andrealexroom commited on
Commit
2c484dc
·
verified ·
1 Parent(s): 3fbc544

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 sha256:78bfae802a230ecbfa6219ab119415f5565a82b5aee22089a8413295915e0146
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:a244954f4dbe4bc5119de46f6c50373ab1bbb40ecb816d8709afb998b67952cf
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:cdf6184baef07bf7c53afd979d86a2b1aedf5c13f27b13599782dd1520783a50
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 sha256:0a080eb50f7a9c25b1f055537efce55e5b5dc9024f576475be08f1aebf76e3b5
3
+ size 28967182666
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63bb73380132bc8e066871e58db453fce21e6e35ea60be588fc267ffe6d0742a
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb10a45a16335fd90a78c88362e448ed62356cc58772045e40296ea7a22adf6
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1513 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.42571669477234403,
5
+ "eval_steps": 187,
6
+ "global_step": 5049,
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": 8.5,
14
+ "learning_rate": 1e-05,
15
+ "loss": 1.9119,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.02,
20
+ "grad_norm": 4.59375,
21
+ "learning_rate": 1e-05,
22
+ "loss": 1.7164,
23
+ "step": 187
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "eval_validation_privacy_sources_loss": 1.0334585905075073,
28
+ "eval_validation_privacy_sources_runtime": 212.2756,
29
+ "eval_validation_privacy_sources_samples_per_second": 1.804,
30
+ "eval_validation_privacy_sources_steps_per_second": 0.904,
31
+ "step": 187
32
+ },
33
+ {
34
+ "epoch": 0.02,
35
+ "eval_validation_agenda_digitale_loss": 1.5160526037216187,
36
+ "eval_validation_agenda_digitale_runtime": 188.4106,
37
+ "eval_validation_agenda_digitale_samples_per_second": 1.805,
38
+ "eval_validation_agenda_digitale_steps_per_second": 0.902,
39
+ "step": 187
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "eval_validation_leggepertutti_loss": 1.3417482376098633,
44
+ "eval_validation_leggepertutti_runtime": 35.8837,
45
+ "eval_validation_leggepertutti_samples_per_second": 1.811,
46
+ "eval_validation_leggepertutti_steps_per_second": 0.92,
47
+ "step": 187
48
+ },
49
+ {
50
+ "epoch": 0.02,
51
+ "eval_validation_altalexprivacy_loss": 1.3672271966934204,
52
+ "eval_validation_altalexprivacy_runtime": 58.6063,
53
+ "eval_validation_altalexprivacy_samples_per_second": 1.809,
54
+ "eval_validation_altalexprivacy_steps_per_second": 0.904,
55
+ "step": 187
56
+ },
57
+ {
58
+ "epoch": 0.02,
59
+ "eval_validation_mc4_it_loss": 1.9217756986618042,
60
+ "eval_validation_mc4_it_runtime": 78.6277,
61
+ "eval_validation_mc4_it_samples_per_second": 1.806,
62
+ "eval_validation_mc4_it_steps_per_second": 0.903,
63
+ "step": 187
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "eval_validation_dolma_loss": 1.9627543687820435,
68
+ "eval_validation_dolma_runtime": 54.0088,
69
+ "eval_validation_dolma_samples_per_second": 1.815,
70
+ "eval_validation_dolma_steps_per_second": 0.907,
71
+ "step": 187
72
+ },
73
+ {
74
+ "epoch": 0.03,
75
+ "grad_norm": 3.859375,
76
+ "learning_rate": 1e-05,
77
+ "loss": 1.6579,
78
+ "step": 374
79
+ },
80
+ {
81
+ "epoch": 0.03,
82
+ "eval_validation_privacy_sources_loss": 0.9830030798912048,
83
+ "eval_validation_privacy_sources_runtime": 210.811,
84
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
85
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
86
+ "step": 374
87
+ },
88
+ {
89
+ "epoch": 0.03,
90
+ "eval_validation_agenda_digitale_loss": 1.4846152067184448,
91
+ "eval_validation_agenda_digitale_runtime": 187.1837,
92
+ "eval_validation_agenda_digitale_samples_per_second": 1.816,
93
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
94
+ "step": 374
95
+ },
96
+ {
97
+ "epoch": 0.03,
98
+ "eval_validation_leggepertutti_loss": 1.3172152042388916,
99
+ "eval_validation_leggepertutti_runtime": 35.7866,
100
+ "eval_validation_leggepertutti_samples_per_second": 1.816,
101
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
102
+ "step": 374
103
+ },
104
+ {
105
+ "epoch": 0.03,
106
+ "eval_validation_altalexprivacy_loss": 1.3326139450073242,
107
+ "eval_validation_altalexprivacy_runtime": 58.3381,
108
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
109
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
110
+ "step": 374
111
+ },
112
+ {
113
+ "epoch": 0.03,
114
+ "eval_validation_mc4_it_loss": 1.8915678262710571,
115
+ "eval_validation_mc4_it_runtime": 78.169,
116
+ "eval_validation_mc4_it_samples_per_second": 1.817,
117
+ "eval_validation_mc4_it_steps_per_second": 0.908,
118
+ "step": 374
119
+ },
120
+ {
121
+ "epoch": 0.03,
122
+ "eval_validation_dolma_loss": 1.9608409404754639,
123
+ "eval_validation_dolma_runtime": 53.9716,
124
+ "eval_validation_dolma_samples_per_second": 1.816,
125
+ "eval_validation_dolma_steps_per_second": 0.908,
126
+ "step": 374
127
+ },
128
+ {
129
+ "epoch": 0.05,
130
+ "grad_norm": 3.484375,
131
+ "learning_rate": 1e-05,
132
+ "loss": 1.6402,
133
+ "step": 561
134
+ },
135
+ {
136
+ "epoch": 0.05,
137
+ "eval_validation_privacy_sources_loss": 0.9559596180915833,
138
+ "eval_validation_privacy_sources_runtime": 210.7246,
139
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
140
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
141
+ "step": 561
142
+ },
143
+ {
144
+ "epoch": 0.05,
145
+ "eval_validation_agenda_digitale_loss": 1.4720743894577026,
146
+ "eval_validation_agenda_digitale_runtime": 187.11,
147
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
148
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
149
+ "step": 561
150
+ },
151
+ {
152
+ "epoch": 0.05,
153
+ "eval_validation_leggepertutti_loss": 1.3074837923049927,
154
+ "eval_validation_leggepertutti_runtime": 35.7797,
155
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
156
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
157
+ "step": 561
158
+ },
159
+ {
160
+ "epoch": 0.05,
161
+ "eval_validation_altalexprivacy_loss": 1.3142317533493042,
162
+ "eval_validation_altalexprivacy_runtime": 58.315,
163
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
164
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
165
+ "step": 561
166
+ },
167
+ {
168
+ "epoch": 0.05,
169
+ "eval_validation_mc4_it_loss": 1.87451171875,
170
+ "eval_validation_mc4_it_runtime": 78.1299,
171
+ "eval_validation_mc4_it_samples_per_second": 1.817,
172
+ "eval_validation_mc4_it_steps_per_second": 0.909,
173
+ "step": 561
174
+ },
175
+ {
176
+ "epoch": 0.05,
177
+ "eval_validation_dolma_loss": 1.956404447555542,
178
+ "eval_validation_dolma_runtime": 53.9194,
