andrealexroom commited on
Commit
64f3e7b
·
verified ·
1 Parent(s): 9f1fa34

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 sha256:33daab5f14eba883080759ff94adbcf9aeebc92006239c7827f10557d9fadcda
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a142060c95aea116cd54a0d4390eae23e78aaf7ef67f1ec8fb8b220d1c5036b
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b810312604707be48908128bd23ebec50cc45ae8d34fb28dbae0ae277c0c5dd
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:be8af846f57b1cf88f1e2217a1c3988a3d9c2318e3438fb8488e456def0d7346
3
+ size 28967182666
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3e429bde762c36daf33ddcd863fe8e4a9386fce953bf5dd0a2dc17c1e3bc5a
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874e13949c83a8e79285be006762239883285abc1d181ec7e87a771163443136
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,963 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.47685298033112705,
5
+ "eval_steps": 187,
6
+ "global_step": 3179,
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": 6.90625,
14
+ "learning_rate": 1e-05,
15
+ "loss": 1.6495,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.03,
20
+ "grad_norm": 3.78125,
21
+ "learning_rate": 1e-05,
22
+ "loss": 1.4166,
23
+ "step": 187
24
+ },
25
+ {
26
+ "epoch": 0.03,
27
+ "eval_validation_loss": 0.991816520690918,
28
+ "eval_validation_runtime": 195.9748,
29
+ "eval_validation_samples_per_second": 1.444,
30
+ "eval_validation_steps_per_second": 0.725,
31
+ "step": 187
32
+ },
33
+ {
34
+ "epoch": 0.03,
35
+ "eval_validation_privacy_sources_loss": 0.991816520690918,
36
+ "eval_validation_privacy_sources_runtime": 194.2107,
37
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
38
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
39
+ "step": 187
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "eval_validation_agenda_digitale_loss": 1.5510241985321045,
44
+ "eval_validation_agenda_digitale_runtime": 175.3431,
45
+ "eval_validation_agenda_digitale_samples_per_second": 1.449,
46
+ "eval_validation_agenda_digitale_steps_per_second": 0.724,
47
+ "step": 187
48
+ },
49
+ {
50
+ "epoch": 0.03,
51
+ "eval_validation_legal_articles_loss": 1.4495986700057983,
52
+ "eval_validation_legal_articles_runtime": 283.197,
53
+ "eval_validation_legal_articles_samples_per_second": 1.444,
54
+ "eval_validation_legal_articles_steps_per_second": 0.724,
55
+ "step": 187
56
+ },
57
+ {
58
+ "epoch": 0.03,
59
+ "eval_validation_leggepertutti_loss": 1.3122680187225342,
60
+ "eval_validation_leggepertutti_runtime": 32.5548,
61
+ "eval_validation_leggepertutti_samples_per_second": 1.444,
62
+ "eval_validation_leggepertutti_steps_per_second": 0.737,
63
+ "step": 187
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "eval_validation_stack_loss": 0.6871374249458313,
68
+ "eval_validation_stack_runtime": 150.2683,
69
+ "eval_validation_stack_samples_per_second": 1.457,
70
+ "eval_validation_stack_steps_per_second": 0.732,
71
+ "step": 187
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "grad_norm": 3.09375,
76
+ "learning_rate": 1e-05,
77
+ "loss": 1.3446,
78
+ "step": 374
79
+ },
80
+ {
81
+ "epoch": 0.06,
82
+ "eval_validation_loss": 0.9406045079231262,
83
+ "eval_validation_runtime": 194.1728,
84
+ "eval_validation_samples_per_second": 1.457,
85
+ "eval_validation_steps_per_second": 0.731,
86
+ "step": 374
87
+ },
88
+ {
89
+ "epoch": 0.06,
90
+ "eval_validation_privacy_sources_loss": 0.9406045079231262,
91
+ "eval_validation_privacy_sources_runtime": 194.2005,
92
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
93
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
94
+ "step": 374
95
+ },
96
+ {
97
+ "epoch": 0.06,
98
+ "eval_validation_agenda_digitale_loss": 1.5328806638717651,
99
+ "eval_validation_agenda_digitale_runtime": 174.3518,
100
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
101
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
102
+ "step": 374
103
+ },
104
+ {
105
+ "epoch": 0.06,
106
+ "eval_validation_legal_articles_loss": 1.4279789924621582,
107
+ "eval_validation_legal_articles_runtime": 280.5994,
108
+ "eval_validation_legal_articles_samples_per_second": 1.458,
109
