talzoomanzoo commited on
Commit
6b7ef02
·
verified ·
1 Parent(s): 9fe37e0

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
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": 131072,
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",
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"
12
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f353ac1cb263eb50b5ccd07ce7dab3ee21a13b84c8a1d7e9bacb54bc1f7f292f
3
+ size 4886466168
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a46436fd6f2cb282ce83efe72cf1b7e030189ca2a098045b281d63da007944
3
+ size 4832007448
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fa9f1a4e40cac9b81779d59357b38e0d02e6b8460d504346eb1d03b71c6c94
3
+ size 4999813112
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bed9ac67cfe2eaa9760e5111344d8d766c66f4ffa7e4c8a87facdbb699dac51
3
+ size 4999813128
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296483aa9e05af2140c6f393836dbdf04028ec74f00fef324088b9bb4481a611
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:bb61ceb231831760b403499b6110a298eeaeb84db2d9e84a728324102e884168
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:af524ac308e7a7ff52a0b3e29659c3ea33f7d032431cf38299484d9cb1e224e6
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
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b074bf97f241c2662caa5ce956b03d1249c3cc0713b6aef7796673362754f98
3
+ size 14512
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58aed9e8d78903cb12015375021c729c3f6c5fd1a1e19e7aee6ddde57c3310b9
3
+ size 14512
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064c6b0f6bb7efd8795b891468d7974ce26df23b449faeb18f6be5e4dd5a3e09
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 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
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
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
trainer_state.json ADDED
@@ -0,0 +1,2995 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9855421686746988,
5
+ "eval_steps": 52,
6
+ "global_step": 414,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004819277108433735,
13
+ "grad_norm": 22.358972549438477,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.5652,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.004819277108433735,
20
+ "eval_loss": 1.4657918214797974,
21
+ "eval_runtime": 407.7477,
22
+ "eval_samples_per_second": 3.983,
23
+ "eval_steps_per_second": 0.996,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.00963855421686747,
28
+ "grad_norm": 21.81947135925293,
29
+ "learning_rate": 4.000000000000001e-06,
30
+ "loss": 1.4671,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.014457831325301205,
35
+ "grad_norm": 17.827760696411133,
36
+ "learning_rate": 6e-06,
37
+ "loss": 1.3721,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.01927710843373494,
42
+ "grad_norm": 12.67513656616211,
43
+ "learning_rate": 8.000000000000001e-06,
44
+ "loss": 1.2023,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.024096385542168676,
49
+ "grad_norm": 12.69899845123291,
50
+ "learning_rate": 1e-05,
51
+ "loss": 1.1047,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.02891566265060241,
56
+ "grad_norm": 10.573343276977539,
57
+ "learning_rate": 1.2e-05,
58
+ "loss": 1.0638,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.033734939759036145,
63
+ "grad_norm": 7.3869709968566895,
64
+ "learning_rate": 1.4e-05,
65
+ "loss": 1.0308,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.03855421686746988,
70
+ "grad_norm": 8.336923599243164,
71
+ "learning_rate": 1.6000000000000003e-05,
72
+ "loss": 1.0038,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.043373493975903614,
77
+ "grad_norm": 8.090559959411621,
78
+ "learning_rate": 1.8e-05,
79
+ "loss": 1.0536,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.04819277108433735,
84
+ "grad_norm": 5.664218425750732,
85
+ "learning_rate": 2e-05,
86
+ "loss": 0.9744,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.05301204819277108,
91
+ "grad_norm": 27.36557388305664,
92
+ "learning_rate": 1.9999697653579705e-05,
93
+ "loss": 1.0602,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.05783132530120482,
98
+ "grad_norm": 13.406028747558594,
99
+ "learning_rate": 1.9998790632601496e-05,
100
+ "loss": 1.038,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.06265060240963856,
105
+ "grad_norm": 5.966604709625244,
106
+ "learning_rate": 1.999727899191228e-05,
107
+ "loss": 0.9748,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.06746987951807229,
112
+ "grad_norm": 5.611815452575684,
113
+ "learning_rate": 1.999516282291988e-05,
114
+ "loss": 0.9866,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.07228915662650602,
119
+ "grad_norm": 5.1906819343566895,
120
+ "learning_rate": 1.9992442253587533e-05,
121
+ "loss": 0.9375,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.07710843373493977,
126
+ "grad_norm": 5.197139739990234,
127
+ "learning_rate": 1.998911744842611e-05,
128
+ "loss": 0.9655,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.0819277108433735,
133
+ "grad_norm": 3.9094479084014893,
134
+ "learning_rate": 1.99851886084842e-05,
135
+ "loss": 0.95,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.08674698795180723,
140
+ "grad_norm": 5.180599212646484,
141
+ "learning_rate": 1.9980655971335944e-05,
142
+ "loss": 1.0035,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.09156626506024096,
147
+ "grad_norm": 4.283572673797607,
148
+ "learning_rate": 1.9975519811066665e-05,
149
+ "loss": 0.9105,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.0963855421686747,
154
+ "grad_norm": 3.92655086517334,
155
+ "learning_rate": 1.9969780438256295e-05,
156
+ "loss": 1.0165,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.10120481927710843,
161
+ "grad_norm": 4.255762577056885,
162
+ "learning_rate": 1.99634381999606e-05,
163
+ "loss": 0.9621,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.10602409638554217,
168
+ "grad_norm": 4.64040994644165,
169
+ "learning_rate": 1.995649347969019e-05,
170
+ "loss": 0.9977,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.1108433734939759,
175
+ "grad_norm": 4.476572513580322,
176
+ "learning_rate": 1.9948946697387322e-05,
177
+ "loss": 1.0254,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.11566265060240964,
182
+ "grad_norm": 4.513229846954346,
183
+ "learning_rate": 1.9940798309400527e-05,
184
+ "loss": 0.9874,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.12048192771084337,
189
+ "grad_norm": 4.014408111572266,
190
+ "learning_rate": 1.993204880845699e-05,
191
+ "loss": 0.9334,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.12530120481927712,
196
+ "grad_norm": 3.4205386638641357,
197
+ "learning_rate": 1.992269872363277e-05,
198
+ "loss": 0.8867,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.13012048192771083,
203
+ "grad_norm": 3.855297088623047,
204
+ "learning_rate": 1.9912748620320796e-05,
205
+ "loss": 0.9767,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.13493975903614458,
210
+ "grad_norm": 3.8717806339263916,
211
+ "learning_rate": 1.9902199100196697e-05,
212
+ "loss": 0.9989,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.13975903614457832,
217
+ "grad_norm": 3.8353829383850098,
218
+ "learning_rate": 1.98910508011824e-05,
219
+ "loss": 0.9553,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.14457831325301204,
224
+ "grad_norm": 3.8910715579986572,
225
+ "learning_rate": 1.987930439740757e-05,
226
+ "loss": 0.9659,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.1493975903614458,
231
+ "grad_norm": 4.098902225494385,
232
+ "learning_rate": 1.9866960599168825e-05,
233
+ "loss": 0.9066,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.15421686746987953,
238
+ "grad_norm": 3.609893321990967,
239
+ "learning_rate": 1.9854020152886816e-05,
240
+ "loss": 0.9287,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.15903614457831325,
245
+ "grad_norm": 3.6637232303619385,
246
+ "learning_rate": 1.9840483841061058e-05,
247
+ "loss": 0.8945,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.163855421686747,
252
+ "grad_norm": 3.991074562072754,
253
+ "learning_rate": 1.982635248222264e-05,
254
+ "loss": 0.8992,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.1686746987951807,
259
+ "grad_norm": 4.303783416748047,
260
+ "learning_rate": 1.981162693088471e-05,
261
+ "loss": 0.9494,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.17349397590361446,
266
+ "grad_norm": 4.269317150115967,
267
+ "learning_rate": 1.9796308077490817e-05,
268
+ "loss": 0.9754,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.1783132530120482,
273
+ "grad_norm": 4.001611709594727,
274
+ "learning_rate": 1.978039684836106e-05,
275
+ "loss": 0.9202,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.18313253012048192,
280
+ "grad_norm": 4.386765956878662,
281
+ "learning_rate": 1.976389420563607e-05,
282
+ "loss": 0.9723,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.18795180722891566,
287
+ "grad_norm": 3.8781235218048096,
288
+ "learning_rate": 1.9746801147218844e-05,
289
+ "loss": 0.9458,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.1927710843373494,
294
+ "grad_norm": 4.019350528717041,
295
+ "learning_rate": 1.9729118706714377e-05,
296
+ "loss": 0.9313,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.19759036144578312,
301
+ "grad_norm": 4.535061836242676,
302
+ "learning_rate": 1.9710847953367193e-05,
303
+ "loss": 1.0018,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.20240963855421687,
308
+ "grad_norm": 4.199214458465576,
309
+ "learning_rate": 1.9691989991996663e-05,
310
+ "loss": 1.0205,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.20722891566265061,
315
+ "grad_norm": 3.905357599258423,
316
+ "learning_rate": 1.9672545962930214e-05,
317
+ "loss": 0.8749,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.21204819277108433,
322
+ "grad_norm": 5.23562479019165,
323