179
+ "eval_validation_dolma_samples_per_second": 1.818,
180
+ "eval_validation_dolma_steps_per_second": 0.909,
181
+ "step": 561
182
+ },
183
+ {
184
+ "epoch": 0.06,
185
+ "grad_norm": 9.625,
186
+ "learning_rate": 1e-05,
187
+ "loss": 1.6284,
188
+ "step": 748
189
+ },
190
+ {
191
+ "epoch": 0.06,
192
+ "eval_validation_privacy_sources_loss": 0.933682918548584,
193
+ "eval_validation_privacy_sources_runtime": 210.799,
194
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
195
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
196
+ "step": 748
197
+ },
198
+ {
199
+ "epoch": 0.06,
200
+ "eval_validation_agenda_digitale_loss": 1.4578524827957153,
201
+ "eval_validation_agenda_digitale_runtime": 187.08,
202
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
203
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
204
+ "step": 748
205
+ },
206
+ {
207
+ "epoch": 0.06,
208
+ "eval_validation_leggepertutti_loss": 1.2905200719833374,
209
+ "eval_validation_leggepertutti_runtime": 35.7738,
210
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
211
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
212
+ "step": 748
213
+ },
214
+ {
215
+ "epoch": 0.06,
216
+ "eval_validation_altalexprivacy_loss": 1.2977306842803955,
217
+ "eval_validation_altalexprivacy_runtime": 58.3215,
218
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
219
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
220
+ "step": 748
221
+ },
222
+ {
223
+ "epoch": 0.06,
224
+ "eval_validation_mc4_it_loss": 1.8592724800109863,
225
+ "eval_validation_mc4_it_runtime": 78.1141,
226
+ "eval_validation_mc4_it_samples_per_second": 1.818,
227
+ "eval_validation_mc4_it_steps_per_second": 0.909,
228
+ "step": 748
229
+ },
230
+ {
231
+ "epoch": 0.06,
232
+ "eval_validation_dolma_loss": 1.9574466943740845,
233
+ "eval_validation_dolma_runtime": 53.9297,
234
+ "eval_validation_dolma_samples_per_second": 1.817,
235
+ "eval_validation_dolma_steps_per_second": 0.909,
236
+ "step": 748
237
+ },
238
+ {
239
+ "epoch": 0.08,
240
+ "grad_norm": 3.390625,
241
+ "learning_rate": 1e-05,
242
+ "loss": 1.6082,
243
+ "step": 935
244
+ },
245
+ {
246
+ "epoch": 0.08,
247
+ "eval_validation_privacy_sources_loss": 0.919241726398468,
248
+ "eval_validation_privacy_sources_runtime": 210.6302,
249
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
250
+ "eval_validation_privacy_sources_steps_per_second": 0.912,
251
+ "step": 935
252
+ },
253
+ {
254
+ "epoch": 0.08,
255
+ "eval_validation_agenda_digitale_loss": 1.4438046216964722,
256
+ "eval_validation_agenda_digitale_runtime": 187.0727,
257
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
258
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
259
+ "step": 935
260
+ },
261
+ {
262
+ "epoch": 0.08,
263
+ "eval_validation_leggepertutti_loss": 1.2822848558425903,
264
+ "eval_validation_leggepertutti_runtime": 35.7909,
265
+ "eval_validation_leggepertutti_samples_per_second": 1.816,
266
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
267
+ "step": 935
268
+ },
269
+ {
270
+ "epoch": 0.08,
271
+ "eval_validation_altalexprivacy_loss": 1.2801928520202637,
272
+ "eval_validation_altalexprivacy_runtime": 58.3369,
273
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
274
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
275
+ "step": 935
276
+ },
277
+ {
278
+ "epoch": 0.08,
279
+ "eval_validation_mc4_it_loss": 1.8457767963409424,
280
+ "eval_validation_mc4_it_runtime": 78.1714,
281
+ "eval_validation_mc4_it_samples_per_second": 1.817,
282
+ "eval_validation_mc4_it_steps_per_second": 0.908,
283
+ "step": 935
284
+ },
285
+ {
286
+ "epoch": 0.08,
287
+ "eval_validation_dolma_loss": 1.9588344097137451,
288
+ "eval_validation_dolma_runtime": 53.9317,
289
+ "eval_validation_dolma_samples_per_second": 1.817,
290
+ "eval_validation_dolma_steps_per_second": 0.909,
291
+ "step": 935
292
+ },
293
+ {
294
+ "epoch": 0.09,
295
+ "grad_norm": 3.46875,
296
+ "learning_rate": 1e-05,
297
+ "loss": 1.5989,
298
+ "step": 1122
299
+ },
300
+ {
301
+ "epoch": 0.09,
302
+ "eval_validation_privacy_sources_loss": 0.9032600522041321,
303
+ "eval_validation_privacy_sources_runtime": 210.7002,
304
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
305
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
306
+ "step": 1122
307
+ },
308
+ {
309
+ "epoch": 0.09,
310
+ "eval_validation_agenda_digitale_loss": 1.433292031288147,
311
+ "eval_validation_agenda_digitale_runtime": 187.0521,
312
+ "eval_validation_agenda_digitale_samples_per_second": 1.818,
313
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
314
+ "step": 1122
315
+ },
316
+ {
317
+ "epoch": 0.09,
318
+ "eval_validation_leggepertutti_loss": 1.2763991355895996,
319
+ "eval_validation_leggepertutti_runtime": 35.7627,
320
+ "eval_validation_leggepertutti_samples_per_second": 1.818,
321
+ "eval_validation_leggepertutti_steps_per_second": 0.923,
322
+ "step": 1122
323
+ },
324
+ {
325
+ "epoch": 0.09,
326
+ "eval_validation_altalexprivacy_loss": 1.2663257122039795,
327
+ "eval_validation_altalexprivacy_runtime": 58.3197,
328
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
329
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
330
+ "step": 1122
331
+ },
332
+ {
333
+ "epoch": 0.09,
334
+ "eval_validation_mc4_it_loss": 1.8358547687530518,
335
+ "eval_validation_mc4_it_runtime": 78.1183,
336
+ "eval_validation_mc4_it_samples_per_second": 1.818,
337
+ "eval_validation_mc4_it_steps_per_second": 0.909,
338
+ "step": 1122
339
+ },
340
+ {
341
+ "epoch": 0.09,
342
+ "eval_validation_dolma_loss": 2.0097882747650146,
343
+ "eval_validation_dolma_runtime": 53.9266,
344
+ "eval_validation_dolma_samples_per_second": 1.817,
345
+ "eval_validation_dolma_steps_per_second": 0.909,
346
+ "step": 1122
347
+ },
348
+ {
349
+ "epoch": 0.11,
350
+ "grad_norm": 3.40625,
351
+ "learning_rate": 1e-05,
352
+ "loss": 1.6161,
353
+ "step": 1309
354
+ },
355
+ {
356
+ "epoch": 0.11,
357
+ "eval_validation_privacy_sources_loss": 0.8906105160713196,
358
+ "eval_validation_privacy_sources_runtime": 210.7431,
359
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
360
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
361
+ "step": 1309
362
+ },
363
+ {
364
+ "epoch": 0.11,
365
+ "eval_validation_agenda_digitale_loss": 1.4252179861068726,
366
+ "eval_validation_agenda_digitale_runtime": 187.1263,
367
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
368
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
369
+ "step": 1309
370
+ },
371
+ {
372
+ "epoch": 0.11,
373
+ "eval_validation_leggepertutti_loss": 1.2690521478652954,
374