+ "eval_validation_legal_articles_steps_per_second": 0.731,
110
+ "step": 374
111
+ },
112
+ {
113
+ "epoch": 0.06,
114
+ "eval_validation_leggepertutti_loss": 1.2925792932510376,
115
+ "eval_validation_leggepertutti_runtime": 32.277,
116
+ "eval_validation_leggepertutti_samples_per_second": 1.456,
117
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
118
+ "step": 374
119
+ },
120
+ {
121
+ "epoch": 0.06,
122
+ "eval_validation_stack_loss": 0.6686830520629883,
123
+ "eval_validation_stack_runtime": 150.3133,
124
+ "eval_validation_stack_samples_per_second": 1.457,
125
+ "eval_validation_stack_steps_per_second": 0.732,
126
+ "step": 374
127
+ },
128
+ {
129
+ "epoch": 0.08,
130
+ "grad_norm": 3.28125,
131
+ "learning_rate": 1e-05,
132
+ "loss": 1.319,
133
+ "step": 561
134
+ },
135
+ {
136
+ "epoch": 0.08,
137
+ "eval_validation_loss": 0.9115561842918396,
138
+ "eval_validation_runtime": 194.2115,
139
+ "eval_validation_samples_per_second": 1.457,
140
+ "eval_validation_steps_per_second": 0.731,
141
+ "step": 561
142
+ },
143
+ {
144
+ "epoch": 0.08,
145
+ "eval_validation_privacy_sources_loss": 0.9115561842918396,
146
+ "eval_validation_privacy_sources_runtime": 194.1897,
147
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
148
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
149
+ "step": 561
150
+ },
151
+ {
152
+ "epoch": 0.08,
153
+ "eval_validation_agenda_digitale_loss": 1.5136183500289917,
154
+ "eval_validation_agenda_digitale_runtime": 174.2245,
155
+ "eval_validation_agenda_digitale_samples_per_second": 1.458,
156
+ "eval_validation_agenda_digitale_steps_per_second": 0.729,
157
+ "step": 561
158
+ },
159
+ {
160
+ "epoch": 0.08,
161
+ "eval_validation_legal_articles_loss": 1.4088979959487915,
162
+ "eval_validation_legal_articles_runtime": 280.593,
163
+ "eval_validation_legal_articles_samples_per_second": 1.458,
164
+ "eval_validation_legal_articles_steps_per_second": 0.731,
165
+ "step": 561
166
+ },
167
+ {
168
+ "epoch": 0.08,
169
+ "eval_validation_leggepertutti_loss": 1.2769514322280884,
170
+ "eval_validation_leggepertutti_runtime": 32.2704,
171
+ "eval_validation_leggepertutti_samples_per_second": 1.456,
172
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
173
+ "step": 561
174
+ },
175
+ {
176
+ "epoch": 0.08,
177
+ "eval_validation_stack_loss": 0.6623967289924622,
178
+ "eval_validation_stack_runtime": 150.2837,
179
+ "eval_validation_stack_samples_per_second": 1.457,
180
+ "eval_validation_stack_steps_per_second": 0.732,
181
+ "step": 561
182
+ },
183
+ {
184
+ "epoch": 0.11,
185
+ "grad_norm": 3.546875,
186
+ "learning_rate": 1e-05,
187
+ "loss": 1.294,
188
+ "step": 748
189
+ },
190
+ {
191
+ "epoch": 0.11,
192
+ "eval_validation_loss": 0.8909656405448914,
193
+ "eval_validation_runtime": 194.2194,
194
+ "eval_validation_samples_per_second": 1.457,
195
+ "eval_validation_steps_per_second": 0.731,
196
+ "step": 748
197
+ },
198
+ {
199
+ "epoch": 0.11,
200
+ "eval_validation_privacy_sources_loss": 0.8909656405448914,
201
+ "eval_validation_privacy_sources_runtime": 194.171,
202
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
203
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
204
+ "step": 748
205
+ },
206
+ {
207
+ "epoch": 0.11,
208
+ "eval_validation_agenda_digitale_loss": 1.5061848163604736,
209
+ "eval_validation_agenda_digitale_runtime": 174.3848,
210
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
211
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
212
+ "step": 748
213
+ },
214
+ {
215
+ "epoch": 0.11,
216
+ "eval_validation_legal_articles_loss": 1.4024670124053955,
217
+ "eval_validation_legal_articles_runtime": 280.6499,
218
+ "eval_validation_legal_articles_samples_per_second": 1.457,
219
+ "eval_validation_legal_articles_steps_per_second": 0.73,
220
+ "step": 748
221
+ },
222
+ {
223
+ "epoch": 0.11,
224
+ "eval_validation_leggepertutti_loss": 1.2745715379714966,
225
+ "eval_validation_leggepertutti_runtime": 32.2457,
226
+ "eval_validation_leggepertutti_samples_per_second": 1.458,
227
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
228
+ "step": 748
229
+ },
230
+ {
231
+ "epoch": 0.11,
232
+ "eval_validation_stack_loss": 0.6597607135772705,
