2339
+ "loss": 0.4055,
2340
+ "step": 1630
2341
+ },
2342
+ {
2343
+ "epoch": 2.675941080196399,
2344
+ "grad_norm": 0.51953125,
2345
+ "learning_rate": 2.7244129214544123e-06,
2346
+ "loss": 0.3838,
2347
+ "step": 1635
2348
+ },
2349
+ {
2350
+ "epoch": 2.684124386252046,
2351
+ "grad_norm": 0.53515625,
2352
+ "learning_rate": 2.7133844203414305e-06,
2353
+ "loss": 0.3838,
2354
+ "step": 1640
2355
+ },
2356
+ {
2357
+ "epoch": 2.6923076923076925,
2358
+ "grad_norm": 0.55078125,
2359
+ "learning_rate": 2.7026258456969538e-06,
2360
+ "loss": 0.3999,
2361
+ "step": 1645
2362
+ },
2363
+ {
2364
+ "epoch": 2.700490998363339,
2365
+ "grad_norm": 0.50390625,
2366
+ "learning_rate": 2.6921380186518042e-06,
2367
+ "loss": 0.3993,
2368
+ "step": 1650
2369
+ },
2370
+ {
2371
+ "epoch": 2.7086743044189854,
2372
+ "grad_norm": 0.5078125,
2373
+ "learning_rate": 2.6819217396724305e-06,
2374
+ "loss": 0.3909,
2375
+ "step": 1655
2376
+ },
2377
+ {
2378
+ "epoch": 2.716857610474632,
2379
+ "grad_norm": 0.52734375,
2380
+ "learning_rate": 2.671977788499817e-06,
2381
+ "loss": 0.3932,
2382
+ "step": 1660
2383
+ },
2384
+ {
2385
+ "epoch": 2.7250409165302782,
2386
+ "grad_norm": 0.53125,
2387
+ "learning_rate": 2.6623069240899642e-06,
2388
+ "loss": 0.398,
2389
+ "step": 1665
2390
+ },
2391
+ {
2392
+ "epoch": 2.7332242225859247,
2393
+ "grad_norm": 0.5078125,
2394
+ "learning_rate": 2.6529098845559703e-06,
2395
+ "loss": 0.3899,
2396
+ "step": 1670
2397
+ },
2398
+ {
2399
+ "epoch": 2.741407528641571,
2400
+ "grad_norm": 0.52734375,
2401
+ "learning_rate": 2.6437873871116903e-06,
2402
+ "loss": 0.385,
2403
+ "step": 1675
2404
+ },
2405
+ {
2406
+ "epoch": 2.7495908346972175,
2407
+ "grad_norm": 0.5234375,
2408
+ "learning_rate": 2.6349401280169985e-06,
2409
+ "loss": 0.3903,
2410
+ "step": 1680
2411
+ },
2412
+ {
2413
+ "epoch": 2.757774140752864,
2414
+ "grad_norm": 0.51953125,
2415
+ "learning_rate": 2.6263687825246463e-06,
2416
+ "loss": 0.3708,
2417
+ "step": 1685
2418
+ },
2419
+ {
2420
+ "epoch": 2.7659574468085104,
2421
+ "grad_norm": 0.51171875,
2422
+ "learning_rate": 2.6180740048287274e-06,
2423
+ "loss": 0.3821,
2424
+ "step": 1690
2425
+ },
2426
+ {
2427
+ "epoch": 2.774140752864157,
2428
+ "grad_norm": 0.55859375,
2429
+ "learning_rate": 2.610056428014743e-06,
2430
+ "loss": 0.4001,
2431
+ "step": 1695
2432
+ },
2433
+ {
2434
+ "epoch": 2.7823240589198037,
2435
+ "grad_norm": 0.546875,
2436
+ "learning_rate": 2.6023166640112875e-06,
2437
+ "loss": 0.4013,
2438
+ "step": 1700
2439
+ },
2440
+ {
2441
+ "epoch": 2.79050736497545,
2442
+ "grad_norm": 0.52734375,
2443
+ "learning_rate": 2.594855303543338e-06,
2444
+ "loss": 0.3969,
2445
