DachengLi commited on
Commit
f27ebb5
1 Parent(s): 6261c98

upload model

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../models/deepseek-7b-instruct-spider",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "eos_token_id": 32021,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "factor": 4.0,
23
+ "type": "linear"
24
+ },
25
+ "rope_theta": 100000,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.36.2",
29
+ "use_cache": false,
30
+ "vocab_size": 32256
31
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32013,
4
+ "eos_token_id": 32021,
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 sha256:82c6e8b7173fc15a0278b5e5645071746e18d7ede033de850f546cdcf8f9e247
3
+ size 4844590720
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3468611ca05ad4281ded46e3eec4aefe95fca767657e987c247ce288092ec28c
3
+ size 4857206856
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a454c1995197410535b550a2ae616ef20e8b0f165e9c8f2d40ffbf31f3eeda
3
+ size 4857206904
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72896018eee630dc0985397c6fb6055a709a5dcbd0a02bde7807ac77af026b44
3
+ size 4857206904
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a710a86ceec761f938cd0998e98099eb0b712764f1c9e6c7fdff653c77f72ce9
3
+ size 4857206904
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa87aaf4b62043bc2251d5d94d3469f9f2b2600770c25e812c66d31ee1058708
3
+ size 2688666416
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26962051072
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-00002-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-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-00003-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-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-00003-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-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-00003-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-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-00004-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-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-00004-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-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-00005-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00005-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-00005-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-00005-of-00006.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-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-00005-of-00006.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-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-00001-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
+ }
pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1509a67408415a601fb41ba5cf5e272a7fbf50b0edbab795c14c2c0b973c0634
3
+ size 26962200769
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4674cf80975f963dc8af8f5b4dc758b3ca71bf419cb48573c86e95bac738bdaa
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44222db69c3f8871290ae698a3ee3978a77b94777f43c4035367d6337f5f61a7
3
+ size 15984
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1497dc200a8fd4322adbee631d75ba29ae5d77e3db54b812130656d4529b0fe0
3
+ size 15984
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c71cfa0980d006041932e786ea8cbaf3051f96f68c18c3a7856c8f8ace4680
3
+ size 15984
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d640f88b2a044019594469bdf65d9d9a252860ba3739e007b849a5da243cfcfa
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f3b53bf76ce4ef7e3e0aed8a3eb9edc90ed0a980d087527018f66c15e7f9eb
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0fda04360cc0855a979ca6e1e614d5ae428795e6c5def4df8687af317d84b48
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90eaab5b4a9aca74ae3a4fa1d50fccb8159d109df5b892380521202be6e77289
3
+ size 15984
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5405cb513307632d485b2c1d3f1b9834f2f1a6676271295db3c7ec53bb10ac76
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|EOT|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "32000": {
6
+ "content": "õ",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "32001": {
14
+ "content": "÷",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "32002": {
22
+ "content": "Á",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32003": {
30
+ "content": "ý",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "32004": {
38
+ "content": "À",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32005": {
46
+ "content": "ÿ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "32006": {
54
+ "content": "ø",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "32007": {
62
