andrealexroom commited on
Commit
e1602c0
·
verified ·
1 Parent(s): b452919

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.38.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.38.0.dev0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22079b093dfde012d978613a675d5c9c425f5a6e485e105f74b1bac0a065bc9
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a796f2f7befd1028b419605bf936133f4ac741831ba2b0da6d83f3e4a876f025
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b8c43824ac0b37d8c41c441bd2b6fb14736b9d0020e2ecd68321766384dfdc
3
+ size 4540516344
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bab4a3c565da0114115579742d24a714384e683627576bcb227bc4e05ff5c1
3
+ size 28967182666
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:756c985f7c23c701c5bcc5bb2690b599901cabe341174c91d826411b99348827
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74aaa50e8f02e10d3a0963f7f5df08a8a3084d8eaa95e26a979fc79e3307d659
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1091 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0303476340967141,
5
+ "eval_steps": 850,
6
+ "global_step": 23800,
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": 1e-05,
14
+ "loss": 1.3872,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.04,
19
+ "learning_rate": 1e-05,
20
+ "loss": 1.3293,
21
+ "step": 850
22
+ },
23
+ {
24
+ "epoch": 0.04,
25
+ "eval_validation_privacy_sources_loss": 0.9622901678085327,
26
+ "eval_validation_privacy_sources_runtime": 200.3089,
27
+ "eval_validation_privacy_sources_samples_per_second": 1.413,
28
+ "eval_validation_privacy_sources_steps_per_second": 0.709,
29
+ "step": 850
30
+ },
31
+ {
32
+ "epoch": 0.04,
33
+ "eval_validation_agenda_digitale_loss": 1.5158238410949707,
34
+ "eval_validation_agenda_digitale_runtime": 179.555,
35
+ "eval_validation_agenda_digitale_samples_per_second": 1.415,
36
+ "eval_validation_agenda_digitale_steps_per_second": 0.707,
37
+ "step": 850
38
+ },
39
+ {
40
+ "epoch": 0.04,
41
+ "eval_validation_leggepertutti_loss": 1.3529233932495117,
42
+ "eval_validation_leggepertutti_runtime": 33.1049,
43
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
44
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
45
+ "step": 850
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "eval_validation_altalexprivacy_loss": 1.339850902557373,
50
+ "eval_validation_altalexprivacy_runtime": 55.8709,
51
+ "eval_validation_altalexprivacy_samples_per_second": 1.414,
52
+ "eval_validation_altalexprivacy_steps_per_second": 0.716,
53
+ "step": 850
54
+ },
55
+ {
56
+ "epoch": 0.07,
57
+ "learning_rate": 1e-05,
58
+ "loss": 1.2253,
59
+ "step": 1700
60
+ },
61
+ {
62
+ "epoch": 0.07,
63
+ "eval_validation_privacy_sources_loss": 0.9017069339752197,
64
+ "eval_validation_privacy_sources_runtime": 199.3204,
65
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
66
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
67
+ "step": 1700
68
+ },
69
+ {
70
+ "epoch": 0.07,
71
+ "eval_validation_agenda_digitale_loss": 1.4798156023025513,
72
+ "eval_validation_agenda_digitale_runtime": 178.914,
73
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
74
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
75
+ "step": 1700
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "eval_validation_leggepertutti_loss": 1.3338710069656372,
80
+ "eval_validation_leggepertutti_runtime": 33.1327,
81
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
82
+ "eval_validation_leggepertutti_steps_per_second": 0.724,
83
+ "step": 1700
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "eval_validation_altalexprivacy_loss": 1.288530707359314,
88
+ "eval_validation_altalexprivacy_runtime": 55.661,
89
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
90
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
91
+ "step": 1700
92
+ },
93
+ {
94
+ "epoch": 0.11,
95
+ "learning_rate": 1e-05,
96
+ "loss": 1.1702,
97
+ "step": 2550
98
+ },
99
+ {
100
+ "epoch": 0.11,
101
+ "eval_validation_privacy_sources_loss": 0.8659703731536865,
102
+ "eval_validation_privacy_sources_runtime": 199.3071,
103
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
104
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
105
+ "step": 2550
106
+ },
107
+ {
108
+ "epoch": 0.11,
109
+ "eval_validation_agenda_digitale_loss": 1.4508357048034668,
110
+ "eval_validation_agenda_digitale_runtime": 178.876,
111
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
112
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
113
+ "step": 2550
114
+ },
115
+ {
116
+ "epoch": 0.11,
117
+ "eval_validation_leggepertutti_loss": 1.3027405738830566,
118
+ "eval_validation_leggepertutti_runtime": 33.112,
119
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
120
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