+ "learning_rate": 1.9652517041934357e-05,
324
+ "loss": 0.9942,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.21686746987951808,
329
+ "grad_norm": 4.048227310180664,
330
+ "learning_rate": 1.9631904440143614e-05,
331
+ "loss": 0.8923,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.2216867469879518,
336
+ "grad_norm": 3.829437732696533,
337
+ "learning_rate": 1.9610709403987248e-05,
338
+ "loss": 0.9125,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.22650602409638554,
343
+ "grad_norm": 3.8191184997558594,
344
+ "learning_rate": 1.9588933215113926e-05,
345
+ "loss": 0.8825,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.23132530120481928,
350
+ "grad_norm": 3.622243642807007,
351
+ "learning_rate": 1.95665771903142e-05,
352
+ "loss": 0.9214,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.236144578313253,
357
+ "grad_norm": 4.483166217803955,
358
+ "learning_rate": 1.954364268144088e-05,
359
+ "loss": 0.9027,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.24096385542168675,
364
+ "grad_norm": 4.152469635009766,
365
+ "learning_rate": 1.95201310753273e-05,
366
+ "loss": 0.9439,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.2457831325301205,
371
+ "grad_norm": 3.4553298950195312,
372
+ "learning_rate": 1.949604379370345e-05,
373
+ "loss": 0.9282,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.25060240963855424,
378
+ "grad_norm": 3.4458351135253906,
379
+ "learning_rate": 1.9471382293110004e-05,
380
+ "loss": 0.8734,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.25060240963855424,
385
+ "eval_loss": 0.9173946380615234,
386
+ "eval_runtime": 409.5887,
387
+ "eval_samples_per_second": 3.965,
388
+ "eval_steps_per_second": 0.991,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.25542168674698795,
393
+ "grad_norm": 3.958357810974121,
394
+ "learning_rate": 1.9446148064810243e-05,
395
+ "loss": 0.9208,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.26024096385542167,
400
+ "grad_norm": 3.440983295440674,
401
+ "learning_rate": 1.9420342634699893e-05,
402
+ "loss": 0.9079,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.26506024096385544,
407
+ "grad_norm": 3.14013934135437,
408
+ "learning_rate": 1.9393967563214833e-05,
409
+ "loss": 0.8653,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.26987951807228916,
414
+ "grad_norm": 3.123026132583618,
415
+ "learning_rate": 1.936702444523675e-05,
416
+ "loss": 0.8783,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2746987951807229,
421
+ "grad_norm": 3.9587645530700684,
422
+ "learning_rate": 1.9339514909996706e-05,
423
+ "loss": 0.9239,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.27951807228915665,
428
+ "grad_norm": 4.004755973815918,
429
+ "learning_rate": 1.9311440620976597e-05,
430
+ "loss": 0.9284,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.28433734939759037,
435
+ "grad_norm": 3.3966100215911865,
436
+ "learning_rate": 1.928280327580858e-05,
437
+ "loss": 0.9284,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2891566265060241,
442
+ "grad_norm": 3.665738105773926,
443
+ "learning_rate": 1.925360460617242e-05,
444
+ "loss": 0.9185,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.29397590361445786,
449
+ "grad_norm": 3.625847339630127,
450
+ "learning_rate": 1.9223846377690754e-05,
451
+ "loss": 0.9208,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2987951807228916,
456
+ "grad_norm": 4.189015865325928,
457
+ "learning_rate": 1.9193530389822364e-05,
458
+ "loss": 0.9652,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.3036144578313253,
463
+ "grad_norm": 4.030600070953369,
464
+ "learning_rate": 1.9162658475753328e-05,
465
+ "loss": 0.9312,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.30843373493975906,
470
+ "grad_norm": 3.5443010330200195,
471
+ "learning_rate": 1.913123250228619e-05,
472
+ "loss": 0.9061,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.3132530120481928,
477
+ "grad_norm": 4.126009464263916,
478
+ "learning_rate": 1.9099254369727062e-05,
479
+ "loss": 0.9663,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3180722891566265,
484
+ "grad_norm": 2.7072594165802,
485
+ "learning_rate": 1.9066726011770725e-05,
486
+ "loss": 0.8867,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3228915662650602,
491
+ "grad_norm": 3.835609197616577,
492
+ "learning_rate": 1.90336493953837e-05,
493
+ "loss": 0.8732,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.327710843373494,
498
+ "grad_norm": 3.9530820846557617,
499
+ "learning_rate": 1.90000265206853e-05,
500
+ "loss": 0.9577,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3325301204819277,
505
+ "grad_norm": 3.488438129425049,
506
+ "learning_rate": 1.8965859420826685e-05,
507
+ "loss": 0.8677,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3373493975903614,
512
+ "grad_norm": 3.690389394760132,
513
+ "learning_rate": 1.8931150161867917e-05,
514
+ "loss": 0.9178,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.3421686746987952,
519
+ "grad_norm": 3.0712807178497314,
520
+ "learning_rate": 1.889590084265304e-05,
521
+ "loss": 0.8756,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3469879518072289,
526
+ "grad_norm": 2.9820151329040527,
527
+ "learning_rate": 1.8860113594683148e-05,
528
+ "loss": 0.8897,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.35180722891566263,
533
+ "grad_norm": 3.4041998386383057,
534
+ "learning_rate": 1.882379058198751e-05,
535
+ "loss": 0.9138,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3566265060240964,
540
+ "grad_norm": 3.2408714294433594,
541
+ "learning_rate": 1.878693400099269e-05,
542
+ "loss": 0.9034,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.3614457831325301,
547
+ "grad_norm": 3.3161394596099854,
548
+ "learning_rate": 1.874954608038976e-05,
549
+ "loss": 0.9153,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.36626506024096384,
554
+ "grad_norm": 3.4559402465820312,
555
+ "learning_rate": 1.8711629080999506e-05,
556
+ "loss": 0.9402,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3710843373493976,
561
+ "grad_norm": 3.232393264770508,
562
+ "learning_rate": 1.867318529563574e-05,
563
+ "loss": 0.934,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3759036144578313,
568
+ "grad_norm": 2.9000368118286133,
569
+ "learning_rate": 1.8634217048966638e-05,
570
+ "loss": 0.899,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.38072289156626504,
575
+ "grad_norm": 3.0255680084228516,
576
+ "learning_rate": 1.8594726697374173e-05,
577
+ "loss": 0.8689,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.3855421686746988,
582
+ "grad_norm": 3.2437119483947754,
583
+ "learning_rate": 1.855471662881164e-05,
584
+ "loss": 0.8719,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.39036144578313253,
589
+ "grad_norm": 3.1790125370025635,
590
+ "learning_rate": 1.8514189262659235e-05,
591
+ "loss": 0.9318,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.39518072289156625,
596
+ "grad_norm": 3.26911997795105,
597
+ "learning_rate": 1.8473147049577777e-05,
598
+ "loss": 0.8369,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.4,
603
+ "grad_norm": 3.6041669845581055,
604
+ "learning_rate": 1.8431592471360506e-05,
605
+ "loss": 0.937,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.40481927710843374,
610
+ "grad_norm": 3.253331422805786,
611
+ "learning_rate": 1.8389528040783014e-05,
612
+ "loss": 0.8296,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.40963855421686746,
617
+ "grad_norm": 3.0919277667999268,
618
+ "learning_rate": 1.8346956301451303e-05,
619
+ "loss": 0.9584,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.41445783132530123,
624
+ "grad_norm": 2.9307501316070557,
625
+ "learning_rate": 1.8303879827647977e-05,
626
+ "loss": 0.8596,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.41927710843373495,
631
+ "grad_norm": 2.7852823734283447,
632
+ "learning_rate": 1.826030122417656e-05,
633
+ "loss": 0.8651,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.42409638554216866,
638
+ "grad_norm": 3.0654289722442627,
639
+ "learning_rate": 1.821622312620401e-05,
640
+ "loss": 0.8692,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.42891566265060244,
645
+ "grad_norm": 3.1769044399261475,
646
+ "learning_rate": 1.8171648199101347e-05,
647
+ "loss": 0.884,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.43373493975903615,
652
+ "grad_norm": 3.5062806606292725,
653
+ "learning_rate": 1.8126579138282502e-05,
654
+ "loss": 0.8249,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.43855421686746987,
659
+ "grad_norm": 3.4617791175842285,
660
+ "learning_rate": 1.8081018669041324e-05,
661
+ "loss": 0.8441,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.4433734939759036,
666
+ "grad_norm": 2.880967140197754,
667
+ "learning_rate": 1.803496954638676e-05,
668
+ "loss": 0.8334,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.44819277108433736,
673
+ "grad_norm": 3.091942071914673,
674
+ "learning_rate": 1.798843455487629e-05,
675
+ "loss": 0.8333,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4530120481927711,
680
+ "grad_norm": 3.1967666149139404,
681
+ "learning_rate": 1.7941416508447537e-05,
682
+ "loss": 0.8893,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4578313253012048,
687
+ "grad_norm": 2.6479837894439697,
688
+ "learning_rate": 1.7893918250248106e-05,
689
+ "loss": 0.8183,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.46265060240963857,
694
+ "grad_norm": 3.1210310459136963,
695
+ "learning_rate": 1.784594265246366e-05,
696
+ "loss": 0.9058,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.4674698795180723,
701
+ "grad_norm": 3.483987331390381,
702
+ "learning_rate": 1.7797492616144256e-05,
703
+ "loss": 0.8344,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.472289156626506,
708
+ "grad_norm": 3.0755786895751953,
709
+ "learning_rate": 1.77485710710289e-05,
710
