andrealexroom commited on
Commit
0f8b463
·
verified ·
1 Parent(s): 78e0c83

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 sha256:5c2d55a64808a77eda176afbbeefd45950227a927c4f1b5324a6fd217e8908ca
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52508742896e41540cefe91538a94f327351d8cef63bb6843ac7af01619af420
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7594935925b29df7d843e7698118f9fea4908ecb8e9597cecc69e1b0f5b320
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 sha256:599aebad274c5bef5f5ee0ec4c0628a4074ed818a8ded6ecff7c28d98a445844
3
+ size 12068282
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d512243777f64d2999c693533533470d96b2283f020be1561b49cab2d5dc04d6
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0700bb3b28b0d12e34c3e4ac36351f6d980765c881cce2cafc084171cb7c7fd
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1729 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8384762393962971,
5
+ "eval_steps": 375,
6
+ "global_step": 13875,
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": 1.8182,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 1e-05,
20
+ "loss": 1.8531,
21
+ "step": 375
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "eval_validation_privacy_sources_loss": 1.0427056550979614,
26
+ "eval_validation_privacy_sources_runtime": 201.1093,
27
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
28
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
29
+ "step": 375
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "eval_validation_agenda_digitale_loss": 1.5768671035766602,
34
+ "eval_validation_agenda_digitale_runtime": 178.6225,
35
+ "eval_validation_agenda_digitale_samples_per_second": 1.903,
36
+ "eval_validation_agenda_digitale_steps_per_second": 1.903,
37
+ "step": 375
38
+ },
39
+ {
40
+ "epoch": 0.02,
41
+ "eval_validation_leggepertutti_loss": 1.41618013381958,
42
+ "eval_validation_leggepertutti_runtime": 34.1702,
43
+ "eval_validation_leggepertutti_samples_per_second": 1.902,
44
+ "eval_validation_leggepertutti_steps_per_second": 1.902,
45
+ "step": 375
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "eval_validation_altalexprivacy_loss": 1.420487880706787,
50
+ "eval_validation_altalexprivacy_runtime": 55.6679,
51
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
52
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
53
+ "step": 375
54
+ },
55
+ {
56
+ "epoch": 0.02,
57
+ "eval_validation_mc4_it_loss": 2.0156803131103516,
58
+ "eval_validation_mc4_it_runtime": 74.5861,
59
+ "eval_validation_mc4_it_samples_per_second": 1.904,
60
+ "eval_validation_mc4_it_steps_per_second": 1.904,
61
+ "step": 375
62
+ },
63
+ {
64
+ "epoch": 0.05,
65
+ "learning_rate": 1e-05,
66
+ "loss": 1.659,
67
+ "step": 750
68
+ },
69
+ {
70
+ "epoch": 0.05,
71
+ "eval_validation_privacy_sources_loss": 0.9875672459602356,
72
+ "eval_validation_privacy_sources_runtime": 201.0647,
73
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
74
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
75
+ "step": 750
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "eval_validation_agenda_digitale_loss": 1.5326132774353027,
80
+ "eval_validation_agenda_digitale_runtime": 178.5645,
81
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
82
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
83
+ "step": 750
84
+ },
85
+ {
86
+ "epoch": 0.05,
87
+ "eval_validation_leggepertutti_loss": 1.3737919330596924,
88
+ "eval_validation_leggepertutti_runtime": 34.1417,
89
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
90
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
91
+ "step": 750
92
+ },
93
+ {
94
+ "epoch": 0.05,
95
+ "eval_validation_altalexprivacy_loss": 1.3635202646255493,
96
+ "eval_validation_altalexprivacy_runtime": 55.6795,
97
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
98
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
99
+ "step": 750
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "eval_validation_mc4_it_loss": 1.9601805210113525,
104
+ "eval_validation_mc4_it_runtime": 74.5661,
105
+ "eval_validation_mc4_it_samples_per_second": 1.904,
106
+ "eval_validation_mc4_it_steps_per_second": 1.904,
107
+ "step": 750
108
+ },
109
+ {
110
+ "epoch": 0.07,
111
+ "learning_rate": 1e-05,
112
+ "loss": 1.5963,
113
+ "step": 1125
114
+ },
115
+ {
116
+ "epoch": 0.07,
117
+ "eval_validation_privacy_sources_loss": 0.9522767066955566,
118
+ "eval_validation_privacy_sources_runtime": 201.0521,
119
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
120
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
121
+ "step": 1125
122
+ },
123
+ {
124
+ "epoch": 0.07,
125
+ "eval_validation_agenda_digitale_loss": 1.4975751638412476,
126
+ "eval_validation_agenda_digitale_runtime": 178.5472,
127
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
128
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
129
+ "step": 1125
130
+ },
131
+ {
132
+ "epoch": 0.07,
133
+ "eval_validation_leggepertutti_loss": 1.3494906425476074,
134
+ "eval_validation_leggepertutti_runtime": 34.1339,
135
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
136
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
137
+ "step": 1125
138
+ },
139
+ {
140
+ "epoch": 0.07,
141
+ "eval_validation_altalexprivacy_loss": 1.3334871530532837,
142
+ "eval_validation_altalexprivacy_runtime": 55.6542,
143
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
144
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
145
+ "step": 1125
146
+ },
147
+ {
148
+ "epoch": 0.07,
149
+ "eval_validation_mc4_it_loss": 1.9144717454910278,
150
+ "eval_validation_mc4_it_runtime": 74.5606,
151
+ "eval_validation_mc4_it_samples_per_second": 1.904,
152
+ "eval_validation_mc4_it_steps_per_second": 1.904,
153
+ "step": 1125
154
+ },
155
+ {
156
+ "epoch": 0.09,
157
+ "learning_rate": 1e-05,
158
+ "loss": 1.577,
159
+ "step": 1500
160
+ },
161
+ {
162
+ "epoch": 0.09,
163
+ "eval_validation_privacy_sources_loss": 0.9246706366539001,
164
+ "eval_validation_privacy_sources_runtime": 201.0413,
165
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
166
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
167
+ "step": 1500
168
+ },
169
+ {
170
+ "epoch": 0.09,
171
+ "eval_validation_agenda_digitale_loss": 1.4834680557250977,
172
+ "eval_validation_agenda_digitale_runtime": 178.5955,
173
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
174
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
175
+ "step": 1500
176
+ },
177
+ {
178
+ "epoch": 0.09,
179
+ "eval_validation_leggepertutti_loss": 1.3424042463302612,
180
+ "eval_validation_leggepertutti_runtime": 34.1348,
181
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
182
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
183
+ "step": 1500
184
+ },
185
+ {
186
+ "epoch": 0.09,
187
+ "eval_validation_altalexprivacy_loss": 1.3129479885101318,
188
+ "eval_validation_altalexprivacy_runtime": 55.6818,
189
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
190
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
191
+ "step": 1500
192
+ },
193
+ {
194
+ "epoch": 0.09,
195
+ "eval_validation_mc4_it_loss": 1.897855281829834,
196
+ "eval_validation_mc4_it_runtime": 74.5687,
197
+ "eval_validation_mc4_it_samples_per_second": 1.904,
198
+ "eval_validation_mc4_it_steps_per_second": 1.904,
199
+ "step": 1500
200
+ },
201
+ {
202
+ "epoch": 0.11,
203
+ "learning_rate": 1e-05,
204
+ "loss": 1.551,
205
+ "step": 1875
206
+ },
207
+ {
208
+ "epoch": 0.11,
209
+ "eval_validation_privacy_sources_loss": 0.9161506295204163,
210
