andrealexroom commited on
Commit
d9e4ef0
1 Parent(s): 0db470e

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": "4.38.2",
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": "4.38.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9bb4194b440adf07bf3c73e48dddf4fecc4f42bd8e30cb8349095bdd952c030
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:bfa0d87e8c0808f0bb3ea1c33f1131177173bce286ddb5b930b927c2d58c0994
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f3c861aaaac07a755643e4f2f1de4445273f4d14fc3f919cbb82f5fcc3c4ee
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:e8b593c5b7b039e5b3b7cb2e1826d2a56d98245ee367829af7d0983cf3925203
3
+ size 28967182538
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fbbec6c0a50fc01f4129b05f91e7d26fa776f0c61f4065bf2fe369beab3f0a
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:717e72ebbb0e88a76b0605b5cb17da061c6f318e81afa55193d76bbf39130918
3
+ size 1000
trainer_state.json ADDED
@@ -0,0 +1,1109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.902445741262868,
5
+ "eval_steps": 187,
6
+ "global_step": 4301,
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
+ "grad_norm": 10.4375,
14
+ "learning_rate": 2.1276595744680852e-07,
15
+ "loss": 1.5104,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "grad_norm": 2.90625,
21
+ "learning_rate": 1e-05,
22
+ "loss": 1.1784,
23
+ "step": 187
24
+ },
25
+ {
26
+ "epoch": 0.04,
27
+ "eval_validation_loss": 0.956233024597168,
28
+ "eval_validation_runtime": 190.0844,
29
+ "eval_validation_samples_per_second": 0.726,
30
+ "eval_validation_steps_per_second": 0.726,
31
+ "step": 187
32
+ },
33
+ {
34
+ "epoch": 0.04,
35
+ "eval_validation_privacy_sources_loss": 0.956233024597168,
36
+ "eval_validation_privacy_sources_runtime": 190.1247,
37
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
38
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
39
+ "step": 187
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "eval_validation_agenda_digitale_loss": 1.5249053239822388,
44
+ "eval_validation_agenda_digitale_runtime": 170.8208,
45
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
46
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
47
+ "step": 187
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "eval_validation_legal_articles_loss": 1.4138059616088867,
52
+ "eval_validation_legal_articles_runtime": 274.0975,
53
+ "eval_validation_legal_articles_samples_per_second": 0.726,
54
+ "eval_validation_legal_articles_steps_per_second": 0.726,
55
+ "step": 187
56
+ },
57
+ {
58
+ "epoch": 0.04,
59
+ "eval_validation_leggepertutti_loss": 1.2507734298706055,
60
+ "eval_validation_leggepertutti_runtime": 26.1774,
61
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
62
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
63
+ "step": 187
64
+ },
65
+ {
66
+ "epoch": 0.08,
67
+ "grad_norm": 3.5625,
68
+ "learning_rate": 1e-05,
69
+ "loss": 1.0602,
70
+ "step": 374
71
+ },
72
+ {
73
+ "epoch": 0.08,
74
+ "eval_validation_loss": 0.9068162441253662,
75
+ "eval_validation_runtime": 190.0623,
76
+ "eval_validation_samples_per_second": 0.726,
77
+ "eval_validation_steps_per_second": 0.726,
78
+ "step": 374
79
+ },
80
+ {
81
+ "epoch": 0.08,
82
+ "eval_validation_privacy_sources_loss": 0.9068162441253662,
83
+ "eval_validation_privacy_sources_runtime": 190.1749,
84
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
85
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
86
+ "step": 374
87
+ },
88
+ {
89
+ "epoch": 0.08,
90
+ "eval_validation_agenda_digitale_loss": 1.5025277137756348,
91
+ "eval_validation_agenda_digitale_runtime": 170.8116,
92
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
93
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
94
+ "step": 374
95
+ },
96
+ {
97
+ "epoch": 0.08,
98
+ "eval_validation_legal_articles_loss": 1.3901658058166504,
99
+ "eval_validation_legal_articles_runtime": 274.2187,
100
+ "eval_validation_legal_articles_samples_per_second": 0.726,
101
+ "eval_validation_legal_articles_steps_per_second": 0.726,
102
+ "step": 374
103
+ },
104
+ {
105
+ "epoch": 0.08,
106
+ "eval_validation_leggepertutti_loss": 1.2389607429504395,
107
+ "eval_validation_leggepertutti_runtime": 26.1823,
108
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
109
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
110
+ "step": 374
111
+ },
112
+ {
113
+ "epoch": 0.12,
114
+ "grad_norm": 2.375,
115
+ "learning_rate": 1e-05,
116
+ "loss": 0.9973,
117
+ "step": 561
118
+ },
119
+ {
120
+ "epoch": 0.12,
121
+ "eval_validation_loss": 0.8726317286491394,
122
+ "eval_validation_runtime": 190.0376,
123
+ "eval_validation_samples_per_second": 0.726,
124
+ "eval_validation_steps_per_second": 0.726,
125
+ "step": 561
126
+ },
127
+ {
128
+ "epoch": 0.12,
129
