Allison Casasola commited on
Commit
76bc2d4
1 Parent(s): becbd4b
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 1600,
14
+ "n_head": 25,
15
+ "n_inner": null,
16
+ "n_layer": 48,
17
+ "n_positions": 1024,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.37.0",
29
+ "use_cache": true,
30
+ "vocab_size": 50257
31
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.37.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4c96a786da80547bc9922afe4ecbac508c55431617efe1662ada2869f159dc
3
+ size 4959881464
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c393a4a1cd4352d3a029be80aa803eb5a1a5013b6148f02ed3e93127f2a637
3
+ size 1270624096
model.safetensors.index.json ADDED
@@ -0,0 +1,587 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6230444800
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
7
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
18
+ "transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
19
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
21
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
23
+ "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
25
+ "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
31
+ "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
33
+ "transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
34
+ "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
35
+ "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
37
+ "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
38
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
39
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
40
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
41
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
42
+ "transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
43
+ "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
44
+ "transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
45
+ "transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
47
+ "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
49
+ "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
51
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
52
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
53
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
55
+ "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
57
+ "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
59
+ "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
60
+ "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
61
+ "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
63
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
64
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
65
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
66
+ "transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
67
+ "transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
68
+ "transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
69
+ "transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
70
+ "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
71
+ "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
73
+ "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
75
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
77
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
79
+ "transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
81
+ "transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
83
+ "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
85
+ "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
86
+ "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
87
+ "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
89
+ "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
90
+ "transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
91
+ "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
92
+ "transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
93
+ "transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
94
+ "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
95
+ "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
96
+ "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
97
+ "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
99
+ "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
101
+ "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
103
+ "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
104
+ "transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
105
+ "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
106
+ "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
107
+ "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
108
+ "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
109
+ "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
110
+ "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
111
+ "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
112
+ "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
113
+ "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
114
+ "transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
115
+ "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
116
+ "transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
117
+ "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
118
+ "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
119
+ "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
120
+ "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
121
+ "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
122
+ "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
123
+ "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
124
+ "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
