andrealexroom commited on
Commit
d9145a6
1 Parent(s): f113ceb

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:f284264faf3927176961f58d44343f1c7b2cc8d9d1af5371a9f8a6384258a947
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:feab25d283844b70131cf2729a5e559770a943ed65531cf5f7233428a16c5f80
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:fbe9b0b83acf95ba95496936e908e7e2482ebc094cb8909564d5666bef60e066
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 sha256:6c1bc2ac11c5b55b9ca039dbf794e5c443e02671c6a93c8592f9716b8775a2ec
3
+ size 28967182538
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7b701852ef538560a66e4b791a7bb74d68d25ed60214d371859aadbff5dec8
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9937a551c39830a942afb1895eaf1c1b35069848c4c72c5b3f07f75125e8fb81
3
+ size 1000
trainer_state.json ADDED
@@ -0,0 +1,1129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9333794774182385,
5
+ "eval_steps": 93,
6
+ "global_step": 2697,
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": 1.466,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 1e-05,
20
+ "loss": 1.3439,
21
+ "step": 93
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "eval_validation_privacy_sources_loss": 0.9993858337402344,
26
+ "eval_validation_privacy_sources_runtime": 208.8742,
27
+ "eval_validation_privacy_sources_samples_per_second": 2.758,
28
+ "eval_validation_privacy_sources_steps_per_second": 1.379,
29
+ "step": 93
30
+ },
31
+ {
32
+ "epoch": 0.03,
33
+ "eval_validation_agenda_digitale_loss": 1.5262001752853394,
34
+ "eval_validation_agenda_digitale_runtime": 186.7009,
35
+ "eval_validation_agenda_digitale_samples_per_second": 2.753,
36
+ "eval_validation_agenda_digitale_steps_per_second": 1.377,
37
+ "step": 93
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "eval_validation_leggepertutti_loss": 1.393169641494751,
42
+ "eval_validation_leggepertutti_runtime": 36.5278,
43
+ "eval_validation_leggepertutti_samples_per_second": 2.765,
44
+ "eval_validation_leggepertutti_steps_per_second": 1.396,
45
+ "step": 93
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "eval_validation_altalexprivacy_loss": 1.3749068975448608,
50
+ "eval_validation_altalexprivacy_runtime": 59.1055,
51
+ "eval_validation_altalexprivacy_samples_per_second": 2.758,
52
+ "eval_validation_altalexprivacy_steps_per_second": 1.387,
53
+ "step": 93
54
+ },
55
+ {
56
+ "epoch": 0.06,
57
+ "learning_rate": 1e-05,
58
+ "loss": 1.2277,
59
+ "step": 186
60
+ },
61
+ {
62
+ "epoch": 0.06,
63
+ "eval_validation_privacy_sources_loss": 0.9398746490478516,
64
+ "eval_validation_privacy_sources_runtime": 207.7931,
65
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
66
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
67
+ "step": 186
68
+ },
69
+ {
70
+ "epoch": 0.06,
71
+ "eval_validation_agenda_digitale_loss": 1.4900918006896973,
72
+ "eval_validation_agenda_digitale_runtime": 185.4857,
73
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
74
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
75
+ "step": 186
76
+ },
77
+ {
78
+ "epoch": 0.06,
79
+ "eval_validation_leggepertutti_loss": 1.3686381578445435,
80
+ "eval_validation_leggepertutti_runtime": 36.4651,
81
+ "eval_validation_leggepertutti_samples_per_second": 2.77,
82
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
83
+ "step": 186
84
+ },
85
+ {
86
+ "epoch": 0.06,
87
+ "eval_validation_altalexprivacy_loss": 1.3352404832839966,
88
+ "eval_validation_altalexprivacy_runtime": 58.8108,
89
+ "eval_validation_altalexprivacy_samples_per_second": 2.772,
90
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
91
+ "step": 186
92
+ },
93
+ {
94
+ "epoch": 0.1,
95
+ "learning_rate": 1e-05,
96
+ "loss": 1.1989,
97
+ "step": 279
98
+ },
99
+ {
100
+ "epoch": 0.1,
101
+ "eval_validation_privacy_sources_loss": 0.9079627990722656,
102
+ "eval_validation_privacy_sources_runtime": 207.7801,
103
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
104
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
105
+ "step": 279
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "eval_validation_agenda_digitale_loss": 1.4663112163543701,
110
+ "eval_validation_agenda_digitale_runtime": 185.4551,
111
+ "eval_validation_agenda_digitale_samples_per_second": 2.772,
112
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
113
+ "step": 279
114
+ },
115
+ {
116
+ "epoch": 0.1,
117
+ "eval_validation_leggepertutti_loss": 1.3589648008346558,
118
+ "eval_validation_leggepertutti_runtime": 36.4528,
119
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
120
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
121
+ "step": 279
122
+ },
123
+ {
124
+ "epoch": 0.1,
125
+ "eval_validation_altalexprivacy_loss": 1.3104432821273804,
126
+ "eval_validation_altalexprivacy_runtime": 58.8143,
127
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
128
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
129
+ "step": 279
130
+ },
131
+ {
132
+ "epoch": 0.13,
