starmpcc commited on
Commit
f775c59
1 Parent(s): e91a954

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nfs_data_storage/llama2_hf/Llama-2-13b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.28.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.9,
8
+ "top_p": 0.6,
9
+ "transformers_version": "4.28.0"
10
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ce08c91e998b40fd73b4a8673663c40488e84e4a93711fa06a44239081e7b7
3
+ size 9956546443
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8248b14b737d33883c0be53eb0ab1dd4117223cc3f38bcf2e9671aa13dbd749
3
+ size 9940859009
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461fda24e61f954387ddddf2b22c954b4bb8055868f8a934a5e52cd7ff13bbdb
3
+ size 9940859567
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d930e03b6e86c2caf6ee5e1ed0ce03a171b09255c198b6faae88f2531de1743
3
+ size 9867417913
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b693fc217e22cef8a45b17d3ecb092abfd79437f23ab588ab0e7036ed314fd
3
+ size 9867459649
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3050261f51c3642693e2def1625b67f1abfe122eab2cec89e5047b433d7eca1
3
+ size 2490476719
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 52063467520
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
408
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
409
+ }
410
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 4096,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
@@ -0,0 +1,997 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9953917050691244,
5
+ "global_step": 162,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.000000000000001e-06,
13
+ "loss": 1.4312,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 8.000000000000001e-06,
19
+ "loss": 1.4237,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 1.2e-05,
25
+ "loss": 1.3934,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 1.6000000000000003e-05,
31
+ "loss": 1.3338,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 2e-05,
37
+ "loss": 1.3131,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.04,
42
+ "learning_rate": 1.9997998037428528e-05,
43
+ "loss": 1.2994,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 1.999199295128493e-05,
49
+ "loss": 1.2578,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.05,
54
+ "learning_rate": 1.998198714596076e-05,
55
+ "loss": 1.2713,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.06,
60
+ "learning_rate": 1.996798462770555e-05,
61
+ "loss": 1.2291,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.06,
66
+ "learning_rate": 1.994999100302281e-05,
67
+ "loss": 1.2212,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.07,
72
+ "learning_rate": 1.992801347642515e-05,
73
+ "loss": 1.2206,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.07,
78
+ "learning_rate": 1.9902060847549716e-05,
79
+ "loss": 1.2123,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.08,
84
+ "learning_rate": 1.987214350763483e-05,
85
+ "loss": 1.2006,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.09,
90
+ "learning_rate": 1.9838273435359447e-05,
91
+ "loss": 1.1977,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.09,
96
+ "learning_rate": 1.9800464192046956e-05,
97
+ "loss": 1.1972,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.1,
102
+ "learning_rate": 1.9758730916235356e-05,
103
+ "loss": 1.201,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.1,
108
+ "learning_rate": 1.9713090317615877e-05,
109
+ "loss": 1.1958,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.11,
114
+ "learning_rate": 1.966356067034256e-05,
115
+ "loss": 1.1706,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.12,
120
+ "learning_rate": 1.96101618057154e-05,
121
+ "loss": 1.1926,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.12,
126
+ "learning_rate": 1.9552915104240067e-05,
127
+ "loss": 1.192,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.13,
132
+ "learning_rate": 1.9491843487067305e-05,
133
+ "loss": 1.1897,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.14,
138
+ "learning_rate": 1.9426971406815464e-05,
139
+ "loss": 1.1891,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.14,
144
+ "learning_rate": 1.9358324837779864e-05,
145
+ "loss": 1.186,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.15,
150
+ "learning_rate": 1.9285931265532875e-05,
151
+ "loss": 1.1704,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.15,
156
+ "learning_rate": 1.920981967591891e-05,
157
+ "loss": 1.1822,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.16,
162
+ "learning_rate": 1.9130020543448705e-05,
163
+ "loss": 1.1682,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.17,
168
+ "learning_rate": 1.9046565819097546e-05,
169
+ "loss": 1.181,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.17,
174
+ "learning_rate": 1.895948891751234e-05,
175
+ "loss": 1.169,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.18,
180
+ "learning_rate": 1.8868824703632658e-05,
181
+ "loss": 1.1743,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.18,
186
+ "learning_rate": 1.8774609478731048e-05,
187
+ "loss": 1.1678,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.19,
192
+ "learning_rate": 1.8676880965878293e-05,
193
+ "loss": 1.1762,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.2,
198
+ "learning_rate": 1.857567829483937e-05,
199
+ "loss": 1.1637,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.2,
204
+ "learning_rate": 1.84710419864062e-05,
205
+ "loss": 1.1644,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.21,
210