+ "eval_validation_privacy_sources_runtime": 201.028,
211
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
212
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
213
+ "step": 1875
214
+ },
215
+ {
216
+ "epoch": 0.11,
217
+ "eval_validation_agenda_digitale_loss": 1.4714491367340088,
218
+ "eval_validation_agenda_digitale_runtime": 178.5046,
219
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
220
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
221
+ "step": 1875
222
+ },
223
+ {
224
+ "epoch": 0.11,
225
+ "eval_validation_leggepertutti_loss": 1.349782109260559,
226
+ "eval_validation_leggepertutti_runtime": 34.1218,
227
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
228
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
229
+ "step": 1875
230
+ },
231
+ {
232
+ "epoch": 0.11,
233
+ "eval_validation_altalexprivacy_loss": 1.3038463592529297,
234
+ "eval_validation_altalexprivacy_runtime": 55.6592,
235
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
236
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
237
+ "step": 1875
238
+ },
239
+ {
240
+ "epoch": 0.11,
241
+ "eval_validation_mc4_it_loss": 1.8886678218841553,
242
+ "eval_validation_mc4_it_runtime": 74.5616,
243
+ "eval_validation_mc4_it_samples_per_second": 1.904,
244
+ "eval_validation_mc4_it_steps_per_second": 1.904,
245
+ "step": 1875
246
+ },
247
+ {
248
+ "epoch": 0.14,
249
+ "learning_rate": 1e-05,
250
+ "loss": 1.5334,
251
+ "step": 2250
252
+ },
253
+ {
254
+ "epoch": 0.14,
255
+ "eval_validation_privacy_sources_loss": 0.8999343514442444,
256
+ "eval_validation_privacy_sources_runtime": 201.0719,
257
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
258
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
259
+ "step": 2250
260
+ },
261
+ {
262
+ "epoch": 0.14,
263
+ "eval_validation_agenda_digitale_loss": 1.470467448234558,
264
+ "eval_validation_agenda_digitale_runtime": 178.5136,
265
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
266
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
267
+ "step": 2250
268
+ },
269
+ {
270
+ "epoch": 0.14,
271
+ "eval_validation_leggepertutti_loss": 1.3344582319259644,
272
+ "eval_validation_leggepertutti_runtime": 34.1414,
273
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
274
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
275
+ "step": 2250
276
+ },
277
+ {
278
+ "epoch": 0.14,
279
+ "eval_validation_altalexprivacy_loss": 1.2899404764175415,
280
+ "eval_validation_altalexprivacy_runtime": 55.6737,
281
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
282
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
283
+ "step": 2250
284
+ },
285
+ {
286
+ "epoch": 0.14,
287
+ "eval_validation_mc4_it_loss": 1.8787847757339478,
288
+ "eval_validation_mc4_it_runtime": 74.5812,
289
+ "eval_validation_mc4_it_samples_per_second": 1.904,
290
+ "eval_validation_mc4_it_steps_per_second": 1.904,
291
+ "step": 2250
292
+ },
293
+ {
294
+ "epoch": 0.16,
295
+ "learning_rate": 1e-05,
296
+ "loss": 1.5289,
297
+ "step": 2625
298
+ },
299
+ {
300
+ "epoch": 0.16,
301
+ "eval_validation_privacy_sources_loss": 0.8850609064102173,
302
+ "eval_validation_privacy_sources_runtime": 201.0584,
303
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
304
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
305
+ "step": 2625
306
+ },
307
+ {
308
+ "epoch": 0.16,
309
+ "eval_validation_agenda_digitale_loss": 1.45303213596344,
310
+ "eval_validation_agenda_digitale_runtime": 178.5557,
311
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
312
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
313
+ "step": 2625
314
+ },
315
+ {
316
+ "epoch": 0.16,
317
+ "eval_validation_leggepertutti_loss": 1.3301901817321777,
318
+ "eval_validation_leggepertutti_runtime": 34.1396,
319
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
320
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
321
+ "step": 2625
322
+ },
323
+ {
324
+ "epoch": 0.16,
325
+ "eval_validation_altalexprivacy_loss": 1.2740957736968994,
326
+ "eval_validation_altalexprivacy_runtime": 55.6629,
327
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
328
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
329
+ "step": 2625
330
+ },
331
+ {
332
+ "epoch": 0.16,
333
+ "eval_validation_mc4_it_loss": 1.8664617538452148,
334
+ "eval_validation_mc4_it_runtime": 74.5651,
335
+ "eval_validation_mc4_it_samples_per_second": 1.904,
336
+ "eval_validation_mc4_it_steps_per_second": 1.904,
337
+ "step": 2625
338
+ },
339
+ {
340
+ "epoch": 0.18,
341
+ "learning_rate": 1e-05,
342
+ "loss": 1.5137,
343
+ "step": 3000
344
+ },
345
+ {
346
+ "epoch": 0.18,
347
+ "eval_validation_privacy_sources_loss": 0.8736271858215332,
348
+ "eval_validation_privacy_sources_runtime": 201.0614,
349
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
350
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
351
+ "step": 3000
352
+ },
353
+ {
354
+ "epoch": 0.18,
355
+ "eval_validation_agenda_digitale_loss": 1.4448249340057373,
356
+ "eval_validation_agenda_digitale_runtime": 178.5096,
357
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
358
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
359
+ "step": 3000
360
+ },
361
+ {
362
+ "epoch": 0.18,
363
+ "eval_validation_leggepertutti_loss": 1.3264199495315552,
364
+ "eval_validation_leggepertutti_runtime": 34.1392,
365
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
366
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
367
+ "step": 3000
368
+ },
369
+ {
370
+ "epoch": 0.18,
371
+ "eval_validation_altalexprivacy_loss": 1.2583509683609009,
372
+ "eval_validation_altalexprivacy_runtime": 55.6465,
373
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
374
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
375
+ "step": 3000
376
+ },
377
+ {
378
+ "epoch": 0.18,
379
+ "eval_validation_mc4_it_loss": 1.8547219038009644,
380
+ "eval_validation_mc4_it_runtime": 74.5381,
381
+ "eval_validation_mc4_it_samples_per_second": 1.905,
382
+ "eval_validation_mc4_it_steps_per_second": 1.905,
383
+ "step": 3000
384
+ },
385
+ {
386
+ "epoch": 0.2,
387
+ "learning_rate": 1e-05,
388
+ "loss": 1.5191,
389
+ "step": 3375
390
+ },
391
+ {
392
+ "epoch": 0.2,
393
+ "eval_validation_privacy_sources_loss": 0.8653725385665894,
394
+ "eval_validation_privacy_sources_runtime": 201.0607,
395
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
396
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
397
+ "step": 3375
398
+ },
399
+ {
400
+ "epoch": 0.2,
401
+ "eval_validation_agenda_digitale_loss": 1.437347173690796,
402
+ "eval_validation_agenda_digitale_runtime": 178.5114,
403
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
404
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
405
+ "step": 3375
406
+ },
407
+ {
408
+ "epoch": 0.2,
409
+ "eval_validation_leggepertutti_loss": 1.3095436096191406,
410
+ "eval_validation_leggepertutti_runtime": 34.1234,
411
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
412
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
413
+ "step": 3375
414
+ },
415
+ {
416
+ "epoch": 0.2,
417
+ "eval_validation_altalexprivacy_loss": 1.24440336227417,
418
+ "eval_validation_altalexprivacy_runtime": 55.6399,
419
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
420
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
421
+ "step": 3375
422
+ },
423
+ {
424
+ "epoch": 0.2,
425
+ "eval_validation_mc4_it_loss": 1.8478875160217285,
426
+ "eval_validation_mc4_it_runtime": 74.5544,
427
+ "eval_validation_mc4_it_samples_per_second": 1.905,
428