133
+ "learning_rate": 1e-05,
134
+ "loss": 1.166,
135
+ "step": 372
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "eval_validation_privacy_sources_loss": 0.8864494562149048,
140
+ "eval_validation_privacy_sources_runtime": 207.7989,
141
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
142
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
143
+ "step": 372
144
+ },
145
+ {
146
+ "epoch": 0.13,
147
+ "eval_validation_agenda_digitale_loss": 1.4535290002822876,
148
+ "eval_validation_agenda_digitale_runtime": 185.4338,
149
+ "eval_validation_agenda_digitale_samples_per_second": 2.772,
150
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
151
+ "step": 372
152
+ },
153
+ {
154
+ "epoch": 0.13,
155
+ "eval_validation_leggepertutti_loss": 1.3470954895019531,
156
+ "eval_validation_leggepertutti_runtime": 36.4554,
157
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
158
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
159
+ "step": 372
160
+ },
161
+ {
162
+ "epoch": 0.13,
163
+ "eval_validation_altalexprivacy_loss": 1.2923557758331299,
164
+ "eval_validation_altalexprivacy_runtime": 58.8034,
165
+ "eval_validation_altalexprivacy_samples_per_second": 2.772,
166
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
167
+ "step": 372
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 1e-05,
172
+ "loss": 1.1502,
173
+ "step": 465
174
+ },
175
+ {
176
+ "epoch": 0.16,
177
+ "eval_validation_privacy_sources_loss": 0.8700113296508789,
178
+ "eval_validation_privacy_sources_runtime": 207.7896,
179
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
180
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
181
+ "step": 465
182
+ },
183
+ {
184
+ "epoch": 0.16,
185
+ "eval_validation_agenda_digitale_loss": 1.4420515298843384,
186
+ "eval_validation_agenda_digitale_runtime": 185.5107,
187
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
188
+ "eval_validation_agenda_digitale_steps_per_second": 1.385,
189
+ "step": 465
190
+ },
191
+ {
192
+ "epoch": 0.16,
193
+ "eval_validation_leggepertutti_loss": 1.3380672931671143,
194
+ "eval_validation_leggepertutti_runtime": 36.4532,
195
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
196
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
197
+ "step": 465
198
+ },
199
+ {
200
+ "epoch": 0.16,
201
+ "eval_validation_altalexprivacy_loss": 1.2828154563903809,
202
+ "eval_validation_altalexprivacy_runtime": 58.7825,
203
+ "eval_validation_altalexprivacy_samples_per_second": 2.773,
204
+ "eval_validation_altalexprivacy_steps_per_second": 1.395,
205
+ "step": 465
206
+ },
207
+ {
208
+ "epoch": 0.19,
209
+ "learning_rate": 1e-05,
210
+ "loss": 1.1293,
211
+ "step": 558
212
+ },
213
+ {
214
+ "epoch": 0.19,
215
+ "eval_validation_privacy_sources_loss": 0.8583760857582092,
216
+ "eval_validation_privacy_sources_runtime": 207.7778,
217
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
218
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
219
+ "step": 558
220
+ },
221
+ {
222
+ "epoch": 0.19,
223
+ "eval_validation_agenda_digitale_loss": 1.4329832792282104,
224
+ "eval_validation_agenda_digitale_runtime": 185.4109,
225
+ "eval_validation_agenda_digitale_samples_per_second": 2.772,
226
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
227
+ "step": 558
228
+ },
229
+ {
230
+ "epoch": 0.19,
231
+ "eval_validation_leggepertutti_loss": 1.332190752029419,
232
+ "eval_validation_leggepertutti_runtime": 36.4466,
233
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
234
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
235
+ "step": 558
236
+ },
237
+ {
238
+ "epoch": 0.19,
239
+ "eval_validation_altalexprivacy_loss": 1.2727842330932617,
240
+ "eval_validation_altalexprivacy_runtime": 58.812,
241
+ "eval_validation_altalexprivacy_samples_per_second": 2.772,
242
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
243
+ "step": 558
244
+ },
245
+ {
246
+ "epoch": 0.23,
247
+ "learning_rate": 1e-05,
248
+ "loss": 1.1214,
249
+ "step": 651
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "eval_validation_privacy_sources_loss": 0.8476831912994385,
254
+ "eval_validation_privacy_sources_runtime": 207.83,
255
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
256
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
257
+ "step": 651
258
+ },
259
+ {
260
+ "epoch": 0.23,
261
+ "eval_validation_agenda_digitale_loss": 1.4262702465057373,
262
+ "eval_validation_agenda_digitale_runtime": 185.4527,
263
+ "eval_validation_agenda_digitale_samples_per_second": 2.772,
264
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
265
+ "step": 651
266
+ },
267
+ {
268
+ "epoch": 0.23,
269
+ "eval_validation_leggepertutti_loss": 1.3270900249481201,
270
+ "eval_validation_leggepertutti_runtime": 36.4393,
271
+ "eval_validation_leggepertutti_samples_per_second": 2.772,
272
+ "eval_validation_leggepertutti_steps_per_second": 1.4,
273
+ "step": 651
274
+ },
275
+ {
276
+ "epoch": 0.23,
277
