Invalid-Null commited on
Commit
6a34e19
·
verified ·
1 Parent(s): d808d66

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # 北洋微衍V0.6/PeiYang MicroEmergence-0.6
2
+
3
+ ## 模型曾用名 / Model Name History
4
+
5
+ 此模型在开发过程中经历了以下命名阶段:
6
+ This model has gone through the following naming stages during development:
7
+
8
+ * 早期阶段 / Initial Stage:
9
+ Invalid-Null/Non-Null
10
+
11
+ * 发展阶段 / Development Stage:
12
+ 天津大学/北洋微衍 (Tianjin University/Peiyang MicroDerivation)
13
+
14
+ * 当前版本 / Current Release:
15
+ 天津大学/北洋微衍 (Tianjin University/Peiyang MicroEmergence)
16
+
17
+ ## 模型概述 / Model Overview
18
+
19
+ 本模型专注于计算催化领域,特别是丙烷脱氢(PDH)过程。
20
+ This model focuses on computational catalysis, specifically designed for propane dehydrogenation (PDH) processes.
21
+
22
+ ## 技术基础 / Technical Foundation
23
+
24
+ * 基础框架 / Base Framework:
25
+ 基于ModelScope的ms-swift框架开发
26
+ Developed using ModelScope's ms-swift framework
27
+
28
+ * 基础模型 / Base Model:
29
+ 基于零一万物的Yi系列6B模型训练,包括yi-6B、yi-6B-chat、yi-1.5-6B、yi-1.5-6B-chat
30
+ Fine-tuned on 01.AI's Yi-6B series model, including yi-6B, yi-6B-chat, yi-1.5-6B and yi-1.5-6B-chat
31
+
32
+ ## 当前状态 / Current Status
33
+
34
+ 详细的技术规格和性能指标将在相关研究论文发表后提供。
35
+ Detailed technical specifications and performance metrics will be available upon publication of our research paper.
36
+
37
+ ## 致谢 / Acknowledgments
38
+
39
+ 特别感谢以下开源项目的贡献:
40
+ We would like to acknowledge the contributions of the following open-source projects:
41
+ * ModelScope的ms-swift框架 / ModelScope's ms-swift framework
42
+ * 零一万物的Yi系列模型 / 01.AI's Yi series models
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/home/wusc/.cache/modelscope/hub/01ai/Yi-1___5-6B-Chat",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 5000000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.40.2",
27
+ "use_cache": false,
28
+ "vocab_size": 64000
29
+ }
configuration.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "framework": "Pytorch",
3
+ "task": "text-generation"
4
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": 7,
4
+ "max_new_tokens": 2048,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.3,
7
+ "top_k": 20,
8
+ "top_p": 0.7,
9
+ "transformers_version": "4.40.2"
10
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09830b4caa65765afa17e6cf936b8753e4457e6c83d3a5c0967d6431748d824c
3
+ size 4932711312
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978a95499a60df4859f0ba065224fb4372654536b5a80be19d4e2d4f09045b57
3
+ size 4976802680
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9db7277c0f7679bb30ae3cd25e44838c203e75ecb306fe3ca6e42d2621377ee
3
+ size 2212590520
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12122071040
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
sft_args.json ADDED
@@ -0,0 +1,230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "yi-1_5-6b-chat",
3
+ "model_id_or_path": "MixModel4",
4
+ "model_revision": "master",
5
+ "model_layer_cls_name": null,
6
+ "sft_type": "full",
7
+ "freeze_parameters": 0.0,
8
+ "additional_trainable_parameters": [],
9
+ "tuner_backend": "peft",
10
+ "template_type": "yi1_5",
11
+ "output_dir": "/data/home/wusc/CatalGPT/SwiftLog/output/yi-1.5-6b-chat/v23-20240525-003630.833747489",
12
+ "add_output_dir_suffix": false,
13
+ "ddp_backend": "nccl",
14
+ "ddp_find_unused_parameters": null,
15
+ "ddp_broadcast_buffers": null,
16
+ "seed": 0,
17
+ "resume_from_checkpoint": null,
18
+ "ignore_data_skip": false,
19
+ "dtype": "fp16",
20
+ "packing": false,
21
+ "dataset": [
22
+ "coig-cqia:ruozhiba",
23
+ "coig-cqia:exam",
24
+ "coig-cqia:segmentfault",
25
+ "cot-en",
26
+ "cot-zh",
27
+ "blossom-math-zh",
28
+ "leetcode-python-en",
29
+ "codefuse-python-en",
30
+ "alpaca-en",
31
+ "alpaca-zh",
32
+ "sharegpt-gpt4",
33
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/PDH_QAPairFromARG_English1985.csv",
34
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/PDH_QAPairFromARG_Chinese1985.csv",
35
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/BackgroundKnowledgeQAPairs51790.csv",
36
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/biology.csv",
37
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/chemistry.csv",
38
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/chinese.csv",
39
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/english.csv",
40
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/geography.csv",
41
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/mathcloze.csv",
42
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/mathqa.csv",
43
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/MultiChoices.csv",
44
