Undi95 commited on
Commit
f086430
1 Parent(s): 5717222

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./EdgerunnersLab_llama-3.1-ortho-baukit-39f-3000t",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8433,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
29
+ "rope_theta": 500000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.44.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 128256
35
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.0.dev0"
12
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1909fc549b84fb4e465028b73e7eb8c5e682f03afc20e8f5d243042b199e7a46
3
+ size 4886466168
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29040355d50aa79cc606defa35a89b79096b17901c81d90f425302e61bebe39
3
+ size 4832007448
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8255920e301bab6a775a79bd99917cf90e94c80636a26261b938ba4cda1bd61e
3
+ size 4999813112
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691d27fb0c751fc981015601bb76e8deb0dc3f9fbad2a920ccd66bc851e976f7
3
+ size 4999813128
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bae4ea73499cd0c38cc39d677e43035d60db247e349aca54b7a538db55a6a98
3
+ size 4832007496
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5cfbc5d2d386777b8399de4faafe9012b90fa1f08978a008b7a99498c1bbb01
3
+ size 4999813120
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7786c2df0f08a47b4294f046e8c47bb828760f2e81c8dc510f97f4aa5a47dfa6
3
+ size 2571158184
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 32121044992
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00007-of-00007.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
296
+ "model.norm.weight": "model-00007-of-00007.safetensors"
297
+ }
298
+ }
pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bb14c7a4bdee79bc3cebc8c99f82f494a5b5638177435db7730c66bdfb3946
3
+ size 32121194957
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d7e02ffb4d440dce7ab4ce0b5617578ec9ce3672acee7434ed6f1153f1ae0c
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b40ca759e432b2688f021b81291d74a40f56a205e9842119f7e772275eebd3
3
+ size 15984
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdaef955ddd36d6bc1c40584113dd6205483e2aa85b02439b8b27e82e02a8359
3
+ size 15984
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b14ae5db356e6512538751d6b386c190754e307cc99cd652d5c6dd891e1f82
3
+ size 15984
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26e28be26826eeeed244b77185c67b443ac185175f8d4bf5ba94caa8b271bc5
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847cedc1d6ca26f299a132c2ade9754887374acb9d98f26594a85d4c7742d474
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd043d1690ae0ff6991b03322799a0b28f021427b15fd9f1e5ed8b9905d9307
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772190f7e6667c865d25fc72da7bdd1b5d39f46fe03bb5c2d754aee1ad3c99c7
3
+ size 15984
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ca8d5a425a356b181e91a52b171eef6fa210932ea22a448af139a1c0b461e0
3
+ size 1064
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": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "left",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,2313 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9781591263650546,
5
+ "eval_steps": 80,
6
+ "global_step": 320,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0062402496099844,
13
+ "grad_norm": 19.714784622192383,
14
+ "learning_rate": 2.0000000000000002e-07,
15
+ "loss": 1.3589,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0062402496099844,
20
+ "eval_loss": 1.3540421724319458,
21
+ "eval_runtime": 132.5999,
22
+ "eval_samples_per_second": 102.195,
23
+ "eval_steps_per_second": 6.388,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0124804992199688,
28
+ "grad_norm": 20.498014450073242,
29
+ "learning_rate": 4.0000000000000003e-07,
30
+ "loss": 1.3662,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0187207488299532,
35
+ "grad_norm": 19.82619285583496,
36
+ "learning_rate": 6.000000000000001e-07,
37
+ "loss": 1.3336,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.0249609984399376,
42
+ "grad_norm": 18.423460006713867,
43
+ "learning_rate": 8.000000000000001e-07,
44
+ "loss": 1.3555,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.031201248049921998,
49
+ "grad_norm": 16.555850982666016,
50
+ "learning_rate": 1.0000000000000002e-06,
51
+ "loss": 1.3527,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.0374414976599064,
56
+ "grad_norm": 10.684965133666992,
57
+ "learning_rate": 1.2000000000000002e-06,
58
+ "loss": 1.3491,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.0436817472698908,
63
+ "grad_norm": 8.396592140197754,
64
+ "learning_rate": 1.4000000000000001e-06,
65
+ "loss": 1.3181,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.0499219968798752,
70
+ "grad_norm": 3.145500421524048,
71
+ "learning_rate": 1.6000000000000001e-06,
72
+ "loss": 1.2984,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.056162246489859596,
77
+ "grad_norm": 2.981050491333008,
78
+ "learning_rate": 1.8000000000000001e-06,
79
+ "loss": 1.2901,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.062402496099843996,
84
+ "grad_norm": 2.741509199142456,
85
+ "learning_rate": 2.0000000000000003e-06,
86
+ "loss": 1.2948,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.0686427457098284,
91
+ "grad_norm": 3.8496174812316895,
92
+ "learning_rate": 2.2e-06,
93
+ "loss": 1.2524,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.0748829953198128,
98
+ "grad_norm": 3.039551258087158,
99
+ "learning_rate": 2.4000000000000003e-06,
100
+ "loss": 1.2369,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.0811232449297972,
105
+ "grad_norm": 2.215259313583374,
106
+ "learning_rate": 2.6e-06,
107
+ "loss": 1.244,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.0873634945397816,
112
+ "grad_norm": 1.4627336263656616,
113
+ "learning_rate": 2.8000000000000003e-06,
114
+ "loss": 1.2201,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.093603744149766,
119
+ "grad_norm": 2.0100812911987305,
120
+ "learning_rate": 3e-06,
121
+ "loss": 1.2097,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.0998439937597504,
126
+ "grad_norm": 2.0757627487182617,
127
+ "learning_rate": 3.2000000000000003e-06,
128
+ "loss": 1.2058,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.1060842433697348,
133
+ "grad_norm": 1.6582179069519043,
134
+ "learning_rate": 3.4000000000000005e-06,
135
+ "loss": 1.1775,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.11232449297971919,
140
+ "grad_norm": 1.2454713582992554,
141
+ "learning_rate": 3.6000000000000003e-06,
142
+ "loss": 1.1405,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.11856474258970359,
147
+ "grad_norm": 1.0032132863998413,
148
+ "learning_rate": 3.8000000000000005e-06,
149
+ "loss": 1.1442,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.12480499219968799,
154
+ "grad_norm": 1.3543955087661743,
155
+ "learning_rate": 4.000000000000001e-06,
156
+ "loss": 1.1874,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.1310452418096724,
161
+ "grad_norm": 1.2795507907867432,
162
+ "learning_rate": 4.2000000000000004e-06,
163
+ "loss": 1.1423,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.1372854914196568,
168
+ "grad_norm": 1.0040080547332764,
169
+ "learning_rate": 4.4e-06,
170
+ "loss": 1.1269,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.1435257410296412,
175
+ "grad_norm": 0.9706005454063416,
176
+ "learning_rate": 4.600000000000001e-06,
177
+ "loss": 1.1508,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.1497659906396256,
182
+ "grad_norm": 0.905784547328949,
183
+ "learning_rate": 4.800000000000001e-06,
184
+ "loss": 1.1003,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.15600624024961,
189
+ "grad_norm": 0.8688749074935913,
190
+ "learning_rate": 5e-06,
191
