DrNicefellow commited on
Commit
dbb6e74
·
verified ·
1 Parent(s): ee38bac

Upload 13 files

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OlmoForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "clip_qkv": null,
8
+ "eos_token_id": 50279,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8192,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "olmo",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 4,
18
+ "pad_token_id": 1,
19
+ "pretraining_tp": 1,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.40.2",
25
+ "use_cache": true,
26
+ "vocab_size": 50304
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50279,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.40.2"
6
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07717af5bd71a92b001a490c0bc75150c8781cc4680e12256fc31dcdf291b5c8
3
+ size 16393633958
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc78f200249564e0fd5174f78a82e3e629d89a69759aa5e450b8c48fa23d4e95
3
+ size 4967152029
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9819ffc663a4111ce66855671a7bacdd6bfe4298825823082fb608c05c767f
3
+ size 3229646818
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8196718592
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
79
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
86
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
87
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
88
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
89
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
90
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
91
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
92
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
100
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
101
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
102
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
103
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
104
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
105
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
106
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
107
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
108
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
109
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
110
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
111
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
112
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
113
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
114
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
115
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
116
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
117
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
118
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
119
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
120
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
121
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
122
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
123
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
124
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
125
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
126
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
127
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
128
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
129
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
130
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
131
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
132
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
133
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
134
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
135
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
138
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
140
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