+ "loss": 0.8815,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.4771084337349398,
715
+ "grad_norm": 3.1040232181549072,
716
+ "learning_rate": 1.7699180975368397e-05,
717
+ "loss": 0.8541,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4819277108433735,
722
+ "grad_norm": 2.973416805267334,
723
+ "learning_rate": 1.764932531574648e-05,
724
+ "loss": 0.8576,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4867469879518072,
729
+ "grad_norm": 2.6803696155548096,
730
+ "learning_rate": 1.759900710689918e-05,
731
+ "loss": 0.8481,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 0.491566265060241,
736
+ "grad_norm": 2.7588868141174316,
737
+ "learning_rate": 1.7548229391532572e-05,
738
+ "loss": 0.8094,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 0.4963855421686747,
743
+ "grad_norm": 3.0891292095184326,
744
+ "learning_rate": 1.7496995240138745e-05,
745
+ "loss": 0.8736,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 0.5012048192771085,
750
+ "grad_norm": 2.803755521774292,
751
+ "learning_rate": 1.7445307750810153e-05,
752
+ "loss": 0.8493,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 0.5012048192771085,
757
+ "eval_loss": 0.8754510283470154,
758
+ "eval_runtime": 409.6247,
759
+ "eval_samples_per_second": 3.965,
760
+ "eval_steps_per_second": 0.991,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.5060240963855421,
765
+ "grad_norm": 3.214620590209961,
766
+ "learning_rate": 1.7393170049052274e-05,
767
+ "loss": 0.898,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.5108433734939759,
772
+ "grad_norm": 2.732611656188965,
773
+ "learning_rate": 1.7340585287594605e-05,
774
+ "loss": 0.862,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.5156626506024097,
779
+ "grad_norm": 3.1261470317840576,
780
+ "learning_rate": 1.728755664620002e-05,
781
+ "loss": 0.9223,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5204819277108433,
786
+ "grad_norm": 3.0365259647369385,
787
+ "learning_rate": 1.72340873314725e-05,
788
+ "loss": 0.8637,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5253012048192771,
793
+ "grad_norm": 3.233238458633423,
794
+ "learning_rate": 1.718018057666323e-05,
795
+ "loss": 0.8649,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5301204819277109,
800
+ "grad_norm": 2.6572329998016357,
801
+ "learning_rate": 1.7125839641475074e-05,
802
+ "loss": 0.8035,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5349397590361445,
807
+ "grad_norm": 2.850344181060791,
808
+ "learning_rate": 1.7071067811865477e-05,
809
+ "loss": 0.8206,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5397590361445783,
814
+ "grad_norm": 3.0765762329101562,
815
+ "learning_rate": 1.7015868399847768e-05,
816
+ "loss": 0.8926,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5445783132530121,
821
+ "grad_norm": 2.928662061691284,
822
+ "learning_rate": 1.6960244743290867e-05,
823
+ "loss": 0.8418,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5493975903614458,
828
+ "grad_norm": 2.8436033725738525,
829
+ "learning_rate": 1.690420020571747e-05,
830
+ "loss": 0.8105,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5542168674698795,
835
+ "grad_norm": 3.2781031131744385,
836
+ "learning_rate": 1.6847738176100632e-05,
837
+ "loss": 0.9141,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5590361445783133,
842
+ "grad_norm": 2.989654302597046,
843
+ "learning_rate": 1.6790862068658863e-05,
844
+ "loss": 0.9185,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.563855421686747,
849
+ "grad_norm": 2.646963596343994,
850
+ "learning_rate": 1.673357532264966e-05,
851
+ "loss": 0.8768,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5686746987951807,
856
+ "grad_norm": 2.966282844543457,
857
+ "learning_rate": 1.667588140216154e-05,
858
+ "loss": 0.8473,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5734939759036145,
863
+ "grad_norm": 3.1524553298950195,
864
+ "learning_rate": 1.6617783795904564e-05,
865
+ "loss": 0.8382,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5783132530120482,
870
+ "grad_norm": 3.058159112930298,
871
+ "learning_rate": 1.65592860169994e-05,
872
+ "loss": 0.8664,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5831325301204819,
877
+ "grad_norm": 2.9778072834014893,
878
+ "learning_rate": 1.650039160276485e-05,
879
+ "loss": 0.8986,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5879518072289157,
884
+ "grad_norm": 3.4090819358825684,
885
+ "learning_rate": 1.644110411450398e-05,
886
+ "loss": 0.8697,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5927710843373494,
891
+ "grad_norm": 3.1264090538024902,
892
+ "learning_rate": 1.6381427137288756e-05,
893
+ "loss": 0.8611,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5975903614457831,
898
+ "grad_norm": 2.660439968109131,
899
+ "learning_rate": 1.6321364279743267e-05,
900
+ "loss": 0.7971,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.6024096385542169,
905
+ "grad_norm": 3.0773823261260986,
906
+ "learning_rate": 1.6260919173825507e-05,
907
+ "loss": 0.8135,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.6072289156626506,
912
+ "grad_norm": 2.897467613220215,
913
+ "learning_rate": 1.6200095474607753e-05,
914
+ "loss": 0.8868,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.6120481927710844,
919
+ "grad_norm": 3.2068772315979004,
920
+ "learning_rate": 1.6138896860055555e-05,
921
+ "loss": 0.8584,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.6168674698795181,
926
+ "grad_norm": 2.853588581085205,
927
+ "learning_rate": 1.6077327030805318e-05,
928
+ "loss": 0.8486,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.6216867469879518,
933
+ "grad_norm": 2.908766984939575,
934
+ "learning_rate": 1.601538970994054e-05,
935
+ "loss": 0.8701,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.6265060240963856,
940
+ "grad_norm": 3.316112518310547,
941
+ "learning_rate": 1.595308864276666e-05,
942
+ "loss": 0.8063,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6313253012048192,
947
+ "grad_norm": 2.69521427154541,
948
+ "learning_rate": 1.589042759658462e-05,
949
+ "loss": 0.787,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.636144578313253,
954
+ "grad_norm": 2.609143018722534,
955
+ "learning_rate": 1.582741036046301e-05,
956
+ "loss": 0.8263,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6409638554216868,
961
+ "grad_norm": 3.1294214725494385,
962
+ "learning_rate": 1.5764040745008987e-05,
963
+ "loss": 0.8637,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6457831325301204,
968
+ "grad_norm": 2.8580658435821533,
969
+ "learning_rate": 1.570032258213783e-05,
970
+ "loss": 0.8542,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6506024096385542,
975
+ "grad_norm": 2.952737808227539,
976
+ "learning_rate": 1.5636259724841224e-05,
977
+ "loss": 0.7718,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.655421686746988,
982
+ "grad_norm": 3.2111058235168457,
983
+ "learning_rate": 1.5571856046954284e-05,
984
+ "loss": 0.8604,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6602409638554216,
989
+ "grad_norm": 3.454385995864868,
990
+ "learning_rate": 1.550711544292131e-05,
991
+ "loss": 0.8955,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6650602409638554,
996
+ "grad_norm": 2.990410566329956,
997
+ "learning_rate": 1.5442041827560274e-05,
998
+ "loss": 0.8322,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6698795180722892,
1003
+ "grad_norm": 2.85209059715271,
1004
+ "learning_rate": 1.537663913582611e-05,
1005
+ "loss": 0.8396,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6746987951807228,
1010
+ "grad_norm": 2.8276262283325195,
1011
+ "learning_rate": 1.531091132257275e-05,
1012
+ "loss": 0.8183,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6795180722891566,
1017
+ "grad_norm": 3.024148464202881,
1018
+ "learning_rate": 1.5244862362314021e-05,
1019
+ "loss": 0.8604,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6843373493975904,
1024
+ "grad_norm": 2.975719451904297,
1025
+ "learning_rate": 1.5178496248983254e-05,
1026
+ "loss": 0.8631,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.689156626506024,
1031
+ "grad_norm": 2.9066529273986816,
1032
+ "learning_rate": 1.511181699569181e-05,
1033
+ "loss": 0.7869,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6939759036144578,
1038
+ "grad_norm": 3.047508716583252,
1039
+ "learning_rate": 1.50448286344864e-05,
1040
+ "loss": 0.8827,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6987951807228916,
1045
+ "grad_norm": 2.746082305908203,
1046
+ "learning_rate": 1.4977535216105258e-05,
1047
+ "loss": 0.9077,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.7036144578313253,
1052
+ "grad_norm": 2.787168025970459,
1053
+ "learning_rate": 1.4909940809733223e-05,
1054
+ "loss": 0.8554,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.708433734939759,
1059
+ "grad_norm": 2.918994903564453,
1060
+ "learning_rate": 1.484204950275565e-05,
1061
+ "loss": 0.84,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.7132530120481928,
1066
+ "grad_norm": 2.950530767440796,
1067
+ "learning_rate": 1.477386540051127e-05,
1068
+ "loss": 0.8038,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.7180722891566265,
1073
+ "grad_norm": 3.0625436305999756,
1074
+ "learning_rate": 1.4705392626043931e-05,
1075
+ "loss": 0.8355,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.7228915662650602,
1080
+ "grad_norm": 2.4308924674987793,
1081
+ "learning_rate": 1.4636635319853274e-05,
1082
+ "loss": 0.824,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.727710843373494,
1087
+ "grad_norm": 3.4381263256073,
1088
+ "learning_rate": 1.4567597639644387e-05,
1089
+ "loss": 0.9047,
1090
+ "step": 151
1091
+ },
1092
+ {
1093
+ "epoch": 0.7325301204819277,
1094
+ "grad_norm": 2.490755319595337,
1095
+ "learning_rate": 1.4498283760076362e-05,
1096
+ "loss": 0.8172,
1097
+ "step": 152
1098
+ },
1099
+ {
1100
+ "epoch": 0.7373493975903614,
1101
