luohy commited on
Commit
9ab391b
1 Parent(s): 2395f5d

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/sls/d/llm/llama2-7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.33.1",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.33.1"
10
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd283fcf100b717b8c17e80ce6fb3b43116d4b9a6de66887881e7dd7c009afa
3
+ size 9976620122
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a604583769f7e56c5a21ac59b563173c7649cc8c18377363afd5ee3591c020a0
3
+ size 3500310787
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476831232
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1800,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "spaces_between_special_tokens": false,
27
+ "tokenizer_class": "LlamaTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "use_default_system_prompt": true
37
+ }
trainer_state.json ADDED
@@ -0,0 +1,718 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9998381091144566,
5
+ "eval_steps": 500,
6
+ "global_step": 1158,
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": 5.7142857142857145e-06,
14
+ "loss": 1.3326,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 1.1428571428571429e-05,
20
+ "loss": 0.841,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 1.7142857142857142e-05,
26
+ "loss": 0.7663,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 1.9999021765072576e-05,
32
+ "loss": 0.7506,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 1.999119703394801e-05,
38
+ "loss": 0.7395,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 1.9975553694939593e-05,
44
+ "loss": 0.7412,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.18,
49
+ "learning_rate": 1.9952103989737013e-05,
50
+ "loss": 0.7374,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "learning_rate": 1.9920866268899203e-05,
56
+ "loss": 0.7292,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.23,
61
+ "learning_rate": 1.988186497749411e-05,
62
+ "loss": 0.7117,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.26,
67
+ "learning_rate": 1.9835130635969228e-05,
68
+ "loss": 0.7154,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.28,
73
+ "learning_rate": 1.978069981626783e-05,
74
+ "loss": 0.7063,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.31,
79
+ "learning_rate": 1.9718615113209588e-05,
80
+ "loss": 0.7022,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.34,
85
+ "learning_rate": 1.9648925111158037e-05,
86
+ "loss": 0.6856,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.36,
91
+ "learning_rate": 1.9571684346000877e-05,
92
+ "loss": 0.6846,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.39,
97
+ "learning_rate": 1.9486953262472945e-05,
98
+ "loss": 0.6944,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.41,
103
+ "learning_rate": 1.9394798166855205e-05,
104
+ "loss": 0.6608,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.44,
109
+ "learning_rate": 1.9295291175086782e-05,
110
+ "loss": 0.6902,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.47,
115
+ "learning_rate": 1.9188510156330676e-05,
116
+ "loss": 0.6819,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.49,
121
+ "learning_rate": 1.9074538672037254e-05,
122
+ "loss": 0.6637,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.52,
127
+ "learning_rate": 1.8953465910553274e-05,
128
+ "loss": 0.6487,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.54,
133
+ "learning_rate": 1.8825386617327586e-05,
134
+ "loss": 0.6593,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.57,
139
+ "learning_rate": 1.869040102076809e-05,
140
+ "loss": 0.6442,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.6,
145
+ "learning_rate": 1.8548614753808046e-05,
146
+ "loss": 0.648,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.62,
151
+ "learning_rate": 1.8400138771243056e-05,
152
+ "loss": 0.6753,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.65,
157
+ "learning_rate": 1.8245089262903407e-05,
158
+ "loss": 0.6119,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.67,