141
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
142
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
143
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
144
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
147
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
148
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
149
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
150
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
151
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
152
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
153
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
156
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
157
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
158
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
159
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
166
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
167
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
192
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
195
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
196
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
197
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
198
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
201
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
202
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
204
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
205
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
206
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
207
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
208
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
209
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
210
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
211
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
212
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
213
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
214
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
215
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
216
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
220
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
225
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
228
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
229
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
230
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin"
232
+ }
233
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aab9424bbcaa00e66fbb7d46c0ee58362f0f7383b933616af4739979c589158
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|padding|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "|||IP_ADDRESS|||",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "|||EMAIL_ADDRESS|||",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "50278": {
215
+ "content": "|||PHONE_NUMBER|||",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "50279": {
223
+ "content": "<|endoftext|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ }
230
+ },
231
+ "bos_token": null,
232
+ "clean_up_tokenization_spaces": true,
233
+ "eos_token": "<|endoftext|>",
234
+ "model_max_length": 1000000000000000019884624838656,
235
+ "pad_token": "<|padding|>",
236
+ "tokenizer_class": "GPTNeoXTokenizer",
237
+ "unk_token": null
238
+ }
trainer_state.json ADDED
@@ -0,0 +1,938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.03178549194008557,
5
+ "eval_steps": 100000000,
6
+ "global_step": 3900,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 8.15012613848348e-06,
13
+ "grad_norm": 3.4710192680358887,
14
+ "learning_rate": 1.0000000000000001e-07,
15
+ "loss": 11.2605,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0002445037841545044,
20
+ "grad_norm": 5.464046955108643,
21
+ "learning_rate": 3e-06,
22
+ "loss": 10.9977,
23
+ "step": 30
24
+ },
25
+ {
26