+ "learning_rate": 1.8363013936173393e-05,
211
+ "loss": 1.1644,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.22,
216
+ "learning_rate": 1.8251637397763597e-05,
217
+ "loss": 1.1557,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.22,
222
+ "learning_rate": 1.8136956965509064e-05,
223
+ "loss": 1.161,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.23,
228
+ "learning_rate": 1.8019018556596402e-05,
229
+ "loss": 1.15,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.23,
234
+ "learning_rate": 1.7897869392681685e-05,
235
+ "loss": 1.1704,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.24,
240
+ "learning_rate": 1.7773557980983264e-05,
241
+ "loss": 1.1521,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.25,
246
+ "learning_rate": 1.7646134094859816e-05,
247
+ "loss": 1.1578,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.25,
252
+ "learning_rate": 1.7515648753881495e-05,
253
+ "loss": 1.1578,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.26,
258
+ "learning_rate": 1.738215420340205e-05,
259
+ "loss": 1.1615,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.26,
264
+ "learning_rate": 1.7245703893640188e-05,
265
+ "loss": 1.157,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.27,
270
+ "learning_rate": 1.7106352458278524e-05,
271
+ "loss": 1.14,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.28,
276
+ "learning_rate": 1.696415569258862e-05,
277
+ "loss": 1.1552,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.28,
282
+ "learning_rate": 1.6819170531091018e-05,
283
+ "loss": 1.1595,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.29,
288
+ "learning_rate": 1.667145502475907e-05,
289
+ "loss": 1.1568,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.29,
294
+ "learning_rate": 1.6521068317775756e-05,
295
+ "loss": 1.1489,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.3,
300
+ "learning_rate": 1.6368070623852794e-05,
301
+ "loss": 1.1649,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.31,
306
+ "learning_rate": 1.6212523202121547e-05,
307
+ "loss": 1.1506,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.31,
312
+ "learning_rate": 1.6054488332605282e-05,
313
+ "loss": 1.1458,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.32,
318
+ "learning_rate": 1.589402929128276e-05,
319
+ "loss": 1.1457,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.33,
324
+ "learning_rate": 1.573121032475297e-05,
325
+ "loss": 1.1539,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.33,
330
+ "learning_rate": 1.5566096624511306e-05,
331
+ "loss": 1.155,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.34,
336
+ "learning_rate": 1.5398754300847346e-05,
337
+ "loss": 1.1385,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.34,
342
+ "learning_rate": 1.5229250356374804e-05,
343
+ "loss": 1.1467,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.35,
348
+ "learning_rate": 1.5057652659204198e-05,
349
+ "loss": 1.1619,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.36,
354
+ "learning_rate": 1.4884029915768945e-05,
355
+ "loss": 1.1297,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.36,
360
+ "learning_rate": 1.4708451643315827e-05,
361
+ "loss": 1.144,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.37,
366
+ "learning_rate": 1.4530988142070802e-05,
367
+ "loss": 1.158,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.37,
372
+ "learning_rate": 1.4351710467091337e-05,
373
+ "loss": 1.1486,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.38,
378
+ "learning_rate": 1.4170690399816469e-05,
379
+ "loss": 1.1456,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.39,
384
+ "learning_rate": 1.3988000419326073e-05,
385
+ "loss": 1.1473,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.39,
390
+ "learning_rate": 1.3803713673320773e-05,
391
+ "loss": 1.143,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.4,
396
+ "learning_rate": 1.3617903948834155e-05,
397
+ "loss": 1.1538,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.41,
402
+ "learning_rate": 1.343064564268899e-05,
403
+ "loss": 1.1435,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.41,
408
+ "learning_rate": 1.324201373170929e-05,
409
+ "loss": 1.1491,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.42,
414
+ "learning_rate": 1.3052083742700172e-05,
415
+ "loss": 1.1334,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.42,
420
+ "learning_rate": 1.286093172220748e-05,
421
+ "loss": 1.1417,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.43,
426
+ "learning_rate": 1.2668634206069305e-05,
427
+ "loss": 1.1518,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.44,
432
+ "learning_rate": 1.2475268188771628e-05,
433
+ "loss": 1.1494,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.44,
438
+ "learning_rate": 1.2280911092620298e-05,
439
+ "loss": 1.1419,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.45,
444
+ "learning_rate": 1.2085640736741708e-05,
445
+ "loss": 1.1357,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.45,
450
+ "learning_rate": 1.1889535305924619e-05,
451
+ "loss": 1.1433,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.46,
456
+ "learning_rate": 1.1692673319315541e-05,
457
+ "loss": 1.1513,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.47,
462
+ "learning_rate": 1.1495133598980263e-05,
463
+ "loss": 1.1388,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.47,
468
+ "learning_rate": 1.1296995238344084e-05,
469
+ "loss": 1.1534,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.48,
474
+ "learning_rate": 1.1098337570523397e-05,