+ "grad_norm": 2.623565196990967,
1102
+ "learning_rate": 1.4428697872509868e-05,
1103
+ "loss": 0.8643,
1104
+ "step": 153
1105
+ },
1106
+ {
1107
+ "epoch": 0.7421686746987952,
1108
+ "grad_norm": 2.729555606842041,
1109
+ "learning_rate": 1.4358844184753713e-05,
1110
+ "loss": 0.7942,
1111
+ "step": 154
1112
+ },
1113
+ {
1114
+ "epoch": 0.7469879518072289,
1115
+ "grad_norm": 2.9937925338745117,
1116
+ "learning_rate": 1.4288726920810381e-05,
1117
+ "loss": 0.8734,
1118
+ "step": 155
1119
+ },
1120
+ {
1121
+ "epoch": 0.7518072289156627,
1122
+ "grad_norm": 2.592301368713379,
1123
+ "learning_rate": 1.4218350320620625e-05,
1124
+ "loss": 0.8604,
1125
+ "step": 156
1126
+ },
1127
+ {
1128
+ "epoch": 0.7518072289156627,
1129
+ "eval_loss": 0.8515476584434509,
1130
+ "eval_runtime": 409.2403,
1131
+ "eval_samples_per_second": 3.968,
1132
+ "eval_steps_per_second": 0.992,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.7566265060240964,
1137
+ "grad_norm": 2.74635648727417,
1138
+ "learning_rate": 1.4147718639807071e-05,
1139
+ "loss": 0.8341,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.7614457831325301,
1144
+ "grad_norm": 2.956916332244873,
1145
+ "learning_rate": 1.4076836149416889e-05,
1146
+ "loss": 0.8565,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.7662650602409639,
1151
+ "grad_norm": 3.0407042503356934,
1152
+ "learning_rate": 1.4005707135663529e-05,
1153
+ "loss": 0.9829,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.7710843373493976,
1158
+ "grad_norm": 2.7380025386810303,
1159
+ "learning_rate": 1.3934335899667526e-05,
1160
+ "loss": 0.8517,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.7759036144578313,
1165
+ "grad_norm": 2.8586325645446777,
1166
+ "learning_rate": 1.386272675719642e-05,
1167
+ "loss": 0.8482,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.7807228915662651,
1172
+ "grad_norm": 3.482114315032959,
1173
+ "learning_rate": 1.3790884038403796e-05,
1174
+ "loss": 0.9079,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.7855421686746988,
1179
+ "grad_norm": 2.5210723876953125,
1180
+ "learning_rate": 1.3718812087567414e-05,
1181
+ "loss": 0.8087,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.7903614457831325,
1186
+ "grad_norm": 2.4037303924560547,
1187
+ "learning_rate": 1.3646515262826551e-05,
1188
+ "loss": 0.7977,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.7951807228915663,
1193
+ "grad_norm": 3.141289710998535,
1194
+ "learning_rate": 1.357399793591844e-05,
1195
+ "loss": 0.8443,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.8,
1200
+ "grad_norm": 2.783255100250244,
1201
+ "learning_rate": 1.3501264491913909e-05,
1202
+ "loss": 0.8331,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.8048192771084337,
1207
+ "grad_norm": 2.3387300968170166,
1208
+ "learning_rate": 1.3428319328952254e-05,
1209
+ "loss": 0.7909,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.8096385542168675,
1214
+ "grad_norm": 2.699117422103882,
1215
+ "learning_rate": 1.335516685797525e-05,
1216
+ "loss": 0.7948,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.8144578313253013,
1221
+ "grad_norm": 2.6115429401397705,
1222
+ "learning_rate": 1.3281811502460448e-05,
1223
+ "loss": 0.7995,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.8192771084337349,
1228
+ "grad_norm": 2.520070791244507,
1229
+ "learning_rate": 1.3208257698153677e-05,
1230
+ "loss": 0.8357,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.8240963855421687,
1235
+ "grad_norm": 2.7537450790405273,
1236
+ "learning_rate": 1.3134509892800821e-05,
1237
+ "loss": 0.822,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.8289156626506025,
1242
+ "grad_norm": 2.5548155307769775,
1243
+ "learning_rate": 1.3060572545878875e-05,
1244
+ "loss": 0.7743,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.8337349397590361,
1249
+ "grad_norm": 2.4238061904907227,
1250
+ "learning_rate": 1.2986450128326267e-05,
1251
+ "loss": 0.8116,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.8385542168674699,
1256
+ "grad_norm": 3.0254759788513184,
1257
+ "learning_rate": 1.2912147122272523e-05,
1258
+ "loss": 0.8264,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.8433734939759037,
1263
+ "grad_norm": 2.9106860160827637,
1264
+ "learning_rate": 1.283766802076722e-05,
1265
+ "loss": 0.849,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.8481927710843373,
1270
+ "grad_norm": 2.2837445735931396,
1271
+ "learning_rate": 1.2763017327508304e-05,
1272
+ "loss": 0.7899,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.8530120481927711,
1277
+ "grad_norm": 2.833048105239868,
1278
+ "learning_rate": 1.2688199556569753e-05,
1279
+ "loss": 0.7616,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.8578313253012049,
1284
+ "grad_norm": 2.5235068798065186,
1285
+ "learning_rate": 1.2613219232128608e-05,
1286
+ "loss": 0.8034,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.8626506024096385,
1291
+ "grad_norm": 3.159371852874756,
1292
+ "learning_rate": 1.2538080888191408e-05,
1293
+ "loss": 0.8073,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.8674698795180723,
1298
+ "grad_norm": 3.462261199951172,
1299
+ "learning_rate": 1.2462789068320016e-05,
1300
+ "loss": 0.8688,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.8722891566265061,
1305
+ "grad_norm": 2.8163440227508545,
1306
+ "learning_rate": 1.2387348325356873e-05,
1307
+ "loss": 0.8153,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.8771084337349397,
1312
+ "grad_norm": 2.5280866622924805,
1313
+ "learning_rate": 1.23117632211497e-05,
1314
+ "loss": 0.7912,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.8819277108433735,
1319
+ "grad_norm": 2.8253021240234375,
1320
+ "learning_rate": 1.2236038326275628e-05,
1321
+ "loss": 0.8437,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.8867469879518072,
1326
+ "grad_norm": 2.289564371109009,
1327
+ "learning_rate": 1.2160178219764838e-05,
1328
+ "loss": 0.8026,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.891566265060241,
1333
+ "grad_norm": 2.4745798110961914,
1334
+ "learning_rate": 1.2084187488823657e-05,
1335
+ "loss": 0.8489,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.8963855421686747,
1340
+ "grad_norm": 3.2900331020355225,
1341
+ "learning_rate": 1.2008070728557186e-05,
1342
+ "loss": 0.8812,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.9012048192771084,
1347
+ "grad_norm": 2.9827733039855957,
1348
+ "learning_rate": 1.193183254169142e-05,
1349
+ "loss": 0.8048,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.9060240963855422,
1354
+ "grad_norm": 2.4809494018554688,
1355
+ "learning_rate": 1.1855477538294934e-05,
1356
+ "loss": 0.8123,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.9108433734939759,
1361
+ "grad_norm": 2.5557541847229004,
1362
+ "learning_rate": 1.177901033550012e-05,
1363
+ "loss": 0.8306,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.9156626506024096,
1368
+ "grad_norm": 2.4625046253204346,
1369
+ "learning_rate": 1.1702435557223988e-05,
1370
+ "loss": 0.7583,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.9204819277108434,
1375
+ "grad_norm": 2.7508351802825928,
1376
+ "learning_rate": 1.1625757833888552e-05,
1377
+ "loss": 0.7602,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.9253012048192771,
1382
+ "grad_norm": 2.6322593688964844,
1383
+ "learning_rate": 1.1548981802140849e-05,
1384
+ "loss": 0.8308,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.9301204819277108,
1389
+ "grad_norm": 2.4383065700531006,
1390
+ "learning_rate": 1.1472112104572547e-05,
1391
+ "loss": 0.805,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.9349397590361446,
1396
+ "grad_norm": 2.955080270767212,
1397
+ "learning_rate": 1.1395153389439232e-05,
1398
+ "loss": 0.8125,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.9397590361445783,
1403
+ "grad_norm": 2.8347744941711426,
1404
+ "learning_rate": 1.1318110310379303e-05,
1405
+ "loss": 0.8082,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.944578313253012,
1410
+ "grad_norm": 3.7410006523132324,
1411
+ "learning_rate": 1.1240987526132595e-05,
1412
+ "loss": 0.7615,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.9493975903614458,
1417
+ "grad_norm": 2.831632137298584,
1418
+ "learning_rate": 1.1163789700258656e-05,
1419
+ "loss": 0.8224,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.9542168674698795,
1424
+ "grad_norm": 3.450864553451538,
1425
+ "learning_rate": 1.1086521500854746e-05,
1426
+ "loss": 0.8494,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.9590361445783132,
1431
+ "grad_norm": 2.5779266357421875,
1432
+ "learning_rate": 1.1009187600273565e-05,
1433
+ "loss": 0.7948,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.963855421686747,
1438
+ "grad_norm": 2.808676242828369,
1439
+ "learning_rate": 1.0931792674840718e-05,
1440
+ "loss": 0.8196,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.9686746987951808,
1445
+ "grad_norm": 2.3105671405792236,
1446
+ "learning_rate": 1.0854341404571929e-05,
1447
+ "loss": 0.7321,
1448
+ "step": 201
1449
+ },
1450
+ {
1451
+ "epoch": 0.9734939759036144,
1452
+ "grad_norm": 2.495274543762207,
1453
+ "learning_rate": 1.0776838472890065e-05,
1454
+ "loss": 0.811,
1455
+ "step": 202
1456
+ },
1457
+ {
1458
+ "epoch": 0.9783132530120482,
1459
+ "grad_norm": 2.6084389686584473,
1460
+ "learning_rate": 1.0699288566341914e-05,
1461
+ "loss": 0.7649,
1462
+ "step": 203
1463
+ },
1464
+ {
1465
+ "epoch": 0.983132530120482,
1466
+ "grad_norm": 2.7586421966552734,
1467
+ "learning_rate": 1.0621696374314807e-05,
1468
+ "loss": 0.8226,
1469
+ "step": 204
1470
+ },
1471
+ {
1472
+ "epoch": 0.9879518072289156,
1473
+ "grad_norm": 2.8034958839416504,
1474
+ "learning_rate": 1.0544066588753044e-05,
1475
+ "loss": 0.8318,
1476
+ "step": 205
1477
+ },
1478
+ {
1479
+ "epoch": 0.9927710843373494,
1480
+ "grad_norm": 3.051496982574463,
1481
+ "learning_rate": 1.0466403903874176e-05,