121
+ "step": 2550
122
+ },
123
+ {
124
+ "epoch": 0.11,
125
+ "eval_validation_altalexprivacy_loss": 1.266638159751892,
126
+ "eval_validation_altalexprivacy_runtime": 55.6304,
127
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
128
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
129
+ "step": 2550
130
+ },
131
+ {
132
+ "epoch": 0.15,
133
+ "learning_rate": 1e-05,
134
+ "loss": 1.1511,
135
+ "step": 3400
136
+ },
137
+ {
138
+ "epoch": 0.15,
139
+ "eval_validation_privacy_sources_loss": 0.8465688228607178,
140
+ "eval_validation_privacy_sources_runtime": 199.2231,
141
+ "eval_validation_privacy_sources_samples_per_second": 1.421,
142
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
143
+ "step": 3400
144
+ },
145
+ {
146
+ "epoch": 0.15,
147
+ "eval_validation_agenda_digitale_loss": 1.4313058853149414,
148
+ "eval_validation_agenda_digitale_runtime": 178.809,
149
+ "eval_validation_agenda_digitale_samples_per_second": 1.421,
150
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
151
+ "step": 3400
152
+ },
153
+ {
154
+ "epoch": 0.15,
155
+ "eval_validation_leggepertutti_loss": 1.2922743558883667,
156
+ "eval_validation_leggepertutti_runtime": 33.1014,
157
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
158
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
159
+ "step": 3400
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "eval_validation_altalexprivacy_loss": 1.2391875982284546,
164
+ "eval_validation_altalexprivacy_runtime": 55.6067,
165
+ "eval_validation_altalexprivacy_samples_per_second": 1.421,
166
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
167
+ "step": 3400
168
+ },
169
+ {
170
+ "epoch": 0.18,
171
+ "learning_rate": 1e-05,
172
+ "loss": 1.1108,
173
+ "step": 4250
174
+ },
175
+ {
176
+ "epoch": 0.18,
177
+ "eval_validation_privacy_sources_loss": 0.8285683393478394,
178
+ "eval_validation_privacy_sources_runtime": 199.2421,
179
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
180
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
181
+ "step": 4250
182
+ },
183
+ {
184
+ "epoch": 0.18,
185
+ "eval_validation_agenda_digitale_loss": 1.4138884544372559,
186
+ "eval_validation_agenda_digitale_runtime": 178.8179,
187
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
188
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
189
+ "step": 4250
190
+ },
191
+ {
192
+ "epoch": 0.18,
193
+ "eval_validation_leggepertutti_loss": 1.2774792909622192,
194
+ "eval_validation_leggepertutti_runtime": 33.1133,
195
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
196
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
197
+ "step": 4250
198
+ },
199
+ {
200
+ "epoch": 0.18,
201
+ "eval_validation_altalexprivacy_loss": 1.2207868099212646,
202
+ "eval_validation_altalexprivacy_runtime": 55.6438,
203
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
204
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
205
+ "step": 4250
206
+ },
207
+ {
208
+ "epoch": 0.22,
209
+ "learning_rate": 1e-05,
210
+ "loss": 1.0925,
211
+ "step": 5100
212
+ },
213
+ {
214
+ "epoch": 0.22,
215
+ "eval_validation_privacy_sources_loss": 0.8132259845733643,
216
+ "eval_validation_privacy_sources_runtime": 199.2711,
217
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
218
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
219
+ "step": 5100
220
+ },
221
+ {
222
+ "epoch": 0.22,
223
+ "eval_validation_agenda_digitale_loss": 1.4020613431930542,
224
+ "eval_validation_agenda_digitale_runtime": 178.883,
225
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
226
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
227
+ "step": 5100
228
+ },
229
+ {
230
+ "epoch": 0.22,
231
+ "eval_validation_leggepertutti_loss": 1.2761023044586182,
232
+ "eval_validation_leggepertutti_runtime": 33.1148,
233
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
234
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
235
+ "step": 5100
236
+ },
237
+ {
238
+ "epoch": 0.22,
239
+ "eval_validation_altalexprivacy_loss": 1.2088932991027832,
240
+ "eval_validation_altalexprivacy_runtime": 55.6438,
241
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
242
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
243
+ "step": 5100
244
+ },
245
+ {
246
+ "epoch": 0.26,
247
+ "learning_rate": 1e-05,
248
+ "loss": 1.0731,
249
+ "step": 5950
250
+ },
251
+ {
252
+ "epoch": 0.26,
253
+ "eval_validation_privacy_sources_loss": 0.8024860620498657,
254
+ "eval_validation_privacy_sources_runtime": 199.203,
255
+ "eval_validation_privacy_sources_samples_per_second": 1.421,
256
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
257
+ "step": 5950
258
+ },
259
+ {
260
+ "epoch": 0.26,
261
+ "eval_validation_agenda_digitale_loss": 1.392274022102356,
262