+ "loss": 1.1046,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.1622464898595944,
196
+ "grad_norm": 0.7418661713600159,
197
+ "learning_rate": 5.2e-06,
198
+ "loss": 1.0736,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.1684867394695788,
203
+ "grad_norm": 0.7218017578125,
204
+ "learning_rate": 5.400000000000001e-06,
205
+ "loss": 1.0924,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.1747269890795632,
210
+ "grad_norm": 0.7364180684089661,
211
+ "learning_rate": 5.600000000000001e-06,
212
+ "loss": 1.0666,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.1809672386895476,
217
+ "grad_norm": 0.6347681879997253,
218
+ "learning_rate": 5.8e-06,
219
+ "loss": 1.0533,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.187207488299532,
224
+ "grad_norm": 0.672021210193634,
225
+ "learning_rate": 6e-06,
226
+ "loss": 1.0719,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.1934477379095164,
231
+ "grad_norm": 0.6880649328231812,
232
+ "learning_rate": 6.200000000000001e-06,
233
+ "loss": 1.0555,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.1996879875195008,
238
+ "grad_norm": 0.5669052004814148,
239
+ "learning_rate": 6.4000000000000006e-06,
240
+ "loss": 1.0845,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.2059282371294852,
245
+ "grad_norm": 0.6051258444786072,
246
+ "learning_rate": 6.600000000000001e-06,
247
+ "loss": 1.0656,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.2121684867394696,
252
+ "grad_norm": 0.5937217473983765,
253
+ "learning_rate": 6.800000000000001e-06,
254
+ "loss": 1.0738,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.21840873634945399,
259
+ "grad_norm": 0.5861482620239258,
260
+ "learning_rate": 7e-06,
261
+ "loss": 1.0497,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.22464898595943839,
266
+ "grad_norm": 0.5939168334007263,
267
+ "learning_rate": 7.2000000000000005e-06,
268
+ "loss": 1.0657,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.23088923556942278,
273
+ "grad_norm": 0.5843105316162109,
274
+ "learning_rate": 7.4e-06,
275
+ "loss": 1.0498,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.23712948517940718,
280
+ "grad_norm": 0.5303648710250854,
281
+ "learning_rate": 7.600000000000001e-06,
282
+ "loss": 1.0604,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.24336973478939158,
287
+ "grad_norm": 0.558338463306427,
288
+ "learning_rate": 7.800000000000002e-06,
289
+ "loss": 1.0383,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.24960998439937598,
294
+ "grad_norm": 0.49629613757133484,
295
+ "learning_rate": 8.000000000000001e-06,
296
+ "loss": 1.0521,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.25585023400936036,
301
+ "grad_norm": 0.5873180627822876,
302
+ "learning_rate": 8.2e-06,
303
+ "loss": 1.0403,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.2620904836193448,
308
+ "grad_norm": 0.5466005802154541,
309
+ "learning_rate": 8.400000000000001e-06,
310
+ "loss": 1.0127,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.26833073322932915,
315
+ "grad_norm": 0.5514444708824158,
316
+ "learning_rate": 8.6e-06,
317
+ "loss": 1.0399,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.2745709828393136,
322
+ "grad_norm": 0.5304705500602722,
323
+ "learning_rate": 8.8e-06,
324
+ "loss": 1.0057,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.28081123244929795,
329
+ "grad_norm": 0.5105130076408386,
330
+ "learning_rate": 9e-06,
331
+ "loss": 1.0174,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.2870514820592824,
336
+ "grad_norm": 0.533640444278717,
337
+ "learning_rate": 9.200000000000002e-06,
338
+ "loss": 1.0342,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.29329173166926675,
343
+ "grad_norm": 0.48208147287368774,
344
+ "learning_rate": 9.4e-06,
345
+ "loss": 1.0195,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.2995319812792512,
350
+ "grad_norm": 0.5069381594657898,
351
+ "learning_rate": 9.600000000000001e-06,
352
+ "loss": 1.0382,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.30577223088923555,
357
+ "grad_norm": 0.4819696843624115,
358
+ "learning_rate": 9.800000000000001e-06,
359
+ "loss": 1.05,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.31201248049922,
364
+ "grad_norm": 0.5414313673973083,
365
+ "learning_rate": 1e-05,
366
+ "loss": 1.0245,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.31825273010920435,
371
+ "grad_norm": 0.4769354462623596,
372
+ "learning_rate": 1.02e-05,
373
+ "loss": 1.005,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.3244929797191888,
378
+ "grad_norm": 0.5051629543304443,
379
+ "learning_rate": 1.04e-05,
380
+ "loss": 1.0158,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.33073322932917315,
385
+ "grad_norm": 0.5432644486427307,
386
+ "learning_rate": 1.0600000000000002e-05,
387
+ "loss": 1.0122,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.3369734789391576,
392
+ "grad_norm": 0.4705195128917694,
393
+ "learning_rate": 1.0800000000000002e-05,
394
+ "loss": 1.0053,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.34321372854914195,
399
+ "grad_norm": 0.5468801856040955,
400
+ "learning_rate": 1.1000000000000001e-05,
401
+ "loss": 1.0173,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.3494539781591264,
406
+ "grad_norm": 0.6218928694725037,
407
+ "learning_rate": 1.1200000000000001e-05,
408
+ "loss": 0.9974,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.35569422776911075,
413
+ "grad_norm": 0.532873272895813,
414
+ "learning_rate": 1.14e-05,
415
+ "loss": 1.006,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.3619344773790952,
420
+ "grad_norm": 0.48144450783729553,
421
+ "learning_rate": 1.16e-05,
422
+ "loss": 1.0025,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.36817472698907955,
427
+ "grad_norm": 0.5385976433753967,
428
+ "learning_rate": 1.18e-05,
429
+ "loss": 0.9976,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.374414976599064,
434
+ "grad_norm": 0.5179689526557922,
435
+ "learning_rate": 1.2e-05,
436
+ "loss": 0.9988,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.38065522620904835,
441
+ "grad_norm": 0.4646259844303131,
442
+ "learning_rate": 1.22e-05,
443
+ "loss": 0.9959,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.3868954758190328,
448
+ "grad_norm": 0.5259431004524231,
449
+ "learning_rate": 1.2400000000000002e-05,
450
+ "loss": 0.9933,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.39313572542901715,
455
+ "grad_norm": 0.5602505803108215,
456
+ "learning_rate": 1.2600000000000001e-05,
457
+ "loss": 0.9732,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.3993759750390016,
462
+ "grad_norm": 0.5400233864784241,
463
+ "learning_rate": 1.2800000000000001e-05,
464
+ "loss": 1.0021,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.40561622464898595,
469
+ "grad_norm": 0.5008605718612671,
470
+ "learning_rate": 1.3000000000000001e-05,
471
+ "loss": 1.0098,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.4118564742589704,
476
+ "grad_norm": 0.5215092301368713,
477
+ "learning_rate": 1.3200000000000002e-05,
478
+ "loss": 0.9805,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.41809672386895474,
483
+ "grad_norm": 0.6043874025344849,
484
+ "learning_rate": 1.3400000000000002e-05,
485
+ "loss": 0.9651,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.4243369734789392,
490
+ "grad_norm": 0.5744293928146362,
491
+ "learning_rate": 1.3600000000000002e-05,
492
+ "loss": 0.9715,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.43057722308892354,
497
+ "grad_norm": 0.6228943467140198,
498
+ "learning_rate": 1.38e-05,
499
+ "loss": 0.9942,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.43681747269890797,
504
+ "grad_norm": 0.6340550780296326,
505
+ "learning_rate": 1.4e-05,
506
+ "loss": 1.0278,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.44305772230889234,