+ "eval_validation_privacy_sources_loss": 0.8726317286491394,
130
+ "eval_validation_privacy_sources_runtime": 189.9977,
131
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
132
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
133
+ "step": 561
134
+ },
135
+ {
136
+ "epoch": 0.12,
137
+ "eval_validation_agenda_digitale_loss": 1.4876974821090698,
138
+ "eval_validation_agenda_digitale_runtime": 170.7148,
139
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
140
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
141
+ "step": 561
142
+ },
143
+ {
144
+ "epoch": 0.12,
145
+ "eval_validation_legal_articles_loss": 1.3721040487289429,
146
+ "eval_validation_legal_articles_runtime": 273.9951,
147
+ "eval_validation_legal_articles_samples_per_second": 0.726,
148
+ "eval_validation_legal_articles_steps_per_second": 0.726,
149
+ "step": 561
150
+ },
151
+ {
152
+ "epoch": 0.12,
153
+ "eval_validation_leggepertutti_loss": 1.213807463645935,
154
+ "eval_validation_leggepertutti_runtime": 26.1576,
155
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
156
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
157
+ "step": 561
158
+ },
159
+ {
160
+ "epoch": 0.16,
161
+ "grad_norm": 2.734375,
162
+ "learning_rate": 1e-05,
163
+ "loss": 0.9936,
164
+ "step": 748
165
+ },
166
+ {
167
+ "epoch": 0.16,
168
+ "eval_validation_loss": 0.8519095778465271,
169
+ "eval_validation_runtime": 190.0914,
170
+ "eval_validation_samples_per_second": 0.726,
171
+ "eval_validation_steps_per_second": 0.726,
172
+ "step": 748
173
+ },
174
+ {
175
+ "epoch": 0.16,
176
+ "eval_validation_privacy_sources_loss": 0.8519095778465271,
177
+ "eval_validation_privacy_sources_runtime": 190.1871,
178
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
179
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
180
+ "step": 748
181
+ },
182
+ {
183
+ "epoch": 0.16,
184
+ "eval_validation_agenda_digitale_loss": 1.4739274978637695,
185
+ "eval_validation_agenda_digitale_runtime": 170.8961,
186
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
187
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
188
+ "step": 748
189
+ },
190
+ {
191
+ "epoch": 0.16,
192
+ "eval_validation_legal_articles_loss": 1.3598031997680664,
193
+ "eval_validation_legal_articles_runtime": 274.1856,
194
+ "eval_validation_legal_articles_samples_per_second": 0.726,
195
+ "eval_validation_legal_articles_steps_per_second": 0.726,
196
+ "step": 748
197
+ },
198
+ {
199
+ "epoch": 0.16,
200
+ "eval_validation_leggepertutti_loss": 1.2074390649795532,
201
+ "eval_validation_leggepertutti_runtime": 26.177,
202
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
203
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
204
+ "step": 748
205
+ },
206
+ {
207
+ "epoch": 0.2,
208
+ "grad_norm": 2.90625,
209
+ "learning_rate": 1e-05,
210
+ "loss": 0.9671,
211
+ "step": 935
212
+ },
213
+ {
214
+ "epoch": 0.2,
215
+ "eval_validation_loss": 0.8343605399131775,
216
+ "eval_validation_runtime": 190.0578,
217
+ "eval_validation_samples_per_second": 0.726,
218
+ "eval_validation_steps_per_second": 0.726,
219
+ "step": 935
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "eval_validation_privacy_sources_loss": 0.8343605399131775,
224
+ "eval_validation_privacy_sources_runtime": 190.0981,
225
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
226
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
227
+ "step": 935
228
+ },
229
+ {
230
+ "epoch": 0.2,
231
+ "eval_validation_agenda_digitale_loss": 1.4663511514663696,
232
+ "eval_validation_agenda_digitale_runtime": 170.7988,
233
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
234
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
235
+ "step": 935
236
+ },
237
+ {
238
+ "epoch": 0.2,
239
+ "eval_validation_legal_articles_loss": 1.3504709005355835,
240
+ "eval_validation_legal_articles_runtime": 274.1096,
241
+ "eval_validation_legal_articles_samples_per_second": 0.726,
242
+ "eval_validation_legal_articles_steps_per_second": 0.726,
243
+ "step": 935
244
+ },
245
+ {
246
+ "epoch": 0.2,
247
+ "eval_validation_leggepertutti_loss": 1.19623863697052,
248
+ "eval_validation_leggepertutti_runtime": 26.1751,
249
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
250
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
251
+ "step": 935
252
+ },
253
+ {
254
+ "epoch": 0.24,
255
+ "grad_norm": 18.625,
256
+ "learning_rate": 1e-05,
257
+ "loss": 0.9582,
258
+ "step": 1122
259
+ },
260
+ {
261
+ "epoch": 0.24,
262
+ "eval_validation_loss": 0.8237400650978088,
263
+ "eval_validation_runtime": 190.0819,
264
+ "eval_validation_samples_per_second": 0.726,
265
+ "eval_validation_steps_per_second": 0.726,
266
+ "step": 1122
267
+ },
268
+ {
269
+ "epoch": 0.24,
270
+ "eval_validation_privacy_sources_loss": 0.8237400650978088,
271