+ "step": 1705
2446
+ },
2447
+ {
2448
+ "epoch": 2.7986906710310966,
2449
+ "grad_norm": 0.5703125,
2450
+ "learning_rate": 2.587672916087175e-06,
2451
+ "loss": 0.4152,
2452
+ "step": 1710
2453
+ },
2454
+ {
2455
+ "epoch": 2.806873977086743,
2456
+ "grad_norm": 0.52734375,
2457
+ "learning_rate": 2.5807700498269134e-06,
2458
+ "loss": 0.3875,
2459
+ "step": 1715
2460
+ },
2461
+ {
2462
+ "epoch": 2.8150572831423895,
2463
+ "grad_norm": 0.51171875,
2464
+ "learning_rate": 2.574147231612665e-06,
2465
+ "loss": 0.3951,
2466
+ "step": 1720
2467
+ },
2468
+ {
2469
+ "epoch": 2.823240589198036,
2470
+ "grad_norm": 0.51953125,
2471
+ "learning_rate": 2.5678049669203252e-06,
2472
+ "loss": 0.404,
2473
+ "step": 1725
2474
+ },
2475
+ {
2476
+ "epoch": 2.8314238952536823,
2477
+ "grad_norm": 0.5390625,
2478
+ "learning_rate": 2.561743739812998e-06,
2479
+ "loss": 0.3845,
2480
+ "step": 1730
2481
+ },
2482
+ {
2483
+ "epoch": 2.839607201309329,
2484
+ "grad_norm": 0.5234375,
2485
+ "learning_rate": 2.5559640129040464e-06,
2486
+ "loss": 0.3885,
2487
+ "step": 1735
2488
+ },
2489
+ {
2490
+ "epoch": 2.8477905073649756,
2491
+ "grad_norm": 0.515625,
2492
+ "learning_rate": 2.550466227321786e-06,
2493
+ "loss": 0.3967,
2494
+ "step": 1740
2495
+ },
2496
+ {
2497
+ "epoch": 2.855973813420622,
2498
+ "grad_norm": 0.515625,
2499
+ "learning_rate": 2.545250802675816e-06,
2500
+ "loss": 0.3865,
2501
+ "step": 1745
2502
+ },
2503
+ {
2504
+ "epoch": 2.8641571194762685,
2505
+ "grad_norm": 0.51953125,
2506
+ "learning_rate": 2.540318137024994e-06,
2507
+ "loss": 0.3873,
2508
+ "step": 1750
2509
+ },
2510
+ {
2511
+ "epoch": 2.872340425531915,
2512
+ "grad_norm": 0.5546875,
2513
+ "learning_rate": 2.5356686068470537e-06,
2514
+ "loss": 0.3912,
2515
+ "step": 1755
2516
+ },
2517
+ {
2518
+ "epoch": 2.8805237315875614,
2519
+ "grad_norm": 0.53515625,
2520
+ "learning_rate": 2.5313025670098725e-06,
2521
+ "loss": 0.3949,
2522
+ "step": 1760
2523
+ },
2524
+ {
2525
+ "epoch": 2.888707037643208,
2526
+ "grad_norm": 0.546875,
2527
+ "learning_rate": 2.5272203507443836e-06,
2528
+ "loss": 0.3985,
2529
+ "step": 1765
2530
+ },
2531
+ {
2532
+ "epoch": 2.8968903436988542,
2533
+ "grad_norm": 0.53125,
2534
+ "learning_rate": 2.523422269619147e-06,
2535
+ "loss": 0.3831,
2536
+ "step": 1770
2537
+ },
2538
+ {
2539
+ "epoch": 2.9050736497545007,
2540
+ "grad_norm": 0.54296875,
2541
+ "learning_rate": 2.5199086135165664e-06,
2542
+ "loss": 0.3916,
2543
+ "step": 1775
2544
+ },
2545
+ {
2546
+ "epoch": 2.913256955810147,
2547
+ "grad_norm": 0.51171875,
2548
+ "learning_rate": 2.516679650610765e-06,
2549
+ "loss": 0.4102,
2550
+ "step": 1780
2551
+ },
2552