125
+ "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
126
+ "transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
127
+ "transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
128
+ "transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
129
+ "transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
130
+ "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
131
+ "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
132
+ "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
133
+ "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
134
+ "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
135
+ "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
136
+ "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
137
+ "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
138
+ "transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
139
+ "transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
140
+ "transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
141
+ "transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
142
+ "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
143
+ "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
144
+ "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
145
+ "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
146
+ "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
147
+ "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
148
+ "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
149
+ "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
150
+ "transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
151
+ "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
152
+ "transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
153
+ "transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
154
+ "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
155
+ "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
156
+ "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
157
+ "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
158
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
159
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
160
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
161
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
162
+ "transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
163
+ "transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
164
+ "transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
165
+ "transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
166
+ "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
167
+ "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
168
+ "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
169
+ "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
170
+ "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
171
+ "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
172
+ "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
173
+ "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
174
+ "transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
175
+ "transformer.h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
176
+ "transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
177
+ "transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
178
+ "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
179
+ "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
180
+ "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
181
+ "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
182
+ "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
183
+ "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
184
+ "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
185
+ "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
186
+ "transformer.h.22.attn.c_attn.bias": "model-00001-of-00002.safetensors",
187
+ "transformer.h.22.attn.c_attn.weight": "model-00001-of-00002.safetensors",
188
+ "transformer.h.22.attn.c_proj.bias": "model-00001-of-00002.safetensors",
189
+ "transformer.h.22.attn.c_proj.weight": "model-00001-of-00002.safetensors",
190
+ "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
191
+ "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
192
+ "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
193
+ "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
194
+ "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
195
+ "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
196
+ "transformer.h.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
197
+ "transformer.h.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
198
+ "transformer.h.23.attn.c_attn.bias": "model-00001-of-00002.safetensors",
199
+ "transformer.h.23.attn.c_attn.weight": "model-00001-of-00002.safetensors",
200
+ "transformer.h.23.attn.c_proj.bias": "model-00001-of-00002.safetensors",
201
+ "transformer.h.23.attn.c_proj.weight": "model-00001-of-00002.safetensors",
202
+ "transformer.h.23.ln_1.bias": "model-00001-of-00002.safetensors",
203
+ "transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
204
+ "transformer.h.23.ln_2.bias": "model-00001-of-00002.safetensors",
205
+ "transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
206
+ "transformer.h.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
207
+ "transformer.h.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
208
+ "transformer.h.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
209
+ "transformer.h.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
210
+ "transformer.h.24.attn.c_attn.bias": "model-00001-of-00002.safetensors",
211
