Safetensors
Macedonian
llama
mkd
macedonia
StefanKrsteski commited on
Commit
8511e3c
·
verified ·
1 Parent(s): c5b975a

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/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
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.47.1",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
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": "4.47.1"
12
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2adfa9c309b3a1704ffeea1a4124a4d8668603d1572de247f0ff3552b328c0
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ce0e9cb808a1edc394effba89c923b8cfa0d52f87980cb61bca284756f7d40
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1309fe5f8a66dc2897f81321bc09137f8b48ba51a9c6a485e5dea0650c56582
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d286cd8bfe64ae7ef567c15513d67516d6565ee6e4ccdde625faa9c1162c792f
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0931f57ffc655f2b9e6660cd0424334485b3a7af9b578e03d204b7fd96f2e1
3
+ size 16311826948
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5e18f922d0af74d820247ae97bee506ab412554a58345ddf2558abc94ee3e3
3
+ size 15024
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2dcca6d9741f46592359768ea2212b9321da6408d1fd7d3a80b017bf37f434
3
+ size 15024
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69420ece2c255923c5cbb3c6c9c4a6b9cb38fb57e5d3033c8b7d436a1faf6f13
3
+ size 15024
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f278b40a1e23b88a657c4e5d03afa8dbbbe14dfeb16f6b4beedaece6cdd0b9
3
+ size 15024
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666addf2f939b635066502b98666baa4ec319cf56e62f7c5868255c08f8786a4
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- 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
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,2388 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.000060055551385,
5
+ "eval_steps": 5551,
6
+ "global_step": 16653,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0030027775692515577,
13
+ "grad_norm": 2.078125,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.7987,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.006005555138503115,
20
+ "grad_norm": 1.1015625,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 1.7101,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.009008332707754673,
27
+ "grad_norm": 1.0390625,
28
+ "learning_rate": 6e-06,
29
+ "loss": 1.6477,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.01201111027700623,
34
+ "grad_norm": 1.0,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 1.6007,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.015013887846257788,
41
+ "grad_norm": 1.0078125,
42
+ "learning_rate": 1e-05,
43
+ "loss": 1.5722,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.018016665415509347,
48
+ "grad_norm": 0.99609375,
49
+ "learning_rate": 1.2e-05,
50
+ "loss": 1.5473,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.021019442984760904,
55
+ "grad_norm": 1.046875,
56
+ "learning_rate": 1.4e-05,
57
+ "loss": 1.5214,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.02402222055401246,
62
+ "grad_norm": 1.03125,
63
+ "learning_rate": 1.6000000000000003e-05,
64
+ "loss": 1.5096,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.02702499812326402,
69
+ "grad_norm": 1.015625,
70
+ "learning_rate": 1.8e-05,
71
+ "loss": 1.4854,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.030027775692515576,
76
+ "grad_norm": 1.0234375,
77
+ "learning_rate": 2e-05,
78
+ "loss": 1.4683,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.03303055326176713,
83
+ "grad_norm": 1.34375,
84
+ "learning_rate": 2.2000000000000003e-05,
85
+ "loss": 1.457,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.036033330831018694,
90
+ "grad_norm": 1.015625,
91
+ "learning_rate": 2.4e-05,
92
+ "loss": 1.4353,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.03903610840027025,
97
+ "grad_norm": 1.0703125,
98
+ "learning_rate": 2.6000000000000002e-05,
99
+ "loss": 1.4267,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.04203888596952181,
104
+ "grad_norm": 1.109375,
105
+ "learning_rate": 2.8e-05,
106
+ "loss": 1.4139,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.04504166353877337,
111
+ "grad_norm": 1.015625,
112
+ "learning_rate": 3.0000000000000004e-05,
113
+ "loss": 1.4037,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.04804444110802492,
118
+ "grad_norm": 0.9609375,
119
+ "learning_rate": 3.2000000000000005e-05,
120
+ "loss": 1.3958,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.05104721867727648,
125
+ "grad_norm": 1.25,
126
+ "learning_rate": 3.4e-05,
127
+ "loss": 1.3935,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.05404999624652804,
132
+ "grad_norm": 0.9296875,
133
+ "learning_rate": 3.6e-05,
134
+ "loss": 1.3817,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.0570527738157796,
139
+ "grad_norm": 1.1640625,
140
+ "learning_rate": 3.8e-05,
141
+ "loss": 1.3769,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.06005555138503115,
146
+ "grad_norm": 1.25,
147
+ "learning_rate": 4e-05,
148
+ "loss": 1.3708,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.0630583289542827,
153
+ "grad_norm": 1.0390625,
154
+ "learning_rate": 3.999976352781044e-05,
155
+ "loss": 1.3571,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.06606110652353427,
160
+ "grad_norm": 0.94921875,
161
+ "learning_rate": 3.999905411683367e-05,
162
+ "loss": 1.3645,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.06906388409278583,
167
+ "grad_norm": 0.91796875,
168
+ "learning_rate": 3.999787178384527e-05,
169
+ "loss": 1.357,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.07206666166203739,
174
+ "grad_norm": 0.921875,
175
+ "learning_rate": 3.9996216556804154e-05,
176
+ "loss": 1.3483,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.07506943923128895,
181
+ "grad_norm": 0.84375,
182
+ "learning_rate": 3.9994088474851825e-05,
183
+ "loss": 1.3425,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.0780722168005405,
188
+ "grad_norm": 0.93359375,
189
+ "learning_rate": 3.99914875883115e-05,
190
+ "loss": 1.3297,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.08107499436979206,
195
+ "grad_norm": 0.82421875,
196
+ "learning_rate": 3.998841395868691e-05,
197
+ "loss": 1.3329,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.08407777193904362,
202
+ "grad_norm": 0.875,
203
+ "learning_rate": 3.9984867658660864e-05,
204
+ "loss": 1.3213,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.08708054950829518,
209
+ "grad_norm": 0.7578125,
210
+ "learning_rate": 3.9980848772093476e-05,
211
+ "loss": 1.3202,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.09008332707754674,
216
+ "grad_norm": 0.86328125,
217
+ "learning_rate": 3.997635739402024e-05,
218
+ "loss": 1.3107,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.09308610464679828,
223
+ "grad_norm": 0.76953125,
224
+ "learning_rate": 3.997139363064977e-05,
225
+ "loss": 1.3112,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.09608888221604985,
230
+ "grad_norm": 0.8515625,
231
+ "learning_rate": 3.996595759936126e-05,
232
+ "loss": 1.3043,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.0990916597853014,
237
+ "grad_norm": 0.74609375,
238
+ "learning_rate": 3.996004942870173e-05,
239
+ "loss": 1.3047,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.10209443735455297,
244
+ "grad_norm": 0.79296875,
245
+ "learning_rate": 3.9953669258382974e-05,
246
+ "loss": 1.2993,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.10509721492380451,
251
+ "grad_norm": 0.81640625,
252
+ "learning_rate": 3.994681723927829e-05,
253