+ "eval_validation_leggepertutti_runtime": 35.7673,
375
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
376
+ "eval_validation_leggepertutti_steps_per_second": 0.923,
377
+ "step": 1309
378
+ },
379
+ {
380
+ "epoch": 0.11,
381
+ "eval_validation_altalexprivacy_loss": 1.258312463760376,
382
+ "eval_validation_altalexprivacy_runtime": 58.3303,
383
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
384
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
385
+ "step": 1309
386
+ },
387
+ {
388
+ "epoch": 0.11,
389
+ "eval_validation_mc4_it_loss": 1.8263970613479614,
390
+ "eval_validation_mc4_it_runtime": 78.147,
391
+ "eval_validation_mc4_it_samples_per_second": 1.817,
392
+ "eval_validation_mc4_it_steps_per_second": 0.909,
393
+ "step": 1309
394
+ },
395
+ {
396
+ "epoch": 0.11,
397
+ "eval_validation_dolma_loss": 1.9555673599243164,
398
+ "eval_validation_dolma_runtime": 53.9288,
399
+ "eval_validation_dolma_samples_per_second": 1.817,
400
+ "eval_validation_dolma_steps_per_second": 0.909,
401
+ "step": 1309
402
+ },
403
+ {
404
+ "epoch": 0.13,
405
+ "grad_norm": 3.25,
406
+ "learning_rate": 1e-05,
407
+ "loss": 1.5911,
408
+ "step": 1496
409
+ },
410
+ {
411
+ "epoch": 0.13,
412
+ "eval_validation_privacy_sources_loss": 0.8815954327583313,
413
+ "eval_validation_privacy_sources_runtime": 210.7215,
414
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
415
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
416
+ "step": 1496
417
+ },
418
+ {
419
+ "epoch": 0.13,
420
+ "eval_validation_agenda_digitale_loss": 1.4188568592071533,
421
+ "eval_validation_agenda_digitale_runtime": 187.0962,
422
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
423
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
424
+ "step": 1496
425
+ },
426
+ {
427
+ "epoch": 0.13,
428
+ "eval_validation_leggepertutti_loss": 1.269508957862854,
429
+ "eval_validation_leggepertutti_runtime": 35.7762,
430
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
431
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
432
+ "step": 1496
433
+ },
434
+ {
435
+ "epoch": 0.13,
436
+ "eval_validation_altalexprivacy_loss": 1.2556049823760986,
437
+ "eval_validation_altalexprivacy_runtime": 58.3467,
438
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
439
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
440
+ "step": 1496
441
+ },
442
+ {
443
+ "epoch": 0.13,
444
+ "eval_validation_mc4_it_loss": 1.8174842596054077,
445
+ "eval_validation_mc4_it_runtime": 78.1412,
446
+ "eval_validation_mc4_it_samples_per_second": 1.817,
447
+ "eval_validation_mc4_it_steps_per_second": 0.909,
448
+ "step": 1496
449
+ },
450
+ {
451
+ "epoch": 0.13,
452
+ "eval_validation_dolma_loss": 1.9592047929763794,
453
+ "eval_validation_dolma_runtime": 53.9471,
454
+ "eval_validation_dolma_samples_per_second": 1.817,
455
+ "eval_validation_dolma_steps_per_second": 0.908,
456
+ "step": 1496
457
+ },
458
+ {
459
+ "epoch": 0.14,
460
+ "grad_norm": 3.359375,
461
+ "learning_rate": 1e-05,
462
+ "loss": 1.5694,
463
+ "step": 1683
464
+ },
465
+ {
466
+ "epoch": 0.14,
467
+ "eval_validation_privacy_sources_loss": 0.8737432956695557,
468
+ "eval_validation_privacy_sources_runtime": 210.8196,
469
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
470
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
471
+ "step": 1683
472
+ },
473
+ {
474
+ "epoch": 0.14,
475
+ "eval_validation_agenda_digitale_loss": 1.4132717847824097,
476
+ "eval_validation_agenda_digitale_runtime": 187.1554,
477
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
478
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
479
+ "step": 1683
480
+ },
481
+ {
482
+ "epoch": 0.14,
483
+ "eval_validation_leggepertutti_loss": 1.2630620002746582,
484
+ "eval_validation_leggepertutti_runtime": 35.7934,
485
+ "eval_validation_leggepertutti_samples_per_second": 1.816,
486
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
487
+ "step": 1683
488
+ },
489
+ {
490
+ "epoch": 0.14,
491
+ "eval_validation_altalexprivacy_loss": 1.247528076171875,
492
+ "eval_validation_altalexprivacy_runtime": 58.3547,
493
+ "eval_validation_altalexprivacy_samples_per_second": 1.816,
494
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
495
+ "step": 1683
496
+ },
497
+ {
498
+ "epoch": 0.14,
499
+ "eval_validation_mc4_it_loss": 1.8103784322738647,
500
+ "eval_validation_mc4_it_runtime": 78.1665,
501
+ "eval_validation_mc4_it_samples_per_second": 1.817,
502
+ "eval_validation_mc4_it_steps_per_second": 0.908,
503
+ "step": 1683
504
+ },
505
+ {
506
+ "epoch": 0.14,
507
+ "eval_validation_dolma_loss": 1.956905722618103,
508
+ "eval_validation_dolma_runtime": 53.9622,
509
+ "eval_validation_dolma_samples_per_second": 1.816,
510
+ "eval_validation_dolma_steps_per_second": 0.908,
511
+ "step": 1683
512
+ },
513
+ {
514
+ "epoch": 0.16,
515
+ "grad_norm": 3.1875,
516
+ "learning_rate": 1e-05,
517
+ "loss": 1.563,
518
+ "step": 1870
519
+ },
520
+ {
521
+ "epoch": 0.16,
522
+ "eval_validation_privacy_sources_loss": 0.8650386929512024,
523
+ "eval_validation_privacy_sources_runtime": 210.8215,
524
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
525
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
526
+ "step": 1870
527
+ },
528
+ {
529
+ "epoch": 0.16,
530
+ "eval_validation_agenda_digitale_loss": 1.4071804285049438,
531
+ "eval_validation_agenda_digitale_runtime": 187.1502,
532
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
533
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
534
+ "step": 1870
535
+ },
536
+ {
537
+ "epoch": 0.16,
538
+ "eval_validation_leggepertutti_loss": 1.2562586069107056,
539
+ "eval_validation_leggepertutti_runtime": 35.7742,
540
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
541
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
542
+ "step": 1870
543
+ },
544
+ {
545
+ "epoch": 0.16,
546
+ "eval_validation_altalexprivacy_loss": 1.240662932395935,
547
+ "eval_validation_altalexprivacy_runtime": 58.3499,
548
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
549
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
550
+ "step": 1870
551
+ },
552
+ {
553
+ "epoch": 0.16,
554
+ "eval_validation_mc4_it_loss": 1.8042465448379517,
555
+ "eval_validation_mc4_it_runtime": 78.1652,
556
+ "eval_validation_mc4_it_samples_per_second": 1.817,
557
+ "eval_validation_mc4_it_steps_per_second": 0.908,
558
+ "step": 1870
559
+ },
560
+ {
561
+ "epoch": 0.16,
562
+ "eval_validation_dolma_loss": 1.9527182579040527,
563
+ "eval_validation_dolma_runtime": 53.948,
564
+ "eval_validation_dolma_samples_per_second": 1.817,
565