+ "content": "ú",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "32008": {
70
+ "content": "þ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "32009": {
78
+ "content": "ü",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "32010": {
86
+ "content": "ù",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "32011": {
94
+ "content": "ö",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "32012": {
102
+ "content": "û",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "32013": {
110
+ "content": "<|begin▁of▁sentence|>",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32014": {
118
+ "content": "<|end▁of▁sentence|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32015": {
126
+ "content": "<|fim▁hole|>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "32016": {
134
+ "content": "<|fim▁begin|>",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "32017": {
142
+ "content": "<|fim▁end|>",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "32018": {
150
+ "content": "<pad>",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "32019": {
158
+ "content": "<|User|>",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "32020": {
166
+ "content": "<|Assistant|>",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "32021": {
174
+ "content": "<|EOT|>",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ }
181
+ },
182
+ "bos_token": "<|begin▁of▁sentence|>",
183
+ "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<|EOT|>",
186
+ "legacy": true,
187
+ "model_max_length": 16384,
188
+ "pad_token": "<|end▁of▁sentence|>",
189
+ "padding_side": "right",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizer",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
trainer_state.json ADDED
@@ -0,0 +1,1461 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9634684865515857,
5
+ "eval_steps": 500,
6
+ "global_step": 2400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 2.666666666666667e-06,
14
+ "loss": 42.4441,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 5.333333333333334e-06,
20
+ "loss": 37.1075,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 8.000000000000001e-06,
26
+ "loss": 27.8987,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 1.0666666666666667e-05,
32
+ "loss": 24.6867,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 22.6003,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 1.6000000000000003e-05,
44
+ "loss": 21.1455,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 1.866666666666667e-05,
50
+ "loss": 21.6205,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 1.9999788644103418e-05,
56
+ "loss": 20.1194,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 1.999809785053594e-05,
62
+ "loss": 20.1889,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.04,
67
+ "learning_rate": 1.9994716549285312e-05,
68
+ "loss": 19.7878,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.04,
73
+ "learning_rate": 1.9989645312071867e-05,
74
+ "loss": 19.5043,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "learning_rate": 1.9982884996355248e-05,
80
+ "loss": 19.2639,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.05,
85
+ "learning_rate": 1.9974436745189444e-05,
86
+ "loss": 19.0332,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.06,
91
+ "learning_rate": 1.9964301987029523e-05,
92
+ "loss": 19.3774,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.06,
97
+ "learning_rate": 1.9952482435490094e-05,
98
+ "loss": 18.8272,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.06,
103
+ "learning_rate": 1.9938980089055565e-05,
104
+ "loss": 18.9226,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.07,
109
+ "learning_rate": 1.992379723074224e-05,
110
+ "loss": 19.2136,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.07,
115
+ "learning_rate": 1.9906936427712295e-05,
116
+ "loss": 18.6037,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.08,
121
+ "learning_rate": 1.9888400530839713e-05,
122
+ "loss": 18.6965,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.08,
127
+ "learning_rate": 1.986819267422826e-05,
128
+ "loss": 18.4695,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.08,
133
+ "learning_rate": 1.9846316274681547e-05,
134
+ "loss": 18.5388,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.09,
139
+ "learning_rate": 1.982277503112531e-05,
140
+ "loss": 18.6583,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.09,
145
+ "learning_rate": 1.979757292398201e-05,
146
+ "loss": 18.1656,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.1,
151
+ "learning_rate": 1.977071421449776e-05,
152
+ "loss": 18.5414,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.1,
157
+ "learning_rate": 1.9742203444021878e-05,
158