511
+ "grad_norm": 0.6537193655967712,
512
+ "learning_rate": 1.4200000000000001e-05,
513
+ "loss": 1.005,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.44929797191887677,
518
+ "grad_norm": 0.6706846356391907,
519
+ "learning_rate": 1.4400000000000001e-05,
520
+ "loss": 0.9736,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.45553822152886114,
525
+ "grad_norm": 0.5686175227165222,
526
+ "learning_rate": 1.46e-05,
527
+ "loss": 0.9753,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.46177847113884557,
532
+ "grad_norm": 0.5182248950004578,
533
+ "learning_rate": 1.48e-05,
534
+ "loss": 0.9964,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.46801872074882994,
539
+ "grad_norm": 0.5445067286491394,
540
+ "learning_rate": 1.5000000000000002e-05,
541
+ "loss": 0.9702,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.47425897035881437,
546
+ "grad_norm": 0.6168459057807922,
547
+ "learning_rate": 1.5200000000000002e-05,
548
+ "loss": 0.9791,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.48049921996879874,
553
+ "grad_norm": 0.6475315093994141,
554
+ "learning_rate": 1.54e-05,
555
+ "loss": 0.98,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.48673946957878317,
560
+ "grad_norm": 0.8365716934204102,
561
+ "learning_rate": 1.5600000000000003e-05,
562
+ "loss": 0.987,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.49297971918876754,
567
+ "grad_norm": 1.0882554054260254,
568
+ "learning_rate": 1.58e-05,
569
+ "loss": 0.9796,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.49921996879875197,
574
+ "grad_norm": 1.109529972076416,
575
+ "learning_rate": 1.6000000000000003e-05,
576
+ "loss": 0.9825,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.49921996879875197,
581
+ "eval_loss": 0.9798125624656677,
582
+ "eval_runtime": 132.8615,
583
+ "eval_samples_per_second": 101.993,
584
+ "eval_steps_per_second": 6.375,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5054602184087363,
589
+ "grad_norm": 0.9999867677688599,
590
+ "learning_rate": 1.62e-05,
591
+ "loss": 0.9591,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5117004680187207,
596
+ "grad_norm": 0.8042426705360413,
597
+ "learning_rate": 1.64e-05,
598
+ "loss": 0.9832,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.5179407176287052,
603
+ "grad_norm": 0.5843170881271362,
604
+ "learning_rate": 1.66e-05,
605
+ "loss": 0.9769,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5241809672386896,
610
+ "grad_norm": 0.6988096237182617,
611
+ "learning_rate": 1.6800000000000002e-05,
612
+ "loss": 0.9556,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5304212168486739,
617
+ "grad_norm": 0.7298963665962219,
618
+ "learning_rate": 1.7e-05,
619
+ "loss": 0.983,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.5366614664586583,
624
+ "grad_norm": 0.7856214046478271,
625
+ "learning_rate": 1.72e-05,
626
+ "loss": 0.9541,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.5429017160686428,
631
+ "grad_norm": 0.6896259188652039,
632
+ "learning_rate": 1.7400000000000003e-05,
633
+ "loss": 0.983,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.5491419656786272,
638
+ "grad_norm": 0.5555576682090759,
639
+ "learning_rate": 1.76e-05,
640
+ "loss": 0.9395,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5553822152886115,
645
+ "grad_norm": 0.6107622385025024,
646
+ "learning_rate": 1.7800000000000002e-05,
647
+ "loss": 0.9601,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.5616224648985959,
652
+ "grad_norm": 0.7116836309432983,
653
+ "learning_rate": 1.8e-05,
654
+ "loss": 0.9647,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.5678627145085804,
659
+ "grad_norm": 0.5782715082168579,
660
+ "learning_rate": 1.8200000000000002e-05,
661
+ "loss": 0.9604,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5741029641185648,
666
+ "grad_norm": 0.512100338935852,
667
+ "learning_rate": 1.8400000000000003e-05,
668
+ "loss": 0.9433,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.5803432137285491,
673
+ "grad_norm": 0.6315212249755859,
674
+ "learning_rate": 1.86e-05,
675
+ "loss": 0.969,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.5865834633385335,
680
+ "grad_norm": 0.6883739233016968,
681
+ "learning_rate": 1.88e-05,
682
+ "loss": 0.9832,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.592823712948518,
687
+ "grad_norm": 0.6760767102241516,
688
+ "learning_rate": 1.9e-05,
689
+ "loss": 0.9414,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.5990639625585024,
694
+ "grad_norm": 0.6577237248420715,
695
+ "learning_rate": 1.9200000000000003e-05,
696
+ "loss": 0.9748,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6053042121684867,
701
+ "grad_norm": 0.9515029788017273,
702
+ "learning_rate": 1.94e-05,
703
+ "loss": 0.9863,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.6115444617784711,
708
+ "grad_norm": 1.40570068359375,
709
+ "learning_rate": 1.9600000000000002e-05,
710
+ "loss": 0.9445,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.6177847113884556,
715
+ "grad_norm": 0.9026833176612854,
716
+ "learning_rate": 1.98e-05,
717
+ "loss": 0.9436,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.62402496099844,
722
+ "grad_norm": 0.6666714549064636,
723
+ "learning_rate": 2e-05,
724
+ "loss": 0.9832,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.6302652106084243,
729
+ "grad_norm": 0.8047837018966675,
730
+ "learning_rate": 1.9998980430094333e-05,
731
+ "loss": 0.9498,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 0.6365054602184087,
736
+ "grad_norm": 0.9035269618034363,
737
+ "learning_rate": 1.9995921928281893e-05,
738
+ "loss": 0.9541,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 0.6427457098283932,
743
+ "grad_norm": 1.027601718902588,
744
+ "learning_rate": 1.9990825118233958e-05,
745
+ "loss": 0.9786,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 0.6489859594383776,
750
+ "grad_norm": 1.1459457874298096,
751
+ "learning_rate": 1.9983691039261358e-05,
752
+ "loss": 0.9482,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 0.6552262090483619,
757
+ "grad_norm": 0.7179874777793884,
758
+ "learning_rate": 1.9974521146102535e-05,
759
+ "loss": 0.9743,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 0.6614664586583463,
764
+ "grad_norm": 0.6881632208824158,
765
+ "learning_rate": 1.9963317308626916e-05,
766
+ "loss": 0.9797,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 0.6677067082683308,
771
+ "grad_norm": 0.7822304368019104,
772
+ "learning_rate": 1.9950081811453598e-05,
773
+ "loss": 0.9682,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 0.6739469578783152,
778
+ "grad_norm": 0.8269001841545105,
779
+ "learning_rate": 1.99348173534855e-05,
780
+ "loss": 0.9455,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 0.6801872074882995,
785
+ "grad_norm": 0.8077254295349121,
786
+ "learning_rate": 1.991752704735903e-05,
787
+ "loss": 0.9243,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 0.6864274570982839,
792
+ "grad_norm": 0.8119699954986572,
793
+ "learning_rate": 1.989821441880933e-05,
794
+ "loss": 0.9273,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 0.6926677067082684,
799
+ "grad_norm": 0.8220670223236084,
800
+ "learning_rate": 1.9876883405951378e-05,
801
+ "loss": 0.9455,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 0.6989079563182528,
806
+ "grad_norm": 0.8622007966041565,
807
+ "learning_rate": 1.9853538358476933e-05,
808
+ "loss": 0.9624,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 0.7051482059282371,
813
+ "grad_norm": 0.8222960233688354,
814
+ "learning_rate": 1.9828184036767556e-05,
815
+ "loss": 0.955,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 0.7113884555382215,
820
+ "grad_norm": 0.62811678647995,
821
+ "learning_rate": 1.9800825610923937e-05,
822