+ "loss": 1.2975,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.10809999249305607,
258
+ "grad_norm": 0.765625,
259
+ "learning_rate": 3.993949353341888e-05,
260
+ "loss": 1.2908,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.11110277006230763,
265
+ "grad_norm": 0.76953125,
266
+ "learning_rate": 3.9931698313989994e-05,
267
+ "loss": 1.2879,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.1141055476315592,
272
+ "grad_norm": 0.7734375,
273
+ "learning_rate": 3.992343176532692e-05,
274
+ "loss": 1.2896,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.11710832520081076,
279
+ "grad_norm": 0.84375,
280
+ "learning_rate": 3.9914694082910535e-05,
281
+ "loss": 1.2825,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.1201111027700623,
286
+ "grad_norm": 0.76953125,
287
+ "learning_rate": 3.990548547336272e-05,
288
+ "loss": 1.2782,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.12311388033931386,
293
+ "grad_norm": 0.7421875,
294
+ "learning_rate": 3.98958061544415e-05,
295
+ "loss": 1.2883,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.1261166579085654,
300
+ "grad_norm": 0.8046875,
301
+ "learning_rate": 3.988565635503583e-05,
302
+ "loss": 1.2804,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.12911943547781699,
307
+ "grad_norm": 0.77734375,
308
+ "learning_rate": 3.987503631516024e-05,
309
+ "loss": 1.2734,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.13212221304706853,
314
+ "grad_norm": 0.85546875,
315
+ "learning_rate": 3.986394628594915e-05,
316
+ "loss": 1.2718,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.1351249906163201,
321
+ "grad_norm": 0.75390625,
322
+ "learning_rate": 3.985238652965091e-05,
323
+ "loss": 1.2704,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.13812776818557165,
328
+ "grad_norm": 0.80078125,
329
+ "learning_rate": 3.984035731962159e-05,
330
+ "loss": 1.269,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.1411305457548232,
335
+ "grad_norm": 0.7265625,
336
+ "learning_rate": 3.982785894031857e-05,
337
+ "loss": 1.2739,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.14413332332407477,
342
+ "grad_norm": 0.72265625,
343
+ "learning_rate": 3.981489168729376e-05,
344
+ "loss": 1.2628,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.14713610089332632,
349
+ "grad_norm": 0.8359375,
350
+ "learning_rate": 3.9801455867186624e-05,
351
+ "loss": 1.2562,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.1501388784625779,
356
+ "grad_norm": 0.828125,
357
+ "learning_rate": 3.978755179771695e-05,
358
+ "loss": 1.2799,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.15314165603182944,
363
+ "grad_norm": 0.7578125,
364
+ "learning_rate": 3.9773179807677306e-05,
365
+ "loss": 1.2664,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.156144433601081,
370
+ "grad_norm": 0.7421875,
371
+ "learning_rate": 3.97583402369253e-05,
372
+ "loss": 1.269,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.15914721117033256,
377
+ "grad_norm": 0.69921875,
378
+ "learning_rate": 3.974303343637549e-05,
379
+ "loss": 1.2645,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.1621499887395841,
384
+ "grad_norm": 1.375,
385
+ "learning_rate": 3.9727259767991156e-05,
386
+ "loss": 1.2611,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.16515276630883569,
391
+ "grad_norm": 0.703125,
392
+ "learning_rate": 3.971101960477568e-05,
393
+ "loss": 1.2487,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.16815554387808723,
398
+ "grad_norm": 0.703125,
399
+ "learning_rate": 3.969431333076377e-05,
400
+ "loss": 1.2479,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.17115832144733878,
405
+ "grad_norm": 2352.0,
406
+ "learning_rate": 3.967714134101233e-05,
407
+ "loss": 1.3042,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 0.17416109901659035,
412
+ "grad_norm": 0.79296875,
413
+ "learning_rate": 3.965950404159117e-05,
414
+ "loss": 1.3198,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 0.1771638765858419,
419
+ "grad_norm": 65.5,
420
+ "learning_rate": 3.9641401849573374e-05,
421
+ "loss": 1.3808,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 0.18016665415509348,
426
+ "grad_norm": 1.3203125,
427
+ "learning_rate": 3.962283519302543e-05,
428
+ "loss": 1.2844,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 0.18316943172434502,
433
+ "grad_norm": 0.79296875,
434
+ "learning_rate": 3.9603804510997135e-05,
435
+ "loss": 1.2443,
436
+ "step": 3050
437
+ },
438
+ {
439
+ "epoch": 0.18617220929359657,
440
+ "grad_norm": 0.70703125,
441
+ "learning_rate": 3.9584310253511195e-05,
442
+ "loss": 1.2428,
443
+ "step": 3100
444
+ },
445
+ {
446
+ "epoch": 0.18917498686284814,
447
+ "grad_norm": 0.73046875,
448
+ "learning_rate": 3.9564352881552595e-05,
449
+ "loss": 1.238,
450
+ "step": 3150
451
+ },
452
+ {
453
+ "epoch": 0.1921777644320997,
454
+ "grad_norm": 0.703125,
455
+ "learning_rate": 3.954393286705767e-05,
456
+ "loss": 1.2408,
457
+ "step": 3200
458
+ },
459
+ {
460
+ "epoch": 0.19518054200135124,
461
+ "grad_norm": 0.69921875,
462
+ "learning_rate": 3.952305069290296e-05,
463
+ "loss": 1.2265,
464
+ "step": 3250
465
+ },
466
+ {
467
+ "epoch": 0.1981833195706028,
468
+ "grad_norm": 0.734375,
469
+ "learning_rate": 3.950170685289383e-05,
470
+ "loss": 1.2405,
471
+ "step": 3300
472
+ },
473
+ {
474
+ "epoch": 0.20118609713985436,
475
+ "grad_norm": 0.6796875,
476
+ "learning_rate": 3.9479901851752734e-05,
477
+ "loss": 1.2422,
478
+ "step": 3350
479
+ },
480
+ {
481
+ "epoch": 0.20418887470910593,
482
+ "grad_norm": 0.73828125,
483
+ "learning_rate": 3.9457636205107305e-05,
484
+ "loss": 1.2312,
485
+ "step": 3400
486
+ },
487
+ {
488
+ "epoch": 0.20719165227835748,
489
+ "grad_norm": 0.671875,
490
+ "learning_rate": 3.9434910439478164e-05,
491
+ "loss": 1.2349,
492
+ "step": 3450
493
+ },
494
+ {
495
+ "epoch": 0.21019442984760903,
496
+ "grad_norm": 0.67578125,
497
+ "learning_rate": 3.941172509226647e-05,
498
+ "loss": 1.2284,
499
+ "step": 3500
500
+ },
501
+ {
502
+ "epoch": 0.2131972074168606,
503
+ "grad_norm": 0.6796875,
504
+ "learning_rate": 3.9388080711741194e-05,
505
+ "loss": 1.2326,
506
+ "step": 3550
507
+ },
508
+ {
509
+ "epoch": 0.21619998498611215,
510
+ "grad_norm": 1.265625,
511
+ "learning_rate": 3.9363977857026196e-05,
512
+ "loss": 1.2271,
513
+ "step": 3600
514
+ },
515
+ {
516
+ "epoch": 0.21920276255536372,
517
+ "grad_norm": 0.70703125,
518
+ "learning_rate": 3.933941709808695e-05,
519
+ "loss": 1.2223,
520
+ "step": 3650
521
+ },
522
+ {
523
+ "epoch": 0.22220554012461527,
524
+ "grad_norm": 0.6796875,
525
+ "learning_rate": 3.9314399015717104e-05,
526
+ "loss": 1.2224,
527
+ "step": 3700
528
+ },
529
+ {
530
+ "epoch": 0.22520831769386682,
531
+ "grad_norm": 0.6796875,
532
+ "learning_rate": 3.9288924201524725e-05,
533
+ "loss": 1.2288,
534
+ "step": 3750
535
+ },
536
+ {
537
+ "epoch": 0.2282110952631184,
538
+ "grad_norm": 0.66015625,
539
+ "learning_rate": 3.926299325791832e-05,
540
+ "loss": 1.2223,
541
+ "step": 3800
542
+ },
543
+ {
544
+ "epoch": 0.23121387283236994,
545
+ "grad_norm": 0.6953125,
546
+ "learning_rate": 3.92366067980926e-05,
547
+ "loss": 1.2215,
548
+ "step": 3850
549
+ },
550
+ {
551
+ "epoch": 0.2342166504016215,
552
+ "grad_norm": 0.67578125,
553
+ "learning_rate": 3.920976544601395e-05,
554
+ "loss": 1.2314,
555
+ "step": 3900
556
+ },
557
+ {
558
+ "epoch": 0.23721942797087306,
559
+ "grad_norm": 0.640625,
560
+ "learning_rate": 3.918246983640571e-05,
561
+ "loss": 1.2225,
562
+ "step": 3950
563
+ },
564
+ {
565
+ "epoch": 0.2402222055401246,
566
+ "grad_norm": 0.7109375,
567
+ "learning_rate": 3.915472061473312e-05,
