Kevin Ni commited on
Commit
365bedf
1 Parent(s): 16ec812

upload the model

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 2,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.36.2",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.2"
6
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480ed596a839f341c3b95f5c79f5647f170bedfaa4c5d10edb1efbad513131f8
3
+ size 4987196936
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21e4d2c0692693b4c6004740b8b74dbb62d38cbe9b4960da0004d9377e3a285
3
+ size 4899116440
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858a2307ab19a79be6067e4caf20e67714d781ac9fd7b2c11d2d6052abb1e1e3
3
+ size 4999813120
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:600be01d7a309c69cf9d2f3a7bd59b74bafd7c158cf657e746799504f3c255ce
3
+ size 4999813128
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5342390697d20c9a71a331d39d4833f07381c8d48adca272712d18fe713c62d6
3
+ size 4832007496
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6077feb54ec8f8eb94c429305948613c3d833828824c3118a5d91bbdeaf1b60
3
+ size 4249014896
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28966928384
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
296
+ "model.norm.weight": "model-00006-of-00006.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<unk>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 4096,
41
+ "pad_token": "<unk>",
42
+ "padding_side": "right",
43
+ "sp_model_kwargs": {},
44
+ "spaces_between_special_tokens": false,
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "truncation_side": "left",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": true
49
+ }
trainer_state.json ADDED
@@ -0,0 +1,720 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.96,
5
+ "eval_steps": 37,
6
+ "global_step": 111,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 1.6666666666666667e-06,
14
+ "loss": 0.6214,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 3.3333333333333333e-06,
20
+ "loss": 0.6223,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 5e-06,
26
+ "loss": 0.6031,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 6.666666666666667e-06,
32
+ "loss": 0.5144,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 8.333333333333334e-06,
38
+ "loss": 0.533,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 1e-05,
44
+ "loss": 0.5674,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.19,
49
+ "learning_rate": 1.1666666666666668e-05,
50
+ "loss": 0.5684,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "learning_rate": 1.3333333333333333e-05,
56
+ "loss": 0.6087,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.24,
61
+ "learning_rate": 1.5000000000000002e-05,
62
+ "loss": 0.6242,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.27,
67
+ "learning_rate": 1.6666666666666667e-05,
68
+ "loss": 0.646,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.29,
73
+ "learning_rate": 1.8333333333333333e-05,
74
+ "loss": 0.7024,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.32,
79
+ "learning_rate": 2e-05,
80
+ "loss": 0.5436,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.35,
85
+ "learning_rate": 1.9994965423831853e-05,
86
+ "loss": 0.6681,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.37,
91
+ "learning_rate": 1.9979866764718846e-05,
92
+ "loss": 0.6271,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.4,