163
+ "learning_rate": 1.8083587562729796e-05,
164
+ "loss": 0.6314,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.7,
169
+ "learning_rate": 1.7915760053823454e-05,
170
+ "loss": 0.6128,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.73,
175
+ "learning_rate": 1.7741738069545126e-05,
176
+ "loss": 0.6201,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.75,
181
+ "learning_rate": 1.756165779074016e-05,
182
+ "loss": 0.6087,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.78,
187
+ "learning_rate": 1.7375660139170276e-05,
188
+ "loss": 0.5939,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.8,
193
+ "learning_rate": 1.7183890667235245e-05,
194
+ "loss": 0.5884,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.83,
199
+ "learning_rate": 1.698649944407093e-05,
200
+ "loss": 0.6041,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.85,
205
+ "learning_rate": 1.6783640938112742e-05,
206
+ "loss": 0.5939,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.88,
211
+ "learning_rate": 1.6575473896216393e-05,
212
+ "loss": 0.5867,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.91,
217
+ "learning_rate": 1.6362161219430618e-05,
218
+ "loss": 0.5946,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.93,
223
+ "learning_rate": 1.6143869835519003e-05,
224
+ "loss": 0.5657,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.96,
229
+ "learning_rate": 1.592077056833073e-05,
230
+ "loss": 0.5826,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.98,
235
+ "learning_rate": 1.5693038004122415e-05,
236
+ "loss": 0.5883,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 1.01,
241
+ "learning_rate": 1.546085035493571e-05,
242
+ "loss": 0.5367,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 1.04,
247
+ "learning_rate": 1.522438931913751e-05,
248
+ "loss": 0.4847,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 1.06,
253
+ "learning_rate": 1.4983839939231986e-05,
254
+ "loss": 0.487,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 1.09,
259
+ "learning_rate": 1.4739390457055593e-05,
260
+ "loss": 0.4939,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 1.11,
265
+ "learning_rate": 1.4491232166468532e-05,
266
+ "loss": 0.4791,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 1.14,
271
+ "learning_rate": 1.4239559263657764e-05,
272
+ "loss": 0.499,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 1.17,
277
+ "learning_rate": 1.3984568695168877e-05,
278
+ "loss": 0.4845,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 1.19,
283
+ "learning_rate": 1.3726460003785609e-05,
284
+ "loss": 0.4752,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 1.22,
289
+ "learning_rate": 1.3465435172377733e-05,
290
+ "loss": 0.4911,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 1.24,
295
+ "learning_rate": 1.3201698465839414e-05,
296
+ "loss": 0.471,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 1.27,
301
+ "learning_rate": 1.2935456271241784e-05,
302
+ "loss": 0.4681,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 1.3,
307
+ "learning_rate": 1.266691693632483e-05,
308
+ "loss": 0.4596,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 1.32,
313
+ "learning_rate": 1.2396290606454912e-05,
314
+ "loss": 0.4635,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 1.35,
319
+ "learning_rate": 1.2123789060175593e-05,
320
+ "loss": 0.477,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 1.37,
325
+ "learning_rate": 1.1849625543480402e-05,
326
+ "loss": 0.4493,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 1.4,
331
+ "learning_rate": 1.1574014602937274e-05,
332
+ "loss": 0.4637,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 1.42,
337
+ "learning_rate": 1.129717191779517e-05,
338
+ "loss": 0.4229,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 1.45,
343
+ "learning_rate": 1.1019314131204394e-05,
344
+ "loss": 0.4225,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 1.48,
349
+ "learning_rate": 1.0740658680682523e-05,