1482
+ "loss": 0.8513,
1483
+ "step": 206
1484
+ },
1485
+ {
1486
+ "epoch": 0.9975903614457832,
1487
+ "grad_norm": 2.5570504665374756,
1488
+ "learning_rate": 1.0388713015885161e-05,
1489
+ "loss": 0.786,
1490
+ "step": 207
1491
+ },
1492
+ {
1493
+ "epoch": 1.002409638554217,
1494
+ "grad_norm": 2.5539052486419678,
1495
+ "learning_rate": 1.031099862269837e-05,
1496
+ "loss": 0.7932,
1497
+ "step": 208
1498
+ },
1499
+ {
1500
+ "epoch": 1.002409638554217,
1501
+ "eval_loss": 0.8150397539138794,
1502
+ "eval_runtime": 408.9584,
1503
+ "eval_samples_per_second": 3.971,
1504
+ "eval_steps_per_second": 0.993,
1505
+ "step": 208
1506
+ },
1507
+ {
1508
+ "epoch": 1.0072289156626506,
1509
+ "grad_norm": 2.4404540061950684,
1510
+ "learning_rate": 1.0233265423647523e-05,
1511
+ "loss": 0.7868,
1512
+ "step": 209
1513
+ },
1514
+ {
1515
+ "epoch": 1.002409638554217,
1516
+ "grad_norm": 2.5475072860717773,
1517
+ "learning_rate": 1.0155518119203511e-05,
1518
+ "loss": 0.6593,
1519
+ "step": 210
1520
+ },
1521
+ {
1522
+ "epoch": 1.0072289156626506,
1523
+ "grad_norm": 2.1499063968658447,
1524
+ "learning_rate": 1.0077761410690172e-05,
1525
+ "loss": 0.5762,
1526
+ "step": 211
1527
+ },
1528
+ {
1529
+ "epoch": 1.0120481927710843,
1530
+ "grad_norm": 2.4631576538085938,
1531
+ "learning_rate": 1e-05,
1532
+ "loss": 0.5896,
1533
+ "step": 212
1534
+ },
1535
+ {
1536
+ "epoch": 1.0168674698795181,
1537
+ "grad_norm": 2.553774833679199,
1538
+ "learning_rate": 9.92223858930983e-06,
1539
+ "loss": 0.6091,
1540
+ "step": 213
1541
+ },
1542
+ {
1543
+ "epoch": 1.0216867469879518,
1544
+ "grad_norm": 2.09922456741333,
1545
+ "learning_rate": 9.844481880796492e-06,
1546
+ "loss": 0.5918,
1547
+ "step": 214
1548
+ },
1549
+ {
1550
+ "epoch": 1.0265060240963855,
1551
+ "grad_norm": 2.326040744781494,
1552
+ "learning_rate": 9.766734576352478e-06,
1553
+ "loss": 0.5406,
1554
+ "step": 215
1555
+ },
1556
+ {
1557
+ "epoch": 1.0313253012048194,
1558
+ "grad_norm": 2.230414628982544,
1559
+ "learning_rate": 9.689001377301634e-06,
1560
+ "loss": 0.5337,
1561
+ "step": 216
1562
+ },
1563
+ {
1564
+ "epoch": 1.036144578313253,
1565
+ "grad_norm": 2.1315929889678955,
1566
+ "learning_rate": 9.61128698411484e-06,
1567
+ "loss": 0.5076,
1568
+ "step": 217
1569
+ },
1570
+ {
1571
+ "epoch": 1.0409638554216867,
1572
+ "grad_norm": 2.31592059135437,
1573
+ "learning_rate": 9.533596096125826e-06,
1574
+ "loss": 0.5451,
1575
+ "step": 218
1576
+ },
1577
+ {
1578
+ "epoch": 1.0457831325301206,
1579
+ "grad_norm": 2.209798812866211,
1580
+ "learning_rate": 9.45593341124696e-06,
1581
+ "loss": 0.5725,
1582
+ "step": 219
1583
+ },
1584
+ {
1585
+ "epoch": 1.0506024096385542,
1586
+ "grad_norm": 2.8493363857269287,
1587
+ "learning_rate": 9.378303625685196e-06,
1588
+ "loss": 0.5594,
1589
+ "step": 220
1590
+ },
1591
+ {
1592
+ "epoch": 1.0554216867469879,
1593
+ "grad_norm": 2.948335647583008,
1594
+ "learning_rate": 9.300711433658088e-06,
1595
+ "loss": 0.4995,
1596
+ "step": 221
1597
+ },
1598
+ {
1599
+ "epoch": 1.0602409638554218,
1600
+ "grad_norm": 2.581233263015747,
1601
+ "learning_rate": 9.223161527109938e-06,
1602
+ "loss": 0.5273,
1603
+ "step": 222
1604
+ },
1605
+ {
1606
+ "epoch": 1.0650602409638554,
1607
+ "grad_norm": 2.436361312866211,
1608
+ "learning_rate": 9.145658595428075e-06,
1609
+ "loss": 0.5356,
1610
+ "step": 223
1611
+ },
1612
+ {
1613
+ "epoch": 1.069879518072289,
1614
+ "grad_norm": 2.5706756114959717,
1615
+ "learning_rate": 9.068207325159285e-06,
1616
+ "loss": 0.5082,
1617
+ "step": 224
1618
+ },
1619
+ {
1620
+ "epoch": 1.074698795180723,
1621
+ "grad_norm": 2.5452582836151123,
1622
+ "learning_rate": 8.990812399726435e-06,
1623
+ "loss": 0.5098,
1624
+ "step": 225
1625
+ },
1626
+ {
1627
+ "epoch": 1.0795180722891566,
1628
+ "grad_norm": 2.2918717861175537,
1629
+ "learning_rate": 8.913478499145255e-06,
1630
+ "loss": 0.493,
1631
+ "step": 226
1632
+ },
1633
+ {
1634
+ "epoch": 1.0843373493975903,
1635
+ "grad_norm": 2.837512969970703,
1636
+ "learning_rate": 8.836210299741346e-06,
1637
+ "loss": 0.5036,
1638
+ "step": 227
1639
+ },
1640
+ {
1641
+ "epoch": 1.0891566265060242,
1642
+ "grad_norm": 2.7534472942352295,
1643
+ "learning_rate": 8.759012473867407e-06,
1644
+ "loss": 0.5333,
1645
+ "step": 228
1646
+ },
1647
+ {
1648
+ "epoch": 1.0939759036144578,
1649
+ "grad_norm": 2.761195659637451,
1650
+ "learning_rate": 8.681889689620699e-06,
1651
+ "loss": 0.5186,
1652
+ "step": 229
1653
+ },
1654
+ {
1655
+ "epoch": 1.0987951807228915,
1656
+ "grad_norm": 2.570779800415039,
1657
+ "learning_rate": 8.604846610560771e-06,
1658
+ "loss": 0.5496,
1659
+ "step": 230
1660
+ },
1661
+ {
1662
+ "epoch": 1.1036144578313254,
1663
+ "grad_norm": 2.4266934394836426,
1664
+ "learning_rate": 8.527887895427454e-06,
1665
+ "loss": 0.5453,
1666
+ "step": 231
1667
+ },
1668
+ {
1669
+ "epoch": 1.108433734939759,
1670
+ "grad_norm": 2.634979248046875,
1671
+ "learning_rate": 8.451018197859153e-06,
1672
+ "loss": 0.5121,
1673
+ "step": 232
1674
+ },
1675
+ {
1676
+ "epoch": 1.1132530120481927,
1677
+ "grad_norm": 2.1403777599334717,
1678
+ "learning_rate": 8.374242166111448e-06,
1679
+ "loss": 0.5354,
1680
+ "step": 233
1681
+ },
1682
+ {
1683
+ "epoch": 1.1180722891566266,
1684
+ "grad_norm": 2.7985663414001465,
1685
+ "learning_rate": 8.297564442776014e-06,
1686
+ "loss": 0.5565,
1687
+ "step": 234
1688
+ },
1689
+ {
1690
+ "epoch": 1.1228915662650603,
1691
+ "grad_norm": 2.486628532409668,
1692
+ "learning_rate": 8.22098966449988e-06,
1693
+ "loss": 0.5428,
1694
+ "step": 235
1695
+ },
1696
+ {
1697
+ "epoch": 1.127710843373494,
1698
+ "grad_norm": 2.3803107738494873,
1699
+ "learning_rate": 8.144522461705067e-06,
1700
+ "loss": 0.509,
1701
+ "step": 236
1702
+ },
1703
+ {
1704
+ "epoch": 1.1325301204819278,
1705
+ "grad_norm": 2.7206227779388428,
1706
+ "learning_rate": 8.068167458308582e-06,
1707
+ "loss": 0.5339,
1708
+ "step": 237
1709
+ },
1710
+ {
1711
+ "epoch": 1.1373493975903615,
1712
+ "grad_norm": 2.4364774227142334,
1713
+ "learning_rate": 7.991929271442817e-06,
1714
+ "loss": 0.5168,
1715
+ "step": 238
1716
+ },
1717
+ {
1718
+ "epoch": 1.1421686746987951,
1719
+ "grad_norm": 2.6346094608306885,
1720
+ "learning_rate": 7.915812511176348e-06,
1721
+ "loss": 0.5861,
1722
+ "step": 239
1723
+ },
1724
+ {
1725
+ "epoch": 1.146987951807229,
1726
+ "grad_norm": 2.683432102203369,
1727
+ "learning_rate": 7.839821780235168e-06,
1728
+ "loss": 0.5066,
1729
+ "step": 240
1730
+ },
1731
+ {
1732
+ "epoch": 1.1518072289156627,
1733
+ "grad_norm": 2.444256544113159,
1734
+ "learning_rate": 7.763961673724379e-06,
1735
+ "loss": 0.498,
1736
+ "step": 241
1737
+ },
1738
+ {
1739
+ "epoch": 1.1566265060240963,
1740
+ "grad_norm": 2.436868906021118,
1741
+ "learning_rate": 7.688236778850307e-06,
1742
+ "loss": 0.5013,
1743
+ "step": 242
1744
+ },
1745
+ {
1746
+ "epoch": 1.16144578313253,
1747
+ "grad_norm": 2.420361042022705,
1748
+ "learning_rate": 7.61265167464313e-06,
1749
+ "loss": 0.506,
1750
+ "step": 243
1751
+ },
1752
+ {
1753
+ "epoch": 1.1662650602409639,
1754
+ "grad_norm": 2.5880956649780273,
1755
+ "learning_rate": 7.537210931679988e-06,
1756
+ "loss": 0.5056,
1757
+ "step": 244
1758
+ },
1759
+ {
1760
+ "epoch": 1.1710843373493975,
1761
+ "grad_norm": 3.139289140701294,
1762
+ "learning_rate": 7.4619191118085955e-06,
1763
+ "loss": 0.5481,
1764
+ "step": 245
1765
+ },
1766
+ {
1767
+ "epoch": 1.1759036144578312,
1768
+ "grad_norm": 2.5460047721862793,
1769
+ "learning_rate": 7.3867807678713965e-06,
1770
+ "loss": 0.45,
1771
+ "step": 246
1772
+ },
1773
+ {
1774
+ "epoch": 1.180722891566265,
1775
+ "grad_norm": 2.1692583560943604,
1776
+ "learning_rate": 7.311800443430251e-06,
1777
+ "loss": 0.4814,
1778
+ "step": 247
1779
+ },
1780
+ {
1781
+ "epoch": 1.1855421686746987,
1782
+ "grad_norm": 2.748295307159424,
1783
+ "learning_rate": 7.236982672491699e-06,
1784
+ "loss": 0.5,
1785
+ "step": 248
1786
+ },
1787
+ {
1788
+ "epoch": 1.1903614457831324,
1789
+ "grad_norm": 2.367530584335327,
1790
+ "learning_rate": 7.162331979232784e-06,
1791
+ "loss": 0.5303,
1792
+ "step": 249
1793
+ },
1794
+ {
1795
+ "epoch": 1.1951807228915663,
1796
+ "grad_norm": 2.0665979385375977,
1797
+ "learning_rate": 7.0878528777274814e-06,
1798
+ "loss": 0.4724,
1799
+ "step": 250
1800
+ },
1801
+ {
1802
+ "epoch": 1.2,
1803
+ "grad_norm": 2.257098913192749,
1804
+ "learning_rate": 7.013549871673736e-06,
1805
+ "loss": 0.5427,
1806
+ "step": 251
1807
+ },
1808
+ {
1809
+ "epoch": 1.2048192771084336,
1810
+ "grad_norm": 2.7129740715026855,
1811
+ "learning_rate": 6.939427454121128e-06,
1812
+ "loss": 0.5241,
1813
+ "step": 252
1814
+ },
1815
+ {
1816
+ "epoch": 1.2096385542168675,
1817
+ "grad_norm": 2.3564581871032715,
1818
+ "learning_rate": 6.865490107199182e-06,
1819
+ "loss": 0.5323,
1820
+ "step": 253
1821
+ },
1822
+ {
1823
+ "epoch": 1.2144578313253012,
1824
+ "grad_norm": 2.4660191535949707,
1825
+ "learning_rate": 6.791742301846325e-06,
1826
+ "loss": 0.5461,
1827
+ "step": 254
1828
+ },
1829
+ {
1830
+ "epoch": 1.2192771084337348,
1831
+ "grad_norm": 2.495473861694336,
1832
+ "learning_rate": 6.718188497539554e-06,
1833
+ "loss": 0.5202,
1834
+ "step": 255
1835
+ },
1836
+ {
1837
+ "epoch": 1.2240963855421687,
1838
+ "grad_norm": 2.41900897026062,
1839
+ "learning_rate": 6.644833142024752e-06,
1840
+ "loss": 0.4786,
1841
+ "step": 256
1842
+ },
1843
+ {
1844
+ "epoch": 1.2289156626506024,
1845
+ "grad_norm": 2.2576987743377686,
1846
+ "learning_rate": 6.571680671047749e-06,
1847
+ "loss": 0.5425,
1848
+ "step": 257
1849
+ },
1850
+ {
1851
+ "epoch": 1.233734939759036,
1852
+ "grad_norm": 2.370042562484741,
1853
+ "learning_rate": 6.498735508086094e-06,
1854
+ "loss": 0.4975,
1855
+ "step": 258
1856
+ },
1857
+ {
1858
+ "epoch": 1.23855421686747,
1859
+ "grad_norm": 2.3406431674957275,
1860
+ "learning_rate": 6.426002064081565e-06,