+ "eval_validation_privacy_sources_runtime": 190.0975,
272
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
273
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
274
+ "step": 1122
275
+ },
276
+ {
277
+ "epoch": 0.24,
278
+ "eval_validation_agenda_digitale_loss": 1.4592102766036987,
279
+ "eval_validation_agenda_digitale_runtime": 170.7961,
280
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
281
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
282
+ "step": 1122
283
+ },
284
+ {
285
+ "epoch": 0.24,
286
+ "eval_validation_legal_articles_loss": 1.341143250465393,
287
+ "eval_validation_legal_articles_runtime": 274.155,
288
+ "eval_validation_legal_articles_samples_per_second": 0.726,
289
+ "eval_validation_legal_articles_steps_per_second": 0.726,
290
+ "step": 1122
291
+ },
292
+ {
293
+ "epoch": 0.24,
294
+ "eval_validation_leggepertutti_loss": 1.1890021562576294,
295
+ "eval_validation_leggepertutti_runtime": 26.1699,
296
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
297
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
298
+ "step": 1122
299
+ },
300
+ {
301
+ "epoch": 0.27,
302
+ "grad_norm": 2.28125,
303
+ "learning_rate": 1e-05,
304
+ "loss": 0.9456,
305
+ "step": 1309
306
+ },
307
+ {
308
+ "epoch": 0.27,
309
+ "eval_validation_loss": 0.8131315112113953,
310
+ "eval_validation_runtime": 189.7603,
311
+ "eval_validation_samples_per_second": 0.727,
312
+ "eval_validation_steps_per_second": 0.727,
313
+ "step": 1309
314
+ },
315
+ {
316
+ "epoch": 0.27,
317
+ "eval_validation_privacy_sources_loss": 0.8131315112113953,
318
+ "eval_validation_privacy_sources_runtime": 189.8097,
319
+ "eval_validation_privacy_sources_samples_per_second": 0.727,
320
+ "eval_validation_privacy_sources_steps_per_second": 0.727,
321
+ "step": 1309
322
+ },
323
+ {
324
+ "epoch": 0.27,
325
+ "eval_validation_agenda_digitale_loss": 1.4516360759735107,
326
+ "eval_validation_agenda_digitale_runtime": 170.4955,
327
+ "eval_validation_agenda_digitale_samples_per_second": 0.727,
328
+ "eval_validation_agenda_digitale_steps_per_second": 0.727,
329
+ "step": 1309
330
+ },
331
+ {
332
+ "epoch": 0.27,
333
+ "eval_validation_legal_articles_loss": 1.3339463472366333,
334
+ "eval_validation_legal_articles_runtime": 273.5945,
335
+ "eval_validation_legal_articles_samples_per_second": 0.727,
336
+ "eval_validation_legal_articles_steps_per_second": 0.727,
337
+ "step": 1309
338
+ },
339
+ {
340
+ "epoch": 0.27,
341
+ "eval_validation_leggepertutti_loss": 1.1844114065170288,
342
+ "eval_validation_leggepertutti_runtime": 26.1031,
343
+ "eval_validation_leggepertutti_samples_per_second": 0.728,
344
+ "eval_validation_leggepertutti_steps_per_second": 0.728,
345
+ "step": 1309
346
+ },
347
+ {
348
+ "epoch": 0.31,
349
+ "grad_norm": 2.203125,
350
+ "learning_rate": 1e-05,
351
+ "loss": 0.9118,
352
+ "step": 1496
353
+ },
354
+ {
355
+ "epoch": 0.31,
356
+ "eval_validation_loss": 0.8056552410125732,
357
+ "eval_validation_runtime": 189.1065,
358
+ "eval_validation_samples_per_second": 0.73,
359
+ "eval_validation_steps_per_second": 0.73,
360
+ "step": 1496
361
+ },
362
+ {
363
+ "epoch": 0.31,
364
+ "eval_validation_privacy_sources_loss": 0.8056552410125732,
365
+ "eval_validation_privacy_sources_runtime": 189.1418,
366
+ "eval_validation_privacy_sources_samples_per_second": 0.73,
367
+ "eval_validation_privacy_sources_steps_per_second": 0.73,
368
+ "step": 1496
369
+ },
370
+ {
371
+ "epoch": 0.31,
372
+ "eval_validation_agenda_digitale_loss": 1.4482883214950562,
373
+ "eval_validation_agenda_digitale_runtime": 169.9314,
374
+ "eval_validation_agenda_digitale_samples_per_second": 0.73,
375
+ "eval_validation_agenda_digitale_steps_per_second": 0.73,
376
+ "step": 1496
377
+ },
378
+ {
379
+ "epoch": 0.31,
380
+ "eval_validation_legal_articles_loss": 1.3298695087432861,
381
+ "eval_validation_legal_articles_runtime": 272.7633,
382
+ "eval_validation_legal_articles_samples_per_second": 0.73,
383
+ "eval_validation_legal_articles_steps_per_second": 0.73,
384
+ "step": 1496
385
+ },
386
+ {
387
+ "epoch": 0.31,
388
+ "eval_validation_leggepertutti_loss": 1.178873896598816,
389
+ "eval_validation_leggepertutti_runtime": 26.0447,
390
+ "eval_validation_leggepertutti_samples_per_second": 0.73,
391
+ "eval_validation_leggepertutti_steps_per_second": 0.73,
392
+ "step": 1496
393
+ },
394
+ {
395
+ "epoch": 0.35,
396
+ "grad_norm": 2.28125,
397
+ "learning_rate": 1e-05,
398
+ "loss": 0.9018,
399
+ "step": 1683
400
+ },
401
+ {
402
+ "epoch": 0.35,
403
+ "eval_validation_loss": 0.7955409288406372,
404
+ "eval_validation_runtime": 190.0308,
405
+ "eval_validation_samples_per_second": 0.726,
406
+ "eval_validation_steps_per_second": 0.726,
407
+ "step": 1683
408
+ },
409
+ {
410
+ "epoch": 0.35,
411