+ "epoch": 0.0004890075683090088,
27
+ "grad_norm": 1.1376756429672241,
28
+ "learning_rate": 6e-06,
29
+ "loss": 9.4082,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.0007335113524635132,
34
+ "grad_norm": 1.2878344058990479,
35
+ "learning_rate": 9e-06,
36
+ "loss": 8.549,
37
+ "step": 90
38
+ },
39
+ {
40
+ "epoch": 0.0009780151366180175,
41
+ "grad_norm": 1.2800588607788086,
42
+ "learning_rate": 1.2e-05,
43
+ "loss": 8.0361,
44
+ "step": 120
45
+ },
46
+ {
47
+ "epoch": 0.001222518920772522,
48
+ "grad_norm": 1.4315314292907715,
49
+ "learning_rate": 1.5e-05,
50
+ "loss": 7.653,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.0014670227049270264,
55
+ "grad_norm": 1.381317377090454,
56
+ "learning_rate": 1.8e-05,
57
+ "loss": 7.4179,
58
+ "step": 180
59
+ },
60
+ {
61
+ "epoch": 0.0017115264890815308,
62
+ "grad_norm": 1.7989460229873657,
63
+ "learning_rate": 2.1e-05,
64
+ "loss": 7.2012,
65
+ "step": 210
66
+ },
67
+ {
68
+ "epoch": 0.001956030273236035,
69
+ "grad_norm": 1.3431414365768433,
70
+ "learning_rate": 2.4e-05,
71
+ "loss": 7.0383,
72
+ "step": 240
73
+ },
74
+ {
75
+ "epoch": 0.0022005340573905395,
76
+ "grad_norm": 1.028826117515564,
77
+ "learning_rate": 2.7000000000000002e-05,
78
+ "loss": 6.866,
79
+ "step": 270
80
+ },
81
+ {
82
+ "epoch": 0.002445037841545044,
83
+ "grad_norm": 1.201025128364563,
84
+ "learning_rate": 3e-05,
85
+ "loss": 6.717,
86
+ "step": 300
87
+ },
88
+ {
89
+ "epoch": 0.0026895416256995483,
90
+ "grad_norm": 1.1023098230361938,
91
+ "learning_rate": 3.3e-05,
92
+ "loss": 6.5535,
93
+ "step": 330
94
+ },
95
+ {
96
+ "epoch": 0.0029340454098540527,
97
+ "grad_norm": 1.2839674949645996,
98
+ "learning_rate": 3.6e-05,
99
+ "loss": 6.4022,
100
+ "step": 360
101
+ },
102
+ {
103
+ "epoch": 0.003178549194008557,
104
+ "grad_norm": 2.267265796661377,
105
+ "learning_rate": 3.9000000000000006e-05,
106
+ "loss": 6.2858,
107
+ "step": 390
108
+ },
109
+ {
110
+ "epoch": 0.0034230529781630616,
111
+ "grad_norm": 1.0635628700256348,
112
+ "learning_rate": 4.2e-05,
113
+ "loss": 6.1681,
114
+ "step": 420
115
+ },
116
+ {
117
+ "epoch": 0.0036675567623175656,
118
+ "grad_norm": 1.263838768005371,
119
+ "learning_rate": 4.5e-05,
120
+ "loss": 6.0728,
121
+ "step": 450
122
+ },
123
+ {
124
+ "epoch": 0.00391206054647207,
125
+ "grad_norm": 1.4611454010009766,
126
+ "learning_rate": 4.8e-05,
127
+ "loss": 5.972,
128
+ "step": 480
129
+ },
130
+ {
131
+ "epoch": 0.0041565643306265745,
132
+ "grad_norm": 1.0120561122894287,
133
+ "learning_rate": 4.999999990869806e-05,
134
+ "loss": 5.8619,
135
+ "step": 510
136
+ },
137
+ {
138
+ "epoch": 0.004401068114781079,
139
+ "grad_norm": 1.1349974870681763,
140
+ "learning_rate": 4.999999853916893e-05,
141
+ "loss": 5.785,
142
+ "step": 540
143
+ },
144
+ {
145
+ "epoch": 0.004645571898935583,
146
+ "grad_norm": 1.0840613842010498,
147
+ "learning_rate": 4.9999995526204936e-05,
148
+ "loss": 5.7071,
149
+ "step": 570
150
+ },
151
+ {
152
+ "epoch": 0.004890075683090088,
153
+ "grad_norm": 1.258074402809143,
154
+ "learning_rate": 4.999999086980628e-05,
155
+ "loss": 5.6199,
156
+ "step": 600
157
+ },
158
+ {
159
+ "epoch": 0.005134579467244592,
160
+ "grad_norm": 1.284726858139038,
161
+ "learning_rate": 4.999998456997326e-05,
162
+ "loss": 5.5465,
163
+ "step": 630
164
+ },
165
+ {
166
+ "epoch": 0.005379083251399097,
167
+ "grad_norm": 1.2079874277114868,
168
+ "learning_rate": 4.999997662670628e-05,
169
+ "loss": 5.4816,
170
+ "step": 660
171
+ },
172
+ {
173
+ "epoch": 0.005623587035553601,
174
+ "grad_norm": 1.3364052772521973,
175
+ "learning_rate": 4.999996704000589e-05,
176
+ "loss": 5.4079,
177
+ "step": 690
178
+ },
179
+ {
180
+ "epoch": 0.0058680908197081055,
181
+ "grad_norm": 0.9860705137252808,
182
+ "learning_rate": 4.99999558098727e-05,
183
+ "loss": 5.3598,
184
+ "step": 720
185
+ },
186
+ {
187
+ "epoch": 0.00611259460386261,
