andrealexroom commited on
Commit
df83f14
·
verified ·
1 Parent(s): 3e61916

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 sha256:6eea9fa2074cb7ff66133a09275f95a6b8e9f50e66db316f12b97ab8d4e2b28c
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c2a5ae1cf048d50603fe2d3a0de9fa2701125e574a2131d36362247f7cb4ea
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:d74215aeefb1409c496d95d6a563fed75340633765490710f5946905766129d8
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:f55d5fc394832cfd473a6d9fa6fc30d2a64e46d443236e375c33f58092cfa902
3
+ size 28967182666
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b0069dee0e4ffb5199dba1cec39acc974730f7326c3b8eb8211cf1a9be16fc
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84bb50a5cba30b8a4c6378c71f9ee0a888b91e418cdbddbf8e3cd83dacbabb0f
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.821209483984632,
5
+ "eval_steps": 78,
6
+ "global_step": 2418,
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": 1.2868,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 1e-05,
20
+ "loss": 1.1922,
21
+ "step": 78
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "eval_validation_privacy_sources_loss": 1.0002105236053467,
26
+ "eval_validation_privacy_sources_runtime": 224.8773,
27
+ "eval_validation_privacy_sources_samples_per_second": 1.258,
28
+ "eval_validation_privacy_sources_steps_per_second": 0.631,
29
+ "step": 78
30
+ },
31
+ {
32
+ "epoch": 0.03,
33
+ "eval_validation_agenda_digitale_loss": 1.506428837776184,
34
+ "eval_validation_agenda_digitale_runtime": 201.6135,
35
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
36
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
37
+ "step": 78
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "eval_validation_leggepertutti_loss": 1.3169218301773071,
42
+ "eval_validation_leggepertutti_runtime": 37.3198,
43
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
44
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
45
+ "step": 78
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "eval_validation_altalexprivacy_loss": 1.3375698328018188,
50
+ "eval_validation_altalexprivacy_runtime": 62.731,
51
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
52
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
53
+ "step": 78
54
+ },
55
+ {
56
+ "epoch": 0.05,
57
+ "learning_rate": 1e-05,
58
+ "loss": 1.0426,
59
+ "step": 156
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "eval_validation_privacy_sources_loss": 0.9441261887550354,
64
+ "eval_validation_privacy_sources_runtime": 224.5852,
65
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
66
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
67
+ "step": 156
68
+ },
69
+ {
70
+ "epoch": 0.05,
71
+ "eval_validation_agenda_digitale_loss": 1.4715445041656494,
72
+ "eval_validation_agenda_digitale_runtime": 201.5442,
73
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
74
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
75
+ "step": 156
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "eval_validation_leggepertutti_loss": 1.290155291557312,
80
+ "eval_validation_leggepertutti_runtime": 37.3113,
81
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
82
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
83
+ "step": 156
84
+ },
85
+ {
86
+ "epoch": 0.05,
87
+ "eval_validation_altalexprivacy_loss": 1.2974395751953125,
88
+ "eval_validation_altalexprivacy_runtime": 62.7333,
89
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
90
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
91
+ "step": 156
92
+ },
93
+ {
94
+ "epoch": 0.08,
95
+ "learning_rate": 1e-05,
96
+ "loss": 0.9843,
97
+ "step": 234
98
+ },
99
+ {
100
+ "epoch": 0.08,
101
+ "eval_validation_privacy_sources_loss": 0.9115681648254395,
102
+ "eval_validation_privacy_sources_runtime": 224.5909,
103
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
104
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
105
+ "step": 234
106
+ },
107
+ {
108
+ "epoch": 0.08,
109
+ "eval_validation_agenda_digitale_loss": 1.454103946685791,
110
+ "eval_validation_agenda_digitale_runtime": 201.5826,
111
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
112
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
113
+ "step": 234
114
+ },
115
+ {
116
+ "epoch": 0.08,
117
+ "eval_validation_leggepertutti_loss": 1.2771508693695068,
118
+ "eval_validation_leggepertutti_runtime": 37.3084,
119
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
120
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
121
+ "step": 234
122
+ },
123
+ {
124
+ "epoch": 0.08,
125
+ "eval_validation_altalexprivacy_loss": 1.2786180973052979,
126
+ "eval_validation_altalexprivacy_runtime": 62.71,
127
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
128
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
129
+ "step": 234
130
+ },
131
+ {
132
+ "epoch": 0.11,
133
+ "learning_rate": 1e-05,
134
+ "loss": 0.9674,
135
+ "step": 312
136
+ },
137
+ {
138
+ "epoch": 0.11,
139
+ "eval_validation_privacy_sources_loss": 0.8925028443336487,
140
+ "eval_validation_privacy_sources_runtime": 224.5822,
141
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
142
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
143
+ "step": 312