+ "eval_validation_privacy_sources_loss": 0.7955409288406372,
412
+ "eval_validation_privacy_sources_runtime": 190.1015,
413
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
414
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
415
+ "step": 1683
416
+ },
417
+ {
418
+ "epoch": 0.35,
419
+ "eval_validation_agenda_digitale_loss": 1.4420207738876343,
420
+ "eval_validation_agenda_digitale_runtime": 170.7677,
421
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
422
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
423
+ "step": 1683
424
+ },
425
+ {
426
+ "epoch": 0.35,
427
+ "eval_validation_legal_articles_loss": 1.3251116275787354,
428
+ "eval_validation_legal_articles_runtime": 274.0824,
429
+ "eval_validation_legal_articles_samples_per_second": 0.726,
430
+ "eval_validation_legal_articles_steps_per_second": 0.726,
431
+ "step": 1683
432
+ },
433
+ {
434
+ "epoch": 0.35,
435
+ "eval_validation_leggepertutti_loss": 1.1761751174926758,
436
+ "eval_validation_leggepertutti_runtime": 26.1786,
437
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
438
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
439
+ "step": 1683
440
+ },
441
+ {
442
+ "epoch": 0.39,
443
+ "grad_norm": 3.375,
444
+ "learning_rate": 1e-05,
445
+ "loss": 0.8911,
446
+ "step": 1870
447
+ },
448
+ {
449
+ "epoch": 0.39,
450
+ "eval_validation_loss": 0.7886275053024292,
451
+ "eval_validation_runtime": 190.0169,
452
+ "eval_validation_samples_per_second": 0.726,
453
+ "eval_validation_steps_per_second": 0.726,
454
+ "step": 1870
455
+ },
456
+ {
457
+ "epoch": 0.39,
458
+ "eval_validation_privacy_sources_loss": 0.7886275053024292,
459
+ "eval_validation_privacy_sources_runtime": 189.9755,
460
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
461
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
462
+ "step": 1870
463
+ },
464
+ {
465
+ "epoch": 0.39,
466
+ "eval_validation_agenda_digitale_loss": 1.437984585762024,
467
+ "eval_validation_agenda_digitale_runtime": 170.7137,
468
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
469
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
470
+ "step": 1870
471
+ },
472
+ {
473
+ "epoch": 0.39,
474
+ "eval_validation_legal_articles_loss": 1.3213441371917725,
475
+ "eval_validation_legal_articles_runtime": 273.9792,
476
+ "eval_validation_legal_articles_samples_per_second": 0.726,
477
+ "eval_validation_legal_articles_steps_per_second": 0.726,
478
+ "step": 1870
479
+ },
480
+ {
481
+ "epoch": 0.39,
482
+ "eval_validation_leggepertutti_loss": 1.1724990606307983,
483
+ "eval_validation_leggepertutti_runtime": 26.1471,
484
+ "eval_validation_leggepertutti_samples_per_second": 0.727,
485
+ "eval_validation_leggepertutti_steps_per_second": 0.727,
486
+ "step": 1870
487
+ },
488
+ {
489
+ "epoch": 0.43,
490
+ "grad_norm": 2.34375,
491
+ "learning_rate": 1e-05,
492
+ "loss": 0.8824,
493
+ "step": 2057
494
+ },
495
+ {
496
+ "epoch": 0.43,
497
+ "eval_validation_loss": 0.7812964916229248,
498
+ "eval_validation_runtime": 189.9852,
499
+ "eval_validation_samples_per_second": 0.726,
500
+ "eval_validation_steps_per_second": 0.726,
501
+ "step": 2057
502
+ },
503
+ {
504
+ "epoch": 0.43,
505
+ "eval_validation_privacy_sources_loss": 0.7812964916229248,
506
+ "eval_validation_privacy_sources_runtime": 190.0648,
507
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
508
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
509
+ "step": 2057
510
+ },
511
+ {
512
+ "epoch": 0.43,
513
+ "eval_validation_agenda_digitale_loss": 1.4352736473083496,
514
+ "eval_validation_agenda_digitale_runtime": 170.7674,
515
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
516
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
517
+ "step": 2057
518
+ },
519
+ {
520
+ "epoch": 0.43,
521
+ "eval_validation_legal_articles_loss": 1.3146668672561646,
522
+ "eval_validation_legal_articles_runtime": 274.0088,
523
+ "eval_validation_legal_articles_samples_per_second": 0.726,
524
+ "eval_validation_legal_articles_steps_per_second": 0.726,
525
+ "step": 2057
526
+ },
527
+ {
528
+ "epoch": 0.43,
529
+ "eval_validation_leggepertutti_loss": 1.1654175519943237,
530
+ "eval_validation_leggepertutti_runtime": 26.1671,
531
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
532
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
533
+ "step": 2057
534
+ },
535
+ {
536
+ "epoch": 0.47,
537
+ "grad_norm": 2.515625,
538
+ "learning_rate": 1e-05,
539
+ "loss": 0.8871,
540
+ "step": 2244
541
+ },
542
+ {
543
+ "epoch": 0.47,
544
+ "eval_validation_loss": 0.7756069898605347,
545
+ "eval_validation_runtime": 190.0643,
546
+ "eval_validation_samples_per_second": 0.726,
547
+ "eval_validation_steps_per_second": 0.726,
548
+ "step": 2244
549
+ },
550
+ {
551
+ "epoch": 0.47,
552
+ "eval_validation_privacy_sources_loss": 0.7756069898605347,