+ "eval_validation_altalexprivacy_loss": 1.260352611541748,
278
+ "eval_validation_altalexprivacy_runtime": 58.8334,
279
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
280
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
281
+ "step": 651
282
+ },
283
+ {
284
+ "epoch": 0.26,
285
+ "learning_rate": 1e-05,
286
+ "loss": 1.1091,
287
+ "step": 744
288
+ },
289
+ {
290
+ "epoch": 0.26,
291
+ "eval_validation_privacy_sources_loss": 0.8393220901489258,
292
+ "eval_validation_privacy_sources_runtime": 207.8694,
293
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
294
+ "eval_validation_privacy_sources_steps_per_second": 1.385,
295
+ "step": 744
296
+ },
297
+ {
298
+ "epoch": 0.26,
299
+ "eval_validation_agenda_digitale_loss": 1.419695258140564,
300
+ "eval_validation_agenda_digitale_runtime": 185.5111,
301
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
302
+ "eval_validation_agenda_digitale_steps_per_second": 1.385,
303
+ "step": 744
304
+ },
305
+ {
306
+ "epoch": 0.26,
307
+ "eval_validation_leggepertutti_loss": 1.3253276348114014,
308
+ "eval_validation_leggepertutti_runtime": 36.4703,
309
+ "eval_validation_leggepertutti_samples_per_second": 2.769,
310
+ "eval_validation_leggepertutti_steps_per_second": 1.398,
311
+ "step": 744
312
+ },
313
+ {
314
+ "epoch": 0.26,
315
+ "eval_validation_altalexprivacy_loss": 1.2589938640594482,
316
+ "eval_validation_altalexprivacy_runtime": 58.8276,
317
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
318
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
319
+ "step": 744
320
+ },
321
+ {
322
+ "epoch": 0.29,
323
+ "learning_rate": 1e-05,
324
+ "loss": 1.1054,
325
+ "step": 837
326
+ },
327
+ {
328
+ "epoch": 0.29,
329
+ "eval_validation_privacy_sources_loss": 0.8303313851356506,
330
+ "eval_validation_privacy_sources_runtime": 207.8766,
331
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
332
+ "eval_validation_privacy_sources_steps_per_second": 1.385,
333
+ "step": 837
334
+ },
335
+ {
336
+ "epoch": 0.29,
337
+ "eval_validation_agenda_digitale_loss": 1.4135520458221436,
338
+ "eval_validation_agenda_digitale_runtime": 185.5466,
339
+ "eval_validation_agenda_digitale_samples_per_second": 2.77,
340
+ "eval_validation_agenda_digitale_steps_per_second": 1.385,
341
+ "step": 837
342
+ },
343
+ {
344
+ "epoch": 0.29,
345
+ "eval_validation_leggepertutti_loss": 1.3197592496871948,
346
+ "eval_validation_leggepertutti_runtime": 36.4762,
347
+ "eval_validation_leggepertutti_samples_per_second": 2.769,
348
+ "eval_validation_leggepertutti_steps_per_second": 1.398,
349
+ "step": 837
350
+ },
351
+ {
352
+ "epoch": 0.29,
353
+ "eval_validation_altalexprivacy_loss": 1.248721957206726,
354
+ "eval_validation_altalexprivacy_runtime": 58.845,
355
+ "eval_validation_altalexprivacy_samples_per_second": 2.77,
356
+ "eval_validation_altalexprivacy_steps_per_second": 1.393,
357
+ "step": 837
358
+ },
359
+ {
360
+ "epoch": 0.32,
361
+ "learning_rate": 1e-05,
362
+ "loss": 1.0981,
363
+ "step": 930
364
+ },
365
+ {
366
+ "epoch": 0.32,
367
+ "eval_validation_privacy_sources_loss": 0.8243758678436279,
368
+ "eval_validation_privacy_sources_runtime": 207.9136,
369
+ "eval_validation_privacy_sources_samples_per_second": 2.77,
370
+ "eval_validation_privacy_sources_steps_per_second": 1.385,
371
+ "step": 930
372
+ },
373
+ {
374
+ "epoch": 0.32,
375
+ "eval_validation_agenda_digitale_loss": 1.4070162773132324,
376
+ "eval_validation_agenda_digitale_runtime": 185.5276,
377
+ "eval_validation_agenda_digitale_samples_per_second": 2.77,
378
+ "eval_validation_agenda_digitale_steps_per_second": 1.385,
379
+ "step": 930
380
+ },
381
+ {
382
+ "epoch": 0.32,
383
+ "eval_validation_leggepertutti_loss": 1.3205946683883667,
384
+ "eval_validation_leggepertutti_runtime": 36.4768,
385
+ "eval_validation_leggepertutti_samples_per_second": 2.769,
386
+ "eval_validation_leggepertutti_steps_per_second": 1.398,
387
+ "step": 930
388
+ },
389
+ {
390
+ "epoch": 0.32,
391
+ "eval_validation_altalexprivacy_loss": 1.236555576324463,
392
+ "eval_validation_altalexprivacy_runtime": 58.8174,
393
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
394
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
395
+ "step": 930
396
+ },
397
+ {
398
+ "epoch": 0.35,
399
+ "learning_rate": 1e-05,
400
+ "loss": 1.0826,
401
+ "step": 1023
402
+ },
403
+ {
404
+ "epoch": 0.35,
405
+ "eval_validation_privacy_sources_loss": 0.8142690062522888,
406
+ "eval_validation_privacy_sources_runtime": 207.8182,
407
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
408
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
409
+ "step": 1023
410
+ },
411
+ {
412
+ "epoch": 0.35,
413
+ "eval_validation_agenda_digitale_loss": 1.4016144275665283,
414
+ "eval_validation_agenda_digitale_runtime": 185.5524,
415
+ "eval_validation_agenda_digitale_samples_per_second": 2.77,
416
+ "eval_validation_agenda_digitale_steps_per_second": 1.385,
417
+ "step": 1023
418
+ },
419
+ {
420
+ "epoch": 0.35,
421