233
+ "eval_validation_stack_runtime": 150.355,
234
+ "eval_validation_stack_samples_per_second": 1.457,
235
+ "eval_validation_stack_steps_per_second": 0.732,
236
+ "step": 748
237
+ },
238
+ {
239
+ "epoch": 0.14,
240
+ "grad_norm": 3.328125,
241
+ "learning_rate": 1e-05,
242
+ "loss": 1.288,
243
+ "step": 935
244
+ },
245
+ {
246
+ "epoch": 0.14,
247
+ "eval_validation_loss": 0.8725160956382751,
248
+ "eval_validation_runtime": 194.2879,
249
+ "eval_validation_samples_per_second": 1.457,
250
+ "eval_validation_steps_per_second": 0.731,
251
+ "step": 935
252
+ },
253
+ {
254
+ "epoch": 0.14,
255
+ "eval_validation_privacy_sources_loss": 0.8725160956382751,
256
+ "eval_validation_privacy_sources_runtime": 194.1987,
257
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
258
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
259
+ "step": 935
260
+ },
261
+ {
262
+ "epoch": 0.14,
263
+ "eval_validation_agenda_digitale_loss": 1.495468020439148,
264
+ "eval_validation_agenda_digitale_runtime": 174.279,
265
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
266
+ "eval_validation_agenda_digitale_steps_per_second": 0.729,
267
+ "step": 935
268
+ },
269
+ {
270
+ "epoch": 0.14,
271
+ "eval_validation_legal_articles_loss": 1.3915969133377075,
272
+ "eval_validation_legal_articles_runtime": 280.636,
273
+ "eval_validation_legal_articles_samples_per_second": 1.457,
274
+ "eval_validation_legal_articles_steps_per_second": 0.73,
275
+ "step": 935
276
+ },
277
+ {
278
+ "epoch": 0.14,
279
+ "eval_validation_leggepertutti_loss": 1.2664177417755127,
280
+ "eval_validation_leggepertutti_runtime": 32.3128,
281
+ "eval_validation_leggepertutti_samples_per_second": 1.455,
282
+ "eval_validation_leggepertutti_steps_per_second": 0.743,
283
+ "step": 935
284
+ },
285
+ {
286
+ "epoch": 0.14,
287
+ "eval_validation_stack_loss": 0.671289324760437,
288
+ "eval_validation_stack_runtime": 150.2763,
289
+ "eval_validation_stack_samples_per_second": 1.457,
290
+ "eval_validation_stack_steps_per_second": 0.732,
291
+ "step": 935
292
+ },
293
+ {
294
+ "epoch": 0.17,
295
+ "grad_norm": 3.03125,
296
+ "learning_rate": 1e-05,
297
+ "loss": 1.2656,
298
+ "step": 1122
299
+ },
300
+ {
301
+ "epoch": 0.17,
302
+ "eval_validation_loss": 0.8576221466064453,
303
+ "eval_validation_runtime": 194.1565,
304
+ "eval_validation_samples_per_second": 1.458,
305
+ "eval_validation_steps_per_second": 0.731,
306
+ "step": 1122
307
+ },
308
+ {
309
+ "epoch": 0.17,
310
+ "eval_validation_privacy_sources_loss": 0.8576221466064453,
311
+ "eval_validation_privacy_sources_runtime": 194.2133,
312
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
313
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
314
+ "step": 1122
315
+ },
316
+ {
317
+ "epoch": 0.17,
318
+ "eval_validation_agenda_digitale_loss": 1.4900646209716797,
319
+ "eval_validation_agenda_digitale_runtime": 174.3063,
320
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
321
+ "eval_validation_agenda_digitale_steps_per_second": 0.729,
322
+ "step": 1122
323
+ },
324
+ {
325
+ "epoch": 0.17,
326
+ "eval_validation_legal_articles_loss": 1.3864495754241943,
327
+ "eval_validation_legal_articles_runtime": 280.7754,
328
+ "eval_validation_legal_articles_samples_per_second": 1.457,
329
+ "eval_validation_legal_articles_steps_per_second": 0.73,
330
+ "step": 1122
331
+ },
332
+ {
333
+ "epoch": 0.17,
334
+ "eval_validation_leggepertutti_loss": 1.2697046995162964,
335
+ "eval_validation_leggepertutti_runtime": 32.2704,
336
+ "eval_validation_leggepertutti_samples_per_second": 1.456,
337
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
338
+ "step": 1122
339
+ },
340
+ {
341
+ "epoch": 0.17,
342
+ "eval_validation_stack_loss": 0.6624614596366882,
343
+ "eval_validation_stack_runtime": 150.2734,
344
+ "eval_validation_stack_samples_per_second": 1.457,
345
+ "eval_validation_stack_steps_per_second": 0.732,
346
+ "step": 1122
347
+ },
348
+ {
349
+ "epoch": 0.2,
350
+ "grad_norm": 3.875,
351
+ "learning_rate": 1e-05,
352
+ "loss": 1.262,
353
+ "step": 1309
354
+ },
355
+ {
356
+ "epoch": 0.2,
357
+ "eval_validation_loss": 0.8469824194908142,
358
+ "eval_validation_runtime": 194.2241,