350
+ "loss": 0.4398,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 1.5,
355
+ "learning_rate": 1.0461423627958803e-05,
356
+ "loss": 0.4286,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 1.53,
361
+ "learning_rate": 1.0181827488329975e-05,
362
+ "loss": 0.428,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 1.55,
367
+ "learning_rate": 9.902089059661206e-06,
368
+ "loss": 0.4289,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 1.58,
373
+ "learning_rate": 9.622427251165921e-06,
374
+ "loss": 0.4253,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 1.61,
379
+ "learning_rate": 9.34306091209845e-06,
380
+ "loss": 0.413,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 1.63,
385
+ "learning_rate": 9.064208660493614e-06,
386
+ "loss": 0.436,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 1.66,
391
+ "learning_rate": 8.786088712087269e-06,
392
+ "loss": 0.4113,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 1.68,
397
+ "learning_rate": 8.508918709551643e-06,
398
+ "loss": 0.4073,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 1.71,
403
+ "learning_rate": 8.232915552179152e-06,
404
+ "loss": 0.4055,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 1.74,
409
+ "learning_rate": 7.958295226147911e-06,
410
+ "loss": 0.4133,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 1.76,
415
+ "learning_rate": 7.685272635501836e-06,
416
+ "loss": 0.3992,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 1.79,
421
+ "learning_rate": 7.414061433977566e-06,
422
+ "loss": 0.3877,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 1.81,
427
+ "learning_rate": 7.144873857809769e-06,
428
+ "loss": 0.3814,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 1.84,
433
+ "learning_rate": 6.8779205596457885e-06,
434
+ "loss": 0.3643,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 1.86,
439
+ "learning_rate": 6.613410443699453e-06,
440
+ "loss": 0.3764,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 1.89,
445
+ "learning_rate": 6.3515505022731805e-06,
446
+ "loss": 0.3554,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 1.92,
451
+ "learning_rate": 6.092545653776194e-06,
452
+ "loss": 0.3686,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 1.94,
457
+ "learning_rate": 5.836598582365717e-06,
458
+ "loss": 0.3535,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 1.97,
463
+ "learning_rate": 5.583909579336528e-06,
464
+ "loss": 0.3883,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 1.99,
469
+ "learning_rate": 5.334676386383093e-06,
470
+ "loss": 0.3548,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 2.02,
475
+ "learning_rate": 5.089094040856877e-06,
476
+ "loss": 0.334,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 2.05,
481
+ "learning_rate": 4.847354723139893e-06,
482
+ "loss": 0.3223,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 2.07,
487
+ "learning_rate": 4.609647606254046e-06,
488
+ "loss": 0.315,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 2.1,
493
+ "learning_rate": 5.7142857142857145e-06,
494
+ "loss": 0.3239,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 2.12,
499
+ "learning_rate": 1.1428571428571429e-05,
500
+ "loss": 0.3096,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 2.15,
505
+ "learning_rate": 1.7142857142857142e-05,
506
+ "loss": 0.2924,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 2.18,
511
+ "learning_rate": 1.9999021765072576e-05,
512
+ "loss": 0.2998,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 2.2,
517
+ "learning_rate": 1.999119703394801e-05,
518
+ "loss": 0.291,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 2.23,
523
+ "learning_rate": 1.9975553694939593e-05,
524
+ "loss": 0.3037,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 2.25,
529
+ "learning_rate": 1.9952103989737013e-05,
530
+ "loss": 0.2889,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 2.28,
535
+ "learning_rate": 1.9920866268899203e-05,
536
+ "loss": 0.3032,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 2.31,