144
+ },
145
+ {
146
+ "epoch": 0.11,
147
+ "eval_validation_agenda_digitale_loss": 1.442084550857544,
148
+ "eval_validation_agenda_digitale_runtime": 201.5693,
149
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
150
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
151
+ "step": 312
152
+ },
153
+ {
154
+ "epoch": 0.11,
155
+ "eval_validation_leggepertutti_loss": 1.2704201936721802,
156
+ "eval_validation_leggepertutti_runtime": 37.2901,
157
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
158
+ "eval_validation_leggepertutti_steps_per_second": 0.644,
159
+ "step": 312
160
+ },
161
+ {
162
+ "epoch": 0.11,
163
+ "eval_validation_altalexprivacy_loss": 1.2658644914627075,
164
+ "eval_validation_altalexprivacy_runtime": 62.696,
165
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
166
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
167
+ "step": 312
168
+ },
169
+ {
170
+ "epoch": 0.13,
171
+ "learning_rate": 1e-05,
172
+ "loss": 0.9451,
173
+ "step": 390
174
+ },
175
+ {
176
+ "epoch": 0.13,
177
+ "eval_validation_privacy_sources_loss": 0.8763552904129028,
178
+ "eval_validation_privacy_sources_runtime": 224.7039,
179
+ "eval_validation_privacy_sources_samples_per_second": 1.259,
180
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
181
+ "step": 390
182
+ },
183
+ {
184
+ "epoch": 0.13,
185
+ "eval_validation_agenda_digitale_loss": 1.4315780401229858,
186
+ "eval_validation_agenda_digitale_runtime": 201.6786,
187
+ "eval_validation_agenda_digitale_samples_per_second": 1.259,
188
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
189
+ "step": 390
190
+ },
191
+ {
192
+ "epoch": 0.13,
193
+ "eval_validation_leggepertutti_loss": 1.2630696296691895,
194
+ "eval_validation_leggepertutti_runtime": 37.333,
195
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
196
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
197
+ "step": 390
198
+ },
199
+ {
200
+ "epoch": 0.13,
201
+ "eval_validation_altalexprivacy_loss": 1.2540370225906372,
202
+ "eval_validation_altalexprivacy_runtime": 62.7795,
203
+ "eval_validation_altalexprivacy_samples_per_second": 1.258,
204
+ "eval_validation_altalexprivacy_steps_per_second": 0.637,
205
+ "step": 390
206
+ },
207
+ {
208
+ "epoch": 0.16,
209
+ "learning_rate": 1e-05,
210
+ "loss": 0.926,
211
+ "step": 468
212
+ },
213
+ {
214
+ "epoch": 0.16,
215
+ "eval_validation_privacy_sources_loss": 0.8631904721260071,
216
+ "eval_validation_privacy_sources_runtime": 224.6404,
217
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
218
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
219
+ "step": 468
220
+ },
221
+ {
222
+ "epoch": 0.16,
223
+ "eval_validation_agenda_digitale_loss": 1.4235539436340332,
224
+ "eval_validation_agenda_digitale_runtime": 201.6226,
225
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
226
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
227
+ "step": 468
228
+ },
229
+ {
230
+ "epoch": 0.16,
231
+ "eval_validation_leggepertutti_loss": 1.2557491064071655,
232
+ "eval_validation_leggepertutti_runtime": 37.3222,
233
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
234
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
235
+ "step": 468
236
+ },
237
+ {
238
+ "epoch": 0.16,
239
+ "eval_validation_altalexprivacy_loss": 1.244572639465332,
240
+ "eval_validation_altalexprivacy_runtime": 62.7205,
241
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
242
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
243
+ "step": 468
244
+ },
245
+ {
246
+ "epoch": 0.19,
247
+ "learning_rate": 1e-05,
248
+ "loss": 0.9164,
249
+ "step": 546
250
+ },
251
+ {
252
+ "epoch": 0.19,
253
+ "eval_validation_privacy_sources_loss": 0.8481507301330566,
254
+ "eval_validation_privacy_sources_runtime": 224.6424,
255
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
256
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
257
+ "step": 546
258
+ },
259
+ {
260
+ "epoch": 0.19,
261
+ "eval_validation_agenda_digitale_loss": 1.4142533540725708,
262
+ "eval_validation_agenda_digitale_runtime": 201.7172,
263
+ "eval_validation_agenda_digitale_samples_per_second": 1.259,
264
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
265
+ "step": 546
266
+ },
267
+ {
268
+ "epoch": 0.19,
269
+ "eval_validation_leggepertutti_loss": 1.2529613971710205,
270
+ "eval_validation_leggepertutti_runtime": 37.3269,
271
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
272
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
273
+ "step": 546
274
+ },
275
+ {
276
+ "epoch": 0.19,
277
+ "eval_validation_altalexprivacy_loss": 1.2327677011489868,
278
+ "eval_validation_altalexprivacy_runtime": 62.729,
279
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
280
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
281
+ "step": 546
282
+ },
283
+ {
284
+ "epoch": 0.21,
285
+ "learning_rate": 1e-05,
286
+ "loss": 0.9088,
287
+ "step": 624
288
+ },
289
+ {
290
+ "epoch": 0.21,
291
+ "eval_validation_privacy_sources_loss": 0.8413664698600769,
292
+ "eval_validation_privacy_sources_runtime": 224.6765,
293
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
294
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
295
+ "step": 624
296
+ },
297
+ {
298
+ "epoch": 0.21,
299