+ "transformer.h.24.attn.c_attn.weight": "model-00001-of-00002.safetensors",
212
+ "transformer.h.24.attn.c_proj.bias": "model-00001-of-00002.safetensors",
213
+ "transformer.h.24.attn.c_proj.weight": "model-00001-of-00002.safetensors",
214
+ "transformer.h.24.ln_1.bias": "model-00001-of-00002.safetensors",
215
+ "transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
216
+ "transformer.h.24.ln_2.bias": "model-00001-of-00002.safetensors",
217
+ "transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
218
+ "transformer.h.24.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
219
+ "transformer.h.24.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
220
+ "transformer.h.24.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
221
+ "transformer.h.24.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
222
+ "transformer.h.25.attn.c_attn.bias": "model-00001-of-00002.safetensors",
223
+ "transformer.h.25.attn.c_attn.weight": "model-00001-of-00002.safetensors",
224
+ "transformer.h.25.attn.c_proj.bias": "model-00001-of-00002.safetensors",
225
+ "transformer.h.25.attn.c_proj.weight": "model-00001-of-00002.safetensors",
226
+ "transformer.h.25.ln_1.bias": "model-00001-of-00002.safetensors",
227
+ "transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
228
+ "transformer.h.25.ln_2.bias": "model-00001-of-00002.safetensors",
229
+ "transformer.h.25.ln_2.weight": "model-00001-of-00002.safetensors",
230
+ "transformer.h.25.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
231
+ "transformer.h.25.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
232
+ "transformer.h.25.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
233
+ "transformer.h.25.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
234
+ "transformer.h.26.attn.c_attn.bias": "model-00001-of-00002.safetensors",
235
+ "transformer.h.26.attn.c_attn.weight": "model-00001-of-00002.safetensors",
236
+ "transformer.h.26.attn.c_proj.bias": "model-00001-of-00002.safetensors",
237
+ "transformer.h.26.attn.c_proj.weight": "model-00001-of-00002.safetensors",
238
+ "transformer.h.26.ln_1.bias": "model-00001-of-00002.safetensors",
239
+ "transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
240
+ "transformer.h.26.ln_2.bias": "model-00001-of-00002.safetensors",
241
+ "transformer.h.26.ln_2.weight": "model-00001-of-00002.safetensors",
242
+ "transformer.h.26.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
243
+ "transformer.h.26.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
244
+ "transformer.h.26.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
245
+ "transformer.h.26.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
246
+ "transformer.h.27.attn.c_attn.bias": "model-00001-of-00002.safetensors",
247
+ "transformer.h.27.attn.c_attn.weight": "model-00001-of-00002.safetensors",
248
+ "transformer.h.27.attn.c_proj.bias": "model-00001-of-00002.safetensors",
249
+ "transformer.h.27.attn.c_proj.weight": "model-00001-of-00002.safetensors",
250
+ "transformer.h.27.ln_1.bias": "model-00001-of-00002.safetensors",
251
+ "transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
252
+ "transformer.h.27.ln_2.bias": "model-00001-of-00002.safetensors",
253
+ "transformer.h.27.ln_2.weight": "model-00001-of-00002.safetensors",
254
+ "transformer.h.27.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
255
+ "transformer.h.27.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
256
+ "transformer.h.27.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
257
+ "transformer.h.27.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
258
+ "transformer.h.28.attn.c_attn.bias": "model-00001-of-00002.safetensors",
259
+ "transformer.h.28.attn.c_attn.weight": "model-00001-of-00002.safetensors",
260
+ "transformer.h.28.attn.c_proj.bias": "model-00001-of-00002.safetensors",
261
+ "transformer.h.28.attn.c_proj.weight": "model-00001-of-00002.safetensors",
262
+ "transformer.h.28.ln_1.bias": "model-00001-of-00002.safetensors",
263
+ "transformer.h.28.ln_1.weight": "model-00001-of-00002.safetensors",
264
+ "transformer.h.28.ln_2.bias": "model-00001-of-00002.safetensors",
265
+ "transformer.h.28.ln_2.weight": "model-00001-of-00002.safetensors",
266
+ "transformer.h.28.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
267
+ "transformer.h.28.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
268
+ "transformer.h.28.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
269
+ "transformer.h.28.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
270
+ "transformer.h.29.attn.c_attn.bias": "model-00001-of-00002.safetensors",
271
+ "transformer.h.29.attn.c_attn.weight": "model-00001-of-00002.safetensors",
272
+ "transformer.h.29.attn.c_proj.bias": "model-00001-of-00002.safetensors",
273
+ "transformer.h.29.attn.c_proj.weight": "model-00001-of-00002.safetensors",
274
+ "transformer.h.29.ln_1.bias": "model-00001-of-00002.safetensors",
275
+ "transformer.h.29.ln_1.weight": "model-00001-of-00002.safetensors",
276
+ "transformer.h.29.ln_2.bias": "model-00001-of-00002.safetensors",
277
+ "transformer.h.29.ln_2.weight": "model-00001-of-00002.safetensors",
278
+ "transformer.h.29.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
279
+ "transformer.h.29.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
280
+ "transformer.h.29.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
281
+ "transformer.h.29.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
282
+ "transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
283
+ "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
284
+ "transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
285
+ "transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
286