359
+ "eval_validation_samples_per_second": 1.457,
360
+ "eval_validation_steps_per_second": 0.731,
361
+ "step": 1309
362
+ },
363
+ {
364
+ "epoch": 0.2,
365
+ "eval_validation_privacy_sources_loss": 0.8469824194908142,
366
+ "eval_validation_privacy_sources_runtime": 194.3211,
367
+ "eval_validation_privacy_sources_samples_per_second": 1.456,
368
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
369
+ "step": 1309
370
+ },
371
+ {
372
+ "epoch": 0.2,
373
+ "eval_validation_agenda_digitale_loss": 1.480202555656433,
374
+ "eval_validation_agenda_digitale_runtime": 174.3439,
375
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
376
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
377
+ "step": 1309
378
+ },
379
+ {
380
+ "epoch": 0.2,
381
+ "eval_validation_legal_articles_loss": 1.37553870677948,
382
+ "eval_validation_legal_articles_runtime": 280.682,
383
+ "eval_validation_legal_articles_samples_per_second": 1.457,
384
+ "eval_validation_legal_articles_steps_per_second": 0.73,
385
+ "step": 1309
386
+ },
387
+ {
388
+ "epoch": 0.2,
389
+ "eval_validation_leggepertutti_loss": 1.2508999109268188,
390
+ "eval_validation_leggepertutti_runtime": 32.2884,
391
+ "eval_validation_leggepertutti_samples_per_second": 1.456,
392
+ "eval_validation_leggepertutti_steps_per_second": 0.743,
393
+ "step": 1309
394
+ },
395
+ {
396
+ "epoch": 0.2,
397
+ "eval_validation_stack_loss": 0.6656920313835144,
398
+ "eval_validation_stack_runtime": 150.3132,
399
+ "eval_validation_stack_samples_per_second": 1.457,
400
+ "eval_validation_stack_steps_per_second": 0.732,
401
+ "step": 1309
402
+ },
403
+ {
404
+ "epoch": 0.22,
405
+ "grad_norm": 4.21875,
406
+ "learning_rate": 1e-05,
407
+ "loss": 1.2504,
408
+ "step": 1496
409
+ },
410
+ {
411
+ "epoch": 0.22,
412
+ "eval_validation_loss": 0.8391339778900146,
413
+ "eval_validation_runtime": 194.3964,
414
+ "eval_validation_samples_per_second": 1.456,
415
+ "eval_validation_steps_per_second": 0.73,
416
+ "step": 1496
417
+ },
418
+ {
419
+ "epoch": 0.22,
420
+ "eval_validation_privacy_sources_loss": 0.8391339778900146,
421
+ "eval_validation_privacy_sources_runtime": 194.3537,
422
+ "eval_validation_privacy_sources_samples_per_second": 1.456,
423
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
424
+ "step": 1496
425
+ },
426
+ {
427
+ "epoch": 0.22,
428
+ "eval_validation_agenda_digitale_loss": 1.4769794940948486,
429
+ "eval_validation_agenda_digitale_runtime": 174.3769,
430
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
431
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
432
+ "step": 1496
433
+ },
434
+ {
435
+ "epoch": 0.22,
436
+ "eval_validation_legal_articles_loss": 1.3722717761993408,
437
+ "eval_validation_legal_articles_runtime": 280.8228,
438
+ "eval_validation_legal_articles_samples_per_second": 1.456,
439
+ "eval_validation_legal_articles_steps_per_second": 0.73,
440
+ "step": 1496
441
+ },
442
+ {
443
+ "epoch": 0.22,
444
+ "eval_validation_leggepertutti_loss": 1.2524480819702148,
445
+ "eval_validation_leggepertutti_runtime": 32.2872,
446
+ "eval_validation_leggepertutti_samples_per_second": 1.456,
447
+ "eval_validation_leggepertutti_steps_per_second": 0.743,
448
+ "step": 1496
449
+ },
450
+ {
451
+ "epoch": 0.22,
452
+ "eval_validation_stack_loss": 0.6621661186218262,
453
+ "eval_validation_stack_runtime": 150.4485,
454
+ "eval_validation_stack_samples_per_second": 1.456,
455
+ "eval_validation_stack_steps_per_second": 0.731,
456
+ "step": 1496
457
+ },
458
+ {
459
+ "epoch": 0.25,
460
+ "grad_norm": 3.859375,
461
+ "learning_rate": 1e-05,
462
+ "loss": 1.2451,
463
+ "step": 1683
464
+ },
465
+ {
466
+ "epoch": 0.25,
467
+ "eval_validation_loss": 0.8308941125869751,
468
+ "eval_validation_runtime": 194.3971,
469
+ "eval_validation_samples_per_second": 1.456,
470
+ "eval_validation_steps_per_second": 0.73,
471
+ "step": 1683
472
+ },
473
+ {
474
+ "epoch": 0.25,
475
+ "eval_validation_privacy_sources_loss": 0.8308941125869751,
476
+ "eval_validation_privacy_sources_runtime": 194.3567,
477
+ "eval_validation_privacy_sources_samples_per_second": 1.456,
478
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
479
+ "step": 1683
