Gwanwoo commited on
Commit
49d8597
·
verified ·
1 Parent(s): 970c96c

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 sha256:43f928cb8d94e98ed2ade3ddaf3d424f01309d53266baa05fe5af44394fc180a
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:ff330b537e9f1d8c855e13a330f71f64f0fa8e46c58fac1cfa6b6af5d89e6273
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:bcaaecfe9f8cc9af7f7af781fb2f4185baf6c6d3e99fddddc9d0cc8882c5955a
3
+ size 4999813112
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75324b57d4d5e310028c913a6748efc1a2561230c68e97512f44b1d3b1c1696a
3
+ size 4999813128
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99deb1fa28df4eafbb0a6c744c264463c6af86f838a803d65f9a8ad76066b387
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:d7e95f948f1732a4208b5f7f2ddd5fd08b99ef67226a6ce0199120dd1af76bdd
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:a3638c561f32a071e0f4e030dacbb2066693498403478419be62a01de971c91c
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:fb1165242405b17b3d6a8186ae61b13dcb1faa5a54320bebd74ef8d71b964bf7
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:562c262916c9997ec644c42fed9655ab28706b74fca20290ca921c4761d6a4b0
3
+ size 15984
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d40f8118f513299624ded0a9bcf09778b961635615090409394d4f96f928f6
3
+ size 15984
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4391f924238a4cb855c4cbdc6d1a14954f785431c75997d05c7a4ee6615dae7
3
+ size 15984
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7b19bb9543a16bf9f4cd96466ac581436f63070f5815f3a7ba57980608994f
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97da4a1ede0a3e0f96411cacd5bfdf84d9355198f7aadc9bcb8be41122043f63
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544cb6421b975bd5d2b2360a4e666003794e6197ae654d2ad963cd6572a86ede
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d6eb32a23f3bef6262bbcb2eda724b2fd6f5e579969aa27c71a5971331722b
3
+ size 15984
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb8c90ca52fb0a38d6c6ad6a0eb37f37781cc08c8f736704df1210d353ef41d
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 +1,3205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9639639639639639,
5
+ "eval_steps": 56,
6
+ "global_step": 444,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0045045045045045045,
13
+ "grad_norm": 163.10311889648438,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 3.6271,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0045045045045045045,
20
+ "eval_loss": 3.646291732788086,
21
+ "eval_runtime": 177.9569,
22
+ "eval_samples_per_second": 9.131,
23
+ "eval_steps_per_second": 1.146,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.009009009009009009,
28
+ "grad_norm": 242.46824645996094,
29
+ "learning_rate": 4.000000000000001e-06,
30
+ "loss": 3.624,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.013513513513513514,
35
+ "grad_norm": 136.7494659423828,
36
+ "learning_rate": 6e-06,
37
+ "loss": 3.0396,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.018018018018018018,
42
+ "grad_norm": 216.1807861328125,
43
+ "learning_rate": 8.000000000000001e-06,
44
+ "loss": 1.8211,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.02252252252252252,
49
+ "grad_norm": 89.306884765625,
50
+ "learning_rate": 1e-05,
51
+ "loss": 1.4198,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.02702702702702703,
56
+ "grad_norm": 37.71053695678711,
57
+ "learning_rate": 1.2e-05,
58
+ "loss": 0.9849,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.03153153153153153,
63
+ "grad_norm": 38.07053756713867,
64
+ "learning_rate": 1.4e-05,
65
+ "loss": 0.9841,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.036036036036036036,
70
+ "grad_norm": 55.28072738647461,
71
+ "learning_rate": 1.6000000000000003e-05,
72
+ "loss": 0.9289,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.04054054054054054,
77
+ "grad_norm": 27.50279426574707,
78
+ "learning_rate": 1.8e-05,
79
+ "loss": 0.8783,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.04504504504504504,
84
+ "grad_norm": 19.499553680419922,
85
+ "learning_rate": 2e-05,
86
+ "loss": 0.8988,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.04954954954954955,
91
+ "grad_norm": 74.55266571044922,
92
+ "learning_rate": 1.9999738007780348e-05,
93
+ "loss": 1.1222,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.05405405405405406,
98
+ "grad_norm": 34.171329498291016,
99
+ "learning_rate": 1.9998952044849376e-05,
100
+ "loss": 0.9393,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.05855855855855856,
105
+ "grad_norm": 19.30731201171875,
106
+ "learning_rate": 1.9997642152390316e-05,
107
+ "loss": 0.6646,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.06306306306306306,
112
+ "grad_norm": 127.51177978515625,
113
+ "learning_rate": 1.9995808399039496e-05,
114
+ "loss": 1.1814,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.06756756756756757,
119
+ "grad_norm": 57.69884490966797,
120
+ "learning_rate": 1.9993450880882736e-05,
121
+ "loss": 1.9801,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.07207207207207207,
126
+ "grad_norm": 25.815502166748047,
127
+ "learning_rate": 1.9990569721450324e-05,
128
+ "loss": 0.9264,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.07657657657657657,
133
+ "grad_norm": 17.614086151123047,
134
+ "learning_rate": 1.998716507171053e-05,
135
+ "loss": 1.2314,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.08108108108108109,
140
+ "grad_norm": 10.285378456115723,
141
+ "learning_rate": 1.9983237110061696e-05,
142
+ "loss": 0.9195,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.08558558558558559,
147
+ "grad_norm": 15.343323707580566,
148
+ "learning_rate": 1.997878604232291e-05,
149
+ "loss": 0.8851,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.09009009009009009,
154
+ "grad_norm": 8.999321937561035,
155
+ "learning_rate": 1.997381210172319e-05,
156
+ "loss": 0.8887,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.0945945945945946,
161
+ "grad_norm": 21.610994338989258,
162
+ "learning_rate": 1.996831554888928e-05,
163
+ "loss": 1.1031,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.0990990990990991,
168
+ "grad_norm": 9.373050689697266,
169
+ "learning_rate": 1.9962296671832e-05,
170
+ "loss": 0.7097,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.1036036036036036,
175
+ "grad_norm": 9.881412506103516,
176
+ "learning_rate": 1.9955755785931145e-05,
177
+ "loss": 0.9457,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.10810810810810811,
182
+ "grad_norm": 23.823366165161133,
183
+ "learning_rate": 1.994869323391895e-05,
184
+ "loss": 0.6484,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.11261261261261261,
189
+ "grad_norm": 24.844844818115234,
190
+ "learning_rate": 1.9941109385862162e-05,
191
+ "loss": 0.9384,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.11711711711711711,
196
+ "grad_norm": 13.40241527557373,
197
+ "learning_rate": 1.9933004639142606e-05,
198
+ "loss": 0.7518,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.12162162162162163,
203
+ "grad_norm": 9.293566703796387,
204
+ "learning_rate": 1.9924379418436405e-05,
205
+ "loss": 0.7535,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.12612612612612611,
210
+ "grad_norm": 11.887752532958984,
211
+ "learning_rate": 1.99152341756917e-05,
212
+ "loss": 0.765,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.13063063063063063,
217
+ "grad_norm": 14.056526184082031,
218
+ "learning_rate": 1.9905569390104988e-05,
219
+ "loss": 0.7607,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.13513513513513514,
224
+ "grad_norm": 12.957476615905762,
225
+ "learning_rate": 1.989538556809598e-05,
226
+ "loss": 0.7565,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.13963963963963963,
231
+ "grad_norm": 11.528905868530273,
232
+ "learning_rate": 1.9884683243281117e-05,
233
+ "loss": 0.8234,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.14414414414414414,
238
+ "grad_norm": 11.887662887573242,
239
+ "learning_rate": 1.9873462976445553e-05,
240
+ "loss": 0.6309,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.14864864864864866,
245
+ "grad_norm": 24.345245361328125,
246
+ "learning_rate": 1.9861725355513824e-05,
247
+ "loss": 0.8961,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.15315315315315314,
252
+ "grad_norm": 12.749674797058105,
253
+ "learning_rate": 1.9849470995518993e-05,
254
+ "loss": 0.6924,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.15765765765765766,
259
+ "grad_norm": 13.506675720214844,
260
+ "learning_rate": 1.9836700538570456e-05,
261
+ "loss": 0.8229,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.16216216216216217,
266
+ "grad_norm": 14.1195650100708,
267
+ "learning_rate": 1.982341465382029e-05,
268
+ "loss": 0.738,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.16666666666666666,
273
+ "grad_norm": 17.105318069458008,
274
+ "learning_rate": 1.9809614037428176e-05,
275
+ "loss": 0.838,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.17117117117117117,
280
+ "grad_norm": 15.875882148742676,
281
+ "learning_rate": 1.9795299412524948e-05,
282
+ "loss": 1.163,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.17567567567567569,
287
+ "grad_norm": 19.44402313232422,
288
+ "learning_rate": 1.9780471529174664e-05,
289
+ "loss": 0.8929,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.18018018018018017,
294
+ "grad_norm": 15.242260932922363,
295
+ "learning_rate": 1.9765131164335345e-05,
296
+ "loss": 0.9484,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.18468468468468469,
301
+ "grad_norm": 12.256373405456543,
302
+ "learning_rate": 1.9749279121818235e-05,
303
+ "loss": 0.6735,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.1891891891891892,
308
+ "grad_norm": 12.591852188110352,
309
+ "learning_rate": 1.9732916232245703e-05,
310
+ "loss": 0.8103,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.19369369369369369,
315
+ "grad_norm": 9.845573425292969,
316
+ "learning_rate": 1.9716043353007693e-05,
317
+ "loss": 0.9466,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.1981981981981982,
322
+ "grad_norm": 13.080997467041016,
323
+ "learning_rate": 1.9698661368216818e-05,
324
+ "loss": 0.8383,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.20270270270270271,
329
+ "grad_norm": 9.672653198242188,
330
+ "learning_rate": 1.9680771188662044e-05,
331
+ "loss": 0.8927,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.2072072072072072,
336
+ "grad_norm": 7.767281532287598,
337
+ "learning_rate": 1.9662373751760934e-05,
338
+ "loss": 0.8048,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.21171171171171171,