+ "eval_validation_dolma_steps_per_second": 0.908,
566
+ "step": 1870
567
+ },
568
+ {
569
+ "epoch": 0.17,
570
+ "grad_norm": 3.171875,
571
+ "learning_rate": 1e-05,
572
+ "loss": 1.5747,
573
+ "step": 2057
574
+ },
575
+ {
576
+ "epoch": 0.17,
577
+ "eval_validation_privacy_sources_loss": 0.8606281876564026,
578
+ "eval_validation_privacy_sources_runtime": 210.8197,
579
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
580
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
581
+ "step": 2057
582
+ },
583
+ {
584
+ "epoch": 0.17,
585
+ "eval_validation_agenda_digitale_loss": 1.401216983795166,
586
+ "eval_validation_agenda_digitale_runtime": 187.1929,
587
+ "eval_validation_agenda_digitale_samples_per_second": 1.816,
588
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
589
+ "step": 2057
590
+ },
591
+ {
592
+ "epoch": 0.17,
593
+ "eval_validation_leggepertutti_loss": 1.249880075454712,
594
+ "eval_validation_leggepertutti_runtime": 35.7828,
595
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
596
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
597
+ "step": 2057
598
+ },
599
+ {
600
+ "epoch": 0.17,
601
+ "eval_validation_altalexprivacy_loss": 1.2347912788391113,
602
+ "eval_validation_altalexprivacy_runtime": 58.3271,
603
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
604
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
605
+ "step": 2057
606
+ },
607
+ {
608
+ "epoch": 0.17,
609
+ "eval_validation_mc4_it_loss": 1.7988897562026978,
610
+ "eval_validation_mc4_it_runtime": 78.1637,
611
+ "eval_validation_mc4_it_samples_per_second": 1.817,
612
+ "eval_validation_mc4_it_steps_per_second": 0.908,
613
+ "step": 2057
614
+ },
615
+ {
616
+ "epoch": 0.17,
617
+ "eval_validation_dolma_loss": 1.9512945413589478,
618
+ "eval_validation_dolma_runtime": 53.9545,
619
+ "eval_validation_dolma_samples_per_second": 1.816,
620
+ "eval_validation_dolma_steps_per_second": 0.908,
621
+ "step": 2057
622
+ },
623
+ {
624
+ "epoch": 0.19,
625
+ "grad_norm": 3.703125,
626
+ "learning_rate": 1e-05,
627
+ "loss": 1.5631,
628
+ "step": 2244
629
+ },
630
+ {
631
+ "epoch": 0.19,
632
+ "eval_validation_privacy_sources_loss": 0.8552854061126709,
633
+ "eval_validation_privacy_sources_runtime": 210.7654,
634
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
635
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
636
+ "step": 2244
637
+ },
638
+ {
639
+ "epoch": 0.19,
640
+ "eval_validation_agenda_digitale_loss": 1.3981597423553467,
641
+ "eval_validation_agenda_digitale_runtime": 187.0896,
642
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
643
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
644
+ "step": 2244
645
+ },
646
+ {
647
+ "epoch": 0.19,
648
+ "eval_validation_leggepertutti_loss": 1.249776840209961,
649
+ "eval_validation_leggepertutti_runtime": 35.7701,
650
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
651
+ "eval_validation_leggepertutti_steps_per_second": 0.923,
652
+ "step": 2244
653
+ },
654
+ {
655
+ "epoch": 0.19,
656
+ "eval_validation_altalexprivacy_loss": 1.2317657470703125,
657
+ "eval_validation_altalexprivacy_runtime": 58.3402,
658
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
659
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
660
+ "step": 2244
661
+ },
662
+ {
663
+ "epoch": 0.19,
664
+ "eval_validation_mc4_it_loss": 1.7936795949935913,
665
+ "eval_validation_mc4_it_runtime": 78.1539,
666
+ "eval_validation_mc4_it_samples_per_second": 1.817,
667
+ "eval_validation_mc4_it_steps_per_second": 0.908,
668
+ "step": 2244
669
+ },
670
+ {
671
+ "epoch": 0.19,
672
+ "eval_validation_dolma_loss": 1.949507474899292,
673
+ "eval_validation_dolma_runtime": 53.9287,
674
+ "eval_validation_dolma_samples_per_second": 1.817,
675
+ "eval_validation_dolma_steps_per_second": 0.909,
676
+ "step": 2244
677
+ },
678
+ {
679
+ "epoch": 0.2,
680
+ "grad_norm": 3.28125,
681
+ "learning_rate": 1e-05,
682
+ "loss": 1.5502,
683
+ "step": 2431
684
+ },
685
+ {
686
+ "epoch": 0.2,
687
+ "eval_validation_privacy_sources_loss": 0.8490111231803894,
688
+ "eval_validation_privacy_sources_runtime": 210.7371,
689
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
690
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
691
+ "step": 2431
692
+ },
693
+ {
694
+ "epoch": 0.2,
695
+ "eval_validation_agenda_digitale_loss": 1.391976237297058,
696
+ "eval_validation_agenda_digitale_runtime": 187.0694,
697
+ "eval_validation_agenda_digitale_samples_per_second": 1.818,
698
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
699
+ "step": 2431
700
+ },
701
+ {
702
+ "epoch": 0.2,
703
+ "eval_validation_leggepertutti_loss": 1.2457927465438843,
704
+ "eval_validation_leggepertutti_runtime": 35.7756,
705
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
706
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
707
+ "step": 2431
708
+ },
709
+ {
710
+ "epoch": 0.2,
711
+ "eval_validation_altalexprivacy_loss": 1.2249823808670044,
712
+ "eval_validation_altalexprivacy_runtime": 58.3391,
713
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
714
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
715
+ "step": 2431
716
+ },
717
+ {
718
+ "epoch": 0.2,
719
+ "eval_validation_mc4_it_loss": 1.7877947092056274,
720
+ "eval_validation_mc4_it_runtime": 78.1519,
721
+ "eval_validation_mc4_it_samples_per_second": 1.817,
722
+ "eval_validation_mc4_it_steps_per_second": 0.908,
723
+ "step": 2431
724
+ },
725
+ {
726
+ "epoch": 0.2,
727
+ "eval_validation_dolma_loss": 1.9478541612625122,
728
+ "eval_validation_dolma_runtime": 53.9392,
729
+ "eval_validation_dolma_samples_per_second": 1.817,
730
+ "eval_validation_dolma_steps_per_second": 0.908,
731
+ "step": 2431
732
+ },
733
+ {
734
+ "epoch": 0.22,
735
+ "grad_norm": 3.109375,
736
+ "learning_rate": 1e-05,
737
+ "loss": 1.5612,
738
+ "step": 2618
739
+ },
740
+ {
741
+ "epoch": 0.22,
742
+ "eval_validation_privacy_sources_loss": 0.8443201184272766,
743
+ "eval_validation_privacy_sources_runtime": 210.7053,
744
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
745
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
746
+ "step": 2618
747
+ },
748
+ {
749
+ "epoch": 0.22,
750
+ "eval_validation_agenda_digitale_loss": 1.3874356746673584,
751
+ "eval_validation_agenda_digitale_runtime": 187.0741,
752
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
753
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
754
+ "step": 2618
755
+ },
756
+ {
757
+ "epoch": 0.22,
758
+ "eval_validation_leggepertutti_loss": 1.242628574371338,
759
+ "eval_validation_leggepertutti_runtime": 35.7724,
760
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