480
+ },
481
+ {
482
+ "epoch": 0.25,
483
+ "eval_validation_agenda_digitale_loss": 1.4716005325317383,
484
+ "eval_validation_agenda_digitale_runtime": 174.5117,
485
+ "eval_validation_agenda_digitale_samples_per_second": 1.455,
486
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
487
+ "step": 1683
488
+ },
489
+ {
490
+ "epoch": 0.25,
491
+ "eval_validation_legal_articles_loss": 1.3668161630630493,
492
+ "eval_validation_legal_articles_runtime": 281.0759,
493
+ "eval_validation_legal_articles_samples_per_second": 1.455,
494
+ "eval_validation_legal_articles_steps_per_second": 0.729,
495
+ "step": 1683
496
+ },
497
+ {
498
+ "epoch": 0.25,
499
+ "eval_validation_leggepertutti_loss": 1.2450143098831177,
500
+ "eval_validation_leggepertutti_runtime": 32.2789,
501
+ "eval_validation_leggepertutti_samples_per_second": 1.456,
502
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
503
+ "step": 1683
504
+ },
505
+ {
506
+ "epoch": 0.25,
507
+ "eval_validation_stack_loss": 0.6625425219535828,
508
+ "eval_validation_stack_runtime": 150.5316,
509
+ "eval_validation_stack_samples_per_second": 1.455,
510
+ "eval_validation_stack_steps_per_second": 0.731,
511
+ "step": 1683
512
+ },
513
+ {
514
+ "epoch": 0.28,
515
+ "grad_norm": 3.3125,
516
+ "learning_rate": 1e-05,
517
+ "loss": 1.2288,
518
+ "step": 1870
519
+ },
520
+ {
521
+ "epoch": 0.28,
522
+ "eval_validation_loss": 0.8248987197875977,
523
+ "eval_validation_runtime": 194.4241,
524
+ "eval_validation_samples_per_second": 1.456,
525
+ "eval_validation_steps_per_second": 0.73,
526
+ "step": 1870
527
+ },
528
+ {
529
+ "epoch": 0.28,
530
+ "eval_validation_privacy_sources_loss": 0.8248987197875977,
531
+ "eval_validation_privacy_sources_runtime": 194.4297,
532
+ "eval_validation_privacy_sources_samples_per_second": 1.456,
533
+ "eval_validation_privacy_sources_steps_per_second": 0.73,
534
+ "step": 1870
535
+ },
536
+ {
537
+ "epoch": 0.28,
538
+ "eval_validation_agenda_digitale_loss": 1.4680345058441162,
539
+ "eval_validation_agenda_digitale_runtime": 174.3517,
540
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
541
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
542
+ "step": 1870
543
+ },
544
+ {
545
+ "epoch": 0.28,
546
+ "eval_validation_legal_articles_loss": 1.3631649017333984,
547
+ "eval_validation_legal_articles_runtime": 280.9131,
548
+ "eval_validation_legal_articles_samples_per_second": 1.456,
549
+ "eval_validation_legal_articles_steps_per_second": 0.73,
550
+ "step": 1870
551
+ },
552
+ {
553
+ "epoch": 0.28,
554
+ "eval_validation_leggepertutti_loss": 1.2426080703735352,
555
+ "eval_validation_leggepertutti_runtime": 32.2719,
556
+ "eval_validation_leggepertutti_samples_per_second": 1.456,
557
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
558
+ "step": 1870
559
+ },
560
+ {
561
+ "epoch": 0.28,
562
+ "eval_validation_stack_loss": 0.6634118556976318,
563
+ "eval_validation_stack_runtime": 150.5416,
564
+ "eval_validation_stack_samples_per_second": 1.455,
565
+ "eval_validation_stack_steps_per_second": 0.731,
566
+ "step": 1870
567
+ },
568
+ {
569
+ "epoch": 0.31,
570
+ "grad_norm": 2.609375,
571
+ "learning_rate": 1e-05,
572
+ "loss": 1.2317,
573
+ "step": 2057
574
+ },
575
+ {
576
+ "epoch": 0.31,
577
+ "eval_validation_loss": 0.8174241781234741,
578
+ "eval_validation_runtime": 194.3262,
579
+ "eval_validation_samples_per_second": 1.456,
580
+ "eval_validation_steps_per_second": 0.731,
581
+ "step": 2057
582
+ },
583
+ {
584
+ "epoch": 0.31,
585
+ "eval_validation_privacy_sources_loss": 0.8174241781234741,
586
+ "eval_validation_privacy_sources_runtime": 194.5246,
587
+ "eval_validation_privacy_sources_samples_per_second": 1.455,
588
+ "eval_validation_privacy_sources_steps_per_second": 0.73,
589
+ "step": 2057
590
+ },
591
+ {
592
+ "epoch": 0.31,
593
+ "eval_validation_agenda_digitale_loss": 1.4647732973098755,
594
+ "eval_validation_agenda_digitale_runtime": 174.3916,
595
+ "eval_validation_agenda_digitale_samples_per_second": 1.456,
596
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
597
+ "step": 2057
598
+ },
599
+ {
600
+ "epoch": 0.31,
601
+ "eval_validation_legal_articles_loss": 1.3598822355270386,