+ "loss": 18.3158,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.1,
163
+ "learning_rate": 1.9712045433238972e-05,
164
+ "loss": 18.0978,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.11,
169
+ "learning_rate": 1.9680245281353894e-05,
170
+ "loss": 18.0812,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.11,
175
+ "learning_rate": 1.9646808365229506e-05,
176
+ "loss": 17.8044,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.12,
181
+ "learning_rate": 1.961174033847757e-05,
182
+ "loss": 17.9748,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.12,
187
+ "learning_rate": 1.9575047130502813e-05,
188
+ "loss": 17.7447,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.12,
193
+ "learning_rate": 1.953673494550037e-05,
194
+ "loss": 18.2907,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.13,
199
+ "learning_rate": 1.949681026140674e-05,
200
+ "loss": 18.1314,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.13,
205
+ "learning_rate": 1.9455279828804526e-05,
206
+ "loss": 17.9227,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.14,
211
+ "learning_rate": 1.9412150669780952e-05,
212
+ "loss": 18.4178,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.14,
217
+ "learning_rate": 1.936743007674063e-05,
218
+ "loss": 17.8701,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.14,
223
+ "learning_rate": 1.9321125611172468e-05,
224
+ "loss": 18.1603,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.15,
229
+ "learning_rate": 1.92732451023712e-05,
230
+ "loss": 17.8314,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.15,
235
+ "learning_rate": 1.9223796646113567e-05,
236
+ "loss": 17.5233,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.16,
241
+ "learning_rate": 1.9172788603289453e-05,
242
+ "loss": 18.2041,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.16,
247
+ "learning_rate": 1.9120229598488218e-05,
248
+ "loss": 18.1653,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 0.16,
253
+ "learning_rate": 1.9066128518540408e-05,
254
+ "loss": 17.6848,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 0.17,
259
+ "learning_rate": 1.9010494511015164e-05,
260
+ "loss": 18.1238,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 0.17,
265
+ "learning_rate": 1.8953336982673506e-05,
266
+ "loss": 17.956,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 0.18,
271
+ "learning_rate": 1.8894665597877824e-05,
272
+ "loss": 17.699,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 0.18,
277
+ "learning_rate": 1.8834490276957788e-05,
278
+ "loss": 17.6947,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 0.18,
283
+ "learning_rate": 1.8772821194533e-05,
284
+ "loss": 17.6464,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 0.19,
289
+ "learning_rate": 1.8709668777792633e-05,
290
+ "loss": 17.89,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 0.19,
295
+ "learning_rate": 1.8645043704732367e-05,
296
+ "loss": 17.6851,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 0.2,
301
+ "learning_rate": 1.8578956902348945e-05,
302
+ "loss": 17.3849,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 0.2,
307
+ "learning_rate": 1.851141954479256e-05,
308
+ "loss": 17.8666,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 0.2,
313
+ "learning_rate": 1.844244305147755e-05,
314
+ "loss": 17.4788,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 0.21,
319
+ "learning_rate": 1.8372039085151537e-05,
320
+ "loss": 17.4202,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 0.21,
325
+ "learning_rate": 1.830021954992345e-05,
326
+ "loss": 17.2379,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 0.22,
331
+ "learning_rate": 1.8226996589250775e-05,
332
+ "loss": 17.5357,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 0.22,
337
+ "learning_rate": 1.8152382583886272e-05,
338
+ "loss": 17.9992,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 0.22,
343
+ "learning_rate": 1.8076390149784622e-05,
344
+ "loss": 17.7149,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 0.23,
349
+ "learning_rate": 1.7999032135969265e-05,
350
+ "loss": 17.5005,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 0.23,
355
+ "learning_rate": 1.7920321622359876e-05,
356
+ "loss": 17.4384,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 0.24,
361
+ "learning_rate": 1.784027191756075e-05,
362
+ "loss": 17.0999,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 0.24,
367
+ "learning_rate": 1.7758896556610547e-05,
368
+ "loss": 17.203,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 0.24,
373
+ "learning_rate": 1.7676209298693765e-05,
374
+ "loss": 17.3599,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 0.25,
379
+ "learning_rate": 1.759222412481428e-05,