97
+ "learning_rate": 1.9954719225730847e-05,
98
+ "loss": 0.5498,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.43,
103
+ "learning_rate": 1.9919548128307954e-05,
104
+ "loss": 0.5232,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.45,
109
+ "learning_rate": 1.9874388886763944e-05,
110
+ "loss": 0.5123,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.48,
115
+ "learning_rate": 1.9819286972627066e-05,
116
+ "loss": 0.4895,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.51,
121
+ "learning_rate": 1.9754297868854075e-05,
122
+ "loss": 0.6108,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.53,
127
+ "learning_rate": 1.9679487013963566e-05,
128
+ "loss": 0.5614,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.56,
133
+ "learning_rate": 1.9594929736144978e-05,
134
+ "loss": 0.5909,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.59,
139
+ "learning_rate": 1.9500711177409456e-05,
140
+ "loss": 0.509,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.61,
145
+ "learning_rate": 1.9396926207859085e-05,
146
+ "loss": 0.5971,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.64,
151
+ "learning_rate": 1.9283679330160726e-05,
152
+ "loss": 0.5839,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.67,
157
+ "learning_rate": 1.9161084574320696e-05,
158
+ "loss": 0.6244,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.69,
163
+ "learning_rate": 1.9029265382866216e-05,
164
+ "loss": 0.6393,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.72,
169
+ "learning_rate": 1.8888354486549238e-05,
170
+ "loss": 0.5592,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.75,
175
+ "learning_rate": 1.873849377069785e-05,
176
+ "loss": 0.5503,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.77,
181
+ "learning_rate": 1.8579834132349773e-05,
182
+ "loss": 0.6075,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.8,
187
+ "learning_rate": 1.8412535328311813e-05,
188
+ "loss": 0.5213,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.83,
193
+ "learning_rate": 1.8236765814298328e-05,
194
+ "loss": 0.6995,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.85,
199
+ "learning_rate": 1.8052702575310588e-05,
200
+ "loss": 0.6255,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.88,
205
+ "learning_rate": 1.7860530947427878e-05,
206
+ "loss": 0.6017,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.91,
211
+ "learning_rate": 1.766044443118978e-05,
212
+ "loss": 0.5557,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.93,
217
+ "learning_rate": 1.745264449675755e-05,
218
+ "loss": 0.6412,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.96,
223
+ "learning_rate": 1.72373403810507e-05,
224
+ "loss": 0.5526,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.99,
229
+ "learning_rate": 1.7014748877063212e-05,
230
+ "loss": 0.5584,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.99,
235
+ "eval_loss": 0.5749802589416504,
236
+ "eval_runtime": 104.2415,
237
+ "eval_samples_per_second": 4.317,
238
+ "eval_steps_per_second": 0.547,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 1.01,
243
+ "learning_rate": 1.6785094115571323e-05,
244
+ "loss": 0.4356,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 1.04,
249
+ "learning_rate": 1.6548607339452853e-05,
250