602
+ "eval_validation_legal_articles_runtime": 281.1038,
603
+ "eval_validation_legal_articles_samples_per_second": 1.455,
604
+ "eval_validation_legal_articles_steps_per_second": 0.729,
605
+ "step": 2057
606
+ },
607
+ {
608
+ "epoch": 0.31,
609
+ "eval_validation_leggepertutti_loss": 1.2417668104171753,
610
+ "eval_validation_leggepertutti_runtime": 32.3021,
611
+ "eval_validation_leggepertutti_samples_per_second": 1.455,
612
+ "eval_validation_leggepertutti_steps_per_second": 0.743,
613
+ "step": 2057
614
+ },
615
+ {
616
+ "epoch": 0.31,
617
+ "eval_validation_stack_loss": 0.6850900053977966,
618
+ "eval_validation_stack_runtime": 150.5998,
619
+ "eval_validation_stack_samples_per_second": 1.454,
620
+ "eval_validation_stack_steps_per_second": 0.73,
621
+ "step": 2057
622
+ },
623
+ {
624
+ "epoch": 0.34,
625
+ "grad_norm": 3.125,
626
+ "learning_rate": 1e-05,
627
+ "loss": 1.2187,
628
+ "step": 2244
629
+ },
630
+ {
631
+ "epoch": 0.34,
632
+ "eval_validation_loss": 0.8112402558326721,
633
+ "eval_validation_runtime": 194.4175,
634
+ "eval_validation_samples_per_second": 1.456,
635
+ "eval_validation_steps_per_second": 0.73,
636
+ "step": 2244
637
+ },
638
+ {
639
+ "epoch": 0.34,
640
+ "eval_validation_privacy_sources_loss": 0.8112402558326721,
641
+ "eval_validation_privacy_sources_runtime": 194.4289,
642
+ "eval_validation_privacy_sources_samples_per_second": 1.456,
643
+ "eval_validation_privacy_sources_steps_per_second": 0.73,
644
+ "step": 2244
645
+ },
646
+ {
647
+ "epoch": 0.34,
648
+ "eval_validation_agenda_digitale_loss": 1.4576207399368286,
649
+ "eval_validation_agenda_digitale_runtime": 174.5397,
650
+ "eval_validation_agenda_digitale_samples_per_second": 1.455,
651
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
652
+ "step": 2244
653
+ },
654
+ {
655
+ "epoch": 0.34,
656
+ "eval_validation_legal_articles_loss": 1.353047490119934,
657
+ "eval_validation_legal_articles_runtime": 281.0845,
658
+ "eval_validation_legal_articles_samples_per_second": 1.455,
659
+ "eval_validation_legal_articles_steps_per_second": 0.729,
660
+ "step": 2244
661
+ },
662
+ {
663
+ "epoch": 0.34,
664
+ "eval_validation_leggepertutti_loss": 1.2340008020401,
665
+ "eval_validation_leggepertutti_runtime": 32.2969,
666
+ "eval_validation_leggepertutti_samples_per_second": 1.455,
667
+ "eval_validation_leggepertutti_steps_per_second": 0.743,
668
+ "step": 2244
669
+ },
670
+ {
671
+ "epoch": 0.34,
672
+ "eval_validation_stack_loss": 0.6579957604408264,
673
+ "eval_validation_stack_runtime": 150.4781,
674
+ "eval_validation_stack_samples_per_second": 1.455,
675
+ "eval_validation_stack_steps_per_second": 0.731,
676
+ "step": 2244
677
+ },
678
+ {
679
+ "epoch": 0.36,
680
+ "grad_norm": 3.15625,
681
+ "learning_rate": 1e-05,
682
+ "loss": 1.2216,
683
+ "step": 2431
684
+ },
685
+ {
686
+ "epoch": 0.36,
687
+ "eval_validation_loss": 0.8057372570037842,
688
+ "eval_validation_runtime": 194.2262,
689
+ "eval_validation_samples_per_second": 1.457,
690
+ "eval_validation_steps_per_second": 0.731,
691
+ "step": 2431
692
+ },
693
+ {
694
+ "epoch": 0.36,
695
+ "eval_validation_privacy_sources_loss": 0.8057372570037842,
696
+ "eval_validation_privacy_sources_runtime": 194.1619,
697
+ "eval_validation_privacy_sources_samples_per_second": 1.458,
698
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
699
+ "step": 2431
700
+ },
701
+ {
702
+ "epoch": 0.36,
703
+ "eval_validation_agenda_digitale_loss": 1.4539768695831299,
704
+ "eval_validation_agenda_digitale_runtime": 174.2757,
705
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
706
+ "eval_validation_agenda_digitale_steps_per_second": 0.729,
707
+ "step": 2431
708
+ },
709
+ {
710
+ "epoch": 0.36,
711
+ "eval_validation_legal_articles_loss": 1.3490097522735596,
712
+ "eval_validation_legal_articles_runtime": 280.6393,
713
+ "eval_validation_legal_articles_samples_per_second": 1.457,
714
+ "eval_validation_legal_articles_steps_per_second": 0.73,
715
+ "step": 2431
716
+ },
717
+ {
718
+ "epoch": 0.36,
719
+ "eval_validation_leggepertutti_loss": 1.2318819761276245,
720
+ "eval_validation_leggepertutti_runtime": 32.2703,
721
+ "eval_validation_leggepertutti_samples_per_second": 1.456,