+ "loss": 0.9551,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 0.717628705148206,
827
+ "grad_norm": 0.7614508271217346,
828
+ "learning_rate": 1.9771468659711595e-05,
829
+ "loss": 0.9413,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 0.7238689547581904,
834
+ "grad_norm": 0.6695716977119446,
835
+ "learning_rate": 1.9740119169423337e-05,
836
+ "loss": 0.9384,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 0.7301092043681747,
841
+ "grad_norm": 0.5493482947349548,
842
+ "learning_rate": 1.9706783532658528e-05,
843
+ "loss": 0.9601,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 0.7363494539781591,
848
+ "grad_norm": 0.7798200249671936,
849
+ "learning_rate": 1.9671468547019575e-05,
850
+ "loss": 0.9555,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 0.7425897035881436,
855
+ "grad_norm": 0.8122205138206482,
856
+ "learning_rate": 1.963418141372579e-05,
857
+ "loss": 0.9351,
858
+ "step": 119
859
+ },
860
+ {
861
+ "epoch": 0.748829953198128,
862
+ "grad_norm": 0.6351688504219055,
863
+ "learning_rate": 1.9594929736144978e-05,
864
+ "loss": 0.9517,
865
+ "step": 120
866
+ },
867
+ {
868
+ "epoch": 0.7550702028081123,
869
+ "grad_norm": 0.8507185578346252,
870
+ "learning_rate": 1.955372151824297e-05,
871
+ "loss": 0.9482,
872
+ "step": 121
873
+ },
874
+ {
875
+ "epoch": 0.7613104524180967,
876
+ "grad_norm": 1.057692050933838,
877
+ "learning_rate": 1.9510565162951538e-05,
878
+ "loss": 0.9626,
879
+ "step": 122
880
+ },
881
+ {
882
+ "epoch": 0.7675507020280812,
883
+ "grad_norm": 0.789968729019165,
884
+ "learning_rate": 1.94654694704549e-05,
885
+ "loss": 0.9504,
886
+ "step": 123
887
+ },
888
+ {
889
+ "epoch": 0.7737909516380655,
890
+ "grad_norm": 0.8988214731216431,
891
+ "learning_rate": 1.941844363639525e-05,
892
+ "loss": 0.9339,
893
+ "step": 124
894
+ },
895
+ {
896
+ "epoch": 0.7800312012480499,
897
+ "grad_norm": 0.6798993945121765,
898
+ "learning_rate": 1.936949724999762e-05,
899
+ "loss": 0.9387,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 0.7862714508580343,
904
+ "grad_norm": 0.7597091794013977,
905
+ "learning_rate": 1.9318640292114526e-05,
906
+ "loss": 0.9884,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 0.7925117004680188,
911
+ "grad_norm": 0.9357583522796631,
912
+ "learning_rate": 1.9265883133190715e-05,
913
+ "loss": 0.9382,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 0.7987519500780031,
918
+ "grad_norm": 0.8738594055175781,
919
+ "learning_rate": 1.92112365311485e-05,
920
+ "loss": 0.9482,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.8049921996879875,
925
+ "grad_norm": 0.8523539900779724,
926
+ "learning_rate": 1.9154711629194062e-05,
927
+ "loss": 0.9299,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.8112324492979719,
932
+ "grad_norm": 0.5781116485595703,
933
+ "learning_rate": 1.9096319953545186e-05,
934
+ "loss": 0.9636,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.8174726989079563,
939
+ "grad_norm": 0.7737751007080078,
940
+ "learning_rate": 1.9036073411080917e-05,
941
+ "loss": 0.9482,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.8237129485179407,
946
+ "grad_norm": 0.7203546762466431,
947
+ "learning_rate": 1.8973984286913584e-05,
948
+ "loss": 0.9298,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.8299531981279251,
953
+ "grad_norm": 0.5875493288040161,
954
+ "learning_rate": 1.891006524188368e-05,
955
+ "loss": 0.9239,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.8361934477379095,
960
+ "grad_norm": 0.7981539964675903,
961
+ "learning_rate": 1.8844329309978146e-05,
962
+ "loss": 0.9546,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.8424336973478939,
967
+ "grad_norm": 0.7623902559280396,
968
+ "learning_rate": 1.8776789895672557e-05,
969
+ "loss": 0.9335,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.8486739469578783,
974
+ "grad_norm": 0.6350914239883423,
975
+ "learning_rate": 1.8707460771197773e-05,
976
+ "loss": 0.9585,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.8549141965678627,
981
+ "grad_norm": 0.6981391310691833,
982
+ "learning_rate": 1.863635607373157e-05,
983
+ "loss": 0.9271,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.8611544461778471,
988
+ "grad_norm": 0.7900795936584473,
989
+ "learning_rate": 1.856349030251589e-05,
990
+ "loss": 0.9022,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.8673946957878315,
995
+ "grad_norm": 0.7494855523109436,
996
+ "learning_rate": 1.8488878315900228e-05,
997
+ "loss": 0.9534,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.8736349453978159,
1002
+ "grad_norm": 0.5757277011871338,
1003
+ "learning_rate": 1.8412535328311813e-05,
1004
+ "loss": 0.9397,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.8798751950078003,
1009
+ "grad_norm": 0.6893640756607056,
1010
+ "learning_rate": 1.8334476907153177e-05,
1011
+ "loss": 0.952,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.8861154446177847,
1016
+ "grad_norm": 0.7050842046737671,
1017
+ "learning_rate": 1.825471896962774e-05,
1018
+ "loss": 0.9417,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.8923556942277691,
1023
+ "grad_norm": 0.5544989109039307,
1024
+ "learning_rate": 1.817327777949407e-05,
1025
+ "loss": 0.9008,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.8985959438377535,
1030
+ "grad_norm": 0.6469840407371521,
1031
+ "learning_rate": 1.8090169943749477e-05,
1032
+ "loss": 0.9471,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.9048361934477379,
1037
+ "grad_norm": 0.6894209384918213,
1038
+ "learning_rate": 1.8005412409243604e-05,
1039
+ "loss": 0.9553,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.9110764430577223,
1044
+ "grad_norm": 0.5356501936912537,
1045
+ "learning_rate": 1.7919022459222754e-05,
1046
+ "loss": 0.9496,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.9173166926677067,
1051
+ "grad_norm": 0.6416233777999878,
1052
+ "learning_rate": 1.7831017709805555e-05,
1053
+ "loss": 0.9558,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.9235569422776911,
1058
+ "grad_norm": 0.7085059881210327,
1059
+ "learning_rate": 1.7741416106390828e-05,
1060
+ "loss": 0.9168,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.9297971918876755,
1065
+ "grad_norm": 0.6492967009544373,
1066
+ "learning_rate": 1.7650235919998234e-05,
1067
+ "loss": 0.9065,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.9360374414976599,
1072
+ "grad_norm": 0.7753322124481201,
1073
+ "learning_rate": 1.7557495743542586e-05,
1074
+ "loss": 0.9285,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.9422776911076443,
1079
+ "grad_norm": 0.6451005935668945,
1080
+ "learning_rate": 1.7463214488042472e-05,
1081
+ "loss": 0.9567,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.9485179407176287,
1086
+ "grad_norm": 0.4824198782444,
1087
+ "learning_rate": 1.736741137876405e-05,
1088
+ "loss": 0.905,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.9547581903276131,
1093
+ "grad_norm": 0.5846424102783203,
1094
+ "learning_rate": 1.727010595130074e-05,
1095
+ "loss": 0.9426,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.9609984399375975,
1100
+ "grad_norm": 0.5984904170036316,
1101
+ "learning_rate": 1.7171318047589637e-05,
1102
+ "loss": 0.9398,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.9672386895475819,
1107
+ "grad_norm": 0.545465886592865,
1108
+ "learning_rate": 1.7071067811865477e-05,
1109
+ "loss": 0.9185,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.9734789391575663,
1114
+ "grad_norm": 0.5724261403083801,
1115
+ "learning_rate": 1.696937568655294e-05,
1116
+ "loss": 0.9222,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.9797191887675507,
1121
+ "grad_norm": 0.5120018124580383,
1122
+ "learning_rate": 1.6866262408098134e-05,
1123
+ "loss": 0.93,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.9859594383775351,
1128
+ "grad_norm": 0.5575640797615051,