541
+ "learning_rate": 1.988186497749411e-05,
542
+ "loss": 0.3041,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 2.33,
547
+ "learning_rate": 1.9835130635969228e-05,
548
+ "loss": 0.2982,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 2.36,
553
+ "learning_rate": 1.978069981626783e-05,
554
+ "loss": 0.271,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 2.38,
559
+ "learning_rate": 1.9718615113209588e-05,
560
+ "loss": 0.2896,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 2.41,
565
+ "learning_rate": 1.9648925111158037e-05,
566
+ "loss": 0.284,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 2.44,
571
+ "learning_rate": 1.9571684346000877e-05,
572
+ "loss": 0.2854,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 2.46,
577
+ "learning_rate": 1.9486953262472945e-05,
578
+ "loss": 0.2717,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 2.49,
583
+ "learning_rate": 1.9394798166855205e-05,
584
+ "loss": 0.2885,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 2.51,
589
+ "learning_rate": 1.9295291175086782e-05,
590
+ "loss": 0.2797,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 2.54,
595
+ "learning_rate": 1.9188510156330676e-05,
596
+ "loss": 0.2627,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 2.56,
601
+ "learning_rate": 1.9074538672037254e-05,
602
+ "loss": 0.2887,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 2.59,
607
+ "learning_rate": 1.8953465910553274e-05,
608
+ "loss": 0.2671,
609
+ "step": 1000
610
+ },
611
+ {
612
+ "epoch": 2.62,
613
+ "learning_rate": 1.8825386617327586e-05,
614
+ "loss": 0.2786,
615
+ "step": 1010
616
+ },
617
+ {
618
+ "epoch": 2.64,
619
+ "learning_rate": 1.869040102076809e-05,
620
+ "loss": 0.2705,
621
+ "step": 1020
622
+ },
623
+ {
624
+ "epoch": 2.67,
625
+ "learning_rate": 1.8548614753808046e-05,
626
+ "loss": 0.2637,
627
+ "step": 1030
628
+ },
629
+ {
630
+ "epoch": 2.69,
631
+ "learning_rate": 1.8400138771243056e-05,
632
+ "loss": 0.2599,
633
+ "step": 1040
634
+ },
635
+ {
636
+ "epoch": 2.72,
637
+ "learning_rate": 1.8245089262903407e-05,
638
+ "loss": 0.2632,
639
+ "step": 1050
640
+ },
641
+ {
642
+ "epoch": 2.75,
643
+ "learning_rate": 1.8083587562729796e-05,
644
+ "loss": 0.2529,
645
+ "step": 1060
646
+ },
647
+ {
648
+ "epoch": 2.77,
649
+ "learning_rate": 1.7915760053823454e-05,
650
+ "loss": 0.2387,
651
+ "step": 1070
652
+ },
653
+ {
654
+ "epoch": 2.8,
655
+ "learning_rate": 1.7741738069545126e-05,
656
+ "loss": 0.2451,
657
+ "step": 1080
658
+ },
659
+ {
660
+ "epoch": 2.82,
661
+ "learning_rate": 1.756165779074016e-05,
662
+ "loss": 0.2542,
663
+ "step": 1090
664
+ },
665
+ {
666
+ "epoch": 2.85,
667
+ "learning_rate": 1.7375660139170276e-05,
668
+ "loss": 0.2492,
669
+ "step": 1100
670
+ },
671
+ {
672
+ "epoch": 2.88,
673
+ "learning_rate": 1.7183890667235245e-05,
674
+ "loss": 0.2344,
675
+ "step": 1110
676
+ },
677
+ {
678
+ "epoch": 2.9,
679
+ "learning_rate": 1.698649944407093e-05,
680
+ "loss": 0.249,
681
+ "step": 1120
682
+ },
683
+ {
684
+ "epoch": 2.93,
685
+ "learning_rate": 1.6783640938112742e-05,
686
+ "loss": 0.2457,
687
+ "step": 1130
688
+ },
689
+ {
690
+ "epoch": 2.95,
691
+ "learning_rate": 1.6575473896216393e-05,
692
+ "loss": 0.2497,
693
+ "step": 1140
694
+ },
695
+ {
696
+ "epoch": 2.98,
697
+ "learning_rate": 1.6362161219430618e-05,
698
+ "loss": 0.2449,
699
+ "step": 1150
700
+ },
701
+ {
702
+ "epoch": 3.0,
703
+ "step": 1158,
704
+ "total_flos": 1.0577162556235842e+19,
705
+ "train_loss": 0.08461039424560231,
706
+ "train_runtime": 32175.0491,
707
+ "train_samples_per_second": 4.607,
708
+ "train_steps_per_second": 0.036
709
+ }
710
+ ],
711
+ "logging_steps": 10,
712
+ "max_steps": 1158,
713
+ "num_train_epochs": 3,
714
+ "save_steps": 400,
715
+ "total_flos": 1.0577162556235842e+19,
716
+ "trial_name": null,
717
+ "trial_params": null
718
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec8d89422f3813e06b81a1e6d7cf08c8459b5d0b1542275c6d5e34bc59f5528
3
+ size 4987