188
+ "grad_norm": 1.2071930170059204,
189
+ "learning_rate": 4.9999942936307445e-05,
190
+ "loss": 5.2884,
191
+ "step": 750
192
+ },
193
+ {
194
+ "epoch": 0.006357098388017114,
195
+ "grad_norm": 0.8959563970565796,
196
+ "learning_rate": 4.9999928419310994e-05,
197
+ "loss": 5.2391,
198
+ "step": 780
199
+ },
200
+ {
201
+ "epoch": 0.006601602172171619,
202
+ "grad_norm": 1.2356096506118774,
203
+ "learning_rate": 4.999991225888427e-05,
204
+ "loss": 5.1879,
205
+ "step": 810
206
+ },
207
+ {
208
+ "epoch": 0.006846105956326123,
209
+ "grad_norm": 0.9705113172531128,
210
+ "learning_rate": 4.999989445502837e-05,
211
+ "loss": 5.1424,
212
+ "step": 840
213
+ },
214
+ {
215
+ "epoch": 0.007090609740480627,
216
+ "grad_norm": 0.9504437446594238,
217
+ "learning_rate": 4.9999875007744436e-05,
218
+ "loss": 5.0966,
219
+ "step": 870
220
+ },
221
+ {
222
+ "epoch": 0.007335113524635131,
223
+ "grad_norm": 0.9488673806190491,
224
+ "learning_rate": 4.9999853917033756e-05,
225
+ "loss": 5.0424,
226
+ "step": 900
227
+ },
228
+ {
229
+ "epoch": 0.007579617308789636,
230
+ "grad_norm": 0.959373950958252,
231
+ "learning_rate": 4.999983118289773e-05,
232
+ "loss": 5.0387,
233
+ "step": 930
234
+ },
235
+ {
236
+ "epoch": 0.00782412109294414,
237
+ "grad_norm": 0.8465414643287659,
238
+ "learning_rate": 4.999980680533782e-05,
239
+ "loss": 4.9769,
240
+ "step": 960
241
+ },
242
+ {
243
+ "epoch": 0.008068624877098645,
244
+ "grad_norm": 0.8328993916511536,
245
+ "learning_rate": 4.999978078435567e-05,
246
+ "loss": 4.9335,
247
+ "step": 990
248
+ },
249
+ {
250
+ "epoch": 0.008313128661253149,
251
+ "grad_norm": 0.8107655644416809,
252
+ "learning_rate": 4.999975311995295e-05,
253
+ "loss": 4.9214,
254
+ "step": 1020
255
+ },
256
+ {
257
+ "epoch": 0.008557632445407654,
258
+ "grad_norm": 0.8149654865264893,
259
+ "learning_rate": 4.99997238121315e-05,
260
+ "loss": 4.8651,
261
+ "step": 1050
262
+ },
263
+ {
264
+ "epoch": 0.008802136229562158,
265
+ "grad_norm": 0.8837414979934692,
266
+ "learning_rate": 4.999969286089325e-05,
267
+ "loss": 4.8327,
268
+ "step": 1080
269
+ },
270
+ {
271
+ "epoch": 0.009046640013716663,
272
+ "grad_norm": 1.1360137462615967,
273
+ "learning_rate": 4.9999660266240235e-05,
274
+ "loss": 4.7906,
275
+ "step": 1110
276
+ },
277
+ {
278
+ "epoch": 0.009291143797871167,
279
+ "grad_norm": 0.7992026209831238,
280
+ "learning_rate": 4.9999626028174585e-05,
281
+ "loss": 4.7612,
282
+ "step": 1140
283
+ },
284
+ {
285
+ "epoch": 0.00953564758202567,
286
+ "grad_norm": 0.8481825590133667,
287
+ "learning_rate": 4.999959014669856e-05,
288
+ "loss": 4.7106,
289
+ "step": 1170
290
+ },
291
+ {
292
+ "epoch": 0.009780151366180176,
293
+ "grad_norm": 0.8183879256248474,
294
+ "learning_rate": 4.9999552621814513e-05,
295
+ "loss": 4.6993,
296
+ "step": 1200
297
+ },
298
+ {
299
+ "epoch": 0.010024655150334679,
300
+ "grad_norm": 0.8460689187049866,
301
+ "learning_rate": 4.9999513453524917e-05,
302
+ "loss": 4.6664,
303
+ "step": 1230
304
+ },
305
+ {
306
+ "epoch": 0.010269158934489184,
307
+ "grad_norm": 0.8723706007003784,
308
+ "learning_rate": 4.9999472641832336e-05,
309
+ "loss": 4.6371,
310
+ "step": 1260
311
+ },
312
+ {
313
+ "epoch": 0.010513662718643688,
314
+ "grad_norm": 0.7682787179946899,
315
+ "learning_rate": 4.999943018673946e-05,
316
+ "loss": 4.6184,
317
+ "step": 1290
318
+ },
319
+ {
320
+ "epoch": 0.010758166502798193,
321
+ "grad_norm": 0.9049955606460571,
322
+ "learning_rate": 4.999938608824909e-05,
323
+ "loss": 4.5968,
324
+ "step": 1320
325
+ },
326
+ {
327
+ "epoch": 0.011002670286952697,
328
+ "grad_norm": 0.7860899567604065,
329
+ "learning_rate": 4.999934034636411e-05,
330
+ "loss": 4.5266,
331
+ "step": 1350
332
+ },
333
+ {
334
+ "epoch": 0.011247174071107202,
335
+ "grad_norm": 0.7918768525123596,
336
+ "learning_rate": 4.999929296108753e-05,
337
+ "loss": 4.5069,