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/gaokao-benchmark/physics.csv",
45
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/CSL396209.csv",
46
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/scimrc21297.csv",
47
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/MultiHopRAG/MultiHopRAG.csv",
48
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/physical_reasoning/physical_reasoning.csv",
49
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/physical_reasoning/physical_reasoning_longer.csv",
50
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/physical_reasoning/physical_reasoning_magic.csv",
51
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/race/race_high_test-00000-of-00001.csv",
52
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/race/race_high_train-00000-of-00001.csv",
53
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/race/race_high_validation-00000-of-00001.csv",
54
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/race/race_middle_test-00000-of-00001.csv",
55
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/race/race_middle_train-00000-of-00001.csv",
56
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/race/race_middle_validation-00000-of-00001.csv",
57
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/SystemConversationsTransformed.jsonl",
58
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/WikiQA-Altered_Numeric_QA_16K.jsonl",
59
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/WikiQA-Altered_Numeric_QA_2K.jsonl",
60
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/WikiQA-Altered_Numeric_QA_4K.jsonl",
61
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/WikiQA-Altered_Numeric_QA_8K.jsonl",
62
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/WikiQA-Free_Form_QA_16K.jsonl",
63
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/WikiQA-Free_Form_QA_2K.jsonl",
64
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/WikiQA-Free_Form_QA_4K.jsonl",
65
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/Smaug/WikiQA-Free_Form_QA_8K.jsonl",
66
+ "/data/home/wusc/CatalGPT/SupervisedFineTuning/truthful_qa/truthful_qa_multiple_choice.csv",
67
+ "self-cognition#8192"
68
+ ],
69
+ "val_dataset": null,
70
+ "dataset_seed": 0,
71
+ "dataset_test_ratio": 0.01,
72
+ "use_loss_scale": false,
73
+ "system": "You are an expert in the field of chemistry and chemical engineering. Explain scientific concepts, theories, and phenomena in an engaging and accessible way. Take a deep breath and think step by step, which is very import to my career.",
74
+ "max_length": 4096,
75
+ "truncation_strategy": "delete",
76
+ "check_dataset_strategy": "warning",
77
+ "model_name": [
78
+ "非空",
79
+ "Non null"
80
+ ],
81
+ "model_author": [
82
+ "空",
83
+ "null"
84
+ ],
85
+ "quant_method": null,
86
+ "quantization_bit": 0,
87
+ "hqq_axis": 0,
88
+ "hqq_dynamic_config_path": null,
89
+ "bnb_4bit_comp_dtype": "fp16",
90
+ "bnb_4bit_quant_type": "nf4",
91
+ "bnb_4bit_use_double_quant": true,
92
+ "bnb_4bit_quant_storage": null,
93
+ "lora_target_modules": [
94
+ "model.embed_tokens",
95
+ "q_proj",
96
+ "k_proj",
97
+ "v_proj",
98
+ "gate_proj",
99
+ "o_proj",
100
+ "up_proj",
101
+ "down_proj"
102
+ ],
103
+ "lora_rank": 16,
104
+ "lora_alpha": 32,
105
+ "lora_dropout_p": 0.05,
106
+ "lora_bias_trainable": "none",
107
+ "lora_modules_to_save": [],
108
+ "lora_dtype": "fp16",
109
+ "lora_lr_ratio": null,
110
+ "use_rslora": true,
111
+ "use_dora": false,
112
+ "adapter_act": "gelu",
113
+ "adapter_length": 128,
114
+ "use_galore": false,
115
+ "galore_rank": 128,
116
+ "galore_target_modules": null,
117
+ "galore_update_proj_gap": 50,
118
+ "galore_scale": 1.0,
119
+ "galore_proj_type": "std",
120
+ "galore_optim_per_parameter": false,
121
+ "galore_with_embedding": false,
122
+ "adalora_target_r": 8,
123
+ "adalora_init_r": 12,
124
+ "adalora_tinit": 0,
125
+ "adalora_tfinal": 0,
126
+ "adalora_deltaT": 1,
127
+ "adalora_beta1": 0.85,
128
+ "adalora_beta2": 0.85,
129
+ "adalora_orth_reg_weight": 0.5,
130
+ "ia3_target_modules": [
131
+ "DEFAULT"
132
+ ],
133
+ "ia3_feedforward_modules": [],
134
+ "ia3_modules_to_save": [],
135
+ "llamapro_num_new_blocks": 4,
136
+ "llamapro_num_groups": null,
137
+ "neftune_noise_alpha": 5.0,
138
+ "neftune_backend": "transformers",
139
+ "lisa_activated_layers": 0,
140
+ "lisa_step_interval": 20,
141
+ "gradient_checkpointing": true,
142
+ "deepspeed": null,
143
+ "batch_size": 2,
144
+ "eval_batch_size": 2,
145
+ "num_train_epochs": 2,
146
+ "max_steps": -1,
147
+ "optim": "adamw_torch",
148
+ "adam_beta1": 0.9,
149
+ "adam_beta2": 0.999,
150