+ "eval_validation_mc4_it_steps_per_second": 1.905,
429
+ "step": 3375
430
+ },
431
+ {
432
+ "epoch": 0.23,
433
+ "learning_rate": 1e-05,
434
+ "loss": 1.5014,
435
+ "step": 3750
436
+ },
437
+ {
438
+ "epoch": 0.23,
439
+ "eval_validation_privacy_sources_loss": 0.866100013256073,
440
+ "eval_validation_privacy_sources_runtime": 201.0279,
441
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
442
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
443
+ "step": 3750
444
+ },
445
+ {
446
+ "epoch": 0.23,
447
+ "eval_validation_agenda_digitale_loss": 1.4383131265640259,
448
+ "eval_validation_agenda_digitale_runtime": 178.5206,
449
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
450
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
451
+ "step": 3750
452
+ },
453
+ {
454
+ "epoch": 0.23,
455
+ "eval_validation_leggepertutti_loss": 1.3121819496154785,
456
+ "eval_validation_leggepertutti_runtime": 34.1311,
457
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
458
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
459
+ "step": 3750
460
+ },
461
+ {
462
+ "epoch": 0.23,
463
+ "eval_validation_altalexprivacy_loss": 1.2500646114349365,
464
+ "eval_validation_altalexprivacy_runtime": 55.6505,
465
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
466
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
467
+ "step": 3750
468
+ },
469
+ {
470
+ "epoch": 0.23,
471
+ "eval_validation_mc4_it_loss": 1.8457143306732178,
472
+ "eval_validation_mc4_it_runtime": 74.5581,
473
+ "eval_validation_mc4_it_samples_per_second": 1.905,
474
+ "eval_validation_mc4_it_steps_per_second": 1.905,
475
+ "step": 3750
476
+ },
477
+ {
478
+ "epoch": 0.25,
479
+ "learning_rate": 1e-05,
480
+ "loss": 1.4925,
481
+ "step": 4125
482
+ },
483
+ {
484
+ "epoch": 0.25,
485
+ "eval_validation_privacy_sources_loss": 0.8534922003746033,
486
+ "eval_validation_privacy_sources_runtime": 201.0002,
487
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
488
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
489
+ "step": 4125
490
+ },
491
+ {
492
+ "epoch": 0.25,
493
+ "eval_validation_agenda_digitale_loss": 1.426421046257019,
494
+ "eval_validation_agenda_digitale_runtime": 178.5283,
495
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
496
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
497
+ "step": 4125
498
+ },
499
+ {
500
+ "epoch": 0.25,
501
+ "eval_validation_leggepertutti_loss": 1.3124033212661743,
502
+ "eval_validation_leggepertutti_runtime": 34.1225,
503
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
504
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
505
+ "step": 4125
506
+ },
507
+ {
508
+ "epoch": 0.25,
509
+ "eval_validation_altalexprivacy_loss": 1.2354837656021118,
510
+ "eval_validation_altalexprivacy_runtime": 55.6534,
511
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
512
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
513
+ "step": 4125
514
+ },
515
+ {
516
+ "epoch": 0.25,
517
+ "eval_validation_mc4_it_loss": 1.839884638786316,
518
+ "eval_validation_mc4_it_runtime": 74.5669,
519
+ "eval_validation_mc4_it_samples_per_second": 1.904,
520
+ "eval_validation_mc4_it_steps_per_second": 1.904,
521
+ "step": 4125
522
+ },
523
+ {
524
+ "epoch": 0.27,
525
+ "learning_rate": 1e-05,
526
+ "loss": 1.4953,
527
+ "step": 4500
528
+ },
529
+ {
530
+ "epoch": 0.27,
531
+ "eval_validation_privacy_sources_loss": 0.849433422088623,
532
+ "eval_validation_privacy_sources_runtime": 201.0776,
533
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
534
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
535
+ "step": 4500
536
+ },
537
+ {
538
+ "epoch": 0.27,
539
+ "eval_validation_agenda_digitale_loss": 1.4208179712295532,
540
+ "eval_validation_agenda_digitale_runtime": 178.5663,
541
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
542
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
543
+ "step": 4500
544
+ },
545
+ {
546
+ "epoch": 0.27,
547
+ "eval_validation_leggepertutti_loss": 1.3129136562347412,
548
+ "eval_validation_leggepertutti_runtime": 34.1427,
549
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
550
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
551
+ "step": 4500
552
+ },
553
+ {
554
+ "epoch": 0.27,
555
+ "eval_validation_altalexprivacy_loss": 1.2299654483795166,
556
+ "eval_validation_altalexprivacy_runtime": 55.664,
557
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
558
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
559
+ "step": 4500
560
+ },
561
+ {
562
+ "epoch": 0.27,
563
+ "eval_validation_mc4_it_loss": 1.8318015336990356,
564
+ "eval_validation_mc4_it_runtime": 74.5767,
565
+ "eval_validation_mc4_it_samples_per_second": 1.904,
566
+ "eval_validation_mc4_it_steps_per_second": 1.904,
567
+ "step": 4500
568
+ },
569
+ {
570
+ "epoch": 0.29,
571
+ "learning_rate": 1e-05,
572
+ "loss": 1.4874,
573
+ "step": 4875
574
+ },
575
+ {
576
+ "epoch": 0.29,
577
+ "eval_validation_privacy_sources_loss": 0.841759979724884,
578
+ "eval_validation_privacy_sources_runtime": 201.1289,
579
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
580
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
581
+ "step": 4875
582
+ },
583
+ {
584
+ "epoch": 0.29,
585
+ "eval_validation_agenda_digitale_loss": 1.416318655014038,
586
+ "eval_validation_agenda_digitale_runtime": 178.5543,
587
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
588
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
589
+ "step": 4875
590
+ },
591
+ {
592
+ "epoch": 0.29,
593
+ "eval_validation_leggepertutti_loss": 1.3116254806518555,
594
+ "eval_validation_leggepertutti_runtime": 34.142,
595
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
596
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
597
+ "step": 4875
598
+ },
599
+ {
600
+ "epoch": 0.29,
601
+ "eval_validation_altalexprivacy_loss": 1.2154171466827393,
602
+ "eval_validation_altalexprivacy_runtime": 55.6852,
603
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
604
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
605
+ "step": 4875
606
+ },
607
+ {
608
+ "epoch": 0.29,
609
+ "eval_validation_mc4_it_loss": 1.8277841806411743,
610
+ "eval_validation_mc4_it_runtime": 74.593,
611
+ "eval_validation_mc4_it_samples_per_second": 1.904,
612
+ "eval_validation_mc4_it_steps_per_second": 1.904,
613
+ "step": 4875
614
+ },
615
+ {
616
+ "epoch": 0.32,
617
+ "learning_rate": 1e-05,
618
+ "loss": 1.4732,
619
+ "step": 5250
620
+ },
621
+ {
622
+ "epoch": 0.32,
623
+ "eval_validation_privacy_sources_loss": 0.8383973240852356,
624
+ "eval_validation_privacy_sources_runtime": 201.1658,
625
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
626
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
627
+ "step": 5250
628
+ },
629
+ {
630
+ "epoch": 0.32,
631
+ "eval_validation_agenda_digitale_loss": 1.4164748191833496,
632
+ "eval_validation_agenda_digitale_runtime": 178.5933,
633
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
634
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
635
+ "step": 5250
636
+ },
637
+ {
638
+ "epoch": 0.32,
639
+ "eval_validation_leggepertutti_loss": 1.306440830230713,
640
+ "eval_validation_leggepertutti_runtime": 34.1439,
641
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
642
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
643
+ "step": 5250
644
+ },
645
+ {
646
+ "epoch": 0.32,
647
+ "eval_validation_altalexprivacy_loss": 1.218838095664978,
648
+ "eval_validation_altalexprivacy_runtime": 55.6909,
649
+ "eval_validation_altalexprivacy_samples_per_second": 1.903,