343
+ "grad_norm": 11.05152416229248,
344
+ "learning_rate": 1.964347002151056e-05,
345
+ "loss": 0.9164,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.21621621621621623,
350
+ "grad_norm": 8.517751693725586,
351
+ "learning_rate": 1.9624060988436968e-05,
352
+ "loss": 0.8499,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.22072072072072071,
357
+ "grad_norm": 7.533637523651123,
358
+ "learning_rate": 1.9604147669543284e-05,
359
+ "loss": 0.6575,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.22522522522522523,
364
+ "grad_norm": 8.48220443725586,
365
+ "learning_rate": 1.958373110825644e-05,
366
+ "loss": 0.724,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.22972972972972974,
371
+ "grad_norm": 11.698317527770996,
372
+ "learning_rate": 1.9562812374372474e-05,
373
+ "loss": 0.9889,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.23423423423423423,
378
+ "grad_norm": 8.52767562866211,
379
+ "learning_rate": 1.954139256400049e-05,
380
+ "loss": 0.8014,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.23873873873873874,
385
+ "grad_norm": 8.182147026062012,
386
+ "learning_rate": 1.9519472799505222e-05,
387
+ "loss": 0.7466,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.24324324324324326,
392
+ "grad_norm": 11.55849838256836,
393
+ "learning_rate": 1.9497054229448223e-05,
394
+ "loss": 1.0313,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.24774774774774774,
399
+ "grad_norm": 11.668252944946289,
400
+ "learning_rate": 1.9474138028527674e-05,
401
+ "loss": 0.8261,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.25225225225225223,
406
+ "grad_norm": 8.304422378540039,
407
+ "learning_rate": 1.945072539751685e-05,
408
+ "loss": 0.9405,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.25225225225225223,
413
+ "eval_loss": 0.8504679799079895,
414
+ "eval_runtime": 177.9362,
415
+ "eval_samples_per_second": 9.132,
416
+ "eval_steps_per_second": 1.146,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.25675675675675674,
421
+ "grad_norm": 10.961694717407227,
422
+ "learning_rate": 1.9426817563201177e-05,
423
+ "loss": 0.6715,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.26126126126126126,
428
+ "grad_norm": 11.584647178649902,
429
+ "learning_rate": 1.9402415778313978e-05,
430
+ "loss": 0.8382,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.26576576576576577,
435
+ "grad_norm": 10.582859992980957,
436
+ "learning_rate": 1.9377521321470806e-05,
437
+ "loss": 0.5171,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2702702702702703,
442
+ "grad_norm": 37.654144287109375,
443
+ "learning_rate": 1.9352135497102464e-05,
444
+ "loss": 0.9862,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2747747747747748,
449
+ "grad_norm": 10.438036918640137,
450
+ "learning_rate": 1.9326259635386647e-05,
451
+ "loss": 0.6018,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.27927927927927926,
456
+ "grad_norm": 8.785849571228027,
457
+ "learning_rate": 1.929989509217824e-05,
458
+ "loss": 0.6765,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.28378378378378377,
463
+ "grad_norm": 17.259614944458008,
464
+ "learning_rate": 1.9273043248938288e-05,
465
+ "loss": 0.8764,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2882882882882883,
470
+ "grad_norm": 10.925613403320312,
471
+ "learning_rate": 1.9245705512661594e-05,
472
+ "loss": 0.8325,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.2927927927927928,
477
+ "grad_norm": 13.911117553710938,
478
+ "learning_rate": 1.921788331580299e-05,
479
+ "loss": 0.7793,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2972972972972973,
484
+ "grad_norm": 9.837306022644043,
485
+ "learning_rate": 1.918957811620231e-05,
486
+ "loss": 0.8792,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.30180180180180183,
491
+ "grad_norm": 7.9939866065979,
492
+ "learning_rate": 1.9160791397007957e-05,
493
+ "loss": 0.8698,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.3063063063063063,
498
+ "grad_norm": 14.362957954406738,
499
+ "learning_rate": 1.9131524666599233e-05,
500
+ "loss": 0.7607,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3108108108108108,
505
+ "grad_norm": 6.983969211578369,
506
+ "learning_rate": 1.9101779458507262e-05,
507
+ "loss": 0.8202,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3153153153153153,
512
+ "grad_norm": 23.819665908813477,
513
+ "learning_rate": 1.907155733133467e-05,
514
+ "loss": 0.8899,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.31981981981981983,
519
+ "grad_norm": 12.710323333740234,
520
+ "learning_rate": 1.9040859868673887e-05,
521
+ "loss": 0.8186,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.32432432432432434,
526
+ "grad_norm": 15.840285301208496,
527
+ "learning_rate": 1.900968867902419e-05,
528
+ "loss": 0.8919,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.32882882882882886,
533
+ "grad_norm": 14.96950626373291,
534
+ "learning_rate": 1.897804539570742e-05,
535
+ "loss": 0.741,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3333333333333333,
540
+ "grad_norm": 11.247888565063477,
541
+ "learning_rate": 1.8945931676782373e-05,
542
+ "loss": 1.0211,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.33783783783783783,
547
+ "grad_norm": 14.260994911193848,
548
+ "learning_rate": 1.891334920495795e-05,
549
+ "loss": 0.889,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.34234234234234234,
554
+ "grad_norm": 12.201192855834961,
555
+ "learning_rate": 1.888029968750498e-05,
556
+ "loss": 0.7323,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.34684684684684686,
561
+ "grad_norm": 18.856571197509766,
562
+ "learning_rate": 1.8846784856166748e-05,
563
+ "loss": 0.7371,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.35135135135135137,
568
+ "grad_norm": 12.25402545928955,
569
+ "learning_rate": 1.881280646706827e-05,
570
+ "loss": 1.0143,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.35585585585585583,
575
+ "grad_norm": 9.681533813476562,
576
+ "learning_rate": 1.8778366300624248e-05,
577
+ "loss": 0.7176,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.36036036036036034,
582
+ "grad_norm": 5.826718330383301,
583
+ "learning_rate": 1.8743466161445823e-05,
584
+ "loss": 0.6044,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.36486486486486486,
589
+ "grad_norm": 9.555679321289062,
590
+ "learning_rate": 1.8708107878245976e-05,
591
+ "loss": 0.8363,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.36936936936936937,
596
+ "grad_norm": 33.45757293701172,
597
+ "learning_rate": 1.867229330374374e-05,
598
+ "loss": 0.8933,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3738738738738739,
603
+ "grad_norm": 10.304471015930176,
604
+ "learning_rate": 1.8636024314567066e-05,
605
+ "loss": 0.8924,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3783783783783784,
610
+ "grad_norm": 9.765284538269043,
611
+ "learning_rate": 1.8599302811154572e-05,
612
+ "loss": 0.9099,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.38288288288288286,
617
+ "grad_norm": 8.251590728759766,
618
+ "learning_rate": 1.856213071765588e-05,
619
+ "loss": 0.825,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.38738738738738737,
624
+ "grad_norm": 9.44628620147705,
625
+ "learning_rate": 1.8524509981830855e-05,
626
+ "loss": 0.9168,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3918918918918919,
631
+ "grad_norm": 11.477169036865234,
632
+ "learning_rate": 1.848644257494751e-05,
633
+ "loss": 0.8821,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3963963963963964,
638
+ "grad_norm": 10.04269790649414,
639
+ "learning_rate": 1.8447930491678735e-05,
640
+ "loss": 1.0161,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.4009009009009009,
645
+ "grad_norm": 29.945859909057617,
646
+ "learning_rate": 1.840897574999776e-05,
647
+ "loss": 0.8849,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.40540540540540543,
652
+ "grad_norm": 11.4473876953125,
653
+ "learning_rate": 1.8369580391072435e-05,
654
+ "loss": 0.7044,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.4099099099099099,
659
+ "grad_norm": 10.856064796447754,
660
+ "learning_rate": 1.8329746479158265e-05,
661
+ "loss": 0.7921,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.4144144144144144,
666
+ "grad_norm": 31.0800838470459,
667
+ "learning_rate": 1.8289476101490257e-05,
668
+ "loss": 0.8362,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.4189189189189189,
673
+ "grad_norm": 8.218323707580566,
674
+ "learning_rate": 1.8248771368173524e-05,
675
+ "loss": 0.8749,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.42342342342342343,
680
+ "grad_norm": 7.694657325744629,
681
+ "learning_rate": 1.8207634412072765e-05,
682
+ "loss": 0.5852,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.42792792792792794,
687
+ "grad_norm": 8.348891258239746,
688
+ "learning_rate": 1.816606738870046e-05,
689
+ "loss": 0.7723,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.43243243243243246,
694
+ "grad_norm": 8.900493621826172,
695
+ "learning_rate": 1.8124072476103957e-05,
696
+ "loss": 0.9153,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.4369369369369369,
701
+ "grad_norm": 9.774189949035645,
702
+ "learning_rate": 1.8081651874751327e-05,
703
+ "loss": 0.8803,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.44144144144144143,
708
+ "grad_norm": 9.698685646057129,
709
+ "learning_rate": 1.803880780741607e-05,
710
+ "loss": 0.9002,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.44594594594594594,
715
+ "grad_norm": 8.907757759094238,
716
+ "learning_rate": 1.7995542519060647e-05,
717
+ "loss": 0.8791,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.45045045045045046,
722
+ "grad_norm": 9.086979866027832,
723
+ "learning_rate": 1.7951858276718845e-05,
724
+ "loss": 0.8544,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.45495495495495497,
729
+ "grad_norm": 6.675291061401367,
730
+ "learning_rate": 1.7907757369376984e-05,
731
+ "loss": 0.7722,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 0.4594594594594595,
736
+ "grad_norm": 6.541719436645508,
737
+ "learning_rate": 1.7863242107853996e-05,
738
+ "loss": 0.8863,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 0.46396396396396394,
743
+ "grad_norm": 17.557701110839844,
744
+ "learning_rate": 1.78183148246803e-05,
745
+ "loss": 0.7193,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 0.46846846846846846,
750
+ "grad_norm": 13.752137184143066,
751
+ "learning_rate": 1.7772977873975633e-05,
752
+ "loss": 0.8188,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 0.47297297297297297,
757
+ "grad_norm": 7.655837535858154,