+ "eval_validation_agenda_digitale_loss": 1.4095916748046875,
300
+ "eval_validation_agenda_digitale_runtime": 201.6531,
301
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
302
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
303
+ "step": 624
304
+ },
305
+ {
306
+ "epoch": 0.21,
307
+ "eval_validation_leggepertutti_loss": 1.2475595474243164,
308
+ "eval_validation_leggepertutti_runtime": 37.3103,
309
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
310
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
311
+ "step": 624
312
+ },
313
+ {
314
+ "epoch": 0.21,
315
+ "eval_validation_altalexprivacy_loss": 1.227779507637024,
316
+ "eval_validation_altalexprivacy_runtime": 62.7042,
317
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
318
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
319
+ "step": 624
320
+ },
321
+ {
322
+ "epoch": 0.24,
323
+ "learning_rate": 1e-05,
324
+ "loss": 0.9006,
325
+ "step": 702
326
+ },
327
+ {
328
+ "epoch": 0.24,
329
+ "eval_validation_privacy_sources_loss": 0.831943929195404,
330
+ "eval_validation_privacy_sources_runtime": 224.6666,
331
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
332
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
333
+ "step": 702
334
+ },
335
+ {
336
+ "epoch": 0.24,
337
+ "eval_validation_agenda_digitale_loss": 1.402382731437683,
338
+ "eval_validation_agenda_digitale_runtime": 201.6915,
339
+ "eval_validation_agenda_digitale_samples_per_second": 1.259,
340
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
341
+ "step": 702
342
+ },
343
+ {
344
+ "epoch": 0.24,
345
+ "eval_validation_leggepertutti_loss": 1.2434861660003662,
346
+ "eval_validation_leggepertutti_runtime": 37.329,
347
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
348
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
349
+ "step": 702
350
+ },
351
+ {
352
+ "epoch": 0.24,
353
+ "eval_validation_altalexprivacy_loss": 1.2196098566055298,
354
+ "eval_validation_altalexprivacy_runtime": 62.7382,
355
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
356
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
357
+ "step": 702
358
+ },
359
+ {
360
+ "epoch": 0.26,
361
+ "learning_rate": 1e-05,
362
+ "loss": 0.8949,
363
+ "step": 780
364
+ },
365
+ {
366
+ "epoch": 0.26,
367
+ "eval_validation_privacy_sources_loss": 0.8237769603729248,
368
+ "eval_validation_privacy_sources_runtime": 224.6746,
369
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
370
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
371
+ "step": 780
372
+ },
373
+ {
374
+ "epoch": 0.26,
375
+ "eval_validation_agenda_digitale_loss": 1.398356318473816,
376
+ "eval_validation_agenda_digitale_runtime": 201.7018,
377
+ "eval_validation_agenda_digitale_samples_per_second": 1.259,
378
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
379
+ "step": 780
380
+ },
381
+ {
382
+ "epoch": 0.26,
383
+ "eval_validation_leggepertutti_loss": 1.2447354793548584,
384
+ "eval_validation_leggepertutti_runtime": 37.3178,
385
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
386
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
387
+ "step": 780
388
+ },
389
+ {
390
+ "epoch": 0.26,
391
+ "eval_validation_altalexprivacy_loss": 1.215567946434021,
392
+ "eval_validation_altalexprivacy_runtime": 62.7324,
393
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
394
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
395
+ "step": 780
396
+ },
397
+ {
398
+ "epoch": 0.29,
399
+ "learning_rate": 1e-05,
400
+ "loss": 0.8949,
401
+ "step": 858
402
+ },
403
+ {
404
+ "epoch": 0.29,
405
+ "eval_validation_privacy_sources_loss": 0.8192195892333984,
406
+ "eval_validation_privacy_sources_runtime": 224.7891,
407
+ "eval_validation_privacy_sources_samples_per_second": 1.259,
408
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
409
+ "step": 858
410
+ },
411
+ {
412
+ "epoch": 0.29,
413
+ "eval_validation_agenda_digitale_loss": 1.3945348262786865,
414
+ "eval_validation_agenda_digitale_runtime": 201.7408,
415
+ "eval_validation_agenda_digitale_samples_per_second": 1.259,
416
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
417
+ "step": 858
418
+ },
419
+ {
420
+ "epoch": 0.29,
421
+ "eval_validation_leggepertutti_loss": 1.2369723320007324,
422
+ "eval_validation_leggepertutti_runtime": 37.3566,
423
+ "eval_validation_leggepertutti_samples_per_second": 1.258,
424
+ "eval_validation_leggepertutti_steps_per_second": 0.642,
425
+ "step": 858
426
+ },
427
+ {
428
+ "epoch": 0.29,
429
+ "eval_validation_altalexprivacy_loss": 1.2105611562728882,
430
+ "eval_validation_altalexprivacy_runtime": 62.7486,
431
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
432
+ "eval_validation_altalexprivacy_steps_per_second": 0.637,
433
+ "step": 858
434
+ },
435
+ {
436
+ "epoch": 0.32,
437
+ "learning_rate": 1e-05,
438
+ "loss": 0.8707,
439
+ "step": 936
440
+ },
441
+ {
442
+ "epoch": 0.32,
443
+ "eval_validation_privacy_sources_loss": 0.8130488395690918,
444
+ "eval_validation_privacy_sources_runtime": 224.6167,
445
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
446
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
447
+ "step": 936
448
+ },
449
+ {
450
+ "epoch": 0.32,
451
+ "eval_validation_agenda_digitale_loss": 1.3879377841949463,