+ "loss": 0.322,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 1.07,
255
+ "learning_rate": 1.6305526670845225e-05,
256
+ "loss": 0.3272,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 1.09,
261
+ "learning_rate": 1.6056096871376667e-05,
262
+ "loss": 0.2546,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 1.12,
267
+ "learning_rate": 1.5800569095711983e-05,
268
+ "loss": 0.3021,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 1.15,
273
+ "learning_rate": 1.5539200638661106e-05,
274
+ "loss": 0.3077,
275
+ "step": 43
276
+ },
277
+ {
278
+ "epoch": 1.17,
279
+ "learning_rate": 1.5272254676105026e-05,
280
+ "loss": 0.3892,
281
+ "step": 44
282
+ },
283
+ {
284
+ "epoch": 1.2,
285
+ "learning_rate": 1.5000000000000002e-05,
286
+ "loss": 0.3273,
287
+ "step": 45
288
+ },
289
+ {
290
+ "epoch": 1.23,
291
+ "learning_rate": 1.472271074772683e-05,
292
+ "loss": 0.2691,
293
+ "step": 46
294
+ },
295
+ {
296
+ "epoch": 1.25,
297
+ "learning_rate": 1.4440666126057743e-05,
298
+ "loss": 0.3001,
299
+ "step": 47
300
+ },
301
+ {
302
+ "epoch": 1.28,
303
+ "learning_rate": 1.4154150130018867e-05,
304
+ "loss": 0.3688,
305
+ "step": 48
306
+ },
307
+ {
308
+ "epoch": 1.31,
309
+ "learning_rate": 1.3863451256931286e-05,
310
+ "loss": 0.2907,
311
+ "step": 49
312
+ },
313
+ {
314
+ "epoch": 1.33,
315
+ "learning_rate": 1.356886221591872e-05,
316
+ "loss": 0.2813,
317
+ "step": 50
318
+ },
319
+ {
320
+ "epoch": 1.36,
321
+ "learning_rate": 1.3270679633174219e-05,
322
+ "loss": 0.2932,
323
+ "step": 51
324
+ },
325
+ {
326
+ "epoch": 1.39,
327
+ "learning_rate": 1.296920375328275e-05,
328
+ "loss": 0.2974,
329
+ "step": 52
330
+ },
331
+ {
332
+ "epoch": 1.41,
333
+ "learning_rate": 1.266473813690035e-05,
334
+ "loss": 0.361,
335
+ "step": 53
336
+ },
337
+ {
338
+ "epoch": 1.44,
339
+ "learning_rate": 1.2357589355094275e-05,
340
+ "loss": 0.2981,
341
+ "step": 54
342
+ },
343
+ {
344
+ "epoch": 1.47,
345
+ "learning_rate": 1.2048066680651908e-05,
346
+ "loss": 0.2904,
347
+ "step": 55
348
+ },
349
+ {
350
+ "epoch": 1.49,
351
+ "learning_rate": 1.1736481776669307e-05,
352
+ "loss": 0.3182,
353
+ "step": 56
354
+ },
355
+ {
356
+ "epoch": 1.52,
357
+ "learning_rate": 1.1423148382732854e-05,
358
+ "loss": 0.2866,
359
+ "step": 57
360
+ },
361
+ {
362
+ "epoch": 1.55,
363
+ "learning_rate": 1.1108381999010111e-05,
364
+ "loss": 0.3435,
365
+ "step": 58
366
+ },
367
+ {
368
+ "epoch": 1.57,
369
+ "learning_rate": 1.0792499568567885e-05,
370
+ "loss": 0.3217,
371
+ "step": 59
372
+ },
373
+ {
374
+ "epoch": 1.6,
375
+ "learning_rate": 1.0475819158237426e-05,
376
+ "loss": 0.4683,
377
+ "step": 60
378
+ },
379
+ {
380
+ "epoch": 1.63,
381
+ "learning_rate": 1.015865963834808e-05,
382
+ "loss": 0.2712,
383
+ "step": 61
384
+ },
385
+ {
386
+ "epoch": 1.65,
387
+ "learning_rate": 9.841340361651921e-06,
388
+ "loss": 0.269,
389
+ "step": 62
390
+ },
391
+ {
392
+ "epoch": 1.68,
393
+ "learning_rate": 9.524180841762577e-06,
394
+ "loss": 0.2982,
395
+ "step": 63
396
+ },
397
+ {
398
+ "epoch": 1.71,
399
+ "learning_rate": 9.207500431432115e-06,
400
+ "loss": 0.291,
401
+ "step": 64
402
+ },
403
+ {
404
+ "epoch": 1.73,
405
+ "learning_rate": 8.89161800098989e-06,
406
+ "loss": 0.2876,
407
+ "step": 65
408
+ },
409
+ {
410
+ "epoch": 1.76,
411
+ "learning_rate": 8.576851617267151e-06,
412
+ "loss": 0.3305,
