ehartford commited on
Commit
d6e3fd1
1 Parent(s): 6d11646

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/models/llama-7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 2048,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.28.1",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3943b9aedd4334a488d31599b7ba8a8e970973b796cbaa8d2527dfee2028568
3
+ size 9877989586
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454f31c0e48362e369b1b9ff5a027a6d7afcf029ccb143e34826cdef16ccaaaa
3
+ size 9894801014
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0961bbcd2f8e0ae8ab93af11ebdf0da2580584f6ae0cf91ad8eee73783123c08
3
+ size 7180990649
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26953670656
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
328
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
329
+ }
330
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "padding_side": "right",
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
trainer_state.json ADDED
@@ -0,0 +1,1213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.988679245283019,
5
+ "global_step": 198,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 2.5e-06,
13
+ "loss": 0.8582,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 5e-06,
19
+ "loss": 0.8625,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 7.500000000000001e-06,
25
+ "loss": 0.7611,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 1e-05,
31
+ "loss": 0.7663,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.08,
36
+ "learning_rate": 1.25e-05,
37
+ "loss": 0.7329,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.09,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.6997,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.11,
48
+ "learning_rate": 1.7500000000000002e-05,
49
+ "loss": 0.6928,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.12,
54
+ "learning_rate": 2e-05,
55
+ "loss": 0.6727,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.14,
60
+ "learning_rate": 1.9998633049924693e-05,
61
+ "loss": 0.6601,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.15,
66
+ "learning_rate": 1.999453257340926e-05,
67
+ "loss": 0.6439,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.17,
72
+ "learning_rate": 1.998769969148305e-05,
73
+ "loss": 0.6591,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.18,
78
+ "learning_rate": 1.9978136272187745e-05,
79
+ "loss": 0.6253,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.2,
84
+ "learning_rate": 1.99658449300667e-05,
85
+ "loss": 0.6277,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.21,
90
+ "learning_rate": 1.9950829025450116e-05,
91
+ "loss": 0.618,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.23,
96
+ "learning_rate": 1.9933092663536384e-05,
97
+ "loss": 0.6163,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.24,
102
+ "learning_rate": 1.9912640693269754e-05,
103
+ "loss": 0.6201,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.26,
108
+ "learning_rate": 1.9889478706014687e-05,
109
+ "loss": 0.6064,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.27,
114
+ "learning_rate": 1.9863613034027224e-05,
115
+ "loss": 0.5918,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.29,
120
+ "learning_rate": 1.9835050748723826e-05,
121
+ "loss": 0.6169,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.3,
126
+ "learning_rate": 1.9803799658748096e-05,
127
+ "loss": 0.5954,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.32,
132
+ "learning_rate": 1.9769868307835996e-05,
133
+ "loss": 0.5874,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.33,
138
+ "learning_rate": 1.973326597248006e-05,
139
+ "loss": 0.5911,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.35,
144
+ "learning_rate": 1.9694002659393306e-05,
145
+ "loss": 0.6012,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.36,
150
+ "learning_rate": 1.9652089102773487e-05,
151
+ "loss": 0.5758,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.38,
156
+ "learning_rate": 1.9607536761368484e-05,
157
+ "loss": 0.6018,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.39,
162
+ "learning_rate": 1.9560357815343577e-05,
163
+ "loss": 0.5704,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.41,
168
+ "learning_rate": 1.9510565162951538e-05,
169
+ "loss": 0.5717,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.42,
174
+ "learning_rate": 1.9458172417006347e-05,
175
+ "loss": 0.5711,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.44,