758
+ "learning_rate": 1.7727233631325666e-05,
759
+ "loss": 0.8265,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 0.4774774774774775,
764
+ "grad_norm": 17.782995223999023,
765
+ "learning_rate": 1.7681084493657526e-05,
766
+ "loss": 0.8834,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 0.481981981981982,
771
+ "grad_norm": 8.557731628417969,
772
+ "learning_rate": 1.7634532879114218e-05,
773
+ "loss": 0.9267,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 0.4864864864864865,
778
+ "grad_norm": 11.982805252075195,
779
+ "learning_rate": 1.758758122692791e-05,
780
+ "loss": 0.7615,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 0.49099099099099097,
785
+ "grad_norm": 9.639427185058594,
786
+ "learning_rate": 1.7540231997292113e-05,
787
+ "loss": 0.7077,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 0.4954954954954955,
792
+ "grad_norm": 16.217180252075195,
793
+ "learning_rate": 1.7492487671232784e-05,
794
+ "loss": 0.6474,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 0.5,
799
+ "grad_norm": 9.991765022277832,
800
+ "learning_rate": 1.7444350750478315e-05,
801
+ "loss": 0.6391,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 0.5045045045045045,
806
+ "grad_norm": 8.743515014648438,
807
+ "learning_rate": 1.7395823757328445e-05,
808
+ "loss": 0.7047,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 0.5045045045045045,
813
+ "eval_loss": 0.8168431520462036,
814
+ "eval_runtime": 177.5737,
815
+ "eval_samples_per_second": 9.151,
816
+ "eval_steps_per_second": 1.149,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.509009009009009,
821
+ "grad_norm": 15.944502830505371,
822
+ "learning_rate": 1.7346909234522108e-05,
823
+ "loss": 0.7911,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5135135135135135,
828
+ "grad_norm": 10.401838302612305,
829
+ "learning_rate": 1.7297609745104184e-05,
830
+ "loss": 0.8621,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5180180180180181,
835
+ "grad_norm": 10.353753089904785,
836
+ "learning_rate": 1.72479278722912e-05,
837
+ "loss": 0.9152,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5225225225225225,
842
+ "grad_norm": 7.570427894592285,
843
+ "learning_rate": 1.719786621933599e-05,
844
+ "loss": 0.7205,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.527027027027027,
849
+ "grad_norm": 8.158760070800781,
850
+ "learning_rate": 1.7147427409391266e-05,
851
+ "loss": 0.808,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5315315315315315,
856
+ "grad_norm": 9.257654190063477,
857
+ "learning_rate": 1.7096614085372186e-05,
858
+ "loss": 0.8001,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.536036036036036,
863
+ "grad_norm": 8.631741523742676,
864
+ "learning_rate": 1.7045428909817853e-05,
865
+ "loss": 0.6817,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5405405405405406,
870
+ "grad_norm": 11.460116386413574,
871
+ "learning_rate": 1.6993874564751824e-05,
872
+ "loss": 0.73,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.545045045045045,
877
+ "grad_norm": 10.779133796691895,
878
+ "learning_rate": 1.6941953751541552e-05,
879
+ "loss": 0.6341,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5495495495495496,
884
+ "grad_norm": 8.752435684204102,
885
+ "learning_rate": 1.688966919075687e-05,
886
+ "loss": 0.8184,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5540540540540541,
891
+ "grad_norm": 7.016055583953857,
892
+ "learning_rate": 1.6837023622027387e-05,
893
+ "loss": 0.8862,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5585585585585585,
898
+ "grad_norm": 8.855381965637207,
899
+ "learning_rate": 1.6784019803899e-05,
900
+ "loss": 0.8218,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5630630630630631,
905
+ "grad_norm": 7.984917163848877,
906
+ "learning_rate": 1.6730660513689293e-05,
907
+ "loss": 0.8618,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5675675675675675,
912
+ "grad_norm": 8.704894065856934,
913
+ "learning_rate": 1.667694854734204e-05,
914
+ "loss": 0.7119,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5720720720720721,
919
+ "grad_norm": 8.422682762145996,
920
+ "learning_rate": 1.6622886719280705e-05,
921
+ "loss": 0.6474,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5765765765765766,
926
+ "grad_norm": 8.3013916015625,
927
+ "learning_rate": 1.6568477862260952e-05,
928
+ "loss": 0.8093,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.581081081081081,
933
+ "grad_norm": 11.088935852050781,
934
+ "learning_rate": 1.6513724827222225e-05,
935
+ "loss": 0.7107,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5855855855855856,
940
+ "grad_norm": 10.994538307189941,
941
+ "learning_rate": 1.6458630483138354e-05,
942
+ "loss": 0.765,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5900900900900901,
947
+ "grad_norm": 9.655191421508789,
948
+ "learning_rate": 1.640319771686725e-05,
949
+ "loss": 0.856,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5945945945945946,
954
+ "grad_norm": 6.447967052459717,
955
+ "learning_rate": 1.6347429432999602e-05,
956
+ "loss": 0.4918,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5990990990990991,
961
+ "grad_norm": 13.354283332824707,
962
+ "learning_rate": 1.6291328553706706e-05,
963
+ "loss": 0.9368,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6036036036036037,
968
+ "grad_norm": 7.4173479080200195,
969
+ "learning_rate": 1.6234898018587336e-05,
970
+ "loss": 0.5841,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6081081081081081,
975
+ "grad_norm": 9.975573539733887,
976
+ "learning_rate": 1.6178140784513733e-05,
977
+ "loss": 0.7425,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.6126126126126126,
982
+ "grad_norm": 12.06775951385498,
983
+ "learning_rate": 1.612105982547663e-05,
984
+ "loss": 0.7928,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6171171171171171,
989
+ "grad_norm": 10.045305252075195,
990
+ "learning_rate": 1.606365813242947e-05,
991
+ "loss": 0.7107,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6216216216216216,
996
+ "grad_norm": 6.733713150024414,
997
+ "learning_rate": 1.6005938713131644e-05,
998
+ "loss": 0.7405,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6261261261261262,
1003
+ "grad_norm": 9.827054977416992,
1004
+ "learning_rate": 1.5947904591990905e-05,
1005
+ "loss": 0.8041,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6306306306306306,
1010
+ "grad_norm": 15.94497013092041,
1011
+ "learning_rate": 1.58895588099049e-05,
1012
+ "loss": 0.7473,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6351351351351351,
1017
+ "grad_norm": 8.732659339904785,
1018
+ "learning_rate": 1.583090442410182e-05,
1019
+ "loss": 0.7213,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6396396396396397,
1024
+ "grad_norm": 8.91889762878418,
1025
+ "learning_rate": 1.5771944507980208e-05,
1026
+ "loss": 0.7379,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6441441441441441,
1031
+ "grad_norm": 9.814751625061035,
1032
+ "learning_rate": 1.5712682150947926e-05,
1033
+ "loss": 0.8005,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6486486486486487,
1038
+ "grad_norm": 9.267265319824219,
1039
+ "learning_rate": 1.5653120458260263e-05,
1040
+ "loss": 0.7276,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6531531531531531,
1045
+ "grad_norm": 6.380439758300781,
1046
+ "learning_rate": 1.5593262550857233e-05,
1047
+ "loss": 0.6824,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6576576576576577,
1052
+ "grad_norm": 8.412906646728516,
1053
+ "learning_rate": 1.5533111565200046e-05,
1054
+ "loss": 0.762,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6621621621621622,
1059
+ "grad_norm": 7.7983598709106445,
1060
+ "learning_rate": 1.5472670653106746e-05,
1061
+ "loss": 0.7898,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6666666666666666,
1066
+ "grad_norm": 7.795454025268555,
1067
+ "learning_rate": 1.541194298158708e-05,
1068
+ "loss": 0.8384,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6711711711711712,
1073
+ "grad_norm": 9.10367202758789,
1074
+ "learning_rate": 1.535093173267654e-05,
1075
+ "loss": 0.6725,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6756756756756757,
1080
+ "grad_norm": 8.102481842041016,
1081
+ "learning_rate": 1.5289640103269626e-05,
1082
+ "loss": 0.8197,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6801801801801802,
1087
+ "grad_norm": 6.219252586364746,
1088
+ "learning_rate": 1.522807130495235e-05,
1089
+ "loss": 0.7383,
1090
+ "step": 151
1091
+ },
1092
+ {
1093
+ "epoch": 0.6846846846846847,
1094
+ "grad_norm": 8.467708587646484,
1095
+ "learning_rate": 1.5166228563833933e-05,
1096
+ "loss": 0.6521,
1097
+ "step": 152
1098
+ },
1099
+ {
1100
+ "epoch": 0.6891891891891891,
1101
+ "grad_norm": 5.030954360961914,
1102
+ "learning_rate": 1.5104115120377784e-05,
1103
+ "loss": 0.6479,
1104
+ "step": 153
1105
+ },
1106
+ {
1107
+ "epoch": 0.6936936936936937,
1108
+ "grad_norm": 13.453343391418457,
1109
+ "learning_rate": 1.5041734229231688e-05,
1110
+ "loss": 0.7183,
1111
+ "step": 154
1112
+ },
1113
+ {
1114
+ "epoch": 0.6981981981981982,
1115
+ "grad_norm": 5.657057762145996,
1116
+ "learning_rate": 1.4979089159057265e-05,
1117
+ "loss": 0.8351,
1118
+ "step": 155
1119
+ },
1120
+ {
1121
+ "epoch": 0.7027027027027027,
1122
+ "grad_norm": 8.919572830200195,
1123
+ "learning_rate": 1.4916183192358717e-05,
1124
+ "loss": 0.7993,
1125
+ "step": 156
1126
+ },
1127
+ {
1128
+ "epoch": 0.7072072072072072,
1129
+ "grad_norm": 6.43416690826416,
1130
+ "learning_rate": 1.4853019625310813e-05,
1131
+ "loss": 0.692,
1132
+ "step": 157
1133
+ },
1134
+ {
1135
+ "epoch": 0.7117117117117117,
1136
+ "grad_norm": 7.916557788848877,
1137
+ "learning_rate": 1.4789601767586174e-05,
1138
+ "loss": 0.5228,
1139
+ "step": 158
1140
+ },
1141
+ {
1142
+ "epoch": 0.7162162162162162,
1143
+ "grad_norm": 6.416381359100342,
1144
+ "learning_rate": 1.4725932942181871e-05,
1145
+ "loss": 0.6388,
1146
+ "step": 159
1147
+ },
1148
+ {
1149
+ "epoch": 0.7207207207207207,
1150
+ "grad_norm": 11.147228240966797,
1151
+ "learning_rate": 1.4662016485245274e-05,
1152
+ "loss": 0.8908,
1153
+ "step": 160
1154
+ },
1155
+ {
1156
+ "epoch": 0.7252252252252253,
1157
+ "grad_norm": 14.02035140991211,
1158
+ "learning_rate": 1.4597855745899275e-05,
1159
+ "loss": 0.8784,
1160
+ "step": 161
1161
+ },
1162
+ {
1163
+ "epoch": 0.7297297297297297,
1164
+ "grad_norm": 6.776102542877197,
1165
+ "learning_rate": 1.4533454086066772e-05,
1166
+ "loss": 0.8829,
1167
+ "step": 162
1168
+ },
1169
+ {
1170
+ "epoch": 0.7342342342342343,
1171
+ "grad_norm": 17.42343521118164,
1172