568
+ "loss": 1.2252,
569
+ "step": 4000
570
+ },
571
+ {
572
+ "epoch": 0.24322498310937618,
573
+ "grad_norm": 0.65625,
574
+ "learning_rate": 3.912651843718811e-05,
575
+ "loss": 1.2158,
576
+ "step": 4050
577
+ },
578
+ {
579
+ "epoch": 0.24622776067862773,
580
+ "grad_norm": 0.77734375,
581
+ "learning_rate": 3.909786397067375e-05,
582
+ "loss": 1.2134,
583
+ "step": 4100
584
+ },
585
+ {
586
+ "epoch": 0.2492305382478793,
587
+ "grad_norm": 0.66015625,
588
+ "learning_rate": 3.9068757892788485e-05,
589
+ "loss": 1.215,
590
+ "step": 4150
591
+ },
592
+ {
593
+ "epoch": 0.2522333158171308,
594
+ "grad_norm": 0.6953125,
595
+ "learning_rate": 3.90392008918101e-05,
596
+ "loss": 1.2196,
597
+ "step": 4200
598
+ },
599
+ {
600
+ "epoch": 0.2552360933863824,
601
+ "grad_norm": 0.703125,
602
+ "learning_rate": 3.900919366667948e-05,
603
+ "loss": 1.2115,
604
+ "step": 4250
605
+ },
606
+ {
607
+ "epoch": 0.25823887095563397,
608
+ "grad_norm": 0.6640625,
609
+ "learning_rate": 3.897873692698405e-05,
610
+ "loss": 1.2128,
611
+ "step": 4300
612
+ },
613
+ {
614
+ "epoch": 0.2612416485248855,
615
+ "grad_norm": 0.66015625,
616
+ "learning_rate": 3.894783139294099e-05,
617
+ "loss": 1.2082,
618
+ "step": 4350
619
+ },
620
+ {
621
+ "epoch": 0.26424442609413706,
622
+ "grad_norm": 0.671875,
623
+ "learning_rate": 3.891647779538024e-05,
624
+ "loss": 1.2065,
625
+ "step": 4400
626
+ },
627
+ {
628
+ "epoch": 0.2672472036633886,
629
+ "grad_norm": 0.72265625,
630
+ "learning_rate": 3.8884676875727176e-05,
631
+ "loss": 1.2153,
632
+ "step": 4450
633
+ },
634
+ {
635
+ "epoch": 0.2702499812326402,
636
+ "grad_norm": 0.6328125,
637
+ "learning_rate": 3.885242938598512e-05,
638
+ "loss": 1.2096,
639
+ "step": 4500
640
+ },
641
+ {
642
+ "epoch": 0.27325275880189176,
643
+ "grad_norm": 0.63671875,
644
+ "learning_rate": 3.881973608871753e-05,
645
+ "loss": 1.2085,
646
+ "step": 4550
647
+ },
648
+ {
649
+ "epoch": 0.2762555363711433,
650
+ "grad_norm": 0.67578125,
651
+ "learning_rate": 3.8786597757029934e-05,
652
+ "loss": 1.2135,
653
+ "step": 4600
654
+ },
655
+ {
656
+ "epoch": 0.27925831394039485,
657
+ "grad_norm": 0.625,
658
+ "learning_rate": 3.875301517455175e-05,
659
+ "loss": 1.1995,
660
+ "step": 4650
661
+ },
662
+ {
663
+ "epoch": 0.2822610915096464,
664
+ "grad_norm": 0.7109375,
665
+ "learning_rate": 3.871898913541765e-05,
666
+ "loss": 1.2068,
667
+ "step": 4700
668
+ },
669
+ {
670
+ "epoch": 0.285263869078898,
671
+ "grad_norm": 0.65234375,
672
+ "learning_rate": 3.868452044424881e-05,
673
+ "loss": 1.1967,
674
+ "step": 4750
675
+ },
676
+ {
677
+ "epoch": 0.28826664664814955,
678
+ "grad_norm": 0.69140625,
679
+ "learning_rate": 3.864960991613395e-05,
680
+ "loss": 1.2041,
681
+ "step": 4800
682
+ },
683
+ {
684
+ "epoch": 0.2912694242174011,
685
+ "grad_norm": 0.65234375,
686
+ "learning_rate": 3.861425837660995e-05,
687
+ "loss": 1.2,
688
+ "step": 4850
689
+ },
690
+ {
691
+ "epoch": 0.29427220178665264,
692
+ "grad_norm": 0.6875,
693
+ "learning_rate": 3.8578466661642416e-05,
694
+ "loss": 1.1983,
695
+ "step": 4900
696
+ },
697
+ {
698
+ "epoch": 0.2972749793559042,
699
+ "grad_norm": 0.66015625,
700
+ "learning_rate": 3.854223561760586e-05,
701
+ "loss": 1.2025,
702
+ "step": 4950
703
+ },
704
+ {
705
+ "epoch": 0.3002777569251558,
706
+ "grad_norm": 0.6875,
707
+ "learning_rate": 3.8505566101263724e-05,
708
+ "loss": 1.1885,
709
+ "step": 5000
710
+ },
711
+ {
712
+ "epoch": 0.30328053449440734,
713
+ "grad_norm": 0.69140625,
714
+ "learning_rate": 3.846845897974808e-05,
715
+ "loss": 1.1895,
716
+ "step": 5050
717
+ },
718
+ {
719
+ "epoch": 0.3062833120636589,
720
+ "grad_norm": 0.63671875,
721
+ "learning_rate": 3.843091513053916e-05,
722
+ "loss": 1.2014,
723
+ "step": 5100
724
+ },
725
+ {
726
+ "epoch": 0.30928608963291043,
727
+ "grad_norm": 0.8203125,
728
+ "learning_rate": 3.839293544144459e-05,
729
+ "loss": 1.1987,
730
+ "step": 5150
731
+ },
732
+ {
733
+ "epoch": 0.312288867202162,
734
+ "grad_norm": 0.65625,
735
+ "learning_rate": 3.8354520810578385e-05,
736
+ "loss": 1.1882,
737
+ "step": 5200
738
+ },
739
+ {
740
+ "epoch": 0.3152916447714136,
741
+ "grad_norm": 1.3671875,
742
+ "learning_rate": 3.8315672146339734e-05,
743
+ "loss": 1.1966,
744
+ "step": 5250
745
+ },
746
+ {
747
+ "epoch": 0.31829442234066513,
748
+ "grad_norm": 0.63671875,
749
+ "learning_rate": 3.827639036739152e-05,
750
+ "loss": 1.1935,
751
+ "step": 5300
752
+ },
753
+ {
754
+ "epoch": 0.3212971999099167,
755
+ "grad_norm": 0.64453125,
756
+ "learning_rate": 3.823667640263856e-05,
757
+ "loss": 1.1888,
758
+ "step": 5350
759
+ },
760
+ {
761
+ "epoch": 0.3242999774791682,
762
+ "grad_norm": 0.6484375,
763
+ "learning_rate": 3.819653119120567e-05,
764
+ "loss": 1.1978,
765
+ "step": 5400
766
+ },
767
+ {
768
+ "epoch": 0.32730275504841977,
769
+ "grad_norm": 0.640625,
770
+ "learning_rate": 3.815595568241546e-05,
771
+ "loss": 1.1863,
772
+ "step": 5450
773
+ },
774
+ {
775
+ "epoch": 0.33030553261767137,
776
+ "grad_norm": 0.6484375,
777
+ "learning_rate": 3.8114950835765864e-05,
778
+ "loss": 1.1809,
779
+ "step": 5500
780
+ },
781
+ {
782
+ "epoch": 0.3333083101869229,
783
+ "grad_norm": 0.6328125,
784
+ "learning_rate": 3.807351762090749e-05,
785
+ "loss": 1.1879,
786
+ "step": 5550
787
+ },
788
+ {
789
+ "epoch": 0.3333683657383079,
790
+ "eval_loss": 1.6565828323364258,
791
+ "eval_runtime": 124.2001,
792
+ "eval_samples_per_second": 361.529,
793
+ "eval_steps_per_second": 45.193,
794
+ "step": 5551
795
+ },
796
+ {
797
+ "epoch": 0.33631108775617446,
798
+ "grad_norm": 0.57421875,
799
+ "learning_rate": 3.803165701762061e-05,
800
+ "loss": 1.1935,
801
+ "step": 5600
802
+ },
803
+ {
804
+ "epoch": 0.339313865325426,
805
+ "grad_norm": 0.6875,
806
+ "learning_rate": 3.7989370015792106e-05,
807
+ "loss": 1.188,
808
+ "step": 5650
809
+ },
810
+ {
811
+ "epoch": 0.34231664289467756,
812
+ "grad_norm": 0.71484375,
813
+ "learning_rate": 3.794665761539195e-05,
814
+ "loss": 1.1943,
815
+ "step": 5700
816
+ },
817
+ {
818
+ "epoch": 0.34531942046392916,
819
+ "grad_norm": 0.64453125,
820
+ "learning_rate": 3.790352082644963e-05,
821
+ "loss": 1.1888,
822
+ "step": 5750
823
+ },
824
+ {
825
+ "epoch": 0.3483221980331807,
826
+ "grad_norm": 0.63671875,
827
+ "learning_rate": 3.7859960669030245e-05,
828
+ "loss": 1.1903,
829
+ "step": 5800
830
+ },
831
+ {
832
+ "epoch": 0.35132497560243225,
833
+ "grad_norm": 0.6328125,
834
+ "learning_rate": 3.781597817321037e-05,
835
+ "loss": 1.1747,
836
+ "step": 5850
837
+ },
838
+ {
839
+ "epoch": 0.3543277531716838,
840
+ "grad_norm": 0.61328125,
841
+ "learning_rate": 3.777157437905372e-05,
842
+ "loss": 1.187,
843
+ "step": 5900
844
+ },
845
+ {
846
+ "epoch": 0.35733053074093535,
847
+ "grad_norm": 0.6796875,
848
+ "learning_rate": 3.772675033658653e-05,
849
+ "loss": 1.1805,
850
+ "step": 5950
851
+ },
852
+ {
853
+ "epoch": 0.36033330831018695,
854
+ "grad_norm": 0.66015625,
855
+ "learning_rate": 3.768150710577274e-05,
856
+ "loss": 1.1833,
857
+ "step": 6000
858
+ },
859
+ {
860
+ "epoch": 0.3633360858794385,
861
+ "grad_norm": 0.671875,
862
+ "learning_rate": 3.763584575648896e-05,
863
+ "loss": 1.1835,
864
+ "step": 6050
865
+ },
866
+ {
867
+ "epoch": 0.36633886344869004,
868
+ "grad_norm": 0.66015625,
869
+ "learning_rate": 3.758976736849909e-05,
870
+ "loss": 1.1835,
871
+ "step": 6100
872
+ },
873
+ {
874
+ "epoch": 0.3693416410179416,
875
+ "grad_norm": 0.625,
876
+ "learning_rate": 3.7543273031428876e-05,
877
+ "loss": 1.1838,
878
+ "step": 6150
879
+ },
880
+ {
881
+ "epoch": 0.37234441858719314,
882
+ "grad_norm": 0.62890625,