180
+ "learning_rate": 1.9403193901161614e-05,
181
+ "loss": 0.5631,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.45,
186
+ "learning_rate": 1.934564464599461e-05,
187
+ "loss": 0.5641,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.47,
192
+ "learning_rate": 1.9285540384897073e-05,
193
+ "loss": 0.5646,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.48,
198
+ "learning_rate": 1.922289754977385e-05,
199
+ "loss": 0.5671,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.5,
204
+ "learning_rate": 1.9157733266550577e-05,
205
+ "loss": 0.5647,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.51,
210
+ "learning_rate": 1.909006535049163e-05,
211
+ "loss": 0.5566,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.53,
216
+ "learning_rate": 1.9019912301329593e-05,
217
+ "loss": 0.5595,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.54,
222
+ "learning_rate": 1.8947293298207637e-05,
223
+ "loss": 0.5542,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.56,
228
+ "learning_rate": 1.887222819443612e-05,
229
+ "loss": 0.5483,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.57,
234
+ "learning_rate": 1.879473751206489e-05,
235
+ "loss": 0.5455,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.59,
240
+ "learning_rate": 1.8714842436272774e-05,
241
+ "loss": 0.5528,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.6,
246
+ "learning_rate": 1.863256480957574e-05,
247
+ "loss": 0.5418,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.62,
252
+ "learning_rate": 1.854792712585539e-05,
253
+ "loss": 0.5628,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.63,
258
+ "learning_rate": 1.8460952524209355e-05,
259
+ "loss": 0.543,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.65,
264
+ "learning_rate": 1.8371664782625287e-05,
265
+ "loss": 0.5433,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.66,
270
+ "learning_rate": 1.8280088311480203e-05,
271
+ "loss": 0.5369,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.68,
276
+ "learning_rate": 1.8186248146866928e-05,
277
+ "loss": 0.537,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.69,
282
+ "learning_rate": 1.8090169943749477e-05,
283
+ "loss": 0.536,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.71,
288
+ "learning_rate": 1.7991879968949248e-05,
289
+ "loss": 0.5252,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.72,
294
+ "learning_rate": 1.789140509396394e-05,
295
+ "loss": 0.5158,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.74,
300
+ "learning_rate": 1.7788772787621126e-05,
301
+ "loss": 0.5253,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.75,
306
+ "learning_rate": 1.7684011108568593e-05,
307
+ "loss": 0.5321,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.77,
312
+ "learning_rate": 1.757714869760335e-05,
313
+ "loss": 0.5474,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.78,
318
+ "learning_rate": 1.7468214769841542e-05,
319
+ "loss": 0.5212,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.8,
324
+ "learning_rate": 1.735723910673132e-05,
325
+ "loss": 0.5329,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.82,
330
+ "learning_rate": 1.7244252047910893e-05,
331
+ "loss": 0.5171,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.83,
336
+ "learning_rate": 1.7129284482913973e-05,
337
+ "loss": 0.5245,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.85,
342
+ "learning_rate": 1.7012367842724887e-05,
343
+ "loss": 0.5229,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.86,
348
+ "learning_rate": 1.6893534091185658e-05,
349
+ "loss": 0.5214,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.88,
354
+ "learning_rate": 1.6772815716257414e-05,
355
+ "loss": 0.5186,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.89,
360
+ "learning_rate": 1.6650245721138483e-05,
361
+ "loss": 0.5175,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.91,
366
+ "learning_rate": 1.6525857615241686e-05,
367
+ "loss": 0.5193,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.92,
372
+ "learning_rate": 1.6399685405033168e-05,
373
+ "loss": 0.5105,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.94,
378
+ "learning_rate": 1.6271763584735373e-05,
379
+ "loss": 0.5023,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.95,
384
+ "learning_rate": 1.6142127126896682e-05,
385
+ "loss": 0.5037,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.97,