553
+ "eval_validation_privacy_sources_runtime": 190.0095,
554
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
555
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
556
+ "step": 2244
557
+ },
558
+ {
559
+ "epoch": 0.47,
560
+ "eval_validation_agenda_digitale_loss": 1.431518316268921,
561
+ "eval_validation_agenda_digitale_runtime": 170.7517,
562
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
563
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
564
+ "step": 2244
565
+ },
566
+ {
567
+ "epoch": 0.47,
568
+ "eval_validation_legal_articles_loss": 1.3110154867172241,
569
+ "eval_validation_legal_articles_runtime": 274.0835,
570
+ "eval_validation_legal_articles_samples_per_second": 0.726,
571
+ "eval_validation_legal_articles_steps_per_second": 0.726,
572
+ "step": 2244
573
+ },
574
+ {
575
+ "epoch": 0.47,
576
+ "eval_validation_leggepertutti_loss": 1.161647915840149,
577
+ "eval_validation_leggepertutti_runtime": 26.1417,
578
+ "eval_validation_leggepertutti_samples_per_second": 0.727,
579
+ "eval_validation_leggepertutti_steps_per_second": 0.727,
580
+ "step": 2244
581
+ },
582
+ {
583
+ "epoch": 0.51,
584
+ "grad_norm": 2.640625,
585
+ "learning_rate": 1e-05,
586
+ "loss": 0.8723,
587
+ "step": 2431
588
+ },
589
+ {
590
+ "epoch": 0.51,
591
+ "eval_validation_loss": 0.7698301076889038,
592
+ "eval_validation_runtime": 189.9735,
593
+ "eval_validation_samples_per_second": 0.726,
594
+ "eval_validation_steps_per_second": 0.726,
595
+ "step": 2431
596
+ },
597
+ {
598
+ "epoch": 0.51,
599
+ "eval_validation_privacy_sources_loss": 0.7698301076889038,
600
+ "eval_validation_privacy_sources_runtime": 190.0719,
601
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
602
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
603
+ "step": 2431
604
+ },
605
+ {
606
+ "epoch": 0.51,
607
+ "eval_validation_agenda_digitale_loss": 1.4284371137619019,
608
+ "eval_validation_agenda_digitale_runtime": 170.7398,
609
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
610
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
611
+ "step": 2431
612
+ },
613
+ {
614
+ "epoch": 0.51,
615
+ "eval_validation_legal_articles_loss": 1.3073266744613647,
616
+ "eval_validation_legal_articles_runtime": 273.9802,
617
+ "eval_validation_legal_articles_samples_per_second": 0.726,
618
+ "eval_validation_legal_articles_steps_per_second": 0.726,
619
+ "step": 2431
620
+ },
621
+ {
622
+ "epoch": 0.51,
623
+ "eval_validation_leggepertutti_loss": 1.1593568325042725,
624
+ "eval_validation_leggepertutti_runtime": 26.1645,
625
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
626
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
627
+ "step": 2431
628
+ },
629
+ {
630
+ "epoch": 0.55,
631
+ "grad_norm": 2.203125,
632
+ "learning_rate": 1e-05,
633
+ "loss": 0.8663,
634
+ "step": 2618
635
+ },
636
+ {
637
+ "epoch": 0.55,
638
+ "eval_validation_loss": 0.7643269896507263,
639
+ "eval_validation_runtime": 189.9762,
640
+ "eval_validation_samples_per_second": 0.726,
641
+ "eval_validation_steps_per_second": 0.726,
642
+ "step": 2618
643
+ },
644
+ {
645
+ "epoch": 0.55,
646
+ "eval_validation_privacy_sources_loss": 0.7643269896507263,
647
+ "eval_validation_privacy_sources_runtime": 189.979,
648
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
649
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
650
+ "step": 2618
651
+ },
652
+ {
653
+ "epoch": 0.55,
654
+ "eval_validation_agenda_digitale_loss": 1.4276658296585083,
655
+ "eval_validation_agenda_digitale_runtime": 170.7641,
656
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
657
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
658
+ "step": 2618
659
+ },
660
+ {
661
+ "epoch": 0.55,
662
+ "eval_validation_legal_articles_loss": 1.306546926498413,
663
+ "eval_validation_legal_articles_runtime": 274.0313,
664
+ "eval_validation_legal_articles_samples_per_second": 0.726,
665
+ "eval_validation_legal_articles_steps_per_second": 0.726,
666
+ "step": 2618
667
+ },
668
+ {
669
+ "epoch": 0.55,
670
+ "eval_validation_leggepertutti_loss": 1.1585664749145508,
671
+ "eval_validation_leggepertutti_runtime": 26.1644,
672
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
673
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
674
+ "step": 2618
675
+ },
676
+ {
677
+ "epoch": 0.59,
678
+ "grad_norm": 2.75,
679
+ "learning_rate": 1e-05,
680
+ "loss": 0.8765,
681
+ "step": 2805
682
+ },
683
+ {
684
+ "epoch": 0.59,
685
+ "eval_validation_loss": 0.7591044306755066,
686
+ "eval_validation_runtime": 189.882,
687
+ "eval_validation_samples_per_second": 0.727,
688
+ "eval_validation_steps_per_second": 0.727,
689
+ "step": 2805
690
+ },
691
+ {
692
+ "epoch": 0.59,
693
+ "eval_validation_privacy_sources_loss": 0.7591044306755066,
694