761
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
762
+ "step": 2618
763
+ },
764
+ {
765
+ "epoch": 0.22,
766
+ "eval_validation_altalexprivacy_loss": 1.22023606300354,
767
+ "eval_validation_altalexprivacy_runtime": 58.3215,
768
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
769
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
770
+ "step": 2618
771
+ },
772
+ {
773
+ "epoch": 0.22,
774
+ "eval_validation_mc4_it_loss": 1.783267617225647,
775
+ "eval_validation_mc4_it_runtime": 78.1277,
776
+ "eval_validation_mc4_it_samples_per_second": 1.818,
777
+ "eval_validation_mc4_it_steps_per_second": 0.909,
778
+ "step": 2618
779
+ },
780
+ {
781
+ "epoch": 0.22,
782
+ "eval_validation_dolma_loss": 1.9474639892578125,
783
+ "eval_validation_dolma_runtime": 53.9215,
784
+ "eval_validation_dolma_samples_per_second": 1.817,
785
+ "eval_validation_dolma_steps_per_second": 0.909,
786
+ "step": 2618
787
+ },
788
+ {
789
+ "epoch": 0.24,
790
+ "grad_norm": 9.0,
791
+ "learning_rate": 1e-05,
792
+ "loss": 1.5625,
793
+ "step": 2805
794
+ },
795
+ {
796
+ "epoch": 0.24,
797
+ "eval_validation_privacy_sources_loss": 0.8386737108230591,
798
+ "eval_validation_privacy_sources_runtime": 210.6496,
799
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
800
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
801
+ "step": 2805
802
+ },
803
+ {
804
+ "epoch": 0.24,
805
+ "eval_validation_agenda_digitale_loss": 1.3825620412826538,
806
+ "eval_validation_agenda_digitale_runtime": 186.9852,
807
+ "eval_validation_agenda_digitale_samples_per_second": 1.818,
808
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
809
+ "step": 2805
810
+ },
811
+ {
812
+ "epoch": 0.24,
813
+ "eval_validation_leggepertutti_loss": 1.2439346313476562,
814
+ "eval_validation_leggepertutti_runtime": 35.762,
815
+ "eval_validation_leggepertutti_samples_per_second": 1.818,
816
+ "eval_validation_leggepertutti_steps_per_second": 0.923,
817
+ "step": 2805
818
+ },
819
+ {
820
+ "epoch": 0.24,
821
+ "eval_validation_altalexprivacy_loss": 1.2144984006881714,
822
+ "eval_validation_altalexprivacy_runtime": 58.2929,
823
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
824
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
825
+ "step": 2805
826
+ },
827
+ {
828
+ "epoch": 0.24,
829
+ "eval_validation_mc4_it_loss": 1.7777953147888184,
830
+ "eval_validation_mc4_it_runtime": 78.0862,
831
+ "eval_validation_mc4_it_samples_per_second": 1.819,
832
+ "eval_validation_mc4_it_steps_per_second": 0.909,
833
+ "step": 2805
834
+ },
835
+ {
836
+ "epoch": 0.24,
837
+ "eval_validation_dolma_loss": 1.9426158666610718,
838
+ "eval_validation_dolma_runtime": 53.8932,
839
+ "eval_validation_dolma_samples_per_second": 1.818,
840
+ "eval_validation_dolma_steps_per_second": 0.909,
841
+ "step": 2805
842
+ },
843
+ {
844
+ "epoch": 0.25,
845
+ "grad_norm": 3.09375,
846
+ "learning_rate": 1e-05,
847
+ "loss": 1.5659,
848
+ "step": 2992
849
+ },
850
+ {
851
+ "epoch": 0.25,
852
+ "eval_validation_privacy_sources_loss": 0.8341156840324402,
853
+ "eval_validation_privacy_sources_runtime": 210.6733,
854
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
855
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
856
+ "step": 2992
857
+ },
858
+ {
859
+ "epoch": 0.25,
860
+ "eval_validation_agenda_digitale_loss": 1.3803825378417969,
861
+ "eval_validation_agenda_digitale_runtime": 187.0096,
862
+ "eval_validation_agenda_digitale_samples_per_second": 1.818,
863
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
864
+ "step": 2992
865
+ },
866
+ {
867
+ "epoch": 0.25,
868
+ "eval_validation_leggepertutti_loss": 1.2398289442062378,
869
+ "eval_validation_leggepertutti_runtime": 35.7578,
870
+ "eval_validation_leggepertutti_samples_per_second": 1.818,
871
+ "eval_validation_leggepertutti_steps_per_second": 0.923,
872
+ "step": 2992
873
+ },
874
+ {
875
+ "epoch": 0.25,
876
+ "eval_validation_altalexprivacy_loss": 1.2100013494491577,
877
+ "eval_validation_altalexprivacy_runtime": 58.3051,
878
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
879
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
880
+ "step": 2992
881
+ },
882
+ {
883
+ "epoch": 0.25,
884
+ "eval_validation_mc4_it_loss": 1.7749333381652832,
885
+ "eval_validation_mc4_it_runtime": 78.0968,
886
+ "eval_validation_mc4_it_samples_per_second": 1.818,
887
+ "eval_validation_mc4_it_steps_per_second": 0.909,
888
+ "step": 2992
889
+ },
890
+ {
891
+ "epoch": 0.25,
892
+ "eval_validation_dolma_loss": 1.9426519870758057,
893
+ "eval_validation_dolma_runtime": 53.9195,
894
+ "eval_validation_dolma_samples_per_second": 1.818,
895
+ "eval_validation_dolma_steps_per_second": 0.909,
896
+ "step": 2992
897
+ },
898
+ {
899
+ "epoch": 0.27,
900
+ "grad_norm": 3.265625,
901
+ "learning_rate": 1e-05,
902
+ "loss": 1.5527,
903
+ "step": 3179
904
+ },
905
+ {
906
+ "epoch": 0.27,
907
+ "eval_validation_privacy_sources_loss": 0.8318145871162415,
908
+ "eval_validation_privacy_sources_runtime": 210.7255,
909
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
910
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
911
+ "step": 3179
912
+ },
913
+ {
914
+ "epoch": 0.27,
915
+ "eval_validation_agenda_digitale_loss": 1.378063440322876,
916
+ "eval_validation_agenda_digitale_runtime": 187.087,
917
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
918
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
919
+ "step": 3179
920
+ },
921
+ {
922
+ "epoch": 0.27,
923
+ "eval_validation_leggepertutti_loss": 1.2370458841323853,
924
+ "eval_validation_leggepertutti_runtime": 35.7809,
925
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
926
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
927
+ "step": 3179
928
+ },
929
+ {
930
+ "epoch": 0.27,
931
+ "eval_validation_altalexprivacy_loss": 1.2080256938934326,
932
+ "eval_validation_altalexprivacy_runtime": 58.3354,
933
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
934
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
935
+ "step": 3179
936
+ },
937
+ {
938
+ "epoch": 0.27,
939
+ "eval_validation_mc4_it_loss": 1.7702537775039673,
940
+ "eval_validation_mc4_it_runtime": 78.1409,
941
+ "eval_validation_mc4_it_samples_per_second": 1.817,
942
+ "eval_validation_mc4_it_steps_per_second": 0.909,
943
+ "step": 3179
944
+ },
945
+ {
946
+ "epoch": 0.27,
947
+ "eval_validation_dolma_loss": 1.950868844985962,
948
+ "eval_validation_dolma_runtime": 53.9369,
949
+ "eval_validation_dolma_samples_per_second": 1.817,
950
+ "eval_validation_dolma_steps_per_second": 0.908,
951
+ "step": 3179
952
+ },
953
+ {
954