390
+ "learning_rate": 1.6010811472830253e-05,
391
+ "loss": 0.5061,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.98,
396
+ "learning_rate": 1.5877852522924733e-05,
397
+ "loss": 0.5158,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 1.0,
402
+ "learning_rate": 1.5743286626829437e-05,
403
+ "loss": 0.498,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 1.01,
408
+ "learning_rate": 1.560715057351673e-05,
409
+ "loss": 0.4929,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 1.03,
414
+ "learning_rate": 1.5469481581224274e-05,
415
+ "loss": 0.5079,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 1.04,
420
+ "learning_rate": 1.533031728727994e-05,
421
+ "loss": 0.475,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 1.06,
426
+ "learning_rate": 1.5189695737812153e-05,
427
+ "loss": 0.491,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 1.07,
432
+ "learning_rate": 1.504765537734844e-05,
433
+ "loss": 0.4846,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 1.09,
438
+ "learning_rate": 1.4904235038305084e-05,
439
+ "loss": 0.4894,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 1.1,
444
+ "learning_rate": 1.4759473930370738e-05,
445
+ "loss": 0.4718,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 1.12,
450
+ "learning_rate": 1.461341162978688e-05,
451
+ "loss": 0.4732,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 1.13,
456
+ "learning_rate": 1.4466088068528068e-05,
457
+ "loss": 0.4719,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 1.15,
462
+ "learning_rate": 1.4317543523384928e-05,
463
+ "loss": 0.488,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 1.16,
468
+ "learning_rate": 1.4167818604952906e-05,
469
+ "loss": 0.4736,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 1.18,
474
+ "learning_rate": 1.4016954246529697e-05,
475
+ "loss": 0.478,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 1.19,
480
+ "learning_rate": 1.3864991692924524e-05,
481
+ "loss": 0.4835,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 1.21,
486
+ "learning_rate": 1.3711972489182208e-05,
487
+ "loss": 0.4827,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 1.22,
492
+ "learning_rate": 1.3557938469225167e-05,
493
+ "loss": 0.46,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 1.24,
498
+ "learning_rate": 1.3402931744416432e-05,
499
+ "loss": 0.4807,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 1.25,
504
+ "learning_rate": 1.3246994692046837e-05,
505
+ "loss": 0.4766,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 1.27,
510
+ "learning_rate": 1.3090169943749475e-05,
511
+ "loss": 0.4696,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 1.28,
516
+ "learning_rate": 1.293250037384465e-05,
517
+ "loss": 0.4727,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 1.3,
522
+ "learning_rate": 1.2774029087618448e-05,
523
+ "loss": 0.4632,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 1.31,
528
+ "learning_rate": 1.26147994095382e-05,
529
+ "loss": 0.467,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 1.33,
534
+ "learning_rate": 1.2454854871407993e-05,
535
+ "loss": 0.4641,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 1.34,
540
+ "learning_rate": 1.2294239200467516e-05,
541
+ "loss": 0.4581,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 1.36,
546
+ "learning_rate": 1.213299630743747e-05,
547
+ "loss": 0.4707,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 1.37,
552
+ "learning_rate": 1.1971170274514802e-05,
553
+ "loss": 0.4664,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 1.39,
558
+ "learning_rate": 1.1808805343321102e-05,
559
+ "loss": 0.4661,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 1.4,
564
+ "learning_rate": 1.164594590280734e-05,
565
+ "loss": 0.4631,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 1.42,
570
+ "learning_rate": 1.148263647711842e-05,
571
+ "loss": 0.4598,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 1.43,
576
+ "learning_rate": 1.1318921713420691e-05,
577
+ "loss": 0.4672,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 1.45,
582
+ "learning_rate": 1.1154846369695864e-05,
583
+ "loss": 0.4646,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 1.46,
588
+ "learning_rate": 1.099045530250463e-05,
589
+ "loss": 0.4557,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 1.48,
594
+ "learning_rate": 1.0825793454723325e-05,
595
+ "loss": 0.4648,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 1.49,