1129
+ "learning_rate": 1.6761749002740195e-05,
1130
+ "loss": 0.9483,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.9921996879875195,
1135
+ "grad_norm": 0.603184163570404,
1136
+ "learning_rate": 1.6655856782223682e-05,
1137
+ "loss": 0.9394,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.9984399375975039,
1142
+ "grad_norm": 0.536756157875061,
1143
+ "learning_rate": 1.6548607339452853e-05,
1144
+ "loss": 0.9227,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.9984399375975039,
1149
+ "eval_loss": 0.9286661744117737,
1150
+ "eval_runtime": 134.8358,
1151
+ "eval_samples_per_second": 100.5,
1152
+ "eval_steps_per_second": 6.282,
1153
+ "step": 160
1154
+ },
1155
+ {
1156
+ "epoch": 1.0046801872074882,
1157
+ "grad_norm": 0.5680767297744751,
1158
+ "learning_rate": 1.6440022544088553e-05,
1159
+ "loss": 0.9263,
1160
+ "step": 161
1161
+ },
1162
+ {
1163
+ "epoch": 1.0109204368174727,
1164
+ "grad_norm": 0.6374309062957764,
1165
+ "learning_rate": 1.6330124538088705e-05,
1166
+ "loss": 0.942,
1167
+ "step": 162
1168
+ },
1169
+ {
1170
+ "epoch": 1.0171606864274572,
1171
+ "grad_norm": 0.5749344825744629,
1172
+ "learning_rate": 1.6218935731193223e-05,
1173
+ "loss": 0.9264,
1174
+ "step": 163
1175
+ },
1176
+ {
1177
+ "epoch": 1.0046801872074882,
1178
+ "grad_norm": 0.9867531657218933,
1179
+ "learning_rate": 1.6106478796354382e-05,
1180
+ "loss": 0.8513,
1181
+ "step": 164
1182
+ },
1183
+ {
1184
+ "epoch": 1.0109204368174727,
1185
+ "grad_norm": 0.7155735492706299,
1186
+ "learning_rate": 1.599277666511347e-05,
1187
+ "loss": 0.8023,
1188
+ "step": 165
1189
+ },
1190
+ {
1191
+ "epoch": 1.0171606864274572,
1192
+ "grad_norm": 1.3990559577941895,
1193
+ "learning_rate": 1.5877852522924733e-05,
1194
+ "loss": 0.7992,
1195
+ "step": 166
1196
+ },
1197
+ {
1198
+ "epoch": 1.0234009360374414,
1199
+ "grad_norm": 0.9339443445205688,
1200
+ "learning_rate": 1.576172980442753e-05,
1201
+ "loss": 0.7982,
1202
+ "step": 167
1203
+ },
1204
+ {
1205
+ "epoch": 1.029641185647426,
1206
+ "grad_norm": 0.8383383750915527,
1207
+ "learning_rate": 1.5644432188667695e-05,
1208
+ "loss": 0.7764,
1209
+ "step": 168
1210
+ },
1211
+ {
1212
+ "epoch": 1.0358814352574104,
1213
+ "grad_norm": 0.8227719664573669,
1214
+ "learning_rate": 1.5525983594269026e-05,
1215
+ "loss": 0.7985,
1216
+ "step": 169
1217
+ },
1218
+ {
1219
+ "epoch": 1.0421216848673946,
1220
+ "grad_norm": 0.8231950998306274,
1221
+ "learning_rate": 1.5406408174555978e-05,
1222
+ "loss": 0.8097,
1223
+ "step": 170
1224
+ },
1225
+ {
1226
+ "epoch": 1.0483619344773791,
1227
+ "grad_norm": 1.1454997062683105,
1228
+ "learning_rate": 1.528573031262842e-05,
1229
+ "loss": 0.7779,
1230
+ "step": 171
1231
+ },
1232
+ {
1233
+ "epoch": 1.0546021840873634,
1234
+ "grad_norm": 0.6939067840576172,
1235
+ "learning_rate": 1.5163974616389621e-05,
1236
+ "loss": 0.8217,
1237
+ "step": 172
1238
+ },
1239
+ {
1240
+ "epoch": 1.0608424336973479,
1241
+ "grad_norm": 0.7526265978813171,
1242
+ "learning_rate": 1.504116591352832e-05,
1243
+ "loss": 0.7886,
1244
+ "step": 173
1245
+ },
1246
+ {
1247
+ "epoch": 1.0670826833073324,
1248
+ "grad_norm": 0.7892379760742188,
1249
+ "learning_rate": 1.491732924645604e-05,
1250
+ "loss": 0.7959,
1251
+ "step": 174
1252
+ },
1253
+ {
1254
+ "epoch": 1.0733229329173166,
1255
+ "grad_norm": 0.7279461026191711,
1256
+ "learning_rate": 1.479248986720057e-05,
1257
+ "loss": 0.7977,
1258
+ "step": 175
1259
+ },
1260
+ {
1261
+ "epoch": 1.079563182527301,
1262
+ "grad_norm": 0.7360721230506897,
1263
+ "learning_rate": 1.4666673232256738e-05,
1264
+ "loss": 0.7883,
1265
+ "step": 176
1266
+ },
1267
+ {
1268
+ "epoch": 1.0858034321372856,
1269
+ "grad_norm": 0.6525989174842834,
1270
+ "learning_rate": 1.4539904997395468e-05,
1271
+ "loss": 0.785,
1272
+ "step": 177
1273
+ },
1274
+ {
1275
+ "epoch": 1.0920436817472698,
1276
+ "grad_norm": 0.7803720235824585,
1277
+ "learning_rate": 1.4412211012432213e-05,
1278
+ "loss": 0.7998,
1279
+ "step": 178
1280
+ },
1281
+ {
1282
+ "epoch": 1.0982839313572543,
1283
+ "grad_norm": 0.6588256359100342,
1284
+ "learning_rate": 1.4283617315955815e-05,
1285
+ "loss": 0.7999,
1286
+ "step": 179
1287
+ },
1288
+ {
1289
+ "epoch": 1.1045241809672386,
1290
+ "grad_norm": 0.5983767509460449,
1291
+ "learning_rate": 1.4154150130018867e-05,
1292
+ "loss": 0.7848,
1293
+ "step": 180
1294
+ },
1295
+ {
1296
+ "epoch": 1.110764430577223,
1297
+ "grad_norm": 0.641603946685791,
1298
+ "learning_rate": 1.4023835854790682e-05,
1299
+ "loss": 0.7937,
1300
+ "step": 181
1301
+ },
1302
+ {
1303
+ "epoch": 1.1170046801872076,
1304
+ "grad_norm": 0.6453792452812195,
1305
+ "learning_rate": 1.3892701063173917e-05,
1306
+ "loss": 0.8004,
1307
+ "step": 182
1308
+ },
1309
+ {
1310
+ "epoch": 1.1232449297971918,
1311
+ "grad_norm": 0.6428067088127136,
1312
+ "learning_rate": 1.3760772495385998e-05,
1313
+ "loss": 0.792,
1314
+ "step": 183
1315
+ },
1316
+ {
1317
+ "epoch": 1.1294851794071763,
1318
+ "grad_norm": 0.6279442310333252,
1319
+ "learning_rate": 1.362807705350641e-05,
1320
+ "loss": 0.7859,
1321
+ "step": 184
1322
+ },
1323
+ {
1324
+ "epoch": 1.1357254290171608,
1325
+ "grad_norm": 0.6000891327857971,
1326
+ "learning_rate": 1.3494641795990986e-05,
1327
+ "loss": 0.8039,
1328
+ "step": 185
1329
+ },
1330
+ {
1331
+ "epoch": 1.141965678627145,
1332
+ "grad_norm": 0.6628398895263672,
1333
+ "learning_rate": 1.3360493932154301e-05,
1334
+ "loss": 0.7829,
1335
+ "step": 186
1336
+ },
1337
+ {
1338
+ "epoch": 1.1482059282371295,
1339
+ "grad_norm": 0.6268762946128845,
1340
+ "learning_rate": 1.3225660816621342e-05,
1341
+ "loss": 0.778,
1342
+ "step": 187
1343
+ },
1344
+ {
1345
+ "epoch": 1.154446177847114,
1346
+ "grad_norm": 0.639062225818634,
1347
+ "learning_rate": 1.3090169943749475e-05,
1348
+ "loss": 0.7796,
1349
+ "step": 188
1350
+ },
1351
+ {
1352
+ "epoch": 1.1606864274570983,
1353
+ "grad_norm": 0.6048714518547058,
1354
+ "learning_rate": 1.2954048942022002e-05,
1355
+ "loss": 0.7883,
1356
+ "step": 189
1357
+ },
1358
+ {
1359
+ "epoch": 1.1669266770670828,
1360
+ "grad_norm": 0.5929723381996155,
1361
+ "learning_rate": 1.2817325568414299e-05,
1362
+ "loss": 0.7736,
1363
+ "step": 190
1364
+ },
1365
+ {
1366
+ "epoch": 1.173166926677067,
1367
+ "grad_norm": 0.5971985459327698,
1368
+ "learning_rate": 1.2680027702733791e-05,
1369
+ "loss": 0.8008,
1370
+ "step": 191
1371
+ },
1372
+ {
1373
+ "epoch": 1.1794071762870515,
1374
+ "grad_norm": 0.6460970044136047,
1375
+ "learning_rate": 1.2542183341934873e-05,
1376
+ "loss": 0.7867,
1377
+ "step": 192
1378
+ },
1379
+ {
1380
+ "epoch": 1.185647425897036,
1381
+ "grad_norm": 0.5345771908760071,
1382
+ "learning_rate": 1.2403820594409926e-05,
1383
+ "loss": 0.7808,
1384
+ "step": 193
1385
+ },
1386
+ {
1387
+ "epoch": 1.1918876755070202,
1388
+ "grad_norm": 0.6704164743423462,
1389
+ "learning_rate": 1.2264967674257647e-05,
1390
+ "loss": 0.7785,
1391
+ "step": 194
1392
+ },
1393
+ {
1394
+ "epoch": 1.1981279251170047,
1395
+ "grad_norm": 0.5182461738586426,
1396
+ "learning_rate": 1.2125652895529766e-05,
1397
+ "loss": 0.7907,
1398
+ "step": 195
1399
+ },
1400
+ {
1401
+ "epoch": 1.204368174726989,
1402
+ "grad_norm": 0.6421562433242798,
1403
+ "learning_rate": 1.1985904666457455e-05,
1404
+ "loss": 0.7914,
1405
+ "step": 196
1406
+ },
1407
+ {
1408
+ "epoch": 1.2106084243369735,
1409
+ "grad_norm": 0.5846896171569824,
1410
+ "learning_rate": 1.1845751483658454e-05,
1411
+ "loss": 0.7631,
1412
+ "step": 197
1413
+ },
1414
+ {
1415
+ "epoch": 1.216848673946958,
1416
+ "grad_norm": 0.5582466721534729,
1417
+ "learning_rate": 1.170522192632624e-05,
1418
+ "loss": 0.7912,
1419
+ "step": 198
1420
+ },
1421
+ {
1422
+ "epoch": 1.2230889235569422,
1423
+ "grad_norm": 0.5527791976928711,
1424
+ "learning_rate": 1.156434465040231e-05,