+ "learning_rate": 1.4468814880294531e-05,
1173
+ "loss": 0.683,
1174
+ "step": 163
1175
+ },
1176
+ {
1177
+ "epoch": 0.7387387387387387,
1178
+ "grad_norm": 9.20740032196045,
1179
+ "learning_rate": 1.4403941515576344e-05,
1180
+ "loss": 0.6757,
1181
+ "step": 164
1182
+ },
1183
+ {
1184
+ "epoch": 0.7432432432432432,
1185
+ "grad_norm": 14.219231605529785,
1186
+ "learning_rate": 1.4338837391175582e-05,
1187
+ "loss": 0.8376,
1188
+ "step": 165
1189
+ },
1190
+ {
1191
+ "epoch": 0.7477477477477478,
1192
+ "grad_norm": 12.6903715133667,
1193
+ "learning_rate": 1.4273505918447054e-05,
1194
+ "loss": 0.7243,
1195
+ "step": 166
1196
+ },
1197
+ {
1198
+ "epoch": 0.7522522522522522,
1199
+ "grad_norm": 11.196137428283691,
1200
+ "learning_rate": 1.4207950520658273e-05,
1201
+ "loss": 0.8814,
1202
+ "step": 167
1203
+ },
1204
+ {
1205
+ "epoch": 0.7567567567567568,
1206
+ "grad_norm": 15.655080795288086,
1207
+ "learning_rate": 1.4142174632810074e-05,
1208
+ "loss": 0.8658,
1209
+ "step": 168
1210
+ },
1211
+ {
1212
+ "epoch": 0.7567567567567568,
1213
+ "eval_loss": 0.8109458088874817,
1214
+ "eval_runtime": 177.2182,
1215
+ "eval_samples_per_second": 9.169,
1216
+ "eval_steps_per_second": 1.151,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.7612612612612613,
1221
+ "grad_norm": 14.430915832519531,
1222
+ "learning_rate": 1.4076181701456624e-05,
1223
+ "loss": 0.7694,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.7657657657657657,
1228
+ "grad_norm": 8.930105209350586,
1229
+ "learning_rate": 1.400997518452484e-05,
1230
+ "loss": 0.6762,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.7702702702702703,
1235
+ "grad_norm": 7.4307403564453125,
1236
+ "learning_rate": 1.3943558551133186e-05,
1237
+ "loss": 0.6309,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.7747747747747747,
1242
+ "grad_norm": 9.10818862915039,
1243
+ "learning_rate": 1.3876935281409907e-05,
1244
+ "loss": 0.8066,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.7792792792792793,
1249
+ "grad_norm": 7.966973304748535,
1250
+ "learning_rate": 1.381010886631066e-05,
1251
+ "loss": 0.7292,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.7837837837837838,
1256
+ "grad_norm": 9.658637046813965,
1257
+ "learning_rate": 1.3743082807435615e-05,
1258
+ "loss": 0.5872,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.7882882882882883,
1263
+ "grad_norm": 9.851784706115723,
1264
+ "learning_rate": 1.3675860616845953e-05,
1265
+ "loss": 0.8581,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.7927927927927928,
1270
+ "grad_norm": 6.482726573944092,
1271
+ "learning_rate": 1.3608445816879865e-05,
1272
+ "loss": 0.8097,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.7972972972972973,
1277
+ "grad_norm": 7.754999160766602,
1278
+ "learning_rate": 1.3540841939967964e-05,
1279
+ "loss": 0.7651,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.8018018018018018,
1284
+ "grad_norm": 5.25705623626709,
1285
+ "learning_rate": 1.3473052528448203e-05,
1286
+ "loss": 0.7379,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.8063063063063063,
1291
+ "grad_norm": 7.3288655281066895,
1292
+ "learning_rate": 1.3405081134380264e-05,
1293
+ "loss": 0.8196,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.8108108108108109,
1298
+ "grad_norm": 6.39313268661499,
1299
+ "learning_rate": 1.3336931319359428e-05,
1300
+ "loss": 0.6106,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.8153153153153153,
1305
+ "grad_norm": 6.135197639465332,
1306
+ "learning_rate": 1.3268606654329952e-05,
1307
+ "loss": 0.6264,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.8198198198198198,
1312
+ "grad_norm": 8.632068634033203,
1313
+ "learning_rate": 1.3200110719397969e-05,
1314
+ "loss": 0.6012,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.8243243243243243,
1319
+ "grad_norm": 6.881383895874023,
1320
+ "learning_rate": 1.3131447103643886e-05,
1321
+ "loss": 0.7038,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.8288288288288288,
1326
+ "grad_norm": 7.713339328765869,
1327
+ "learning_rate": 1.3062619404934319e-05,
1328
+ "loss": 0.773,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.8333333333333334,
1333
+ "grad_norm": 5.589472770690918,
1334
+ "learning_rate": 1.2993631229733584e-05,
1335
+ "loss": 0.8342,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.8378378378378378,
1340
+ "grad_norm": 7.90900993347168,
1341
+ "learning_rate": 1.2924486192914705e-05,
1342
+ "loss": 0.8121,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.8423423423423423,
1347
+ "grad_norm": 6.5045166015625,
1348
+ "learning_rate": 1.285518791757002e-05,
1349
+ "loss": 0.5196,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.8468468468468469,
1354
+ "grad_norm": 5.993255138397217,
1355
+ "learning_rate": 1.278574003482133e-05,
1356
+ "loss": 0.7156,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.8513513513513513,
1361
+ "grad_norm": 7.4153313636779785,
1362
+ "learning_rate": 1.2716146183629619e-05,
1363
+ "loss": 0.7183,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.8558558558558559,
1368
+ "grad_norm": 14.237358093261719,
1369
+ "learning_rate": 1.2646410010604397e-05,
1370
+ "loss": 0.7203,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.8603603603603603,
1375
+ "grad_norm": 6.8599700927734375,
1376
+ "learning_rate": 1.2576535169812616e-05,
1377
+ "loss": 0.7834,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.8648648648648649,
1382
+ "grad_norm": 7.724032402038574,
1383
+ "learning_rate": 1.2506525322587207e-05,
1384
+ "loss": 0.8184,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.8693693693693694,
1389
+ "grad_norm": 9.730342864990234,
1390
+ "learning_rate": 1.243638413733522e-05,
1391
+ "loss": 0.8373,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.8738738738738738,
1396
+ "grad_norm": 4.979872703552246,
1397
+ "learning_rate": 1.236611528934562e-05,
1398
+ "loss": 0.459,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.8783783783783784,
1403
+ "grad_norm": 4.859985828399658,
1404
+ "learning_rate": 1.2295722460596698e-05,
1405
+ "loss": 0.6895,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.8828828828828829,
1410
+ "grad_norm": 8.581028938293457,
1411
+ "learning_rate": 1.2225209339563144e-05,
1412
+ "loss": 0.7399,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.8873873873873874,
1417
+ "grad_norm": 4.375821590423584,
1418
+ "learning_rate": 1.2154579621022778e-05,
1419
+ "loss": 0.6034,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.8918918918918919,
1424
+ "grad_norm": 6.873833656311035,
1425
+ "learning_rate": 1.2083837005862946e-05,
1426
+ "loss": 0.7193,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.8963963963963963,
1431
+ "grad_norm": 6.126974105834961,
1432
+ "learning_rate": 1.2012985200886602e-05,
1433
+ "loss": 0.5947,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.9009009009009009,
1438
+ "grad_norm": 7.188669204711914,
1439
+ "learning_rate": 1.1942027918618076e-05,
1440
+ "loss": 0.7375,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.9054054054054054,
1445
+ "grad_norm": 5.053603172302246,
1446
+ "learning_rate": 1.1870968877108546e-05,
1447
+ "loss": 0.5256,
1448
+ "step": 201
1449
+ },
1450
+ {
1451
+ "epoch": 0.9099099099099099,
1452
+ "grad_norm": 8.81440544128418,
1453
+ "learning_rate": 1.1799811799741209e-05,
1454
+ "loss": 0.5382,
1455
+ "step": 202
1456
+ },
1457
+ {
1458
+ "epoch": 0.9144144144144144,
1459
+ "grad_norm": 6.666991710662842,
1460
+ "learning_rate": 1.17285604150362e-05,
1461
+ "loss": 0.7269,
1462
+ "step": 203
1463
+ },
1464
+ {
1465
+ "epoch": 0.918918918918919,
1466
+ "grad_norm": 6.382652282714844,
1467
+ "learning_rate": 1.1657218456455207e-05,
1468
+ "loss": 0.6991,
1469
+ "step": 204
1470
+ },
1471
+ {
1472
+ "epoch": 0.9234234234234234,
1473
+ "grad_norm": 9.950919151306152,
1474
+ "learning_rate": 1.1585789662205835e-05,
1475
+ "loss": 0.7093,
1476
+ "step": 205
1477
+ },
1478
+ {
1479
+ "epoch": 0.9279279279279279,
1480
+ "grad_norm": 8.805401802062988,
1481
+ "learning_rate": 1.1514277775045768e-05,
1482
+ "loss": 0.7167,
1483
+ "step": 206
1484
+ },
1485
+ {
1486
+ "epoch": 0.9324324324324325,
1487
+ "grad_norm": 9.931432723999023,
1488
+ "learning_rate": 1.144268654208661e-05,
1489
+ "loss": 0.6583,
1490
+ "step": 207
1491
+ },
1492
+ {
1493
+ "epoch": 0.9369369369369369,
1494
+ "grad_norm": 10.574563026428223,
1495
+ "learning_rate": 1.1371019714597562e-05,
1496
+ "loss": 0.9348,
1497
+ "step": 208
1498
+ },
1499
+ {
1500
+ "epoch": 0.9414414414414415,
1501
+ "grad_norm": 7.706573009490967,
1502
+ "learning_rate": 1.1299281047808876e-05,
1503
+ "loss": 0.7703,
1504
+ "step": 209
1505
+ },
1506
+ {
1507
+ "epoch": 0.9459459459459459,
1508
+ "grad_norm": 12.46348762512207,
1509
+ "learning_rate": 1.1227474300715056e-05,
1510
+ "loss": 0.6255,
1511
+ "step": 210
1512
+ },
1513
+ {
1514
+ "epoch": 0.9504504504504504,
1515
+ "grad_norm": 13.356134414672852,
1516
+ "learning_rate": 1.1155603235877912e-05,
1517
+ "loss": 0.8815,
1518
+ "step": 211
1519
+ },
1520
+ {
1521
+ "epoch": 0.954954954954955,
1522
+ "grad_norm": 12.36632251739502,
1523
+ "learning_rate": 1.1083671619229409e-05,
1524
+ "loss": 0.7756,
1525
+ "step": 212
1526
+ },
1527
+ {
1528
+ "epoch": 0.9594594594594594,
1529
+ "grad_norm": 6.048164367675781,
1530
+ "learning_rate": 1.1011683219874324e-05,
1531
+ "loss": 0.897,
1532
+ "step": 213
1533
+ },
1534
+ {
1535
+ "epoch": 0.963963963963964,
1536
+ "grad_norm": 12.071527481079102,
1537
+ "learning_rate": 1.0939641809892767e-05,
1538
+ "loss": 0.7138,
1539
+ "step": 214
1540
+ },
1541
+ {
1542
+ "epoch": 0.9684684684684685,
1543
+ "grad_norm": 17.603248596191406,
1544
+ "learning_rate": 1.086755116414252e-05,
1545
+ "loss": 0.5896,
1546
+ "step": 215
1547
+ },
1548
+ {
1549
+ "epoch": 0.972972972972973,
1550
+ "grad_norm": 12.864622116088867,
1551
+ "learning_rate": 1.0795415060061242e-05,
1552
+ "loss": 0.9211,
1553
+ "step": 216
1554
+ },
1555
+ {
1556
+ "epoch": 0.9774774774774775,
1557
+ "grad_norm": 5.669272422790527,
1558
+ "learning_rate": 1.072323727746854e-05,
1559
+ "loss": 0.7366,
1560
+ "step": 217
1561
+ },
1562
+ {
1563
+ "epoch": 0.9819819819819819,
1564
+ "grad_norm": 7.244740009307861,
1565
+ "learning_rate": 1.0651021598367905e-05,
1566
+ "loss": 0.8982,
1567
+ "step": 218
1568
+ },
1569
+ {
1570
+ "epoch": 0.9864864864864865,
1571
+ "grad_norm": 6.348238945007324,
1572
+ "learning_rate": 1.0578771806748547e-05,
1573
+ "loss": 0.804,
1574
+ "step": 219
1575
+ },
1576
+ {
1577
+ "epoch": 0.990990990990991,
1578
+ "grad_norm": 5.5439558029174805,
1579
+ "learning_rate": 1.0506491688387128e-05,