1861
+ "loss": 0.5147,
1862
+ "step": 259
1863
+ },
1864
+ {
1865
+ "epoch": 1.2433734939759036,
1866
+ "grad_norm": 2.116950750350952,
1867
+ "learning_rate": 6.35348473717345e-06,
1868
+ "loss": 0.5234,
1869
+ "step": 260
1870
+ },
1871
+ {
1872
+ "epoch": 1.2433734939759036,
1873
+ "eval_loss": 0.8304641842842102,
1874
+ "eval_runtime": 409.2944,
1875
+ "eval_samples_per_second": 3.968,
1876
+ "eval_steps_per_second": 0.992,
1877
+ "step": 260
1878
+ },
1879
+ {
1880
+ "epoch": 1.2481927710843372,
1881
+ "grad_norm": 2.3892273902893066,
1882
+ "learning_rate": 6.281187912432587e-06,
1883
+ "loss": 0.4892,
1884
+ "step": 261
1885
+ },
1886
+ {
1887
+ "epoch": 1.2530120481927711,
1888
+ "grad_norm": 2.5329415798187256,
1889
+ "learning_rate": 6.209115961596208e-06,
1890
+ "loss": 0.5576,
1891
+ "step": 262
1892
+ },
1893
+ {
1894
+ "epoch": 1.2578313253012048,
1895
+ "grad_norm": 2.706501007080078,
1896
+ "learning_rate": 6.137273242803581e-06,
1897
+ "loss": 0.5035,
1898
+ "step": 263
1899
+ },
1900
+ {
1901
+ "epoch": 1.2626506024096384,
1902
+ "grad_norm": 2.6569039821624756,
1903
+ "learning_rate": 6.065664100332478e-06,
1904
+ "loss": 0.5538,
1905
+ "step": 264
1906
+ },
1907
+ {
1908
+ "epoch": 1.2674698795180723,
1909
+ "grad_norm": 2.657332420349121,
1910
+ "learning_rate": 5.994292864336473e-06,
1911
+ "loss": 0.5215,
1912
+ "step": 265
1913
+ },
1914
+ {
1915
+ "epoch": 1.272289156626506,
1916
+ "grad_norm": 2.228058099746704,
1917
+ "learning_rate": 5.923163850583114e-06,
1918
+ "loss": 0.5005,
1919
+ "step": 266
1920
+ },
1921
+ {
1922
+ "epoch": 1.2771084337349397,
1923
+ "grad_norm": 2.5667221546173096,
1924
+ "learning_rate": 5.852281360192933e-06,
1925
+ "loss": 0.471,
1926
+ "step": 267
1927
+ },
1928
+ {
1929
+ "epoch": 1.2819277108433735,
1930
+ "grad_norm": 2.6076254844665527,
1931
+ "learning_rate": 5.781649679379379e-06,
1932
+ "loss": 0.4565,
1933
+ "step": 268
1934
+ },
1935
+ {
1936
+ "epoch": 1.2867469879518072,
1937
+ "grad_norm": 2.777376651763916,
1938
+ "learning_rate": 5.711273079189621e-06,
1939
+ "loss": 0.4975,
1940
+ "step": 269
1941
+ },
1942
+ {
1943
+ "epoch": 1.2915662650602409,
1944
+ "grad_norm": 2.7435245513916016,
1945
+ "learning_rate": 5.64115581524629e-06,
1946
+ "loss": 0.4969,
1947
+ "step": 270
1948
+ },
1949
+ {
1950
+ "epoch": 1.2963855421686747,
1951
+ "grad_norm": 2.2904560565948486,
1952
+ "learning_rate": 5.571302127490133e-06,
1953
+ "loss": 0.5133,
1954
+ "step": 271
1955
+ },
1956
+ {
1957
+ "epoch": 1.3012048192771084,
1958
+ "grad_norm": 2.808234930038452,
1959
+ "learning_rate": 5.501716239923642e-06,
1960
+ "loss": 0.5225,
1961
+ "step": 272
1962
+ },
1963
+ {
1964
+ "epoch": 1.306024096385542,
1965
+ "grad_norm": 2.489271879196167,
1966
+ "learning_rate": 5.432402360355616e-06,
1967
+ "loss": 0.5022,
1968
+ "step": 273
1969
+ },
1970
+ {
1971
+ "epoch": 1.310843373493976,
1972
+ "grad_norm": 2.973238229751587,
1973
+ "learning_rate": 5.3633646801467255e-06,
1974
+ "loss": 0.5028,
1975
+ "step": 274
1976
+ },
1977
+ {
1978
+ "epoch": 1.3156626506024096,
1979
+ "grad_norm": 2.9348108768463135,
1980
+ "learning_rate": 5.294607373956071e-06,
1981
+ "loss": 0.5381,
1982
+ "step": 275
1983
+ },
1984
+ {
1985
+ "epoch": 1.3204819277108433,
1986
+ "grad_norm": 2.496760368347168,
1987
+ "learning_rate": 5.226134599488728e-06,
1988
+ "loss": 0.5031,
1989
+ "step": 276
1990
+ },
1991
+ {
1992
+ "epoch": 1.3253012048192772,
1993
+ "grad_norm": 2.667630910873413,
1994
+ "learning_rate": 5.15795049724435e-06,
1995
+ "loss": 0.4783,
1996
+ "step": 277
1997
+ },
1998
+ {
1999
+ "epoch": 1.3301204819277108,
2000
+ "grad_norm": 2.5155699253082275,
2001
+ "learning_rate": 5.090059190266779e-06,
2002
+ "loss": 0.5119,
2003
+ "step": 278
2004
+ },
2005
+ {
2006
+ "epoch": 1.3349397590361445,
2007
+ "grad_norm": 2.7496049404144287,
2008
+ "learning_rate": 5.022464783894743e-06,
2009
+ "loss": 0.5757,
2010
+ "step": 279
2011
+ },
2012
+ {
2013
+ "epoch": 1.3397590361445784,
2014
+ "grad_norm": 2.7545154094696045,
2015
+ "learning_rate": 4.955171365513603e-06,
2016
+ "loss": 0.516,
2017
+ "step": 280
2018
+ },
2019
+ {
2020
+ "epoch": 1.344578313253012,
2021
+ "grad_norm": 2.573042631149292,
2022
+ "learning_rate": 4.88818300430819e-06,
2023
+ "loss": 0.5566,
2024
+ "step": 281
2025
+ },
2026
+ {
2027
+ "epoch": 1.3493975903614457,
2028
+ "grad_norm": 2.389958381652832,
2029
+ "learning_rate": 4.821503751016746e-06,
2030
+ "loss": 0.4836,
2031
+ "step": 282
2032
+ },
2033
+ {
2034
+ "epoch": 1.3542168674698796,
2035
+ "grad_norm": 2.508965015411377,
2036
+ "learning_rate": 4.7551376376859794e-06,
2037
+ "loss": 0.5694,
2038
+ "step": 283
2039
+ },
2040
+ {
2041
+ "epoch": 1.3590361445783132,
2042
+ "grad_norm": 2.017404794692993,
2043
+ "learning_rate": 4.689088677427249e-06,
2044
+ "loss": 0.4656,
2045
+ "step": 284
2046
+ },
2047
+ {
2048
+ "epoch": 1.363855421686747,
2049
+ "grad_norm": 3.2286880016326904,
2050
+ "learning_rate": 4.623360864173893e-06,
2051
+ "loss": 0.4912,
2052
+ "step": 285
2053
+ },
2054
+ {
2055
+ "epoch": 1.3686746987951808,
2056
+ "grad_norm": 2.6164350509643555,
2057
+ "learning_rate": 4.557958172439726e-06,
2058
+ "loss": 0.5043,
2059
+ "step": 286
2060
+ },
2061
+ {
2062
+ "epoch": 1.3734939759036144,
2063
+ "grad_norm": 2.4611318111419678,
2064
+ "learning_rate": 4.492884557078688e-06,
2065
+ "loss": 0.5335,
2066
+ "step": 287
2067
+ },
2068
+ {
2069
+ "epoch": 1.378313253012048,
2070
+ "grad_norm": 2.9601011276245117,
2071
+ "learning_rate": 4.4281439530457174e-06,
2072
+ "loss": 0.4957,
2073
+ "step": 288
2074
+ },
2075
+ {
2076
+ "epoch": 1.383132530120482,
2077
+ "grad_norm": 2.7370502948760986,
2078
+ "learning_rate": 4.36374027515878e-06,
2079
+ "loss": 0.4763,
2080
+ "step": 289
2081
+ },
2082
+ {
2083
+ "epoch": 1.3879518072289156,
2084
+ "grad_norm": 2.5553810596466064,
2085
+ "learning_rate": 4.299677417862174e-06,
2086
+ "loss": 0.5059,
2087
+ "step": 290
2088
+ },
2089
+ {
2090
+ "epoch": 1.3927710843373493,
2091
+ "grad_norm": 2.570694923400879,
2092
+ "learning_rate": 4.2359592549910145e-06,
2093
+ "loss": 0.5084,
2094
+ "step": 291
2095
+ },
2096
+ {
2097
+ "epoch": 1.3975903614457832,
2098
+ "grad_norm": 2.36863112449646,
2099
+ "learning_rate": 4.172589639536992e-06,
2100
+ "loss": 0.4869,
2101
+ "step": 292
2102
+ },
2103
+ {
2104
+ "epoch": 1.4024096385542169,
2105
+ "grad_norm": 2.5481040477752686,
2106
+ "learning_rate": 4.109572403415386e-06,
2107
+ "loss": 0.4549,
2108
+ "step": 293
2109
+ },
2110
+ {
2111
+ "epoch": 1.4072289156626505,
2112
+ "grad_norm": 2.881804943084717,
2113
+ "learning_rate": 4.046911357233343e-06,
2114
+ "loss": 0.471,
2115
+ "step": 294
2116
+ },
2117
+ {
2118
+ "epoch": 1.4120481927710844,
2119
+ "grad_norm": 2.4108259677886963,
2120
+ "learning_rate": 3.984610290059467e-06,
2121
+ "loss": 0.5182,
2122
+ "step": 295
2123
+ },
2124
+ {
2125
+ "epoch": 1.416867469879518,
2126
+ "grad_norm": 2.496755599975586,
2127
+ "learning_rate": 3.9226729691946865e-06,
2128
+ "loss": 0.487,
2129
+ "step": 296
2130
+ },
2131
+ {
2132
+ "epoch": 1.4216867469879517,
2133
+ "grad_norm": 2.440626859664917,
2134
+ "learning_rate": 3.861103139944448e-06,
2135
+ "loss": 0.4929,
2136
+ "step": 297
2137
+ },
2138
+ {
2139
+ "epoch": 1.4265060240963856,
2140
+ "grad_norm": 2.4067342281341553,
2141
+ "learning_rate": 3.799904525392251e-06,
2142
+ "loss": 0.4646,
2143
+ "step": 298
2144
+ },
2145
+ {
2146
+ "epoch": 1.4313253012048193,
2147
+ "grad_norm": 2.7123348712921143,
2148
+ "learning_rate": 3.739080826174498e-06,
2149
+ "loss": 0.4928,
2150
+ "step": 299
2151
+ },
2152
+ {
2153
+ "epoch": 1.436144578313253,
2154
+ "grad_norm": 2.511476516723633,
2155
+ "learning_rate": 3.6786357202567367e-06,
2156
+ "loss": 0.5088,
2157
+ "step": 300
2158
+ },
2159
+ {
2160
+ "epoch": 1.4409638554216868,
2161
+ "grad_norm": 2.1973259449005127,
2162
+ "learning_rate": 3.618572862711247e-06,
2163
+ "loss": 0.4619,
2164
+ "step": 301
2165
+ },
2166
+ {
2167
+ "epoch": 1.4457831325301205,
2168
+ "grad_norm": 2.9753270149230957,
2169
+ "learning_rate": 3.558895885496023e-06,
2170
+ "loss": 0.4815,
2171
+ "step": 302
2172
+ },
2173
+ {
2174
+ "epoch": 1.4506024096385541,
2175
+ "grad_norm": 2.129323959350586,
2176
+ "learning_rate": 3.4996083972351514e-06,
2177
+ "loss": 0.4618,
2178
+ "step": 303
2179
+ },
2180
+ {
2181
+ "epoch": 1.455421686746988,
2182
+ "grad_norm": 2.362595319747925,
2183
+ "learning_rate": 3.440713983000601e-06,
2184
+ "loss": 0.4782,
2185
+ "step": 304
2186
+ },
2187
+ {
2188
+ "epoch": 1.4602409638554217,
2189
+ "grad_norm": 2.060520648956299,
2190
+ "learning_rate": 3.3822162040954355e-06,
2191
+ "loss": 0.5068,
2192
+ "step": 305
2193
+ },
2194
+ {
2195
+ "epoch": 1.4650602409638553,
2196
+ "grad_norm": 2.2528958320617676,
2197
+ "learning_rate": 3.3241185978384636e-06,
2198
+ "loss": 0.5308,
2199
+ "step": 306
2200
+ },
2201
+ {
2202
+ "epoch": 1.4698795180722892,
2203
+ "grad_norm": 2.2133140563964844,
2204
+ "learning_rate": 3.266424677350346e-06,
2205
+ "loss": 0.5077,
2206
+ "step": 307
2207
+ },
2208
+ {
2209
+ "epoch": 1.4746987951807229,
2210
+ "grad_norm": 2.223902463912964,
2211
+ "learning_rate": 3.209137931341143e-06,
2212
+ "loss": 0.4697,
2213
+ "step": 308
2214
+ },
2215
+ {
2216
+ "epoch": 1.4795180722891565,
2217
+ "grad_norm": 2.8000707626342773,
2218
+ "learning_rate": 3.1522618238993728e-06,
2219
+ "loss": 0.4934,
2220
+ "step": 309
2221
+ },
2222
+ {
2223
+ "epoch": 1.4843373493975904,
2224
+ "grad_norm": 2.3651952743530273,
2225
+ "learning_rate": 3.0957997942825337e-06,
2226
+ "loss": 0.5103,
2227
+ "step": 310
2228
+ },
2229
+ {
2230
+ "epoch": 1.489156626506024,
2231
+ "grad_norm": 2.443889856338501,
2232
+ "learning_rate": 3.039755256709134e-06,
2233
+ "loss": 0.4617,
2234
+ "step": 311
2235
+ },
2236
+ {
2237
+ "epoch": 1.4939759036144578,
2238
+ "grad_norm": 2.4047086238861084,
2239