1425
+ "loss": 0.7938,
1426
+ "step": 199
1427
+ },
1428
+ {
1429
+ "epoch": 1.2293291731669267,
1430
+ "grad_norm": 0.5673221945762634,
1431
+ "learning_rate": 1.1423148382732854e-05,
1432
+ "loss": 0.7947,
1433
+ "step": 200
1434
+ },
1435
+ {
1436
+ "epoch": 1.2355694227769112,
1437
+ "grad_norm": 0.5078392028808594,
1438
+ "learning_rate": 1.1281661915210931e-05,
1439
+ "loss": 0.7771,
1440
+ "step": 201
1441
+ },
1442
+ {
1443
+ "epoch": 1.2418096723868954,
1444
+ "grad_norm": 0.5475752353668213,
1445
+ "learning_rate": 1.1139914098905406e-05,
1446
+ "loss": 0.7781,
1447
+ "step": 202
1448
+ },
1449
+ {
1450
+ "epoch": 1.24804992199688,
1451
+ "grad_norm": 0.5290600657463074,
1452
+ "learning_rate": 1.0997933838177828e-05,
1453
+ "loss": 0.7622,
1454
+ "step": 203
1455
+ },
1456
+ {
1457
+ "epoch": 1.2542901716068644,
1458
+ "grad_norm": 0.4957723915576935,
1459
+ "learning_rate": 1.08557500847884e-05,
1460
+ "loss": 0.7857,
1461
+ "step": 204
1462
+ },
1463
+ {
1464
+ "epoch": 1.2605304212168487,
1465
+ "grad_norm": 0.5119233727455139,
1466
+ "learning_rate": 1.0713391831992324e-05,
1467
+ "loss": 0.7585,
1468
+ "step": 205
1469
+ },
1470
+ {
1471
+ "epoch": 1.2667706708268331,
1472
+ "grad_norm": 0.5187195539474487,
1473
+ "learning_rate": 1.0570888108627682e-05,
1474
+ "loss": 0.7885,
1475
+ "step": 206
1476
+ },
1477
+ {
1478
+ "epoch": 1.2730109204368174,
1479
+ "grad_norm": 0.5066515803337097,
1480
+ "learning_rate": 1.0428267973196027e-05,
1481
+ "loss": 0.7691,
1482
+ "step": 207
1483
+ },
1484
+ {
1485
+ "epoch": 1.2792511700468019,
1486
+ "grad_norm": 0.48673221468925476,
1487
+ "learning_rate": 1.0285560507936962e-05,
1488
+ "loss": 0.7715,
1489
+ "step": 208
1490
+ },
1491
+ {
1492
+ "epoch": 1.2854914196567861,
1493
+ "grad_norm": 0.5083721876144409,
1494
+ "learning_rate": 1.0142794812897874e-05,
1495
+ "loss": 0.7812,
1496
+ "step": 209
1497
+ },
1498
+ {
1499
+ "epoch": 1.2917316692667706,
1500
+ "grad_norm": 0.5033391118049622,
1501
+ "learning_rate": 1e-05,
1502
+ "loss": 0.7756,
1503
+ "step": 210
1504
+ },
1505
+ {
1506
+ "epoch": 1.2979719188767551,
1507
+ "grad_norm": 0.532008945941925,
1508
+ "learning_rate": 9.85720518710213e-06,
1509
+ "loss": 0.7898,
1510
+ "step": 211
1511
+ },
1512
+ {
1513
+ "epoch": 1.3042121684867394,
1514
+ "grad_norm": 0.5123456716537476,
1515
+ "learning_rate": 9.71443949206304e-06,
1516
+ "loss": 0.7779,
1517
+ "step": 212
1518
+ },
1519
+ {
1520
+ "epoch": 1.3104524180967239,
1521
+ "grad_norm": 0.48444995284080505,
1522
+ "learning_rate": 9.571732026803978e-06,
1523
+ "loss": 0.7598,
1524
+ "step": 213
1525
+ },
1526
+ {
1527
+ "epoch": 1.3166926677067083,
1528
+ "grad_norm": 0.5265589356422424,
1529
+ "learning_rate": 9.42911189137232e-06,
1530
+ "loss": 0.783,
1531
+ "step": 214
1532
+ },
1533
+ {
1534
+ "epoch": 1.3229329173166926,
1535
+ "grad_norm": 0.5039641261100769,
1536
+ "learning_rate": 9.286608168007678e-06,
1537
+ "loss": 0.7798,
1538
+ "step": 215
1539
+ },
1540
+ {
1541
+ "epoch": 1.329173166926677,
1542
+ "grad_norm": 0.5092752575874329,
1543
+ "learning_rate": 9.144249915211605e-06,
1544
+ "loss": 0.7635,
1545
+ "step": 216
1546
+ },
1547
+ {
1548
+ "epoch": 1.3354134165366616,
1549
+ "grad_norm": 0.5394583940505981,
1550
+ "learning_rate": 9.002066161822174e-06,
1551
+ "loss": 0.7999,
1552
+ "step": 217
1553
+ },
1554
+ {
1555
+ "epoch": 1.3416536661466458,
1556
+ "grad_norm": 0.5039361119270325,
1557
+ "learning_rate": 8.860085901094595e-06,
1558
+ "loss": 0.7745,
1559
+ "step": 218
1560
+ },
1561
+ {
1562
+ "epoch": 1.3478939157566303,
1563
+ "grad_norm": 0.5087692737579346,
1564
+ "learning_rate": 8.718338084789074e-06,
1565
+ "loss": 0.8093,
1566
+ "step": 219
1567
+ },
1568
+ {
1569
+ "epoch": 1.3541341653666148,
1570
+ "grad_norm": 0.5368974208831787,
1571
+ "learning_rate": 8.576851617267151e-06,
1572
+ "loss": 0.7596,
1573
+ "step": 220
1574
+ },
1575
+ {
1576
+ "epoch": 1.360374414976599,
1577
+ "grad_norm": 0.5123481750488281,
1578
+ "learning_rate": 8.43565534959769e-06,
1579
+ "loss": 0.7665,
1580
+ "step": 221
1581
+ },
1582
+ {
1583
+ "epoch": 1.3666146645865835,
1584
+ "grad_norm": 0.5048606395721436,
1585
+ "learning_rate": 8.294778073673762e-06,
1586
+ "loss": 0.769,
1587
+ "step": 222
1588
+ },
1589
+ {
1590
+ "epoch": 1.3728549141965678,
1591
+ "grad_norm": 0.5156130790710449,
1592
+ "learning_rate": 8.154248516341547e-06,
1593
+ "loss": 0.7989,
1594
+ "step": 223
1595
+ },
1596
+ {
1597
+ "epoch": 1.3790951638065523,
1598
+ "grad_norm": 0.5228000283241272,
1599
+ "learning_rate": 8.014095333542548e-06,
1600
+ "loss": 0.7775,
1601
+ "step": 224
1602
+ },
1603
+ {
1604
+ "epoch": 1.3853354134165365,
1605
+ "grad_norm": 0.5356248617172241,
1606
+ "learning_rate": 7.874347104470234e-06,
1607
+ "loss": 0.7629,
1608
+ "step": 225
1609
+ },
1610
+ {
1611
+ "epoch": 1.391575663026521,
1612
+ "grad_norm": 0.49624764919281006,
1613
+ "learning_rate": 7.735032325742355e-06,
1614
+ "loss": 0.8026,
1615
+ "step": 226
1616
+ },
1617
+ {
1618
+ "epoch": 1.3978159126365055,
1619
+ "grad_norm": 0.5164198279380798,
1620
+ "learning_rate": 7.596179405590076e-06,
1621
+ "loss": 0.7803,
1622
+ "step": 227
1623
+ },
1624
+ {
1625
+ "epoch": 1.4040561622464898,
1626
+ "grad_norm": 0.47972792387008667,
1627
+ "learning_rate": 7.4578166580651335e-06,
1628
+ "loss": 0.7783,
1629
+ "step": 228
1630
+ },
1631
+ {
1632
+ "epoch": 1.4102964118564743,
1633
+ "grad_norm": 0.4989663064479828,
1634
+ "learning_rate": 7.319972297266215e-06,
1635
+ "loss": 0.7728,
1636
+ "step": 229
1637
+ },
1638
+ {
1639
+ "epoch": 1.4165366614664587,
1640
+ "grad_norm": 0.5109092593193054,
1641
+ "learning_rate": 7.182674431585703e-06,
1642
+ "loss": 0.7919,
1643
+ "step": 230
1644
+ },
1645
+ {
1646
+ "epoch": 1.422776911076443,
1647
+ "grad_norm": 0.5069689750671387,
1648
+ "learning_rate": 7.045951057978001e-06,
1649
+ "loss": 0.8015,
1650
+ "step": 231
1651
+ },
1652
+ {
1653
+ "epoch": 1.4290171606864275,
1654
+ "grad_norm": 0.5074580907821655,
1655
+ "learning_rate": 6.909830056250527e-06,
1656
+ "loss": 0.7844,
1657
+ "step": 232
1658
+ },
1659
+ {
1660
+ "epoch": 1.435257410296412,
1661
+ "grad_norm": 0.47711381316185,
1662
+ "learning_rate": 6.774339183378663e-06,
1663
+ "loss": 0.7601,
1664
+ "step": 233
1665
+ },
1666
+ {
1667
+ "epoch": 1.4414976599063962,
1668
+ "grad_norm": 0.4926273822784424,
1669
+ "learning_rate": 6.639506067845698e-06,
1670
+ "loss": 0.7904,
1671
+ "step": 234
1672
+ },
1673
+ {
1674
+ "epoch": 1.4477379095163807,
1675
+ "grad_norm": 0.5004563927650452,
1676
+ "learning_rate": 6.505358204009018e-06,
1677
+ "loss": 0.7638,
1678
+ "step": 235
1679
+ },
1680
+ {
1681
+ "epoch": 1.4539781591263652,
1682
+ "grad_norm": 0.5014521479606628,
1683
+ "learning_rate": 6.3719229464935915e-06,
1684
+ "loss": 0.794,
1685
+ "step": 236
1686
+ },
1687
+ {
1688
+ "epoch": 1.4602184087363494,
1689
+ "grad_norm": 0.5181212425231934,
1690
+ "learning_rate": 6.239227504614004e-06,
1691
+ "loss": 0.7495,
1692
+ "step": 237
1693
+ },
1694
+ {
1695
+ "epoch": 1.466458658346334,
1696
+ "grad_norm": 0.5317255258560181,
1697
+ "learning_rate": 6.107298936826086e-06,
1698
+ "loss": 0.7884,
1699
+ "step": 238
1700
+ },
1701
+ {
1702
+ "epoch": 1.4726989079563182,
1703
+ "grad_norm": 0.5126049518585205,
1704
+ "learning_rate": 5.9761641452093225e-06,
1705
+ "loss": 0.7869,
1706
+ "step": 239
1707
+ },
1708
+ {
1709
+ "epoch": 1.4789391575663027,
1710
+ "grad_norm": 0.5322765707969666,
1711
+ "learning_rate": 5.845849869981137e-06,
1712
+ "loss": 0.7712,
1713
+ "step": 240
1714
+ },
1715
+ {
1716
+ "epoch": 1.4789391575663027,
1717
+ "eval_loss": 0.9110648036003113,
1718
+ "eval_runtime": 134.5659,
1719
+ "eval_samples_per_second": 100.702,
1720
+ "eval_steps_per_second": 6.294,
1721
+ "step": 240
1722
+ },
1723
+ {
1724