883
+ "learning_rate": 3.749636384474008e-05,
884
+ "loss": 1.1752,
885
+ "step": 6200
886
+ },
887
+ {
888
+ "epoch": 0.3753471961564447,
889
+ "grad_norm": 0.6328125,
890
+ "learning_rate": 3.7449040917704514e-05,
891
+ "loss": 1.178,
892
+ "step": 6250
893
+ },
894
+ {
895
+ "epoch": 0.3783499737256963,
896
+ "grad_norm": 0.6015625,
897
+ "learning_rate": 3.740130536937778e-05,
898
+ "loss": 1.1728,
899
+ "step": 6300
900
+ },
901
+ {
902
+ "epoch": 0.38135275129494783,
903
+ "grad_norm": 0.6484375,
904
+ "learning_rate": 3.735315832857287e-05,
905
+ "loss": 1.1763,
906
+ "step": 6350
907
+ },
908
+ {
909
+ "epoch": 0.3843555288641994,
910
+ "grad_norm": 0.64453125,
911
+ "learning_rate": 3.730460093383337e-05,
912
+ "loss": 1.1732,
913
+ "step": 6400
914
+ },
915
+ {
916
+ "epoch": 0.3873583064334509,
917
+ "grad_norm": 0.703125,
918
+ "learning_rate": 3.7255634333406645e-05,
919
+ "loss": 1.1801,
920
+ "step": 6450
921
+ },
922
+ {
923
+ "epoch": 0.3903610840027025,
924
+ "grad_norm": 0.59375,
925
+ "learning_rate": 3.720625968521661e-05,
926
+ "loss": 1.1642,
927
+ "step": 6500
928
+ },
929
+ {
930
+ "epoch": 0.3933638615719541,
931
+ "grad_norm": 0.62890625,
932
+ "learning_rate": 3.7156478156836386e-05,
933
+ "loss": 1.1741,
934
+ "step": 6550
935
+ },
936
+ {
937
+ "epoch": 0.3963666391412056,
938
+ "grad_norm": 0.6953125,
939
+ "learning_rate": 3.710629092546067e-05,
940
+ "loss": 1.1713,
941
+ "step": 6600
942
+ },
943
+ {
944
+ "epoch": 0.39936941671045717,
945
+ "grad_norm": 0.61328125,
946
+ "learning_rate": 3.7055699177877904e-05,
947
+ "loss": 1.167,
948
+ "step": 6650
949
+ },
950
+ {
951
+ "epoch": 0.4023721942797087,
952
+ "grad_norm": 0.6015625,
953
+ "learning_rate": 3.700470411044224e-05,
954
+ "loss": 1.1778,
955
+ "step": 6700
956
+ },
957
+ {
958
+ "epoch": 0.40537497184896026,
959
+ "grad_norm": 0.63671875,
960
+ "learning_rate": 3.695330692904519e-05,
961
+ "loss": 1.1683,
962
+ "step": 6750
963
+ },
964
+ {
965
+ "epoch": 0.40837774941821187,
966
+ "grad_norm": 0.57421875,
967
+ "learning_rate": 3.690150884908715e-05,
968
+ "loss": 1.1689,
969
+ "step": 6800
970
+ },
971
+ {
972
+ "epoch": 0.4113805269874634,
973
+ "grad_norm": 0.5859375,
974
+ "learning_rate": 3.6849311095448677e-05,
975
+ "loss": 1.1706,
976
+ "step": 6850
977
+ },
978
+ {
979
+ "epoch": 0.41438330455671496,
980
+ "grad_norm": 0.66796875,
981
+ "learning_rate": 3.6796714902461467e-05,
982
+ "loss": 1.1644,
983
+ "step": 6900
984
+ },
985
+ {
986
+ "epoch": 0.4173860821259665,
987
+ "grad_norm": 0.6328125,
988
+ "learning_rate": 3.674372151387921e-05,
989
+ "loss": 1.1621,
990
+ "step": 6950
991
+ },
992
+ {
993
+ "epoch": 0.42038885969521805,
994
+ "grad_norm": 0.65234375,
995
+ "learning_rate": 3.669033218284818e-05,
996
+ "loss": 1.1681,
997
+ "step": 7000
998
+ },
999
+ {
1000
+ "epoch": 0.42339163726446966,
1001
+ "grad_norm": 0.57421875,
1002
+ "learning_rate": 3.663654817187757e-05,
1003
+ "loss": 1.1588,
1004
+ "step": 7050
1005
+ },
1006
+ {
1007
+ "epoch": 0.4263944148337212,
1008
+ "grad_norm": 0.65625,
1009
+ "learning_rate": 3.658237075280966e-05,
1010
+ "loss": 1.1586,
1011
+ "step": 7100
1012
+ },
1013
+ {
1014
+ "epoch": 0.42939719240297275,
1015
+ "grad_norm": 0.609375,
1016
+ "learning_rate": 3.6527801206789754e-05,
1017
+ "loss": 1.1598,
1018
+ "step": 7150
1019
+ },
1020
+ {
1021
+ "epoch": 0.4323999699722243,
1022
+ "grad_norm": 0.61328125,
1023
+ "learning_rate": 3.6472840824235845e-05,
1024
+ "loss": 1.1598,
1025
+ "step": 7200
1026
+ },
1027
+ {
1028
+ "epoch": 0.43540274754147584,
1029
+ "grad_norm": 0.578125,
1030
+ "learning_rate": 3.641749090480814e-05,
1031
+ "loss": 1.1584,
1032
+ "step": 7250
1033
+ },
1034
+ {
1035
+ "epoch": 0.43840552511072745,
1036
+ "grad_norm": 0.64453125,
1037
+ "learning_rate": 3.636175275737829e-05,
1038
+ "loss": 1.1587,
1039
+ "step": 7300
1040
+ },
1041
+ {
1042
+ "epoch": 0.441408302679979,
1043
+ "grad_norm": 0.58984375,
1044
+ "learning_rate": 3.6305627699998484e-05,
1045
+ "loss": 1.1644,
1046
+ "step": 7350
1047
+ },
1048
+ {
1049
+ "epoch": 0.44441108024923054,
1050
+ "grad_norm": 0.72265625,
1051
+ "learning_rate": 3.624911705987024e-05,
1052
+ "loss": 1.1584,
1053
+ "step": 7400
1054
+ },
1055
+ {
1056
+ "epoch": 0.4474138578184821,
1057
+ "grad_norm": 0.67578125,
1058
+ "learning_rate": 3.619222217331304e-05,
1059
+ "loss": 1.1574,
1060
+ "step": 7450
1061
+ },
1062
+ {
1063
+ "epoch": 0.45041663538773363,
1064
+ "grad_norm": 0.58984375,
1065
+ "learning_rate": 3.613494438573272e-05,
1066
+ "loss": 1.1512,
1067
+ "step": 7500
1068
+ },
1069
+ {
1070
+ "epoch": 0.45341941295698523,
1071
+ "grad_norm": 0.6171875,
1072
+ "learning_rate": 3.6077285051589666e-05,
1073
+ "loss": 1.1588,
1074
+ "step": 7550
1075
+ },
1076
+ {
1077
+ "epoch": 0.4564221905262368,
1078
+ "grad_norm": 0.625,
1079
+ "learning_rate": 3.6019245534366766e-05,
1080
+ "loss": 1.1562,
1081
+ "step": 7600
1082
+ },
1083
+ {
1084
+ "epoch": 0.45942496809548833,
1085
+ "grad_norm": 0.6171875,
1086
+ "learning_rate": 3.596082720653722e-05,
1087
+ "loss": 1.1589,
1088
+ "step": 7650
1089
+ },
1090
+ {
1091
+ "epoch": 0.4624277456647399,
1092
+ "grad_norm": 0.58203125,
1093
+ "learning_rate": 3.590203144953199e-05,
1094
+ "loss": 1.1565,
1095
+ "step": 7700
1096
+ },
1097
+ {
1098
+ "epoch": 0.4654305232339914,
1099
+ "grad_norm": 0.609375,
1100
+ "learning_rate": 3.584285965370722e-05,
1101
+ "loss": 1.1548,
1102
+ "step": 7750
1103
+ },
1104
+ {
1105
+ "epoch": 0.468433300803243,
1106
+ "grad_norm": 0.61328125,
1107
+ "learning_rate": 3.578331321831134e-05,
1108
+ "loss": 1.149,
1109
+ "step": 7800
1110
+ },
1111
+ {
1112
+ "epoch": 0.47143607837249457,
1113
+ "grad_norm": 0.60546875,
1114
+ "learning_rate": 3.572339355145193e-05,
1115
+ "loss": 1.1596,
1116
+ "step": 7850
1117
+ },
1118
+ {
1119
+ "epoch": 0.4744388559417461,
1120
+ "grad_norm": 0.5703125,
1121
+ "learning_rate": 3.5663102070062465e-05,
1122
+ "loss": 1.1582,
1123
+ "step": 7900
1124
+ },
1125
+ {
1126
+ "epoch": 0.47744163351099767,
1127
+ "grad_norm": 0.58984375,
1128
+ "learning_rate": 3.560244019986883e-05,
1129
+ "loss": 1.1474,
1130
+ "step": 7950
1131
+ },
1132
+ {
1133
+ "epoch": 0.4804444110802492,
1134
+ "grad_norm": 0.609375,
1135
+ "learning_rate": 3.554140937535553e-05,
1136
+ "loss": 1.1552,
1137
+ "step": 8000
1138
+ },
1139
+ {
1140
+ "epoch": 0.4834471886495008,
1141
+ "grad_norm": 0.609375,
1142
+ "learning_rate": 3.548001103973185e-05,
1143
+ "loss": 1.1528,
1144
+ "step": 8050
1145
+ },
1146
+ {
1147
+ "epoch": 0.48644996621875236,
1148
+ "grad_norm": 0.625,
1149
+ "learning_rate": 3.541824664489767e-05,
1150
+ "loss": 1.1613,
1151
+ "step": 8100
1152
+ },
1153
+ {
1154
+ "epoch": 0.4894527437880039,
1155
+ "grad_norm": 0.62109375,
1156
+ "learning_rate": 3.5356117651409155e-05,
1157
+ "loss": 1.1443,
1158
+ "step": 8150
1159
+ },
1160
+ {
1161
+ "epoch": 0.49245552135725545,
1162
+ "grad_norm": 0.7109375,
1163
+ "learning_rate": 3.5293625528444224e-05,
1164
+ "loss": 1.1453,
1165
+ "step": 8200
1166
+ },
1167
+ {
1168
+ "epoch": 0.495458298926507,
1169
+ "grad_norm": 0.6015625,
1170
+ "learning_rate": 3.523077175376779e-05,
1171
+ "loss": 1.1494,
1172
+ "step": 8250
1173
+ },
1174
+ {
1175
+ "epoch": 0.4984610764957586,
1176
+ "grad_norm": 0.62890625,
1177
+ "learning_rate": 3.516755781369682e-05,
1178
+ "loss": 1.1484,
1179
+ "step": 8300
1180
+ },
1181
+ {
1182
+ "epoch": 0.5014638540650102,
1183
+ "grad_norm": 0.58203125,
1184
+ "learning_rate": 3.5103985203065206e-05,
1185
+ "loss": 1.1438,
1186
+ "step": 8350
1187
+ },
1188
+ {
1189
+ "epoch": 0.5044666316342616,
1190