452
+ "eval_validation_agenda_digitale_runtime": 201.5934,
453
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
454
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
455
+ "step": 936
456
+ },
457
+ {
458
+ "epoch": 0.32,
459
+ "eval_validation_leggepertutti_loss": 1.2382495403289795,
460
+ "eval_validation_leggepertutti_runtime": 37.3119,
461
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
462
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
463
+ "step": 936
464
+ },
465
+ {
466
+ "epoch": 0.32,
467
+ "eval_validation_altalexprivacy_loss": 1.2007031440734863,
468
+ "eval_validation_altalexprivacy_runtime": 62.7366,
469
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
470
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
471
+ "step": 936
472
+ },
473
+ {
474
+ "epoch": 0.34,
475
+ "learning_rate": 1e-05,
476
+ "loss": 0.8751,
477
+ "step": 1014
478
+ },
479
+ {
480
+ "epoch": 0.34,
481
+ "eval_validation_privacy_sources_loss": 0.8075301647186279,
482
+ "eval_validation_privacy_sources_runtime": 224.6205,
483
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
484
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
485
+ "step": 1014
486
+ },
487
+ {
488
+ "epoch": 0.34,
489
+ "eval_validation_agenda_digitale_loss": 1.3856638669967651,
490
+ "eval_validation_agenda_digitale_runtime": 201.5938,
491
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
492
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
493
+ "step": 1014
494
+ },
495
+ {
496
+ "epoch": 0.34,
497
+ "eval_validation_leggepertutti_loss": 1.2311820983886719,
498
+ "eval_validation_leggepertutti_runtime": 37.2845,
499
+ "eval_validation_leggepertutti_samples_per_second": 1.261,
500
+ "eval_validation_leggepertutti_steps_per_second": 0.644,
501
+ "step": 1014
502
+ },
503
+ {
504
+ "epoch": 0.34,
505
+ "eval_validation_altalexprivacy_loss": 1.1969715356826782,
506
+ "eval_validation_altalexprivacy_runtime": 62.7088,
507
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
508
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
509
+ "step": 1014
510
+ },
511
+ {
512
+ "epoch": 0.37,
513
+ "learning_rate": 1e-05,
514
+ "loss": 0.8589,
515
+ "step": 1092
516
+ },
517
+ {
518
+ "epoch": 0.37,
519
+ "eval_validation_privacy_sources_loss": 0.802371084690094,
520
+ "eval_validation_privacy_sources_runtime": 224.5992,
521
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
522
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
523
+ "step": 1092
524
+ },
525
+ {
526
+ "epoch": 0.37,
527
+ "eval_validation_agenda_digitale_loss": 1.38155996799469,
528
+ "eval_validation_agenda_digitale_runtime": 201.594,
529
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
530
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
531
+ "step": 1092
532
+ },
533
+ {
534
+ "epoch": 0.37,
535
+ "eval_validation_leggepertutti_loss": 1.2296923398971558,
536
+ "eval_validation_leggepertutti_runtime": 37.3198,
537
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
538
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
539
+ "step": 1092
540
+ },
541
+ {
542
+ "epoch": 0.37,
543
+ "eval_validation_altalexprivacy_loss": 1.1883776187896729,
544
+ "eval_validation_altalexprivacy_runtime": 62.6985,
545
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
546
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
547
+ "step": 1092
548
+ },
549
+ {
550
+ "epoch": 0.4,
551
+ "learning_rate": 1e-05,
552
+ "loss": 0.8525,
553
+ "step": 1170
554
+ },
555
+ {
556
+ "epoch": 0.4,
557
+ "eval_validation_privacy_sources_loss": 0.7987944483757019,
558
+ "eval_validation_privacy_sources_runtime": 224.6514,
559
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
560
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
561
+ "step": 1170
562
+ },
563
+ {
564
+ "epoch": 0.4,
565
+ "eval_validation_agenda_digitale_loss": 1.378859519958496,
566
+ "eval_validation_agenda_digitale_runtime": 201.5551,
567
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
568
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
569
+ "step": 1170
570
+ },
571
+ {
572
+ "epoch": 0.4,
573
+ "eval_validation_leggepertutti_loss": 1.2266310453414917,
574
+ "eval_validation_leggepertutti_runtime": 37.3135,
575
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
576
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
577
+ "step": 1170
578
+ },
579
+ {
580
+ "epoch": 0.4,
581
+ "eval_validation_altalexprivacy_loss": 1.184443473815918,
582
+ "eval_validation_altalexprivacy_runtime": 62.7093,
583
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
584
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
585
+ "step": 1170
586
+ },
587
+ {
588
+ "epoch": 0.42,
589
+ "learning_rate": 1e-05,
590
+ "loss": 0.8351,
591
+ "step": 1248
592
+ },
593
+ {
594
+ "epoch": 0.42,
595
+ "eval_validation_privacy_sources_loss": 0.7923627495765686,
596
+ "eval_validation_privacy_sources_runtime": 224.6783,
597
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
598
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
599
+ "step": 1248
600
+ },
601
+ {
602
+ "epoch": 0.42,
603
+ "eval_validation_agenda_digitale_loss": 1.3744804859161377,
604
+ "eval_validation_agenda_digitale_runtime": 201.619,