650
+ "eval_validation_altalexprivacy_steps_per_second": 1.903,
651
+ "step": 5250
652
+ },
653
+ {
654
+ "epoch": 0.32,
655
+ "eval_validation_mc4_it_loss": 1.8245536088943481,
656
+ "eval_validation_mc4_it_runtime": 74.6076,
657
+ "eval_validation_mc4_it_samples_per_second": 1.903,
658
+ "eval_validation_mc4_it_steps_per_second": 1.903,
659
+ "step": 5250
660
+ },
661
+ {
662
+ "epoch": 0.34,
663
+ "learning_rate": 1e-05,
664
+ "loss": 1.4802,
665
+ "step": 5625
666
+ },
667
+ {
668
+ "epoch": 0.34,
669
+ "eval_validation_privacy_sources_loss": 0.8325279951095581,
670
+ "eval_validation_privacy_sources_runtime": 201.1527,
671
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
672
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
673
+ "step": 5625
674
+ },
675
+ {
676
+ "epoch": 0.34,
677
+ "eval_validation_agenda_digitale_loss": 1.4099715948104858,
678
+ "eval_validation_agenda_digitale_runtime": 178.591,
679
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
680
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
681
+ "step": 5625
682
+ },
683
+ {
684
+ "epoch": 0.34,
685
+ "eval_validation_leggepertutti_loss": 1.30331552028656,
686
+ "eval_validation_leggepertutti_runtime": 34.1424,
687
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
688
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
689
+ "step": 5625
690
+ },
691
+ {
692
+ "epoch": 0.34,
693
+ "eval_validation_altalexprivacy_loss": 1.2109583616256714,
694
+ "eval_validation_altalexprivacy_runtime": 55.6849,
695
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
696
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
697
+ "step": 5625
698
+ },
699
+ {
700
+ "epoch": 0.34,
701
+ "eval_validation_mc4_it_loss": 1.8209081888198853,
702
+ "eval_validation_mc4_it_runtime": 74.6027,
703
+ "eval_validation_mc4_it_samples_per_second": 1.903,
704
+ "eval_validation_mc4_it_steps_per_second": 1.903,
705
+ "step": 5625
706
+ },
707
+ {
708
+ "epoch": 0.36,
709
+ "learning_rate": 1e-05,
710
+ "loss": 1.4593,
711
+ "step": 6000
712
+ },
713
+ {
714
+ "epoch": 0.36,
715
+ "eval_validation_privacy_sources_loss": 0.8251636028289795,
716
+ "eval_validation_privacy_sources_runtime": 201.1198,
717
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
718
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
719
+ "step": 6000
720
+ },
721
+ {
722
+ "epoch": 0.36,
723
+ "eval_validation_agenda_digitale_loss": 1.4080655574798584,
724
+ "eval_validation_agenda_digitale_runtime": 178.6071,
725
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
726
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
727
+ "step": 6000
728
+ },
729
+ {
730
+ "epoch": 0.36,
731
+ "eval_validation_leggepertutti_loss": 1.3091273307800293,
732
+ "eval_validation_leggepertutti_runtime": 34.1414,
733
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
734
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
735
+ "step": 6000
736
+ },
737
+ {
738
+ "epoch": 0.36,
739
+ "eval_validation_altalexprivacy_loss": 1.2088643312454224,
740
+ "eval_validation_altalexprivacy_runtime": 55.6807,
741
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
742
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
743
+ "step": 6000
744
+ },
745
+ {
746
+ "epoch": 0.36,
747
+ "eval_validation_mc4_it_loss": 1.8172013759613037,
748
+ "eval_validation_mc4_it_runtime": 74.5793,
749
+ "eval_validation_mc4_it_samples_per_second": 1.904,
750
+ "eval_validation_mc4_it_steps_per_second": 1.904,
751
+ "step": 6000
752
+ },
753
+ {
754
+ "epoch": 0.39,
755
+ "learning_rate": 1e-05,
756
+ "loss": 1.4548,
757
+ "step": 6375
758
+ },
759
+ {
760
+ "epoch": 0.39,
761
+ "eval_validation_privacy_sources_loss": 0.8178727030754089,
762
+ "eval_validation_privacy_sources_runtime": 201.1666,
763
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
764
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
765
+ "step": 6375
766
+ },
767
+ {
768
+ "epoch": 0.39,
769
+ "eval_validation_agenda_digitale_loss": 1.4031239748001099,
770
+ "eval_validation_agenda_digitale_runtime": 178.5499,
771
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
772
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
773
+ "step": 6375
774
+ },
775
+ {
776
+ "epoch": 0.39,
777
+ "eval_validation_leggepertutti_loss": 1.3012996912002563,
778
+ "eval_validation_leggepertutti_runtime": 34.1355,
779
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
780
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
781
+ "step": 6375
782
+ },
783
+ {
784
+ "epoch": 0.39,
785
+ "eval_validation_altalexprivacy_loss": 1.2039263248443604,
786
+ "eval_validation_altalexprivacy_runtime": 55.6853,
787
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
788
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
789
+ "step": 6375
790
+ },
791
+ {
792
+ "epoch": 0.39,
793
+ "eval_validation_mc4_it_loss": 1.8110533952713013,
794
+ "eval_validation_mc4_it_runtime": 74.5796,
795
+ "eval_validation_mc4_it_samples_per_second": 1.904,
796
+ "eval_validation_mc4_it_steps_per_second": 1.904,
797
+ "step": 6375
798
+ },
799
+ {
800
+ "epoch": 0.41,
801
+ "learning_rate": 1e-05,
802
+ "loss": 1.4632,
803
+ "step": 6750
804
+ },
805
+ {
806
+ "epoch": 0.41,
807
+ "eval_validation_privacy_sources_loss": 0.8175713419914246,
808
+ "eval_validation_privacy_sources_runtime": 201.1217,
809
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
810
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
811
+ "step": 6750
812
+ },
813
+ {
814
+ "epoch": 0.41,
815
+ "eval_validation_agenda_digitale_loss": 1.400506615638733,
816
+ "eval_validation_agenda_digitale_runtime": 178.5782,
817
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
818
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
819
+ "step": 6750
820
+ },
821
+ {
822
+ "epoch": 0.41,
823
+ "eval_validation_leggepertutti_loss": 1.309232473373413,
824
+ "eval_validation_leggepertutti_runtime": 34.1571,
825
+ "eval_validation_leggepertutti_samples_per_second": 1.903,
826
+ "eval_validation_leggepertutti_steps_per_second": 1.903,
827
+ "step": 6750
828
+ },
829
+ {
830
+ "epoch": 0.41,
831
+ "eval_validation_altalexprivacy_loss": 1.2150640487670898,
832
+ "eval_validation_altalexprivacy_runtime": 55.6852,
833
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
834
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
835
+ "step": 6750
836
+ },
837
+ {
838
+ "epoch": 0.41,
839
+ "eval_validation_mc4_it_loss": 1.8074498176574707,
840
+ "eval_validation_mc4_it_runtime": 74.6076,
841
+ "eval_validation_mc4_it_samples_per_second": 1.903,
842
+ "eval_validation_mc4_it_steps_per_second": 1.903,
843
+ "step": 6750
844
+ },
845
+ {
846
+ "epoch": 0.43,
847
+ "learning_rate": 1e-05,
848
+ "loss": 1.4552,
849
+ "step": 7125
850
+ },
851
+ {
852
+ "epoch": 0.43,
853
+ "eval_validation_privacy_sources_loss": 0.8120561838150024,
854
+ "eval_validation_privacy_sources_runtime": 201.1152,
855
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
856
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
857
+ "step": 7125
858
+ },
859
+ {
860
+ "epoch": 0.43,
861
+ "eval_validation_agenda_digitale_loss": 1.4063242673873901,
862
+ "eval_validation_agenda_digitale_runtime": 178.5089,
863
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
864
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
865
+ "step": 7125
866
+ },
867
+ {
868
+ "epoch": 0.43,
869
+ "eval_validation_leggepertutti_loss": 1.308206558227539,
870
+ "eval_validation_leggepertutti_runtime": 34.1455,
871
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