+ "epoch": 1.485179407176287,
1725
+ "grad_norm": 0.5006371140480042,
1726
+ "learning_rate": 5.716382684044191e-06,
1727
+ "loss": 0.7939,
1728
+ "step": 241
1729
+ },
1730
+ {
1731
+ "epoch": 1.4914196567862714,
1732
+ "grad_norm": 0.5099849104881287,
1733
+ "learning_rate": 5.587788987567785e-06,
1734
+ "loss": 0.771,
1735
+ "step": 242
1736
+ },
1737
+ {
1738
+ "epoch": 1.497659906396256,
1739
+ "grad_norm": 0.5397711396217346,
1740
+ "learning_rate": 5.460095002604533e-06,
1741
+ "loss": 0.7642,
1742
+ "step": 243
1743
+ },
1744
+ {
1745
+ "epoch": 1.5039001560062402,
1746
+ "grad_norm": 0.47754916548728943,
1747
+ "learning_rate": 5.333326767743263e-06,
1748
+ "loss": 0.7848,
1749
+ "step": 244
1750
+ },
1751
+ {
1752
+ "epoch": 1.5101404056162246,
1753
+ "grad_norm": 0.5114724636077881,
1754
+ "learning_rate": 5.207510132799436e-06,
1755
+ "loss": 0.7743,
1756
+ "step": 245
1757
+ },
1758
+ {
1759
+ "epoch": 1.5163806552262091,
1760
+ "grad_norm": 0.4859448969364166,
1761
+ "learning_rate": 5.082670753543961e-06,
1762
+ "loss": 0.7748,
1763
+ "step": 246
1764
+ },
1765
+ {
1766
+ "epoch": 1.5226209048361934,
1767
+ "grad_norm": 0.46158257126808167,
1768
+ "learning_rate": 4.958834086471683e-06,
1769
+ "loss": 0.7951,
1770
+ "step": 247
1771
+ },
1772
+ {
1773
+ "epoch": 1.5288611544461779,
1774
+ "grad_norm": 0.48695865273475647,
1775
+ "learning_rate": 4.836025383610382e-06,
1776
+ "loss": 0.7968,
1777
+ "step": 248
1778
+ },
1779
+ {
1780
+ "epoch": 1.5351014040561624,
1781
+ "grad_norm": 0.4924914240837097,
1782
+ "learning_rate": 4.714269687371581e-06,
1783
+ "loss": 0.792,
1784
+ "step": 249
1785
+ },
1786
+ {
1787
+ "epoch": 1.5413416536661466,
1788
+ "grad_norm": 0.5044175982475281,
1789
+ "learning_rate": 4.593591825444028e-06,
1790
+ "loss": 0.781,
1791
+ "step": 250
1792
+ },
1793
+ {
1794
+ "epoch": 1.547581903276131,
1795
+ "grad_norm": 0.4598456919193268,
1796
+ "learning_rate": 4.474016405730973e-06,
1797
+ "loss": 0.794,
1798
+ "step": 251
1799
+ },
1800
+ {
1801
+ "epoch": 1.5538221528861156,
1802
+ "grad_norm": 0.48866939544677734,
1803
+ "learning_rate": 4.355567811332311e-06,
1804
+ "loss": 0.7853,
1805
+ "step": 252
1806
+ },
1807
+ {
1808
+ "epoch": 1.5600624024960998,
1809
+ "grad_norm": 0.4878495931625366,
1810
+ "learning_rate": 4.2382701955724724e-06,
1811
+ "loss": 0.743,
1812
+ "step": 253
1813
+ },
1814
+ {
1815
+ "epoch": 1.566302652106084,
1816
+ "grad_norm": 0.4770466387271881,
1817
+ "learning_rate": 4.12214747707527e-06,
1818
+ "loss": 0.7442,
1819
+ "step": 254
1820
+ },
1821
+ {
1822
+ "epoch": 1.5725429017160688,
1823
+ "grad_norm": 0.4467732012271881,
1824
+ "learning_rate": 4.007223334886531e-06,
1825
+ "loss": 0.7611,
1826
+ "step": 255
1827
+ },
1828
+ {
1829
+ "epoch": 1.578783151326053,
1830
+ "grad_norm": 0.47116416692733765,
1831
+ "learning_rate": 3.893521203645618e-06,
1832
+ "loss": 0.7921,
1833
+ "step": 256
1834
+ },
1835
+ {
1836
+ "epoch": 1.5850234009360373,
1837
+ "grad_norm": 0.468517005443573,
1838
+ "learning_rate": 3.78106426880678e-06,
1839
+ "loss": 0.7811,
1840
+ "step": 257
1841
+ },
1842
+ {
1843
+ "epoch": 1.5912636505460218,
1844
+ "grad_norm": 0.46981289982795715,
1845
+ "learning_rate": 3.6698754619112974e-06,
1846
+ "loss": 0.7756,
1847
+ "step": 258
1848
+ },
1849
+ {
1850
+ "epoch": 1.5975039001560063,
1851
+ "grad_norm": 0.45571863651275635,
1852
+ "learning_rate": 3.5599774559114475e-06,
1853
+ "loss": 0.7469,
1854
+ "step": 259
1855
+ },
1856
+ {
1857
+ "epoch": 1.6037441497659906,
1858
+ "grad_norm": 0.4486157298088074,
1859
+ "learning_rate": 3.4513926605471504e-06,
1860
+ "loss": 0.7566,
1861
+ "step": 260
1862
+ },
1863
+ {
1864
+ "epoch": 1.609984399375975,
1865
+ "grad_norm": 0.47735777497291565,
1866
+ "learning_rate": 3.344143217776319e-06,
1867
+ "loss": 0.7753,
1868
+ "step": 261
1869
+ },
1870
+ {
1871
+ "epoch": 1.6162246489859595,
1872
+ "grad_norm": 0.4546492099761963,
1873
+ "learning_rate": 3.2382509972598087e-06,
1874
+ "loss": 0.7741,
1875
+ "step": 262
1876
+ },
1877
+ {
1878
+ "epoch": 1.6224648985959438,
1879
+ "grad_norm": 0.4690036177635193,
1880
+ "learning_rate": 3.133737591901864e-06,
1881
+ "loss": 0.7693,
1882
+ "step": 263
1883
+ },
1884
+ {
1885
+ "epoch": 1.6287051482059283,
1886
+ "grad_norm": 0.4607780873775482,
1887
+ "learning_rate": 3.0306243134470668e-06,
1888
+ "loss": 0.7312,
1889
+ "step": 264
1890
+ },
1891
+ {
1892
+ "epoch": 1.6349453978159127,
1893
+ "grad_norm": 0.4510229825973511,
1894
+ "learning_rate": 2.9289321881345257e-06,
1895
+ "loss": 0.7705,
1896
+ "step": 265
1897
+ },
1898
+ {
1899
+ "epoch": 1.641185647425897,
1900
+ "grad_norm": 0.43797171115875244,
1901
+ "learning_rate": 2.8286819524103657e-06,
1902
+ "loss": 0.7666,
1903
+ "step": 266
1904
+ },
1905
+ {
1906
+ "epoch": 1.6474258970358813,
1907
+ "grad_norm": 0.45275524258613586,
1908
+ "learning_rate": 2.7298940486992654e-06,
1909
+ "loss": 0.8028,
1910
+ "step": 267
1911
+ },
1912
+ {
1913
+ "epoch": 1.653666146645866,
1914
+ "grad_norm": 0.4479183852672577,
1915
+ "learning_rate": 2.6325886212359496e-06,
1916
+ "loss": 0.7647,
1917
+ "step": 268
1918
+ },
1919
+ {
1920
+ "epoch": 1.6599063962558502,
1921
+ "grad_norm": 0.4575185775756836,
1922
+ "learning_rate": 2.5367855119575314e-06,
1923
+ "loss": 0.7731,
1924
+ "step": 269
1925
+ },
1926
+ {
1927
+ "epoch": 1.6661466458658345,
1928
+ "grad_norm": 0.45092037320137024,
1929
+ "learning_rate": 2.4425042564574186e-06,
1930
+ "loss": 0.7895,
1931
+ "step": 270
1932
+ },
1933
+ {
1934
+ "epoch": 1.672386895475819,
1935
+ "grad_norm": 0.4297903776168823,
1936
+ "learning_rate": 2.3497640800017687e-06,
1937
+ "loss": 0.7597,
1938
+ "step": 271
1939
+ },
1940
+ {
1941
+ "epoch": 1.6786271450858035,
1942
+ "grad_norm": 0.43731772899627686,
1943
+ "learning_rate": 2.2585838936091753e-06,
1944
+ "loss": 0.7775,
1945
+ "step": 272
1946
+ },
1947
+ {
1948
+ "epoch": 1.6848673946957877,
1949
+ "grad_norm": 0.4288908541202545,
1950
+ "learning_rate": 2.1689822901944456e-06,
1951
+ "loss": 0.787,
1952
+ "step": 273
1953
+ },
1954
+ {
1955
+ "epoch": 1.6911076443057722,
1956
+ "grad_norm": 0.42555147409439087,
1957
+ "learning_rate": 2.0809775407772505e-06,
1958
+ "loss": 0.7751,
1959
+ "step": 274
1960
+ },
1961
+ {
1962
+ "epoch": 1.6973478939157567,
1963
+ "grad_norm": 0.45276904106140137,
1964
+ "learning_rate": 1.994587590756397e-06,
1965
+ "loss": 0.7893,
1966
+ "step": 275
1967
+ },
1968
+ {
1969
+ "epoch": 1.703588143525741,
1970
+ "grad_norm": 0.44294846057891846,
1971
+ "learning_rate": 1.9098300562505266e-06,
1972
+ "loss": 0.7794,
1973
+ "step": 276
1974
+ },
1975
+ {
1976
+ "epoch": 1.7098283931357254,
1977
+ "grad_norm": 0.4307778775691986,
1978
+ "learning_rate": 1.826722220505931e-06,
1979
+ "loss": 0.7791,
1980
+ "step": 277
1981
+ },
1982
+ {
1983
+ "epoch": 1.71606864274571,
1984
+ "grad_norm": 0.43245357275009155,
1985
+ "learning_rate": 1.74528103037226e-06,
1986
+ "loss": 0.7497,
1987
+ "step": 278
1988
+ },
1989
+ {
1990
+ "epoch": 1.7223088923556942,
1991
+ "grad_norm": 0.4251644015312195,
1992
+ "learning_rate": 1.6655230928468257e-06,
1993
+ "loss": 0.7743,
1994
+ "step": 279
1995
+ },
1996
+ {
1997
+ "epoch": 1.7285491419656787,
1998
+ "grad_norm": 0.4321819543838501,
1999
+ "learning_rate": 1.587464671688187e-06,
2000
+ "loss": 0.7522,
2001
+ "step": 280
2002
+ },
2003
+ {
2004
+ "epoch": 1.7347893915756631,
2005
+ "grad_norm": 0.4292062222957611,
2006
+ "learning_rate": 1.5111216840997745e-06,
2007
+ "loss": 0.7698,
2008
+ "step": 281
2009
+ },
2010
+ {
2011
+ "epoch": 1.7410296411856474,
2012
+ "grad_norm": 0.45093026757240295,
2013
+ "learning_rate": 1.436509697484111e-06,
2014
+ "loss": 0.7647,
2015
+ "step": 282
2016
+ },
2017
+ {
2018
+ "epoch": 1.7472698907956317,
2019
+ "grad_norm": 0.42376089096069336,
2020