+ "grad_norm": 0.61328125,
1191
+ "learning_rate": 3.5040055425188375e-05,
1192
+ "loss": 1.1511,
1193
+ "step": 8400
1194
+ },
1195
+ {
1196
+ "epoch": 0.5074694092035132,
1197
+ "grad_norm": 0.59765625,
1198
+ "learning_rate": 3.49757699918278e-05,
1199
+ "loss": 1.1493,
1200
+ "step": 8450
1201
+ },
1202
+ {
1203
+ "epoch": 0.5104721867727648,
1204
+ "grad_norm": 0.62890625,
1205
+ "learning_rate": 3.491113042315519e-05,
1206
+ "loss": 1.1482,
1207
+ "step": 8500
1208
+ },
1209
+ {
1210
+ "epoch": 0.5134749643420163,
1211
+ "grad_norm": 0.57421875,
1212
+ "learning_rate": 3.484613824771658e-05,
1213
+ "loss": 1.1466,
1214
+ "step": 8550
1215
+ },
1216
+ {
1217
+ "epoch": 0.5164777419112679,
1218
+ "grad_norm": 0.59375,
1219
+ "learning_rate": 3.4780795002396165e-05,
1220
+ "loss": 1.1443,
1221
+ "step": 8600
1222
+ },
1223
+ {
1224
+ "epoch": 0.5194805194805194,
1225
+ "grad_norm": 0.58984375,
1226
+ "learning_rate": 3.4715102232379994e-05,
1227
+ "loss": 1.1497,
1228
+ "step": 8650
1229
+ },
1230
+ {
1231
+ "epoch": 0.522483297049771,
1232
+ "grad_norm": 0.59375,
1233
+ "learning_rate": 3.4649061491119366e-05,
1234
+ "loss": 1.1473,
1235
+ "step": 8700
1236
+ },
1237
+ {
1238
+ "epoch": 0.5254860746190226,
1239
+ "grad_norm": 0.65234375,
1240
+ "learning_rate": 3.458267434029416e-05,
1241
+ "loss": 1.1428,
1242
+ "step": 8750
1243
+ },
1244
+ {
1245
+ "epoch": 0.5284888521882741,
1246
+ "grad_norm": 0.62109375,
1247
+ "learning_rate": 3.451594234977586e-05,
1248
+ "loss": 1.1372,
1249
+ "step": 8800
1250
+ },
1251
+ {
1252
+ "epoch": 0.5314916297575257,
1253
+ "grad_norm": 0.61328125,
1254
+ "learning_rate": 3.444886709759046e-05,
1255
+ "loss": 1.1389,
1256
+ "step": 8850
1257
+ },
1258
+ {
1259
+ "epoch": 0.5344944073267772,
1260
+ "grad_norm": 0.66015625,
1261
+ "learning_rate": 3.438145016988114e-05,
1262
+ "loss": 1.1363,
1263
+ "step": 8900
1264
+ },
1265
+ {
1266
+ "epoch": 0.5374971848960288,
1267
+ "grad_norm": 0.59375,
1268
+ "learning_rate": 3.431369316087074e-05,
1269
+ "loss": 1.1421,
1270
+ "step": 8950
1271
+ },
1272
+ {
1273
+ "epoch": 0.5404999624652804,
1274
+ "grad_norm": 0.56640625,
1275
+ "learning_rate": 3.4245597672824096e-05,
1276
+ "loss": 1.1398,
1277
+ "step": 9000
1278
+ },
1279
+ {
1280
+ "epoch": 0.5435027400345319,
1281
+ "grad_norm": 0.63671875,
1282
+ "learning_rate": 3.4177165316010116e-05,
1283
+ "loss": 1.1437,
1284
+ "step": 9050
1285
+ },
1286
+ {
1287
+ "epoch": 0.5465055176037835,
1288
+ "grad_norm": 0.63671875,
1289
+ "learning_rate": 3.410839770866374e-05,
1290
+ "loss": 1.1395,
1291
+ "step": 9100
1292
+ },
1293
+ {
1294
+ "epoch": 0.549508295173035,
1295
+ "grad_norm": 0.60546875,
1296
+ "learning_rate": 3.403929647694763e-05,
1297
+ "loss": 1.1405,
1298
+ "step": 9150
1299
+ },
1300
+ {
1301
+ "epoch": 0.5525110727422866,
1302
+ "grad_norm": 0.609375,
1303
+ "learning_rate": 3.3969863254913725e-05,
1304
+ "loss": 1.1344,
1305
+ "step": 9200
1306
+ },
1307
+ {
1308
+ "epoch": 0.5555138503115382,
1309
+ "grad_norm": 0.57421875,
1310
+ "learning_rate": 3.390009968446465e-05,
1311
+ "loss": 1.1315,
1312
+ "step": 9250
1313
+ },
1314
+ {
1315
+ "epoch": 0.5585166278807897,
1316
+ "grad_norm": 0.59765625,
1317
+ "learning_rate": 3.383000741531483e-05,
1318
+ "loss": 1.1389,
1319
+ "step": 9300
1320
+ },
1321
+ {
1322
+ "epoch": 0.5615194054500413,
1323
+ "grad_norm": 0.65234375,
1324
+ "learning_rate": 3.375958810495149e-05,
1325
+ "loss": 1.1392,
1326
+ "step": 9350
1327
+ },
1328
+ {
1329
+ "epoch": 0.5645221830192928,
1330
+ "grad_norm": 0.5859375,
1331
+ "learning_rate": 3.3688843418595496e-05,
1332
+ "loss": 1.1426,
1333
+ "step": 9400
1334
+ },
1335
+ {
1336
+ "epoch": 0.5675249605885444,
1337
+ "grad_norm": 0.59765625,
1338
+ "learning_rate": 3.3617775029161915e-05,
1339
+ "loss": 1.1336,
1340
+ "step": 9450
1341
+ },
1342
+ {
1343
+ "epoch": 0.570527738157796,
1344
+ "grad_norm": 0.58984375,
1345
+ "learning_rate": 3.3546384617220526e-05,
1346
+ "loss": 1.1368,
1347
+ "step": 9500
1348
+ },
1349
+ {
1350
+ "epoch": 0.5735305157270475,
1351
+ "grad_norm": 0.57421875,
1352
+ "learning_rate": 3.347467387095604e-05,
1353
+ "loss": 1.1372,
1354
+ "step": 9550
1355
+ },
1356
+ {
1357
+ "epoch": 0.5765332932962991,
1358
+ "grad_norm": 0.62890625,
1359
+ "learning_rate": 3.340264448612815e-05,
1360
+ "loss": 1.1374,
1361
+ "step": 9600
1362
+ },
1363
+ {
1364
+ "epoch": 0.5795360708655506,
1365
+ "grad_norm": 0.5625,
1366
+ "learning_rate": 3.333029816603151e-05,
1367
+ "loss": 1.1378,
1368
+ "step": 9650
1369
+ },
1370
+ {
1371
+ "epoch": 0.5825388484348022,
1372
+ "grad_norm": 0.5703125,
1373
+ "learning_rate": 3.325763662145539e-05,
1374
+ "loss": 1.1219,
1375
+ "step": 9700
1376
+ },
1377
+ {
1378
+ "epoch": 0.5855416260040538,
1379
+ "grad_norm": 0.5703125,
1380
+ "learning_rate": 3.318466157064324e-05,
1381
+ "loss": 1.1294,
1382
+ "step": 9750
1383
+ },
1384
+ {
1385
+ "epoch": 0.5885444035733053,
1386
+ "grad_norm": 0.78515625,
1387
+ "learning_rate": 3.311137473925206e-05,
1388
+ "loss": 1.1278,
1389
+ "step": 9800
1390
+ },
1391
+ {
1392
+ "epoch": 0.5915471811425569,
1393
+ "grad_norm": 0.609375,
1394
+ "learning_rate": 3.303777786031162e-05,
1395
+ "loss": 1.1266,
1396
+ "step": 9850
1397
+ },
1398
+ {
1399
+ "epoch": 0.5945499587118084,
1400
+ "grad_norm": 0.59375,
1401
+ "learning_rate": 3.296387267418341e-05,
1402
+ "loss": 1.1288,
1403
+ "step": 9900
1404
+ },
1405
+ {
1406
+ "epoch": 0.59755273628106,
1407
+ "grad_norm": 0.58984375,
1408
+ "learning_rate": 3.2889660928519545e-05,
1409
+ "loss": 1.1256,
1410
+ "step": 9950
1411
+ },
1412
+ {
1413
+ "epoch": 0.6005555138503116,
1414
+ "grad_norm": 0.58984375,
1415
+ "learning_rate": 3.2815144378221445e-05,
1416
+ "loss": 1.1282,
1417
+ "step": 10000
1418
+ },
1419
+ {
1420
+ "epoch": 0.6035582914195631,
1421
+ "grad_norm": 0.60546875,
1422
+ "learning_rate": 3.274032478539827e-05,
1423
+ "loss": 1.1282,
1424
+ "step": 10050
1425
+ },
1426
+ {
1427
+ "epoch": 0.6065610689888147,
1428
+ "grad_norm": 1.0234375,
1429
+ "learning_rate": 3.266520391932533e-05,
1430
+ "loss": 1.1266,
1431
+ "step": 10100
1432
+ },
1433
+ {
1434
+ "epoch": 0.6095638465580662,
1435
+ "grad_norm": 0.6015625,
1436
+ "learning_rate": 3.258978355640218e-05,
1437
+ "loss": 1.1244,
1438
+ "step": 10150
1439
+ },
1440
+ {
1441
+ "epoch": 0.6125666241273178,
1442
+ "grad_norm": 0.59765625,
1443
+ "learning_rate": 3.251406548011067e-05,
1444
+ "loss": 1.1325,
1445
+ "step": 10200
1446
+ },
1447
+ {
1448
+ "epoch": 0.6155694016965694,
1449
+ "grad_norm": 0.7578125,
1450
+ "learning_rate": 3.243805148097271e-05,
1451
+ "loss": 1.1222,
1452
+ "step": 10250
1453
+ },
1454
+ {
1455
+ "epoch": 0.6185721792658209,
1456
+ "grad_norm": 0.62890625,
1457
+ "learning_rate": 3.236174335650799e-05,
1458
+ "loss": 1.1223,
1459
+ "step": 10300
1460
+ },
1461
+ {
1462
+ "epoch": 0.6215749568350725,
1463
+ "grad_norm": 0.6015625,
1464
+ "learning_rate": 3.2285142911191446e-05,
1465
+ "loss": 1.1257,
1466
+ "step": 10350
1467
+ },
1468
+ {
1469
+ "epoch": 0.624577734404324,
1470
+ "grad_norm": 0.6328125,
1471
+ "learning_rate": 3.220825195641057e-05,
1472
+ "loss": 1.1165,
1473
+ "step": 10400
1474
+ },
1475
+ {
1476
+ "epoch": 0.6275805119735756,
1477
+ "grad_norm": 0.6171875,
1478
+ "learning_rate": 3.213107231042261e-05,
1479
+ "loss": 1.1221,
1480
+ "step": 10450
1481
+ },
1482
+ {
1483
+ "epoch": 0.6305832895428272,
1484
+ "grad_norm": 0.61328125,
1485
+ "learning_rate": 3.205360579831155e-05,
1486
+ "loss": 1.1109,
1487
+ "step": 10500
1488
+ },
1489
+ {
1490
+ "epoch": 0.6335860671120787,
1491
+ "grad_norm": 0.62109375,
1492