+ "epoch": 0.28,
955
+ "grad_norm": 3.265625,
956
+ "learning_rate": 1e-05,
957
+ "loss": 1.5476,
958
+ "step": 3366
959
+ },
960
+ {
961
+ "epoch": 0.28,
962
+ "eval_validation_privacy_sources_loss": 0.8264653086662292,
963
+ "eval_validation_privacy_sources_runtime": 210.7205,
964
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
965
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
966
+ "step": 3366
967
+ },
968
+ {
969
+ "epoch": 0.28,
970
+ "eval_validation_agenda_digitale_loss": 1.3743617534637451,
971
+ "eval_validation_agenda_digitale_runtime": 187.1448,
972
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
973
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
974
+ "step": 3366
975
+ },
976
+ {
977
+ "epoch": 0.28,
978
+ "eval_validation_leggepertutti_loss": 1.2376344203948975,
979
+ "eval_validation_leggepertutti_runtime": 35.7729,
980
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
981
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
982
+ "step": 3366
983
+ },
984
+ {
985
+ "epoch": 0.28,
986
+ "eval_validation_altalexprivacy_loss": 1.2052847146987915,
987
+ "eval_validation_altalexprivacy_runtime": 58.3348,
988
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
989
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
990
+ "step": 3366
991
+ },
992
+ {
993
+ "epoch": 0.28,
994
+ "eval_validation_mc4_it_loss": 1.7669274806976318,
995
+ "eval_validation_mc4_it_runtime": 78.1532,
996
+ "eval_validation_mc4_it_samples_per_second": 1.817,
997
+ "eval_validation_mc4_it_steps_per_second": 0.908,
998
+ "step": 3366
999
+ },
1000
+ {
1001
+ "epoch": 0.28,
1002
+ "eval_validation_dolma_loss": 1.9461361169815063,
1003
+ "eval_validation_dolma_runtime": 53.9281,
1004
+ "eval_validation_dolma_samples_per_second": 1.817,
1005
+ "eval_validation_dolma_steps_per_second": 0.909,
1006
+ "step": 3366
1007
+ },
1008
+ {
1009
+ "epoch": 0.3,
1010
+ "grad_norm": 3.625,
1011
+ "learning_rate": 1e-05,
1012
+ "loss": 1.558,
1013
+ "step": 3553
1014
+ },
1015
+ {
1016
+ "epoch": 0.3,
1017
+ "eval_validation_privacy_sources_loss": 0.822688102722168,
1018
+ "eval_validation_privacy_sources_runtime": 210.9998,
1019
+ "eval_validation_privacy_sources_samples_per_second": 1.815,
1020
+ "eval_validation_privacy_sources_steps_per_second": 0.91,
1021
+ "step": 3553
1022
+ },
1023
+ {
1024
+ "epoch": 0.3,
1025
+ "eval_validation_agenda_digitale_loss": 1.3728498220443726,
1026
+ "eval_validation_agenda_digitale_runtime": 187.2711,
1027
+ "eval_validation_agenda_digitale_samples_per_second": 1.816,
1028
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
1029
+ "step": 3553
1030
+ },
1031
+ {
1032
+ "epoch": 0.3,
1033
+ "eval_validation_leggepertutti_loss": 1.2360832691192627,
1034
+ "eval_validation_leggepertutti_runtime": 35.7958,
1035
+ "eval_validation_leggepertutti_samples_per_second": 1.816,
1036
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
1037
+ "step": 3553
1038
+ },
1039
+ {
1040
+ "epoch": 0.3,
1041
+ "eval_validation_altalexprivacy_loss": 1.2027132511138916,
1042
+ "eval_validation_altalexprivacy_runtime": 58.3972,
1043
+ "eval_validation_altalexprivacy_samples_per_second": 1.815,
1044
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
1045
+ "step": 3553
1046
+ },
1047
+ {
1048
+ "epoch": 0.3,
1049
+ "eval_validation_mc4_it_loss": 1.7643710374832153,
1050
+ "eval_validation_mc4_it_runtime": 78.2118,
1051
+ "eval_validation_mc4_it_samples_per_second": 1.816,
1052
+ "eval_validation_mc4_it_steps_per_second": 0.908,
1053
+ "step": 3553
1054
+ },
1055
+ {
1056
+ "epoch": 0.3,
1057
+ "eval_validation_dolma_loss": 1.9442397356033325,
1058
+ "eval_validation_dolma_runtime": 53.9609,
1059
+ "eval_validation_dolma_samples_per_second": 1.816,
1060
+ "eval_validation_dolma_steps_per_second": 0.908,
1061
+ "step": 3553
1062
+ },
1063
+ {
1064
+ "epoch": 0.32,
1065
+ "grad_norm": 4.65625,
1066
+ "learning_rate": 1e-05,
1067
+ "loss": 1.535,
1068
+ "step": 3740
1069
+ },
1070
+ {
1071
+ "epoch": 0.32,
1072
+ "eval_validation_privacy_sources_loss": 0.8193829655647278,
1073
+ "eval_validation_privacy_sources_runtime": 210.8214,
1074
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
1075
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
1076
+ "step": 3740
1077
+ },
1078
+ {
1079
+ "epoch": 0.32,
1080
+ "eval_validation_agenda_digitale_loss": 1.3690398931503296,
1081
+ "eval_validation_agenda_digitale_runtime": 187.1433,
1082
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
1083
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
1084
+ "step": 3740
1085
+ },
1086
+ {
1087
+ "epoch": 0.32,
1088
+ "eval_validation_leggepertutti_loss": 1.2321481704711914,
1089
+ "eval_validation_leggepertutti_runtime": 35.7856,
1090
+ "eval_validation_leggepertutti_samples_per_second": 1.816,
1091
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
1092
+ "step": 3740
1093
+ },
1094
+ {
1095
+ "epoch": 0.32,
1096
+ "eval_validation_altalexprivacy_loss": 1.1964303255081177,
1097
+ "eval_validation_altalexprivacy_runtime": 58.3552,
1098
+ "eval_validation_altalexprivacy_samples_per_second": 1.816,
1099
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
1100
+ "step": 3740
1101
+ },
1102
+ {
1103
+ "epoch": 0.32,
1104
+ "eval_validation_mc4_it_loss": 1.7612253427505493,
1105
+ "eval_validation_mc4_it_runtime": 78.1715,
1106
+ "eval_validation_mc4_it_samples_per_second": 1.817,
1107
+ "eval_validation_mc4_it_steps_per_second": 0.908,
1108
+ "step": 3740
1109
+ },
1110
+ {
1111
+ "epoch": 0.32,
1112
+ "eval_validation_dolma_loss": 1.9415688514709473,
1113
+ "eval_validation_dolma_runtime": 53.9531,
1114
+ "eval_validation_dolma_samples_per_second": 1.816,
1115
+ "eval_validation_dolma_steps_per_second": 0.908,
1116
+ "step": 3740
1117
+ },
1118
+ {
1119
+ "epoch": 0.33,
1120
+ "grad_norm": 3.203125,
1121
+ "learning_rate": 1e-05,
1122
+ "loss": 1.551,
1123
+ "step": 3927
1124
+ },
1125
+ {
1126
+ "epoch": 0.33,
1127
+ "eval_validation_privacy_sources_loss": 0.8159863352775574,
1128
+ "eval_validation_privacy_sources_runtime": 210.8294,
1129
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
1130
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
1131
+ "step": 3927
1132
+ },
1133
+ {
1134
+ "epoch": 0.33,
1135
+ "eval_validation_agenda_digitale_loss": 1.3660005331039429,
1136
+ "eval_validation_agenda_digitale_runtime": 187.2084,
1137
+ "eval_validation_agenda_digitale_samples_per_second": 1.816,
1138
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
1139
+ "step": 3927
1140
+ },
1141
+ {
1142
+ "epoch": 0.33,
1143
+ "eval_validation_leggepertutti_loss": 1.2291594743728638,