872
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
873
+ "step": 7125
874
+ },
875
+ {
876
+ "epoch": 0.43,
877
+ "eval_validation_altalexprivacy_loss": 1.2067214250564575,
878
+ "eval_validation_altalexprivacy_runtime": 55.6756,
879
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
880
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
881
+ "step": 7125
882
+ },
883
+ {
884
+ "epoch": 0.43,
885
+ "eval_validation_mc4_it_loss": 1.8089640140533447,
886
+ "eval_validation_mc4_it_runtime": 74.5767,
887
+ "eval_validation_mc4_it_samples_per_second": 1.904,
888
+ "eval_validation_mc4_it_steps_per_second": 1.904,
889
+ "step": 7125
890
+ },
891
+ {
892
+ "epoch": 0.45,
893
+ "learning_rate": 1e-05,
894
+ "loss": 1.4483,
895
+ "step": 7500
896
+ },
897
+ {
898
+ "epoch": 0.45,
899
+ "eval_validation_privacy_sources_loss": 0.8069853782653809,
900
+ "eval_validation_privacy_sources_runtime": 201.0802,
901
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
902
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
903
+ "step": 7500
904
+ },
905
+ {
906
+ "epoch": 0.45,
907
+ "eval_validation_agenda_digitale_loss": 1.3969142436981201,
908
+ "eval_validation_agenda_digitale_runtime": 178.554,
909
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
910
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
911
+ "step": 7500
912
+ },
913
+ {
914
+ "epoch": 0.45,
915
+ "eval_validation_leggepertutti_loss": 1.3084008693695068,
916
+ "eval_validation_leggepertutti_runtime": 34.1363,
917
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
918
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
919
+ "step": 7500
920
+ },
921
+ {
922
+ "epoch": 0.45,
923
+ "eval_validation_altalexprivacy_loss": 1.2030524015426636,
924
+ "eval_validation_altalexprivacy_runtime": 55.665,
925
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
926
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
927
+ "step": 7500
928
+ },
929
+ {
930
+ "epoch": 0.45,
931
+ "eval_validation_mc4_it_loss": 1.8052242994308472,
932
+ "eval_validation_mc4_it_runtime": 74.5713,
933
+ "eval_validation_mc4_it_samples_per_second": 1.904,
934
+ "eval_validation_mc4_it_steps_per_second": 1.904,
935
+ "step": 7500
936
+ },
937
+ {
938
+ "epoch": 0.48,
939
+ "learning_rate": 1e-05,
940
+ "loss": 1.4517,
941
+ "step": 7875
942
+ },
943
+ {
944
+ "epoch": 0.48,
945
+ "eval_validation_privacy_sources_loss": 0.8065386414527893,
946
+ "eval_validation_privacy_sources_runtime": 201.0916,
947
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
948
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
949
+ "step": 7875
950
+ },
951
+ {
952
+ "epoch": 0.48,
953
+ "eval_validation_agenda_digitale_loss": 1.3922195434570312,
954
+ "eval_validation_agenda_digitale_runtime": 178.5089,
955
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
956
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
957
+ "step": 7875
958
+ },
959
+ {
960
+ "epoch": 0.48,
961
+ "eval_validation_leggepertutti_loss": 1.3103892803192139,
962
+ "eval_validation_leggepertutti_runtime": 34.131,
963
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
964
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
965
+ "step": 7875
966
+ },
967
+ {
968
+ "epoch": 0.48,
969
+ "eval_validation_altalexprivacy_loss": 1.1936033964157104,
970
+ "eval_validation_altalexprivacy_runtime": 55.6533,
971
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
972
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
973
+ "step": 7875
974
+ },
975
+ {
976
+ "epoch": 0.48,
977
+ "eval_validation_mc4_it_loss": 1.798509120941162,
978
+ "eval_validation_mc4_it_runtime": 74.566,
979
+ "eval_validation_mc4_it_samples_per_second": 1.904,
980
+ "eval_validation_mc4_it_steps_per_second": 1.904,
981
+ "step": 7875
982
+ },
983
+ {
984
+ "epoch": 0.5,
985
+ "learning_rate": 1e-05,
986
+ "loss": 1.4471,
987
+ "step": 8250
988
+ },
989
+ {
990
+ "epoch": 0.5,
991
+ "eval_validation_privacy_sources_loss": 0.800136148929596,
992
+ "eval_validation_privacy_sources_runtime": 201.0553,
993
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
994
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
995
+ "step": 8250
996
+ },
997
+ {
998
+ "epoch": 0.5,
999
+ "eval_validation_agenda_digitale_loss": 1.3954713344573975,
1000
+ "eval_validation_agenda_digitale_runtime": 178.5066,
1001
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1002
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1003
+ "step": 8250
1004
+ },
1005
+ {
1006
+ "epoch": 0.5,
1007
+ "eval_validation_leggepertutti_loss": 1.307741403579712,
1008
+ "eval_validation_leggepertutti_runtime": 34.1429,
1009
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
1010
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
1011
+ "step": 8250
1012
+ },
1013
+ {
1014
+ "epoch": 0.5,
1015
+ "eval_validation_altalexprivacy_loss": 1.1900213956832886,
1016
+ "eval_validation_altalexprivacy_runtime": 55.6455,
1017
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
1018
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
1019
+ "step": 8250
1020
+ },
1021
+ {
1022
+ "epoch": 0.5,
1023
+ "eval_validation_mc4_it_loss": 1.7979615926742554,
1024
+ "eval_validation_mc4_it_runtime": 74.5424,
1025
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1026
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1027
+ "step": 8250
1028
+ },
1029
+ {
1030
+ "epoch": 0.52,
1031
+ "learning_rate": 1e-05,
1032
+ "loss": 1.4507,
1033
+ "step": 8625
1034
+ },
1035
+ {
1036
+ "epoch": 0.52,
1037
+ "eval_validation_privacy_sources_loss": 0.7995487451553345,
1038
+ "eval_validation_privacy_sources_runtime": 201.0023,
1039
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1040
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1041
+ "step": 8625
1042
+ },
1043
+ {
1044
+ "epoch": 0.52,
1045
+ "eval_validation_agenda_digitale_loss": 1.399002194404602,
1046
+ "eval_validation_agenda_digitale_runtime": 178.4541,
1047
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1048
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1049
+ "step": 8625
1050
+ },
1051
+ {
1052
+ "epoch": 0.52,
1053
+ "eval_validation_leggepertutti_loss": 1.3205926418304443,
1054
+ "eval_validation_leggepertutti_runtime": 34.1184,
1055
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
1056
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
1057
+ "step": 8625
1058
+ },
1059
+ {
1060
+ "epoch": 0.52,
1061
+ "eval_validation_altalexprivacy_loss": 1.1914081573486328,
1062
+ "eval_validation_altalexprivacy_runtime": 55.627,
1063
+ "eval_validation_altalexprivacy_samples_per_second": 1.906,
1064
+ "eval_validation_altalexprivacy_steps_per_second": 1.906,
1065
+ "step": 8625
1066
+ },
1067
+ {
1068
+ "epoch": 0.52,
1069
+ "eval_validation_mc4_it_loss": 1.7979826927185059,
1070
+ "eval_validation_mc4_it_runtime": 74.5323,
1071
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1072
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1073
+ "step": 8625
1074
+ },
1075
+ {
1076
+ "epoch": 0.54,
1077
+ "learning_rate": 1e-05,
1078
+ "loss": 1.4443,
1079
+ "step": 9000
1080
+ },
1081
+ {
1082
+ "epoch": 0.54,
1083
+ "eval_validation_privacy_sources_loss": 0.792545735836029,
1084
+ "eval_validation_privacy_sources_runtime": 201.0153,
1085
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1086
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1087
+ "step": 9000
1088
+ },
1089
+ {
1090
+ "epoch": 0.54,
1091
+ "eval_validation_agenda_digitale_loss": 1.3885917663574219,
1092