+ "eval_validation_agenda_digitale_runtime": 178.825,
263
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
264
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
265
+ "step": 5950
266
+ },
267
+ {
268
+ "epoch": 0.26,
269
+ "eval_validation_leggepertutti_loss": 1.2612470388412476,
270
+ "eval_validation_leggepertutti_runtime": 33.1124,
271
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
272
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
273
+ "step": 5950
274
+ },
275
+ {
276
+ "epoch": 0.26,
277
+ "eval_validation_altalexprivacy_loss": 1.1972081661224365,
278
+ "eval_validation_altalexprivacy_runtime": 55.6529,
279
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
280
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
281
+ "step": 5950
282
+ },
283
+ {
284
+ "epoch": 0.29,
285
+ "learning_rate": 1e-05,
286
+ "loss": 1.0762,
287
+ "step": 6800
288
+ },
289
+ {
290
+ "epoch": 0.29,
291
+ "eval_validation_privacy_sources_loss": 0.7932194471359253,
292
+ "eval_validation_privacy_sources_runtime": 199.279,
293
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
294
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
295
+ "step": 6800
296
+ },
297
+ {
298
+ "epoch": 0.29,
299
+ "eval_validation_agenda_digitale_loss": 1.3839406967163086,
300
+ "eval_validation_agenda_digitale_runtime": 178.8269,
301
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
302
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
303
+ "step": 6800
304
+ },
305
+ {
306
+ "epoch": 0.29,
307
+ "eval_validation_leggepertutti_loss": 1.255569577217102,
308
+ "eval_validation_leggepertutti_runtime": 33.1069,
309
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
310
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
311
+ "step": 6800
312
+ },
313
+ {
314
+ "epoch": 0.29,
315
+ "eval_validation_altalexprivacy_loss": 1.1889532804489136,
316
+ "eval_validation_altalexprivacy_runtime": 55.6343,
317
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
318
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
319
+ "step": 6800
320
+ },
321
+ {
322
+ "epoch": 0.33,
323
+ "learning_rate": 1e-05,
324
+ "loss": 1.0485,
325
+ "step": 7650
326
+ },
327
+ {
328
+ "epoch": 0.33,
329
+ "eval_validation_privacy_sources_loss": 0.7843455672264099,
330
+ "eval_validation_privacy_sources_runtime": 199.2372,
331
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
332
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
333
+ "step": 7650
334
+ },
335
+ {
336
+ "epoch": 0.33,
337
+ "eval_validation_agenda_digitale_loss": 1.3763149976730347,
338
+ "eval_validation_agenda_digitale_runtime": 178.8007,
339
+ "eval_validation_agenda_digitale_samples_per_second": 1.421,
340
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
341
+ "step": 7650
342
+ },
343
+ {
344
+ "epoch": 0.33,
345
+ "eval_validation_leggepertutti_loss": 1.2523000240325928,
346
+ "eval_validation_leggepertutti_runtime": 33.1038,
347
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
348
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
349
+ "step": 7650
350
+ },
351
+ {
352
+ "epoch": 0.33,
353
+ "eval_validation_altalexprivacy_loss": 1.1805671453475952,
354
+ "eval_validation_altalexprivacy_runtime": 55.6339,
355
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
356
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
357
+ "step": 7650
358
+ },
359
+ {
360
+ "epoch": 0.37,
361
+ "learning_rate": 1e-05,
362
+ "loss": 1.054,
363
+ "step": 8500
364
+ },
365
+ {
366
+ "epoch": 0.37,
367
+ "eval_validation_privacy_sources_loss": 0.7795467972755432,
368
+ "eval_validation_privacy_sources_runtime": 199.2864,
369
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
370
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
371
+ "step": 8500
372
+ },
373
+ {
374
+ "epoch": 0.37,
375
+ "eval_validation_agenda_digitale_loss": 1.3715742826461792,
376
+ "eval_validation_agenda_digitale_runtime": 178.8753,
377
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
378
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
379
+ "step": 8500
380
+ },
381
+ {
382
+ "epoch": 0.37,
383
+ "eval_validation_leggepertutti_loss": 1.244837999343872,
384
+ "eval_validation_leggepertutti_runtime": 33.1078,
385
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
386
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
387
+ "step": 8500
388
+ },
389
+ {
390
+ "epoch": 0.37,
391
+ "eval_validation_altalexprivacy_loss": 1.172226905822754,
392
+ "eval_validation_altalexprivacy_runtime": 55.646,
393
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
394
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
395
+ "step": 8500
396
+ },
397
+ {
398
+ "epoch": 0.4,
399
+ "learning_rate": 1e-05,
400
+ "loss": 1.048,
401
+ "step": 9350
402
+ },
403
+ {