600
+ "learning_rate": 1.0660905843256995e-05,
601
+ "loss": 0.4484,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 1.51,
606
+ "learning_rate": 1.0495837546732224e-05,
607
+ "loss": 0.4541,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 1.52,
612
+ "learning_rate": 1.0330633693173083e-05,
613
+ "loss": 0.4661,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 1.54,
618
+ "learning_rate": 1.0165339447663586e-05,
619
+ "loss": 0.4592,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 1.55,
624
+ "learning_rate": 1e-05,
625
+ "loss": 0.4558,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 1.57,
630
+ "learning_rate": 9.834660552336415e-06,
631
+ "loss": 0.4455,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 1.58,
636
+ "learning_rate": 9.669366306826919e-06,
637
+ "loss": 0.4492,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 1.6,
642
+ "learning_rate": 9.504162453267776e-06,
643
+ "loss": 0.4406,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 1.62,
648
+ "learning_rate": 9.339094156743007e-06,
649
+ "loss": 0.4503,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 1.63,
654
+ "learning_rate": 9.174206545276678e-06,
655
+ "loss": 0.4526,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 1.65,
660
+ "learning_rate": 9.009544697495373e-06,
661
+ "loss": 0.4396,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 1.66,
666
+ "learning_rate": 8.84515363030414e-06,
667
+ "loss": 0.4434,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 1.68,
672
+ "learning_rate": 8.68107828657931e-06,
673
+ "loss": 0.4395,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 1.69,
678
+ "learning_rate": 8.51736352288158e-06,
679
+ "loss": 0.4454,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 1.71,
684
+ "learning_rate": 8.35405409719266e-06,
685
+ "loss": 0.4366,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 1.72,
690
+ "learning_rate": 8.191194656678905e-06,
691
+ "loss": 0.4367,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 1.74,
696
+ "learning_rate": 8.0288297254852e-06,
697
+ "loss": 0.4452,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 1.75,
702
+ "learning_rate": 7.867003692562533e-06,
703
+ "loss": 0.4551,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 1.77,
708
+ "learning_rate": 7.705760799532485e-06,
709
+ "loss": 0.4432,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 1.78,
714
+ "learning_rate": 7.545145128592009e-06,
715
+ "loss": 0.4397,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 1.8,
720
+ "learning_rate": 7.385200590461803e-06,
721
+ "loss": 0.436,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 1.81,
726
+ "learning_rate": 7.225970912381557e-06,
727
+ "loss": 0.4523,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 1.83,
732
+ "learning_rate": 7.067499626155354e-06,
733
+ "loss": 0.4363,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 1.84,
738
+ "learning_rate": 6.909830056250527e-06,
739
+ "loss": 0.4515,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 1.86,
744
+ "learning_rate": 6.7530053079531664e-06,
745
+ "loss": 0.4445,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 1.87,
750
+ "learning_rate": 6.59706825558357e-06,
751
+ "loss": 0.4349,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 1.89,
756
+ "learning_rate": 6.442061530774835e-06,
757
+ "loss": 0.4506,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 1.9,
762
+ "learning_rate": 6.2880275108177915e-06,
763
+ "loss": 0.4373,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 1.92,
768
+ "learning_rate": 6.13500830707548e-06,
769
+ "loss": 0.4437,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 1.93,
774
+ "learning_rate": 5.983045753470308e-06,
775
+ "loss": 0.4448,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 1.95,
780
+ "learning_rate": 5.832181395047099e-06,
781
+ "loss": 0.4505,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 1.96,
786
+ "learning_rate": 5.6824564766150724e-06,
787
+ "loss": 0.4388,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 1.98,
792
+ "learning_rate": 5.533911931471936e-06,
793
+ "loss": 0.4411,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 1.99,
798
+ "learning_rate": 5.386588370213124e-06,
799
+ "loss": 0.4344,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 2.01,
804
+ "learning_rate": 5.240526069629265e-06,
805
+ "loss": 0.4179,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 2.02,