+ "learning_rate": 3.197585425194498e-05,
1493
+ "loss": 1.1177,
1494
+ "step": 10550
1495
+ },
1496
+ {
1497
+ "epoch": 0.6365888446813303,
1498
+ "grad_norm": 0.58984375,
1499
+ "learning_rate": 3.1897819509930724e-05,
1500
+ "loss": 1.1239,
1501
+ "step": 10600
1502
+ },
1503
+ {
1504
+ "epoch": 0.6395916222505817,
1505
+ "grad_norm": 0.57421875,
1506
+ "learning_rate": 3.18195034175734e-05,
1507
+ "loss": 1.1187,
1508
+ "step": 10650
1509
+ },
1510
+ {
1511
+ "epoch": 0.6425943998198334,
1512
+ "grad_norm": 0.6484375,
1513
+ "learning_rate": 3.174090782683082e-05,
1514
+ "loss": 1.1169,
1515
+ "step": 10700
1516
+ },
1517
+ {
1518
+ "epoch": 0.645597177389085,
1519
+ "grad_norm": 0.59375,
1520
+ "learning_rate": 3.166203459627011e-05,
1521
+ "loss": 1.1224,
1522
+ "step": 10750
1523
+ },
1524
+ {
1525
+ "epoch": 0.6485999549583364,
1526
+ "grad_norm": 0.625,
1527
+ "learning_rate": 3.158288559102384e-05,
1528
+ "loss": 1.1205,
1529
+ "step": 10800
1530
+ },
1531
+ {
1532
+ "epoch": 0.651602732527588,
1533
+ "grad_norm": 0.63671875,
1534
+ "learning_rate": 3.150346268274584e-05,
1535
+ "loss": 1.1222,
1536
+ "step": 10850
1537
+ },
1538
+ {
1539
+ "epoch": 0.6546055100968395,
1540
+ "grad_norm": 0.609375,
1541
+ "learning_rate": 3.142376774956703e-05,
1542
+ "loss": 1.121,
1543
+ "step": 10900
1544
+ },
1545
+ {
1546
+ "epoch": 0.6576082876660911,
1547
+ "grad_norm": 0.609375,
1548
+ "learning_rate": 3.134380267605095e-05,
1549
+ "loss": 1.115,
1550
+ "step": 10950
1551
+ },
1552
+ {
1553
+ "epoch": 0.6606110652353427,
1554
+ "grad_norm": 0.58203125,
1555
+ "learning_rate": 3.1263569353149196e-05,
1556
+ "loss": 1.1136,
1557
+ "step": 11000
1558
+ },
1559
+ {
1560
+ "epoch": 0.6636138428045942,
1561
+ "grad_norm": 0.59765625,
1562
+ "learning_rate": 3.118306967815671e-05,
1563
+ "loss": 1.1236,
1564
+ "step": 11050
1565
+ },
1566
+ {
1567
+ "epoch": 0.6666166203738458,
1568
+ "grad_norm": 0.578125,
1569
+ "learning_rate": 3.1102305554666944e-05,
1570
+ "loss": 1.1144,
1571
+ "step": 11100
1572
+ },
1573
+ {
1574
+ "epoch": 0.6667367314766158,
1575
+ "eval_loss": 1.5269793272018433,
1576
+ "eval_runtime": 124.1236,
1577
+ "eval_samples_per_second": 361.752,
1578
+ "eval_steps_per_second": 45.221,
1579
+ "step": 11102
1580
+ },
1581
+ {
1582
+ "epoch": 0.6696193979430973,
1583
+ "grad_norm": 0.6640625,
1584
+ "learning_rate": 3.1021278892526816e-05,
1585
+ "loss": 1.1133,
1586
+ "step": 11150
1587
+ },
1588
+ {
1589
+ "epoch": 0.6726221755123489,
1590
+ "grad_norm": 0.6015625,
1591
+ "learning_rate": 3.093999160779154e-05,
1592
+ "loss": 1.1139,
1593
+ "step": 11200
1594
+ },
1595
+ {
1596
+ "epoch": 0.6756249530816005,
1597
+ "grad_norm": 0.60546875,
1598
+ "learning_rate": 3.085844562267933e-05,
1599
+ "loss": 1.107,
1600
+ "step": 11250
1601
+ },
1602
+ {
1603
+ "epoch": 0.678627730650852,
1604
+ "grad_norm": 0.5703125,
1605
+ "learning_rate": 3.077664286552596e-05,
1606
+ "loss": 1.1131,
1607
+ "step": 11300
1608
+ },
1609
+ {
1610
+ "epoch": 0.6816305082201036,
1611
+ "grad_norm": 0.546875,
1612
+ "learning_rate": 3.0694585270739135e-05,
1613
+ "loss": 1.1089,
1614
+ "step": 11350
1615
+ },
1616
+ {
1617
+ "epoch": 0.6846332857893551,
1618
+ "grad_norm": 0.6484375,
1619
+ "learning_rate": 3.061227477875277e-05,
1620
+ "loss": 1.1167,
1621
+ "step": 11400
1622
+ },
1623
+ {
1624
+ "epoch": 0.6876360633586067,
1625
+ "grad_norm": 0.61328125,
1626
+ "learning_rate": 3.052971333598109e-05,
1627
+ "loss": 1.1156,
1628
+ "step": 11450
1629
+ },
1630
+ {
1631
+ "epoch": 0.6906388409278583,
1632
+ "grad_norm": 0.6015625,
1633
+ "learning_rate": 3.0446902894772612e-05,
1634
+ "loss": 1.1169,
1635
+ "step": 11500
1636
+ },
1637
+ {
1638
+ "epoch": 0.6936416184971098,
1639
+ "grad_norm": 0.59765625,
1640
+ "learning_rate": 3.0363845413363956e-05,
1641
+ "loss": 1.1043,
1642
+ "step": 11550
1643
+ },
1644
+ {
1645
+ "epoch": 0.6966443960663614,
1646
+ "grad_norm": 0.59765625,
1647
+ "learning_rate": 3.028054285583359e-05,
1648
+ "loss": 1.1089,
1649
+ "step": 11600
1650
+ },
1651
+ {
1652
+ "epoch": 0.6996471736356129,
1653
+ "grad_norm": 0.6015625,
1654
+ "learning_rate": 3.019699719205533e-05,
1655
+ "loss": 1.1096,
1656
+ "step": 11650
1657
+ },
1658
+ {
1659
+ "epoch": 0.7026499512048645,
1660
+ "grad_norm": 0.5859375,
1661
+ "learning_rate": 3.011321039765177e-05,
1662
+ "loss": 1.114,
1663
+ "step": 11700
1664
+ },
1665
+ {
1666
+ "epoch": 0.7056527287741161,
1667
+ "grad_norm": 0.62109375,
1668
+ "learning_rate": 3.0029184453947586e-05,
1669
+ "loss": 1.1077,
1670
+ "step": 11750
1671
+ },
1672
+ {
1673
+ "epoch": 0.7086555063433676,
1674
+ "grad_norm": 0.56640625,
1675
+ "learning_rate": 2.9944921347922665e-05,
1676
+ "loss": 1.1132,
1677
+ "step": 11800
1678
+ },
1679
+ {
1680
+ "epoch": 0.7116582839126192,
1681
+ "grad_norm": 0.59765625,
1682
+ "learning_rate": 2.9860423072165133e-05,
1683
+ "loss": 1.1011,
1684
+ "step": 11850
1685
+ },
1686
+ {
1687
+ "epoch": 0.7146610614818707,
1688
+ "grad_norm": 0.6640625,
1689
+ "learning_rate": 2.9775691624824207e-05,
1690
+ "loss": 1.107,
1691
+ "step": 11900
1692
+ },
1693
+ {
1694
+ "epoch": 0.7176638390511223,
1695
+ "grad_norm": 0.609375,
1696
+ "learning_rate": 2.9690729009562988e-05,
1697
+ "loss": 1.1007,
1698
+ "step": 11950
1699
+ },
1700
+ {
1701
+ "epoch": 0.7206666166203739,
1702
+ "grad_norm": 0.57421875,
1703
+ "learning_rate": 2.9605537235511034e-05,
1704
+ "loss": 1.1178,
1705
+ "step": 12000
1706
+ },
1707
+ {
1708
+ "epoch": 0.7236693941896254,
1709
+ "grad_norm": 0.5625,
1710
+ "learning_rate": 2.952011831721688e-05,
1711
+ "loss": 1.0965,
1712
+ "step": 12050
1713
+ },
1714
+ {
1715
+ "epoch": 0.726672171758877,
1716
+ "grad_norm": 0.56640625,
1717
+ "learning_rate": 2.943447427460039e-05,
1718
+ "loss": 1.1048,
1719
+ "step": 12100
1720
+ },
1721
+ {
1722
+ "epoch": 0.7296749493281285,
1723
+ "grad_norm": 0.60546875,
1724
+ "learning_rate": 2.9348607132904993e-05,
1725
+ "loss": 1.1024,
1726
+ "step": 12150
1727
+ },
1728
+ {
1729
+ "epoch": 0.7326777268973801,
1730
+ "grad_norm": 0.64453125,
1731
+ "learning_rate": 2.9262518922649793e-05,
1732
+ "loss": 1.1065,
1733
+ "step": 12200
1734
+ },
1735
+ {
1736
+ "epoch": 0.7356805044666316,
1737
+ "grad_norm": 0.64453125,
1738
+ "learning_rate": 2.9176211679581534e-05,
1739
+ "loss": 1.1075,
1740
+ "step": 12250
1741
+ },
1742
+ {
1743
+ "epoch": 0.7386832820358832,
1744
+ "grad_norm": 0.6328125,
1745
+ "learning_rate": 2.9089687444626508e-05,
1746
+ "loss": 1.1031,
1747
+ "step": 12300
1748
+ },
1749
+ {
1750
+ "epoch": 0.7416860596051348,
1751
+ "grad_norm": 0.6015625,
1752
+ "learning_rate": 2.9002948263842233e-05,
1753
+ "loss": 1.1004,
1754
+ "step": 12350
1755
+ },
1756
+ {
1757
+ "epoch": 0.7446888371743863,
1758
+ "grad_norm": 0.58203125,
1759
+ "learning_rate": 2.891599618836911e-05,
1760
+ "loss": 1.106,
1761
+ "step": 12400
1762
+ },
1763
+ {
1764
+ "epoch": 0.7476916147436379,
1765
+ "grad_norm": 0.609375,
1766
+ "learning_rate": 2.8828833274381915e-05,
1767
+ "loss": 1.1004,
1768
+ "step": 12450
1769
+ },
1770
+ {
1771
+ "epoch": 0.7506943923128894,
1772
+ "grad_norm": 0.58203125,
1773
+ "learning_rate": 2.8741461583041156e-05,
1774
+ "loss": 1.1077,
1775
+ "step": 12500
1776
+ },
1777
+ {
1778
+ "epoch": 0.753697169882141,
1779
+ "grad_norm": 0.59375,
1780
+ "learning_rate": 2.865388318044434e-05,
1781
+ "loss": 1.1013,
1782
+ "step": 12550
1783
+ },
1784
+ {
1785
+ "epoch": 0.7566999474513926,
1786
+ "grad_norm": 0.61328125,
1787
+ "learning_rate": 2.8566100137577132e-05,
1788
+ "loss": 1.0931,
1789
+ "step": 12600
1790
+ },
1791
+ {
1792
+ "epoch": 0.7597027250206441,