404
+ "epoch": 0.4,
405
+ "eval_validation_privacy_sources_loss": 0.7726686000823975,
406
+ "eval_validation_privacy_sources_runtime": 199.223,
407
+ "eval_validation_privacy_sources_samples_per_second": 1.421,
408
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
409
+ "step": 9350
410
+ },
411
+ {
412
+ "epoch": 0.4,
413
+ "eval_validation_agenda_digitale_loss": 1.3649834394454956,
414
+ "eval_validation_agenda_digitale_runtime": 178.7809,
415
+ "eval_validation_agenda_digitale_samples_per_second": 1.421,
416
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
417
+ "step": 9350
418
+ },
419
+ {
420
+ "epoch": 0.4,
421
+ "eval_validation_leggepertutti_loss": 1.236178994178772,
422
+ "eval_validation_leggepertutti_runtime": 33.1028,
423
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
424
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
425
+ "step": 9350
426
+ },
427
+ {
428
+ "epoch": 0.4,
429
+ "eval_validation_altalexprivacy_loss": 1.1653445959091187,
430
+ "eval_validation_altalexprivacy_runtime": 55.6437,
431
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
432
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
433
+ "step": 9350
434
+ },
435
+ {
436
+ "epoch": 0.44,
437
+ "learning_rate": 1e-05,
438
+ "loss": 1.0298,
439
+ "step": 10200
440
+ },
441
+ {
442
+ "epoch": 0.44,
443
+ "eval_validation_privacy_sources_loss": 0.7679473161697388,
444
+ "eval_validation_privacy_sources_runtime": 199.2891,
445
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
446
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
447
+ "step": 10200
448
+ },
449
+ {
450
+ "epoch": 0.44,
451
+ "eval_validation_agenda_digitale_loss": 1.3605149984359741,
452
+ "eval_validation_agenda_digitale_runtime": 178.9059,
453
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
454
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
455
+ "step": 10200
456
+ },
457
+ {
458
+ "epoch": 0.44,
459
+ "eval_validation_leggepertutti_loss": 1.236514925956726,
460
+ "eval_validation_leggepertutti_runtime": 33.1183,
461
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
462
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
463
+ "step": 10200
464
+ },
465
+ {
466
+ "epoch": 0.44,
467
+ "eval_validation_altalexprivacy_loss": 1.1572242975234985,
468
+ "eval_validation_altalexprivacy_runtime": 55.6539,
469
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
470
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
471
+ "step": 10200
472
+ },
473
+ {
474
+ "epoch": 0.48,
475
+ "learning_rate": 1e-05,
476
+ "loss": 1.0185,
477
+ "step": 11050
478
+ },
479
+ {
480
+ "epoch": 0.48,
481
+ "eval_validation_privacy_sources_loss": 0.7627520561218262,
482
+ "eval_validation_privacy_sources_runtime": 199.2688,
483
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
484
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
485
+ "step": 11050
486
+ },
487
+ {
488
+ "epoch": 0.48,
489
+ "eval_validation_agenda_digitale_loss": 1.3563733100891113,
490
+ "eval_validation_agenda_digitale_runtime": 178.8566,
491
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
492
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
493
+ "step": 11050
494
+ },
495
+ {
496
+ "epoch": 0.48,
497
+ "eval_validation_leggepertutti_loss": 1.2360310554504395,
498
+ "eval_validation_leggepertutti_runtime": 33.1157,
499
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
500
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
501
+ "step": 11050
502
+ },
503
+ {
504
+ "epoch": 0.48,
505
+ "eval_validation_altalexprivacy_loss": 1.1465963125228882,
506
+ "eval_validation_altalexprivacy_runtime": 55.66,
507
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
508
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
509
+ "step": 11050
510
+ },
511
+ {
512
+ "epoch": 0.52,
513
+ "learning_rate": 1e-05,
514
+ "loss": 1.0216,
515
+ "step": 11900
516
+ },
517
+ {
518
+ "epoch": 0.52,
519
+ "eval_validation_privacy_sources_loss": 0.7578811645507812,
520
+ "eval_validation_privacy_sources_runtime": 199.3006,
521
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
522
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
523
+ "step": 11900
524
+ },
525
+ {
526
+ "epoch": 0.52,
527
+ "eval_validation_agenda_digitale_loss": 1.3509842157363892,
528
+ "eval_validation_agenda_digitale_runtime": 178.8885,
529
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
530
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
531
+ "step": 11900
532
+ },
533
+ {
534
+ "epoch": 0.52,
535
+ "eval_validation_leggepertutti_loss": 1.235782504081726,
536
+ "eval_validation_leggepertutti_runtime": 33.1202,
537
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
538
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
539
+ "step": 11900