605
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
606
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
607
+ "step": 1248
608
+ },
609
+ {
610
+ "epoch": 0.42,
611
+ "eval_validation_leggepertutti_loss": 1.2276861667633057,
612
+ "eval_validation_leggepertutti_runtime": 37.3273,
613
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
614
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
615
+ "step": 1248
616
+ },
617
+ {
618
+ "epoch": 0.42,
619
+ "eval_validation_altalexprivacy_loss": 1.1810448169708252,
620
+ "eval_validation_altalexprivacy_runtime": 62.7321,
621
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
622
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
623
+ "step": 1248
624
+ },
625
+ {
626
+ "epoch": 0.45,
627
+ "learning_rate": 1e-05,
628
+ "loss": 0.8677,
629
+ "step": 1326
630
+ },
631
+ {
632
+ "epoch": 0.45,
633
+ "eval_validation_privacy_sources_loss": 0.7889499068260193,
634
+ "eval_validation_privacy_sources_runtime": 224.6868,
635
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
636
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
637
+ "step": 1326
638
+ },
639
+ {
640
+ "epoch": 0.45,
641
+ "eval_validation_agenda_digitale_loss": 1.3705928325653076,
642
+ "eval_validation_agenda_digitale_runtime": 201.6361,
643
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
644
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
645
+ "step": 1326
646
+ },
647
+ {
648
+ "epoch": 0.45,
649
+ "eval_validation_leggepertutti_loss": 1.2240731716156006,
650
+ "eval_validation_leggepertutti_runtime": 37.3245,
651
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
652
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
653
+ "step": 1326
654
+ },
655
+ {
656
+ "epoch": 0.45,
657
+ "eval_validation_altalexprivacy_loss": 1.1790387630462646,
658
+ "eval_validation_altalexprivacy_runtime": 62.7345,
659
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
660
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
661
+ "step": 1326
662
+ },
663
+ {
664
+ "epoch": 0.48,
665
+ "learning_rate": 1e-05,
666
+ "loss": 0.8525,
667
+ "step": 1404
668
+ },
669
+ {
670
+ "epoch": 0.48,
671
+ "eval_validation_privacy_sources_loss": 0.7861167192459106,
672
+ "eval_validation_privacy_sources_runtime": 224.6061,
673
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
674
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
675
+ "step": 1404
676
+ },
677
+ {
678
+ "epoch": 0.48,
679
+ "eval_validation_agenda_digitale_loss": 1.3675950765609741,
680
+ "eval_validation_agenda_digitale_runtime": 201.56,
681
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
682
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
683
+ "step": 1404
684
+ },
685
+ {
686
+ "epoch": 0.48,
687
+ "eval_validation_leggepertutti_loss": 1.221396565437317,
688
+ "eval_validation_leggepertutti_runtime": 37.3138,
689
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
690
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
691
+ "step": 1404
692
+ },
693
+ {
694
+ "epoch": 0.48,
695
+ "eval_validation_altalexprivacy_loss": 1.1739190816879272,
696
+ "eval_validation_altalexprivacy_runtime": 62.7334,
697
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
698
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
699
+ "step": 1404
700
+ },
701
+ {
702
+ "epoch": 0.5,
703
+ "learning_rate": 1e-05,
704
+ "loss": 0.8367,
705
+ "step": 1482
706
+ },
707
+ {
708
+ "epoch": 0.5,
709
+ "eval_validation_privacy_sources_loss": 0.7826875448226929,
710
+ "eval_validation_privacy_sources_runtime": 224.6469,
711
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
712
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
713
+ "step": 1482
714
+ },
715
+ {
716
+ "epoch": 0.5,
717
+ "eval_validation_agenda_digitale_loss": 1.3640720844268799,
718
+ "eval_validation_agenda_digitale_runtime": 201.5686,
719
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
720
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
721
+ "step": 1482
722
+ },
723
+ {
724
+ "epoch": 0.5,
725
+ "eval_validation_leggepertutti_loss": 1.2208744287490845,
726
+ "eval_validation_leggepertutti_runtime": 37.3251,
727
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
728
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
729
+ "step": 1482
730
+ },
731
+ {
732
+ "epoch": 0.5,
733
+ "eval_validation_altalexprivacy_loss": 1.1706568002700806,
734
+ "eval_validation_altalexprivacy_runtime": 62.7198,
735
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
736
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
737
+ "step": 1482
738
+ },
739
+ {
740
+ "epoch": 0.53,
741
+ "learning_rate": 1e-05,
742
+ "loss": 0.8275,
743
+ "step": 1560
744
+ },
745
+ {
746
+ "epoch": 0.53,
747
+ "eval_validation_privacy_sources_loss": 0.7790248990058899,
748
+ "eval_validation_privacy_sources_runtime": 224.5806,
749
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
750
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
751
+ "step": 1560
752
+ },
753
+ {
754
+ "epoch": 0.53,
755
+ "eval_validation_agenda_digitale_loss": 1.3617193698883057,
756
+ "eval_validation_agenda_digitale_runtime": 201.5271,
757
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
758