+ "learning_rate": 0.0002,
151
+ "weight_decay": 0.1,
152
+ "gradient_accumulation_steps": 32,
153
+ "max_grad_norm": 0.5,
154
+ "predict_with_generate": false,
155
+ "lr_scheduler_type": "cosine",
156
+ "warmup_ratio": 0.1,
157
+ "eval_steps": 160,
158
+ "save_steps": 160,
159
+ "save_only_model": false,
160
+ "save_total_limit": 2,
161
+ "logging_steps": 5,
162
+ "dataloader_num_workers": 4,
163
+ "dataloader_pin_memory": true,
164
+ "push_to_hub": false,
165
+ "hub_model_id": null,
166
+ "hub_token": null,
167
+ "hub_private_repo": false,
168
+ "push_hub_strategy": "push_best",
169
+ "test_oom_error": false,
170
+ "disable_tqdm": false,
171
+ "lazy_tokenize": true,
172
+ "preprocess_num_proc": 2,
173
+ "use_flash_attn": false,
174
+ "ignore_args_error": false,
175
+ "check_model_is_latest": true,
176
+ "logging_dir": "/data/home/wusc/CatalGPT/SwiftLog/output/yi-1.5-6b-chat/v23-20240525-003630.833747489/runs",
177
+ "report_to": [
178
+ "tensorboard"
179
+ ],
180
+ "acc_strategy": "token",
181
+ "save_on_each_node": true,
182
+ "evaluation_strategy": "steps",
183
+ "save_strategy": "steps",
184
+ "save_safetensors": true,
185
+ "gpu_memory_fraction": null,
186
+ "include_num_input_tokens_seen": false,
187
+ "local_repo_path": null,
188
+ "custom_register_path": null,
189
+ "custom_dataset_info": null,
190
+ "device_map_config_path": null,
191
+ "max_new_tokens": 2048,
192
+ "do_sample": true,
193
+ "temperature": 0.3,
194
+ "top_k": 20,
195
+ "top_p": 0.7,
196
+ "repetition_penalty": 1.0,
197
+ "num_beams": 1,
198
+ "fsdp": "",
199
+ "fsdp_config": null,
200
+ "sequence_parallel_size": 1,
201
+ "per_device_train_batch_size": null,
202
+ "per_device_eval_batch_size": null,
203
+ "self_cognition_sample": 8192,
204
+ "train_dataset_mix_ratio": 0.0,
205
+ "train_dataset_mix_ds": [
206
+ "ms-bench"
207
+ ],
208
+ "train_dataset_sample": -1,
209
+ "val_dataset_sample": -1,
210
+ "safe_serialization": null,
211
+ "only_save_model": null,
212
+ "neftune_alpha": null,
213
+ "deepspeed_config_path": null,
214
+ "model_cache_dir": null,
215
+ "custom_train_dataset_path": [],
216
+ "custom_val_dataset_path": [],
217
+ "use_self_cognition": true,
218
+ "lora_use_embedding": true,
219
+ "lora_use_all": true,
220
+ "lora_m2s_use_embedding": false,
221
+ "lora_m2s_use_ln": false,
222
+ "torch_dtype": "torch.float16",
223
+ "fp16": true,
224
+ "bf16": false,
225
+ "bnb_4bit_compute_dtype": "torch.float16",
226
+ "load_in_4bit": false,
227
+ "load_in_8bit": false,
228
+ "train_sampler_random": true,
229
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/data/home/wusc/CatalGPT/SwiftLog/output/yi-1.5-6b-chat/v23-20240525-003630.833747489', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, evaluation_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=32, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.0002, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=2, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data/home/wusc/CatalGPT/SwiftLog/output/yi-1.5-6b-chat/v23-20240525-003630.833747489/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=160, save_total_limit=2, save_safetensors=True, save_on_each_node=True, save_only_model=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, jit_mode_eval=False, use_ipex=False, bf16=False, fp16=True, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=160, dataloader_num_workers=4, dataloader_prefetch_factor=None, past_index=-1, run_name='/data/home/wusc/CatalGPT/SwiftLog/output/yi-1.5-6b-chat/v23-20240525-003630.833747489', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, gradient_accumulation_kwargs=None), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=5.0, optim_target_modules=None, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"do_sample\": true,\n \"eos_token_id\": 7,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 0,\n \"temperature\": 0.3,\n \"top_k\": 20,\n \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[])"
230
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|startoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "7": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "bos_token": "<|startoftext|>",
40
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
41
+ "clean_up_tokenization_spaces": false,
42
+ "eos_token": "<|im_end|>",
43
+ "legacy": true,
44
+ "model_max_length": 4096,
45
+ "pad_token": "<unk>",
46
+ "padding_side": "right",
47
+ "sp_model_kwargs": {},
48
+ "spaces_between_special_tokens": false,
49
+ "split_special_tokens": false,
50
+ "tokenizer_class": "LlamaTokenizer",
51
+ "unk_token": "<unk>",
52
+ "use_default_system_prompt": false
53
+ }