338
+ "step": 1380
339
+ },
340
+ {
341
+ "epoch": 0.011491677855261706,
342
+ "grad_norm": 0.6713089942932129,
343
+ "learning_rate": 4.9999243932422466e-05,
344
+ "loss": 4.4663,
345
+ "step": 1410
346
+ },
347
+ {
348
+ "epoch": 0.011736181639416211,
349
+ "grad_norm": 0.756101131439209,
350
+ "learning_rate": 4.999919326037215e-05,
351
+ "loss": 4.4782,
352
+ "step": 1440
353
+ },
354
+ {
355
+ "epoch": 0.011980685423570715,
356
+ "grad_norm": 0.7067996263504028,
357
+ "learning_rate": 4.99991409449399e-05,
358
+ "loss": 4.4388,
359
+ "step": 1470
360
+ },
361
+ {
362
+ "epoch": 0.01222518920772522,
363
+ "grad_norm": 0.7132194638252258,
364
+ "learning_rate": 4.999908698612916e-05,
365
+ "loss": 4.4135,
366
+ "step": 1500
367
+ },
368
+ {
369
+ "epoch": 0.012469692991879723,
370
+ "grad_norm": 0.7282501459121704,
371
+ "learning_rate": 4.9999031383943486e-05,
372
+ "loss": 4.4057,
373
+ "step": 1530
374
+ },
375
+ {
376
+ "epoch": 0.012714196776034229,
377
+ "grad_norm": 0.6851722598075867,
378
+ "learning_rate": 4.999897413838651e-05,
379
+ "loss": 4.3612,
380
+ "step": 1560
381
+ },
382
+ {
383
+ "epoch": 0.012958700560188732,
384
+ "grad_norm": 0.7953110337257385,
385
+ "learning_rate": 4.999891524946202e-05,
386
+ "loss": 4.3268,
387
+ "step": 1590
388
+ },
389
+ {
390
+ "epoch": 0.013203204344343238,
391
+ "grad_norm": 0.726719319820404,
392
+ "learning_rate": 4.999885471717387e-05,
393
+ "loss": 4.314,
394
+ "step": 1620
395
+ },
396
+ {
397
+ "epoch": 0.013447708128497741,
398
+ "grad_norm": 0.7354792356491089,
399
+ "learning_rate": 4.999879254152605e-05,
400
+ "loss": 4.2807,
401
+ "step": 1650
402
+ },
403
+ {
404
+ "epoch": 0.013692211912652246,
405
+ "grad_norm": 0.7072017788887024,
406
+ "learning_rate": 4.999872872252265e-05,
407
+ "loss": 4.282,
408
+ "step": 1680
409
+ },
410
+ {
411
+ "epoch": 0.01393671569680675,
412
+ "grad_norm": 0.690112292766571,
413
+ "learning_rate": 4.999866326016785e-05,
414
+ "loss": 4.2686,
415
+ "step": 1710
416
+ },
417
+ {
418
+ "epoch": 0.014181219480961254,
419
+ "grad_norm": 0.697634756565094,
420
+ "learning_rate": 4.999859615446596e-05,
421
+ "loss": 4.2662,
422
+ "step": 1740
423
+ },
424
+ {
425
+ "epoch": 0.014425723265115759,
426
+ "grad_norm": 0.6999862790107727,
427
+ "learning_rate": 4.99985274054214e-05,
428
+ "loss": 4.2207,
429
+ "step": 1770
430
+ },
431
+ {
432
+ "epoch": 0.014670227049270262,
433
+ "grad_norm": 0.6920334100723267,
434
+ "learning_rate": 4.999845701303868e-05,
435
+ "loss": 4.2163,
436
+ "step": 1800
437
+ },
438
+ {
439
+ "epoch": 0.014914730833424768,
440
+ "grad_norm": 0.6884493827819824,
441
+ "learning_rate": 4.999838497732243e-05,
442
+ "loss": 4.209,
443
+ "step": 1830
444
+ },
445
+ {
446
+ "epoch": 0.015159234617579271,
447
+ "grad_norm": 0.776447057723999,
448
+ "learning_rate": 4.999831129827739e-05,
449
+ "loss": 4.1856,
450
+ "step": 1860
451
+ },
452
+ {
453
+ "epoch": 0.015403738401733777,
454
+ "grad_norm": 0.7332949042320251,
455
+ "learning_rate": 4.9998235975908394e-05,
456
+ "loss": 4.156,
457
+ "step": 1890
458
+ },
459
+ {
460
+ "epoch": 0.01564824218588828,
461
+ "grad_norm": 0.6691558361053467,
462
+ "learning_rate": 4.99981590102204e-05,
463
+ "loss": 4.1339,
464
+ "step": 1920
465
+ },
466
+ {
467
+ "epoch": 0.015892745970042785,
468
+ "grad_norm": 0.6789201498031616,
469
+ "learning_rate": 4.9998080401218464e-05,
470
+ "loss": 4.1344,
471
+ "step": 1950
472
+ },
473
+ {
474
+ "epoch": 0.01613724975419729,
475
+ "grad_norm": 0.6654175519943237,
476
+ "learning_rate": 4.999800014890777e-05,
477
+ "loss": 4.1295,
478
+ "step": 1980
479
+ },
480
+ {
481
+ "epoch": 0.016381753538351793,
482
+ "grad_norm": 0.6632519364356995,
483
+ "learning_rate": 4.9997918253293555e-05,
484
+ "loss": 4.1036,
485
+ "step": 2010
486
+ },
487
+ {
488
+ "epoch": 0.016626257322506298,
489
+ "grad_norm": 0.6618740558624268,