+ "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
287
+ "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
288
+ "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
289
+ "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
290
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
291
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
292
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
293
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
294
+ "transformer.h.30.attn.c_attn.bias": "model-00001-of-00002.safetensors",
295
+ "transformer.h.30.attn.c_attn.weight": "model-00001-of-00002.safetensors",
296
+ "transformer.h.30.attn.c_proj.bias": "model-00001-of-00002.safetensors",
297
+ "transformer.h.30.attn.c_proj.weight": "model-00001-of-00002.safetensors",
298
+ "transformer.h.30.ln_1.bias": "model-00001-of-00002.safetensors",
299
+ "transformer.h.30.ln_1.weight": "model-00001-of-00002.safetensors",
300
+ "transformer.h.30.ln_2.bias": "model-00001-of-00002.safetensors",
301
+ "transformer.h.30.ln_2.weight": "model-00001-of-00002.safetensors",
302
+ "transformer.h.30.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
303
+ "transformer.h.30.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
304
+ "transformer.h.30.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
305
+ "transformer.h.30.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
306
+ "transformer.h.31.attn.c_attn.bias": "model-00001-of-00002.safetensors",
307
+ "transformer.h.31.attn.c_attn.weight": "model-00001-of-00002.safetensors",
308
+ "transformer.h.31.attn.c_proj.bias": "model-00001-of-00002.safetensors",
309
+ "transformer.h.31.attn.c_proj.weight": "model-00001-of-00002.safetensors",
310
+ "transformer.h.31.ln_1.bias": "model-00001-of-00002.safetensors",
311
+ "transformer.h.31.ln_1.weight": "model-00001-of-00002.safetensors",
312
+ "transformer.h.31.ln_2.bias": "model-00001-of-00002.safetensors",
313
+ "transformer.h.31.ln_2.weight": "model-00001-of-00002.safetensors",
314
+ "transformer.h.31.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
315
+ "transformer.h.31.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
316
+ "transformer.h.31.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
317
+ "transformer.h.31.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
318
+ "transformer.h.32.attn.c_attn.bias": "model-00001-of-00002.safetensors",
319
+ "transformer.h.32.attn.c_attn.weight": "model-00001-of-00002.safetensors",
320
+ "transformer.h.32.attn.c_proj.bias": "model-00001-of-00002.safetensors",
321
+ "transformer.h.32.attn.c_proj.weight": "model-00001-of-00002.safetensors",
322
+ "transformer.h.32.ln_1.bias": "model-00001-of-00002.safetensors",
323
+ "transformer.h.32.ln_1.weight": "model-00001-of-00002.safetensors",
324
+ "transformer.h.32.ln_2.bias": "model-00001-of-00002.safetensors",
325
+ "transformer.h.32.ln_2.weight": "model-00001-of-00002.safetensors",
326
+ "transformer.h.32.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
327
+ "transformer.h.32.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
328
+ "transformer.h.32.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
329
+ "transformer.h.32.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
330
+ "transformer.h.33.attn.c_attn.bias": "model-00001-of-00002.safetensors",
331
+ "transformer.h.33.attn.c_attn.weight": "model-00001-of-00002.safetensors",
332
+ "transformer.h.33.attn.c_proj.bias": "model-00001-of-00002.safetensors",
333
+ "transformer.h.33.attn.c_proj.weight": "model-00001-of-00002.safetensors",
334
+ "transformer.h.33.ln_1.bias": "model-00001-of-00002.safetensors",
335
+ "transformer.h.33.ln_1.weight": "model-00001-of-00002.safetensors",
336
+ "transformer.h.33.ln_2.bias": "model-00001-of-00002.safetensors",
337
+ "transformer.h.33.ln_2.weight": "model-00001-of-00002.safetensors",
338
+ "transformer.h.33.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
339
+ "transformer.h.33.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
340
+ "transformer.h.33.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
341
+ "transformer.h.33.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
342
+ "transformer.h.34.attn.c_attn.bias": "model-00001-of-00002.safetensors",
343
+ "transformer.h.34.attn.c_attn.weight": "model-00001-of-00002.safetensors",
344
+ "transformer.h.34.attn.c_proj.bias": "model-00001-of-00002.safetensors",
345
+ "transformer.h.34.attn.c_proj.weight": "model-00001-of-00002.safetensors",
346
+ "transformer.h.34.ln_1.bias": "model-00001-of-00002.safetensors",
347
+ "transformer.h.34.ln_1.weight": "model-00001-of-00002.safetensors",
348
+ "transformer.h.34.ln_2.bias": "model-00001-of-00002.safetensors",
349
+ "transformer.h.34.ln_2.weight": "model-00001-of-00002.safetensors",
350
+ "transformer.h.34.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
351
+ "transformer.h.34.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
352
+ "transformer.h.34.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
353
+ "transformer.h.34.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
354
+ "transformer.h.35.attn.c_attn.bias": "model-00001-of-00002.safetensors",
355
+ "transformer.h.35.attn.c_attn.weight": "model-00001-of-00002.safetensors",
356
+ "transformer.h.35.attn.c_proj.bias": "model-00001-of-00002.safetensors",
357
+ "transformer.h.35.attn.c_proj.weight": "model-00001-of-00002.safetensors",
358
+ "transformer.h.35.ln_1.bias": "model-00001-of-00002.safetensors",
359
+ "transformer.h.35.ln_1.weight": "model-00001-of-00002.safetensors",
360
+ "transformer.h.35.ln_2.bias": "model-00001-of-00002.safetensors",
361