1144
+ "eval_validation_leggepertutti_runtime": 35.7917,
1145
+ "eval_validation_leggepertutti_samples_per_second": 1.816,
1146
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
1147
+ "step": 3927
1148
+ },
1149
+ {
1150
+ "epoch": 0.33,
1151
+ "eval_validation_altalexprivacy_loss": 1.1953657865524292,
1152
+ "eval_validation_altalexprivacy_runtime": 58.3486,
1153
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
1154
+ "eval_validation_altalexprivacy_steps_per_second": 0.908,
1155
+ "step": 3927
1156
+ },
1157
+ {
1158
+ "epoch": 0.33,
1159
+ "eval_validation_mc4_it_loss": 1.7568954229354858,
1160
+ "eval_validation_mc4_it_runtime": 78.1754,
1161
+ "eval_validation_mc4_it_samples_per_second": 1.816,
1162
+ "eval_validation_mc4_it_steps_per_second": 0.908,
1163
+ "step": 3927
1164
+ },
1165
+ {
1166
+ "epoch": 0.33,
1167
+ "eval_validation_dolma_loss": 1.9388848543167114,
1168
+ "eval_validation_dolma_runtime": 53.9683,
1169
+ "eval_validation_dolma_samples_per_second": 1.816,
1170
+ "eval_validation_dolma_steps_per_second": 0.908,
1171
+ "step": 3927
1172
+ },
1173
+ {
1174
+ "epoch": 0.35,
1175
+ "grad_norm": 3.578125,
1176
+ "learning_rate": 1e-05,
1177
+ "loss": 1.5452,
1178
+ "step": 4114
1179
+ },
1180
+ {
1181
+ "epoch": 0.35,
1182
+ "eval_validation_privacy_sources_loss": 0.8137150406837463,
1183
+ "eval_validation_privacy_sources_runtime": 210.7357,
1184
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
1185
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
1186
+ "step": 4114
1187
+ },
1188
+ {
1189
+ "epoch": 0.35,
1190
+ "eval_validation_agenda_digitale_loss": 1.3656136989593506,
1191
+ "eval_validation_agenda_digitale_runtime": 187.146,
1192
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
1193
+ "eval_validation_agenda_digitale_steps_per_second": 0.908,
1194
+ "step": 4114
1195
+ },
1196
+ {
1197
+ "epoch": 0.35,
1198
+ "eval_validation_leggepertutti_loss": 1.2296239137649536,
1199
+ "eval_validation_leggepertutti_runtime": 35.7766,
1200
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
1201
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
1202
+ "step": 4114
1203
+ },
1204
+ {
1205
+ "epoch": 0.35,
1206
+ "eval_validation_altalexprivacy_loss": 1.1915565729141235,
1207
+ "eval_validation_altalexprivacy_runtime": 58.3322,
1208
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
1209
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
1210
+ "step": 4114
1211
+ },
1212
+ {
1213
+ "epoch": 0.35,
1214
+ "eval_validation_mc4_it_loss": 1.7542990446090698,
1215
+ "eval_validation_mc4_it_runtime": 78.1622,
1216
+ "eval_validation_mc4_it_samples_per_second": 1.817,
1217
+ "eval_validation_mc4_it_steps_per_second": 0.908,
1218
+ "step": 4114
1219
+ },
1220
+ {
1221
+ "epoch": 0.35,
1222
+ "eval_validation_dolma_loss": 1.9385536909103394,
1223
+ "eval_validation_dolma_runtime": 53.9474,
1224
+ "eval_validation_dolma_samples_per_second": 1.817,
1225
+ "eval_validation_dolma_steps_per_second": 0.908,
1226
+ "step": 4114
1227
+ },
1228
+ {
1229
+ "epoch": 0.36,
1230
+ "grad_norm": 3.421875,
1231
+ "learning_rate": 1e-05,
1232
+ "loss": 1.5371,
1233
+ "step": 4301
1234
+ },
1235
+ {
1236
+ "epoch": 0.36,
1237
+ "eval_validation_privacy_sources_loss": 0.8114846348762512,
1238
+ "eval_validation_privacy_sources_runtime": 210.7483,
1239
+ "eval_validation_privacy_sources_samples_per_second": 1.817,
1240
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
1241
+ "step": 4301
1242
+ },
1243
+ {
1244
+ "epoch": 0.36,
1245
+ "eval_validation_agenda_digitale_loss": 1.36287522315979,
1246
+ "eval_validation_agenda_digitale_runtime": 187.0978,
1247
+ "eval_validation_agenda_digitale_samples_per_second": 1.817,
1248
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
1249
+ "step": 4301
1250
+ },
1251
+ {
1252
+ "epoch": 0.36,
1253
+ "eval_validation_leggepertutti_loss": 1.225502371788025,
1254
+ "eval_validation_leggepertutti_runtime": 35.7725,
1255
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
1256
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
1257
+ "step": 4301
1258
+ },
1259
+ {
1260
+ "epoch": 0.36,
1261
+ "eval_validation_altalexprivacy_loss": 1.1899324655532837,
1262
+ "eval_validation_altalexprivacy_runtime": 58.3269,
1263
+ "eval_validation_altalexprivacy_samples_per_second": 1.817,
1264
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
1265
+ "step": 4301
1266
+ },
1267
+ {
1268
+ "epoch": 0.36,
1269
+ "eval_validation_mc4_it_loss": 1.7518540620803833,
1270
+ "eval_validation_mc4_it_runtime": 78.1395,
1271
+ "eval_validation_mc4_it_samples_per_second": 1.817,
1272
+ "eval_validation_mc4_it_steps_per_second": 0.909,
1273
+ "step": 4301
1274
+ },
1275
+ {
1276
+ "epoch": 0.36,
1277
+ "eval_validation_dolma_loss": 1.9364405870437622,
1278
+ "eval_validation_dolma_runtime": 53.9366,
1279
+ "eval_validation_dolma_samples_per_second": 1.817,
1280
+ "eval_validation_dolma_steps_per_second": 0.908,
1281
+ "step": 4301
1282
+ },
1283
+ {
1284
+ "epoch": 0.38,
1285
+ "grad_norm": 3.4375,
1286
+ "learning_rate": 1e-05,
1287
+ "loss": 1.5349,
1288
+ "step": 4488
1289
+ },
1290
+ {
1291
+ "epoch": 0.38,
1292
+ "eval_validation_privacy_sources_loss": 0.8089282512664795,
1293
+ "eval_validation_privacy_sources_runtime": 210.6735,
1294
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
1295
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
1296
+ "step": 4488
1297
+ },
1298
+ {
1299
+ "epoch": 0.38,
1300
+ "eval_validation_agenda_digitale_loss": 1.3604696989059448,
1301
+ "eval_validation_agenda_digitale_runtime": 187.0247,
1302
+ "eval_validation_agenda_digitale_samples_per_second": 1.818,
1303
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
1304
+ "step": 4488
1305
+ },
1306
+ {
1307
+ "epoch": 0.38,
1308
+ "eval_validation_leggepertutti_loss": 1.2236857414245605,
1309
+ "eval_validation_leggepertutti_runtime": 35.775,
1310
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
1311
+ "eval_validation_leggepertutti_steps_per_second": 0.922,
1312
+ "step": 4488
1313
+ },
1314
+ {
1315
+ "epoch": 0.38,
1316
+ "eval_validation_altalexprivacy_loss": 1.1892808675765991,
1317
+ "eval_validation_altalexprivacy_runtime": 58.2983,
1318
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
1319
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
1320
+ "step": 4488
1321
+ },
1322
+ {
1323
+ "epoch": 0.38,
1324
+ "eval_validation_mc4_it_loss": 1.7490640878677368,
1325
+ "eval_validation_mc4_it_runtime": 78.1304,
1326
+ "eval_validation_mc4_it_samples_per_second": 1.817,
1327
+ "eval_validation_mc4_it_steps_per_second": 0.909,