490
+ "learning_rate": 4.999783471438124e-05,
491
+ "loss": 4.0857,
492
+ "step": 2040
493
+ },
494
+ {
495
+ "epoch": 0.016870761106660803,
496
+ "grad_norm": 0.6384952068328857,
497
+ "learning_rate": 4.999774953217631e-05,
498
+ "loss": 4.0755,
499
+ "step": 2070
500
+ },
501
+ {
502
+ "epoch": 0.01711526489081531,
503
+ "grad_norm": 0.6808215975761414,
504
+ "learning_rate": 4.9997662706684345e-05,
505
+ "loss": 4.0568,
506
+ "step": 2100
507
+ },
508
+ {
509
+ "epoch": 0.01735976867496981,
510
+ "grad_norm": 0.6514068841934204,
511
+ "learning_rate": 4.999757423791107e-05,
512
+ "loss": 4.0474,
513
+ "step": 2130
514
+ },
515
+ {
516
+ "epoch": 0.017604272459124316,
517
+ "grad_norm": 0.6691142320632935,
518
+ "learning_rate": 4.9997484125862306e-05,
519
+ "loss": 4.0467,
520
+ "step": 2160
521
+ },
522
+ {
523
+ "epoch": 0.01784877624327882,
524
+ "grad_norm": 0.6240984201431274,
525
+ "learning_rate": 4.999739237054395e-05,
526
+ "loss": 4.0259,
527
+ "step": 2190
528
+ },
529
+ {
530
+ "epoch": 0.018093280027433326,
531
+ "grad_norm": 0.6286123991012573,
532
+ "learning_rate": 4.9997298971962065e-05,
533
+ "loss": 4.0098,
534
+ "step": 2220
535
+ },
536
+ {
537
+ "epoch": 0.018337783811587828,
538
+ "grad_norm": 0.6232910752296448,
539
+ "learning_rate": 4.999720393012277e-05,
540
+ "loss": 4.0203,
541
+ "step": 2250
542
+ },
543
+ {
544
+ "epoch": 0.018582287595742333,
545
+ "grad_norm": 0.6792376041412354,
546
+ "learning_rate": 4.999710724503233e-05,
547
+ "loss": 3.9909,
548
+ "step": 2280
549
+ },
550
+ {
551
+ "epoch": 0.01882679137989684,
552
+ "grad_norm": 0.6824718117713928,
553
+ "learning_rate": 4.9997008916697075e-05,
554
+ "loss": 3.9922,
555
+ "step": 2310
556
+ },
557
+ {
558
+ "epoch": 0.01907129516405134,
559
+ "grad_norm": 0.6520410776138306,
560
+ "learning_rate": 4.999690894512349e-05,
561
+ "loss": 3.9533,
562
+ "step": 2340
563
+ },
564
+ {
565
+ "epoch": 0.019315798948205846,
566
+ "grad_norm": 0.6467030048370361,
567
+ "learning_rate": 4.999680733031814e-05,
568
+ "loss": 3.9464,
569
+ "step": 2370
570
+ },
571
+ {
572
+ "epoch": 0.01956030273236035,
573
+ "grad_norm": 0.6356080770492554,
574
+ "learning_rate": 4.9996704072287716e-05,
575
+ "loss": 3.9288,
576
+ "step": 2400
577
+ },
578
+ {
579
+ "epoch": 0.019804806516514856,
580
+ "grad_norm": 0.6498362421989441,
581
+ "learning_rate": 4.9996599171038984e-05,
582
+ "loss": 3.9345,
583
+ "step": 2430
584
+ },
585
+ {
586
+ "epoch": 0.020049310300669358,
587
+ "grad_norm": 0.6107562184333801,
588
+ "learning_rate": 4.999649262657886e-05,
589
+ "loss": 3.9368,
590
+ "step": 2460
591
+ },
592
+ {
593
+ "epoch": 0.020293814084823864,
594
+ "grad_norm": 0.6478250622749329,
595
+ "learning_rate": 4.999638443891434e-05,
596
+ "loss": 3.9273,
597
+ "step": 2490
598
+ },
599
+ {
600
+ "epoch": 0.02053831786897837,
601
+ "grad_norm": 0.631263256072998,
602
+ "learning_rate": 4.999627460805253e-05,
603
+ "loss": 3.9136,
604
+ "step": 2520
605
+ },
606
+ {
607
+ "epoch": 0.020782821653132874,
608
+ "grad_norm": 0.6120920777320862,
609
+ "learning_rate": 4.999616313400066e-05,
610
+ "loss": 3.8834,
611
+ "step": 2550
612
+ },
613
+ {
614
+ "epoch": 0.021027325437287376,
615
+ "grad_norm": 0.6151197552680969,
616
+ "learning_rate": 4.999605001676605e-05,
617
+ "loss": 3.8994,
618
+ "step": 2580
619
+ },
620
+ {
621
+ "epoch": 0.02127182922144188,
622
+ "grad_norm": 0.623715877532959,
623
+ "learning_rate": 4.9995935256356144e-05,
624
+ "loss": 3.8929,
625
+ "step": 2610
626
+ },
627
+ {
628
+ "epoch": 0.021516333005596387,
629
+ "grad_norm": 0.6688769459724426,
630
+ "learning_rate": 4.9995818852778476e-05,
631
+ "loss": 3.8499,
632
+ "step": 2640
633
+ },
634
+ {
635
+ "epoch": 0.021760836789750892,
636
+ "grad_norm": 0.6272155046463013,
637
+ "learning_rate": 4.999570080604071e-05,
638
+ "loss": 3.8861,
639
+ "step": 2670
640
+ },
641
+ {