+ "transformer.h.35.ln_2.weight": "model-00001-of-00002.safetensors",
362
+ "transformer.h.35.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
363
+ "transformer.h.35.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
364
+ "transformer.h.35.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
365
+ "transformer.h.35.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
366
+ "transformer.h.36.attn.c_attn.bias": "model-00001-of-00002.safetensors",
367
+ "transformer.h.36.attn.c_attn.weight": "model-00001-of-00002.safetensors",
368
+ "transformer.h.36.attn.c_proj.bias": "model-00001-of-00002.safetensors",
369
+ "transformer.h.36.attn.c_proj.weight": "model-00001-of-00002.safetensors",
370
+ "transformer.h.36.ln_1.bias": "model-00001-of-00002.safetensors",
371
+ "transformer.h.36.ln_1.weight": "model-00001-of-00002.safetensors",
372
+ "transformer.h.36.ln_2.bias": "model-00001-of-00002.safetensors",
373
+ "transformer.h.36.ln_2.weight": "model-00001-of-00002.safetensors",
374
+ "transformer.h.36.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
375
+ "transformer.h.36.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
376
+ "transformer.h.36.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
377
+ "transformer.h.36.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
378
+ "transformer.h.37.attn.c_attn.bias": "model-00001-of-00002.safetensors",
379
+ "transformer.h.37.attn.c_attn.weight": "model-00001-of-00002.safetensors",
380
+ "transformer.h.37.attn.c_proj.bias": "model-00001-of-00002.safetensors",
381
+ "transformer.h.37.attn.c_proj.weight": "model-00001-of-00002.safetensors",
382
+ "transformer.h.37.ln_1.bias": "model-00001-of-00002.safetensors",
383
+ "transformer.h.37.ln_1.weight": "model-00001-of-00002.safetensors",
384
+ "transformer.h.37.ln_2.bias": "model-00001-of-00002.safetensors",
385
+ "transformer.h.37.ln_2.weight": "model-00001-of-00002.safetensors",
386
+ "transformer.h.37.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
387
+ "transformer.h.37.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
388
+ "transformer.h.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
389
+ "transformer.h.37.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
390
+ "transformer.h.38.attn.c_attn.bias": "model-00002-of-00002.safetensors",
391
+ "transformer.h.38.attn.c_attn.weight": "model-00002-of-00002.safetensors",
392
+ "transformer.h.38.attn.c_proj.bias": "model-00002-of-00002.safetensors",
393
+ "transformer.h.38.attn.c_proj.weight": "model-00002-of-00002.safetensors",
394
+ "transformer.h.38.ln_1.bias": "model-00002-of-00002.safetensors",
395
+ "transformer.h.38.ln_1.weight": "model-00002-of-00002.safetensors",
396
+ "transformer.h.38.ln_2.bias": "model-00002-of-00002.safetensors",
397
+ "transformer.h.38.ln_2.weight": "model-00002-of-00002.safetensors",
398
+ "transformer.h.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
399
+ "transformer.h.38.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
400
+ "transformer.h.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
401
+ "transformer.h.38.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
402
+ "transformer.h.39.attn.c_attn.bias": "model-00002-of-00002.safetensors",
403
+ "transformer.h.39.attn.c_attn.weight": "model-00002-of-00002.safetensors",
404
+ "transformer.h.39.attn.c_proj.bias": "model-00002-of-00002.safetensors",
405
+ "transformer.h.39.attn.c_proj.weight": "model-00002-of-00002.safetensors",
406
+ "transformer.h.39.ln_1.bias": "model-00002-of-00002.safetensors",
407
+ "transformer.h.39.ln_1.weight": "model-00002-of-00002.safetensors",
408
+ "transformer.h.39.ln_2.bias": "model-00002-of-00002.safetensors",
409
+ "transformer.h.39.ln_2.weight": "model-00002-of-00002.safetensors",
410
+ "transformer.h.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
411
+ "transformer.h.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
412
+ "transformer.h.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
413
+ "transformer.h.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
414
+ "transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
415
+ "transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
416
+ "transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
417
+ "transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
418
+ "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
419
+ "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
420
+ "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
421
+ "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
422
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
423
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
424
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
425
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
426
+ "transformer.h.40.attn.c_attn.bias": "model-00002-of-00002.safetensors",
427
+ "transformer.h.40.attn.c_attn.weight": "model-00002-of-00002.safetensors",
428
+ "transformer.h.40.attn.c_proj.bias": "model-00002-of-00002.safetensors",
429
+ "transformer.h.40.attn.c_proj.weight": "model-00002-of-00002.safetensors",
430
+ "transformer.h.40.ln_1.bias": "model-00002-of-00002.safetensors",
431
+ "transformer.h.40.ln_1.weight": "model-00002-of-00002.safetensors",
432
+ "transformer.h.40.ln_2.bias": "model-00002-of-00002.safetensors",
433
+ "transformer.h.40.ln_2.weight": "model-00002-of-00002.safetensors",
434
+ "transformer.h.40.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
435
+ "transformer.h.40.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
436
+ "transformer.h.40.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
437
+ "transformer.h.40.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