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
759
+ "step": 1560
760
+ },
761
+ {
762
+ "epoch": 0.53,
763
+ "eval_validation_leggepertutti_loss": 1.2156528234481812,
764
+ "eval_validation_leggepertutti_runtime": 37.3178,
765
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
766
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
767
+ "step": 1560
768
+ },
769
+ {
770
+ "epoch": 0.53,
771
+ "eval_validation_altalexprivacy_loss": 1.1662012338638306,
772
+ "eval_validation_altalexprivacy_runtime": 62.6914,
773
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
774
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
775
+ "step": 1560
776
+ },
777
+ {
778
+ "epoch": 0.56,
779
+ "learning_rate": 1e-05,
780
+ "loss": 0.8345,
781
+ "step": 1638
782
+ },
783
+ {
784
+ "epoch": 0.56,
785
+ "eval_validation_privacy_sources_loss": 0.7750757336616516,
786
+ "eval_validation_privacy_sources_runtime": 224.5457,
787
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
788
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
789
+ "step": 1638
790
+ },
791
+ {
792
+ "epoch": 0.56,
793
+ "eval_validation_agenda_digitale_loss": 1.359161615371704,
794
+ "eval_validation_agenda_digitale_runtime": 201.5443,
795
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
796
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
797
+ "step": 1638
798
+ },
799
+ {
800
+ "epoch": 0.56,
801
+ "eval_validation_leggepertutti_loss": 1.21549391746521,
802
+ "eval_validation_leggepertutti_runtime": 37.3017,
803
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
804
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
805
+ "step": 1638
806
+ },
807
+ {
808
+ "epoch": 0.56,
809
+ "eval_validation_altalexprivacy_loss": 1.164724588394165,
810
+ "eval_validation_altalexprivacy_runtime": 62.7184,
811
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
812
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
813
+ "step": 1638
814
+ },
815
+ {
816
+ "epoch": 0.58,
817
+ "learning_rate": 1e-05,
818
+ "loss": 0.8212,
819
+ "step": 1716
820
+ },
821
+ {
822
+ "epoch": 0.58,
823
+ "eval_validation_privacy_sources_loss": 0.7707695364952087,
824
+ "eval_validation_privacy_sources_runtime": 224.6072,
825
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
826
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
827
+ "step": 1716
828
+ },
829
+ {
830
+ "epoch": 0.58,
831
+ "eval_validation_agenda_digitale_loss": 1.3564361333847046,
832
+ "eval_validation_agenda_digitale_runtime": 201.5688,
833
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
834
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
835
+ "step": 1716
836
+ },
837
+ {
838
+ "epoch": 0.58,
839
+ "eval_validation_leggepertutti_loss": 1.2156838178634644,
840
+ "eval_validation_leggepertutti_runtime": 37.3115,
841
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
842
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
843
+ "step": 1716
844
+ },
845
+ {
846
+ "epoch": 0.58,
847
+ "eval_validation_altalexprivacy_loss": 1.162009358406067,
848
+ "eval_validation_altalexprivacy_runtime": 62.7139,
849
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
850
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
851
+ "step": 1716
852
+ },
853
+ {
854
+ "epoch": 0.61,
855
+ "learning_rate": 1e-05,
856
+ "loss": 0.8192,
857
+ "step": 1794
858
+ },
859
+ {
860
+ "epoch": 0.61,
861
+ "eval_validation_privacy_sources_loss": 0.7677339315414429,
862
+ "eval_validation_privacy_sources_runtime": 224.5755,
863
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
864
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
865
+ "step": 1794
866
+ },
867
+ {
868
+ "epoch": 0.61,
869
+ "eval_validation_agenda_digitale_loss": 1.3542948961257935,
870
+ "eval_validation_agenda_digitale_runtime": 201.5485,
871
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
872
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
873
+ "step": 1794
874
+ },
875
+ {
876
+ "epoch": 0.61,
877
+ "eval_validation_leggepertutti_loss": 1.2127934694290161,
878
+ "eval_validation_leggepertutti_runtime": 37.3114,
879
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
880
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
881
+ "step": 1794
882
+ },
883
+ {
884
+ "epoch": 0.61,
885
+ "eval_validation_altalexprivacy_loss": 1.1589841842651367,
886
+ "eval_validation_altalexprivacy_runtime": 62.7164,
887
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
888
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
889
+ "step": 1794
890
+ },
891
+ {
892
+ "epoch": 0.64,
893
+ "learning_rate": 1e-05,
894
+ "loss": 0.8223,
895
+ "step": 1872
896
+ },
897
+ {
898
+ "epoch": 0.64,
899
+ "eval_validation_privacy_sources_loss": 0.7649637460708618,
900
+ "eval_validation_privacy_sources_runtime": 224.5258,
901
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
902
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
903
+ "step": 1872
904
+ },
905
+ {
906
+ "epoch": 0.64,
907
+ "eval_validation_agenda_digitale_loss": 1.3530330657958984,
908
+ "eval_validation_agenda_digitale_runtime": 201.5061,
909
+ "eval_validation_agenda_digitale_samples_per_second": 1.261,
910
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
911
+ "step": 1872