+ "eval_validation_leggepertutti_loss": 1.314708948135376,
422
+ "eval_validation_leggepertutti_runtime": 36.4554,
423
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
424
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
425
+ "step": 1023
426
+ },
427
+ {
428
+ "epoch": 0.35,
429
+ "eval_validation_altalexprivacy_loss": 1.230077862739563,
430
+ "eval_validation_altalexprivacy_runtime": 58.8338,
431
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
432
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
433
+ "step": 1023
434
+ },
435
+ {
436
+ "epoch": 0.39,
437
+ "learning_rate": 1e-05,
438
+ "loss": 1.0854,
439
+ "step": 1116
440
+ },
441
+ {
442
+ "epoch": 0.39,
443
+ "eval_validation_privacy_sources_loss": 0.8100457787513733,
444
+ "eval_validation_privacy_sources_runtime": 207.7761,
445
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
446
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
447
+ "step": 1116
448
+ },
449
+ {
450
+ "epoch": 0.39,
451
+ "eval_validation_agenda_digitale_loss": 1.3958582878112793,
452
+ "eval_validation_agenda_digitale_runtime": 185.4776,
453
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
454
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
455
+ "step": 1116
456
+ },
457
+ {
458
+ "epoch": 0.39,
459
+ "eval_validation_leggepertutti_loss": 1.3077082633972168,
460
+ "eval_validation_leggepertutti_runtime": 36.4414,
461
+ "eval_validation_leggepertutti_samples_per_second": 2.772,
462
+ "eval_validation_leggepertutti_steps_per_second": 1.4,
463
+ "step": 1116
464
+ },
465
+ {
466
+ "epoch": 0.39,
467
+ "eval_validation_altalexprivacy_loss": 1.221291422843933,
468
+ "eval_validation_altalexprivacy_runtime": 58.8442,
469
+ "eval_validation_altalexprivacy_samples_per_second": 2.77,
470
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
471
+ "step": 1116
472
+ },
473
+ {
474
+ "epoch": 0.42,
475
+ "learning_rate": 1e-05,
476
+ "loss": 1.0771,
477
+ "step": 1209
478
+ },
479
+ {
480
+ "epoch": 0.42,
481
+ "eval_validation_privacy_sources_loss": 0.8034979701042175,
482
+ "eval_validation_privacy_sources_runtime": 207.8146,
483
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
484
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
485
+ "step": 1209
486
+ },
487
+ {
488
+ "epoch": 0.42,
489
+ "eval_validation_agenda_digitale_loss": 1.3933522701263428,
490
+ "eval_validation_agenda_digitale_runtime": 185.4596,
491
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
492
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
493
+ "step": 1209
494
+ },
495
+ {
496
+ "epoch": 0.42,
497
+ "eval_validation_leggepertutti_loss": 1.3102238178253174,
498
+ "eval_validation_leggepertutti_runtime": 36.4505,
499
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
500
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
501
+ "step": 1209
502
+ },
503
+ {
504
+ "epoch": 0.42,
505
+ "eval_validation_altalexprivacy_loss": 1.2192506790161133,
506
+ "eval_validation_altalexprivacy_runtime": 58.8165,
507
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
508
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
509
+ "step": 1209
510
+ },
511
+ {
512
+ "epoch": 0.45,
513
+ "learning_rate": 1e-05,
514
+ "loss": 1.0637,
515
+ "step": 1302
516
+ },
517
+ {
518
+ "epoch": 0.45,
519
+ "eval_validation_privacy_sources_loss": 0.7970249056816101,
520
+ "eval_validation_privacy_sources_runtime": 207.8381,
521
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
522
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
523
+ "step": 1302
524
+ },
525
+ {
526
+ "epoch": 0.45,
527
+ "eval_validation_agenda_digitale_loss": 1.3897120952606201,
528
+ "eval_validation_agenda_digitale_runtime": 185.475,
529
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
530
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
531
+ "step": 1302
532
+ },
533
+ {
534
+ "epoch": 0.45,
535
+ "eval_validation_leggepertutti_loss": 1.303721308708191,
536
+ "eval_validation_leggepertutti_runtime": 36.4613,
537
+ "eval_validation_leggepertutti_samples_per_second": 2.77,
538
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
539
+ "step": 1302
540
+ },
541
+ {
542
+ "epoch": 0.45,
543
+ "eval_validation_altalexprivacy_loss": 1.2124699354171753,
544
+ "eval_validation_altalexprivacy_runtime": 58.8366,
545
+ "eval_validation_altalexprivacy_samples_per_second": 2.77,
546
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
547
+ "step": 1302
548
+ },
549
+ {
550
+ "epoch": 0.48,
551
+ "learning_rate": 1e-05,
552
+ "loss": 1.0566,
553
+ "step": 1395
554
+ },
555
+ {
556
+ "epoch": 0.48,
557
+ "eval_validation_privacy_sources_loss": 0.7921364307403564,
558
+ "eval_validation_privacy_sources_runtime": 207.8584,
559
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
560
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
561
+ "step": 1395
562
+ },
563
+ {
564
+ "epoch": 0.48,
565
+ "eval_validation_agenda_digitale_loss": 1.3843779563903809,
566