722
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
723
+ "step": 2431
724
+ },
725
+ {
726
+ "epoch": 0.36,
727
+ "eval_validation_stack_loss": 0.6572250127792358,
728
+ "eval_validation_stack_runtime": 150.3723,
729
+ "eval_validation_stack_samples_per_second": 1.456,
730
+ "eval_validation_stack_steps_per_second": 0.732,
731
+ "step": 2431
732
+ },
733
+ {
734
+ "epoch": 0.39,
735
+ "grad_norm": 2.921875,
736
+ "learning_rate": 1e-05,
737
+ "loss": 1.2137,
738
+ "step": 2618
739
+ },
740
+ {
741
+ "epoch": 0.39,
742
+ "eval_validation_loss": 0.8002484440803528,
743
+ "eval_validation_runtime": 194.1411,
744
+ "eval_validation_samples_per_second": 1.458,
745
+ "eval_validation_steps_per_second": 0.731,
746
+ "step": 2618
747
+ },
748
+ {
749
+ "epoch": 0.39,
750
+ "eval_validation_privacy_sources_loss": 0.8002484440803528,
751
+ "eval_validation_privacy_sources_runtime": 194.1642,
752
+ "eval_validation_privacy_sources_samples_per_second": 1.458,
753
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
754
+ "step": 2618
755
+ },
756
+ {
757
+ "epoch": 0.39,
758
+ "eval_validation_agenda_digitale_loss": 1.4513797760009766,
759
+ "eval_validation_agenda_digitale_runtime": 174.2611,
760
+ "eval_validation_agenda_digitale_samples_per_second": 1.458,
761
+ "eval_validation_agenda_digitale_steps_per_second": 0.729,
762
+ "step": 2618
763
+ },
764
+ {
765
+ "epoch": 0.39,
766
+ "eval_validation_legal_articles_loss": 1.3452379703521729,
767
+ "eval_validation_legal_articles_runtime": 280.6444,
768
+ "eval_validation_legal_articles_samples_per_second": 1.457,
769
+ "eval_validation_legal_articles_steps_per_second": 0.73,
770
+ "step": 2618
771
+ },
772
+ {
773
+ "epoch": 0.39,
774
+ "eval_validation_leggepertutti_loss": 1.2279798984527588,
775
+ "eval_validation_leggepertutti_runtime": 32.2374,
776
+ "eval_validation_leggepertutti_samples_per_second": 1.458,
777
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
778
+ "step": 2618
779
+ },
780
+ {
781
+ "epoch": 0.39,
782
+ "eval_validation_stack_loss": 0.658513605594635,
783
+ "eval_validation_stack_runtime": 150.3305,
784
+ "eval_validation_stack_samples_per_second": 1.457,
785
+ "eval_validation_stack_steps_per_second": 0.732,
786
+ "step": 2618
787
+ },
788
+ {
789
+ "epoch": 0.42,
790
+ "grad_norm": 3.234375,
791
+ "learning_rate": 1e-05,
792
+ "loss": 1.2201,
793
+ "step": 2805
794
+ },
795
+ {
796
+ "epoch": 0.42,
797
+ "eval_validation_loss": 0.7958617806434631,
798
+ "eval_validation_runtime": 194.1642,
799
+ "eval_validation_samples_per_second": 1.458,
800
+ "eval_validation_steps_per_second": 0.731,
801
+ "step": 2805
802
+ },
803
+ {
804
+ "epoch": 0.42,
805
+ "eval_validation_privacy_sources_loss": 0.7958617806434631,
806
+ "eval_validation_privacy_sources_runtime": 194.1721,
807
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
808
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
809
+ "step": 2805
810
+ },
811
+ {
812
+ "epoch": 0.42,
813
+ "eval_validation_agenda_digitale_loss": 1.4462895393371582,
814
+ "eval_validation_agenda_digitale_runtime": 174.2261,
815
+ "eval_validation_agenda_digitale_samples_per_second": 1.458,
816
+ "eval_validation_agenda_digitale_steps_per_second": 0.729,
817
+ "step": 2805
818
+ },
819
+ {
820
+ "epoch": 0.42,
821
+ "eval_validation_legal_articles_loss": 1.3407931327819824,
822
+ "eval_validation_legal_articles_runtime": 280.6639,
823
+ "eval_validation_legal_articles_samples_per_second": 1.457,
824
+ "eval_validation_legal_articles_steps_per_second": 0.73,
825
+ "step": 2805
826
+ },
827
+ {
828
+ "epoch": 0.42,
829
+ "eval_validation_leggepertutti_loss": 1.223404884338379,
830
+ "eval_validation_leggepertutti_runtime": 32.2573,
831
+ "eval_validation_leggepertutti_samples_per_second": 1.457,
832
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
833
+ "step": 2805
834
+ },
835
+ {
836
+ "epoch": 0.42,
837
+ "eval_validation_stack_loss": 0.6563575863838196,
838
+ "eval_validation_stack_runtime": 150.1796,
839
+ "eval_validation_stack_samples_per_second": 1.458,
840
+ "eval_validation_stack_steps_per_second": 0.732,
841
+ "step": 2805
842
+ },
843
+ {
844