380
+ "loss": 17.7387,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 0.25,
385
+ "learning_rate": 1.75069552354314e-05,
386
+ "loss": 17.4499,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 0.26,
391
+ "learning_rate": 1.7420417048058816e-05,
392
+ "loss": 17.396,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 0.26,
397
+ "learning_rate": 1.7332624194826847e-05,
398
+ "loss": 17.441,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 0.26,
403
+ "learning_rate": 1.7243591520008384e-05,
404
+ "loss": 17.0808,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 0.27,
409
+ "learning_rate": 1.7153334077508983e-05,
410
+ "loss": 17.1419,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 0.27,
415
+ "learning_rate": 1.7061867128321524e-05,
416
+ "loss": 17.3086,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 0.28,
421
+ "learning_rate": 1.6969206137945797e-05,
422
+ "loss": 17.3577,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 0.28,
427
+ "learning_rate": 1.6875366773773604e-05,
428
+ "loss": 17.6731,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 0.29,
433
+ "learning_rate": 1.678036490243962e-05,
434
+ "loss": 17.3216,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 0.29,
439
+ "learning_rate": 1.6684216587138647e-05,
440
+ "loss": 17.3844,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 0.29,
445
+ "learning_rate": 1.658693808490959e-05,
446
+ "loss": 17.4103,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 0.3,
451
+ "learning_rate": 1.6488545843886677e-05,
452
+ "loss": 17.0814,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 0.3,
457
+ "learning_rate": 1.6389056500518343e-05,
458
+ "loss": 17.3081,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 0.31,
463
+ "learning_rate": 1.6288486876754314e-05,
464
+ "loss": 17.148,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 0.31,
469
+ "learning_rate": 1.618685397720128e-05,
470
+ "loss": 16.8685,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 0.31,
475
+ "learning_rate": 1.6084174986247738e-05,
476
+ "loss": 17.4187,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 0.32,
481
+ "learning_rate": 1.598046726515836e-05,
482
+ "loss": 17.4885,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 0.32,
487
+ "learning_rate": 1.5875748349138533e-05,
488
+ "loss": 17.2386,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 0.33,
493
+ "learning_rate": 1.5770035944369456e-05,
494
+ "loss": 16.9695,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 0.33,
499
+ "learning_rate": 1.5663347925014302e-05,
500
+ "loss": 17.3497,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 0.33,
505
+ "learning_rate": 1.5555702330196024e-05,
506
+ "loss": 16.9592,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 0.34,
511
+ "learning_rate": 1.5447117360947244e-05,
512
+ "loss": 17.5106,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 0.34,
517
+ "learning_rate": 1.5337611377132757e-05,
518
+ "loss": 17.2786,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 0.35,
523
+ "learning_rate": 1.522720289434521e-05,
524
+ "loss": 17.4009,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 0.35,
529
+ "learning_rate": 1.511591058077441e-05,
530
+ "loss": 17.2044,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 0.35,
535
+ "learning_rate": 1.500375325405087e-05,
536
+ "loss": 17.1285,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 0.36,
541
+ "learning_rate": 1.489074987806406e-05,
542
+ "loss": 17.3726,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 0.36,
547
+ "learning_rate": 1.477691955975594e-05,
548
+ "loss": 17.1684,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 0.37,
553
+ "learning_rate": 1.46622815458903e-05,
554
+ "loss": 17.2715,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 0.37,
559
+ "learning_rate": 1.454685521979846e-05,
560
+ "loss": 17.3633,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 0.37,
565
+ "learning_rate": 1.443066009810188e-05,
566
+ "loss": 17.1012,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 0.38,
571
+ "learning_rate": 1.4313715827412243e-05,
572
+ "loss": 16.7467,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 0.38,
577
+ "learning_rate": 1.4196042181009525e-05,
578
+ "loss": 16.741,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 0.39,
583
+ "learning_rate": 1.4077659055498695e-05,
584
+ "loss": 17.0569,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 0.39,
589
+ "learning_rate": 1.3958586467445532e-05,
590
+ "loss": 17.0277,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 0.39,
595
+ "learning_rate": 1.383884454999215e-05,
596
+ "loss": 16.8944,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 0.4,