810
+ "learning_rate": 5.095764961694923e-06,
811
+ "loss": 0.4154,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 2.04,
816
+ "learning_rate": 4.952344622651566e-06,
817
+ "loss": 0.4176,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 2.05,
822
+ "learning_rate": 4.8103042621878515e-06,
823
+ "loss": 0.4261,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 2.07,
828
+ "learning_rate": 4.669682712720065e-06,
829
+ "loss": 0.4259,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 2.08,
834
+ "learning_rate": 4.530518418775734e-06,
835
+ "loss": 0.4197,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 2.1,
840
+ "learning_rate": 4.392849426483275e-06,
841
+ "loss": 0.423,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 2.11,
846
+ "learning_rate": 4.256713373170565e-06,
847
+ "loss": 0.4145,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 2.13,
852
+ "learning_rate": 4.12214747707527e-06,
853
+ "loss": 0.4259,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 2.14,
858
+ "learning_rate": 3.989188527169749e-06,
859
+ "loss": 0.4123,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 2.16,
864
+ "learning_rate": 3.857872873103322e-06,
865
+ "loss": 0.4179,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 2.17,
870
+ "learning_rate": 3.72823641526463e-06,
871
+ "loss": 0.4229,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 2.19,
876
+ "learning_rate": 3.6003145949668338e-06,
877
+ "loss": 0.4136,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 2.2,
882
+ "learning_rate": 3.4741423847583134e-06,
883
+ "loss": 0.4211,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 2.22,
888
+ "learning_rate": 3.349754278861517e-06,
889
+ "loss": 0.4199,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 2.23,
894
+ "learning_rate": 3.2271842837425917e-06,
895
+ "loss": 0.4162,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 2.25,
900
+ "learning_rate": 3.1064659088143424e-06,
901
+ "loss": 0.411,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 2.26,
906
+ "learning_rate": 2.9876321572751143e-06,
907
+ "loss": 0.4213,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 2.28,
912
+ "learning_rate": 2.8707155170860303e-06,
913
+ "loss": 0.4235,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 2.29,
918
+ "learning_rate": 2.7557479520891104e-06,
919
+ "loss": 0.4046,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 2.31,
924
+ "learning_rate": 2.642760893268684e-06,
925
+ "loss": 0.4227,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 2.32,
930
+ "learning_rate": 2.5317852301584642e-06,
931
+ "loss": 0.4276,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 2.34,
936
+ "learning_rate": 2.422851302396655e-06,
937
+ "loss": 0.4136,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 2.35,
942
+ "learning_rate": 2.315988891431412e-06,
943
+ "loss": 0.4064,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 2.37,
948
+ "learning_rate": 2.211227212378877e-06,
949
+ "loss": 0.4105,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 2.38,
954
+ "learning_rate": 2.1085949060360654e-06,
955
+ "loss": 0.4126,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 2.4,
960
+ "learning_rate": 2.008120031050753e-06,
961
+ "loss": 0.4124,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 2.42,
966
+ "learning_rate": 1.9098300562505266e-06,
967
+ "loss": 0.4172,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 2.43,
972
+ "learning_rate": 1.8137518531330768e-06,
973
+ "loss": 0.4183,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 2.45,
978
+ "learning_rate": 1.7199116885197996e-06,
979
+ "loss": 0.4127,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 2.46,
984
+ "learning_rate": 1.6283352173747148e-06,
985
+ "loss": 0.4104,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 2.48,
990
+ "learning_rate": 1.5390474757906449e-06,
991
+ "loss": 0.4159,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 2.49,
996
+ "learning_rate": 1.4520728741446087e-06,
997
+ "loss": 0.4049,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 2.51,
1002
+ "learning_rate": 1.367435190424261e-06,
1003
+ "loss": 0.4102,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 2.52,
1008
+ "learning_rate": 1.2851575637272262e-06,
1009
+ "loss": 0.4163,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 2.54,
1014
+ "learning_rate": 1.2052624879351105e-06,
1015