+ {
2553
+ "epoch": 2.9214402618657935,
2554
+ "grad_norm": 0.55859375,
2555
+ "learning_rate": 2.5137356273471183e-06,
2556
+ "loss": 0.407,
2557
+ "step": 1785
2558
+ },
2559
+ {
2560
+ "epoch": 2.9296235679214404,
2561
+ "grad_norm": 0.53125,
2562
+ "learning_rate": 2.511076768423443e-06,
2563
+ "loss": 0.4131,
2564
+ "step": 1790
2565
+ },
2566
+ {
2567
+ "epoch": 2.937806873977087,
2568
+ "grad_norm": 0.53125,
2569
+ "learning_rate": 2.508703276772852e-06,
2570
+ "loss": 0.3914,
2571
+ "step": 1795
2572
+ },
2573
+ {
2574
+ "epoch": 2.9459901800327333,
2575
+ "grad_norm": 0.53125,
2576
+ "learning_rate": 2.506615333548257e-06,
2577
+ "loss": 0.4093,
2578
+ "step": 1800
2579
+ },
2580
+ {
2581
+ "epoch": 2.9541734860883797,
2582
+ "grad_norm": 0.5,
2583
+ "learning_rate": 2.5048130981085524e-06,
2584
+ "loss": 0.3938,
2585
+ "step": 1805
2586
+ },
2587
+ {
2588
+ "epoch": 2.962356792144026,
2589
+ "grad_norm": 0.53125,
2590
+ "learning_rate": 2.5032967080064435e-06,
2591
+ "loss": 0.4007,
2592
+ "step": 1810
2593
+ },
2594
+ {
2595
+ "epoch": 2.9705400981996726,
2596
+ "grad_norm": 0.50390625,
2597
+ "learning_rate": 2.5020662789779555e-06,
2598
+ "loss": 0.3872,
2599
+ "step": 1815
2600
+ },
2601
+ {
2602
+ "epoch": 2.978723404255319,
2603
+ "grad_norm": 0.55078125,
2604
+ "learning_rate": 2.501121904933595e-06,
2605
+ "loss": 0.3835,
2606
+ "step": 1820
2607
+ },
2608
+ {
2609
+ "epoch": 2.986906710310966,
2610
+ "grad_norm": 0.53125,
2611
+ "learning_rate": 2.5004636579511843e-06,
2612
+ "loss": 0.4001,
2613
+ "step": 1825
2614
+ },
2615
+ {
2616
+ "epoch": 2.9950900163666123,
2617
+ "grad_norm": 0.53125,
2618
+ "learning_rate": 2.5000915882703615e-06,
2619
+ "loss": 0.3819,
2620
+ "step": 1830
2621
+ },
2622
+ {
2623
+ "epoch": 2.9950900163666123,
2624
+ "eval_loss": 0.3913484513759613,
2625
+ "eval_runtime": 5.0457,
2626
+ "eval_samples_per_second": 16.45,
2627
+ "eval_steps_per_second": 16.45,
2628
+ "step": 1830
2629
+ }
2630
+ ],
2631
+ "logging_steps": 5,
2632
+ "max_steps": 1833,
2633
+ "num_input_tokens_seen": 0,
2634
+ "num_train_epochs": 3,
2635
+ "save_steps": 500,
2636
+ "stateful_callbacks": {
2637
+ "TrainerControl": {
2638
+ "args": {
2639
+ "should_epoch_stop": false,
2640
+ "should_evaluate": false,
2641
+ "should_log": false,
2642
+ "should_save": true,
2643
+ "should_training_stop": false
2644
+ },
2645
+ "attributes": {}
2646
+ }
2647
+ },
2648
+ "total_flos": 3.0422166028387615e+18,
2649
+ "train_batch_size": 48,
2650
+ "trial_name": null,
2651
+ "trial_params": null
2652
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f828b7e29de6c762d8909d037a56959522ccc160d9149bc37dbf27129cae3d8
3
+ size 5688