+ "eval_validation_agenda_digitale_runtime": 185.4492,
567
+ "eval_validation_agenda_digitale_samples_per_second": 2.772,
568
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
569
+ "step": 1395
570
+ },
571
+ {
572
+ "epoch": 0.48,
573
+ "eval_validation_leggepertutti_loss": 1.3031646013259888,
574
+ "eval_validation_leggepertutti_runtime": 36.4511,
575
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
576
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
577
+ "step": 1395
578
+ },
579
+ {
580
+ "epoch": 0.48,
581
+ "eval_validation_altalexprivacy_loss": 1.2079439163208008,
582
+ "eval_validation_altalexprivacy_runtime": 58.8443,
583
+ "eval_validation_altalexprivacy_samples_per_second": 2.77,
584
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
585
+ "step": 1395
586
+ },
587
+ {
588
+ "epoch": 0.51,
589
+ "learning_rate": 1e-05,
590
+ "loss": 1.0553,
591
+ "step": 1488
592
+ },
593
+ {
594
+ "epoch": 0.51,
595
+ "eval_validation_privacy_sources_loss": 0.7880584001541138,
596
+ "eval_validation_privacy_sources_runtime": 207.9058,
597
+ "eval_validation_privacy_sources_samples_per_second": 2.77,
598
+ "eval_validation_privacy_sources_steps_per_second": 1.385,
599
+ "step": 1488
600
+ },
601
+ {
602
+ "epoch": 0.51,
603
+ "eval_validation_agenda_digitale_loss": 1.3801347017288208,
604
+ "eval_validation_agenda_digitale_runtime": 185.4606,
605
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
606
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
607
+ "step": 1488
608
+ },
609
+ {
610
+ "epoch": 0.51,
611
+ "eval_validation_leggepertutti_loss": 1.304322361946106,
612
+ "eval_validation_leggepertutti_runtime": 36.4655,
613
+ "eval_validation_leggepertutti_samples_per_second": 2.77,
614
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
615
+ "step": 1488
616
+ },
617
+ {
618
+ "epoch": 0.51,
619
+ "eval_validation_altalexprivacy_loss": 1.200743556022644,
620
+ "eval_validation_altalexprivacy_runtime": 58.8181,
621
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
622
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
623
+ "step": 1488
624
+ },
625
+ {
626
+ "epoch": 0.55,
627
+ "learning_rate": 1e-05,
628
+ "loss": 1.0464,
629
+ "step": 1581
630
+ },
631
+ {
632
+ "epoch": 0.55,
633
+ "eval_validation_privacy_sources_loss": 0.7845947742462158,
634
+ "eval_validation_privacy_sources_runtime": 207.7953,
635
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
636
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
637
+ "step": 1581
638
+ },
639
+ {
640
+ "epoch": 0.55,
641
+ "eval_validation_agenda_digitale_loss": 1.3774136304855347,
642
+ "eval_validation_agenda_digitale_runtime": 185.4238,
643
+ "eval_validation_agenda_digitale_samples_per_second": 2.772,
644
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
645
+ "step": 1581
646
+ },
647
+ {
648
+ "epoch": 0.55,
649
+ "eval_validation_leggepertutti_loss": 1.2997848987579346,
650
+ "eval_validation_leggepertutti_runtime": 36.4545,
651
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
652
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
653
+ "step": 1581
654
+ },
655
+ {
656
+ "epoch": 0.55,
657
+ "eval_validation_altalexprivacy_loss": 1.196614146232605,
658
+ "eval_validation_altalexprivacy_runtime": 58.7946,
659
+ "eval_validation_altalexprivacy_samples_per_second": 2.772,
660
+ "eval_validation_altalexprivacy_steps_per_second": 1.395,
661
+ "step": 1581
662
+ },
663
+ {
664
+ "epoch": 0.58,
665
+ "learning_rate": 1e-05,
666
+ "loss": 1.0387,
667
+ "step": 1674
668
+ },
669
+ {
670
+ "epoch": 0.58,
671
+ "eval_validation_privacy_sources_loss": 0.7808618545532227,
672
+ "eval_validation_privacy_sources_runtime": 207.8015,
673
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
674
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
675
+ "step": 1674
676
+ },
677
+ {
678
+ "epoch": 0.58,
679
+ "eval_validation_agenda_digitale_loss": 1.375112533569336,
680
+ "eval_validation_agenda_digitale_runtime": 185.4231,
681
+ "eval_validation_agenda_digitale_samples_per_second": 2.772,
682
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
683
+ "step": 1674
684
+ },
685
+ {
686
+ "epoch": 0.58,
687
+ "eval_validation_leggepertutti_loss": 1.3011507987976074,
688
+ "eval_validation_leggepertutti_runtime": 36.4454,
689
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
690
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
691
+ "step": 1674
692
+ },
693
+ {
694
+ "epoch": 0.58,
695
+ "eval_validation_altalexprivacy_loss": 1.190794825553894,
696
+ "eval_validation_altalexprivacy_runtime": 58.8028,
697
+ "eval_validation_altalexprivacy_samples_per_second": 2.772,
698
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
699
+ "step": 1674
700
+ },
701
+ {
702
+ "epoch": 0.61,
703
+ "learning_rate": 1e-05,
704
+ "loss": 1.0318,
705
+ "step": 1767
706
+ },
707
+ {
708
+ "epoch": 0.61,
709
+ "eval_validation_privacy_sources_loss": 0.7766129970550537,
710
+ "eval_validation_privacy_sources_runtime": 207.7465,