+ "eval_validation_agenda_digitale_runtime": 178.4592,
1093
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1094
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1095
+ "step": 9000
1096
+ },
1097
+ {
1098
+ "epoch": 0.54,
1099
+ "eval_validation_leggepertutti_loss": 1.3087489604949951,
1100
+ "eval_validation_leggepertutti_runtime": 34.119,
1101
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
1102
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
1103
+ "step": 9000
1104
+ },
1105
+ {
1106
+ "epoch": 0.54,
1107
+ "eval_validation_altalexprivacy_loss": 1.1843422651290894,
1108
+ "eval_validation_altalexprivacy_runtime": 55.6292,
1109
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
1110
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
1111
+ "step": 9000
1112
+ },
1113
+ {
1114
+ "epoch": 0.54,
1115
+ "eval_validation_mc4_it_loss": 1.7959390878677368,
1116
+ "eval_validation_mc4_it_runtime": 74.5352,
1117
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1118
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1119
+ "step": 9000
1120
+ },
1121
+ {
1122
+ "epoch": 0.57,
1123
+ "learning_rate": 1e-05,
1124
+ "loss": 1.4414,
1125
+ "step": 9375
1126
+ },
1127
+ {
1128
+ "epoch": 0.57,
1129
+ "eval_validation_privacy_sources_loss": 0.7874200344085693,
1130
+ "eval_validation_privacy_sources_runtime": 200.9921,
1131
+ "eval_validation_privacy_sources_samples_per_second": 1.906,
1132
+ "eval_validation_privacy_sources_steps_per_second": 1.906,
1133
+ "step": 9375
1134
+ },
1135
+ {
1136
+ "epoch": 0.57,
1137
+ "eval_validation_agenda_digitale_loss": 1.384313941001892,
1138
+ "eval_validation_agenda_digitale_runtime": 178.4792,
1139
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1140
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1141
+ "step": 9375
1142
+ },
1143
+ {
1144
+ "epoch": 0.57,
1145
+ "eval_validation_leggepertutti_loss": 1.3108775615692139,
1146
+ "eval_validation_leggepertutti_runtime": 34.1238,
1147
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
1148
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
1149
+ "step": 9375
1150
+ },
1151
+ {
1152
+ "epoch": 0.57,
1153
+ "eval_validation_altalexprivacy_loss": 1.1870638132095337,
1154
+ "eval_validation_altalexprivacy_runtime": 55.6364,
1155
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
1156
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
1157
+ "step": 9375
1158
+ },
1159
+ {
1160
+ "epoch": 0.57,
1161
+ "eval_validation_mc4_it_loss": 1.7907894849777222,
1162
+ "eval_validation_mc4_it_runtime": 74.5431,
1163
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1164
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1165
+ "step": 9375
1166
+ },
1167
+ {
1168
+ "epoch": 0.59,
1169
+ "learning_rate": 1e-05,
1170
+ "loss": 1.433,
1171
+ "step": 9750
1172
+ },
1173
+ {
1174
+ "epoch": 0.59,
1175
+ "eval_validation_privacy_sources_loss": 0.7924759984016418,
1176
+ "eval_validation_privacy_sources_runtime": 201.0344,
1177
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1178
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1179
+ "step": 9750
1180
+ },
1181
+ {
1182
+ "epoch": 0.59,
1183
+ "eval_validation_agenda_digitale_loss": 1.3898183107376099,
1184
+ "eval_validation_agenda_digitale_runtime": 178.4614,
1185
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1186
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1187
+ "step": 9750
1188
+ },
1189
+ {
1190
+ "epoch": 0.59,
1191
+ "eval_validation_leggepertutti_loss": 1.3060747385025024,
1192
+ "eval_validation_leggepertutti_runtime": 34.1209,
1193
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
1194
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
1195
+ "step": 9750
1196
+ },
1197
+ {
1198
+ "epoch": 0.59,
1199
+ "eval_validation_altalexprivacy_loss": 1.185739278793335,
1200
+ "eval_validation_altalexprivacy_runtime": 55.6652,
1201
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
1202
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
1203
+ "step": 9750
1204
+ },
1205
+ {
1206
+ "epoch": 0.59,
1207
+ "eval_validation_mc4_it_loss": 1.791359782218933,
1208
+ "eval_validation_mc4_it_runtime": 74.5272,
1209
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1210
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1211
+ "step": 9750
1212
+ },
1213
+ {
1214
+ "epoch": 0.61,
1215
+ "learning_rate": 1e-05,
1216
+ "loss": 1.4242,
1217
+ "step": 10125
1218
+ },
1219
+ {
1220
+ "epoch": 0.61,
1221
+ "eval_validation_privacy_sources_loss": 0.7808073163032532,
1222
+ "eval_validation_privacy_sources_runtime": 201.0669,
1223
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1224
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1225
+ "step": 10125
1226
+ },
1227
+ {
1228
+ "epoch": 0.61,
1229
+ "eval_validation_agenda_digitale_loss": 1.3824373483657837,
1230
+ "eval_validation_agenda_digitale_runtime": 178.5205,
1231
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1232
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1233
+ "step": 10125
1234
+ },
1235
+ {
1236
+ "epoch": 0.61,
1237
+ "eval_validation_leggepertutti_loss": 1.3063251972198486,
1238
+ "eval_validation_leggepertutti_runtime": 34.12,
1239
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
1240
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
1241
+ "step": 10125
1242
+ },
1243
+ {
1244
+ "epoch": 0.61,
1245
+ "eval_validation_altalexprivacy_loss": 1.1804792881011963,
1246
+ "eval_validation_altalexprivacy_runtime": 55.6373,
1247
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
1248
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
1249
+ "step": 10125
1250
+ },
1251
+ {
1252
+ "epoch": 0.61,
1253
+ "eval_validation_mc4_it_loss": 1.7866684198379517,
1254
+ "eval_validation_mc4_it_runtime": 74.5309,
1255
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1256
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1257
+ "step": 10125
1258
+ },
1259
+ {
1260
+ "epoch": 0.63,
1261
+ "learning_rate": 1e-05,
1262
+ "loss": 1.4326,
1263
+ "step": 10500
1264
+ },
1265
+ {
1266
+ "epoch": 0.63,
1267
+ "eval_validation_privacy_sources_loss": 0.7777509689331055,
1268
+ "eval_validation_privacy_sources_runtime": 201.0374,
1269
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1270
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1271
+ "step": 10500
1272
+ },
1273
+ {
1274
+ "epoch": 0.63,
1275
+ "eval_validation_agenda_digitale_loss": 1.379618763923645,
1276
+ "eval_validation_agenda_digitale_runtime": 178.5258,
1277
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
1278
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
1279
+ "step": 10500
1280
+ },
1281
+ {
1282
+ "epoch": 0.63,
1283
+ "eval_validation_leggepertutti_loss": 1.295432448387146,
1284
+ "eval_validation_leggepertutti_runtime": 34.132,
1285
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
1286
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
1287
+ "step": 10500
1288
+ },
1289
+ {
1290
+ "epoch": 0.63,
1291
+ "eval_validation_altalexprivacy_loss": 1.1772747039794922,
1292
+ "eval_validation_altalexprivacy_runtime": 55.6589,
1293
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
1294
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
1295
+ "step": 10500
1296
+ },
1297
+ {
1298
+ "epoch": 0.63,
1299
+ "eval_validation_mc4_it_loss": 1.7828530073165894,
1300
+ "eval_validation_mc4_it_runtime": 74.5782,
1301
+ "eval_validation_mc4_it_samples_per_second": 1.904,
1302
+ "eval_validation_mc4_it_steps_per_second": 1.904,
1303
+ "step": 10500
1304