1580
+ "loss": 0.5346,
1581
+ "step": 220
1582
+ },
1583
+ {
1584
+ "epoch": 0.9954954954954955,
1585
+ "grad_norm": 5.38005256652832,
1586
+ "learning_rate": 1.0434185030649374e-05,
1587
+ "loss": 0.6872,
1588
+ "step": 221
1589
+ },
1590
+ {
1591
+ "epoch": 1.0,
1592
+ "grad_norm": 12.912734031677246,
1593
+ "learning_rate": 1.0361855622291637e-05,
1594
+ "loss": 0.8099,
1595
+ "step": 222
1596
+ },
1597
+ {
1598
+ "epoch": 1.0045045045045045,
1599
+ "grad_norm": 7.5897297859191895,
1600
+ "learning_rate": 1.0289507253262358e-05,
1601
+ "loss": 0.7033,
1602
+ "step": 223
1603
+ },
1604
+ {
1605
+ "epoch": 1.009009009009009,
1606
+ "grad_norm": 8.13759994506836,
1607
+ "learning_rate": 1.0217143714503508e-05,
1608
+ "loss": 0.3599,
1609
+ "step": 224
1610
+ },
1611
+ {
1612
+ "epoch": 1.009009009009009,
1613
+ "eval_loss": 0.7478944659233093,
1614
+ "eval_runtime": 178.0785,
1615
+ "eval_samples_per_second": 9.125,
1616
+ "eval_steps_per_second": 1.146,
1617
+ "step": 224
1618
+ },
1619
+ {
1620
+ "epoch": 1.0135135135135136,
1621
+ "grad_norm": 7.843093395233154,
1622
+ "learning_rate": 1.0144768797751905e-05,
1623
+ "loss": 0.6685,
1624
+ "step": 225
1625
+ },
1626
+ {
1627
+ "epoch": 1.018018018018018,
1628
+ "grad_norm": 6.668365478515625,
1629
+ "learning_rate": 1.0072386295340572e-05,
1630
+ "loss": 0.7798,
1631
+ "step": 226
1632
+ },
1633
+ {
1634
+ "epoch": 1.0225225225225225,
1635
+ "grad_norm": 17.80467987060547,
1636
+ "learning_rate": 1e-05,
1637
+ "loss": 0.6196,
1638
+ "step": 227
1639
+ },
1640
+ {
1641
+ "epoch": 1.027027027027027,
1642
+ "grad_norm": 12.371468544006348,
1643
+ "learning_rate": 9.92761370465943e-06,
1644
+ "loss": 1.0499,
1645
+ "step": 228
1646
+ },
1647
+ {
1648
+ "epoch": 1.0315315315315314,
1649
+ "grad_norm": 9.211063385009766,
1650
+ "learning_rate": 9.855231202248098e-06,
1651
+ "loss": 0.7076,
1652
+ "step": 229
1653
+ },
1654
+ {
1655
+ "epoch": 1.0360360360360361,
1656
+ "grad_norm": 8.459956169128418,
1657
+ "learning_rate": 9.782856285496494e-06,
1658
+ "loss": 0.6235,
1659
+ "step": 230
1660
+ },
1661
+ {
1662
+ "epoch": 1.0045045045045045,
1663
+ "grad_norm": 4.878438949584961,
1664
+ "learning_rate": 9.710492746737644e-06,
1665
+ "loss": 0.4943,
1666
+ "step": 231
1667
+ },
1668
+ {
1669
+ "epoch": 1.009009009009009,
1670
+ "grad_norm": 7.915105819702148,
1671
+ "learning_rate": 9.638144377708366e-06,
1672
+ "loss": 0.559,
1673
+ "step": 232
1674
+ },
1675
+ {
1676
+ "epoch": 1.0135135135135136,
1677
+ "grad_norm": 5.238325119018555,
1678
+ "learning_rate": 9.565814969350628e-06,
1679
+ "loss": 0.4101,
1680
+ "step": 233
1681
+ },
1682
+ {
1683
+ "epoch": 1.018018018018018,
1684
+ "grad_norm": 5.5473761558532715,
1685
+ "learning_rate": 9.493508311612874e-06,
1686
+ "loss": 0.4053,
1687
+ "step": 234
1688
+ },
1689
+ {
1690
+ "epoch": 1.0225225225225225,
1691
+ "grad_norm": 13.226475715637207,
1692
+ "learning_rate": 9.421228193251453e-06,
1693
+ "loss": 0.4291,
1694
+ "step": 235
1695
+ },
1696
+ {
1697
+ "epoch": 1.027027027027027,
1698
+ "grad_norm": 7.770974636077881,
1699
+ "learning_rate": 9.348978401632101e-06,
1700
+ "loss": 0.4449,
1701
+ "step": 236
1702
+ },
1703
+ {
1704
+ "epoch": 1.0315315315315314,
1705
+ "grad_norm": 8.609363555908203,
1706
+ "learning_rate": 9.276762722531462e-06,
1707
+ "loss": 0.5591,
1708
+ "step": 237
1709
+ },
1710
+ {
1711
+ "epoch": 1.0360360360360361,
1712
+ "grad_norm": 9.076277732849121,
1713
+ "learning_rate": 9.204584939938763e-06,
1714
+ "loss": 0.7801,
1715
+ "step": 238
1716
+ },
1717
+ {
1718
+ "epoch": 1.0405405405405406,
1719
+ "grad_norm": 4.317523956298828,
1720
+ "learning_rate": 9.132448835857483e-06,
1721
+ "loss": 0.3385,
1722
+ "step": 239
1723
+ },
1724
+ {
1725
+ "epoch": 1.045045045045045,
1726
+ "grad_norm": 8.347039222717285,
1727
+ "learning_rate": 9.060358190107235e-06,
1728
+ "loss": 0.5321,
1729
+ "step": 240
1730
+ },
1731
+ {
1732
+ "epoch": 1.0495495495495495,
1733
+ "grad_norm": 8.409918785095215,
1734
+ "learning_rate": 8.98831678012568e-06,
1735
+ "loss": 0.4421,
1736
+ "step": 241
1737
+ },
1738
+ {
1739
+ "epoch": 1.054054054054054,
1740
+ "grad_norm": 6.159451961517334,
1741
+ "learning_rate": 8.916328380770595e-06,
1742
+ "loss": 0.6598,
1743
+ "step": 242
1744
+ },
1745
+ {
1746
+ "epoch": 1.0585585585585586,
1747
+ "grad_norm": 11.68327522277832,
1748
+ "learning_rate": 8.844396764122093e-06,
1749
+ "loss": 0.4878,
1750
+ "step": 243
1751
+ },
1752
+ {
1753
+ "epoch": 1.063063063063063,
1754
+ "grad_norm": 4.7915191650390625,
1755
+ "learning_rate": 8.772525699284947e-06,
1756
+ "loss": 0.6375,
1757
+ "step": 244
1758
+ },
1759
+ {
1760
+ "epoch": 1.0675675675675675,
1761
+ "grad_norm": 5.316025733947754,
1762
+ "learning_rate": 8.700718952191126e-06,
1763
+ "loss": 0.4973,
1764
+ "step": 245
1765
+ },
1766
+ {
1767
+ "epoch": 1.072072072072072,
1768
+ "grad_norm": 5.144191741943359,
1769
+ "learning_rate": 8.62898028540244e-06,
1770
+ "loss": 0.5357,
1771
+ "step": 246
1772
+ },
1773
+ {
1774
+ "epoch": 1.0765765765765765,
1775
+ "grad_norm": 5.196255207061768,
1776
+ "learning_rate": 8.557313457913395e-06,
1777
+ "loss": 0.3334,
1778
+ "step": 247
1779
+ },
1780
+ {
1781
+ "epoch": 1.0810810810810811,
1782
+ "grad_norm": 5.423978328704834,
1783
+ "learning_rate": 8.485722224954237e-06,
1784
+ "loss": 0.5748,
1785
+ "step": 248
1786
+ },
1787
+ {
1788
+ "epoch": 1.0855855855855856,
1789
+ "grad_norm": 4.671257019042969,
1790
+ "learning_rate": 8.414210337794167e-06,
1791
+ "loss": 0.5119,
1792
+ "step": 249
1793
+ },
1794
+ {
1795
+ "epoch": 1.09009009009009,
1796
+ "grad_norm": 6.139837741851807,
1797
+ "learning_rate": 8.342781543544799e-06,
1798
+ "loss": 0.5453,
1799
+ "step": 250
1800
+ },
1801
+ {
1802
+ "epoch": 1.0945945945945945,
1803
+ "grad_norm": 4.831565856933594,
1804
+ "learning_rate": 8.271439584963801e-06,
1805
+ "loss": 0.3381,
1806
+ "step": 251
1807
+ },
1808
+ {
1809
+ "epoch": 1.0990990990990992,
1810
+ "grad_norm": 5.024011135101318,
1811
+ "learning_rate": 8.200188200258793e-06,
1812
+ "loss": 0.1158,
1813
+ "step": 252
1814
+ },
1815
+ {
1816
+ "epoch": 1.1036036036036037,
1817
+ "grad_norm": 3.3059139251708984,
1818
+ "learning_rate": 8.12903112289146e-06,
1819
+ "loss": 0.3945,
1820
+ "step": 253
1821
+ },
1822
+ {
1823
+ "epoch": 1.1081081081081081,
1824
+ "grad_norm": 6.7433319091796875,
1825
+ "learning_rate": 8.057972081381926e-06,
1826
+ "loss": 0.5059,
1827
+ "step": 254
1828
+ },
1829
+ {
1830
+ "epoch": 1.1126126126126126,
1831
+ "grad_norm": 6.164863109588623,
1832
+ "learning_rate": 7.987014799113398e-06,
1833
+ "loss": 0.4234,
1834
+ "step": 255
1835
+ },
1836
+ {
1837
+ "epoch": 1.117117117117117,
1838
+ "grad_norm": 6.8952155113220215,
1839
+ "learning_rate": 7.916162994137056e-06,
1840
+ "loss": 0.4958,
1841
+ "step": 256
1842
+ },
1843
+ {
1844
+ "epoch": 1.1216216216216217,
1845
+ "grad_norm": 5.957776069641113,
1846
+ "learning_rate": 7.845420378977224e-06,
1847
+ "loss": 0.3515,
1848
+ "step": 257
1849
+ },
1850
+ {
1851
+ "epoch": 1.1261261261261262,
1852
+ "grad_norm": 9.42939567565918,
1853
+ "learning_rate": 7.774790660436857e-06,
1854
+ "loss": 0.2484,
1855
+ "step": 258
1856
+ },
1857
+ {
1858
+ "epoch": 1.1306306306306306,
1859
+ "grad_norm": 7.934135437011719,
1860
+ "learning_rate": 7.704277539403304e-06,
1861
+ "loss": 0.4167,
1862
+ "step": 259
1863
+ },
1864
+ {
1865
+ "epoch": 1.135135135135135,
1866
+ "grad_norm": 6.654007911682129,
1867
+ "learning_rate": 7.633884710654383e-06,
1868
+ "loss": 0.5662,
1869
+ "step": 260
1870
+ },
1871
+ {
1872
+ "epoch": 1.1396396396396395,
1873
+ "grad_norm": 8.044957160949707,
1874
+ "learning_rate": 7.563615862664781e-06,
1875
+ "loss": 0.4205,
1876
+ "step": 261
1877
+ },
1878
+ {
1879
+ "epoch": 1.1441441441441442,
1880
+ "grad_norm": 7.115239143371582,
1881
+ "learning_rate": 7.493474677412795e-06,
1882
+ "loss": 0.6096,
1883
+ "step": 262
1884
+ },
1885
+ {
1886
+ "epoch": 1.1486486486486487,
1887
+ "grad_norm": 12.922812461853027,
1888
+ "learning_rate": 7.423464830187387e-06,
1889
+ "loss": 0.6586,
1890
+ "step": 263
1891
+ },
1892
+ {
1893
+ "epoch": 1.1531531531531531,
1894
+ "grad_norm": 6.83433198928833,
1895
+ "learning_rate": 7.353589989395605e-06,
1896
+ "loss": 0.4778,
1897
+ "step": 264
1898
+ },
1899
+ {
1900
+ "epoch": 1.1576576576576576,
1901
+ "grad_norm": 6.0931172370910645,
1902
+ "learning_rate": 7.283853816370386e-06,
1903
+ "loss": 0.4284,
1904
+ "step": 265
1905
+ },
1906
+ {
1907
+ "epoch": 1.1621621621621623,
1908
+ "grad_norm": 7.684704780578613,
1909
+ "learning_rate": 7.214259965178674e-06,
1910
+ "loss": 0.4711,
1911
+ "step": 266
1912
+ },
1913
+ {
1914
+ "epoch": 1.1666666666666667,
1915
+ "grad_norm": 6.312220573425293,
1916
+ "learning_rate": 7.1448120824299795e-06,
1917
+ "loss": 0.516,
1918
+ "step": 267
1919
+ },
1920
+ {
1921
+ "epoch": 1.1711711711711712,
1922
+ "grad_norm": 10.755828857421875,
1923
+ "learning_rate": 7.075513807085299e-06,
1924
+ "loss": 0.3978,
1925
+ "step": 268
1926
+ },
1927
+ {
1928
+ "epoch": 1.1756756756756757,
1929
+ "grad_norm": 6.550760269165039,
1930
+ "learning_rate": 7.006368770266421e-06,
1931
+ "loss": 0.5478,
1932
+ "step": 269
1933
+ },
1934
+ {
1935
+ "epoch": 1.1801801801801801,
1936
+ "grad_norm": 7.007323265075684,
1937
+ "learning_rate": 6.937380595065686e-06,
1938
+ "loss": 0.419,
1939
+ "step": 270
1940
+ },
1941
+ {
1942
+ "epoch": 1.1846846846846848,
1943
+ "grad_norm": 5.438976764678955,
1944
+ "learning_rate": 6.868552896356118e-06,
1945
+ "loss": 0.3348,
1946
+ "step": 271
1947
+ },
1948
+ {
1949
+ "epoch": 1.1891891891891893,
1950
+ "grad_norm": 5.593977451324463,
1951
+ "learning_rate": 6.799889280602031e-06,
1952
+ "loss": 0.4757,
1953
+ "step": 272
1954
+ },
1955
+ {
1956
+ "epoch": 1.1936936936936937,
1957
+ "grad_norm": 12.432474136352539,
1958
+ "learning_rate": 6.731393345670051e-06,
1959
+ "loss": 0.3754,
1960
+ "step": 273
1961
+ },
1962
+ {
1963
+ "epoch": 1.1981981981981982,
1964
+ "grad_norm": 7.555688858032227,
1965
+ "learning_rate": 6.663068680640574e-06,
1966
+ "loss": 0.4091,
1967
+ "step": 274
1968
+ },
1969
+ {
1970
+ "epoch": 1.2027027027027026,
1971
+ "grad_norm": 7.822305679321289,
1972
+ "learning_rate": 6.59491886561974e-06,
1973
+ "loss": 0.3913,
1974
+ "step": 275
1975
+ },
1976
+ {
1977
+ "epoch": 1.2072072072072073,
1978
+ "grad_norm": 7.551604747772217,
1979
+ "learning_rate": 6.526947471551799e-06,
1980
+ "loss": 0.5056,
1981
+ "step": 276
1982
+ },
1983
+ {
1984
+ "epoch": 1.2117117117117118,
1985
+ "grad_norm": 7.9216461181640625,
1986
+ "learning_rate": 6.4591580600320405e-06,