+ "learning_rate": 1.3636439262684299e-06,
2021
+ "loss": 0.7556,
2022
+ "step": 283
2023
+ },
2024
+ {
2025
+ "epoch": 1.7535101404056164,
2026
+ "grad_norm": 0.4337958097457886,
2027
+ "learning_rate": 1.2925392288022299e-06,
2028
+ "loss": 0.7756,
2029
+ "step": 284
2030
+ },
2031
+ {
2032
+ "epoch": 1.7597503900156006,
2033
+ "grad_norm": 0.4319595992565155,
2034
+ "learning_rate": 1.2232101043274437e-06,
2035
+ "loss": 0.7816,
2036
+ "step": 285
2037
+ },
2038
+ {
2039
+ "epoch": 1.765990639625585,
2040
+ "grad_norm": 0.4335976243019104,
2041
+ "learning_rate": 1.1556706900218572e-06,
2042
+ "loss": 0.7902,
2043
+ "step": 286
2044
+ },
2045
+ {
2046
+ "epoch": 1.7722308892355694,
2047
+ "grad_norm": 0.4158109724521637,
2048
+ "learning_rate": 1.0899347581163222e-06,
2049
+ "loss": 0.7396,
2050
+ "step": 287
2051
+ },
2052
+ {
2053
+ "epoch": 1.7784711388455539,
2054
+ "grad_norm": 0.42235442996025085,
2055
+ "learning_rate": 1.0260157130864178e-06,
2056
+ "loss": 0.7747,
2057
+ "step": 288
2058
+ },
2059
+ {
2060
+ "epoch": 1.7847113884555381,
2061
+ "grad_norm": 0.43022453784942627,
2062
+ "learning_rate": 9.63926588919083e-07,
2063
+ "loss": 0.7616,
2064
+ "step": 289
2065
+ },
2066
+ {
2067
+ "epoch": 1.7909516380655226,
2068
+ "grad_norm": 0.42115500569343567,
2069
+ "learning_rate": 9.036800464548157e-07,
2070
+ "loss": 0.7609,
2071
+ "step": 290
2072
+ },
2073
+ {
2074
+ "epoch": 1.797191887675507,
2075
+ "grad_norm": 0.43961915373802185,
2076
+ "learning_rate": 8.4528837080594e-07,
2077
+ "loss": 0.7665,
2078
+ "step": 291
2079
+ },
2080
+ {
2081
+ "epoch": 1.8034321372854913,
2082
+ "grad_norm": 0.42159175872802734,
2083
+ "learning_rate": 7.887634688515e-07,
2084
+ "loss": 0.7684,
2085
+ "step": 292
2086
+ },
2087
+ {
2088
+ "epoch": 1.8096723868954758,
2089
+ "grad_norm": 0.4211348295211792,
2090
+ "learning_rate": 7.341168668092857e-07,
2091
+ "loss": 0.7701,
2092
+ "step": 293
2093
+ },
2094
+ {
2095
+ "epoch": 1.8159126365054603,
2096
+ "grad_norm": 0.447083055973053,
2097
+ "learning_rate": 6.813597078854772e-07,
2098
+ "loss": 0.8051,
2099
+ "step": 294
2100
+ },
2101
+ {
2102
+ "epoch": 1.8221528861154446,
2103
+ "grad_norm": 0.42439502477645874,
2104
+ "learning_rate": 6.305027500023841e-07,
2105
+ "loss": 0.7794,
2106
+ "step": 295
2107
+ },
2108
+ {
2109
+ "epoch": 1.828393135725429,
2110
+ "grad_norm": 0.43265220522880554,
2111
+ "learning_rate": 5.815563636047539e-07,
2112
+ "loss": 0.7722,
2113
+ "step": 296
2114
+ },
2115
+ {
2116
+ "epoch": 1.8346333853354135,
2117
+ "grad_norm": 0.4244794249534607,
2118
+ "learning_rate": 5.345305295450997e-07,
2119
+ "loss": 0.7638,
2120
+ "step": 297
2121
+ },
2122
+ {
2123
+ "epoch": 1.8408736349453978,
2124
+ "grad_norm": 0.41255486011505127,
2125
+ "learning_rate": 4.894348370484648e-07,
2126
+ "loss": 0.772,
2127
+ "step": 298
2128
+ },
2129
+ {
2130
+ "epoch": 1.847113884555382,
2131
+ "grad_norm": 0.4242880344390869,
2132
+ "learning_rate": 4.4627848175703315e-07,
2133
+ "loss": 0.7643,
2134
+ "step": 299
2135
+ },
2136
+ {
2137
+ "epoch": 1.8533541341653668,
2138
+ "grad_norm": 0.41673314571380615,
2139
+ "learning_rate": 4.0507026385502747e-07,
2140
+ "loss": 0.7601,
2141
+ "step": 300
2142
+ },
2143
+ {
2144
+ "epoch": 1.859594383775351,
2145
+ "grad_norm": 0.42518967390060425,
2146
+ "learning_rate": 3.658185862742103e-07,
2147
+ "loss": 0.7699,
2148
+ "step": 301
2149
+ },
2150
+ {
2151
+ "epoch": 1.8658346333853353,
2152
+ "grad_norm": 0.42029449343681335,
2153
+ "learning_rate": 3.2853145298042954e-07,
2154
+ "loss": 0.7498,
2155
+ "step": 302
2156
+ },
2157
+ {
2158
+ "epoch": 1.8720748829953198,
2159
+ "grad_norm": 0.4201337695121765,
2160
+ "learning_rate": 2.93216467341475e-07,
2161
+ "loss": 0.7626,
2162
+ "step": 303
2163
+ },
2164
+ {
2165
+ "epoch": 1.8783151326053042,
2166
+ "grad_norm": 0.42505332827568054,
2167
+ "learning_rate": 2.5988083057666534e-07,
2168
+ "loss": 0.774,
2169
+ "step": 304
2170
+ },
2171
+ {
2172
+ "epoch": 1.8845553822152885,
2173
+ "grad_norm": 0.41834697127342224,
2174
+ "learning_rate": 2.2853134028840594e-07,
2175
+ "loss": 0.7638,
2176
+ "step": 305
2177
+ },
2178
+ {
2179
+ "epoch": 1.890795631825273,
2180
+ "grad_norm": 0.4278232455253601,
2181
+ "learning_rate": 1.9917438907606556e-07,
2182
+ "loss": 0.7906,
2183
+ "step": 306
2184
+ },
2185
+ {
2186
+ "epoch": 1.8970358814352575,
2187
+ "grad_norm": 0.429078608751297,
2188
+ "learning_rate": 1.7181596323244453e-07,
2189
+ "loss": 0.7839,
2190
+ "step": 307
2191
+ },
2192
+ {
2193
+ "epoch": 1.9032761310452417,
2194
+ "grad_norm": 0.4142579138278961,
2195
+ "learning_rate": 1.464616415230702e-07,
2196
+ "loss": 0.7687,
2197
+ "step": 308
2198
+ },
2199
+ {
2200
+ "epoch": 1.9095163806552262,
2201
+ "grad_norm": 0.40971171855926514,
2202
+ "learning_rate": 1.231165940486234e-07,
2203
+ "loss": 0.7647,
2204
+ "step": 309
2205
+ },
2206
+ {
2207
+ "epoch": 1.9157566302652107,
2208
+ "grad_norm": 0.4336109161376953,
2209
+ "learning_rate": 1.0178558119067316e-07,
2210
+ "loss": 0.7691,
2211
+ "step": 310
2212
+ },
2213
+ {
2214
+ "epoch": 1.921996879875195,
2215
+ "grad_norm": 0.40623047947883606,
2216
+ "learning_rate": 8.247295264097288e-08,
2217
+ "loss": 0.7728,
2218
+ "step": 311
2219
+ },
2220
+ {
2221
+ "epoch": 1.9282371294851794,
2222
+ "grad_norm": 0.4205041527748108,
2223
+ "learning_rate": 6.51826465144978e-08,
2224
+ "loss": 0.7533,
2225
+ "step": 312
2226
+ },
2227
+ {
2228
+ "epoch": 1.934477379095164,
2229
+ "grad_norm": 0.416535347700119,
2230
+ "learning_rate": 4.991818854640396e-08,
2231
+ "loss": 0.7826,
2232
+ "step": 313
2233
+ },
2234
+ {
2235
+ "epoch": 1.9407176287051482,
2236
+ "grad_norm": 0.41483184695243835,
2237
+ "learning_rate": 3.668269137308666e-08,
2238
+ "loss": 0.7688,
2239
+ "step": 314
2240
+ },
2241
+ {
2242
+ "epoch": 1.9469578783151325,
2243
+ "grad_norm": 0.4072718322277069,
2244
+ "learning_rate": 2.547885389746485e-08,
2245
+ "loss": 0.7943,
2246
+ "step": 315
2247
+ },
2248
+ {
2249
+ "epoch": 1.9531981279251172,
2250
+ "grad_norm": 0.413289338350296,
2251
+ "learning_rate": 1.630896073864352e-08,
2252
+ "loss": 0.7867,
2253
+ "step": 316
2254
+ },
2255
+ {
2256
+ "epoch": 1.9594383775351014,
2257
+ "grad_norm": 0.4177180528640747,
2258
+ "learning_rate": 9.174881766043086e-09,
2259
+ "loss": 0.781,
2260
+ "step": 317
2261
+ },
2262
+ {
2263
+ "epoch": 1.9656786271450857,
2264
+ "grad_norm": 0.41807225346565247,
2265
+ "learning_rate": 4.0780717181077015e-09,
2266
+ "loss": 0.769,
2267
+ "step": 318
2268
+ },
2269
+ {
2270
+ "epoch": 1.9719188767550702,
2271
+ "grad_norm": 0.41558825969696045,
2272
+ "learning_rate": 1.019569905666984e-09,
2273
+ "loss": 0.7504,
2274
+ "step": 319
2275
+ },
2276
+ {
2277
+ "epoch": 1.9781591263650546,
2278
+ "grad_norm": 0.4160574674606323,
2279
+ "learning_rate": 0.0,
2280
+ "loss": 0.8025,
2281
+ "step": 320
2282
+ },
2283
+ {
2284
+ "epoch": 1.9781591263650546,
2285
+ "eval_loss": 0.903252899646759,
2286
+ "eval_runtime": 134.5566,
2287
+ "eval_samples_per_second": 100.709,
2288
+ "eval_steps_per_second": 6.295,
2289
+ "step": 320
2290
+ }
2291
+ ],
2292
+ "logging_steps": 1,
2293
+ "max_steps": 320,
2294
+ "num_input_tokens_seen": 0,
2295
+ "num_train_epochs": 2,
2296
+ "save_steps": 80,
2297
+ "stateful_callbacks": {
2298
+ "TrainerControl": {
2299
+ "args": {
2300
+ "should_epoch_stop": false,
2301
+ "should_evaluate": false,
2302
+ "should_log": false,
2303
+ "should_save": true,
2304
+ "should_training_stop": true
2305
+ },
2306
+ "attributes": {}
2307
+ }
2308
+ },
2309
+ "total_flos": 1.9476972312723456e+18,
2310
+ "train_batch_size": 2,
2311
+ "trial_name": null,
2312
+ "trial_params": null
2313
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591224f87192e59011e298ebd929ad9beb36915e0ea0e3ed704591a3004b0216
3
+ size 6520