438
+ "transformer.h.41.attn.c_attn.bias": "model-00002-of-00002.safetensors",
439
+ "transformer.h.41.attn.c_attn.weight": "model-00002-of-00002.safetensors",
440
+ "transformer.h.41.attn.c_proj.bias": "model-00002-of-00002.safetensors",
441
+ "transformer.h.41.attn.c_proj.weight": "model-00002-of-00002.safetensors",
442
+ "transformer.h.41.ln_1.bias": "model-00002-of-00002.safetensors",
443
+ "transformer.h.41.ln_1.weight": "model-00002-of-00002.safetensors",
444
+ "transformer.h.41.ln_2.bias": "model-00002-of-00002.safetensors",
445
+ "transformer.h.41.ln_2.weight": "model-00002-of-00002.safetensors",
446
+ "transformer.h.41.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
447
+ "transformer.h.41.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
448
+ "transformer.h.41.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
449
+ "transformer.h.41.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
450
+ "transformer.h.42.attn.c_attn.bias": "model-00002-of-00002.safetensors",
451
+ "transformer.h.42.attn.c_attn.weight": "model-00002-of-00002.safetensors",
452
+ "transformer.h.42.attn.c_proj.bias": "model-00002-of-00002.safetensors",
453
+ "transformer.h.42.attn.c_proj.weight": "model-00002-of-00002.safetensors",
454
+ "transformer.h.42.ln_1.bias": "model-00002-of-00002.safetensors",
455
+ "transformer.h.42.ln_1.weight": "model-00002-of-00002.safetensors",
456
+ "transformer.h.42.ln_2.bias": "model-00002-of-00002.safetensors",
457
+ "transformer.h.42.ln_2.weight": "model-00002-of-00002.safetensors",
458
+ "transformer.h.42.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
459
+ "transformer.h.42.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
460
+ "transformer.h.42.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
461
+ "transformer.h.42.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
462
+ "transformer.h.43.attn.c_attn.bias": "model-00002-of-00002.safetensors",
463
+ "transformer.h.43.attn.c_attn.weight": "model-00002-of-00002.safetensors",
464
+ "transformer.h.43.attn.c_proj.bias": "model-00002-of-00002.safetensors",
465
+ "transformer.h.43.attn.c_proj.weight": "model-00002-of-00002.safetensors",
466
+ "transformer.h.43.ln_1.bias": "model-00002-of-00002.safetensors",
467
+ "transformer.h.43.ln_1.weight": "model-00002-of-00002.safetensors",
468
+ "transformer.h.43.ln_2.bias": "model-00002-of-00002.safetensors",
469
+ "transformer.h.43.ln_2.weight": "model-00002-of-00002.safetensors",
470
+ "transformer.h.43.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
471
+ "transformer.h.43.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
472
+ "transformer.h.43.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
473
+ "transformer.h.43.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
474
+ "transformer.h.44.attn.c_attn.bias": "model-00002-of-00002.safetensors",
475
+ "transformer.h.44.attn.c_attn.weight": "model-00002-of-00002.safetensors",
476
+ "transformer.h.44.attn.c_proj.bias": "model-00002-of-00002.safetensors",
477
+ "transformer.h.44.attn.c_proj.weight": "model-00002-of-00002.safetensors",
478
+ "transformer.h.44.ln_1.bias": "model-00002-of-00002.safetensors",
479
+ "transformer.h.44.ln_1.weight": "model-00002-of-00002.safetensors",
480
+ "transformer.h.44.ln_2.bias": "model-00002-of-00002.safetensors",
481
+ "transformer.h.44.ln_2.weight": "model-00002-of-00002.safetensors",
482
+ "transformer.h.44.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
483
+ "transformer.h.44.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
484
+ "transformer.h.44.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
485
+ "transformer.h.44.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
486
+ "transformer.h.45.attn.c_attn.bias": "model-00002-of-00002.safetensors",
487
+ "transformer.h.45.attn.c_attn.weight": "model-00002-of-00002.safetensors",
488
+ "transformer.h.45.attn.c_proj.bias": "model-00002-of-00002.safetensors",
489
+ "transformer.h.45.attn.c_proj.weight": "model-00002-of-00002.safetensors",
490
+ "transformer.h.45.ln_1.bias": "model-00002-of-00002.safetensors",
491
+ "transformer.h.45.ln_1.weight": "model-00002-of-00002.safetensors",
492
+ "transformer.h.45.ln_2.bias": "model-00002-of-00002.safetensors",
493
+ "transformer.h.45.ln_2.weight": "model-00002-of-00002.safetensors",
494
+ "transformer.h.45.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
495
+ "transformer.h.45.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
496
+ "transformer.h.45.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
497
+ "transformer.h.45.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
498
+ "transformer.h.46.attn.c_attn.bias": "model-00002-of-00002.safetensors",
499
+ "transformer.h.46.attn.c_attn.weight": "model-00002-of-00002.safetensors",
500
+ "transformer.h.46.attn.c_proj.bias": "model-00002-of-00002.safetensors",
501
+ "transformer.h.46.attn.c_proj.weight": "model-00002-of-00002.safetensors",
502
+ "transformer.h.46.ln_1.bias": "model-00002-of-00002.safetensors",
503
+ "transformer.h.46.ln_1.weight": "model-00002-of-00002.safetensors",
504
+ "transformer.h.46.ln_2.bias": "model-00002-of-00002.safetensors",
505
+ "transformer.h.46.ln_2.weight": "model-00002-of-00002.safetensors",
506
+ "transformer.h.46.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
507
+ "transformer.h.46.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
508
+ "transformer.h.46.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
509
+ "transformer.h.46.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
510
+ "transformer.h.47.attn.c_attn.bias": "model-00002-of-00002.safetensors",
511