+ },
1305
+ {
1306
+ "epoch": 0.66,
1307
+ "learning_rate": 1e-05,
1308
+ "loss": 1.4338,
1309
+ "step": 10875
1310
+ },
1311
+ {
1312
+ "epoch": 0.66,
1313
+ "eval_validation_privacy_sources_loss": 0.7794314622879028,
1314
+ "eval_validation_privacy_sources_runtime": 201.0921,
1315
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1316
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1317
+ "step": 10875
1318
+ },
1319
+ {
1320
+ "epoch": 0.66,
1321
+ "eval_validation_agenda_digitale_loss": 1.377228021621704,
1322
+ "eval_validation_agenda_digitale_runtime": 178.5817,
1323
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
1324
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
1325
+ "step": 10875
1326
+ },
1327
+ {
1328
+ "epoch": 0.66,
1329
+ "eval_validation_leggepertutti_loss": 1.297864556312561,
1330
+ "eval_validation_leggepertutti_runtime": 34.1259,
1331
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
1332
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
1333
+ "step": 10875
1334
+ },
1335
+ {
1336
+ "epoch": 0.66,
1337
+ "eval_validation_altalexprivacy_loss": 1.1749671697616577,
1338
+ "eval_validation_altalexprivacy_runtime": 55.6732,
1339
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
1340
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
1341
+ "step": 10875
1342
+ },
1343
+ {
1344
+ "epoch": 0.66,
1345
+ "eval_validation_mc4_it_loss": 1.783444881439209,
1346
+ "eval_validation_mc4_it_runtime": 74.5529,
1347
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1348
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1349
+ "step": 10875
1350
+ },
1351
+ {
1352
+ "epoch": 0.68,
1353
+ "learning_rate": 1e-05,
1354
+ "loss": 1.4256,
1355
+ "step": 11250
1356
+ },
1357
+ {
1358
+ "epoch": 0.68,
1359
+ "eval_validation_privacy_sources_loss": 0.7760239839553833,
1360
+ "eval_validation_privacy_sources_runtime": 201.0466,
1361
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1362
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1363
+ "step": 11250
1364
+ },
1365
+ {
1366
+ "epoch": 0.68,
1367
+ "eval_validation_agenda_digitale_loss": 1.3752855062484741,
1368
+ "eval_validation_agenda_digitale_runtime": 178.4787,
1369
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1370
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1371
+ "step": 11250
1372
+ },
1373
+ {
1374
+ "epoch": 0.68,
1375
+ "eval_validation_leggepertutti_loss": 1.2967567443847656,
1376
+ "eval_validation_leggepertutti_runtime": 34.1193,
1377
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
1378
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
1379
+ "step": 11250
1380
+ },
1381
+ {
1382
+ "epoch": 0.68,
1383
+ "eval_validation_altalexprivacy_loss": 1.1724153757095337,
1384
+ "eval_validation_altalexprivacy_runtime": 55.6586,
1385
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
1386
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
1387
+ "step": 11250
1388
+ },
1389
+ {
1390
+ "epoch": 0.68,
1391
+ "eval_validation_mc4_it_loss": 1.7826387882232666,
1392
+ "eval_validation_mc4_it_runtime": 74.5463,
1393
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1394
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1395
+ "step": 11250
1396
+ },
1397
+ {
1398
+ "epoch": 0.7,
1399
+ "learning_rate": 1e-05,
1400
+ "loss": 1.4268,
1401
+ "step": 11625
1402
+ },
1403
+ {
1404
+ "epoch": 0.7,
1405
+ "eval_validation_privacy_sources_loss": 0.774089515209198,
1406
+ "eval_validation_privacy_sources_runtime": 201.0626,
1407
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1408
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1409
+ "step": 11625
1410
+ },
1411
+ {
1412
+ "epoch": 0.7,
1413
+ "eval_validation_agenda_digitale_loss": 1.3730041980743408,
1414
+ "eval_validation_agenda_digitale_runtime": 178.5135,
1415
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1416
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1417
+ "step": 11625
1418
+ },
1419
+ {
1420
+ "epoch": 0.7,
1421
+ "eval_validation_leggepertutti_loss": 1.2966502904891968,
1422
+ "eval_validation_leggepertutti_runtime": 34.1312,
1423
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
1424
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
1425
+ "step": 11625
1426
+ },
1427
+ {
1428
+ "epoch": 0.7,
1429
+ "eval_validation_altalexprivacy_loss": 1.1657850742340088,
1430
+ "eval_validation_altalexprivacy_runtime": 55.6676,
1431
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
1432
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
1433
+ "step": 11625
1434
+ },
1435
+ {
1436
+ "epoch": 0.7,
1437
+ "eval_validation_mc4_it_loss": 1.779410719871521,
1438
+ "eval_validation_mc4_it_runtime": 74.5539,
1439
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1440
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1441
+ "step": 11625
1442
+ },
1443
+ {
1444
+ "epoch": 0.73,
1445
+ "learning_rate": 1e-05,
1446
+ "loss": 1.4261,
1447
+ "step": 12000
1448
+ },
1449
+ {
1450
+ "epoch": 0.73,
1451
+ "eval_validation_privacy_sources_loss": 0.7726185321807861,
1452
+ "eval_validation_privacy_sources_runtime": 201.1083,
1453
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
1454
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
1455
+ "step": 12000
1456
+ },
1457
+ {
1458
+ "epoch": 0.73,
1459
+ "eval_validation_agenda_digitale_loss": 1.3718849420547485,
1460
+ "eval_validation_agenda_digitale_runtime": 178.546,
1461
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
1462
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
1463
+ "step": 12000
1464
+ },
1465
+ {
1466
+ "epoch": 0.73,
1467
+ "eval_validation_leggepertutti_loss": 1.2959471940994263,
1468
+ "eval_validation_leggepertutti_runtime": 34.1289,
1469
+ "eval_validation_leggepertutti_samples_per_second": 1.905,
1470
+ "eval_validation_leggepertutti_steps_per_second": 1.905,
1471
+ "step": 12000
1472
+ },
1473
+ {
1474
+ "epoch": 0.73,
1475
+ "eval_validation_altalexprivacy_loss": 1.1594833135604858,
1476
+ "eval_validation_altalexprivacy_runtime": 55.6758,
1477
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
1478
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
1479
+ "step": 12000
1480
+ },
1481
+ {
1482
+ "epoch": 0.73,
1483
+ "eval_validation_mc4_it_loss": 1.778807520866394,
1484
+ "eval_validation_mc4_it_runtime": 74.5604,
1485
+ "eval_validation_mc4_it_samples_per_second": 1.904,
1486
+ "eval_validation_mc4_it_steps_per_second": 1.904,
1487
+ "step": 12000
1488
+ },
1489
+ {
1490
+ "epoch": 0.75,
1491
+ "learning_rate": 1e-05,
1492
+ "loss": 1.4175,
1493
+ "step": 12375
1494
+ },
1495
+ {
1496
+ "epoch": 0.75,
1497
+ "eval_validation_privacy_sources_loss": 0.7693954110145569,
1498
+ "eval_validation_privacy_sources_runtime": 201.0957,
1499
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1500
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1501
+ "step": 12375
1502
+ },
1503
+ {
1504
+ "epoch": 0.75,
1505
+ "eval_validation_agenda_digitale_loss": 1.369871735572815,
1506
+ "eval_validation_agenda_digitale_runtime": 178.5478,
1507
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
1508
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
1509
+ "step": 12375
1510
+ },
1511
+ {
1512
+ "epoch": 0.75,
1513
+ "eval_validation_leggepertutti_loss": 1.2951487302780151,
1514
+ "eval_validation_leggepertutti_runtime": 34.1392,
1515
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
1516
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
1517
+ "step": 12375
1518
+ },
1519
+ {
1520
+ "epoch": 0.75,
1521