642
+ "epoch": 0.022005340573905394,
643
+ "grad_norm": 0.597653329372406,
644
+ "learning_rate": 4.99955811161506e-05,
645
+ "loss": 3.8674,
646
+ "step": 2700
647
+ },
648
+ {
649
+ "epoch": 0.0222498443580599,
650
+ "grad_norm": 0.5608483552932739,
651
+ "learning_rate": 4.9995459783116004e-05,
652
+ "loss": 3.8493,
653
+ "step": 2730
654
+ },
655
+ {
656
+ "epoch": 0.022494348142214404,
657
+ "grad_norm": 0.5991063117980957,
658
+ "learning_rate": 4.999533680694493e-05,
659
+ "loss": 3.8454,
660
+ "step": 2760
661
+ },
662
+ {
663
+ "epoch": 0.02273885192636891,
664
+ "grad_norm": 0.5738102793693542,
665
+ "learning_rate": 4.9995212187645416e-05,
666
+ "loss": 3.8395,
667
+ "step": 2790
668
+ },
669
+ {
670
+ "epoch": 0.02298335571052341,
671
+ "grad_norm": 0.6145568490028381,
672
+ "learning_rate": 4.9995085925225693e-05,
673
+ "loss": 3.8313,
674
+ "step": 2820
675
+ },
676
+ {
677
+ "epoch": 0.023227859494677917,
678
+ "grad_norm": 0.6019515991210938,
679
+ "learning_rate": 4.999495801969404e-05,
680
+ "loss": 3.8277,
681
+ "step": 2850
682
+ },
683
+ {
684
+ "epoch": 0.023472363278832422,
685
+ "grad_norm": 0.6177758574485779,
686
+ "learning_rate": 4.9994828471058876e-05,
687
+ "loss": 3.8083,
688
+ "step": 2880
689
+ },
690
+ {
691
+ "epoch": 0.023716867062986924,
692
+ "grad_norm": 0.5616528987884521,
693
+ "learning_rate": 4.9994697279328714e-05,
694
+ "loss": 3.8114,
695
+ "step": 2910
696
+ },
697
+ {
698
+ "epoch": 0.02396137084714143,
699
+ "grad_norm": 0.6194447875022888,
700
+ "learning_rate": 4.9994564444512176e-05,
701
+ "loss": 3.8183,
702
+ "step": 2940
703
+ },
704
+ {
705
+ "epoch": 0.024205874631295934,
706
+ "grad_norm": 0.578895092010498,
707
+ "learning_rate": 4.9994429966618e-05,
708
+ "loss": 3.7871,
709
+ "step": 2970
710
+ },
711
+ {
712
+ "epoch": 0.02445037841545044,
713
+ "grad_norm": 0.6014060378074646,
714
+ "learning_rate": 4.999429384565502e-05,
715
+ "loss": 3.7711,
716
+ "step": 3000
717
+ },
718
+ {
719
+ "epoch": 0.02469488219960494,
720
+ "grad_norm": 0.5589067339897156,
721
+ "learning_rate": 4.999415608163217e-05,
722
+ "loss": 3.7533,
723
+ "step": 3030
724
+ },
725
+ {
726
+ "epoch": 0.024939385983759447,
727
+ "grad_norm": 0.5722873210906982,
728
+ "learning_rate": 4.999401667455854e-05,
729
+ "loss": 3.7585,
730
+ "step": 3060
731
+ },
732
+ {
733
+ "epoch": 0.025183889767913952,
734
+ "grad_norm": 0.5734965801239014,
735
+ "learning_rate": 4.9993875624443274e-05,
736
+ "loss": 3.77,
737
+ "step": 3090
738
+ },
739
+ {
740
+ "epoch": 0.025428393552068457,
741
+ "grad_norm": 0.5524207353591919,
742
+ "learning_rate": 4.9993732931295646e-05,
743
+ "loss": 3.718,
744
+ "step": 3120
745
+ },
746
+ {
747
+ "epoch": 0.02567289733622296,
748
+ "grad_norm": 0.5776082277297974,
749
+ "learning_rate": 4.999358859512503e-05,
750
+ "loss": 3.7573,
751
+ "step": 3150
752
+ },
753
+ {
754
+ "epoch": 0.025917401120377465,
755
+ "grad_norm": 0.5799595713615417,
756
+ "learning_rate": 4.9993442615940936e-05,
757
+ "loss": 3.7552,
758
+ "step": 3180
759
+ },
760
+ {
761
+ "epoch": 0.02616190490453197,
762
+ "grad_norm": 0.5820346474647522,
763
+ "learning_rate": 4.999329499375292e-05,
764
+ "loss": 3.7394,
765
+ "step": 3210
766
+ },
767
+ {
768
+ "epoch": 0.026406408688686475,
769
+ "grad_norm": 0.5450282096862793,
770
+ "learning_rate": 4.999314572857074e-05,
771
+ "loss": 3.7393,
772
+ "step": 3240
773
+ },
774
+ {
775
+ "epoch": 0.026650912472840977,
776
+ "grad_norm": 0.6213249564170837,
777
+ "learning_rate": 4.9992994820404174e-05,
778
+ "loss": 3.7191,
779
+ "step": 3270
780
+ },
781
+ {
782
+ "epoch": 0.026895416256995482,
783
+ "grad_norm": 0.5940688848495483,
784
+ "learning_rate": 4.999284226926314e-05,
785
+ "loss": 3.719,
786
+ "step": 3300
787
+ },
788
+ {
789
+ "epoch": 0.027139920041149988,
790
+ "grad_norm": 0.5779993534088135,
791
+ "learning_rate": 4.999268807515768e-05,