1793
+ "grad_norm": 0.59765625,
1794
+ "learning_rate": 2.8478114530264373e-05,
1795
+ "loss": 1.0965,
1796
+ "step": 12650
1797
+ },
1798
+ {
1799
+ "epoch": 0.7627055025898957,
1800
+ "grad_norm": 0.65234375,
1801
+ "learning_rate": 2.8389928439120983e-05,
1802
+ "loss": 1.1062,
1803
+ "step": 12700
1804
+ },
1805
+ {
1806
+ "epoch": 0.7657082801591472,
1807
+ "grad_norm": 0.6171875,
1808
+ "learning_rate": 2.8301543949502766e-05,
1809
+ "loss": 1.1039,
1810
+ "step": 12750
1811
+ },
1812
+ {
1813
+ "epoch": 0.7687110577283988,
1814
+ "grad_norm": 0.59765625,
1815
+ "learning_rate": 2.8212963151457105e-05,
1816
+ "loss": 1.0921,
1817
+ "step": 12800
1818
+ },
1819
+ {
1820
+ "epoch": 0.7717138352976504,
1821
+ "grad_norm": 0.6015625,
1822
+ "learning_rate": 2.8124188139673522e-05,
1823
+ "loss": 1.0961,
1824
+ "step": 12850
1825
+ },
1826
+ {
1827
+ "epoch": 0.7747166128669019,
1828
+ "grad_norm": 0.578125,
1829
+ "learning_rate": 2.803522101343416e-05,
1830
+ "loss": 1.0877,
1831
+ "step": 12900
1832
+ },
1833
+ {
1834
+ "epoch": 0.7777193904361535,
1835
+ "grad_norm": 0.5859375,
1836
+ "learning_rate": 2.794606387656413e-05,
1837
+ "loss": 1.0901,
1838
+ "step": 12950
1839
+ },
1840
+ {
1841
+ "epoch": 0.780722168005405,
1842
+ "grad_norm": 0.5625,
1843
+ "learning_rate": 2.7856718837381765e-05,
1844
+ "loss": 1.0963,
1845
+ "step": 13000
1846
+ },
1847
+ {
1848
+ "epoch": 0.7837249455746566,
1849
+ "grad_norm": 0.6015625,
1850
+ "learning_rate": 2.776718800864878e-05,
1851
+ "loss": 1.1012,
1852
+ "step": 13050
1853
+ },
1854
+ {
1855
+ "epoch": 0.7867277231439082,
1856
+ "grad_norm": 0.59765625,
1857
+ "learning_rate": 2.7677473507520285e-05,
1858
+ "loss": 1.0958,
1859
+ "step": 13100
1860
+ },
1861
+ {
1862
+ "epoch": 0.7897305007131596,
1863
+ "grad_norm": 0.6171875,
1864
+ "learning_rate": 2.7587577455494722e-05,
1865
+ "loss": 1.1048,
1866
+ "step": 13150
1867
+ },
1868
+ {
1869
+ "epoch": 0.7927332782824112,
1870
+ "grad_norm": 0.58984375,
1871
+ "learning_rate": 2.749750197836373e-05,
1872
+ "loss": 1.0984,
1873
+ "step": 13200
1874
+ },
1875
+ {
1876
+ "epoch": 0.7957360558516627,
1877
+ "grad_norm": 0.5703125,
1878
+ "learning_rate": 2.7407249206161827e-05,
1879
+ "loss": 1.0977,
1880
+ "step": 13250
1881
+ },
1882
+ {
1883
+ "epoch": 0.7987388334209143,
1884
+ "grad_norm": 0.6015625,
1885
+ "learning_rate": 2.7316821273116087e-05,
1886
+ "loss": 1.096,
1887
+ "step": 13300
1888
+ },
1889
+ {
1890
+ "epoch": 0.8017416109901659,
1891
+ "grad_norm": 0.578125,
1892
+ "learning_rate": 2.7226220317595632e-05,
1893
+ "loss": 1.0974,
1894
+ "step": 13350
1895
+ },
1896
+ {
1897
+ "epoch": 0.8047443885594174,
1898
+ "grad_norm": 0.55078125,
1899
+ "learning_rate": 2.7135448482061106e-05,
1900
+ "loss": 1.0974,
1901
+ "step": 13400
1902
+ },
1903
+ {
1904
+ "epoch": 0.807747166128669,
1905
+ "grad_norm": 0.57421875,
1906
+ "learning_rate": 2.7044507913013975e-05,
1907
+ "loss": 1.0923,
1908
+ "step": 13450
1909
+ },
1910
+ {
1911
+ "epoch": 0.8107499436979205,
1912
+ "grad_norm": 0.56640625,
1913
+ "learning_rate": 2.6953400760945782e-05,
1914
+ "loss": 1.088,
1915
+ "step": 13500
1916
+ },
1917
+ {
1918
+ "epoch": 0.8137527212671721,
1919
+ "grad_norm": 0.5703125,
1920
+ "learning_rate": 2.6862129180287308e-05,
1921
+ "loss": 1.0935,
1922
+ "step": 13550
1923
+ },
1924
+ {
1925
+ "epoch": 0.8167554988364237,
1926
+ "grad_norm": 0.625,
1927
+ "learning_rate": 2.6770695329357605e-05,
1928
+ "loss": 1.0899,
1929
+ "step": 13600
1930
+ },
1931
+ {
1932
+ "epoch": 0.8197582764056752,
1933
+ "grad_norm": 0.625,
1934
+ "learning_rate": 2.6679101370312968e-05,
1935
+ "loss": 1.0892,
1936
+ "step": 13650
1937
+ },
1938
+ {
1939
+ "epoch": 0.8227610539749268,
1940
+ "grad_norm": 0.58203125,
1941
+ "learning_rate": 2.6587349469095783e-05,
1942
+ "loss": 1.0916,
1943
+ "step": 13700
1944
+ },
1945
+ {
1946
+ "epoch": 0.8257638315441783,
1947
+ "grad_norm": 0.59765625,
1948
+ "learning_rate": 2.649544179538337e-05,
1949
+ "loss": 1.0976,
1950
+ "step": 13750
1951
+ },
1952
+ {
1953
+ "epoch": 0.8287666091134299,
1954
+ "grad_norm": 0.62890625,
1955
+ "learning_rate": 2.64033805225366e-05,
1956
+ "loss": 1.1017,
1957
+ "step": 13800
1958
+ },
1959
+ {
1960
+ "epoch": 0.8317693866826815,
1961
+ "grad_norm": 0.546875,
1962
+ "learning_rate": 2.6311167827548563e-05,
1963
+ "loss": 1.0827,
1964
+ "step": 13850
1965
+ },
1966
+ {
1967
+ "epoch": 0.834772164251933,
1968
+ "grad_norm": 0.62109375,
1969
+ "learning_rate": 2.6218805890993033e-05,
1970
+ "loss": 1.0893,
1971
+ "step": 13900
1972
+ },
1973
+ {
1974
+ "epoch": 0.8377749418211846,
1975
+ "grad_norm": 0.57421875,
1976
+ "learning_rate": 2.6126296896972956e-05,
1977
+ "loss": 1.0927,
1978
+ "step": 13950
1979
+ },
1980
+ {
1981
+ "epoch": 0.8407777193904361,
1982
+ "grad_norm": 0.58203125,
1983
+ "learning_rate": 2.6033643033068764e-05,
1984
+ "loss": 1.0847,
1985
+ "step": 14000
1986
+ },
1987
+ {
1988
+ "epoch": 0.8437804969596877,
1989
+ "grad_norm": 0.55078125,
1990
+ "learning_rate": 2.5940846490286668e-05,
1991
+ "loss": 1.0878,
1992
+ "step": 14050
1993
+ },
1994
+ {
1995
+ "epoch": 0.8467832745289393,
1996
+ "grad_norm": 0.57421875,
1997
+ "learning_rate": 2.5847909463006825e-05,
1998
+ "loss": 1.0792,
1999
+ "step": 14100
2000
+ },
2001
+ {
2002
+ "epoch": 0.8497860520981908,
2003
+ "grad_norm": 0.6484375,
2004
+ "learning_rate": 2.575483414893148e-05,
2005
+ "loss": 1.094,
2006
+ "step": 14150
2007
+ },
2008
+ {
2009
+ "epoch": 0.8527888296674424,
2010
+ "grad_norm": 0.6640625,
2011
+ "learning_rate": 2.5661622749032962e-05,
2012
+ "loss": 1.0829,
2013
+ "step": 14200
2014
+ },
2015
+ {
2016
+ "epoch": 0.8557916072366939,
2017
+ "grad_norm": 0.6015625,
2018
+ "learning_rate": 2.5568277467501642e-05,
2019
+ "loss": 1.0887,
2020
+ "step": 14250
2021
+ },
2022
+ {
2023
+ "epoch": 0.8587943848059455,
2024
+ "grad_norm": 0.69140625,
2025
+ "learning_rate": 2.5474800511693846e-05,
2026
+ "loss": 1.0953,
2027
+ "step": 14300
2028
+ },
2029
+ {
2030
+ "epoch": 0.8617971623751971,
2031
+ "grad_norm": 0.609375,
2032
+ "learning_rate": 2.5381194092079607e-05,
2033
+ "loss": 1.0876,
2034
+ "step": 14350
2035
+ },
2036
+ {
2037
+ "epoch": 0.8647999399444486,
2038
+ "grad_norm": 0.57421875,
2039
+ "learning_rate": 2.5287460422190432e-05,
2040
+ "loss": 1.0864,
2041
+ "step": 14400
2042
+ },
2043
+ {
2044
+ "epoch": 0.8678027175137002,
2045
+ "grad_norm": 0.5703125,
2046
+ "learning_rate": 2.5193601718566924e-05,
2047
+ "loss": 1.0844,
2048
+ "step": 14450
2049
+ },
2050
+ {
2051
+ "epoch": 0.8708054950829517,
2052
+ "grad_norm": 0.58984375,
2053
+ "learning_rate": 2.5099620200706406e-05,
2054
+ "loss": 1.0829,
2055
+ "step": 14500
2056
+ },
2057
+ {
2058
+ "epoch": 0.8738082726522033,
2059
+ "grad_norm": 0.55859375,
2060
+ "learning_rate": 2.5005518091010413e-05,
2061
+ "loss": 1.0932,
2062
+ "step": 14550
2063
+ },
2064
+ {
2065
+ "epoch": 0.8768110502214549,
2066
+ "grad_norm": 0.6015625,
2067
+ "learning_rate": 2.491129761473213e-05,
2068
+ "loss": 1.0812,
2069
+ "step": 14600
2070
+ },
2071
+ {
2072
+ "epoch": 0.8798138277907064,
2073
+ "grad_norm": 0.5859375,
2074
+ "learning_rate": 2.4816960999923794e-05,
2075
+ "loss": 1.0817,
2076
+ "step": 14650
2077
+ },
2078
+ {
2079
+ "epoch": 0.882816605359958,
2080
+ "grad_norm": 0.59765625,
2081
+ "learning_rate": 2.472251047738399e-05,
2082
+ "loss": 1.0859,
2083
+ "step": 14700
2084
+ },
2085
+ {
2086
+ "epoch": 0.8858193829292095,
2087
+ "grad_norm": 0.58203125,
2088
+ "learning_rate": 2.462794828060491e-05,
2089
+ "loss": 1.0834,
2090
+ "step": 14750
2091
+ },
2092
+ {
2093
+ "epoch": 0.8888221604984611,