912
+ },
913
+ {
914
+ "epoch": 0.64,
915
+ "eval_validation_leggepertutti_loss": 1.2127245664596558,
916
+ "eval_validation_leggepertutti_runtime": 37.3038,
917
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
918
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
919
+ "step": 1872
920
+ },
921
+ {
922
+ "epoch": 0.64,
923
+ "eval_validation_altalexprivacy_loss": 1.1484553813934326,
924
+ "eval_validation_altalexprivacy_runtime": 62.6979,
925
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
926
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
927
+ "step": 1872
928
+ },
929
+ {
930
+ "epoch": 0.66,
931
+ "learning_rate": 1e-05,
932
+ "loss": 0.8184,
933
+ "step": 1950
934
+ },
935
+ {
936
+ "epoch": 0.66,
937
+ "eval_validation_privacy_sources_loss": 0.7624295949935913,
938
+ "eval_validation_privacy_sources_runtime": 224.6066,
939
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
940
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
941
+ "step": 1950
942
+ },
943
+ {
944
+ "epoch": 0.66,
945
+ "eval_validation_agenda_digitale_loss": 1.3500715494155884,
946
+ "eval_validation_agenda_digitale_runtime": 201.6049,
947
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
948
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
949
+ "step": 1950
950
+ },
951
+ {
952
+ "epoch": 0.66,
953
+ "eval_validation_leggepertutti_loss": 1.2118768692016602,
954
+ "eval_validation_leggepertutti_runtime": 37.3114,
955
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
956
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
957
+ "step": 1950
958
+ },
959
+ {
960
+ "epoch": 0.66,
961
+ "eval_validation_altalexprivacy_loss": 1.1498790979385376,
962
+ "eval_validation_altalexprivacy_runtime": 62.7252,
963
+ "eval_validation_altalexprivacy_samples_per_second": 1.259,
964
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
965
+ "step": 1950
966
+ },
967
+ {
968
+ "epoch": 0.69,
969
+ "learning_rate": 1e-05,
970
+ "loss": 0.8263,
971
+ "step": 2028
972
+ },
973
+ {
974
+ "epoch": 0.69,
975
+ "eval_validation_privacy_sources_loss": 0.7596579194068909,
976
+ "eval_validation_privacy_sources_runtime": 224.5436,
977
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
978
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
979
+ "step": 2028
980
+ },
981
+ {
982
+ "epoch": 0.69,
983
+ "eval_validation_agenda_digitale_loss": 1.3486237525939941,
984
+ "eval_validation_agenda_digitale_runtime": 201.5865,
985
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
986
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
987
+ "step": 2028
988
+ },
989
+ {
990
+ "epoch": 0.69,
991
+ "eval_validation_leggepertutti_loss": 1.2151111364364624,
992
+ "eval_validation_leggepertutti_runtime": 37.3212,
993
+ "eval_validation_leggepertutti_samples_per_second": 1.259,
994
+ "eval_validation_leggepertutti_steps_per_second": 0.643,
995
+ "step": 2028
996
+ },
997
+ {
998
+ "epoch": 0.69,
999
+ "eval_validation_altalexprivacy_loss": 1.1481529474258423,
1000
+ "eval_validation_altalexprivacy_runtime": 62.7124,
1001
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
1002
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
1003
+ "step": 2028
1004
+ },
1005
+ {
1006
+ "epoch": 0.72,
1007
+ "learning_rate": 1e-05,
1008
+ "loss": 0.8072,
1009
+ "step": 2106
1010
+ },
1011
+ {
1012
+ "epoch": 0.72,
1013
+ "eval_validation_privacy_sources_loss": 0.7558060884475708,
1014
+ "eval_validation_privacy_sources_runtime": 224.5565,
1015
+ "eval_validation_privacy_sources_samples_per_second": 1.26,
1016
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
1017
+ "step": 2106
1018
+ },
1019
+ {
1020
+ "epoch": 0.72,
1021
+ "eval_validation_agenda_digitale_loss": 1.3457963466644287,
1022
+ "eval_validation_agenda_digitale_runtime": 201.6812,
1023
+ "eval_validation_agenda_digitale_samples_per_second": 1.259,
1024
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
1025
+ "step": 2106
1026
+ },
1027
+ {
1028
+ "epoch": 0.72,
1029
+ "eval_validation_leggepertutti_loss": 1.2086989879608154,
1030
+ "eval_validation_leggepertutti_runtime": 37.2947,
1031
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
1032
+ "eval_validation_leggepertutti_steps_per_second": 0.644,
1033
+ "step": 2106
1034
+ },
1035
+ {
1036
+ "epoch": 0.72,
1037
+ "eval_validation_altalexprivacy_loss": 1.143056035041809,
1038
+ "eval_validation_altalexprivacy_runtime": 62.7129,
1039
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
1040
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
1041
+ "step": 2106
1042
+ },
1043
+ {
1044
+ "epoch": 0.74,
1045
+ "learning_rate": 1e-05,
1046
+ "loss": 0.8106,
1047
+ "step": 2184
1048
+ },
1049
+ {
1050
+ "epoch": 0.74,
1051
+ "eval_validation_privacy_sources_loss": 0.7534470558166504,
1052
+ "eval_validation_privacy_sources_runtime": 224.4612,
1053
+ "eval_validation_privacy_sources_samples_per_second": 1.261,
1054
+ "eval_validation_privacy_sources_steps_per_second": 0.633,
1055
+ "step": 2184
1056
+ },
1057
+ {
1058
+ "epoch": 0.74,
1059
+ "eval_validation_agenda_digitale_loss": 1.3441107273101807,
1060
+ "eval_validation_agenda_digitale_runtime": 201.517,
1061
+ "eval_validation_agenda_digitale_samples_per_second": 1.26,
1062