711
+ "eval_validation_privacy_sources_samples_per_second": 2.773,
712
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
713
+ "step": 1767
714
+ },
715
+ {
716
+ "epoch": 0.61,
717
+ "eval_validation_agenda_digitale_loss": 1.372268795967102,
718
+ "eval_validation_agenda_digitale_runtime": 185.4359,
719
+ "eval_validation_agenda_digitale_samples_per_second": 2.772,
720
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
721
+ "step": 1767
722
+ },
723
+ {
724
+ "epoch": 0.61,
725
+ "eval_validation_leggepertutti_loss": 1.2967208623886108,
726
+ "eval_validation_leggepertutti_runtime": 36.4479,
727
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
728
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
729
+ "step": 1767
730
+ },
731
+ {
732
+ "epoch": 0.61,
733
+ "eval_validation_altalexprivacy_loss": 1.1859400272369385,
734
+ "eval_validation_altalexprivacy_runtime": 58.8168,
735
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
736
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
737
+ "step": 1767
738
+ },
739
+ {
740
+ "epoch": 0.64,
741
+ "learning_rate": 1e-05,
742
+ "loss": 1.0549,
743
+ "step": 1860
744
+ },
745
+ {
746
+ "epoch": 0.64,
747
+ "eval_validation_privacy_sources_loss": 0.7737349271774292,
748
+ "eval_validation_privacy_sources_runtime": 207.757,
749
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
750
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
751
+ "step": 1860
752
+ },
753
+ {
754
+ "epoch": 0.64,
755
+ "eval_validation_agenda_digitale_loss": 1.3696516752243042,
756
+ "eval_validation_agenda_digitale_runtime": 185.376,
757
+ "eval_validation_agenda_digitale_samples_per_second": 2.773,
758
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
759
+ "step": 1860
760
+ },
761
+ {
762
+ "epoch": 0.64,
763
+ "eval_validation_leggepertutti_loss": 1.2951971292495728,
764
+ "eval_validation_leggepertutti_runtime": 36.4425,
765
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
766
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
767
+ "step": 1860
768
+ },
769
+ {
770
+ "epoch": 0.64,
771
+ "eval_validation_altalexprivacy_loss": 1.180280089378357,
772
+ "eval_validation_altalexprivacy_runtime": 58.807,
773
+ "eval_validation_altalexprivacy_samples_per_second": 2.772,
774
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
775
+ "step": 1860
776
+ },
777
+ {
778
+ "epoch": 0.68,
779
+ "learning_rate": 1e-05,
780
+ "loss": 1.0244,
781
+ "step": 1953
782
+ },
783
+ {
784
+ "epoch": 0.68,
785
+ "eval_validation_privacy_sources_loss": 0.7704524993896484,
786
+ "eval_validation_privacy_sources_runtime": 207.8153,
787
+ "eval_validation_privacy_sources_samples_per_second": 2.772,
788
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
789
+ "step": 1953
790
+ },
791
+ {
792
+ "epoch": 0.68,
793
+ "eval_validation_agenda_digitale_loss": 1.3666201829910278,
794
+ "eval_validation_agenda_digitale_runtime": 185.3706,
795
+ "eval_validation_agenda_digitale_samples_per_second": 2.773,
796
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
797
+ "step": 1953
798
+ },
799
+ {
800
+ "epoch": 0.68,
801
+ "eval_validation_leggepertutti_loss": 1.2933101654052734,
802
+ "eval_validation_leggepertutti_runtime": 36.4405,
803
+ "eval_validation_leggepertutti_samples_per_second": 2.772,
804
+ "eval_validation_leggepertutti_steps_per_second": 1.4,
805
+ "step": 1953
806
+ },
807
+ {
808
+ "epoch": 0.68,
809
+ "eval_validation_altalexprivacy_loss": 1.1771676540374756,
810
+ "eval_validation_altalexprivacy_runtime": 58.8195,
811
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
812
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
813
+ "step": 1953
814
+ },
815
+ {
816
+ "epoch": 0.71,
817
+ "learning_rate": 1e-05,
818
+ "loss": 1.0244,
819
+ "step": 2046
820
+ },
821
+ {
822
+ "epoch": 0.71,
823
+ "eval_validation_privacy_sources_loss": 0.7678720951080322,
824
+ "eval_validation_privacy_sources_runtime": 207.6339,
825
+ "eval_validation_privacy_sources_samples_per_second": 2.774,
826
+ "eval_validation_privacy_sources_steps_per_second": 1.387,
827
+ "step": 2046
828
+ },
829
+ {
830
+ "epoch": 0.71,
831
+ "eval_validation_agenda_digitale_loss": 1.3635469675064087,
832
+ "eval_validation_agenda_digitale_runtime": 185.2599,
833
+ "eval_validation_agenda_digitale_samples_per_second": 2.774,
834
+ "eval_validation_agenda_digitale_steps_per_second": 1.387,
835
+ "step": 2046
836
+ },
837
+ {
838
+ "epoch": 0.71,
839
+ "eval_validation_leggepertutti_loss": 1.2988970279693604,
840
+ "eval_validation_leggepertutti_runtime": 36.3946,
841
+ "eval_validation_leggepertutti_samples_per_second": 2.775,
842
+ "eval_validation_leggepertutti_steps_per_second": 1.401,
843
+ "step": 2046
844
+ },
845
+ {
846
+ "epoch": 0.71,
847
+ "eval_validation_altalexprivacy_loss": 1.1761205196380615,
848
+ "eval_validation_altalexprivacy_runtime": 58.7639,
849
+ "eval_validation_altalexprivacy_samples_per_second": 2.774,
850