540
+ },
541
+ {
542
+ "epoch": 0.52,
543
+ "eval_validation_altalexprivacy_loss": 1.142249584197998,
544
+ "eval_validation_altalexprivacy_runtime": 55.6558,
545
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
546
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
547
+ "step": 11900
548
+ },
549
+ {
550
+ "epoch": 0.55,
551
+ "learning_rate": 1e-05,
552
+ "loss": 1.0038,
553
+ "step": 12750
554
+ },
555
+ {
556
+ "epoch": 0.55,
557
+ "eval_validation_privacy_sources_loss": 0.7522856593132019,
558
+ "eval_validation_privacy_sources_runtime": 199.4393,
559
+ "eval_validation_privacy_sources_samples_per_second": 1.419,
560
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
561
+ "step": 12750
562
+ },
563
+ {
564
+ "epoch": 0.55,
565
+ "eval_validation_agenda_digitale_loss": 1.349084496498108,
566
+ "eval_validation_agenda_digitale_runtime": 178.9286,
567
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
568
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
569
+ "step": 12750
570
+ },
571
+ {
572
+ "epoch": 0.55,
573
+ "eval_validation_leggepertutti_loss": 1.2313765287399292,
574
+ "eval_validation_leggepertutti_runtime": 33.12,
575
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
576
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
577
+ "step": 12750
578
+ },
579
+ {
580
+ "epoch": 0.55,
581
+ "eval_validation_altalexprivacy_loss": 1.1391321420669556,
582
+ "eval_validation_altalexprivacy_runtime": 55.6743,
583
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
584
+ "eval_validation_altalexprivacy_steps_per_second": 0.718,
585
+ "step": 12750
586
+ },
587
+ {
588
+ "epoch": 0.59,
589
+ "learning_rate": 1e-05,
590
+ "loss": 1.0026,
591
+ "step": 13600
592
+ },
593
+ {
594
+ "epoch": 0.59,
595
+ "eval_validation_privacy_sources_loss": 0.7488484978675842,
596
+ "eval_validation_privacy_sources_runtime": 199.3564,
597
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
598
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
599
+ "step": 13600
600
+ },
601
+ {
602
+ "epoch": 0.59,
603
+ "eval_validation_agenda_digitale_loss": 1.3464651107788086,
604
+ "eval_validation_agenda_digitale_runtime": 178.9247,
605
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
606
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
607
+ "step": 13600
608
+ },
609
+ {
610
+ "epoch": 0.59,
611
+ "eval_validation_leggepertutti_loss": 1.2265664339065552,
612
+ "eval_validation_leggepertutti_runtime": 33.1294,
613
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
614
+ "eval_validation_leggepertutti_steps_per_second": 0.724,
615
+ "step": 13600
616
+ },
617
+ {
618
+ "epoch": 0.59,
619
+ "eval_validation_altalexprivacy_loss": 1.1346131563186646,
620
+ "eval_validation_altalexprivacy_runtime": 55.6856,
621
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
622
+ "eval_validation_altalexprivacy_steps_per_second": 0.718,
623
+ "step": 13600
624
+ },
625
+ {
626
+ "epoch": 0.63,
627
+ "learning_rate": 1e-05,
628
+ "loss": 1.0026,
629
+ "step": 14450
630
+ },
631
+ {
632
+ "epoch": 0.63,
633
+ "eval_validation_privacy_sources_loss": 0.745000958442688,
634
+ "eval_validation_privacy_sources_runtime": 199.3312,
635
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
636
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
637
+ "step": 14450
638
+ },
639
+ {
640
+ "epoch": 0.63,
641
+ "eval_validation_agenda_digitale_loss": 1.343147873878479,
642
+ "eval_validation_agenda_digitale_runtime": 178.8878,
643
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
644
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
645
+ "step": 14450
646
+ },
647
+ {
648
+ "epoch": 0.63,
649
+ "eval_validation_leggepertutti_loss": 1.2294485569000244,
650
+ "eval_validation_leggepertutti_runtime": 33.1117,
651
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
652
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
653
+ "step": 14450
654
+ },
655
+ {
656
+ "epoch": 0.63,
657
+ "eval_validation_altalexprivacy_loss": 1.135871171951294,
658
+ "eval_validation_altalexprivacy_runtime": 55.6423,
659
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
660
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
661
+ "step": 14450
662
+ },
663
+ {
664
+ "epoch": 0.66,
665
+ "learning_rate": 1e-05,
666
+ "loss": 0.9954,
667
+ "step": 15300
668
+ },
669
+ {
670
+ "epoch": 0.66,
671
+ "eval_validation_privacy_sources_loss": 0.7410914301872253,
672
+ "eval_validation_privacy_sources_runtime": 199.3489,
673
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
674
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
675
+ "step": 15300
676
+ },
677
+ {
678
+ "epoch": 0.66,
679
+ "eval_validation_agenda_digitale_loss": 1.3405917882919312,
680
+ "eval_validation_agenda_digitale_runtime": 178.8997,