+ "eval_validation_privacy_sources_runtime": 189.9501,
695
+ "eval_validation_privacy_sources_samples_per_second": 0.727,
696
+ "eval_validation_privacy_sources_steps_per_second": 0.727,
697
+ "step": 2805
698
+ },
699
+ {
700
+ "epoch": 0.59,
701
+ "eval_validation_agenda_digitale_loss": 1.4212045669555664,
702
+ "eval_validation_agenda_digitale_runtime": 170.6266,
703
+ "eval_validation_agenda_digitale_samples_per_second": 0.727,
704
+ "eval_validation_agenda_digitale_steps_per_second": 0.727,
705
+ "step": 2805
706
+ },
707
+ {
708
+ "epoch": 0.59,
709
+ "eval_validation_legal_articles_loss": 1.3000119924545288,
710
+ "eval_validation_legal_articles_runtime": 273.9772,
711
+ "eval_validation_legal_articles_samples_per_second": 0.726,
712
+ "eval_validation_legal_articles_steps_per_second": 0.726,
713
+ "step": 2805
714
+ },
715
+ {
716
+ "epoch": 0.59,
717
+ "eval_validation_leggepertutti_loss": 1.1529566049575806,
718
+ "eval_validation_leggepertutti_runtime": 26.1754,
719
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
720
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
721
+ "step": 2805
722
+ },
723
+ {
724
+ "epoch": 0.63,
725
+ "grad_norm": 2.25,
726
+ "learning_rate": 1e-05,
727
+ "loss": 0.8603,
728
+ "step": 2992
729
+ },
730
+ {
731
+ "epoch": 0.63,
732
+ "eval_validation_loss": 0.7559717893600464,
733
+ "eval_validation_runtime": 189.9515,
734
+ "eval_validation_samples_per_second": 0.727,
735
+ "eval_validation_steps_per_second": 0.727,
736
+ "step": 2992
737
+ },
738
+ {
739
+ "epoch": 0.63,
740
+ "eval_validation_privacy_sources_loss": 0.7559717893600464,
741
+ "eval_validation_privacy_sources_runtime": 189.9552,
742
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
743
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
744
+ "step": 2992
745
+ },
746
+ {
747
+ "epoch": 0.63,
748
+ "eval_validation_agenda_digitale_loss": 1.4198051691055298,
749
+ "eval_validation_agenda_digitale_runtime": 170.7077,
750
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
751
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
752
+ "step": 2992
753
+ },
754
+ {
755
+ "epoch": 0.63,
756
+ "eval_validation_legal_articles_loss": 1.2991034984588623,
757
+ "eval_validation_legal_articles_runtime": 273.9099,
758
+ "eval_validation_legal_articles_samples_per_second": 0.727,
759
+ "eval_validation_legal_articles_steps_per_second": 0.727,
760
+ "step": 2992
761
+ },
762
+ {
763
+ "epoch": 0.63,
764
+ "eval_validation_leggepertutti_loss": 1.1550276279449463,
765
+ "eval_validation_leggepertutti_runtime": 26.1726,
766
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
767
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
768
+ "step": 2992
769
+ },
770
+ {
771
+ "epoch": 0.67,
772
+ "grad_norm": 2.28125,
773
+ "learning_rate": 1e-05,
774
+ "loss": 0.8584,
775
+ "step": 3179
776
+ },
777
+ {
778
+ "epoch": 0.67,
779
+ "eval_validation_loss": 0.7532868385314941,
780
+ "eval_validation_runtime": 190.0516,
781
+ "eval_validation_samples_per_second": 0.726,
782
+ "eval_validation_steps_per_second": 0.726,
783
+ "step": 3179
784
+ },
785
+ {
786
+ "epoch": 0.67,
787
+ "eval_validation_privacy_sources_loss": 0.7532868385314941,
788
+ "eval_validation_privacy_sources_runtime": 190.0874,
789
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
790
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
791
+ "step": 3179
792
+ },
793
+ {
794
+ "epoch": 0.67,
795
+ "eval_validation_agenda_digitale_loss": 1.4165968894958496,
796
+ "eval_validation_agenda_digitale_runtime": 170.7869,
797
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
798
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
799
+ "step": 3179
800
+ },
801
+ {
802
+ "epoch": 0.67,
803
+ "eval_validation_legal_articles_loss": 1.2945970296859741,
804
+ "eval_validation_legal_articles_runtime": 273.9816,
805
+ "eval_validation_legal_articles_samples_per_second": 0.726,
806
+ "eval_validation_legal_articles_steps_per_second": 0.726,
807
+ "step": 3179
808
+ },
809
+ {
810
+ "epoch": 0.67,
811
+ "eval_validation_leggepertutti_loss": 1.1494359970092773,
812
+ "eval_validation_leggepertutti_runtime": 26.1538,
813
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
814
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
815
+ "step": 3179
816
+ },
817
+ {
818
+ "epoch": 0.71,
819
+ "grad_norm": 10.875,
820
+ "learning_rate": 1e-05,
821
+ "loss": 0.8506,
822
+ "step": 3366
823
+ },
824
+ {
825
+ "epoch": 0.71,
826
+ "eval_validation_loss": 0.750731885433197,
827
+ "eval_validation_runtime": 190.0222,
828
+ "eval_validation_samples_per_second": 0.726,
829
+ "eval_validation_steps_per_second": 0.726,
830
+ "step": 3366
831
+ },
832
+ {
833
+ "epoch": 0.71,
834
+ "eval_validation_privacy_sources_loss": 0.750731885433197,
835