601
+ "learning_rate": 1.3718453549452843e-05,
602
+ "loss": 17.1323,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 0.4,
607
+ "learning_rate": 1.3597433821890787e-05,
608
+ "loss": 16.9379,
609
+ "step": 1000
610
+ },
611
+ {
612
+ "epoch": 0.41,
613
+ "learning_rate": 1.3475805829676149e-05,
614
+ "loss": 16.9814,
615
+ "step": 1010
616
+ },
617
+ {
618
+ "epoch": 0.41,
619
+ "learning_rate": 1.3353590138026273e-05,
620
+ "loss": 17.1369,
621
+ "step": 1020
622
+ },
623
+ {
624
+ "epoch": 0.41,
625
+ "learning_rate": 1.323080741152845e-05,
626
+ "loss": 16.8629,
627
+ "step": 1030
628
+ },
629
+ {
630
+ "epoch": 0.42,
631
+ "learning_rate": 1.3107478410645875e-05,
632
+ "loss": 16.8607,
633
+ "step": 1040
634
+ },
635
+ {
636
+ "epoch": 0.42,
637
+ "learning_rate": 1.2983623988207432e-05,
638
+ "loss": 16.6911,
639
+ "step": 1050
640
+ },
641
+ {
642
+ "epoch": 0.43,
643
+ "learning_rate": 1.28592650858818e-05,
644
+ "loss": 16.9764,
645
+ "step": 1060
646
+ },
647
+ {
648
+ "epoch": 0.43,
649
+ "learning_rate": 1.2734422730636617e-05,
650
+ "loss": 16.8255,
651
+ "step": 1070
652
+ },
653
+ {
654
+ "epoch": 0.43,
655
+ "learning_rate": 1.2609118031183144e-05,
656
+ "loss": 16.8564,
657
+ "step": 1080
658
+ },
659
+ {
660
+ "epoch": 0.44,
661
+ "learning_rate": 1.2483372174407155e-05,
662
+ "loss": 16.9249,
663
+ "step": 1090
664
+ },
665
+ {
666
+ "epoch": 0.44,
667
+ "learning_rate": 1.2357206421786611e-05,
668
+ "loss": 16.8046,
669
+ "step": 1100
670
+ },
671
+ {
672
+ "epoch": 0.45,
673
+ "learning_rate": 1.2230642105796674e-05,
674
+ "loss": 17.0138,
675
+ "step": 1110
676
+ },
677
+ {
678
+ "epoch": 0.45,
679
+ "learning_rate": 1.2103700626302784e-05,
680
+ "loss": 16.8029,
681
+ "step": 1120
682
+ },
683
+ {
684
+ "epoch": 0.45,
685
+ "learning_rate": 1.197640344694228e-05,
686
+ "loss": 16.7554,
687
+ "step": 1130
688
+ },
689
+ {
690
+ "epoch": 0.46,
691
+ "learning_rate": 1.1848772091495287e-05,
692
+ "loss": 16.62,
693
+ "step": 1140
694
+ },
695
+ {
696
+ "epoch": 0.46,
697
+ "learning_rate": 1.1720828140245393e-05,
698
+ "loss": 16.8458,
699
+ "step": 1150
700
+ },
701
+ {
702
+ "epoch": 0.47,
703
+ "learning_rate": 1.1592593226330802e-05,
704
+ "loss": 17.1714,
705
+ "step": 1160
706
+ },
707
+ {
708
+ "epoch": 0.47,
709
+ "learning_rate": 1.1464089032086547e-05,
710
+ "loss": 17.0085,
711
+ "step": 1170
712
+ },
713
+ {
714
+ "epoch": 0.47,
715
+ "learning_rate": 1.1335337285378359e-05,
716
+ "loss": 16.8423,
717
+ "step": 1180
718
+ },
719
+ {
720
+ "epoch": 0.48,
721
+ "learning_rate": 1.1206359755928865e-05,
722
+ "loss": 16.8152,
723
+ "step": 1190
724
+ },
725
+ {
726
+ "epoch": 0.48,
727
+ "learning_rate": 1.1077178251636702e-05,
728
+ "loss": 16.619,
729
+ "step": 1200
730
+ },
731
+ {
732
+ "epoch": 0.49,
733
+ "learning_rate": 1.0947814614889174e-05,
734
+ "loss": 16.7087,
735
+ "step": 1210
736
+ },
737
+ {
738
+ "epoch": 0.49,
739
+ "learning_rate": 1.0818290718869068e-05,
740
+ "loss": 16.7935,
741
+ "step": 1220
742
+ },
743
+ {
744
+ "epoch": 0.49,
745
+ "learning_rate": 1.0688628463856287e-05,
746
+ "loss": 17.4941,
747
+ "step": 1230
748
+ },
749
+ {
750
+ "epoch": 0.5,
751
+ "learning_rate": 1.055884977352487e-05,
752
+ "loss": 17.0523,
753
+ "step": 1240
754
+ },
755
+ {
756
+ "epoch": 0.5,
757
+ "learning_rate": 1.0428976591236082e-05,
758
+ "loss": 16.7451,
759
+ "step": 1250
760
+ },
761
+ {
762
+ "epoch": 0.51,
763
+ "learning_rate": 1.029903087632817e-05,
764
+ "loss": 16.8536,
765
+ "step": 1260
766
+ },
767
+ {
768
+ "epoch": 0.51,
769
+ "learning_rate": 1.0169034600403404e-05,
770
+ "loss": 16.6058,
771
+ "step": 1270
772
+ },
773
+ {
774
+ "epoch": 0.51,
775
+ "learning_rate": 1.003900974361306e-05,
776
+ "loss": 16.6489,
777
+ "step": 1280
778
+ },
779
+ {
780
+ "epoch": 0.52,
781
+ "learning_rate": 9.908978290940948e-06,
782
+ "loss": 16.989,
783
+ "step": 1290
784
+ },
785
+ {
786
+ "epoch": 0.52,
787
+ "learning_rate": 9.778962228486138e-06,
788
+ "loss": 16.885,
789
+ "step": 1300
790
+ },
791
+ {
792
+ "epoch": 0.53,
793
+ "learning_rate": 9.648983539745468e-06,
794
+ "loss": 16.9012,
795
+ "step": 1310
796
+ },
797
+ {
798
+ "epoch": 0.53,
799
+ "learning_rate": 9.51906420189652e-06,
800
+ "loss": 16.8678,
801
+ "step": 1320
802
+ },
803
+ {
804
+ "epoch": 0.53,
805
+ "learning_rate": 9.38922618208166e-06,
806
+ "loss": 16.7718,
807
+ "step": 1330
808
+ },
809
+ {
810
+ "epoch": 0.54,
811
+ "learning_rate": 9.259491433693751e-06,
812
+ "loss": 16.7869,
813
+ "step": 1340
814
+ },
815
+ {
816
+ "epoch": 0.54,
817
+ "learning_rate": 9.129881892664232e-06,
818
+ "loss": 16.9432,
819
+ "step": 1350
820
+ },
821
+ {
822
+ "epoch": 0.55,