681
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
682
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
683
+ "step": 15300
684
+ },
685
+ {
686
+ "epoch": 0.66,
687
+ "eval_validation_leggepertutti_loss": 1.2265692949295044,
688
+ "eval_validation_leggepertutti_runtime": 33.1168,
689
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
690
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
691
+ "step": 15300
692
+ },
693
+ {
694
+ "epoch": 0.66,
695
+ "eval_validation_altalexprivacy_loss": 1.1313049793243408,
696
+ "eval_validation_altalexprivacy_runtime": 55.6608,
697
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
698
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
699
+ "step": 15300
700
+ },
701
+ {
702
+ "epoch": 0.7,
703
+ "learning_rate": 1e-05,
704
+ "loss": 0.9951,
705
+ "step": 16150
706
+ },
707
+ {
708
+ "epoch": 0.7,
709
+ "eval_validation_privacy_sources_loss": 0.7371454834938049,
710
+ "eval_validation_privacy_sources_runtime": 199.2936,
711
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
712
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
713
+ "step": 16150
714
+ },
715
+ {
716
+ "epoch": 0.7,
717
+ "eval_validation_agenda_digitale_loss": 1.3382099866867065,
718
+ "eval_validation_agenda_digitale_runtime": 178.857,
719
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
720
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
721
+ "step": 16150
722
+ },
723
+ {
724
+ "epoch": 0.7,
725
+ "eval_validation_leggepertutti_loss": 1.2268116474151611,
726
+ "eval_validation_leggepertutti_runtime": 33.1096,
727
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
728
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
729
+ "step": 16150
730
+ },
731
+ {
732
+ "epoch": 0.7,
733
+ "eval_validation_altalexprivacy_loss": 1.1287522315979004,
734
+ "eval_validation_altalexprivacy_runtime": 55.6347,
735
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
736
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
737
+ "step": 16150
738
+ },
739
+ {
740
+ "epoch": 0.74,
741
+ "learning_rate": 1e-05,
742
+ "loss": 0.995,
743
+ "step": 17000
744
+ },
745
+ {
746
+ "epoch": 0.74,
747
+ "eval_validation_privacy_sources_loss": 0.7312896847724915,
748
+ "eval_validation_privacy_sources_runtime": 199.3058,
749
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
750
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
751
+ "step": 17000
752
+ },
753
+ {
754
+ "epoch": 0.74,
755
+ "eval_validation_agenda_digitale_loss": 1.3348143100738525,
756
+ "eval_validation_agenda_digitale_runtime": 178.8799,
757
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
758
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
759
+ "step": 17000
760
+ },
761
+ {
762
+ "epoch": 0.74,
763
+ "eval_validation_leggepertutti_loss": 1.2212121486663818,
764
+ "eval_validation_leggepertutti_runtime": 33.0958,
765
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
766
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
767
+ "step": 17000
768
+ },
769
+ {
770
+ "epoch": 0.74,
771
+ "eval_validation_altalexprivacy_loss": 1.1240836381912231,
772
+ "eval_validation_altalexprivacy_runtime": 55.6448,
773
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
774
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
775
+ "step": 17000
776
+ },
777
+ {
778
+ "epoch": 0.77,
779
+ "learning_rate": 1e-05,
780
+ "loss": 0.9972,
781
+ "step": 17850
782
+ },
783
+ {
784
+ "epoch": 0.77,
785
+ "eval_validation_privacy_sources_loss": 0.7291250824928284,
786
+ "eval_validation_privacy_sources_runtime": 199.2823,
787
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
788
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
789
+ "step": 17850
790
+ },
791
+ {
792
+ "epoch": 0.77,
793
+ "eval_validation_agenda_digitale_loss": 1.3328888416290283,
794
+ "eval_validation_agenda_digitale_runtime": 178.8216,
795
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
796
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
797
+ "step": 17850
798
+ },
799
+ {
800
+ "epoch": 0.77,
801
+ "eval_validation_leggepertutti_loss": 1.2234724760055542,
802
+ "eval_validation_leggepertutti_runtime": 33.1127,
803
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
804
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
805
+ "step": 17850
806
+ },
807
+ {
808
+ "epoch": 0.77,
809
+ "eval_validation_altalexprivacy_loss": 1.1235439777374268,
810
+ "eval_validation_altalexprivacy_runtime": 55.6436,
811
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
812
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
813
+ "step": 17850
814
+ },
815
+ {
816
+ "epoch": 0.81,
817
+ "learning_rate": 1e-05,
818
+ "loss": 0.9893,
819
+ "step": 18700
820
+ },
821
+ {
822
+ "epoch": 0.81,