+ "eval_validation_altalexprivacy_loss": 1.165571928024292,
1522
+ "eval_validation_altalexprivacy_runtime": 55.6509,
1523
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
1524
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
1525
+ "step": 12375
1526
+ },
1527
+ {
1528
+ "epoch": 0.75,
1529
+ "eval_validation_mc4_it_loss": 1.778039574623108,
1530
+ "eval_validation_mc4_it_runtime": 74.5747,
1531
+ "eval_validation_mc4_it_samples_per_second": 1.904,
1532
+ "eval_validation_mc4_it_steps_per_second": 1.904,
1533
+ "step": 12375
1534
+ },
1535
+ {
1536
+ "epoch": 0.77,
1537
+ "learning_rate": 1e-05,
1538
+ "loss": 1.4184,
1539
+ "step": 12750
1540
+ },
1541
+ {
1542
+ "epoch": 0.77,
1543
+ "eval_validation_privacy_sources_loss": 0.7700363993644714,
1544
+ "eval_validation_privacy_sources_runtime": 201.1054,
1545
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
1546
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
1547
+ "step": 12750
1548
+ },
1549
+ {
1550
+ "epoch": 0.77,
1551
+ "eval_validation_agenda_digitale_loss": 1.3706245422363281,
1552
+ "eval_validation_agenda_digitale_runtime": 178.5538,
1553
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
1554
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
1555
+ "step": 12750
1556
+ },
1557
+ {
1558
+ "epoch": 0.77,
1559
+ "eval_validation_leggepertutti_loss": 1.3042017221450806,
1560
+ "eval_validation_leggepertutti_runtime": 34.1314,
1561
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
1562
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
1563
+ "step": 12750
1564
+ },
1565
+ {
1566
+ "epoch": 0.77,
1567
+ "eval_validation_altalexprivacy_loss": 1.1619981527328491,
1568
+ "eval_validation_altalexprivacy_runtime": 55.6735,
1569
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
1570
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
1571
+ "step": 12750
1572
+ },
1573
+ {
1574
+ "epoch": 0.77,
1575
+ "eval_validation_mc4_it_loss": 1.772789716720581,
1576
+ "eval_validation_mc4_it_runtime": 74.5651,
1577
+ "eval_validation_mc4_it_samples_per_second": 1.904,
1578
+ "eval_validation_mc4_it_steps_per_second": 1.904,
1579
+ "step": 12750
1580
+ },
1581
+ {
1582
+ "epoch": 0.79,
1583
+ "learning_rate": 1e-05,
1584
+ "loss": 1.4328,
1585
+ "step": 13125
1586
+ },
1587
+ {
1588
+ "epoch": 0.79,
1589
+ "eval_validation_privacy_sources_loss": 0.7653990387916565,
1590
+ "eval_validation_privacy_sources_runtime": 201.1035,
1591
+ "eval_validation_privacy_sources_samples_per_second": 1.904,
1592
+ "eval_validation_privacy_sources_steps_per_second": 1.904,
1593
+ "step": 13125
1594
+ },
1595
+ {
1596
+ "epoch": 0.79,
1597
+ "eval_validation_agenda_digitale_loss": 1.3673630952835083,
1598
+ "eval_validation_agenda_digitale_runtime": 178.543,
1599
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
1600
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
1601
+ "step": 13125
1602
+ },
1603
+ {
1604
+ "epoch": 0.79,
1605
+ "eval_validation_leggepertutti_loss": 1.2916979789733887,
1606
+ "eval_validation_leggepertutti_runtime": 34.1329,
1607
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
1608
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
1609
+ "step": 13125
1610
+ },
1611
+ {
1612
+ "epoch": 0.79,
1613
+ "eval_validation_altalexprivacy_loss": 1.156830072402954,
1614
+ "eval_validation_altalexprivacy_runtime": 55.646,
1615
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
1616
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
1617
+ "step": 13125
1618
+ },
1619
+ {
1620
+ "epoch": 0.79,
1621
+ "eval_validation_mc4_it_loss": 1.773768663406372,
1622
+ "eval_validation_mc4_it_runtime": 74.5527,
1623
+ "eval_validation_mc4_it_samples_per_second": 1.905,
1624
+ "eval_validation_mc4_it_steps_per_second": 1.905,
1625
+ "step": 13125
1626
+ },
1627
+ {
1628
+ "epoch": 0.82,
1629
+ "learning_rate": 1e-05,
1630
+ "loss": 1.4065,
1631
+ "step": 13500
1632
+ },
1633
+ {
1634
+ "epoch": 0.82,
1635
+ "eval_validation_privacy_sources_loss": 0.7647636532783508,
1636
+ "eval_validation_privacy_sources_runtime": 201.0591,
1637
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1638
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1639
+ "step": 13500
1640
+ },
1641
+ {
1642
+ "epoch": 0.82,
1643
+ "eval_validation_agenda_digitale_loss": 1.3673948049545288,
1644
+ "eval_validation_agenda_digitale_runtime": 178.5334,
1645
+ "eval_validation_agenda_digitale_samples_per_second": 1.904,
1646
+ "eval_validation_agenda_digitale_steps_per_second": 1.904,
1647
+ "step": 13500
1648
+ },
1649
+ {
1650
+ "epoch": 0.82,
1651
+ "eval_validation_leggepertutti_loss": 1.2989599704742432,
1652
+ "eval_validation_leggepertutti_runtime": 34.1356,
1653
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
1654
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
1655
+ "step": 13500
1656
+ },
1657
+ {
1658
+ "epoch": 0.82,
1659
+ "eval_validation_altalexprivacy_loss": 1.1564033031463623,
1660
+ "eval_validation_altalexprivacy_runtime": 55.6555,
1661
+ "eval_validation_altalexprivacy_samples_per_second": 1.905,
1662
+ "eval_validation_altalexprivacy_steps_per_second": 1.905,
1663
+ "step": 13500
1664
+ },
1665
+ {
1666
+ "epoch": 0.82,
1667
+ "eval_validation_mc4_it_loss": 1.7719225883483887,
1668
+ "eval_validation_mc4_it_runtime": 74.5639,
1669
+ "eval_validation_mc4_it_samples_per_second": 1.904,
1670
+ "eval_validation_mc4_it_steps_per_second": 1.904,
1671
+ "step": 13500
1672
+ },
1673
+ {
1674
+ "epoch": 0.84,
1675
+ "learning_rate": 1e-05,
1676
+ "loss": 1.4013,
1677
+ "step": 13875
1678
+ },
1679
+ {
1680
+ "epoch": 0.84,
1681
+ "eval_validation_privacy_sources_loss": 0.7642931938171387,
1682
+ "eval_validation_privacy_sources_runtime": 201.026,
1683
+ "eval_validation_privacy_sources_samples_per_second": 1.905,
1684
+ "eval_validation_privacy_sources_steps_per_second": 1.905,
1685
+ "step": 13875
1686
+ },
1687
+ {
1688
+ "epoch": 0.84,
1689
+ "eval_validation_agenda_digitale_loss": 1.3678263425827026,
1690
+ "eval_validation_agenda_digitale_runtime": 178.4828,
1691
+ "eval_validation_agenda_digitale_samples_per_second": 1.905,
1692
+ "eval_validation_agenda_digitale_steps_per_second": 1.905,
1693
+ "step": 13875
1694
+ },
1695
+ {
1696
+ "epoch": 0.84,
1697
+ "eval_validation_leggepertutti_loss": 1.2972129583358765,
1698
+ "eval_validation_leggepertutti_runtime": 34.1357,
1699
+ "eval_validation_leggepertutti_samples_per_second": 1.904,
1700
+ "eval_validation_leggepertutti_steps_per_second": 1.904,
1701
+ "step": 13875
1702
+ },
1703
+ {
1704
+ "epoch": 0.84,
1705
+ "eval_validation_altalexprivacy_loss": 1.150413990020752,
1706
+ "eval_validation_altalexprivacy_runtime": 55.6689,
1707
+ "eval_validation_altalexprivacy_samples_per_second": 1.904,
1708
+ "eval_validation_altalexprivacy_steps_per_second": 1.904,
1709
+ "step": 13875
1710
+ },
1711
+ {
1712
+ "epoch": 0.84,
1713
+ "eval_validation_mc4_it_loss": 1.770357370376587,
1714
+ "eval_validation_mc4_it_runtime": 74.606,
1715
+ "eval_validation_mc4_it_samples_per_second": 1.903,
1716
+ "eval_validation_mc4_it_steps_per_second": 1.903,
1717
+ "step": 13875
1718
+ }
1719
+ ],
1720
+ "logging_steps": 375,
1721
+ "max_steps": 33094,
1722
+ "num_input_tokens_seen": 0,
1723
+ "num_train_epochs": 2,
1724
+ "save_steps": 375,
1725
+ "total_flos": 2.9096138489462784e+19,
1726
+ "train_batch_size": 1,
1727
+ "trial_name": null,
1728
+ "trial_params": null
1729
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1416eac7b08ba06348e92dafebae38c37b959841df010dcd3f885aab6249f9a6
3
+ size 4792