1987
+ "loss": 0.5716,
1988
+ "step": 277
1989
+ },
1990
+ {
1991
+ "epoch": 1.2162162162162162,
1992
+ "grad_norm": 5.806591510772705,
1993
+ "learning_rate": 6.391554183120139e-06,
1994
+ "loss": 0.4627,
1995
+ "step": 278
1996
+ },
1997
+ {
1998
+ "epoch": 1.2207207207207207,
1999
+ "grad_norm": 6.734259128570557,
2000
+ "learning_rate": 6.324139383154049e-06,
2001
+ "loss": 0.6408,
2002
+ "step": 279
2003
+ },
2004
+ {
2005
+ "epoch": 1.2252252252252251,
2006
+ "grad_norm": 9.174220085144043,
2007
+ "learning_rate": 6.2569171925643915e-06,
2008
+ "loss": 0.3462,
2009
+ "step": 280
2010
+ },
2011
+ {
2012
+ "epoch": 1.2252252252252251,
2013
+ "eval_loss": 0.754913330078125,
2014
+ "eval_runtime": 177.1913,
2015
+ "eval_samples_per_second": 9.171,
2016
+ "eval_steps_per_second": 1.151,
2017
+ "step": 280
2018
+ },
2019
+ {
2020
+ "epoch": 1.2297297297297298,
2021
+ "grad_norm": 8.161945343017578,
2022
+ "learning_rate": 6.189891133689343e-06,
2023
+ "loss": 0.4028,
2024
+ "step": 281
2025
+ },
2026
+ {
2027
+ "epoch": 1.2342342342342343,
2028
+ "grad_norm": 5.667252540588379,
2029
+ "learning_rate": 6.123064718590099e-06,
2030
+ "loss": 0.5784,
2031
+ "step": 282
2032
+ },
2033
+ {
2034
+ "epoch": 1.2387387387387387,
2035
+ "grad_norm": 5.325718879699707,
2036
+ "learning_rate": 6.056441448866817e-06,
2037
+ "loss": 0.5521,
2038
+ "step": 283
2039
+ },
2040
+ {
2041
+ "epoch": 1.2432432432432432,
2042
+ "grad_norm": 6.017253875732422,
2043
+ "learning_rate": 5.990024815475162e-06,
2044
+ "loss": 0.2732,
2045
+ "step": 284
2046
+ },
2047
+ {
2048
+ "epoch": 1.2477477477477477,
2049
+ "grad_norm": 6.889372825622559,
2050
+ "learning_rate": 5.923818298543379e-06,
2051
+ "loss": 0.3225,
2052
+ "step": 285
2053
+ },
2054
+ {
2055
+ "epoch": 1.2522522522522523,
2056
+ "grad_norm": 4.173173427581787,
2057
+ "learning_rate": 5.857825367189931e-06,
2058
+ "loss": 0.4452,
2059
+ "step": 286
2060
+ },
2061
+ {
2062
+ "epoch": 1.2567567567567568,
2063
+ "grad_norm": 4.246283054351807,
2064
+ "learning_rate": 5.792049479341732e-06,
2065
+ "loss": 0.3418,
2066
+ "step": 287
2067
+ },
2068
+ {
2069
+ "epoch": 1.2612612612612613,
2070
+ "grad_norm": 6.418617248535156,
2071
+ "learning_rate": 5.726494081552949e-06,
2072
+ "loss": 0.5461,
2073
+ "step": 288
2074
+ },
2075
+ {
2076
+ "epoch": 1.2657657657657657,
2077
+ "grad_norm": 4.809614181518555,
2078
+ "learning_rate": 5.66116260882442e-06,
2079
+ "loss": 0.4197,
2080
+ "step": 289
2081
+ },
2082
+ {
2083
+ "epoch": 1.2702702702702702,
2084
+ "grad_norm": 9.890124320983887,
2085
+ "learning_rate": 5.5960584844236565e-06,
2086
+ "loss": 0.4534,
2087
+ "step": 290
2088
+ },
2089
+ {
2090
+ "epoch": 1.2747747747747749,
2091
+ "grad_norm": 8.217459678649902,
2092
+ "learning_rate": 5.531185119705475e-06,
2093
+ "loss": 0.4158,
2094
+ "step": 291
2095
+ },
2096
+ {
2097
+ "epoch": 1.2792792792792793,
2098
+ "grad_norm": 5.305176258087158,
2099
+ "learning_rate": 5.46654591393323e-06,
2100
+ "loss": 0.3184,
2101
+ "step": 292
2102
+ },
2103
+ {
2104
+ "epoch": 1.2837837837837838,
2105
+ "grad_norm": 5.6850266456604,
2106
+ "learning_rate": 5.402144254100725e-06,
2107
+ "loss": 0.3378,
2108
+ "step": 293
2109
+ },
2110
+ {
2111
+ "epoch": 1.2882882882882882,
2112
+ "grad_norm": 7.203133583068848,
2113
+ "learning_rate": 5.337983514754723e-06,
2114
+ "loss": 0.4963,
2115
+ "step": 294
2116
+ },
2117
+ {
2118
+ "epoch": 1.2927927927927927,
2119
+ "grad_norm": 16.63918685913086,
2120
+ "learning_rate": 5.274067057818131e-06,
2121
+ "loss": 0.5457,
2122
+ "step": 295
2123
+ },
2124
+ {
2125
+ "epoch": 1.2972972972972974,
2126
+ "grad_norm": 12.17789363861084,
2127
+ "learning_rate": 5.210398232413824e-06,
2128
+ "loss": 0.5918,
2129
+ "step": 296
2130
+ },
2131
+ {
2132
+ "epoch": 1.3018018018018018,
2133
+ "grad_norm": 6.860198974609375,
2134
+ "learning_rate": 5.146980374689192e-06,
2135
+ "loss": 0.5953,
2136
+ "step": 297
2137
+ },
2138
+ {
2139
+ "epoch": 1.3063063063063063,
2140
+ "grad_norm": 5.866564750671387,
2141
+ "learning_rate": 5.0838168076412844e-06,
2142
+ "loss": 0.472,
2143
+ "step": 298
2144
+ },
2145
+ {
2146
+ "epoch": 1.3108108108108107,
2147
+ "grad_norm": 5.696018218994141,
2148
+ "learning_rate": 5.020910840942738e-06,
2149
+ "loss": 0.3857,
2150
+ "step": 299
2151
+ },
2152
+ {
2153
+ "epoch": 1.3153153153153152,
2154
+ "grad_norm": 6.834244728088379,
2155
+ "learning_rate": 4.958265770768315e-06,
2156
+ "loss": 0.57,
2157
+ "step": 300
2158
+ },
2159
+ {
2160
+ "epoch": 1.3198198198198199,
2161
+ "grad_norm": 7.692021369934082,
2162
+ "learning_rate": 4.895884879622216e-06,
2163
+ "loss": 0.5617,
2164
+ "step": 301
2165
+ },
2166
+ {
2167
+ "epoch": 1.3243243243243243,
2168
+ "grad_norm": 4.152243614196777,
2169
+ "learning_rate": 4.83377143616607e-06,
2170
+ "loss": 0.2358,
2171
+ "step": 302
2172
+ },
2173
+ {
2174
+ "epoch": 1.3288288288288288,
2175
+ "grad_norm": 6.799951553344727,
2176
+ "learning_rate": 4.771928695047653e-06,
2177
+ "loss": 0.3526,
2178
+ "step": 303
2179
+ },
2180
+ {
2181
+ "epoch": 1.3333333333333333,
2182
+ "grad_norm": 4.947359085083008,
2183
+ "learning_rate": 4.710359896730379e-06,
2184
+ "loss": 0.3928,
2185
+ "step": 304
2186
+ },
2187
+ {
2188
+ "epoch": 1.3378378378378377,
2189
+ "grad_norm": 6.709052562713623,
2190
+ "learning_rate": 4.649068267323465e-06,
2191
+ "loss": 0.6301,
2192
+ "step": 305
2193
+ },
2194
+ {
2195
+ "epoch": 1.3423423423423424,
2196
+ "grad_norm": 6.307892799377441,
2197
+ "learning_rate": 4.588057018412922e-06,
2198
+ "loss": 0.4378,
2199
+ "step": 306
2200
+ },
2201
+ {
2202
+ "epoch": 1.3468468468468469,
2203
+ "grad_norm": 7.695209980010986,
2204
+ "learning_rate": 4.527329346893259e-06,
2205
+ "loss": 0.6796,
2206
+ "step": 307
2207
+ },
2208
+ {
2209
+ "epoch": 1.3513513513513513,
2210
+ "grad_norm": 6.152185916900635,
2211
+ "learning_rate": 4.466888434799959e-06,
2212
+ "loss": 0.3891,
2213
+ "step": 308
2214
+ },
2215
+ {
2216
+ "epoch": 1.3558558558558558,
2217
+ "grad_norm": 4.046474456787109,
2218
+ "learning_rate": 4.406737449142769e-06,
2219
+ "loss": 0.4294,
2220
+ "step": 309
2221
+ },
2222
+ {
2223
+ "epoch": 1.3603603603603602,
2224
+ "grad_norm": 5.958534240722656,
2225
+ "learning_rate": 4.34687954173974e-06,
2226
+ "loss": 0.4479,
2227
+ "step": 310
2228
+ },
2229
+ {
2230
+ "epoch": 1.364864864864865,
2231
+ "grad_norm": 8.716999053955078,
2232
+ "learning_rate": 4.287317849052075e-06,
2233
+ "loss": 0.3639,
2234
+ "step": 311
2235
+ },
2236
+ {
2237
+ "epoch": 1.3693693693693694,
2238
+ "grad_norm": 8.074333190917969,
2239
+ "learning_rate": 4.228055492019794e-06,
2240
+ "loss": 0.4478,
2241
+ "step": 312
2242
+ },
2243
+ {
2244
+ "epoch": 1.3738738738738738,
2245
+ "grad_norm": 12.057003021240234,
2246
+ "learning_rate": 4.169095575898181e-06,
2247
+ "loss": 0.4312,
2248
+ "step": 313
2249
+ },
2250
+ {
2251
+ "epoch": 1.3783783783783785,
2252
+ "grad_norm": 5.945882797241211,
2253
+ "learning_rate": 4.110441190095102e-06,
2254
+ "loss": 0.3519,
2255
+ "step": 314
2256
+ },
2257
+ {
2258
+ "epoch": 1.3828828828828827,
2259
+ "grad_norm": 6.729231357574463,
2260
+ "learning_rate": 4.0520954080090954e-06,
2261
+ "loss": 0.6728,
2262
+ "step": 315
2263
+ },
2264
+ {
2265
+ "epoch": 1.3873873873873874,
2266
+ "grad_norm": 5.043709754943848,
2267
+ "learning_rate": 3.994061286868361e-06,
2268
+ "loss": 0.4016,
2269
+ "step": 316
2270
+ },
2271
+ {
2272
+ "epoch": 1.3918918918918919,
2273
+ "grad_norm": 6.180406093597412,
2274
+ "learning_rate": 3.936341867570534e-06,
2275
+ "loss": 0.4705,
2276
+ "step": 317
2277
+ },
2278
+ {
2279
+ "epoch": 1.3963963963963963,
2280
+ "grad_norm": 5.179868698120117,
2281
+ "learning_rate": 3.878940174523371e-06,
2282
+ "loss": 0.5061,
2283
+ "step": 318
2284
+ },
2285
+ {
2286
+ "epoch": 1.400900900900901,
2287
+ "grad_norm": 6.802118301391602,
2288
+ "learning_rate": 3.821859215486275e-06,
2289
+ "loss": 0.437,
2290
+ "step": 319
2291
+ },
2292
+ {
2293
+ "epoch": 1.4054054054054055,
2294
+ "grad_norm": 19.907636642456055,
2295
+ "learning_rate": 3.7651019814126656e-06,
2296
+ "loss": 0.549,
2297
+ "step": 320
2298
+ },
2299
+ {
2300
+ "epoch": 1.40990990990991,
2301
+ "grad_norm": 4.293713569641113,
2302
+ "learning_rate": 3.7086714462933005e-06,
2303
+ "loss": 0.5374,
2304
+ "step": 321
2305
+ },
2306
+ {
2307
+ "epoch": 1.4144144144144144,
2308
+ "grad_norm": 8.800954818725586,
2309
+ "learning_rate": 3.652570567000402e-06,
2310
+ "loss": 0.5221,
2311
+ "step": 322
2312
+ },
2313
+ {
2314
+ "epoch": 1.4189189189189189,
2315
+ "grad_norm": 6.786999702453613,
2316
+ "learning_rate": 3.5968022831327508e-06,
2317
+ "loss": 0.3571,
2318
+ "step": 323
2319
+ },
2320
+ {
2321
+ "epoch": 1.4234234234234235,
2322
+ "grad_norm": 5.38525390625,
2323
+ "learning_rate": 3.541369516861648e-06,
2324
+ "loss": 0.3992,
2325
+ "step": 324
2326
+ },
2327
+ {
2328
+ "epoch": 1.427927927927928,
2329
+ "grad_norm": 5.08693265914917,
2330
+ "learning_rate": 3.48627517277778e-06,
2331
+ "loss": 0.2466,
2332
+ "step": 325
2333
+ },
2334
+ {
2335
+ "epoch": 1.4324324324324325,
2336
+ "grad_norm": 9.072467803955078,
2337
+ "learning_rate": 3.4315221377390496e-06,
2338
+ "loss": 0.3921,
2339
+ "step": 326
2340
+ },
2341
+ {
2342
+ "epoch": 1.436936936936937,
2343
+ "grad_norm": 9.078206062316895,
2344
+ "learning_rate": 3.3771132807192954e-06,
2345
+ "loss": 0.6601,
2346
+ "step": 327
2347
+ },
2348
+ {
2349
+ "epoch": 1.4414414414414414,
2350
+ "grad_norm": 6.75455904006958,
2351
+ "learning_rate": 3.3230514526579617e-06,
2352
+ "loss": 0.2954,
2353
+ "step": 328
2354
+ },
2355
+ {
2356
+ "epoch": 1.445945945945946,
2357
+ "grad_norm": 9.443964958190918,
2358
+ "learning_rate": 3.269339486310711e-06,
2359
+ "loss": 0.4426,
2360
+ "step": 329
2361
+ },
2362
+ {
2363
+ "epoch": 1.4504504504504505,
2364
+ "grad_norm": 7.443724632263184,
2365
+ "learning_rate": 3.215980196101002e-06,
2366
+ "loss": 0.5569,
2367
+ "step": 330
2368
+ },
2369
+ {
2370
+ "epoch": 1.454954954954955,
2371
+ "grad_norm": 6.184237003326416,
2372
+ "learning_rate": 3.1629763779726143e-06,
2373
+ "loss": 0.4716,
2374
+ "step": 331
2375
+ },
2376
+ {
2377
+ "epoch": 1.4594594594594594,
2378
+ "grad_norm": 4.803828716278076,
2379
+ "learning_rate": 3.110330809243134e-06,
2380
+ "loss": 0.2991,
2381
+ "step": 332
2382
+ },
2383
+ {
2384
+ "epoch": 1.4639639639639639,
2385
+ "grad_norm": 6.429229736328125,
2386
+ "learning_rate": 3.0580462484584462e-06,
2387
+ "loss": 0.548,
2388
+ "step": 333
2389
+ },
2390
+ {
2391
+ "epoch": 1.4684684684684686,
2392
+ "grad_norm": 8.601090431213379,
2393