1328
+ "step": 4488
1329
+ },
1330
+ {
1331
+ "epoch": 0.38,
1332
+ "eval_validation_dolma_loss": 1.9361358880996704,
1333
+ "eval_validation_dolma_runtime": 53.9258,
1334
+ "eval_validation_dolma_samples_per_second": 1.817,
1335
+ "eval_validation_dolma_steps_per_second": 0.909,
1336
+ "step": 4488
1337
+ },
1338
+ {
1339
+ "epoch": 0.39,
1340
+ "grad_norm": 3.265625,
1341
+ "learning_rate": 1e-05,
1342
+ "loss": 1.538,
1343
+ "step": 4675
1344
+ },
1345
+ {
1346
+ "epoch": 0.39,
1347
+ "eval_validation_privacy_sources_loss": 0.8068882822990417,
1348
+ "eval_validation_privacy_sources_runtime": 210.6987,
1349
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
1350
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
1351
+ "step": 4675
1352
+ },
1353
+ {
1354
+ "epoch": 0.39,
1355
+ "eval_validation_agenda_digitale_loss": 1.357992172241211,
1356
+ "eval_validation_agenda_digitale_runtime": 187.0601,
1357
+ "eval_validation_agenda_digitale_samples_per_second": 1.818,
1358
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
1359
+ "step": 4675
1360
+ },
1361
+ {
1362
+ "epoch": 0.39,
1363
+ "eval_validation_leggepertutti_loss": 1.2222189903259277,
1364
+ "eval_validation_leggepertutti_runtime": 35.7685,
1365
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
1366
+ "eval_validation_leggepertutti_steps_per_second": 0.923,
1367
+ "step": 4675
1368
+ },
1369
+ {
1370
+ "epoch": 0.39,
1371
+ "eval_validation_altalexprivacy_loss": 1.1868293285369873,
1372
+ "eval_validation_altalexprivacy_runtime": 58.3028,
1373
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
1374
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
1375
+ "step": 4675
1376
+ },
1377
+ {
1378
+ "epoch": 0.39,
1379
+ "eval_validation_mc4_it_loss": 1.747467279434204,
1380
+ "eval_validation_mc4_it_runtime": 78.0822,
1381
+ "eval_validation_mc4_it_samples_per_second": 1.819,
1382
+ "eval_validation_mc4_it_steps_per_second": 0.909,
1383
+ "step": 4675
1384
+ },
1385
+ {
1386
+ "epoch": 0.39,
1387
+ "eval_validation_dolma_loss": 1.9376739263534546,
1388
+ "eval_validation_dolma_runtime": 53.9131,
1389
+ "eval_validation_dolma_samples_per_second": 1.818,
1390
+ "eval_validation_dolma_steps_per_second": 0.909,
1391
+ "step": 4675
1392
+ },
1393
+ {
1394
+ "epoch": 0.41,
1395
+ "grad_norm": 4.5625,
1396
+ "learning_rate": 1e-05,
1397
+ "loss": 1.5217,
1398
+ "step": 4862
1399
+ },
1400
+ {
1401
+ "epoch": 0.41,
1402
+ "eval_validation_privacy_sources_loss": 0.8034628033638,
1403
+ "eval_validation_privacy_sources_runtime": 210.664,
1404
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
1405
+ "eval_validation_privacy_sources_steps_per_second": 0.911,
1406
+ "step": 4862
1407
+ },
1408
+ {
1409
+ "epoch": 0.41,
1410
+ "eval_validation_agenda_digitale_loss": 1.3556355237960815,
1411
+ "eval_validation_agenda_digitale_runtime": 187.0481,
1412
+ "eval_validation_agenda_digitale_samples_per_second": 1.818,
1413
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
1414
+ "step": 4862
1415
+ },
1416
+ {
1417
+ "epoch": 0.41,
1418
+ "eval_validation_leggepertutti_loss": 1.2238881587982178,
1419
+ "eval_validation_leggepertutti_runtime": 35.77,
1420
+ "eval_validation_leggepertutti_samples_per_second": 1.817,
1421
+ "eval_validation_leggepertutti_steps_per_second": 0.923,
1422
+ "step": 4862
1423
+ },
1424
+ {
1425
+ "epoch": 0.41,
1426
+ "eval_validation_altalexprivacy_loss": 1.1821054220199585,
1427
+ "eval_validation_altalexprivacy_runtime": 58.3131,
1428
+ "eval_validation_altalexprivacy_samples_per_second": 1.818,
1429
+ "eval_validation_altalexprivacy_steps_per_second": 0.909,
1430
+ "step": 4862
1431
+ },
1432
+ {
1433
+ "epoch": 0.41,
1434
+ "eval_validation_mc4_it_loss": 1.7454167604446411,
1435
+ "eval_validation_mc4_it_runtime": 78.136,
1436
+ "eval_validation_mc4_it_samples_per_second": 1.817,
1437
+ "eval_validation_mc4_it_steps_per_second": 0.909,
1438
+ "step": 4862
1439
+ },
1440
+ {
1441
+ "epoch": 0.41,
1442
+ "eval_validation_dolma_loss": 1.9336557388305664,
1443
+ "eval_validation_dolma_runtime": 53.931,
1444
+ "eval_validation_dolma_samples_per_second": 1.817,
1445
+ "eval_validation_dolma_steps_per_second": 0.909,
1446
+ "step": 4862
1447
+ },
1448
+ {
1449
+ "epoch": 0.43,
1450
+ "grad_norm": 3.25,
1451
+ "learning_rate": 1e-05,
1452
+ "loss": 1.5231,
1453
+ "step": 5049
1454
+ },
1455
+ {
1456
+ "epoch": 0.43,
1457
+ "eval_validation_privacy_sources_loss": 0.8018712997436523,
1458
+ "eval_validation_privacy_sources_runtime": 210.6286,
1459
+ "eval_validation_privacy_sources_samples_per_second": 1.818,
1460
+ "eval_validation_privacy_sources_steps_per_second": 0.912,
1461
+ "step": 5049
1462
+ },
1463
+ {
1464
+ "epoch": 0.43,
1465
+ "eval_validation_agenda_digitale_loss": 1.3536696434020996,
1466
+ "eval_validation_agenda_digitale_runtime": 186.962,
1467
+ "eval_validation_agenda_digitale_samples_per_second": 1.819,
1468
+ "eval_validation_agenda_digitale_steps_per_second": 0.909,
1469
+ "step": 5049
1470
+ },
1471
+ {
1472
+ "epoch": 0.43,
1473
+ "eval_validation_leggepertutti_loss": 1.219115138053894,
1474
+ "eval_validation_leggepertutti_runtime": 35.7552,
1475
+ "eval_validation_leggepertutti_samples_per_second": 1.818,
1476
+ "eval_validation_leggepertutti_steps_per_second": 0.923,
1477
+ "step": 5049
1478
+ },
1479
+ {
1480
+ "epoch": 0.43,
1481
+ "eval_validation_altalexprivacy_loss": 1.1803195476531982,
1482
+ "eval_validation_altalexprivacy_runtime": 58.254,
1483
+ "eval_validation_altalexprivacy_samples_per_second": 1.82,
1484
+ "eval_validation_altalexprivacy_steps_per_second": 0.91,
1485
+ "step": 5049
1486
+ },
1487
+ {
1488
+ "epoch": 0.43,
1489
+ "eval_validation_mc4_it_loss": 1.7427842617034912,
1490
+ "eval_validation_mc4_it_runtime": 78.0819,
1491
+ "eval_validation_mc4_it_samples_per_second": 1.819,
1492
+ "eval_validation_mc4_it_steps_per_second": 0.909,
1493
+ "step": 5049
1494
+ },
1495
+ {
1496
+ "epoch": 0.43,
1497
+ "eval_validation_dolma_loss": 1.932908058166504,
1498
+ "eval_validation_dolma_runtime": 53.9066,
1499
+ "eval_validation_dolma_samples_per_second": 1.818,
1500
+ "eval_validation_dolma_steps_per_second": 0.909,
1501
+ "step": 5049
1502
+ }
1503
+ ],
1504
+ "logging_steps": 187,
1505
+ "max_steps": 23720,
1506
+ "num_input_tokens_seen": 0,
1507
+ "num_train_epochs": 2,
1508
+ "save_steps": 187,
1509
+ "total_flos": 2.1175697763358212e+19,
1510
+ "train_batch_size": 1,
1511
+ "trial_name": null,
1512
+ "trial_params": null
1513
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63700be8e0e5a403f4dd9e7450a90e07bbe4642ff63d321781e28b7f3c06b218
3
+ size 4792