413
+ "step": 66
414
+ },
415
+ {
416
+ "epoch": 1.79,
417
+ "learning_rate": 8.263518223330698e-06,
418
+ "loss": 0.277,
419
+ "step": 67
420
+ },
421
+ {
422
+ "epoch": 1.81,
423
+ "learning_rate": 7.951933319348095e-06,
424
+ "loss": 0.3488,
425
+ "step": 68
426
+ },
427
+ {
428
+ "epoch": 1.84,
429
+ "learning_rate": 7.642410644905726e-06,
430
+ "loss": 0.2724,
431
+ "step": 69
432
+ },
433
+ {
434
+ "epoch": 1.87,
435
+ "learning_rate": 7.335261863099652e-06,
436
+ "loss": 0.2422,
437
+ "step": 70
438
+ },
439
+ {
440
+ "epoch": 1.89,
441
+ "learning_rate": 7.0307962467172555e-06,
442
+ "loss": 0.3694,
443
+ "step": 71
444
+ },
445
+ {
446
+ "epoch": 1.92,
447
+ "learning_rate": 6.729320366825785e-06,
448
+ "loss": 0.2733,
449
+ "step": 72
450
+ },
451
+ {
452
+ "epoch": 1.95,
453
+ "learning_rate": 6.431137784081283e-06,
454
+ "loss": 0.3317,
455
+ "step": 73
456
+ },
457
+ {
458
+ "epoch": 1.97,
459
+ "learning_rate": 6.136548743068713e-06,
460
+ "loss": 0.2657,
461
+ "step": 74
462
+ },
463
+ {
464
+ "epoch": 1.97,
465
+ "eval_loss": 0.5498270392417908,
466
+ "eval_runtime": 104.2243,
467
+ "eval_samples_per_second": 4.318,
468
+ "eval_steps_per_second": 0.547,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 2.0,
473
+ "learning_rate": 5.845849869981137e-06,
474
+ "loss": 0.32,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 2.03,
479
+ "learning_rate": 5.559333873942259e-06,
480
+ "loss": 0.155,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 2.05,
485
+ "learning_rate": 5.277289252273175e-06,
486
+ "loss": 0.1405,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 2.08,
491
+ "learning_rate": 5.000000000000003e-06,
492
+ "loss": 0.1197,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 2.11,
497
+ "learning_rate": 4.727745323894976e-06,
498
+ "loss": 0.1303,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 2.13,
503
+ "learning_rate": 4.460799361338898e-06,
504
+ "loss": 0.1307,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 2.16,
509
+ "learning_rate": 4.19943090428802e-06,
510
+ "loss": 0.1019,
511
+ "step": 81
512
+ },
513
+ {
514
+ "epoch": 2.19,
515
+ "learning_rate": 3.943903128623336e-06,
516
+ "loss": 0.1476,
517
+ "step": 82
518
+ },
519
+ {
520
+ "epoch": 2.21,
521
+ "learning_rate": 3.6944733291547784e-06,
522
+ "loss": 0.1323,
523
+ "step": 83
524
+ },
525
+ {
526
+ "epoch": 2.24,
527
+ "learning_rate": 3.4513926605471504e-06,
528
+ "loss": 0.1013,
529
+ "step": 84
530
+ },
531
+ {
532
+ "epoch": 2.27,
533
+ "learning_rate": 3.2149058844286796e-06,
534
+ "loss": 0.1221,
535
+ "step": 85
536
+ },
537
+ {
538
+ "epoch": 2.29,
539
+ "learning_rate": 2.9852511229367862e-06,
540
+ "loss": 0.1113,
541
+ "step": 86
542
+ },
543
+ {
544
+ "epoch": 2.32,
545
+ "learning_rate": 2.7626596189492983e-06,
546
+ "loss": 0.1214,
547
+ "step": 87
548
+ },
549
+ {
550
+ "epoch": 2.35,
551
+ "learning_rate": 2.5473555032424534e-06,
552
+ "loss": 0.0978,
553
+ "step": 88
554
+ },
555
+ {
556
+ "epoch": 2.37,
557
+ "learning_rate": 2.339555568810221e-06,
558
+ "loss": 0.1203,
559
+ "step": 89
560
+ },
561
+ {
562
+ "epoch": 2.4,
563
+ "learning_rate": 2.1394690525721275e-06,
564
+ "loss": 0.0996,
565
+ "step": 90
566
+ },
567
+ {
568
+ "epoch": 2.43,
569
+ "learning_rate": 1.947297424689414e-06,
570
+ "loss": 0.0911,
571
+ "step": 91
572