792
+ "loss": 3.7092,
793
+ "step": 3330
794
+ },
795
+ {
796
+ "epoch": 0.027384423825304493,
797
+ "grad_norm": 0.5899255871772766,
798
+ "learning_rate": 4.999253223809792e-05,
799
+ "loss": 3.6939,
800
+ "step": 3360
801
+ },
802
+ {
803
+ "epoch": 0.027628927609458995,
804
+ "grad_norm": 0.6330375671386719,
805
+ "learning_rate": 4.999237475809411e-05,
806
+ "loss": 3.7102,
807
+ "step": 3390
808
+ },
809
+ {
810
+ "epoch": 0.0278734313936135,
811
+ "grad_norm": 0.5771914720535278,
812
+ "learning_rate": 4.99922156351566e-05,
813
+ "loss": 3.7196,
814
+ "step": 3420
815
+ },
816
+ {
817
+ "epoch": 0.028117935177768005,
818
+ "grad_norm": 0.5769143104553223,
819
+ "learning_rate": 4.999205486929586e-05,
820
+ "loss": 3.7127,
821
+ "step": 3450
822
+ },
823
+ {
824
+ "epoch": 0.028362438961922507,
825
+ "grad_norm": 0.5581954121589661,
826
+ "learning_rate": 4.999189246052245e-05,
827
+ "loss": 3.689,
828
+ "step": 3480
829
+ },
830
+ {
831
+ "epoch": 0.028606942746077012,
832
+ "grad_norm": 0.6041043400764465,
833
+ "learning_rate": 4.999172840884704e-05,
834
+ "loss": 3.6831,
835
+ "step": 3510
836
+ },
837
+ {
838
+ "epoch": 0.028851446530231518,
839
+ "grad_norm": 0.5458335280418396,
840
+ "learning_rate": 4.999156271428043e-05,
841
+ "loss": 3.6694,
842
+ "step": 3540
843
+ },
844
+ {
845
+ "epoch": 0.029095950314386023,
846
+ "grad_norm": 0.5470607280731201,
847
+ "learning_rate": 4.9991395376833496e-05,
848
+ "loss": 3.6702,
849
+ "step": 3570
850
+ },
851
+ {
852
+ "epoch": 0.029340454098540525,
853
+ "grad_norm": 0.5878787040710449,
854
+ "learning_rate": 4.999122639651725e-05,
855
+ "loss": 3.6492,
856
+ "step": 3600
857
+ },
858
+ {
859
+ "epoch": 0.02958495788269503,
860
+ "grad_norm": 0.5691691637039185,
861
+ "learning_rate": 4.9991055773342795e-05,
862
+ "loss": 3.6812,
863
+ "step": 3630
864
+ },
865
+ {
866
+ "epoch": 0.029829461666849535,
867
+ "grad_norm": 0.5548356771469116,
868
+ "learning_rate": 4.9990883507321354e-05,
869
+ "loss": 3.645,
870
+ "step": 3660
871
+ },
872
+ {
873
+ "epoch": 0.03007396545100404,
874
+ "grad_norm": 0.5686156153678894,
875
+ "learning_rate": 4.999070959846424e-05,
876
+ "loss": 3.6505,
877
+ "step": 3690
878
+ },
879
+ {
880
+ "epoch": 0.030318469235158543,
881
+ "grad_norm": 0.5596534013748169,
882
+ "learning_rate": 4.999053404678289e-05,
883
+ "loss": 3.6532,
884
+ "step": 3720
885
+ },
886
+ {
887
+ "epoch": 0.030562973019313048,
888
+ "grad_norm": 0.54421067237854,
889
+ "learning_rate": 4.999035685228884e-05,
890
+ "loss": 3.6238,
891
+ "step": 3750
892
+ },
893
+ {
894
+ "epoch": 0.030807476803467553,
895
+ "grad_norm": 0.56732177734375,
896
+ "learning_rate": 4.999017801499375e-05,
897
+ "loss": 3.6449,
898
+ "step": 3780
899
+ },
900
+ {
901
+ "epoch": 0.03105198058762206,
902
+ "grad_norm": 0.5608410239219666,
903
+ "learning_rate": 4.998999753490937e-05,
904
+ "loss": 3.6344,
905
+ "step": 3810
906
+ },
907
+ {
908
+ "epoch": 0.03129648437177656,
909
+ "grad_norm": 0.5919491648674011,
910
+ "learning_rate": 4.998981541204757e-05,
911
+ "loss": 3.6213,
912
+ "step": 3840
913
+ },
914
+ {
915
+ "epoch": 0.031540988155931066,
916
+ "grad_norm": 0.5795233249664307,
917
+ "learning_rate": 4.998963164642031e-05,
918
+ "loss": 3.6239,
919
+ "step": 3870
920
+ },
921
+ {
922
+ "epoch": 0.03178549194008557,
923
+ "grad_norm": 0.5669205784797668,
924
+ "learning_rate": 4.9989446238039676e-05,
925
+ "loss": 3.5831,
926
+ "step": 3900
927
+ }
928
+ ],
929
+ "logging_steps": 30,
930
+ "max_steps": 368091,
931
+ "num_input_tokens_seen": 0,
932
+ "num_train_epochs": 3,
933
+ "save_steps": 100,
934
+ "total_flos": 3.730642953043968e+18,
935
+ "train_batch_size": 2,
936
+ "trial_name": null,
937
+ "trial_params": null
938
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f909d8205eae6d012dc965e337249e1d014ef52c5b7115301085202b50cb6566
3
+ size 4984