475
+ "loss": 1.1606,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.49,
480
+ "learning_rate": 1.08992401365613e-05,
481
+ "loss": 1.1422,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.49,
486
+ "learning_rate": 1.0699782653579973e-05,
487
+ "loss": 1.142,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.5,
492
+ "learning_rate": 1.0500044982862519e-05,
493
+ "loss": 1.1407,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.5,
498
+ "learning_rate": 1.0300107097877114e-05,
499
+ "loss": 1.143,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.51,
504
+ "learning_rate": 1.0100049052256236e-05,
505
+ "loss": 1.1441,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.52,
510
+ "learning_rate": 9.899950947743767e-06,
511
+ "loss": 1.1395,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.52,
516
+ "learning_rate": 9.699892902122887e-06,
517
+ "loss": 1.1412,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.53,
522
+ "learning_rate": 9.499955017137485e-06,
523
+ "loss": 1.1392,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.53,
528
+ "learning_rate": 9.300217346420029e-06,
529
+ "loss": 1.1427,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.54,
534
+ "learning_rate": 9.100759863438702e-06,
535
+ "loss": 1.1344,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.55,
540
+ "learning_rate": 8.901662429476607e-06,
541
+ "loss": 1.1436,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.55,
546
+ "learning_rate": 8.703004761655918e-06,
547
+ "loss": 1.1475,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.56,
552
+ "learning_rate": 8.504866401019738e-06,
553
+ "loss": 1.1404,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.57,
558
+ "learning_rate": 8.30732668068446e-06,
559
+ "loss": 1.1339,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.57,
564
+ "learning_rate": 8.110464694075383e-06,
565
+ "loss": 1.1467,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.58,
570
+ "learning_rate": 7.914359263258295e-06,
571
+ "loss": 1.1414,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.58,
576
+ "learning_rate": 7.719088907379705e-06,
577
+ "loss": 1.1364,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.59,
582
+ "learning_rate": 7.524731811228374e-06,
583
+ "loss": 1.1235,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.6,
588
+ "learning_rate": 7.331365793930698e-06,
589
+ "loss": 1.1377,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.6,
594
+ "learning_rate": 7.139068277792524e-06,
595
+ "loss": 1.1398,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.61,
600
+ "learning_rate": 6.947916257299829e-06,
601
+ "loss": 1.1281,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.61,
606
+ "learning_rate": 6.757986268290713e-06,
607
+ "loss": 1.1355,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.62,
612
+ "learning_rate": 6.569354357311015e-06,
613
+ "loss": 1.1415,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.63,
618
+ "learning_rate": 6.382096051165847e-06,
619
+ "loss": 1.1266,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.63,
624
+ "learning_rate": 6.196286326679231e-06,
625
+ "loss": 1.1503,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.64,
630
+ "learning_rate": 6.0119995806739316e-06,
631
+ "loss": 1.1375,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.65,
636
+ "learning_rate": 5.829309600183536e-06,
637
+ "loss": 1.1273,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.65,
642
+ "learning_rate": 5.648289532908666e-06,
643
+ "loss": 1.1294,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.66,
648
+ "learning_rate": 5.469011857929202e-06,
649
+ "loss": 1.1322,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.66,
654
+ "learning_rate": 5.291548356684177e-06,
655
+ "loss": 1.1385,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.67,
660
+ "learning_rate": 5.115970084231059e-06,
661
+ "loss": 1.1479,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.68,
666
+ "learning_rate": 4.942347340795803e-06,
667
+ "loss": 1.1376,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.68,
672
+ "learning_rate": 4.7707496436252e-06,
673
+ "loss": 1.1315,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.69,
678
+ "learning_rate": 4.601245699152659e-06,
679
+ "loss": 1.1318,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.69,
684
+ "learning_rate": 4.4339033754886974e-06,
685
+ "loss": 1.1319,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.7,
690
+ "learning_rate": 4.268789675247029e-06,
691
+ "loss": 1.1293,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.71,
696
+ "learning_rate": 4.105970708717244e-06,
697
+ "loss": 1.1245,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.71,
702
+ "learning_rate": 3.945511667394719e-06,
703
+ "loss": 1.1403,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.72,
708
+ "learning_rate": 3.787476797878459e-06,
709
+ "loss": 1.141,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.73,
714
+ "learning_rate": 3.6319293761472073e-06,
715
+ "loss": 1.1272,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.73,
720
+ "learning_rate": 3.47893168222425e-06,
721
+ "loss": 1.1353,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.74,
726
+ "learning_rate": 3.3285449752409315e-06,
727
+ "loss": 1.1352,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.74,
732
+ "learning_rate": 3.1808294689089856e-06,
733
+ "loss": 1.1348,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.75,
738
+ "learning_rate": 3.035844307411384e-06,
739