+ "learning_rate": 3.0061254352481806e-06,
2394
+ "loss": 0.3895,
2395
+ "step": 334
2396
+ },
2397
+ {
2398
+ "epoch": 1.472972972972973,
2399
+ "grad_norm": 6.159488201141357,
2400
+ "learning_rate": 2.954571090182149e-06,
2401
+ "loss": 0.4045,
2402
+ "step": 335
2403
+ },
2404
+ {
2405
+ "epoch": 1.4774774774774775,
2406
+ "grad_norm": 4.915952205657959,
2407
+ "learning_rate": 2.90338591462782e-06,
2408
+ "loss": 0.5391,
2409
+ "step": 336
2410
+ },
2411
+ {
2412
+ "epoch": 1.4774774774774775,
2413
+ "eval_loss": 0.7116559147834778,
2414
+ "eval_runtime": 177.4066,
2415
+ "eval_samples_per_second": 9.16,
2416
+ "eval_steps_per_second": 1.15,
2417
+ "step": 336
2418
+ },
2419
+ {
2420
+ "epoch": 1.481981981981982,
2421
+ "grad_norm": 4.157137393951416,
2422
+ "learning_rate": 2.8525725906087354e-06,
2423
+ "loss": 0.3774,
2424
+ "step": 337
2425
+ },
2426
+ {
2427
+ "epoch": 1.4864864864864864,
2428
+ "grad_norm": 4.249359130859375,
2429
+ "learning_rate": 2.8021337806640137e-06,
2430
+ "loss": 0.4709,
2431
+ "step": 338
2432
+ },
2433
+ {
2434
+ "epoch": 1.490990990990991,
2435
+ "grad_norm": 6.608872413635254,
2436
+ "learning_rate": 2.7520721277088023e-06,
2437
+ "loss": 0.5008,
2438
+ "step": 339
2439
+ },
2440
+ {
2441
+ "epoch": 1.4954954954954955,
2442
+ "grad_norm": 4.429202079772949,
2443
+ "learning_rate": 2.7023902548958193e-06,
2444
+ "loss": 0.3589,
2445
+ "step": 340
2446
+ },
2447
+ {
2448
+ "epoch": 1.5,
2449
+ "grad_norm": 5.2943902015686035,
2450
+ "learning_rate": 2.653090765477896e-06,
2451
+ "loss": 0.524,
2452
+ "step": 341
2453
+ },
2454
+ {
2455
+ "epoch": 1.5045045045045045,
2456
+ "grad_norm": 5.522627353668213,
2457
+ "learning_rate": 2.6041762426715565e-06,
2458
+ "loss": 0.3548,
2459
+ "step": 342
2460
+ },
2461
+ {
2462
+ "epoch": 1.509009009009009,
2463
+ "grad_norm": 5.750497341156006,
2464
+ "learning_rate": 2.5556492495216867e-06,
2465
+ "loss": 0.5341,
2466
+ "step": 343
2467
+ },
2468
+ {
2469
+ "epoch": 1.5135135135135136,
2470
+ "grad_norm": 4.218414306640625,
2471
+ "learning_rate": 2.5075123287672174e-06,
2472
+ "loss": 0.1714,
2473
+ "step": 344
2474
+ },
2475
+ {
2476
+ "epoch": 1.518018018018018,
2477
+ "grad_norm": 6.593997955322266,
2478
+ "learning_rate": 2.4597680027078874e-06,
2479
+ "loss": 0.4605,
2480
+ "step": 345
2481
+ },
2482
+ {
2483
+ "epoch": 1.5225225225225225,
2484
+ "grad_norm": 7.52809476852417,
2485
+ "learning_rate": 2.4124187730720916e-06,
2486
+ "loss": 0.251,
2487
+ "step": 346
2488
+ },
2489
+ {
2490
+ "epoch": 1.527027027027027,
2491
+ "grad_norm": 7.195810794830322,
2492
+ "learning_rate": 2.365467120885783e-06,
2493
+ "loss": 0.4982,
2494
+ "step": 347
2495
+ },
2496
+ {
2497
+ "epoch": 1.5315315315315314,
2498
+ "grad_norm": 6.924576759338379,
2499
+ "learning_rate": 2.3189155063424784e-06,
2500
+ "loss": 0.4595,
2501
+ "step": 348
2502
+ },
2503
+ {
2504
+ "epoch": 1.5360360360360361,
2505
+ "grad_norm": 4.178314685821533,
2506
+ "learning_rate": 2.2727663686743382e-06,
2507
+ "loss": 0.2899,
2508
+ "step": 349
2509
+ },
2510
+ {
2511
+ "epoch": 1.5405405405405406,
2512
+ "grad_norm": 4.642699718475342,
2513
+ "learning_rate": 2.2270221260243675e-06,
2514
+ "loss": 0.1253,
2515
+ "step": 350
2516
+ },
2517
+ {
2518
+ "epoch": 1.545045045045045,
2519
+ "grad_norm": 8.187874794006348,
2520
+ "learning_rate": 2.1816851753197023e-06,
2521
+ "loss": 0.4612,
2522
+ "step": 351
2523
+ },
2524
+ {
2525
+ "epoch": 1.5495495495495497,
2526
+ "grad_norm": 5.853338718414307,
2527
+ "learning_rate": 2.1367578921460075e-06,
2528
+ "loss": 0.3895,
2529
+ "step": 352
2530
+ },
2531
+ {
2532
+ "epoch": 1.554054054054054,
2533
+ "grad_norm": 4.953735828399658,
2534
+ "learning_rate": 2.092242630623016e-06,
2535
+ "loss": 0.4528,
2536
+ "step": 353
2537
+ },
2538
+ {
2539
+ "epoch": 1.5585585585585586,
2540
+ "grad_norm": 7.307708263397217,
2541
+ "learning_rate": 2.0481417232811575e-06,
2542
+ "loss": 0.4046,
2543
+ "step": 354
2544
+ },
2545
+ {
2546
+ "epoch": 1.563063063063063,
2547
+ "grad_norm": 6.422986030578613,
2548
+ "learning_rate": 2.004457480939355e-06,
2549
+ "loss": 0.3708,
2550
+ "step": 355
2551
+ },
2552
+ {
2553
+ "epoch": 1.5675675675675675,
2554
+ "grad_norm": 6.175309181213379,
2555
+ "learning_rate": 1.961192192583934e-06,
2556
+ "loss": 0.5432,
2557
+ "step": 356
2558
+ },
2559
+ {
2560
+ "epoch": 1.5720720720720722,
2561
+ "grad_norm": 4.025996685028076,
2562
+ "learning_rate": 1.918348125248677e-06,
2563
+ "loss": 0.2745,
2564
+ "step": 357
2565
+ },
2566
+ {
2567
+ "epoch": 1.5765765765765765,
2568
+ "grad_norm": 4.922974109649658,
2569
+ "learning_rate": 1.8759275238960473e-06,
2570
+ "loss": 0.3692,
2571
+ "step": 358
2572
+ },
2573
+ {
2574
+ "epoch": 1.5810810810810811,
2575
+ "grad_norm": 4.9051032066345215,
2576
+ "learning_rate": 1.8339326112995426e-06,
2577
+ "loss": 0.3061,
2578
+ "step": 359
2579
+ },
2580
+ {
2581
+ "epoch": 1.5855855855855856,
2582
+ "grad_norm": 7.265330791473389,
2583
+ "learning_rate": 1.7923655879272395e-06,
2584
+ "loss": 0.543,
2585
+ "step": 360
2586
+ },
2587
+ {
2588
+ "epoch": 1.59009009009009,
2589
+ "grad_norm": 10.32652473449707,
2590
+ "learning_rate": 1.7512286318264783e-06,
2591
+ "loss": 0.4476,
2592
+ "step": 361
2593
+ },
2594
+ {
2595
+ "epoch": 1.5945945945945947,
2596
+ "grad_norm": 7.651137351989746,
2597
+ "learning_rate": 1.7105238985097472e-06,
2598
+ "loss": 0.2927,
2599
+ "step": 362
2600
+ },
2601
+ {
2602
+ "epoch": 1.599099099099099,
2603
+ "grad_norm": 5.687959671020508,
2604
+ "learning_rate": 1.6702535208417348e-06,
2605
+ "loss": 0.4765,
2606
+ "step": 363
2607
+ },
2608
+ {
2609
+ "epoch": 1.6036036036036037,
2610
+ "grad_norm": 7.388071537017822,
2611
+ "learning_rate": 1.630419608927566e-06,
2612
+ "loss": 0.5267,
2613
+ "step": 364
2614
+ },
2615
+ {
2616
+ "epoch": 1.6081081081081081,
2617
+ "grad_norm": 8.331589698791504,
2618
+ "learning_rate": 1.5910242500022433e-06,
2619
+ "loss": 0.5056,
2620
+ "step": 365
2621
+ },
2622
+ {
2623
+ "epoch": 1.6126126126126126,
2624
+ "grad_norm": 5.013023376464844,
2625
+ "learning_rate": 1.5520695083212678e-06,
2626
+ "loss": 0.254,
2627
+ "step": 366
2628
+ },
2629
+ {
2630
+ "epoch": 1.6171171171171173,
2631
+ "grad_norm": 5.669906139373779,
2632
+ "learning_rate": 1.5135574250524898e-06,
2633
+ "loss": 0.4575,
2634
+ "step": 367
2635
+ },
2636
+ {
2637
+ "epoch": 1.6216216216216215,
2638
+ "grad_norm": 4.581337928771973,
2639
+ "learning_rate": 1.4754900181691467e-06,
2640
+ "loss": 0.3603,
2641
+ "step": 368
2642
+ },
2643
+ {
2644
+ "epoch": 1.6261261261261262,
2645
+ "grad_norm": 5.660158634185791,
2646
+ "learning_rate": 1.4378692823441209e-06,
2647
+ "loss": 0.321,
2648
+ "step": 369
2649
+ },
2650
+ {
2651
+ "epoch": 1.6306306306306306,
2652
+ "grad_norm": 11.152261734008789,
2653
+ "learning_rate": 1.4006971888454324e-06,
2654
+ "loss": 0.4755,
2655
+ "step": 370
2656
+ },
2657
+ {
2658
+ "epoch": 1.635135135135135,
2659
+ "grad_norm": 5.952630043029785,
2660
+ "learning_rate": 1.3639756854329333e-06,
2661
+ "loss": 0.262,
2662
+ "step": 371
2663
+ },
2664
+ {
2665
+ "epoch": 1.6396396396396398,
2666
+ "grad_norm": 6.51498556137085,
2667
+ "learning_rate": 1.3277066962562647e-06,
2668
+ "loss": 0.6055,
2669
+ "step": 372
2670
+ },
2671
+ {
2672
+ "epoch": 1.644144144144144,
2673
+ "grad_norm": 10.196480751037598,
2674
+ "learning_rate": 1.2918921217540226e-06,
2675
+ "loss": 0.4316,
2676
+ "step": 373
2677
+ },
2678
+ {
2679
+ "epoch": 1.6486486486486487,
2680
+ "grad_norm": 6.058411598205566,
2681
+ "learning_rate": 1.2565338385541792e-06,
2682
+ "loss": 0.5043,
2683
+ "step": 374
2684
+ },
2685
+ {
2686
+ "epoch": 1.6531531531531531,
2687
+ "grad_norm": 8.228148460388184,
2688
+ "learning_rate": 1.2216336993757561e-06,
2689
+ "loss": 0.4216,
2690
+ "step": 375
2691
+ },
2692
+ {
2693
+ "epoch": 1.6576576576576576,
2694
+ "grad_norm": 3.8451309204101562,
2695
+ "learning_rate": 1.1871935329317363e-06,
2696
+ "loss": 0.2803,
2697
+ "step": 376
2698
+ },
2699
+ {
2700
+ "epoch": 1.6621621621621623,
2701
+ "grad_norm": 7.231492042541504,
2702
+ "learning_rate": 1.1532151438332551e-06,
2703
+ "loss": 0.3277,
2704
+ "step": 377
2705
+ },
2706
+ {
2707
+ "epoch": 1.6666666666666665,
2708
+ "grad_norm": 5.2547502517700195,
2709
+ "learning_rate": 1.1197003124950223e-06,
2710
+ "loss": 0.3188,
2711
+ "step": 378
2712
+ },
2713
+ {
2714
+ "epoch": 1.6711711711711712,
2715
+ "grad_norm": 7.146738052368164,
2716
+ "learning_rate": 1.0866507950420525e-06,
2717
+ "loss": 0.5312,
2718
+ "step": 379
2719
+ },
2720
+ {
2721
+ "epoch": 1.6756756756756757,
2722
+ "grad_norm": 13.643159866333008,
2723
+ "learning_rate": 1.0540683232176307e-06,
2724
+ "loss": 0.4993,
2725
+ "step": 380
2726
+ },
2727
+ {
2728
+ "epoch": 1.6801801801801801,
2729
+ "grad_norm": 4.724654674530029,
2730
+ "learning_rate": 1.0219546042925842e-06,
2731
+ "loss": 0.3137,
2732
+ "step": 381
2733
+ },
2734
+ {
2735
+ "epoch": 1.6846846846846848,
2736
+ "grad_norm": 7.496217250823975,
2737
+ "learning_rate": 9.903113209758098e-07,
2738
+ "loss": 0.262,
2739
+ "step": 382
2740
+ },
2741
+ {
2742
+ "epoch": 1.689189189189189,
2743
+ "grad_norm": 4.976952075958252,
2744
+ "learning_rate": 9.591401313261139e-07,
2745
+ "loss": 0.2584,
2746
+ "step": 383
2747
+ },
2748
+ {
2749
+ "epoch": 1.6936936936936937,
2750
+ "grad_norm": 4.605782985687256,
2751
+ "learning_rate": 9.284426686653303e-07,
2752
+ "loss": 0.4567,
2753
+ "step": 384
2754
+ },
2755
+ {
2756
+ "epoch": 1.6981981981981982,
2757
+ "grad_norm": 5.3156561851501465,
2758
+ "learning_rate": 8.98220541492738e-07,
2759
+ "loss": 0.4177,
2760
+ "step": 385
2761
+ },
2762
+ {
2763
+ "epoch": 1.7027027027027026,
2764
+ "grad_norm": 8.66347599029541,
2765
+ "learning_rate": 8.68475333400769e-07,
2766
+ "loss": 0.482,
2767
+ "step": 386
2768
+ },
2769
+ {
2770
+ "epoch": 1.7072072072072073,
2771
+ "grad_norm": 6.3165082931518555,
2772
+ "learning_rate": 8.392086029920443e-07,
2773
+ "loss": 0.4675,
2774
+ "step": 387
2775
+ },
2776
+ {
2777
+ "epoch": 1.7117117117117115,
2778
+ "grad_norm": 5.286152362823486,
2779
+ "learning_rate": 8.10421883797694e-07,
2780
+ "loss": 0.3679,
2781
+ "step": 388
2782
+ },
2783
+ {
2784
+ "epoch": 1.7162162162162162,
2785
+ "grad_norm": 4.9256367683410645,
2786
+ "learning_rate": 7.821166841970107e-07,
2787
+ "loss": 0.437,
2788
+ "step": 389
2789
+ },
2790
+ {
2791
+ "epoch": 1.7207207207207207,
2792
+ "grad_norm": 7.306694984436035,
2793
+ "learning_rate": 7.542944873384106e-07,
2794
+ "loss": 0.5635,
2795
+ "step": 390
2796
+ },
2797
+ {
2798
+ "epoch": 1.7252252252252251,
2799