823
+ "eval_validation_privacy_sources_loss": 0.7286735773086548,
824
+ "eval_validation_privacy_sources_runtime": 199.3294,
825
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
826
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
827
+ "step": 18700
828
+ },
829
+ {
830
+ "epoch": 0.81,
831
+ "eval_validation_agenda_digitale_loss": 1.3304667472839355,
832
+ "eval_validation_agenda_digitale_runtime": 178.8336,
833
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
834
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
835
+ "step": 18700
836
+ },
837
+ {
838
+ "epoch": 0.81,
839
+ "eval_validation_leggepertutti_loss": 1.217714786529541,
840
+ "eval_validation_leggepertutti_runtime": 33.1048,
841
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
842
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
843
+ "step": 18700
844
+ },
845
+ {
846
+ "epoch": 0.81,
847
+ "eval_validation_altalexprivacy_loss": 1.1187307834625244,
848
+ "eval_validation_altalexprivacy_runtime": 55.6405,
849
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
850
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
851
+ "step": 18700
852
+ },
853
+ {
854
+ "epoch": 0.85,
855
+ "learning_rate": 1e-05,
856
+ "loss": 0.9956,
857
+ "step": 19550
858
+ },
859
+ {
860
+ "epoch": 0.85,
861
+ "eval_validation_privacy_sources_loss": 0.7259235978126526,
862
+ "eval_validation_privacy_sources_runtime": 199.3068,
863
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
864
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
865
+ "step": 19550
866
+ },
867
+ {
868
+ "epoch": 0.85,
869
+ "eval_validation_agenda_digitale_loss": 1.327946662902832,
870
+ "eval_validation_agenda_digitale_runtime": 178.8961,
871
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
872
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
873
+ "step": 19550
874
+ },
875
+ {
876
+ "epoch": 0.85,
877
+ "eval_validation_leggepertutti_loss": 1.2208385467529297,
878
+ "eval_validation_leggepertutti_runtime": 33.1153,
879
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
880
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
881
+ "step": 19550
882
+ },
883
+ {
884
+ "epoch": 0.85,
885
+ "eval_validation_altalexprivacy_loss": 1.1140854358673096,
886
+ "eval_validation_altalexprivacy_runtime": 55.664,
887
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
888
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
889
+ "step": 19550
890
+ },
891
+ {
892
+ "epoch": 0.88,
893
+ "learning_rate": 1e-05,
894
+ "loss": 0.9756,
895
+ "step": 20400
896
+ },
897
+ {
898
+ "epoch": 0.88,
899
+ "eval_validation_privacy_sources_loss": 0.7232377529144287,
900
+ "eval_validation_privacy_sources_runtime": 199.2754,
901
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
902
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
903
+ "step": 20400
904
+ },
905
+ {
906
+ "epoch": 0.88,
907
+ "eval_validation_agenda_digitale_loss": 1.3270857334136963,
908
+ "eval_validation_agenda_digitale_runtime": 178.8559,
909
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
910
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
911
+ "step": 20400
912
+ },
913
+ {
914
+ "epoch": 0.88,
915
+ "eval_validation_leggepertutti_loss": 1.2199361324310303,
916
+ "eval_validation_leggepertutti_runtime": 33.1051,
917
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
918
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
919
+ "step": 20400
920
+ },
921
+ {
922
+ "epoch": 0.88,
923
+ "eval_validation_altalexprivacy_loss": 1.1153144836425781,
924
+ "eval_validation_altalexprivacy_runtime": 55.6286,
925
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
926
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
927
+ "step": 20400
928
+ },
929
+ {
930
+ "epoch": 0.92,
931
+ "learning_rate": 1e-05,
932
+ "loss": 0.9686,
933
+ "step": 21250
934
+ },
935
+ {
936
+ "epoch": 0.92,
937
+ "eval_validation_privacy_sources_loss": 0.7215350866317749,
938
+ "eval_validation_privacy_sources_runtime": 199.2882,
939
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
940
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
941
+ "step": 21250
942
+ },
943
+ {
944
+ "epoch": 0.92,
945
+ "eval_validation_agenda_digitale_loss": 1.3252431154251099,
946
+ "eval_validation_agenda_digitale_runtime": 178.8508,
947
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
948
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
949
+ "step": 21250
950
+ },
951
+ {
952
+ "epoch": 0.92,
953
+ "eval_validation_leggepertutti_loss": 1.2179052829742432,
954
+ "eval_validation_leggepertutti_runtime": 33.1089,
955
+ "eval_validation_leggepertutti_samples_per_second": 1.42,
956
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
957
+ "step": 21250
958
+ },
959
+ {