+ "learning_rate": 2.9841316001522345e-06,
2240
+ "loss": 0.4875,
2241
+ "step": 312
2242
+ },
2243
+ {
2244
+ "epoch": 1.4939759036144578,
2245
+ "eval_loss": 0.8194815516471863,
2246
+ "eval_runtime": 409.5498,
2247
+ "eval_samples_per_second": 3.965,
2248
+ "eval_steps_per_second": 0.991,
2249
+ "step": 312
2250
+ },
2251
+ {
2252
+ "epoch": 1.4987951807228916,
2253
+ "grad_norm": 2.333664655685425,
2254
+ "learning_rate": 2.9289321881345257e-06,
2255
+ "loss": 0.4577,
2256
+ "step": 313
2257
+ },
2258
+ {
2259
+ "epoch": 1.5036144578313253,
2260
+ "grad_norm": 2.499919891357422,
2261
+ "learning_rate": 2.8741603585249312e-06,
2262
+ "loss": 0.4762,
2263
+ "step": 314
2264
+ },
2265
+ {
2266
+ "epoch": 1.508433734939759,
2267
+ "grad_norm": 2.4571406841278076,
2268
+ "learning_rate": 2.8198194233367747e-06,
2269
+ "loss": 0.4675,
2270
+ "step": 315
2271
+ },
2272
+ {
2273
+ "epoch": 1.5132530120481928,
2274
+ "grad_norm": 2.5920493602752686,
2275
+ "learning_rate": 2.7659126685275028e-06,
2276
+ "loss": 0.5091,
2277
+ "step": 316
2278
+ },
2279
+ {
2280
+ "epoch": 1.5180722891566265,
2281
+ "grad_norm": 2.5612003803253174,
2282
+ "learning_rate": 2.7124433537999838e-06,
2283
+ "loss": 0.5184,
2284
+ "step": 317
2285
+ },
2286
+ {
2287
+ "epoch": 1.5228915662650602,
2288
+ "grad_norm": 2.8769936561584473,
2289
+ "learning_rate": 2.6594147124053983e-06,
2290
+ "loss": 0.479,
2291
+ "step": 318
2292
+ },
2293
+ {
2294
+ "epoch": 1.527710843373494,
2295
+ "grad_norm": 2.339310884475708,
2296
+ "learning_rate": 2.6068299509477267e-06,
2297
+ "loss": 0.4722,
2298
+ "step": 319
2299
+ },
2300
+ {
2301
+ "epoch": 1.5325301204819277,
2302
+ "grad_norm": 2.3183751106262207,
2303
+ "learning_rate": 2.5546922491898497e-06,
2304
+ "loss": 0.5014,
2305
+ "step": 320
2306
+ },
2307
+ {
2308
+ "epoch": 1.5373493975903614,
2309
+ "grad_norm": 2.3917415142059326,
2310
+ "learning_rate": 2.5030047598612585e-06,
2311
+ "loss": 0.4792,
2312
+ "step": 321
2313
+ },
2314
+ {
2315
+ "epoch": 1.5421686746987953,
2316
+ "grad_norm": 2.690859079360962,
2317
+ "learning_rate": 2.451770608467432e-06,
2318
+ "loss": 0.4994,
2319
+ "step": 322
2320
+ },
2321
+ {
2322
+ "epoch": 1.546987951807229,
2323
+ "grad_norm": 2.50500750541687,
2324
+ "learning_rate": 2.400992893100822e-06,
2325
+ "loss": 0.5582,
2326
+ "step": 323
2327
+ },
2328
+ {
2329
+ "epoch": 1.5518072289156626,
2330
+ "grad_norm": 2.4828755855560303,
2331
+ "learning_rate": 2.3506746842535244e-06,
2332
+ "loss": 0.4803,
2333
+ "step": 324
2334
+ },
2335
+ {
2336
+ "epoch": 1.5566265060240965,
2337
+ "grad_norm": 2.1874091625213623,
2338
+ "learning_rate": 2.3008190246316033e-06,
2339
+ "loss": 0.508,
2340
+ "step": 325
2341
+ },
2342
+ {
2343
+ "epoch": 1.5614457831325301,
2344
+ "grad_norm": 2.585437774658203,
2345
+ "learning_rate": 2.251428928971102e-06,
2346
+ "loss": 0.4728,
2347
+ "step": 326
2348
+ },
2349
+ {
2350
+ "epoch": 1.5662650602409638,
2351
+ "grad_norm": 2.979546070098877,
2352
+ "learning_rate": 2.2025073838557454e-06,
2353
+ "loss": 0.5259,
2354
+ "step": 327
2355
+ },
2356
+ {
2357
+ "epoch": 1.5710843373493977,
2358
+ "grad_norm": 2.4768764972686768,
2359
+ "learning_rate": 2.1540573475363402e-06,
2360
+ "loss": 0.4947,
2361
+ "step": 328
2362
+ },
2363
+ {
2364
+ "epoch": 1.5759036144578313,
2365
+ "grad_norm": 2.252917528152466,
2366
+ "learning_rate": 2.106081749751897e-06,
2367
+ "loss": 0.4853,
2368
+ "step": 329
2369
+ },
2370
+ {
2371
+ "epoch": 1.580722891566265,
2372
+ "grad_norm": 2.5890207290649414,
2373
+ "learning_rate": 2.058583491552465e-06,
2374
+ "loss": 0.4351,
2375
+ "step": 330
2376
+ },
2377
+ {
2378
+ "epoch": 1.5855421686746989,
2379
+ "grad_norm": 2.643648862838745,
2380
+ "learning_rate": 2.011565445123711e-06,
2381
+ "loss": 0.4515,
2382
+ "step": 331
2383
+ },
2384
+ {
2385
+ "epoch": 1.5903614457831325,
2386
+ "grad_norm": 2.6879475116729736,
2387
+ "learning_rate": 1.9650304536132426e-06,
2388
+ "loss": 0.5402,
2389
+ "step": 332
2390
+ },
2391
+ {
2392
+ "epoch": 1.5951807228915662,
2393
+ "grad_norm": 2.378323793411255,
2394
+ "learning_rate": 1.918981330958678e-06,
2395
+ "loss": 0.5162,
2396
+ "step": 333
2397
+ },
2398
+ {
2399
+ "epoch": 1.6,
2400
+ "grad_norm": 2.823969602584839,
2401
+ "learning_rate": 1.8734208617174986e-06,
2402
+ "loss": 0.4819,
2403
+ "step": 334
2404
+ },
2405
+ {
2406
+ "epoch": 1.6048192771084338,
2407
+ "grad_norm": 3.2256662845611572,
2408
+ "learning_rate": 1.8283518008986566e-06,
2409
+ "loss": 0.5214,
2410
+ "step": 335
2411
+ },
2412
+ {
2413
+ "epoch": 1.6096385542168674,
2414
+ "grad_norm": 2.3168673515319824,
2415
+ "learning_rate": 1.7837768737959937e-06,
2416
+ "loss": 0.5203,
2417
+ "step": 336
2418
+ },
2419
+ {
2420
+ "epoch": 1.6144578313253013,
2421
+ "grad_norm": 2.1533286571502686,
2422
+ "learning_rate": 1.7396987758234418e-06,
2423
+ "loss": 0.4727,
2424
+ "step": 337
2425
+ },
2426
+ {
2427
+ "epoch": 1.619277108433735,
2428
+ "grad_norm": 2.7853829860687256,
2429
+ "learning_rate": 1.6961201723520248e-06,
2430
+ "loss": 0.436,
2431
+ "step": 338
2432
+ },
2433
+ {
2434
+ "epoch": 1.6240963855421686,
2435
+ "grad_norm": 2.411254405975342,
2436
+ "learning_rate": 1.6530436985486997e-06,
2437
+ "loss": 0.4624,
2438
+ "step": 339
2439
+ },
2440
+ {
2441
+ "epoch": 1.6289156626506025,
2442
+ "grad_norm": 2.624218225479126,
2443
+ "learning_rate": 1.6104719592169905e-06,
2444
+ "loss": 0.4959,
2445
+ "step": 340
2446
+ },
2447
+ {
2448
+ "epoch": 1.6337349397590362,
2449
+ "grad_norm": 2.527923107147217,
2450
+ "learning_rate": 1.5684075286394983e-06,
2451
+ "loss": 0.4542,
2452
+ "step": 341
2453
+ },
2454
+ {
2455
+ "epoch": 1.6385542168674698,
2456
+ "grad_norm": 2.568006992340088,
2457
+ "learning_rate": 1.5268529504222262e-06,
2458
+ "loss": 0.5073,
2459
+ "step": 342
2460
+ },
2461
+ {
2462
+ "epoch": 1.6433734939759037,
2463
+ "grad_norm": 2.477860689163208,
2464
+ "learning_rate": 1.485810737340767e-06,
2465
+ "loss": 0.4342,
2466
+ "step": 343
2467
+ },
2468
+ {
2469
+ "epoch": 1.6481927710843374,
2470
+ "grad_norm": 2.5466296672821045,
2471
+ "learning_rate": 1.4452833711883629e-06,
2472
+ "loss": 0.4665,
2473
+ "step": 344
2474
+ },
2475
+ {
2476
+ "epoch": 1.653012048192771,
2477
+ "grad_norm": 3.1020963191986084,
2478
+ "learning_rate": 1.405273302625828e-06,
2479
+ "loss": 0.46,
2480
+ "step": 345
2481
+ },
2482
+ {
2483
+ "epoch": 1.657831325301205,
2484
+ "grad_norm": 2.133432149887085,
2485
+ "learning_rate": 1.3657829510333653e-06,
2486
+ "loss": 0.4656,
2487
+ "step": 346
2488
+ },
2489
+ {
2490
+ "epoch": 1.6626506024096386,
2491
+ "grad_norm": 2.116241216659546,
2492
+ "learning_rate": 1.326814704364262e-06,
2493
+ "loss": 0.4492,
2494
+ "step": 347
2495
+ },
2496
+ {
2497
+ "epoch": 1.6674698795180722,
2498
+ "grad_norm": 2.3933207988739014,
2499
+ "learning_rate": 1.2883709190004956e-06,
2500
+ "loss": 0.4416,
2501
+ "step": 348
2502
+ },
2503
+ {
2504
+ "epoch": 1.6722891566265061,
2505
+ "grad_norm": 2.776743173599243,
2506
+ "learning_rate": 1.2504539196102438e-06,
2507
+ "loss": 0.498,
2508
+ "step": 349
2509
+ },
2510
+ {
2511
+ "epoch": 1.6771084337349398,
2512
+ "grad_norm": 2.7146615982055664,
2513
+ "learning_rate": 1.2130659990073146e-06,
2514
+ "loss": 0.4832,
2515
+ "step": 350
2516
+ },
2517
+ {
2518
+ "epoch": 1.6819277108433734,
2519
+ "grad_norm": 2.236459255218506,
2520
+ "learning_rate": 1.176209418012495e-06,
2521
+ "loss": 0.4773,
2522
+ "step": 351
2523
+ },
2524
+ {
2525
+ "epoch": 1.6867469879518073,
2526
+ "grad_norm": 2.7243292331695557,
2527
+ "learning_rate": 1.1398864053168534e-06,
2528
+ "loss": 0.5527,
2529
+ "step": 352
2530
+ },
2531
+ {
2532
+ "epoch": 1.691566265060241,
2533
+ "grad_norm": 2.543335199356079,
2534
+ "learning_rate": 1.1040991573469629e-06,
2535
+ "loss": 0.4674,
2536
+ "step": 353
2537
+ },
2538
+ {
2539
+ "epoch": 1.6963855421686747,
2540
+ "grad_norm": 2.4757049083709717,
2541
+ "learning_rate": 1.0688498381320855e-06,
2542
+ "loss": 0.4628,
2543
+ "step": 354
2544
+ },
2545
+ {
2546
+ "epoch": 1.7012048192771085,
2547
+ "grad_norm": 2.4857890605926514,
2548
+ "learning_rate": 1.0341405791733183e-06,
2549
+ "loss": 0.4914,
2550
+ "step": 355
2551
+ },
2552
+ {
2553
+ "epoch": 1.7060240963855422,
2554
+ "grad_norm": 2.2958590984344482,
2555
+ "learning_rate": 9.999734793146998e-07,
2556
+ "loss": 0.4194,
2557
+ "step": 356
2558
+ },
2559
+ {
2560
+ "epoch": 1.7108433734939759,
2561
+ "grad_norm": 2.729526996612549,
2562
+ "learning_rate": 9.663506046162986e-07,
2563
+ "loss": 0.4839,
2564
+ "step": 357
2565
+ },
2566
+ {
2567
+ "epoch": 1.7156626506024097,
2568
+ "grad_norm": 2.457387924194336,
2569
+ "learning_rate": 9.332739882292752e-07,
2570
+ "loss": 0.402,
2571
+ "step": 358
2572
+ },
2573
+ {
2574
+ "epoch": 1.7204819277108434,
2575
+ "grad_norm": 2.145829439163208,
2576
+ "learning_rate": 9.0074563027294e-07,
2577
+ "loss": 0.4728,
2578
+ "step": 359
2579
+ },
2580
+ {
2581
+ "epoch": 1.725301204819277,
2582
+ "grad_norm": 2.3702030181884766,
2583
+ "learning_rate": 8.687674977138116e-07,
2584
+ "loss": 0.484,
2585
+ "step": 360
2586
+ },
2587
+ {
2588
+ "epoch": 1.730120481927711,
2589
+ "grad_norm": 2.976496934890747,
2590
+ "learning_rate": 8.373415242466721e-07,
2591
+ "loss": 0.4865,
2592
+ "step": 361
2593
+ },
2594
+ {
2595
+ "epoch": 1.7349397590361446,
2596
+ "grad_norm": 2.717363119125366,
2597
+ "learning_rate": 8.06469610177636e-07,
2598
+ "loss": 0.434,
2599
+ "step": 362
2600
+ },
2601
+ {
2602
+ "epoch": 1.7397590361445783,
2603
+ "grad_norm": 2.484947443008423,
2604
+ "learning_rate": 7.761536223092459e-07,
2605
+ "loss": 0.4643,
2606
+ "step": 363
2607
+ },
2608
+ {
2609
+ "epoch": 1.7445783132530122,
2610
+ "grad_norm": 2.8820717334747314,
2611
+ "learning_rate": 7.463953938275859e-07,
2612
+ "loss": 0.518,
2613
+ "step": 364
2614
+ },
2615
+ {
2616
+ "epoch": 1.7445783132530122,
2617