+ "grad_norm": 10.425533294677734,
2800
+ "learning_rate": 7.269567510617126e-07,
2801
+ "loss": 0.4728,
2802
+ "step": 391
2803
+ },
2804
+ {
2805
+ "epoch": 1.7297297297297298,
2806
+ "grad_norm": 6.2873334884643555,
2807
+ "learning_rate": 7.001049078217614e-07,
2808
+ "loss": 0.5543,
2809
+ "step": 392
2810
+ },
2811
+ {
2812
+ "epoch": 1.7297297297297298,
2813
+ "eval_loss": 0.6970276236534119,
2814
+ "eval_runtime": 176.8992,
2815
+ "eval_samples_per_second": 9.186,
2816
+ "eval_steps_per_second": 1.153,
2817
+ "step": 392
2818
+ },
2819
+ {
2820
+ "epoch": 1.7342342342342343,
2821
+ "grad_norm": 4.78045654296875,
2822
+ "learning_rate": 6.737403646133567e-07,
2823
+ "loss": 0.3715,
2824
+ "step": 393
2825
+ },
2826
+ {
2827
+ "epoch": 1.7387387387387387,
2828
+ "grad_norm": 5.409590244293213,
2829
+ "learning_rate": 6.478645028975372e-07,
2830
+ "loss": 0.2953,
2831
+ "step": 394
2832
+ },
2833
+ {
2834
+ "epoch": 1.7432432432432432,
2835
+ "grad_norm": 5.208950519561768,
2836
+ "learning_rate": 6.22478678529197e-07,
2837
+ "loss": 0.3446,
2838
+ "step": 395
2839
+ },
2840
+ {
2841
+ "epoch": 1.7477477477477477,
2842
+ "grad_norm": 5.461174011230469,
2843
+ "learning_rate": 5.975842216860239e-07,
2844
+ "loss": 0.3399,
2845
+ "step": 396
2846
+ },
2847
+ {
2848
+ "epoch": 1.7522522522522523,
2849
+ "grad_norm": 5.419333457946777,
2850
+ "learning_rate": 5.731824367988259e-07,
2851
+ "loss": 0.3556,
2852
+ "step": 397
2853
+ },
2854
+ {
2855
+ "epoch": 1.7567567567567568,
2856
+ "grad_norm": 9.81429672241211,
2857
+ "learning_rate": 5.492746024831541e-07,
2858
+ "loss": 0.3397,
2859
+ "step": 398
2860
+ },
2861
+ {
2862
+ "epoch": 1.7612612612612613,
2863
+ "grad_norm": 4.5039849281311035,
2864
+ "learning_rate": 5.258619714723278e-07,
2865
+ "loss": 0.357,
2866
+ "step": 399
2867
+ },
2868
+ {
2869
+ "epoch": 1.7657657657657657,
2870
+ "grad_norm": 5.249424934387207,
2871
+ "learning_rate": 5.029457705517793e-07,
2872
+ "loss": 0.3679,
2873
+ "step": 400
2874
+ },
2875
+ {
2876
+ "epoch": 1.7702702702702702,
2877
+ "grad_norm": 4.992920398712158,
2878
+ "learning_rate": 4.805272004947781e-07,
2879
+ "loss": 0.3676,
2880
+ "step": 401
2881
+ },
2882
+ {
2883
+ "epoch": 1.7747747747747749,
2884
+ "grad_norm": 7.499919414520264,
2885
+ "learning_rate": 4.5860743599951186e-07,
2886
+ "loss": 0.5091,
2887
+ "step": 402
2888
+ },
2889
+ {
2890
+ "epoch": 1.7792792792792793,
2891
+ "grad_norm": 5.496927738189697,
2892
+ "learning_rate": 4.371876256275287e-07,
2893
+ "loss": 0.4257,
2894
+ "step": 403
2895
+ },
2896
+ {
2897
+ "epoch": 1.7837837837837838,
2898
+ "grad_norm": 4.664565563201904,
2899
+ "learning_rate": 4.162688917435631e-07,
2900
+ "loss": 0.3542,
2901
+ "step": 404
2902
+ },
2903
+ {
2904
+ "epoch": 1.7882882882882885,
2905
+ "grad_norm": 5.523669719696045,
2906
+ "learning_rate": 3.9585233045671743e-07,
2907
+ "loss": 0.4135,
2908
+ "step": 405
2909
+ },
2910
+ {
2911
+ "epoch": 1.7927927927927927,
2912
+ "grad_norm": 5.046310901641846,
2913
+ "learning_rate": 3.759390115630357e-07,
2914
+ "loss": 0.35,
2915
+ "step": 406
2916
+ },
2917
+ {
2918
+ "epoch": 1.7972972972972974,
2919
+ "grad_norm": 5.559905529022217,
2920
+ "learning_rate": 3.565299784894427e-07,
2921
+ "loss": 0.3861,
2922
+ "step": 407
2923
+ },
2924
+ {
2925
+ "epoch": 1.8018018018018018,
2926
+ "grad_norm": 6.247352600097656,
2927
+ "learning_rate": 3.3762624823906577e-07,
2928
+ "loss": 0.3957,
2929
+ "step": 408
2930
+ },
2931
+ {
2932
+ "epoch": 1.8063063063063063,
2933
+ "grad_norm": 3.7196853160858154,
2934
+ "learning_rate": 3.1922881133795827e-07,
2935
+ "loss": 0.25,
2936
+ "step": 409
2937
+ },
2938
+ {
2939
+ "epoch": 1.810810810810811,
2940
+ "grad_norm": 7.223121643066406,
2941
+ "learning_rate": 3.0133863178318237e-07,
2942
+ "loss": 0.3527,
2943
+ "step": 410
2944
+ },
2945
+ {
2946
+ "epoch": 1.8153153153153152,
2947
+ "grad_norm": 7.171990871429443,
2948
+ "learning_rate": 2.839566469923105e-07,
2949
+ "loss": 0.5896,
2950
+ "step": 411
2951
+ },
2952
+ {
2953
+ "epoch": 1.8198198198198199,
2954
+ "grad_norm": 4.478882312774658,
2955
+ "learning_rate": 2.6708376775430035e-07,
2956
+ "loss": 0.3571,
2957
+ "step": 412
2958
+ },
2959
+ {
2960
+ "epoch": 1.8243243243243243,
2961
+ "grad_norm": 5.6608757972717285,
2962
+ "learning_rate": 2.507208781817638e-07,
2963
+ "loss": 0.4026,
2964
+ "step": 413
2965
+ },
2966
+ {
2967
+ "epoch": 1.8288288288288288,
2968
+ "grad_norm": 6.219975471496582,
2969
+ "learning_rate": 2.348688356646578e-07,
2970
+ "loss": 0.587,
2971
+ "step": 414
2972
+ },
2973
+ {
2974
+ "epoch": 1.8333333333333335,
2975
+ "grad_norm": 5.211012840270996,
2976
+ "learning_rate": 2.1952847082533868e-07,
2977
+ "loss": 0.3426,
2978
+ "step": 415
2979
+ },
2980
+ {
2981
+ "epoch": 1.8378378378378377,
2982
+ "grad_norm": 6.536632537841797,
2983
+ "learning_rate": 2.0470058747505516e-07,
2984
+ "loss": 0.5444,
2985
+ "step": 416
2986
+ },
2987
+ {
2988
+ "epoch": 1.8423423423423424,
2989
+ "grad_norm": 4.671348571777344,
2990
+ "learning_rate": 1.9038596257182185e-07,
2991
+ "loss": 0.3379,
2992
+ "step": 417
2993
+ },
2994
+ {
2995
+ "epoch": 1.8468468468468469,
2996
+ "grad_norm": 5.941648483276367,
2997
+ "learning_rate": 1.765853461797107e-07,
2998
+ "loss": 0.3836,
2999
+ "step": 418
3000
+ },
3001
+ {
3002
+ "epoch": 1.8513513513513513,
3003
+ "grad_norm": 4.831808090209961,
3004
+ "learning_rate": 1.6329946142954355e-07,
3005
+ "loss": 0.2659,
3006
+ "step": 419
3007
+ },
3008
+ {
3009
+ "epoch": 1.855855855855856,
3010
+ "grad_norm": 6.753133296966553,
3011
+ "learning_rate": 1.5052900448100815e-07,
3012
+ "loss": 0.4657,
3013
+ "step": 420
3014
+ },
3015
+ {
3016
+ "epoch": 1.8603603603603602,
3017
+ "grad_norm": 5.005588054656982,
3018
+ "learning_rate": 1.382746444861771e-07,
3019
+ "loss": 0.3396,
3020
+ "step": 421
3021
+ },
3022
+ {
3023
+ "epoch": 1.864864864864865,
3024
+ "grad_norm": 9.87230396270752,
3025
+ "learning_rate": 1.2653702355444608e-07,
3026
+ "loss": 0.52,
3027
+ "step": 422
3028
+ },
3029
+ {
3030
+ "epoch": 1.8693693693693694,
3031
+ "grad_norm": 6.92303466796875,
3032
+ "learning_rate": 1.1531675671888621e-07,
3033
+ "loss": 0.3074,
3034
+ "step": 423
3035
+ },
3036
+ {
3037
+ "epoch": 1.8738738738738738,
3038
+ "grad_norm": 7.144577503204346,
3039
+ "learning_rate": 1.0461443190402098e-07,
3040
+ "loss": 0.3671,
3041
+ "step": 424
3042
+ },
3043
+ {
3044
+ "epoch": 1.8783783783783785,
3045
+ "grad_norm": 6.0537028312683105,
3046
+ "learning_rate": 9.443060989501651e-08,
3047
+ "loss": 0.4349,
3048
+ "step": 425
3049
+ },
3050
+ {
3051
+ "epoch": 1.8828828828828827,
3052
+ "grad_norm": 7.686923503875732,
3053
+ "learning_rate": 8.476582430830049e-08,
3054
+ "loss": 0.3669,
3055
+ "step": 426
3056
+ },
3057
+ {
3058
+ "epoch": 1.8873873873873874,
3059
+ "grad_norm": 5.918185234069824,
3060
+ "learning_rate": 7.562058156359686e-08,
3061
+ "loss": 0.3818,
3062
+ "step": 427
3063
+ },
3064
+ {
3065
+ "epoch": 1.8918918918918919,
3066
+ "grad_norm": 5.703508377075195,
3067
+ "learning_rate": 6.699536085739589e-08,
3068
+ "loss": 0.4104,
3069
+ "step": 428
3070
+ },
3071
+ {
3072
+ "epoch": 1.8963963963963963,
3073
+ "grad_norm": 5.9672040939331055,
3074
+ "learning_rate": 5.889061413784092e-08,
3075
+ "loss": 0.3871,
3076
+ "step": 429
3077
+ },
3078
+ {
3079
+ "epoch": 1.900900900900901,
3080
+ "grad_norm": 7.508155345916748,
3081
+ "learning_rate": 5.1306766081048456e-08,
3082
+ "loss": 0.4733,
3083
+ "step": 430
3084
+ },
3085
+ {
3086
+ "epoch": 1.9054054054054053,
3087
+ "grad_norm": 10.046340942382812,
3088
+ "learning_rate": 4.424421406885704e-08,
3089
+ "loss": 0.361,
3090
+ "step": 431
3091
+ },
3092
+ {
3093
+ "epoch": 1.90990990990991,
3094
+ "grad_norm": 6.767731666564941,
3095
+ "learning_rate": 3.7703328167999485e-08,
3096
+ "loss": 0.2985,
3097
+ "step": 432
3098
+ },
3099
+ {
3100
+ "epoch": 1.9144144144144144,
3101
+ "grad_norm": 6.296059608459473,
3102
+ "learning_rate": 3.16844511107206e-08,
3103
+ "loss": 0.4861,
3104
+ "step": 433
3105
+ },
3106
+ {
3107
+ "epoch": 1.9189189189189189,
3108
+ "grad_norm": 13.80888557434082,
3109
+ "learning_rate": 2.6187898276813785e-08,
3110
+ "loss": 0.4462,
3111
+ "step": 434
3112
+ },
3113
+ {
3114
+ "epoch": 1.9234234234234235,
3115
+ "grad_norm": 5.754329681396484,
3116
+ "learning_rate": 2.121395767709089e-08,
3117
+ "loss": 0.5155,
3118
+ "step": 435
3119
+ },
3120
+ {
3121
+ "epoch": 1.9279279279279278,
3122
+ "grad_norm": 6.89099645614624,
3123
+ "learning_rate": 1.6762889938303216e-08,
3124
+ "loss": 0.3796,
3125
+ "step": 436
3126
+ },
3127
+ {
3128
+ "epoch": 1.9324324324324325,
3129
+ "grad_norm": 6.652087211608887,
3130
+ "learning_rate": 1.2834928289472415e-08,
3131
+ "loss": 0.4463,
3132
+ "step": 437
3133
+ },
3134
+ {
3135
+ "epoch": 1.936936936936937,
3136
+ "grad_norm": 5.476640224456787,
3137
+ "learning_rate": 9.430278549675819e-09,
3138
+ "loss": 0.3736,
3139
+ "step": 438
3140
+ },
3141
+ {
3142
+ "epoch": 1.9414414414414414,
3143
+ "grad_norm": 6.45073938369751,
3144
+ "learning_rate": 6.549119117263969e-09,
3145
+ "loss": 0.3385,
3146
+ "step": 439
3147
+ },
3148
+ {
3149
+ "epoch": 1.945945945945946,
3150
+ "grad_norm": 5.402563095092773,
3151
+ "learning_rate": 4.1916009605058594e-09,
3152
+ "loss": 0.328,
3153
+ "step": 440
3154
+ },
3155
+ {
3156
+ "epoch": 1.9504504504504503,
3157
+ "grad_norm": 5.578840255737305,
3158
+ "learning_rate": 2.357847609686381e-09,
3159
+ "loss": 0.4148,
3160
+ "step": 441
3161
+ },
3162
+ {
3163
+ "epoch": 1.954954954954955,
3164
+ "grad_norm": 3.9637973308563232,
3165
+ "learning_rate": 1.0479551506259456e-09,
3166
+ "loss": 0.3404,
3167
+ "step": 442
3168
+ },
3169
+ {
3170
+ "epoch": 1.9594594594594594,
3171
+ "grad_norm": 7.74646520614624,
3172
+ "learning_rate": 2.6199221965228507e-10,
3173
+ "loss": 0.3663,
3174
+ "step": 443
3175
+ },
3176
+ {
3177
+ "epoch": 1.9639639639639639,
3178
+ "grad_norm": 7.980604648590088,
3179
+ "learning_rate": 0.0,
3180
+ "loss": 0.4843,
3181
+ "step": 444
3182
+ }
3183
+ ],
3184
+ "logging_steps": 1,
3185
+ "max_steps": 444,
3186
+ "num_input_tokens_seen": 0,
3187
+ "num_train_epochs": 2,
3188
+ "save_steps": 111,
3189
+ "stateful_callbacks": {
3190
+ "TrainerControl": {
3191
+ "args": {
3192
+ "should_epoch_stop": false,
3193
+ "should_evaluate": false,
3194
+ "should_log": false,
3195
+ "should_save": true,
3196
+ "should_training_stop": true
3197
+ },
3198
+ "attributes": {}
3199
+ }
3200
+ },
3201
+ "total_flos": 3.422818596248617e+17,
3202
+ "train_batch_size": 1,
3203
+ "trial_name": null,
3204
+ "trial_params": null
3205
+ }