+ "eval_validation_privacy_sources_runtime": 190.0188,
836
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
837
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
838
+ "step": 3366
839
+ },
840
+ {
841
+ "epoch": 0.71,
842
+ "eval_validation_agenda_digitale_loss": 1.4151290655136108,
843
+ "eval_validation_agenda_digitale_runtime": 170.7202,
844
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
845
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
846
+ "step": 3366
847
+ },
848
+ {
849
+ "epoch": 0.71,
850
+ "eval_validation_legal_articles_loss": 1.2938265800476074,
851
+ "eval_validation_legal_articles_runtime": 274.068,
852
+ "eval_validation_legal_articles_samples_per_second": 0.726,
853
+ "eval_validation_legal_articles_steps_per_second": 0.726,
854
+ "step": 3366
855
+ },
856
+ {
857
+ "epoch": 0.71,
858
+ "eval_validation_leggepertutti_loss": 1.151176929473877,
859
+ "eval_validation_leggepertutti_runtime": 26.1605,
860
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
861
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
862
+ "step": 3366
863
+ },
864
+ {
865
+ "epoch": 0.75,
866
+ "grad_norm": 3.0,
867
+ "learning_rate": 1e-05,
868
+ "loss": 0.8608,
869
+ "step": 3553
870
+ },
871
+ {
872
+ "epoch": 0.75,
873
+ "eval_validation_loss": 0.7474144101142883,
874
+ "eval_validation_runtime": 189.9367,
875
+ "eval_validation_samples_per_second": 0.727,
876
+ "eval_validation_steps_per_second": 0.727,
877
+ "step": 3553
878
+ },
879
+ {
880
+ "epoch": 0.75,
881
+ "eval_validation_privacy_sources_loss": 0.7474144101142883,
882
+ "eval_validation_privacy_sources_runtime": 190.0407,
883
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
884
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
885
+ "step": 3553
886
+ },
887
+ {
888
+ "epoch": 0.75,
889
+ "eval_validation_agenda_digitale_loss": 1.4130672216415405,
890
+ "eval_validation_agenda_digitale_runtime": 170.6819,
891
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
892
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
893
+ "step": 3553
894
+ },
895
+ {
896
+ "epoch": 0.75,
897
+ "eval_validation_legal_articles_loss": 1.2912746667861938,
898
+ "eval_validation_legal_articles_runtime": 273.9492,
899
+ "eval_validation_legal_articles_samples_per_second": 0.726,
900
+ "eval_validation_legal_articles_steps_per_second": 0.726,
901
+ "step": 3553
902
+ },
903
+ {
904
+ "epoch": 0.75,
905
+ "eval_validation_leggepertutti_loss": 1.1468725204467773,
906
+ "eval_validation_leggepertutti_runtime": 26.1436,
907
+ "eval_validation_leggepertutti_samples_per_second": 0.727,
908
+ "eval_validation_leggepertutti_steps_per_second": 0.727,
909
+ "step": 3553
910
+ },
911
+ {
912
+ "epoch": 0.78,
913
+ "grad_norm": 2.265625,
914
+ "learning_rate": 1e-05,
915
+ "loss": 0.8363,
916
+ "step": 3740
917
+ },
918
+ {
919
+ "epoch": 0.78,
920
+ "eval_validation_loss": 0.7443498969078064,
921
+ "eval_validation_runtime": 189.9118,
922
+ "eval_validation_samples_per_second": 0.727,
923
+ "eval_validation_steps_per_second": 0.727,
924
+ "step": 3740
925
+ },
926
+ {
927
+ "epoch": 0.78,
928
+ "eval_validation_privacy_sources_loss": 0.7443498969078064,
929
+ "eval_validation_privacy_sources_runtime": 190.0301,
930
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
931
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
932
+ "step": 3740
933
+ },
934
+ {
935
+ "epoch": 0.78,
936
+ "eval_validation_agenda_digitale_loss": 1.4134020805358887,
937
+ "eval_validation_agenda_digitale_runtime": 170.7516,
938
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
939
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
940
+ "step": 3740
941
+ },
942
+ {
943
+ "epoch": 0.78,
944
+ "eval_validation_legal_articles_loss": 1.2929922342300415,
945
+ "eval_validation_legal_articles_runtime": 274.0196,
946
+ "eval_validation_legal_articles_samples_per_second": 0.726,
947
+ "eval_validation_legal_articles_steps_per_second": 0.726,
948
+ "step": 3740
949
+ },
950
+ {
951
+ "epoch": 0.78,
952
+ "eval_validation_leggepertutti_loss": 1.1504395008087158,
953
+ "eval_validation_leggepertutti_runtime": 26.181,
954
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
955
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
956
+ "step": 3740
957
+ },
958
+ {
959
+ "epoch": 0.82,
960
+ "grad_norm": 2.125,
961
+ "learning_rate": 1e-05,
962
+ "loss": 0.8409,
963
+ "step": 3927
964
+ },
965
+ {
966
+ "epoch": 0.82,
967
+ "eval_validation_loss": 0.7407341599464417,
968
+ "eval_validation_runtime": 190.0375,
969
+ "eval_validation_samples_per_second": 0.726,
970
+ "eval_validation_steps_per_second": 0.726,
971
+ "step": 3927
972
+ },
973
+ {
974
+ "epoch": 0.82,
975
+ "eval_validation_privacy_sources_loss": 0.7407341599464417,
976
+ "eval_validation_privacy_sources_runtime": 190.0419,