+ "loss": 0.4126,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 2.55,
1020
+ "learning_rate": 1.127771805563882e-06,
1021
+ "loss": 0.4046,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 2.57,
1026
+ "learning_rate": 1.0527067017923654e-06,
1027
+ "loss": 0.4093,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 2.58,
1032
+ "learning_rate": 9.800876986704111e-07,
1033
+ "loss": 0.4106,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 2.6,
1038
+ "learning_rate": 9.09934649508375e-07,
1039
+ "loss": 0.4137,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 2.61,
1044
+ "learning_rate": 8.42266733449425e-07,
1045
+ "loss": 0.4156,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 2.63,
1050
+ "learning_rate": 7.771024502261526e-07,
1051
+ "loss": 0.4166,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 2.64,
1056
+ "learning_rate": 7.144596151029304e-07,
1057
+ "loss": 0.412,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 2.66,
1062
+ "learning_rate": 6.543553540053926e-07,
1063
+ "loss": 0.4027,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 2.67,
1068
+ "learning_rate": 5.968060988383884e-07,
1069
+ "loss": 0.4191,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 2.69,
1074
+ "learning_rate": 5.418275829936537e-07,
1075
+ "loss": 0.4093,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 2.7,
1080
+ "learning_rate": 4.894348370484648e-07,
1081
+ "loss": 0.4143,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 2.72,
1086
+ "learning_rate": 4.396421846564236e-07,
1087
+ "loss": 0.4044,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 2.73,
1092
+ "learning_rate": 3.924632386315186e-07,
1093
+ "loss": 0.4133,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 2.75,
1098
+ "learning_rate": 3.4791089722651437e-07,
1099
+ "loss": 0.4093,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 2.76,
1104
+ "learning_rate": 3.059973406066963e-07,
1105
+ "loss": 0.4156,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 2.78,
1110
+ "learning_rate": 2.667340275199426e-07,
1111
+ "loss": 0.407,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 2.79,
1116
+ "learning_rate": 2.3013169216400732e-07,
1117
+ "loss": 0.4157,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 2.81,
1122
+ "learning_rate": 1.9620034125190645e-07,
1123
+ "loss": 0.4187,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 2.82,
1128
+ "learning_rate": 1.6494925127617632e-07,
1129
+ "loss": 0.4145,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 2.84,
1134
+ "learning_rate": 1.3638696597277678e-07,
1135
+ "loss": 0.4102,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 2.85,
1140
+ "learning_rate": 1.1052129398531508e-07,
1141
+ "loss": 0.3985,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 2.87,
1146
+ "learning_rate": 8.735930673024806e-08,
1147
+ "loss": 0.4076,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 2.88,
1152
+ "learning_rate": 6.690733646361858e-08,
1153
+ "loss": 0.4251,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 2.9,
1158
+ "learning_rate": 4.9170974549885844e-08,
1159
+ "loss": 0.4026,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 2.91,
1164
+ "learning_rate": 3.4155069933301535e-08,
1165
+ "loss": 0.4114,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 2.93,
1170
+ "learning_rate": 2.1863727812254653e-08,
1171
+ "loss": 0.4171,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 2.94,
1176
+ "learning_rate": 1.230030851695263e-08,
1177
+ "loss": 0.412,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 2.96,
1182
+ "learning_rate": 5.467426590739511e-09,
1183
+ "loss": 0.4121,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 2.97,
1188
+ "learning_rate": 1.3669500753099586e-09,
1189
+ "loss": 0.4031,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 2.99,
1194
+ "learning_rate": 0.0,
1195
+ "loss": 0.4044,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 2.99,
1200
+ "step": 198,
1201
+ "total_flos": 2.0980282356054098e+18,
1202
+ "train_loss": 0.48554843874892806,
1203
+ "train_runtime": 32384.6701,
1204
+ "train_samples_per_second": 3.141,
1205
+ "train_steps_per_second": 0.006
1206
+ }
1207
+ ],
1208
+ "max_steps": 198,
1209
+ "num_train_epochs": 3,
1210
+ "total_flos": 2.0980282356054098e+18,
1211
+ "trial_name": null,
1212
+ "trial_params": null
1213
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33fe34f8db2582d20551eb8519c18cc26e32d20e3db83aa9689486e565a69569
3
+ size 3771