+ },
573
+ {
574
+ "epoch": 2.45,
575
+ "learning_rate": 1.7632341857016733e-06,
576
+ "loss": 0.1242,
577
+ "step": 92
578
+ },
579
+ {
580
+ "epoch": 2.48,
581
+ "learning_rate": 1.587464671688187e-06,
582
+ "loss": 0.0862,
583
+ "step": 93
584
+ },
585
+ {
586
+ "epoch": 2.51,
587
+ "learning_rate": 1.4201658676502294e-06,
588
+ "loss": 0.1283,
589
+ "step": 94
590
+ },
591
+ {
592
+ "epoch": 2.53,
593
+ "learning_rate": 1.2615062293021508e-06,
594
+ "loss": 0.0871,
595
+ "step": 95
596
+ },
597
+ {
598
+ "epoch": 2.56,
599
+ "learning_rate": 1.1116455134507665e-06,
600
+ "loss": 0.1011,
601
+ "step": 96
602
+ },
603
+ {
604
+ "epoch": 2.59,
605
+ "learning_rate": 9.707346171337895e-07,
606
+ "loss": 0.1149,
607
+ "step": 97
608
+ },
609
+ {
610
+ "epoch": 2.61,
611
+ "learning_rate": 8.389154256793042e-07,
612
+ "loss": 0.1035,
613
+ "step": 98
614
+ },
615
+ {
616
+ "epoch": 2.64,
617
+ "learning_rate": 7.163206698392744e-07,
618
+ "loss": 0.0994,
619
+ "step": 99
620
+ },
621
+ {
622
+ "epoch": 2.67,
623
+ "learning_rate": 6.030737921409169e-07,
624
+ "loss": 0.1097,
625
+ "step": 100
626
+ },
627
+ {
628
+ "epoch": 2.69,
629
+ "learning_rate": 4.992888225905467e-07,
630
+ "loss": 0.1054,
631
+ "step": 101
632
+ },
633
+ {
634
+ "epoch": 2.72,
635
+ "learning_rate": 4.0507026385502747e-07,
636
+ "loss": 0.1129,
637
+ "step": 102
638
+ },
639
+ {
640
+ "epoch": 2.75,
641
+ "learning_rate": 3.2051298603643754e-07,
642
+ "loss": 0.0807,
643
+ "step": 103
644
+ },
645
+ {
646
+ "epoch": 2.77,
647
+ "learning_rate": 2.4570213114592957e-07,
648
+ "loss": 0.0884,
649
+ "step": 104
650
+ },
651
+ {
652
+ "epoch": 2.8,
653
+ "learning_rate": 1.8071302737293294e-07,
654
+ "loss": 0.0887,
655
+ "step": 105
656
+ },
657
+ {
658
+ "epoch": 2.83,
659
+ "learning_rate": 1.2561111323605714e-07,
660
+ "loss": 0.1025,
661
+ "step": 106
662
+ },
663
+ {
664
+ "epoch": 2.85,
665
+ "learning_rate": 8.04518716920466e-08,
666
+ "loss": 0.1056,
667
+ "step": 107
668
+ },
669
+ {
670
+ "epoch": 2.88,
671
+ "learning_rate": 4.528077426915412e-08,
672
+ "loss": 0.1127,
673
+ "step": 108
674
+ },
675
+ {
676
+ "epoch": 2.91,
677
+ "learning_rate": 2.013323528115674e-08,
678
+ "loss": 0.1046,
679
+ "step": 109
680
+ },
681
+ {
682
+ "epoch": 2.93,
683
+ "learning_rate": 5.034576168149175e-09,
684
+ "loss": 0.0842,
685
+ "step": 110
686
+ },
687
+ {
688
+ "epoch": 2.96,
689
+ "learning_rate": 0.0,
690
+ "loss": 0.1081,
691
+ "step": 111
692
+ },
693
+ {
694
+ "epoch": 2.96,
695
+ "eval_loss": 0.622760534286499,
696
+ "eval_runtime": 104.3841,
697
+ "eval_samples_per_second": 4.311,
698
+ "eval_steps_per_second": 0.546,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 2.96,
703
+ "step": 111,
704
+ "total_flos": 3.879485131928371e+16,
705
+ "train_loss": 0.33863106195454123,
706
+ "train_runtime": 3186.7794,
707
+ "train_samples_per_second": 0.565,
708
+ "train_steps_per_second": 0.035
709
+ }
710
+ ],
711
+ "logging_steps": 1.0,
712
+ "max_steps": 111,
713
+ "num_input_tokens_seen": 0,
714
+ "num_train_epochs": 3,
715
+ "save_steps": 37,
716
+ "total_flos": 3.879485131928371e+16,
717
+ "train_batch_size": 1,
718
+ "trial_name": null,
719
+ "trial_params": null
720
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcbdaa817e9ff4b67bb94b9d3cbdc30ed9d8b406243c7932f6df7aced1665ede
3
+ size 4920