823
+ "learning_rate": 9.00041947375411e-06,
824
+ "loss": 16.8835,
825
+ "step": 1360
826
+ },
827
+ {
828
+ "epoch": 0.55,
829
+ "learning_rate": 8.871126066848552e-06,
830
+ "loss": 16.8081,
831
+ "step": 1370
832
+ },
833
+ {
834
+ "epoch": 0.55,
835
+ "learning_rate": 8.742023533255677e-06,
836
+ "loss": 16.6375,
837
+ "step": 1380
838
+ },
839
+ {
840
+ "epoch": 0.56,
841
+ "learning_rate": 8.613133702010196e-06,
842
+ "loss": 16.7379,
843
+ "step": 1390
844
+ },
845
+ {
846
+ "epoch": 0.56,
847
+ "learning_rate": 8.484478366182472e-06,
848
+ "loss": 16.5849,
849
+ "step": 1400
850
+ },
851
+ {
852
+ "epoch": 0.57,
853
+ "learning_rate": 8.356079279193703e-06,
854
+ "loss": 16.6192,
855
+ "step": 1410
856
+ },
857
+ {
858
+ "epoch": 0.57,
859
+ "learning_rate": 8.227958151137773e-06,
860
+ "loss": 16.4591,
861
+ "step": 1420
862
+ },
863
+ {
864
+ "epoch": 0.57,
865
+ "learning_rate": 8.10013664511047e-06,
866
+ "loss": 16.5343,
867
+ "step": 1430
868
+ },
869
+ {
870
+ "epoch": 0.58,
871
+ "learning_rate": 7.9726363735466e-06,
872
+ "loss": 16.9542,
873
+ "step": 1440
874
+ },
875
+ {
876
+ "epoch": 0.58,
877
+ "learning_rate": 7.84547889456571e-06,
878
+ "loss": 16.8205,
879
+ "step": 1450
880
+ },
881
+ {
882
+ "epoch": 0.59,
883
+ "learning_rate": 7.718685708326965e-06,
884
+ "loss": 16.5807,
885
+ "step": 1460
886
+ },
887
+ {
888
+ "epoch": 0.59,
889
+ "learning_rate": 7.592278253393859e-06,
890
+ "loss": 16.5174,
891
+ "step": 1470
892
+ },
893
+ {
894
+ "epoch": 0.59,
895
+ "learning_rate": 7.466277903109291e-06,
896
+ "loss": 16.6076,
897
+ "step": 1480
898
+ },
899
+ {
900
+ "epoch": 0.6,
901
+ "learning_rate": 7.340705961981722e-06,
902
+ "loss": 16.7884,
903
+ "step": 1490
904
+ },
905
+ {
906
+ "epoch": 0.6,
907
+ "learning_rate": 7.215583662082939e-06,
908
+ "loss": 16.8359,
909
+ "step": 1500
910
+ },
911
+ {
912
+ "epoch": 0.61,
913
+ "learning_rate": 7.090932159458067e-06,
914
+ "loss": 16.5588,
915
+ "step": 1510
916
+ },
917
+ {
918
+ "epoch": 0.61,
919
+ "learning_rate": 6.966772530548448e-06,
920
+ "loss": 16.6256,
921
+ "step": 1520
922
+ },
923
+ {
924
+ "epoch": 0.61,
925
+ "learning_rate": 6.843125768627983e-06,
926
+ "loss": 16.7764,
927
+ "step": 1530
928
+ },
929
+ {
930
+ "epoch": 0.62,
931
+ "learning_rate": 6.720012780253509e-06,
932
+ "loss": 16.9245,
933
+ "step": 1540
934
+ },
935
+ {
936
+ "epoch": 0.62,
937
+ "learning_rate": 6.597454381729873e-06,
938
+ "loss": 16.5384,
939
+ "step": 1550
940
+ },
941
+ {
942
+ "epoch": 0.63,
943
+ "learning_rate": 6.475471295590248e-06,
944
+ "loss": 16.6298,
945
+ "step": 1560
946
+ },
947
+ {
948
+ "epoch": 0.63,
949
+ "learning_rate": 6.354084147092296e-06,
950
+ "loss": 16.752,
951
+ "step": 1570
952
+ },
953
+ {
954
+ "epoch": 0.63,
955
+ "learning_rate": 6.2333134607308e-06,
956
+ "loss": 16.6684,
957
+ "step": 1580
958
+ },
959
+ {
960
+ "epoch": 0.64,
961
+ "learning_rate": 6.113179656767319e-06,
962
+ "loss": 16.4827,
963
+ "step": 1590
964
+ },
965
+ {
966
+ "epoch": 0.64,
967
+ "learning_rate": 5.993703047777468e-06,
968
+ "loss": 16.5697,
969
+ "step": 1600
970
+ },
971
+ {
972
+ "epoch": 0.65,
973
+ "learning_rate": 5.874903835216417e-06,
974
+ "loss": 16.4795,
975
+ "step": 1610
976
+ },
977
+ {
978
+ "epoch": 0.65,
979
+ "learning_rate": 5.756802106003148e-06,
980
+ "loss": 16.8255,
981
+ "step": 1620
982
+ },
983
+ {
984
+ "epoch": 0.65,
985
+ "learning_rate": 5.639417829124132e-06,
986
+ "loss": 16.6714,
987
+ "step": 1630
988
+ },
989
+ {
990
+ "epoch": 0.66,
991
+ "learning_rate": 5.52277085225688e-06,
992
+ "loss": 16.7242,
993
+ "step": 1640
994
+ },
995
+ {
996
+ "epoch": 0.66,
997
+ "learning_rate": 5.406880898414069e-06,
998
+ "loss": 16.4696,
999
+ "step": 1650
1000
+ },
1001
+ {
1002
+ "epoch": 0.67,
1003
+ "learning_rate": 5.291767562608705e-06,
1004
+ "loss": 16.5084,
1005
+ "step": 1660
1006
+ },
1007
+ {
1008
+ "epoch": 0.67,
1009
+ "learning_rate": 5.177450308540928e-06,
1010
+ "loss": 16.5646,
1011
+ "step": 1670
1012
+ },
1013
+ {
1014
+ "epoch": 0.67,
1015
+ "learning_rate": 5.0639484653070535e-06,
1016
+ "loss": 16.4026,
1017
+ "step": 1680
1018
+ },
1019
+ {
1020
+ "epoch": 0.68,
1021
+ "learning_rate": 4.95128122413135e-06,
1022
+ "loss": 16.3032,
1023
+ "step": 1690
1024
+ },
1025
+ {
1026
+ "epoch": 0.68,
1027
+ "learning_rate": 4.83946763512111e-06,
1028
+ "loss": 16.5088,
1029
+ "step": 1700
1030
+ },
1031
+ {
1032
+ "epoch": 0.69,
1033
+ "learning_rate": 4.7285266040456255e-06,
1034
+ "loss": 16.3905,
1035
+ "step": 1710
1036
+ },
1037
+ {
1038
+ "epoch": 0.69,
1039
+ "learning_rate": 4.618476889139538e-06,
1040
+ "loss": 16.4207,
1041
+ "step": 1720
1042
+ },
1043
+ {
1044