+ "loss": 1.1303,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.76,
744
+ "learning_rate": 2.8936475417214795e-06,
745
+ "loss": 1.1252,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.76,
750
+ "learning_rate": 2.754296106359811e-06,
751
+ "loss": 1.1362,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.77,
756
+ "learning_rate": 2.6178457965979543e-06,
757
+ "loss": 1.1346,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.77,
762
+ "learning_rate": 2.484351246118507e-06,
763
+ "loss": 1.1387,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.78,
768
+ "learning_rate": 2.353865905140187e-06,
769
+ "loss": 1.1345,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.79,
774
+ "learning_rate": 2.226442019016739e-06,
775
+ "loss": 1.1253,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.79,
780
+ "learning_rate": 2.1021306073183166e-06,
781
+ "loss": 1.1274,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.8,
786
+ "learning_rate": 1.9809814434036e-06,
787
+ "loss": 1.1356,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.8,
792
+ "learning_rate": 1.8630430344909378e-06,
793
+ "loss": 1.1375,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.81,
798
+ "learning_rate": 1.748362602236403e-06,
799
+ "loss": 1.1236,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.82,
804
+ "learning_rate": 1.63698606382661e-06,
805
+ "loss": 1.1405,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.82,
810
+ "learning_rate": 1.528958013593801e-06,
811
+ "loss": 1.1332,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.83,
816
+ "learning_rate": 1.4243217051606285e-06,
817
+ "loss": 1.1283,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.84,
822
+ "learning_rate": 1.3231190341217081e-06,
823
+ "loss": 1.1321,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.84,
828
+ "learning_rate": 1.2253905212689554e-06,
829
+ "loss": 1.1269,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.85,
834
+ "learning_rate": 1.1311752963673438e-06,
835
+ "loss": 1.1288,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.85,
840
+ "learning_rate": 1.0405110824876619e-06,
841
+ "loss": 1.1348,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.86,
846
+ "learning_rate": 9.534341809024583e-07,
847
+ "loss": 1.1371,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.87,
852
+ "learning_rate": 8.699794565512976e-07,
853
+ "loss": 1.1294,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.87,
858
+ "learning_rate": 7.901803240810901e-07,
859
+ "loss": 1.1365,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.88,
864
+ "learning_rate": 7.140687344671282e-07,
865
+ "loss": 1.1381,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.88,
870
+ "learning_rate": 6.416751622201389e-07,
871
+ "loss": 1.1416,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.89,
876
+ "learning_rate": 5.730285931845381e-07,
877
+ "loss": 1.1299,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.9,
882
+ "learning_rate": 5.08156512932696e-07,
883
+ "loss": 1.1346,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.9,
888
+ "learning_rate": 4.4708489575993496e-07,
889
+ "loss": 1.139,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.91,
894
+ "learning_rate": 3.8983819428460414e-07,
895
+ "loss": 1.119,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.92,
900
+ "learning_rate": 3.364393296574453e-07,
901
+ "loss": 1.1309,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.92,
906
+ "learning_rate": 2.8690968238412444e-07,
907
+ "loss": 1.1268,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.93,
912
+ "learning_rate": 2.41269083764647e-07,
913
+ "loss": 1.1372,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.93,
918
+ "learning_rate": 1.9953580795304628e-07,
919
+ "loss": 1.1429,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.94,
924
+ "learning_rate": 1.6172656464055748e-07,
925
+ "loss": 1.1181,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.95,
930
+ "learning_rate": 1.278564923651704e-07,
931
+ "loss": 1.1209,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.95,
936
+ "learning_rate": 9.793915245028595e-08,
937
+ "loss": 1.123,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.96,
942
+ "learning_rate": 7.19865235748507e-08,
943
+ "loss": 1.1397,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.96,
948
+ "learning_rate": 5.000899697719552e-08,
949
+ "loss": 1.136,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.97,
954
+ "learning_rate": 3.201537229445051e-08,
955
+ "loss": 1.137,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.98,
960
+ "learning_rate": 1.8012854039244354e-08,
961
+ "loss": 1.1256,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.98,
966
+ "learning_rate": 8.007048715068522e-09,
967
+ "loss": 1.1329,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.99,
972
+ "learning_rate": 2.0019625714740032e-09,
973
+ "loss": 1.1339,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 1.0,
978
+ "learning_rate": 0.0,
979
+ "loss": 1.1352,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 1.0,
984
+ "step": 162,
985
+ "total_flos": 8.291234906646774e+17,
986
+ "train_loss": 1.1575636539930179,
987
+ "train_runtime": 7042.5737,
988
+ "train_samples_per_second": 2.956,
989
+ "train_steps_per_second": 0.023
990
+ }
991
+ ],
992
+ "max_steps": 162,
993
+ "num_train_epochs": 1,
994
+ "total_flos": 8.291234906646774e+17,
995
+ "trial_name": null,
996
+ "trial_params": null
997
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0575a82acae570d523a62fcf420b69fdf61b094c1d8e5466f435e1f11a808164
3
+ size 3771