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
1063
+ "step": 2184
1064
+ },
1065
+ {
1066
+ "epoch": 0.74,
1067
+ "eval_validation_leggepertutti_loss": 1.2076504230499268,
1068
+ "eval_validation_leggepertutti_runtime": 37.2886,
1069
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
1070
+ "eval_validation_leggepertutti_steps_per_second": 0.644,
1071
+ "step": 2184
1072
+ },
1073
+ {
1074
+ "epoch": 0.74,
1075
+ "eval_validation_altalexprivacy_loss": 1.1403050422668457,
1076
+ "eval_validation_altalexprivacy_runtime": 62.6997,
1077
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
1078
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
1079
+ "step": 2184
1080
+ },
1081
+ {
1082
+ "epoch": 0.77,
1083
+ "learning_rate": 1e-05,
1084
+ "loss": 0.8165,
1085
+ "step": 2262
1086
+ },
1087
+ {
1088
+ "epoch": 0.77,
1089
+ "eval_validation_privacy_sources_loss": 0.7504842877388,
1090
+ "eval_validation_privacy_sources_runtime": 224.5078,
1091
+ "eval_validation_privacy_sources_samples_per_second": 1.261,
1092
+ "eval_validation_privacy_sources_steps_per_second": 0.632,
1093
+ "step": 2262
1094
+ },
1095
+ {
1096
+ "epoch": 0.77,
1097
+ "eval_validation_agenda_digitale_loss": 1.3427860736846924,
1098
+ "eval_validation_agenda_digitale_runtime": 201.481,
1099
+ "eval_validation_agenda_digitale_samples_per_second": 1.261,
1100
+ "eval_validation_agenda_digitale_steps_per_second": 0.63,
1101
+ "step": 2262
1102
+ },
1103
+ {
1104
+ "epoch": 0.77,
1105
+ "eval_validation_leggepertutti_loss": 1.2089033126831055,
1106
+ "eval_validation_leggepertutti_runtime": 37.295,
1107
+ "eval_validation_leggepertutti_samples_per_second": 1.26,
1108
+ "eval_validation_leggepertutti_steps_per_second": 0.644,
1109
+ "step": 2262
1110
+ },
1111
+ {
1112
+ "epoch": 0.77,
1113
+ "eval_validation_altalexprivacy_loss": 1.1397895812988281,
1114
+ "eval_validation_altalexprivacy_runtime": 62.6922,
1115
+ "eval_validation_altalexprivacy_samples_per_second": 1.26,
1116
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
1117
+ "step": 2262
1118
+ },
1119
+ {
1120
+ "epoch": 0.79,
1121
+ "learning_rate": 1e-05,
1122
+ "loss": 0.7981,
1123
+ "step": 2340
1124
+ },
1125
+ {
1126
+ "epoch": 0.79,
1127
+ "eval_validation_privacy_sources_loss": 0.7486781477928162,
1128
+ "eval_validation_privacy_sources_runtime": 224.4052,
1129
+ "eval_validation_privacy_sources_samples_per_second": 1.261,
1130
+ "eval_validation_privacy_sources_steps_per_second": 0.633,
1131
+ "step": 2340
1132
+ },
1133
+ {
1134
+ "epoch": 0.79,
1135
+ "eval_validation_agenda_digitale_loss": 1.3407869338989258,
1136
+ "eval_validation_agenda_digitale_runtime": 201.3764,
1137
+ "eval_validation_agenda_digitale_samples_per_second": 1.261,
1138
+ "eval_validation_agenda_digitale_steps_per_second": 0.631,
1139
+ "step": 2340
1140
+ },
1141
+ {
1142
+ "epoch": 0.79,
1143
+ "eval_validation_leggepertutti_loss": 1.2058355808258057,
1144
+ "eval_validation_leggepertutti_runtime": 37.2866,
1145
+ "eval_validation_leggepertutti_samples_per_second": 1.261,
1146
+ "eval_validation_leggepertutti_steps_per_second": 0.644,
1147
+ "step": 2340
1148
+ },
1149
+ {
1150
+ "epoch": 0.79,
1151
+ "eval_validation_altalexprivacy_loss": 1.1342254877090454,
1152
+ "eval_validation_altalexprivacy_runtime": 62.6677,
1153
+ "eval_validation_altalexprivacy_samples_per_second": 1.261,
1154
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
1155
+ "step": 2340
1156
+ },
1157
+ {
1158
+ "epoch": 0.82,
1159
+ "learning_rate": 1e-05,
1160
+ "loss": 0.7939,
1161
+ "step": 2418
1162
+ },
1163
+ {
1164
+ "epoch": 0.82,
1165
+ "eval_validation_privacy_sources_loss": 0.7474262118339539,
1166
+ "eval_validation_privacy_sources_runtime": 224.4858,
1167
+ "eval_validation_privacy_sources_samples_per_second": 1.261,
1168
+ "eval_validation_privacy_sources_steps_per_second": 0.633,
1169
+ "step": 2418
1170
+ },
1171
+ {
1172
+ "epoch": 0.82,
1173
+ "eval_validation_agenda_digitale_loss": 1.3384801149368286,
1174
+ "eval_validation_agenda_digitale_runtime": 201.426,
1175
+ "eval_validation_agenda_digitale_samples_per_second": 1.261,
1176
+ "eval_validation_agenda_digitale_steps_per_second": 0.631,
1177
+ "step": 2418
1178
+ },
1179
+ {
1180
+ "epoch": 0.82,
1181
+ "eval_validation_leggepertutti_loss": 1.206802248954773,
1182
+ "eval_validation_leggepertutti_runtime": 37.2757,
1183
+ "eval_validation_leggepertutti_samples_per_second": 1.261,
1184
+ "eval_validation_leggepertutti_steps_per_second": 0.644,
1185
+ "step": 2418
1186
+ },
1187
+ {
1188
+ "epoch": 0.82,
1189
+ "eval_validation_altalexprivacy_loss": 1.1315449476242065,
1190
+ "eval_validation_altalexprivacy_runtime": 62.6622,
1191
+ "eval_validation_altalexprivacy_samples_per_second": 1.261,
1192
+ "eval_validation_altalexprivacy_steps_per_second": 0.638,
1193
+ "step": 2418
1194
+ }
1195
+ ],
1196
+ "logging_steps": 78,
1197
+ "max_steps": 5888,
1198
+ "num_input_tokens_seen": 0,
1199
+ "num_train_epochs": 2,
1200
+ "save_steps": 78,
1201
+ "total_flos": 2.7043156898026095e+19,
1202
+ "train_batch_size": 1,
1203
+ "trial_name": null,
1204
+ "trial_params": null
1205
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b4c46ac41c11c941c916f588a0d91ad48f797f7249ddd3234d253e261f638bf
3
+ size 4664