+ "eval_validation_altalexprivacy_steps_per_second": 1.395,
851
+ "step": 2046
852
+ },
853
+ {
854
+ "epoch": 0.74,
855
+ "learning_rate": 1e-05,
856
+ "loss": 1.0203,
857
+ "step": 2139
858
+ },
859
+ {
860
+ "epoch": 0.74,
861
+ "eval_validation_privacy_sources_loss": 0.7644345164299011,
862
+ "eval_validation_privacy_sources_runtime": 207.6697,
863
+ "eval_validation_privacy_sources_samples_per_second": 2.774,
864
+ "eval_validation_privacy_sources_steps_per_second": 1.387,
865
+ "step": 2139
866
+ },
867
+ {
868
+ "epoch": 0.74,
869
+ "eval_validation_agenda_digitale_loss": 1.3618555068969727,
870
+ "eval_validation_agenda_digitale_runtime": 185.3011,
871
+ "eval_validation_agenda_digitale_samples_per_second": 2.774,
872
+ "eval_validation_agenda_digitale_steps_per_second": 1.387,
873
+ "step": 2139
874
+ },
875
+ {
876
+ "epoch": 0.74,
877
+ "eval_validation_leggepertutti_loss": 1.2900038957595825,
878
+ "eval_validation_leggepertutti_runtime": 36.4155,
879
+ "eval_validation_leggepertutti_samples_per_second": 2.774,
880
+ "eval_validation_leggepertutti_steps_per_second": 1.401,
881
+ "step": 2139
882
+ },
883
+ {
884
+ "epoch": 0.74,
885
+ "eval_validation_altalexprivacy_loss": 1.170756220817566,
886
+ "eval_validation_altalexprivacy_runtime": 58.7521,
887
+ "eval_validation_altalexprivacy_samples_per_second": 2.774,
888
+ "eval_validation_altalexprivacy_steps_per_second": 1.396,
889
+ "step": 2139
890
+ },
891
+ {
892
+ "epoch": 0.77,
893
+ "learning_rate": 1e-05,
894
+ "loss": 1.0256,
895
+ "step": 2232
896
+ },
897
+ {
898
+ "epoch": 0.77,
899
+ "eval_validation_privacy_sources_loss": 0.7612179517745972,
900
+ "eval_validation_privacy_sources_runtime": 207.7191,
901
+ "eval_validation_privacy_sources_samples_per_second": 2.773,
902
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
903
+ "step": 2232
904
+ },
905
+ {
906
+ "epoch": 0.77,
907
+ "eval_validation_agenda_digitale_loss": 1.3602862358093262,
908
+ "eval_validation_agenda_digitale_runtime": 185.3214,
909
+ "eval_validation_agenda_digitale_samples_per_second": 2.774,
910
+ "eval_validation_agenda_digitale_steps_per_second": 1.387,
911
+ "step": 2232
912
+ },
913
+ {
914
+ "epoch": 0.77,
915
+ "eval_validation_leggepertutti_loss": 1.288977861404419,
916
+ "eval_validation_leggepertutti_runtime": 36.4223,
917
+ "eval_validation_leggepertutti_samples_per_second": 2.773,
918
+ "eval_validation_leggepertutti_steps_per_second": 1.4,
919
+ "step": 2232
920
+ },
921
+ {
922
+ "epoch": 0.77,
923
+ "eval_validation_altalexprivacy_loss": 1.1712496280670166,
924
+ "eval_validation_altalexprivacy_runtime": 58.7757,
925
+ "eval_validation_altalexprivacy_samples_per_second": 2.773,
926
+ "eval_validation_altalexprivacy_steps_per_second": 1.395,
927
+ "step": 2232
928
+ },
929
+ {
930
+ "epoch": 0.8,
931
+ "learning_rate": 1e-05,
932
+ "loss": 1.011,
933
+ "step": 2325
934
+ },
935
+ {
936
+ "epoch": 0.8,
937
+ "eval_validation_privacy_sources_loss": 0.7570701241493225,
938
+ "eval_validation_privacy_sources_runtime": 207.9647,
939
+ "eval_validation_privacy_sources_samples_per_second": 2.77,
940
+ "eval_validation_privacy_sources_steps_per_second": 1.385,
941
+ "step": 2325
942
+ },
943
+ {
944
+ "epoch": 0.8,
945
+ "eval_validation_agenda_digitale_loss": 1.3573753833770752,
946
+ "eval_validation_agenda_digitale_runtime": 185.4907,
947
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
948
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
949
+ "step": 2325
950
+ },
951
+ {
952
+ "epoch": 0.8,
953
+ "eval_validation_leggepertutti_loss": 1.2890092134475708,
954
+ "eval_validation_leggepertutti_runtime": 36.4584,
955
+ "eval_validation_leggepertutti_samples_per_second": 2.77,
956
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
957
+ "step": 2325
958
+ },
959
+ {
960
+ "epoch": 0.8,
961
+ "eval_validation_altalexprivacy_loss": 1.1662389039993286,
962
+ "eval_validation_altalexprivacy_runtime": 58.8138,
963
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
964
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
965
+ "step": 2325
966
+ },
967
+ {
968
+ "epoch": 0.84,
969
+ "learning_rate": 1e-05,
970
+ "loss": 1.0016,
971
+ "step": 2418
972
+ },
973
+ {
974
+ "epoch": 0.84,
975
+ "eval_validation_privacy_sources_loss": 0.7539491653442383,
976
+ "eval_validation_privacy_sources_runtime": 207.8953,
977
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
978
+ "eval_validation_privacy_sources_steps_per_second": 1.385,
979
+ "step": 2418
980
+ },
981
+ {
982
+ "epoch": 0.84,
983
+ "eval_validation_agenda_digitale_loss": 1.3551262617111206,
984
+ "eval_validation_agenda_digitale_runtime": 185.5266,
985
+ "eval_validation_agenda_digitale_samples_per_second": 2.77,
986
+ "eval_validation_agenda_digitale_steps_per_second": 1.385,
987
+ "step": 2418
988
+ },
989
+ {
990
+ "epoch": 0.84,
991
+ "eval_validation_leggepertutti_loss": 1.287420630455017,
992
+ "eval_validation_leggepertutti_runtime": 36.4572,
993