+ "epoch": 0.69,
1045
+ "learning_rate": 4.50933709793113e-06,
1046
+ "loss": 16.5308,
1047
+ "step": 1730
1048
+ },
1049
+ {
1050
+ "epoch": 0.7,
1051
+ "learning_rate": 4.401125684096124e-06,
1052
+ "loss": 16.521,
1053
+ "step": 1740
1054
+ },
1055
+ {
1056
+ "epoch": 0.7,
1057
+ "learning_rate": 4.293860944337482e-06,
1058
+ "loss": 16.3123,
1059
+ "step": 1750
1060
+ },
1061
+ {
1062
+ "epoch": 0.71,
1063
+ "learning_rate": 4.1875610152917225e-06,
1064
+ "loss": 16.6079,
1065
+ "step": 1760
1066
+ },
1067
+ {
1068
+ "epoch": 0.71,
1069
+ "learning_rate": 4.082243870462362e-06,
1070
+ "loss": 16.5056,
1071
+ "step": 1770
1072
+ },
1073
+ {
1074
+ "epoch": 0.71,
1075
+ "learning_rate": 3.977927317180864e-06,
1076
+ "loss": 16.4315,
1077
+ "step": 1780
1078
+ },
1079
+ {
1080
+ "epoch": 0.72,
1081
+ "learning_rate": 3.87462899359575e-06,
1082
+ "loss": 16.1708,
1083
+ "step": 1790
1084
+ },
1085
+ {
1086
+ "epoch": 0.72,
1087
+ "learning_rate": 3.772366365690283e-06,
1088
+ "loss": 16.3817,
1089
+ "step": 1800
1090
+ },
1091
+ {
1092
+ "epoch": 0.73,
1093
+ "learning_rate": 3.6711567243292547e-06,
1094
+ "loss": 16.5455,
1095
+ "step": 1810
1096
+ },
1097
+ {
1098
+ "epoch": 0.73,
1099
+ "learning_rate": 3.5710171823354145e-06,
1100
+ "loss": 16.3721,
1101
+ "step": 1820
1102
+ },
1103
+ {
1104
+ "epoch": 0.73,
1105
+ "learning_rate": 3.4719646715959777e-06,
1106
+ "loss": 16.4659,
1107
+ "step": 1830
1108
+ },
1109
+ {
1110
+ "epoch": 0.74,
1111
+ "learning_rate": 3.3740159401997173e-06,
1112
+ "loss": 16.5392,
1113
+ "step": 1840
1114
+ },
1115
+ {
1116
+ "epoch": 0.74,
1117
+ "learning_rate": 3.2771875496051743e-06,
1118
+ "loss": 16.6646,
1119
+ "step": 1850
1120
+ },
1121
+ {
1122
+ "epoch": 0.75,
1123
+ "learning_rate": 3.181495871840379e-06,
1124
+ "loss": 16.3682,
1125
+ "step": 1860
1126
+ },
1127
+ {
1128
+ "epoch": 0.75,
1129
+ "learning_rate": 3.0869570867346167e-06,
1130
+ "loss": 16.5935,
1131
+ "step": 1870
1132
+ },
1133
+ {
1134
+ "epoch": 0.75,
1135
+ "learning_rate": 2.9935871791827166e-06,
1136
+ "loss": 16.539,
1137
+ "step": 1880
1138
+ },
1139
+ {
1140
+ "epoch": 0.76,
1141
+ "learning_rate": 2.9014019364422606e-06,
1142
+ "loss": 16.1143,
1143
+ "step": 1890
1144
+ },
1145
+ {
1146
+ "epoch": 0.76,
1147
+ "learning_rate": 2.8104169454642293e-06,
1148
+ "loss": 16.5375,
1149
+ "step": 1900
1150
+ },
1151
+ {
1152
+ "epoch": 0.77,
1153
+ "learning_rate": 2.7206475902575225e-06,
1154
+ "loss": 16.3927,
1155
+ "step": 1910
1156
+ },
1157
+ {
1158
+ "epoch": 0.77,
1159
+ "learning_rate": 2.6321090492877823e-06,
1160
+ "loss": 16.3639,
1161
+ "step": 1920
1162
+ },
1163
+ {
1164
+ "epoch": 0.77,
1165
+ "learning_rate": 2.544816292910962e-06,
1166
+ "loss": 16.3929,
1167
+ "step": 1930
1168
+ },
1169
+ {
1170
+ "epoch": 0.78,
1171
+ "learning_rate": 2.458784080842127e-06,
1172
+ "loss": 16.3984,
1173
+ "step": 1940
1174
+ },
1175
+ {
1176
+ "epoch": 0.78,
1177
+ "learning_rate": 2.3740269596597943e-06,
1178
+ "loss": 16.3938,
1179
+ "step": 1950
1180
+ },
1181
+ {
1182
+ "epoch": 0.79,
1183
+ "learning_rate": 2.2905592603463888e-06,
1184
+ "loss": 16.3884,
1185
+ "step": 1960
1186
+ },
1187
+ {
1188
+ "epoch": 0.79,
1189
+ "learning_rate": 2.2083950958651103e-06,
1190
+ "loss": 16.3289,
1191
+ "step": 1970
1192
+ },
1193
+ {
1194
+ "epoch": 0.79,
1195
+ "learning_rate": 2.1275483587736577e-06,
1196
+ "loss": 16.3735,
1197
+ "step": 1980
1198
+ },
1199
+ {
1200
+ "epoch": 0.8,
1201
+ "learning_rate": 2.048032718875255e-06,
1202
+ "loss": 16.4073,
1203
+ "step": 1990
1204
+ },
1205
+ {
1206
+ "epoch": 0.8,
1207
+ "learning_rate": 1.969861620907314e-06,
1208
+ "loss": 16.4259,
1209
+ "step": 2000
1210
+ },
1211
+ {
1212
+ "epoch": 0.81,
1213
+ "learning_rate": 1.8930482822681473e-06,
1214
+ "loss": 16.3312,
1215
+ "step": 2010
1216
+ },
1217
+ {
1218
+ "epoch": 0.81,
1219
+ "learning_rate": 1.8176056907821482e-06,
1220
+ "loss": 16.2809,
1221
+ "step": 2020
1222
+ },
1223
+ {
1224
+ "epoch": 0.81,
1225
+ "learning_rate": 1.7435466025037684e-06,
1226
+ "loss": 16.2617,
1227
+ "step": 2030
1228
+ },
1229
+ {
1230
+ "epoch": 0.82,
1231
+ "learning_rate": 1.6708835395606704e-06,
1232
+ "loss": 16.6299,
1233
+ "step": 2040
1234
+ },
1235
+ {
1236
+ "epoch": 0.82,
1237
+ "learning_rate": 1.5996287880364736e-06,
1238
+ "loss": 16.2559,
1239
+ "step": 2050
1240
+ },
1241
+ {
1242
+ "epoch": 0.83,
1243
+ "learning_rate": 1.5297943958933748e-06,
1244
+ "loss": 16.4145,
1245
+ "step": 2060
1246
+ },
1247
+ {
1248
+ "epoch": 0.83,
1249
+ "learning_rate": 1.4613921709350342e-06,
1250
+ "loss": 16.3823,
1251
+ "step": 2070
1252
+ },
1253
+ {
1254
+ "epoch": 0.84,
1255
+ "learning_rate": 1.3944336788100976e-06,