+ "epoch": 0.45,
845
+ "grad_norm": 3.78125,
846
+ "learning_rate": 1e-05,
847
+ "loss": 1.2215,
848
+ "step": 2992
849
+ },
850
+ {
851
+ "epoch": 0.45,
852
+ "eval_validation_loss": 0.7921054363250732,
853
+ "eval_validation_runtime": 194.1573,
854
+ "eval_validation_samples_per_second": 1.458,
855
+ "eval_validation_steps_per_second": 0.731,
856
+ "step": 2992
857
+ },
858
+ {
859
+ "epoch": 0.45,
860
+ "eval_validation_privacy_sources_loss": 0.7921054363250732,
861
+ "eval_validation_privacy_sources_runtime": 194.2033,
862
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
863
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
864
+ "step": 2992
865
+ },
866
+ {
867
+ "epoch": 0.45,
868
+ "eval_validation_agenda_digitale_loss": 1.4434641599655151,
869
+ "eval_validation_agenda_digitale_runtime": 174.1771,
870
+ "eval_validation_agenda_digitale_samples_per_second": 1.458,
871
+ "eval_validation_agenda_digitale_steps_per_second": 0.729,
872
+ "step": 2992
873
+ },
874
+ {
875
+ "epoch": 0.45,
876
+ "eval_validation_legal_articles_loss": 1.3380062580108643,
877
+ "eval_validation_legal_articles_runtime": 280.5633,
878
+ "eval_validation_legal_articles_samples_per_second": 1.458,
879
+ "eval_validation_legal_articles_steps_per_second": 0.731,
880
+ "step": 2992
881
+ },
882
+ {
883
+ "epoch": 0.45,
884
+ "eval_validation_leggepertutti_loss": 1.2243036031723022,
885
+ "eval_validation_leggepertutti_runtime": 32.2495,
886
+ "eval_validation_leggepertutti_samples_per_second": 1.457,
887
+ "eval_validation_leggepertutti_steps_per_second": 0.744,
888
+ "step": 2992
889
+ },
890
+ {
891
+ "epoch": 0.45,
892
+ "eval_validation_stack_loss": 0.6555092334747314,
893
+ "eval_validation_stack_runtime": 150.2591,
894
+ "eval_validation_stack_samples_per_second": 1.457,
895
+ "eval_validation_stack_steps_per_second": 0.732,
896
+ "step": 2992
897
+ },
898
+ {
899
+ "epoch": 0.48,
900
+ "grad_norm": 3.671875,
901
+ "learning_rate": 1e-05,
902
+ "loss": 1.1871,
903
+ "step": 3179
904
+ },
905
+ {
906
+ "epoch": 0.48,
907
+ "eval_validation_loss": 0.7875866293907166,
908
+ "eval_validation_runtime": 194.215,
909
+ "eval_validation_samples_per_second": 1.457,
910
+ "eval_validation_steps_per_second": 0.731,
911
+ "step": 3179
912
+ },
913
+ {
914
+ "epoch": 0.48,
915
+ "eval_validation_privacy_sources_loss": 0.7875866293907166,
916
+ "eval_validation_privacy_sources_runtime": 194.2832,
917
+ "eval_validation_privacy_sources_samples_per_second": 1.457,
918
+ "eval_validation_privacy_sources_steps_per_second": 0.731,
919
+ "step": 3179
920
+ },
921
+ {
922
+ "epoch": 0.48,
923
+ "eval_validation_agenda_digitale_loss": 1.440475344657898,
924
+ "eval_validation_agenda_digitale_runtime": 174.3856,
925
+ "eval_validation_agenda_digitale_samples_per_second": 1.457,
926
+ "eval_validation_agenda_digitale_steps_per_second": 0.728,
927
+ "step": 3179
928
+ },
929
+ {
930
+ "epoch": 0.48,
931
+ "eval_validation_legal_articles_loss": 1.3334453105926514,
932
+ "eval_validation_legal_articles_runtime": 280.7664,
933
+ "eval_validation_legal_articles_samples_per_second": 1.457,
934
+ "eval_validation_legal_articles_steps_per_second": 0.73,
935
+ "step": 3179
936
+ },
937
+ {
938
+ "epoch": 0.48,
939
+ "eval_validation_leggepertutti_loss": 1.2178949117660522,
940
+ "eval_validation_leggepertutti_runtime": 32.2965,
941
+ "eval_validation_leggepertutti_samples_per_second": 1.455,
942
+ "eval_validation_leggepertutti_steps_per_second": 0.743,
943
+ "step": 3179
944
+ },
945
+ {
946
+ "epoch": 0.48,
947
+ "eval_validation_stack_loss": 0.6562801003456116,
948
+ "eval_validation_stack_runtime": 150.3911,
949
+ "eval_validation_stack_samples_per_second": 1.456,
950
+ "eval_validation_stack_steps_per_second": 0.731,
951
+ "step": 3179
952
+ }
953
+ ],
954
+ "logging_steps": 187,
955
+ "max_steps": 13332,
956
+ "num_input_tokens_seen": 0,
957
+ "num_train_epochs": 2,
958
+ "save_steps": 187,
959
+ "total_flos": 1.7777128986522943e+19,
960
+ "train_batch_size": 1,
961
+ "trial_name": null,
962
+ "trial_params": null
963
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf2a9148e9bea1d113ef2d2a437699d4398014244e8ed4d313390e212b2ed05
3
+ size 4792