960
+ "epoch": 0.92,
961
+ "eval_validation_altalexprivacy_loss": 1.1136621236801147,
962
+ "eval_validation_altalexprivacy_runtime": 55.6569,
963
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
964
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
965
+ "step": 21250
966
+ },
967
+ {
968
+ "epoch": 0.96,
969
+ "learning_rate": 1e-05,
970
+ "loss": 0.9668,
971
+ "step": 22100
972
+ },
973
+ {
974
+ "epoch": 0.96,
975
+ "eval_validation_privacy_sources_loss": 0.7189317941665649,
976
+ "eval_validation_privacy_sources_runtime": 199.2824,
977
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
978
+ "eval_validation_privacy_sources_steps_per_second": 0.713,
979
+ "step": 22100
980
+ },
981
+ {
982
+ "epoch": 0.96,
983
+ "eval_validation_agenda_digitale_loss": 1.3224520683288574,
984
+ "eval_validation_agenda_digitale_runtime": 178.8592,
985
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
986
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
987
+ "step": 22100
988
+ },
989
+ {
990
+ "epoch": 0.96,
991
+ "eval_validation_leggepertutti_loss": 1.2184735536575317,
992
+ "eval_validation_leggepertutti_runtime": 33.1168,
993
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
994
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
995
+ "step": 22100
996
+ },
997
+ {
998
+ "epoch": 0.96,
999
+ "eval_validation_altalexprivacy_loss": 1.1038388013839722,
1000
+ "eval_validation_altalexprivacy_runtime": 55.6491,
1001
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
1002
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
1003
+ "step": 22100
1004
+ },
1005
+ {
1006
+ "epoch": 0.99,
1007
+ "learning_rate": 1e-05,
1008
+ "loss": 0.9834,
1009
+ "step": 22950
1010
+ },
1011
+ {
1012
+ "epoch": 0.99,
1013
+ "eval_validation_privacy_sources_loss": 0.7173371315002441,
1014
+ "eval_validation_privacy_sources_runtime": 199.3153,
1015
+ "eval_validation_privacy_sources_samples_per_second": 1.42,
1016
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
1017
+ "step": 22950
1018
+ },
1019
+ {
1020
+ "epoch": 0.99,
1021
+ "eval_validation_agenda_digitale_loss": 1.3209081888198853,
1022
+ "eval_validation_agenda_digitale_runtime": 178.8423,
1023
+ "eval_validation_agenda_digitale_samples_per_second": 1.42,
1024
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
1025
+ "step": 22950
1026
+ },
1027
+ {
1028
+ "epoch": 0.99,
1029
+ "eval_validation_leggepertutti_loss": 1.217122197151184,
1030
+ "eval_validation_leggepertutti_runtime": 33.1115,
1031
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
1032
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
1033
+ "step": 22950
1034
+ },
1035
+ {
1036
+ "epoch": 0.99,
1037
+ "eval_validation_altalexprivacy_loss": 1.1051535606384277,
1038
+ "eval_validation_altalexprivacy_runtime": 55.6446,
1039
+ "eval_validation_altalexprivacy_samples_per_second": 1.42,
1040
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
1041
+ "step": 22950
1042
+ },
1043
+ {
1044
+ "epoch": 1.03,
1045
+ "learning_rate": 1e-05,
1046
+ "loss": 0.8689,
1047
+ "step": 23800
1048
+ },
1049
+ {
1050
+ "epoch": 1.03,
1051
+ "eval_validation_privacy_sources_loss": 0.7219465970993042,
1052
+ "eval_validation_privacy_sources_runtime": 199.3892,
1053
+ "eval_validation_privacy_sources_samples_per_second": 1.419,
1054
+ "eval_validation_privacy_sources_steps_per_second": 0.712,
1055
+ "step": 23800
1056
+ },
1057
+ {
1058
+ "epoch": 1.03,
1059
+ "eval_validation_agenda_digitale_loss": 1.3297736644744873,
1060
+ "eval_validation_agenda_digitale_runtime": 178.9453,
1061
+ "eval_validation_agenda_digitale_samples_per_second": 1.419,
1062
+ "eval_validation_agenda_digitale_steps_per_second": 0.71,
1063
+ "step": 23800
1064
+ },
1065
+ {
1066
+ "epoch": 1.03,
1067
+ "eval_validation_leggepertutti_loss": 1.2270944118499756,
1068
+ "eval_validation_leggepertutti_runtime": 33.1299,
1069
+ "eval_validation_leggepertutti_samples_per_second": 1.419,
1070
+ "eval_validation_leggepertutti_steps_per_second": 0.724,
1071
+ "step": 23800
1072
+ },
1073
+ {
1074
+ "epoch": 1.03,
1075
+ "eval_validation_altalexprivacy_loss": 1.115221381187439,
1076
+ "eval_validation_altalexprivacy_runtime": 55.6611,
1077
+ "eval_validation_altalexprivacy_samples_per_second": 1.419,
1078
+ "eval_validation_altalexprivacy_steps_per_second": 0.719,
1079
+ "step": 23800
1080
+ }
1081
+ ],
1082
+ "logging_steps": 850,
1083
+ "max_steps": 46198,
1084
+ "num_input_tokens_seen": 0,
1085
+ "num_train_epochs": 2,
1086
+ "save_steps": 850,
1087
+ "total_flos": 1.663635065583698e+19,
1088
+ "train_batch_size": 1,
1089
+ "trial_name": null,
1090
+ "trial_params": null
1091
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461741ecc74f8396f46fe579020b7c6357cc25e96639e8ec788186f6b8108217
3
+ size 4856