+ "transformer.h.47.attn.c_attn.weight": "model-00002-of-00002.safetensors",
512
+ "transformer.h.47.attn.c_proj.bias": "model-00002-of-00002.safetensors",
513
+ "transformer.h.47.attn.c_proj.weight": "model-00002-of-00002.safetensors",
514
+ "transformer.h.47.ln_1.bias": "model-00002-of-00002.safetensors",
515
+ "transformer.h.47.ln_1.weight": "model-00002-of-00002.safetensors",
516
+ "transformer.h.47.ln_2.bias": "model-00002-of-00002.safetensors",
517
+ "transformer.h.47.ln_2.weight": "model-00002-of-00002.safetensors",
518
+ "transformer.h.47.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
519
+ "transformer.h.47.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
520
+ "transformer.h.47.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
521
+ "transformer.h.47.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
522
+ "transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
523
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
524
+ "transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
525
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
526
+ "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
527
+ "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
528
+ "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
529
+ "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
530
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
531
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
532
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
533
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
534
+ "transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
535
+ "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
536
+ "transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
537
+ "transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
538
+ "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
539
+ "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
540
+ "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
541
+ "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
542
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
543
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
544
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
545
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
546
+ "transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
547
+ "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
548
+ "transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
549
+ "transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
550
+ "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
551
+ "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
552
+ "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
553
+ "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
554
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
555
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
556
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
557
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
558
+ "transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
559
+ "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
560
+ "transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
561
+ "transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
562
+ "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
563
+ "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
564
+ "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
565
+ "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
566
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
567
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
568
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
569
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
570
+ "transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
571
+ "transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
572
+ "transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
573
+ "transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
574
+ "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
575
+ "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
576
+ "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
577
+ "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
578
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
579
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
580
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
581
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
582
+ "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
583
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
584
+ "transformer.wpe.weight": "model-00001-of-00002.safetensors",
585
+ "transformer.wte.weight": "model-00001-of-00002.safetensors"
586
+ }
587
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8a431687d319e9cdb6967a40e088c2b59adb1a5978bf2fb82bd0ff093d2a6e
3
+ size 12461385005
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:946c419c7ab632e079cf0167240359d4f10c27dc3027da6abd5c54884347427c
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a111f30af158c1091b2d84caeac3f481aef09c2d7e1174ba38278f4ee0fbb43c
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "tokenizer_class": "GPT2Tokenizer",
18
+ "unk_token": "<|endoftext|>"
19
+ }
trainer_state.json ADDED
@@ -0,0 +1,285 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.3235294117647059,
5
+ "eval_steps": 500,
6
+ "global_step": 22000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 4.9632352941176476e-05,
14
+ "loss": 6.7506,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 4.9264705882352944e-05,
20
+ "loss": 6.0294,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 4.889705882352941e-05,