1256
+ "loss": 16.3725,
1257
+ "step": 2080
1258
+ },
1259
+ {
1260
+ "epoch": 0.84,
1261
+ "learning_rate": 1.3289302410566318e-06,
1262
+ "loss": 16.2138,
1263
+ "step": 2090
1264
+ },
1265
+ {
1266
+ "epoch": 0.84,
1267
+ "learning_rate": 1.2648929331878423e-06,
1268
+ "loss": 16.2873,
1269
+ "step": 2100
1270
+ },
1271
+ {
1272
+ "epoch": 0.85,
1273
+ "learning_rate": 1.202332582819402e-06,
1274
+ "loss": 16.4605,
1275
+ "step": 2110
1276
+ },
1277
+ {
1278
+ "epoch": 0.85,
1279
+ "learning_rate": 1.141259767838675e-06,
1280
+ "loss": 16.1904,
1281
+ "step": 2120
1282
+ },
1283
+ {
1284
+ "epoch": 0.86,
1285
+ "learning_rate": 1.0816848146161895e-06,
1286
+ "loss": 16.4713,
1287
+ "step": 2130
1288
+ },
1289
+ {
1290
+ "epoch": 0.86,
1291
+ "learning_rate": 1.0236177962596173e-06,
1292
+ "loss": 16.143,
1293
+ "step": 2140
1294
+ },
1295
+ {
1296
+ "epoch": 0.86,
1297
+ "learning_rate": 9.670685309105786e-07,
1298
+ "loss": 16.2049,
1299
+ "step": 2150
1300
+ },
1301
+ {
1302
+ "epoch": 0.87,
1303
+ "learning_rate": 9.120465800845723e-07,
1304
+ "loss": 16.3906,
1305
+ "step": 2160
1306
+ },
1307
+ {
1308
+ "epoch": 0.87,
1309
+ "learning_rate": 8.585612470542859e-07,
1310
+ "loss": 16.1819,
1311
+ "step": 2170
1312
+ },
1313
+ {
1314
+ "epoch": 0.88,
1315
+ "learning_rate": 8.06621575276556e-07,
1316
+ "loss": 16.2495,
1317
+ "step": 2180
1318
+ },
1319
+ {
1320
+ "epoch": 0.88,
1321
+ "learning_rate": 7.562363468632949e-07,
1322
+ "loss": 16.3325,
1323
+ "step": 2190
1324
+ },
1325
+ {
1326
+ "epoch": 0.88,
1327
+ "learning_rate": 7.074140810965724e-07,
1328
+ "loss": 16.3265,
1329
+ "step": 2200
1330
+ },
1331
+ {
1332
+ "epoch": 0.89,
1333
+ "learning_rate": 6.601630329881525e-07,
1334
+ "loss": 16.3694,
1335
+ "step": 2210
1336
+ },
1337
+ {
1338
+ "epoch": 0.89,
1339
+ "learning_rate": 6.14491191883716e-07,
1340
+ "loss": 16.2883,
1341
+ "step": 2220
1342
+ },
1343
+ {
1344
+ "epoch": 0.9,
1345
+ "learning_rate": 5.704062801119947e-07,
1346
+ "loss": 16.2978,
1347
+ "step": 2230
1348
+ },
1349
+ {
1350
+ "epoch": 0.9,
1351
+ "learning_rate": 5.279157516790545e-07,
1352
+ "loss": 16.2589,
1353
+ "step": 2240
1354
+ },
1355
+ {
1356
+ "epoch": 0.9,
1357
+ "learning_rate": 4.870267910079618e-07,
1358
+ "loss": 16.6149,
1359
+ "step": 2250
1360
+ },
1361
+ {
1362
+ "epoch": 0.91,
1363
+ "learning_rate": 4.4774631172400663e-07,
1364
+ "loss": 16.2879,
1365
+ "step": 2260
1366
+ },
1367
+ {
1368
+ "epoch": 0.91,
1369
+ "learning_rate": 4.100809554857343e-07,
1370
+ "loss": 16.2822,
1371
+ "step": 2270
1372
+ },
1373
+ {
1374
+ "epoch": 0.92,
1375
+ "learning_rate": 3.740370908619528e-07,
1376
+ "loss": 16.3097,
1377
+ "step": 2280
1378
+ },
1379
+ {
1380
+ "epoch": 0.92,
1381
+ "learning_rate": 3.396208122549194e-07,
1382
+ "loss": 16.3474,
1383
+ "step": 2290
1384
+ },
1385
+ {
1386
+ "epoch": 0.92,
1387
+ "learning_rate": 3.0683793886986943e-07,
1388
+ "loss": 16.2617,
1389
+ "step": 2300
1390
+ },
1391
+ {
1392
+ "epoch": 0.93,
1393
+ "learning_rate": 2.7569401373110595e-07,
1394
+ "loss": 16.1619,
1395
+ "step": 2310
1396
+ },
1397
+ {
1398
+ "epoch": 0.93,
1399
+ "learning_rate": 2.461943027447555e-07,
1400
+ "loss": 16.2584,
1401
+ "step": 2320
1402
+ },
1403
+ {
1404
+ "epoch": 0.94,
1405
+ "learning_rate": 2.1834379380839655e-07,
1406
+ "loss": 16.1723,
1407
+ "step": 2330
1408
+ },
1409
+ {
1410
+ "epoch": 0.94,
1411
+ "learning_rate": 1.921471959676957e-07,
1412
+ "loss": 16.2365,
1413
+ "step": 2340
1414
+ },
1415
+ {
1416
+ "epoch": 0.94,
1417
+ "learning_rate": 1.676089386201818e-07,
1418
+ "loss": 16.2976,
1419
+ "step": 2350
1420
+ },
1421
+ {
1422
+ "epoch": 0.95,
1423
+ "learning_rate": 1.4473317076631355e-07,
1424
+ "loss": 16.3046,
1425
+ "step": 2360
1426
+ },
1427
+ {
1428
+ "epoch": 0.95,
1429
+ "learning_rate": 1.2352376030795753e-07,
1430
+ "loss": 16.2992,
1431
+ "step": 2370
1432
+ },
1433
+ {
1434
+ "epoch": 0.96,
1435
+ "learning_rate": 1.0398429339438353e-07,
1436
+ "loss": 16.2474,
1437
+ "step": 2380
1438
+ },
1439
+ {
1440
+ "epoch": 0.96,
1441
+ "learning_rate": 8.61180738159173e-08,
1442
+ "loss": 16.2852,
1443
+ "step": 2390
1444
+ },
1445
+ {
1446
+ "epoch": 0.96,
1447
+ "learning_rate": 6.992812244532188e-08,
1448
+ "loss": 16.3501,
1449
+ "step": 2400
1450
+ }
1451
+ ],
1452
+ "logging_steps": 10,
1453
+ "max_steps": 2491,
1454
+ "num_input_tokens_seen": 0,
1455
+ "num_train_epochs": 1,
1456
+ "save_steps": 100,
1457
+ "total_flos": 0.0,
1458
+ "train_batch_size": 1,
1459
+ "trial_name": null,
1460
+ "trial_params": null
1461
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e461913d14006955a6349c0ee521da3252656211ab6e99ebc16228c210e0212f
3
+ size 5176