+ "eval_validation_leggepertutti_samples_per_second": 2.77,
994
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
995
+ "step": 2418
996
+ },
997
+ {
998
+ "epoch": 0.84,
999
+ "eval_validation_altalexprivacy_loss": 1.1637060642242432,
1000
+ "eval_validation_altalexprivacy_runtime": 58.8299,
1001
+ "eval_validation_altalexprivacy_samples_per_second": 2.771,
1002
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
1003
+ "step": 2418
1004
+ },
1005
+ {
1006
+ "epoch": 0.87,
1007
+ "learning_rate": 1e-05,
1008
+ "loss": 1.0106,
1009
+ "step": 2511
1010
+ },
1011
+ {
1012
+ "epoch": 0.87,
1013
+ "eval_validation_privacy_sources_loss": 0.7510882616043091,
1014
+ "eval_validation_privacy_sources_runtime": 207.8929,
1015
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
1016
+ "eval_validation_privacy_sources_steps_per_second": 1.385,
1017
+ "step": 2511
1018
+ },
1019
+ {
1020
+ "epoch": 0.87,
1021
+ "eval_validation_agenda_digitale_loss": 1.3524880409240723,
1022
+ "eval_validation_agenda_digitale_runtime": 185.5648,
1023
+ "eval_validation_agenda_digitale_samples_per_second": 2.77,
1024
+ "eval_validation_agenda_digitale_steps_per_second": 1.385,
1025
+ "step": 2511
1026
+ },
1027
+ {
1028
+ "epoch": 0.87,
1029
+ "eval_validation_leggepertutti_loss": 1.2826858758926392,
1030
+ "eval_validation_leggepertutti_runtime": 36.4693,
1031
+ "eval_validation_leggepertutti_samples_per_second": 2.769,
1032
+ "eval_validation_leggepertutti_steps_per_second": 1.398,
1033
+ "step": 2511
1034
+ },
1035
+ {
1036
+ "epoch": 0.87,
1037
+ "eval_validation_altalexprivacy_loss": 1.1573538780212402,
1038
+ "eval_validation_altalexprivacy_runtime": 58.8452,
1039
+ "eval_validation_altalexprivacy_samples_per_second": 2.77,
1040
+ "eval_validation_altalexprivacy_steps_per_second": 1.393,
1041
+ "step": 2511
1042
+ },
1043
+ {
1044
+ "epoch": 0.9,
1045
+ "learning_rate": 1e-05,
1046
+ "loss": 1.0075,
1047
+ "step": 2604
1048
+ },
1049
+ {
1050
+ "epoch": 0.9,
1051
+ "eval_validation_privacy_sources_loss": 0.74814373254776,
1052
+ "eval_validation_privacy_sources_runtime": 207.9033,
1053
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
1054
+ "eval_validation_privacy_sources_steps_per_second": 1.385,
1055
+ "step": 2604
1056
+ },
1057
+ {
1058
+ "epoch": 0.9,
1059
+ "eval_validation_agenda_digitale_loss": 1.3509397506713867,
1060
+ "eval_validation_agenda_digitale_runtime": 185.5149,
1061
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
1062
+ "eval_validation_agenda_digitale_steps_per_second": 1.385,
1063
+ "step": 2604
1064
+ },
1065
+ {
1066
+ "epoch": 0.9,
1067
+ "eval_validation_leggepertutti_loss": 1.2835361957550049,
1068
+ "eval_validation_leggepertutti_runtime": 36.4782,
1069
+ "eval_validation_leggepertutti_samples_per_second": 2.769,
1070
+ "eval_validation_leggepertutti_steps_per_second": 1.398,
1071
+ "step": 2604
1072
+ },
1073
+ {
1074
+ "epoch": 0.9,
1075
+ "eval_validation_altalexprivacy_loss": 1.1581933498382568,
1076
+ "eval_validation_altalexprivacy_runtime": 58.808,
1077
+ "eval_validation_altalexprivacy_samples_per_second": 2.772,
1078
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
1079
+ "step": 2604
1080
+ },
1081
+ {
1082
+ "epoch": 0.93,
1083
+ "learning_rate": 1e-05,
1084
+ "loss": 0.9994,
1085
+ "step": 2697
1086
+ },
1087
+ {
1088
+ "epoch": 0.93,
1089
+ "eval_validation_privacy_sources_loss": 0.7448787689208984,
1090
+ "eval_validation_privacy_sources_runtime": 207.8624,
1091
+ "eval_validation_privacy_sources_samples_per_second": 2.771,
1092
+ "eval_validation_privacy_sources_steps_per_second": 1.386,
1093
+ "step": 2697
1094
+ },
1095
+ {
1096
+ "epoch": 0.93,
1097
+ "eval_validation_agenda_digitale_loss": 1.3478621244430542,
1098
+ "eval_validation_agenda_digitale_runtime": 185.4737,
1099
+ "eval_validation_agenda_digitale_samples_per_second": 2.771,
1100
+ "eval_validation_agenda_digitale_steps_per_second": 1.386,
1101
+ "step": 2697
1102
+ },
1103
+ {
1104
+ "epoch": 0.93,
1105
+ "eval_validation_leggepertutti_loss": 1.2804486751556396,
1106
+ "eval_validation_leggepertutti_runtime": 36.4501,
1107
+ "eval_validation_leggepertutti_samples_per_second": 2.771,
1108
+ "eval_validation_leggepertutti_steps_per_second": 1.399,
1109
+ "step": 2697
1110
+ },
1111
+ {
1112
+ "epoch": 0.93,
1113
+ "eval_validation_altalexprivacy_loss": 1.1511160135269165,
1114
+ "eval_validation_altalexprivacy_runtime": 58.8365,
1115
+ "eval_validation_altalexprivacy_samples_per_second": 2.77,
1116
+ "eval_validation_altalexprivacy_steps_per_second": 1.394,
1117
+ "step": 2697
1118
+ }
1119
+ ],
1120
+ "logging_steps": 93,
1121
+ "max_steps": 5778,
1122
+ "num_input_tokens_seen": 0,
1123
+ "num_train_epochs": 2,
1124
+ "save_steps": 93,
1125
+ "total_flos": 1.5081760577745322e+19,
1126
+ "train_batch_size": 1,
1127
+ "trial_name": null,
1128
+ "trial_params": null
1129
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381b0ccb279ba45e147d20ad32c1f388f1f2fe50afdc6dc20d9c3ef171360953
3
+ size 4664