26
+ "loss": 5.6952,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 4.8529411764705885e-05,
32
+ "loss": 5.3818,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.04,
37
+ "learning_rate": 4.816176470588236e-05,
38
+ "loss": 5.138,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 4.7794117647058826e-05,
44
+ "loss": 4.946,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.05,
49
+ "learning_rate": 4.742647058823529e-05,
50
+ "loss": 4.7386,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.06,
55
+ "learning_rate": 4.705882352941177e-05,
56
+ "loss": 4.5023,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.07,
61
+ "learning_rate": 4.669117647058824e-05,
62
+ "loss": 4.2927,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.07,
67
+ "learning_rate": 4.632352941176471e-05,
68
+ "loss": 4.1612,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.08,
73
+ "learning_rate": 4.5955882352941176e-05,
74
+ "loss": 4.0391,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.09,
79
+ "learning_rate": 4.558823529411765e-05,
80
+ "loss": 4.0038,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.1,
85
+ "learning_rate": 4.522058823529412e-05,
86
+ "loss": 3.9057,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.1,
91
+ "learning_rate": 4.485294117647059e-05,
92
+ "loss": 3.8217,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.11,
97
+ "learning_rate": 4.448529411764706e-05,
98
+ "loss": 3.7518,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.12,
103
+ "learning_rate": 4.411764705882353e-05,
104
+ "loss": 3.6375,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.12,
109
+ "learning_rate": 4.375e-05,
110
+ "loss": 3.568,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.13,
115
+ "learning_rate": 4.3382352941176474e-05,
116
+ "loss": 3.4688,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.14,
121
+ "learning_rate": 4.301470588235295e-05,
122
+ "loss": 3.4439,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.15,
127
+ "learning_rate": 4.2647058823529415e-05,
128
+ "loss": 3.4011,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.15,
133
+ "learning_rate": 4.227941176470588e-05,
134
+ "loss": 3.366,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.16,
139
+ "learning_rate": 4.1911764705882356e-05,
140
+ "loss": 3.359,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.17,
145
+ "learning_rate": 4.154411764705883e-05,
146
+ "loss": 3.3448,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 0.18,
151
+ "learning_rate": 4.11764705882353e-05,
152
+ "loss": 3.3091,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 0.18,
157
+ "learning_rate": 4.0808823529411765e-05,
158
+ "loss": 3.2667,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 0.19,
163
+ "learning_rate": 4.044117647058824e-05,
164
+ "loss": 3.2444,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 0.2,
169
+ "learning_rate": 4.007352941176471e-05,
170
+ "loss": 3.2749,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 0.21,
175
+ "learning_rate": 3.970588235294117e-05,
176
+ "loss": 3.2861,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 0.21,
181
+ "learning_rate": 3.933823529411765e-05,
182
+ "loss": 3.3115,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 0.22,
187
+ "learning_rate": 3.897058823529412e-05,
188
+ "loss": 3.2376,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 0.23,
193
+ "learning_rate": 3.8602941176470595e-05,
194
+ "loss": 3.2652,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 0.24,
199
+ "learning_rate": 3.8235294117647055e-05,
200
+ "loss": 3.1289,
201
+ "step": 16000
202
+ },
203
+ {
204
+ "epoch": 0.24,
205
+ "learning_rate": 3.786764705882353e-05,
206
+ "loss": 3.1547,
207
+ "step": 16500
208
+ },
209
+ {
210
+ "epoch": 0.25,
211
+ "learning_rate": 3.7500000000000003e-05,
212
+ "loss": 3.1133,
213
+ "step": 17000
214
+ },
215
+ {
216
+ "epoch": 0.26,
217
+ "learning_rate": 3.713235294117647e-05,
218
+ "loss": 3.0532,
219
+ "step": 17500
220
+ },
221
+ {
222
+ "epoch": 0.26,
223
+ "learning_rate": 3.6764705882352945e-05,
224
+ "loss": 3.0215,
225
+ "step": 18000
226
+ },
227
+ {
228
+ "epoch": 0.27,
229
+ "learning_rate": 3.639705882352941e-05,
230
+ "loss": 3.0597,
231
+ "step": 18500
232
+ },
233
+ {
234
+ "epoch": 0.28,
235
+ "learning_rate": 3.6029411764705886e-05,
236
+ "loss": 3.0665,
237
+ "step": 19000
238
+ },
239
+ {
240
+ "epoch": 0.29,
241
+ "learning_rate": 3.566176470588235e-05,
242
+ "loss": 3.0695,
243
+ "step": 19500
244
+ },
245
+ {
246
+ "epoch": 0.29,
247
+ "learning_rate": 3.529411764705883e-05,
248
+ "loss": 3.0227,
249
+ "step": 20000
250
+ },
251
+ {
252
+ "epoch": 0.3,
253
+ "learning_rate": 3.4926470588235294e-05,
254
+ "loss": 3.0734,
255
+ "step": 20500
256
+ },
257
+ {
258
+ "epoch": 0.31,
259
+ "learning_rate": 3.455882352941177e-05,
260
+ "loss": 3.0519,
261
+ "step": 21000
262
+ },
263
+ {
264
+ "epoch": 0.32,
265
+ "learning_rate": 3.4191176470588236e-05,
266
+ "loss": 3.0109,
267
+ "step": 21500
268
+ },
269
+ {
270
+ "epoch": 0.32,
271
+ "learning_rate": 3.382352941176471e-05,
272
+ "loss": 2.9793,
273
+ "step": 22000
274
+ }
275
+ ],
276
+ "logging_steps": 500,
277
+ "max_steps": 68000,
278
+ "num_input_tokens_seen": 0,
279
+ "num_train_epochs": 9223372036854775807,
280
+ "save_steps": 2000,
281
+ "total_flos": 1.5955896827904e+18,
282
+ "train_batch_size": 8,
283
+ "trial_name": null,
284
+ "trial_params": null
285
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54196a5b5424b83d6f1a19148fdc7dc0653b297698b9830cd193c6a85358145a
3
+ size 4283
vocab.json ADDED
The diff for this file is too large to render. See raw diff