+ "eval_loss": 0.81573086977005,
2618
+ "eval_runtime": 409.3624,
2619
+ "eval_samples_per_second": 3.967,
2620
+ "eval_steps_per_second": 0.992,
2621
+ "step": 364
2622
+ },
2623
+ {
2624
+ "epoch": 1.7493975903614458,
2625
+ "grad_norm": 2.5007619857788086,
2626
+ "learning_rate": 7.171967241914224e-07,
2627
+ "loss": 0.5117,
2628
+ "step": 365
2629
+ },
2630
+ {
2631
+ "epoch": 1.7542168674698795,
2632
+ "grad_norm": 2.8851635456085205,
2633
+ "learning_rate": 6.885593790234057e-07,
2634
+ "loss": 0.433,
2635
+ "step": 366
2636
+ },
2637
+ {
2638
+ "epoch": 1.7590361445783134,
2639
+ "grad_norm": 2.6130123138427734,
2640
+ "learning_rate": 6.604850900032956e-07,
2641
+ "loss": 0.4695,
2642
+ "step": 367
2643
+ },
2644
+ {
2645
+ "epoch": 1.763855421686747,
2646
+ "grad_norm": 2.500542402267456,
2647
+ "learning_rate": 6.329755547632499e-07,
2648
+ "loss": 0.5145,
2649
+ "step": 368
2650
+ },
2651
+ {
2652
+ "epoch": 1.7686746987951807,
2653
+ "grad_norm": 2.8018507957458496,
2654
+ "learning_rate": 6.0603243678517e-07,
2655
+ "loss": 0.4638,
2656
+ "step": 369
2657
+ },
2658
+ {
2659
+ "epoch": 1.7734939759036146,
2660
+ "grad_norm": 2.414989709854126,
2661
+ "learning_rate": 5.796573653001091e-07,
2662
+ "loss": 0.4589,
2663
+ "step": 370
2664
+ },
2665
+ {
2666
+ "epoch": 1.7783132530120482,
2667
+ "grad_norm": 2.3818142414093018,
2668
+ "learning_rate": 5.538519351897575e-07,
2669
+ "loss": 0.4495,
2670
+ "step": 371
2671
+ },
2672
+ {
2673
+ "epoch": 1.783132530120482,
2674
+ "grad_norm": 2.182438373565674,
2675
+ "learning_rate": 5.286177068899989e-07,
2676
+ "loss": 0.4818,
2677
+ "step": 372
2678
+ },
2679
+ {
2680
+ "epoch": 1.7879518072289158,
2681
+ "grad_norm": 2.615506649017334,
2682
+ "learning_rate": 5.039562062965508e-07,
2683
+ "loss": 0.4734,
2684
+ "step": 373
2685
+ },
2686
+ {
2687
+ "epoch": 1.7927710843373494,
2688
+ "grad_norm": 2.4921176433563232,
2689
+ "learning_rate": 4.798689246727006e-07,
2690
+ "loss": 0.4741,
2691
+ "step": 374
2692
+ },
2693
+ {
2694
+ "epoch": 1.797590361445783,
2695
+ "grad_norm": 2.8143961429595947,
2696
+ "learning_rate": 4.563573185591219e-07,
2697
+ "loss": 0.4854,
2698
+ "step": 375
2699
+ },
2700
+ {
2701
+ "epoch": 1.802409638554217,
2702
+ "grad_norm": 2.3554911613464355,
2703
+ "learning_rate": 4.3342280968580287e-07,
2704
+ "loss": 0.4648,
2705
+ "step": 376
2706
+ },
2707
+ {
2708
+ "epoch": 1.8072289156626506,
2709
+ "grad_norm": 2.3002068996429443,
2710
+ "learning_rate": 4.11066784886075e-07,
2711
+ "loss": 0.5014,
2712
+ "step": 377
2713
+ },
2714
+ {
2715
+ "epoch": 1.8120481927710843,
2716
+ "grad_norm": 2.49564266204834,
2717
+ "learning_rate": 3.8929059601275463e-07,
2718
+ "loss": 0.4487,
2719
+ "step": 378
2720
+ },
2721
+ {
2722
+ "epoch": 1.8168674698795182,
2723
+ "grad_norm": 2.61617112159729,
2724
+ "learning_rate": 3.6809555985639065e-07,
2725
+ "loss": 0.5117,
2726
+ "step": 379
2727
+ },
2728
+ {
2729
+ "epoch": 1.8216867469879519,
2730
+ "grad_norm": 2.6199090480804443,
2731
+ "learning_rate": 3.474829580656436e-07,
2732
+ "loss": 0.462,
2733
+ "step": 380
2734
+ },
2735
+ {
2736
+ "epoch": 1.8265060240963855,
2737
+ "grad_norm": 2.755880355834961,
2738
+ "learning_rate": 3.2745403706978876e-07,
2739
+ "loss": 0.4853,
2740
+ "step": 381
2741
+ },
2742
+ {
2743
+ "epoch": 1.8313253012048194,
2744
+ "grad_norm": 2.9723000526428223,
2745
+ "learning_rate": 3.080100080033388e-07,
2746
+ "loss": 0.4672,
2747
+ "step": 382
2748
+ },
2749
+ {
2750
+ "epoch": 1.836144578313253,
2751
+ "grad_norm": 2.1068785190582275,
2752
+ "learning_rate": 2.8915204663281014e-07,
2753
+ "loss": 0.4219,
2754
+ "step": 383
2755
+ },
2756
+ {
2757
+ "epoch": 1.8409638554216867,
2758
+ "grad_norm": 2.6642982959747314,
2759
+ "learning_rate": 2.708812932856253e-07,
2760
+ "loss": 0.5069,
2761
+ "step": 384
2762
+ },
2763
+ {
2764
+ "epoch": 1.8457831325301206,
2765
+ "grad_norm": 2.3558390140533447,
2766
+ "learning_rate": 2.5319885278115907e-07,
2767
+ "loss": 0.5048,
2768
+ "step": 385
2769
+ },
2770
+ {
2771
+ "epoch": 1.8506024096385543,
2772
+ "grad_norm": 2.335449457168579,
2773
+ "learning_rate": 2.3610579436392999e-07,
2774
+ "loss": 0.429,
2775
+ "step": 386
2776
+ },
2777
+ {
2778
+ "epoch": 1.855421686746988,
2779
+ "grad_norm": 2.720520496368408,
2780
+ "learning_rate": 2.1960315163894075e-07,
2781
+ "loss": 0.4955,
2782
+ "step": 387
2783
+ },
2784
+ {
2785
+ "epoch": 1.8602409638554218,
2786
+ "grad_norm": 2.581988573074341,
2787
+ "learning_rate": 2.036919225091827e-07,
2788
+ "loss": 0.4604,
2789
+ "step": 388
2790
+ },
2791
+ {
2792
+ "epoch": 1.8650602409638555,
2793
+ "grad_norm": 2.5386810302734375,
2794
+ "learning_rate": 1.8837306911529185e-07,
2795
+ "loss": 0.4738,
2796
+ "step": 389
2797
+ },
2798
+ {
2799
+ "epoch": 1.8698795180722891,
2800
+ "grad_norm": 2.541105031967163,
2801
+ "learning_rate": 1.7364751777736334e-07,
2802
+ "loss": 0.498,
2803
+ "step": 390
2804
+ },
2805
+ {
2806
+ "epoch": 1.874698795180723,
2807
+ "grad_norm": 2.8123772144317627,
2808
+ "learning_rate": 1.595161589389449e-07,
2809
+ "loss": 0.443,
2810
+ "step": 391
2811
+ },
2812
+ {
2813
+ "epoch": 1.8795180722891565,
2814
+ "grad_norm": 2.696023464202881,
2815
+ "learning_rate": 1.459798471131868e-07,
2816
+ "loss": 0.4207,
2817
+ "step": 392
2818
+ },
2819
+ {
2820
+ "epoch": 1.8843373493975903,
2821
+ "grad_norm": 2.6544225215911865,
2822
+ "learning_rate": 1.3303940083117527e-07,
2823
+ "loss": 0.4832,
2824
+ "step": 393
2825
+ },
2826
+ {
2827
+ "epoch": 1.8891566265060242,
2828
+ "grad_norm": 3.1610257625579834,
2829
+ "learning_rate": 1.206956025924333e-07,
2830
+ "loss": 0.5528,
2831
+ "step": 394
2832
+ },
2833
+ {
2834
+ "epoch": 1.8939759036144577,
2835
+ "grad_norm": 2.7090446949005127,
2836
+ "learning_rate": 1.0894919881760168e-07,
2837
+ "loss": 0.4851,
2838
+ "step": 395
2839
+ },
2840
+ {
2841
+ "epoch": 1.8987951807228916,
2842
+ "grad_norm": 2.694115400314331,
2843
+ "learning_rate": 9.780089980330643e-08,
2844
+ "loss": 0.5122,
2845
+ "step": 396
2846
+ },
2847
+ {
2848
+ "epoch": 1.9036144578313254,
2849
+ "grad_norm": 2.570265531539917,
2850
+ "learning_rate": 8.725137967920739e-08,
2851
+ "loss": 0.4875,
2852
+ "step": 397
2853
+ },
2854
+ {
2855
+ "epoch": 1.9084337349397589,
2856
+ "grad_norm": 2.4135944843292236,
2857
+ "learning_rate": 7.730127636723539e-08,
2858
+ "loss": 0.4679,
2859
+ "step": 398
2860
+ },
2861
+ {
2862
+ "epoch": 1.9132530120481928,
2863
+ "grad_norm": 2.6173839569091797,
2864
+ "learning_rate": 6.795119154301199e-08,
2865
+ "loss": 0.4829,
2866
+ "step": 399
2867
+ },
2868
+ {
2869
+ "epoch": 1.9180722891566266,
2870
+ "grad_norm": 2.9347667694091797,
2871
+ "learning_rate": 5.920169059947412e-08,
2872
+ "loss": 0.4665,
2873
+ "step": 400
2874
+ },
2875
+ {
2876
+ "epoch": 1.92289156626506,
2877
+ "grad_norm": 2.5810000896453857,
2878
+ "learning_rate": 5.105330261267916e-08,
2879
+ "loss": 0.4994,
2880
+ "step": 401
2881
+ },
2882
+ {
2883
+ "epoch": 1.927710843373494,
2884
+ "grad_norm": 2.610971450805664,
2885
+ "learning_rate": 4.350652030981395e-08,
2886
+ "loss": 0.4584,
2887
+ "step": 402
2888
+ },
2889
+ {
2890
+ "epoch": 1.9325301204819278,
2891
+ "grad_norm": 2.3277273178100586,
2892
+ "learning_rate": 3.6561800039403016e-08,
2893
+ "loss": 0.4905,
2894
+ "step": 403
2895
+ },
2896
+ {
2897
+ "epoch": 1.9373493975903613,
2898
+ "grad_norm": 2.5518689155578613,
2899
+ "learning_rate": 3.0219561743707326e-08,
2900
+ "loss": 0.4783,
2901
+ "step": 404
2902
+ },
2903
+ {
2904
+ "epoch": 1.9421686746987952,
2905
+ "grad_norm": 2.45817232131958,
2906
+ "learning_rate": 2.4480188933336812e-08,
2907
+ "loss": 0.4618,
2908
+ "step": 405
2909
+ },
2910
+ {
2911
+ "epoch": 1.946987951807229,
2912
+ "grad_norm": 2.610630750656128,
2913
+ "learning_rate": 1.9344028664056715e-08,
2914
+ "loss": 0.4827,
2915
+ "step": 406
2916
+ },
2917
+ {
2918
+ "epoch": 1.9518072289156625,
2919
+ "grad_norm": 2.5346062183380127,
2920
+ "learning_rate": 1.4811391515799911e-08,
2921
+ "loss": 0.5063,
2922
+ "step": 407
2923
+ },
2924
+ {
2925
+ "epoch": 1.9566265060240964,
2926
+ "grad_norm": 2.244114637374878,
2927
+ "learning_rate": 1.0882551573891953e-08,
2928
+ "loss": 0.465,
2929
+ "step": 408
2930
+ },
2931
+ {
2932
+ "epoch": 1.9614457831325303,
2933
+ "grad_norm": 2.285471200942993,
2934
+ "learning_rate": 7.557746412468758e-09,
2935
+ "loss": 0.4649,
2936
+ "step": 409
2937
+ },
2938
+ {
2939
+ "epoch": 1.9662650602409637,
2940
+ "grad_norm": 2.321476936340332,
2941
+ "learning_rate": 4.837177080119215e-09,
2942
+ "loss": 0.4664,
2943
+ "step": 410
2944
+ },
2945
+ {
2946
+ "epoch": 1.9710843373493976,
2947
+ "grad_norm": 2.40159273147583,
2948
+ "learning_rate": 2.7210080877237978e-09,
2949
+ "loss": 0.497,
2950
+ "step": 411
2951
+ },
2952
+ {
2953
+ "epoch": 1.9759036144578315,
2954
+ "grad_norm": 2.6286189556121826,
2955
+ "learning_rate": 1.209367398504746e-09,
2956
+ "loss": 0.5062,
2957
+ "step": 412
2958
+ },
2959
+ {
2960
+ "epoch": 1.980722891566265,
2961
+ "grad_norm": 2.8081414699554443,
2962
+ "learning_rate": 3.023464202944748e-10,
2963
+ "loss": 0.503,
2964
+ "step": 413
2965
+ },
2966
+ {
2967
+ "epoch": 1.9855421686746988,
2968
+ "grad_norm": 2.3685240745544434,
2969
+ "learning_rate": 0.0,
2970
+ "loss": 0.4999,
2971
+ "step": 414
2972
+ }
2973
+ ],
2974
+ "logging_steps": 1,
2975
+ "max_steps": 414,
2976
+ "num_input_tokens_seen": 0,
2977
+ "num_train_epochs": 2,
2978
+ "save_steps": 104,
2979
+ "stateful_callbacks": {
2980
+ "TrainerControl": {
2981
+ "args": {
2982
+ "should_epoch_stop": false,
2983
+ "should_evaluate": false,
2984
+ "should_log": false,
2985
+ "should_save": true,
2986
+ "should_training_stop": true
2987
+ },
2988
+ "attributes": {}
2989
+ }
2990
+ },
2991
+ "total_flos": 1.2766188277900247e+18,
2992
+ "train_batch_size": 2,
2993
+ "trial_name": null,
2994
+ "trial_params": null
2995
+ }