2094
+ "grad_norm": 0.59375,
2095
+ "learning_rate": 2.4533276645719513e-05,
2096
+ "loss": 1.0818,
2097
+ "step": 14800
2098
+ },
2099
+ {
2100
+ "epoch": 0.8918249380677127,
2101
+ "grad_norm": 0.63671875,
2102
+ "learning_rate": 2.4438497811448688e-05,
2103
+ "loss": 1.0805,
2104
+ "step": 14850
2105
+ },
2106
+ {
2107
+ "epoch": 0.8948277156369642,
2108
+ "grad_norm": 0.5859375,
2109
+ "learning_rate": 2.4343614019048277e-05,
2110
+ "loss": 1.0806,
2111
+ "step": 14900
2112
+ },
2113
+ {
2114
+ "epoch": 0.8978304932062158,
2115
+ "grad_norm": 0.55078125,
2116
+ "learning_rate": 2.4248627512256105e-05,
2117
+ "loss": 1.0808,
2118
+ "step": 14950
2119
+ },
2120
+ {
2121
+ "epoch": 0.9008332707754673,
2122
+ "grad_norm": 0.56640625,
2123
+ "learning_rate": 2.415354053723888e-05,
2124
+ "loss": 1.0735,
2125
+ "step": 15000
2126
+ },
2127
+ {
2128
+ "epoch": 0.9038360483447189,
2129
+ "grad_norm": 0.6171875,
2130
+ "learning_rate": 2.405835534253913e-05,
2131
+ "loss": 1.0837,
2132
+ "step": 15050
2133
+ },
2134
+ {
2135
+ "epoch": 0.9068388259139705,
2136
+ "grad_norm": 0.59375,
2137
+ "learning_rate": 2.3963074179021996e-05,
2138
+ "loss": 1.0809,
2139
+ "step": 15100
2140
+ },
2141
+ {
2142
+ "epoch": 0.909841603483222,
2143
+ "grad_norm": 0.59375,
2144
+ "learning_rate": 2.3867699299822005e-05,
2145
+ "loss": 1.0823,
2146
+ "step": 15150
2147
+ },
2148
+ {
2149
+ "epoch": 0.9128443810524736,
2150
+ "grad_norm": 0.5703125,
2151
+ "learning_rate": 2.3772232960289818e-05,
2152
+ "loss": 1.0854,
2153
+ "step": 15200
2154
+ },
2155
+ {
2156
+ "epoch": 0.915847158621725,
2157
+ "grad_norm": 0.6015625,
2158
+ "learning_rate": 2.3676677417938864e-05,
2159
+ "loss": 1.0741,
2160
+ "step": 15250
2161
+ },
2162
+ {
2163
+ "epoch": 0.9188499361909767,
2164
+ "grad_norm": 0.59765625,
2165
+ "learning_rate": 2.358103493239198e-05,
2166
+ "loss": 1.0825,
2167
+ "step": 15300
2168
+ },
2169
+ {
2170
+ "epoch": 0.9218527137602283,
2171
+ "grad_norm": 0.56640625,
2172
+ "learning_rate": 2.348530776532796e-05,
2173
+ "loss": 1.073,
2174
+ "step": 15350
2175
+ },
2176
+ {
2177
+ "epoch": 0.9248554913294798,
2178
+ "grad_norm": 0.5859375,
2179
+ "learning_rate": 2.3389498180428082e-05,
2180
+ "loss": 1.0716,
2181
+ "step": 15400
2182
+ },
2183
+ {
2184
+ "epoch": 0.9278582688987314,
2185
+ "grad_norm": 0.5859375,
2186
+ "learning_rate": 2.329360844332258e-05,
2187
+ "loss": 1.0814,
2188
+ "step": 15450
2189
+ },
2190
+ {
2191
+ "epoch": 0.9308610464679828,
2192
+ "grad_norm": 0.6171875,
2193
+ "learning_rate": 2.3197640821537065e-05,
2194
+ "loss": 1.0826,
2195
+ "step": 15500
2196
+ },
2197
+ {
2198
+ "epoch": 0.9338638240372344,
2199
+ "grad_norm": 0.5625,
2200
+ "learning_rate": 2.3101597584438897e-05,
2201
+ "loss": 1.0864,
2202
+ "step": 15550
2203
+ },
2204
+ {
2205
+ "epoch": 0.936866601606486,
2206
+ "grad_norm": 0.59765625,
2207
+ "learning_rate": 2.300548100318354e-05,
2208
+ "loss": 1.0784,
2209
+ "step": 15600
2210
+ },
2211
+ {
2212
+ "epoch": 0.9398693791757375,
2213
+ "grad_norm": 0.57421875,
2214
+ "learning_rate": 2.2909293350660827e-05,
2215
+ "loss": 1.0716,
2216
+ "step": 15650
2217
+ },
2218
+ {
2219
+ "epoch": 0.9428721567449891,
2220
+ "grad_norm": 0.609375,
2221
+ "learning_rate": 2.2813036901441246e-05,
2222
+ "loss": 1.0704,
2223
+ "step": 15700
2224
+ },
2225
+ {
2226
+ "epoch": 0.9458749343142406,
2227
+ "grad_norm": 0.5859375,
2228
+ "learning_rate": 2.271671393172212e-05,
2229
+ "loss": 1.073,
2230
+ "step": 15750
2231
+ },
2232
+ {
2233
+ "epoch": 0.9488777118834922,
2234
+ "grad_norm": 0.59375,
2235
+ "learning_rate": 2.262032671927382e-05,
2236
+ "loss": 1.075,
2237
+ "step": 15800
2238
+ },
2239
+ {
2240
+ "epoch": 0.9518804894527438,
2241
+ "grad_norm": 0.67578125,
2242
+ "learning_rate": 2.2523877543385842e-05,
2243
+ "loss": 1.0733,
2244
+ "step": 15850
2245
+ },
2246
+ {
2247
+ "epoch": 0.9548832670219953,
2248
+ "grad_norm": 0.5859375,
2249
+ "learning_rate": 2.2427368684812986e-05,
2250
+ "loss": 1.0701,
2251
+ "step": 15900
2252
+ },
2253
+ {
2254
+ "epoch": 0.9578860445912469,
2255
+ "grad_norm": 0.609375,
2256
+ "learning_rate": 2.2330802425721346e-05,
2257
+ "loss": 1.0782,
2258
+ "step": 15950
2259
+ },
2260
+ {
2261
+ "epoch": 0.9608888221604984,
2262
+ "grad_norm": 0.5703125,
2263
+ "learning_rate": 2.223418104963441e-05,
2264
+ "loss": 1.0728,
2265
+ "step": 16000
2266
+ },
2267
+ {
2268
+ "epoch": 0.96389159972975,
2269
+ "grad_norm": 0.6328125,
2270
+ "learning_rate": 2.2137506841378998e-05,
2271
+ "loss": 1.0687,
2272
+ "step": 16050
2273
+ },
2274
+ {
2275
+ "epoch": 0.9668943772990016,
2276
+ "grad_norm": 0.60546875,
2277
+ "learning_rate": 2.2040782087031292e-05,
2278
+ "loss": 1.0665,
2279
+ "step": 16100
2280
+ },
2281
+ {
2282
+ "epoch": 0.9698971548682531,
2283
+ "grad_norm": 0.578125,
2284
+ "learning_rate": 2.194400907386273e-05,
2285
+ "loss": 1.0669,
2286
+ "step": 16150
2287
+ },
2288
+ {
2289
+ "epoch": 0.9728999324375047,
2290
+ "grad_norm": 0.59375,
2291
+ "learning_rate": 2.1847190090285942e-05,
2292
+ "loss": 1.07,
2293
+ "step": 16200
2294
+ },
2295
+ {
2296
+ "epoch": 0.9759027100067562,
2297
+ "grad_norm": 0.56640625,
2298
+ "learning_rate": 2.175032742580064e-05,
2299
+ "loss": 1.0606,
2300
+ "step": 16250
2301
+ },
2302
+ {
2303
+ "epoch": 0.9789054875760078,
2304
+ "grad_norm": 0.578125,
2305
+ "learning_rate": 2.1653423370939456e-05,
2306
+ "loss": 1.0639,
2307
+ "step": 16300
2308
+ },
2309
+ {
2310
+ "epoch": 0.9819082651452594,
2311
+ "grad_norm": 0.58203125,
2312
+ "learning_rate": 2.1556480217213788e-05,
2313
+ "loss": 1.0675,
2314
+ "step": 16350
2315
+ },
2316
+ {
2317
+ "epoch": 0.9849110427145109,
2318
+ "grad_norm": 0.609375,
2319
+ "learning_rate": 2.145950025705963e-05,
2320
+ "loss": 1.0714,
2321
+ "step": 16400
2322
+ },
2323
+ {
2324
+ "epoch": 0.9879138202837625,
2325
+ "grad_norm": 0.55859375,
2326
+ "learning_rate": 2.1362485783783316e-05,
2327
+ "loss": 1.0718,
2328
+ "step": 16450
2329
+ },
2330
+ {
2331
+ "epoch": 0.990916597853014,
2332
+ "grad_norm": 0.6171875,
2333
+ "learning_rate": 2.1265439091507356e-05,
2334
+ "loss": 1.0719,
2335
+ "step": 16500
2336
+ },
2337
+ {
2338
+ "epoch": 0.9939193754222656,
2339
+ "grad_norm": 0.5625,
2340
+ "learning_rate": 2.1168362475116123e-05,
2341
+ "loss": 1.0656,
2342
+ "step": 16550
2343
+ },
2344
+ {
2345
+ "epoch": 0.9969221529915172,
2346
+ "grad_norm": 0.58203125,
2347
+ "learning_rate": 2.1071258230201618e-05,
2348
+ "loss": 1.0662,
2349
+ "step": 16600
2350
+ },
2351
+ {
2352
+ "epoch": 0.9999249305607687,
2353
+ "grad_norm": 0.5703125,
2354
+ "learning_rate": 2.0974128653009188e-05,
2355
+ "loss": 1.0661,
2356
+ "step": 16650
2357
+ },
2358
+ {
2359
+ "epoch": 1.000060055551385,
2360
+ "eval_loss": 1.4946130514144897,
2361
+ "eval_runtime": 123.7357,
2362
+ "eval_samples_per_second": 362.887,
2363
+ "eval_steps_per_second": 45.363,
2364
+ "step": 16653
2365
+ }
2366
+ ],
2367
+ "logging_steps": 50,
2368
+ "max_steps": 33302,
2369
+ "num_input_tokens_seen": 0,
2370
+ "num_train_epochs": 2,
2371
+ "save_steps": 5551,
2372
+ "stateful_callbacks": {
2373
+ "TrainerControl": {
2374
+ "args": {
2375
+ "should_epoch_stop": false,
2376
+ "should_evaluate": false,
2377
+ "should_log": false,
2378
+ "should_save": true,
2379
+ "should_training_stop": false
2380
+ },
2381
+ "attributes": {}
2382
+ }
2383
+ },
2384
+ "total_flos": 1.9656692686911858e+20,
2385
+ "train_batch_size": 2,
2386
+ "trial_name": null,
2387
+ "trial_params": null
2388
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f51d32d50973845924454d0dd7a840d6a90adc25f68b42a04956c5b0c7b518b
3
+ size 6392