977
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
978
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
979
+ "step": 3927
980
+ },
981
+ {
982
+ "epoch": 0.82,
983
+ "eval_validation_agenda_digitale_loss": 1.4093834161758423,
984
+ "eval_validation_agenda_digitale_runtime": 170.7265,
985
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
986
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
987
+ "step": 3927
988
+ },
989
+ {
990
+ "epoch": 0.82,
991
+ "eval_validation_legal_articles_loss": 1.287365436553955,
992
+ "eval_validation_legal_articles_runtime": 273.961,
993
+ "eval_validation_legal_articles_samples_per_second": 0.726,
994
+ "eval_validation_legal_articles_steps_per_second": 0.726,
995
+ "step": 3927
996
+ },
997
+ {
998
+ "epoch": 0.82,
999
+ "eval_validation_leggepertutti_loss": 1.1438554525375366,
1000
+ "eval_validation_leggepertutti_runtime": 26.1491,
1001
+ "eval_validation_leggepertutti_samples_per_second": 0.727,
1002
+ "eval_validation_leggepertutti_steps_per_second": 0.727,
1003
+ "step": 3927
1004
+ },
1005
+ {
1006
+ "epoch": 0.86,
1007
+ "grad_norm": 2.3125,
1008
+ "learning_rate": 1e-05,
1009
+ "loss": 0.847,
1010
+ "step": 4114
1011
+ },
1012
+ {
1013
+ "epoch": 0.86,
1014
+ "eval_validation_loss": 0.7385227680206299,
1015
+ "eval_validation_runtime": 190.0405,
1016
+ "eval_validation_samples_per_second": 0.726,
1017
+ "eval_validation_steps_per_second": 0.726,
1018
+ "step": 4114
1019
+ },
1020
+ {
1021
+ "epoch": 0.86,
1022
+ "eval_validation_privacy_sources_loss": 0.7385227680206299,
1023
+ "eval_validation_privacy_sources_runtime": 190.0065,
1024
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
1025
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
1026
+ "step": 4114
1027
+ },
1028
+ {
1029
+ "epoch": 0.86,
1030
+ "eval_validation_agenda_digitale_loss": 1.4071052074432373,
1031
+ "eval_validation_agenda_digitale_runtime": 170.7073,
1032
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
1033
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
1034
+ "step": 4114
1035
+ },
1036
+ {
1037
+ "epoch": 0.86,
1038
+ "eval_validation_legal_articles_loss": 1.284498929977417,
1039
+ "eval_validation_legal_articles_runtime": 274.0307,
1040
+ "eval_validation_legal_articles_samples_per_second": 0.726,
1041
+ "eval_validation_legal_articles_steps_per_second": 0.726,
1042
+ "step": 4114
1043
+ },
1044
+ {
1045
+ "epoch": 0.86,
1046
+ "eval_validation_leggepertutti_loss": 1.1409564018249512,
1047
+ "eval_validation_leggepertutti_runtime": 26.1558,
1048
+ "eval_validation_leggepertutti_samples_per_second": 0.726,
1049
+ "eval_validation_leggepertutti_steps_per_second": 0.726,
1050
+ "step": 4114
1051
+ },
1052
+ {
1053
+ "epoch": 0.9,
1054
+ "grad_norm": 2.1875,
1055
+ "learning_rate": 1e-05,
1056
+ "loss": 0.8356,
1057
+ "step": 4301
1058
+ },
1059
+ {
1060
+ "epoch": 0.9,
1061
+ "eval_validation_loss": 0.7365601658821106,
1062
+ "eval_validation_runtime": 190.0607,
1063
+ "eval_validation_samples_per_second": 0.726,
1064
+ "eval_validation_steps_per_second": 0.726,
1065
+ "step": 4301
1066
+ },
1067
+ {
1068
+ "epoch": 0.9,
1069
+ "eval_validation_privacy_sources_loss": 0.7365601658821106,
1070
+ "eval_validation_privacy_sources_runtime": 190.1229,
1071
+ "eval_validation_privacy_sources_samples_per_second": 0.726,
1072
+ "eval_validation_privacy_sources_steps_per_second": 0.726,
1073
+ "step": 4301
1074
+ },
1075
+ {
1076
+ "epoch": 0.9,
1077
+ "eval_validation_agenda_digitale_loss": 1.407541036605835,
1078
+ "eval_validation_agenda_digitale_runtime": 170.8311,
1079
+ "eval_validation_agenda_digitale_samples_per_second": 0.726,
1080
+ "eval_validation_agenda_digitale_steps_per_second": 0.726,
1081
+ "step": 4301
1082
+ },
1083
+ {
1084
+ "epoch": 0.9,
1085
+ "eval_validation_legal_articles_loss": 1.2855533361434937,
1086
+ "eval_validation_legal_articles_runtime": 274.1776,
1087
+ "eval_validation_legal_articles_samples_per_second": 0.726,
1088
+ "eval_validation_legal_articles_steps_per_second": 0.726,
1089
+ "step": 4301
1090
+ },
1091
+ {
1092
+ "epoch": 0.9,
1093
+ "eval_validation_leggepertutti_loss": 1.1440407037734985,
1094
+ "eval_validation_leggepertutti_runtime": 26.1983,
1095
+ "eval_validation_leggepertutti_samples_per_second": 0.725,
1096
+ "eval_validation_leggepertutti_steps_per_second": 0.725,
1097
+ "step": 4301
1098
+ }
1099
+ ],
1100
+ "logging_steps": 187,
1101
+ "max_steps": 4765,
1102
+ "num_input_tokens_seen": 0,
1103
+ "num_train_epochs": 1,
1104
+ "save_steps": 187,
1105
+ "total_flos": 4.8102819610591494e+19,
1106
+ "train_batch_size": 1,
1107
+ "trial_name": null,
1108
+ "trial_params": null
1109
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0243941b83ef2de867a93374f8a37948a6e3a9d886f1f852af27a74b60573afc
3
+ size 4792