PEFT
PyTorch
gpt_bigcode
code
ArmelR commited on
Commit
e636568
1 Parent(s): 7e664ad

adding files

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints-fft/checkpoint-200",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 6144,
20
+ "n_head": 48,
21
+ "n_inner": 24576,
22
+ "n_layer": 40,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "resid_pdrop": 0.1,
27
+ "scale_attention_softmax_in_fp32": true,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.33.0.dev0",
36
+ "use_cache": true,
37
+ "validate_runner_input": true,
38
+ "vocab_size": 49152
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.33.0.dev0"
6
+ }
pytorch_model-00001-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e070f27b346424b672e1cb31f9e9f67e04866956041190ddcbe205282f2416
3
+ size 9904379303
pytorch_model-00002-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bcf0980b165b1b82a65df90dc2d3b53b8f0505f57524140ca23e3bcb1698a92
3
+ size 9860464915
pytorch_model-00003-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8721ac8e8cae6ab40a1f8939bd76a7f564e78af88d4e0ce06b1c2d2c228d8e4d
3
+ size 9854246167
pytorch_model-00004-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2399dbb1fbd1e3de0395d7fe6b43dde4014c18141f83cbdd535b8febdbce00ed
3
+ size 9860464979
pytorch_model-00005-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cfb64bd63f7e69f7519b0ad0ff83a7b5a40ce28041b9b1daa67ecd2acb4db43
3
+ size 9854246167
pytorch_model-00006-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c64964b7682841c1a55b49c7a12ad208737f02059f1eaf88f75e2c8f06dcab
3
+ size 9860464979
pytorch_model-00007-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81eccee5bfc5fe15ede2267567ea6d44646757b800ecc901cea28aa859f35e4
3
+ size 2875719771
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,492 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 62069825536
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00007.bin",
7
+ "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
8
+ "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
9
+ "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
10
+ "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
11
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00007.bin",
12
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00007.bin",
13
+ "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00007.bin",
14
+ "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00007.bin",
15
+ "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
16
+ "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
17
+ "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
18
+ "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
19
+ "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
20
+ "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
21
+ "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
22
+ "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
23
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00007.bin",
24
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00007.bin",
25
+ "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00007.bin",
26
+ "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00007.bin",
27
+ "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
28
+ "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
29
+ "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
30
+ "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
31
+ "transformer.h.10.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
32
+ "transformer.h.10.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
33
+ "transformer.h.10.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
34
+ "transformer.h.10.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
35
+ "transformer.h.10.ln_1.bias": "pytorch_model-00002-of-00007.bin",
36
+ "transformer.h.10.ln_1.weight": "pytorch_model-00002-of-00007.bin",
37
+ "transformer.h.10.ln_2.bias": "pytorch_model-00002-of-00007.bin",
38
+ "transformer.h.10.ln_2.weight": "pytorch_model-00002-of-00007.bin",
39
+ "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
40
+ "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
41
+ "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
42
+ "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
43
+ "transformer.h.11.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
44
+ "transformer.h.11.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
45
+ "transformer.h.11.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
46
+ "transformer.h.11.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
47
+ "transformer.h.11.ln_1.bias": "pytorch_model-00002-of-00007.bin",
48
+ "transformer.h.11.ln_1.weight": "pytorch_model-00002-of-00007.bin",
49
+ "transformer.h.11.ln_2.bias": "pytorch_model-00002-of-00007.bin",
50
+ "transformer.h.11.ln_2.weight": "pytorch_model-00002-of-00007.bin",
51
+ "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
52
+ "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
53
+ "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
54
+ "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
55
+ "transformer.h.12.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
56
+ "transformer.h.12.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
57
+ "transformer.h.12.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
58
+ "transformer.h.12.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
59
+ "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00007.bin",
60
+ "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00007.bin",
61
+ "transformer.h.12.ln_2.bias": "pytorch_model-00003-of-00007.bin",
62
+ "transformer.h.12.ln_2.weight": "pytorch_model-00003-of-00007.bin",
63
+ "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
64
+ "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
65
+ "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
66
+ "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
67
+ "transformer.h.13.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
68
+ "transformer.h.13.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
69
+ "transformer.h.13.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
70
+ "transformer.h.13.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
71
+ "transformer.h.13.ln_1.bias": "pytorch_model-00003-of-00007.bin",
72
+ "transformer.h.13.ln_1.weight": "pytorch_model-00003-of-00007.bin",
73
+ "transformer.h.13.ln_2.bias": "pytorch_model-00003-of-00007.bin",
74
+ "transformer.h.13.ln_2.weight": "pytorch_model-00003-of-00007.bin",
75
+ "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
76
+ "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
77
+ "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
78
+ "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
79
+ "transformer.h.14.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
80
+ "transformer.h.14.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
81
+ "transformer.h.14.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
82
+ "transformer.h.14.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
83
+ "transformer.h.14.ln_1.bias": "pytorch_model-00003-of-00007.bin",
84
+ "transformer.h.14.ln_1.weight": "pytorch_model-00003-of-00007.bin",
85
+ "transformer.h.14.ln_2.bias": "pytorch_model-00003-of-00007.bin",
86
+ "transformer.h.14.ln_2.weight": "pytorch_model-00003-of-00007.bin",
87
+ "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
88
+ "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
89
+ "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
90
+ "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
91
+ "transformer.h.15.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
92
+ "transformer.h.15.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
93
+ "transformer.h.15.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
94
+ "transformer.h.15.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
95
+ "transformer.h.15.ln_1.bias": "pytorch_model-00003-of-00007.bin",
96
+ "transformer.h.15.ln_1.weight": "pytorch_model-00003-of-00007.bin",
97
+ "transformer.h.15.ln_2.bias": "pytorch_model-00003-of-00007.bin",
98
+ "transformer.h.15.ln_2.weight": "pytorch_model-00003-of-00007.bin",
99
+ "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
100
+ "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
101
+ "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
102
+ "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
103
+ "transformer.h.16.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
104
+ "transformer.h.16.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
105
+ "transformer.h.16.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
106
+ "transformer.h.16.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
107
+ "transformer.h.16.ln_1.bias": "pytorch_model-00003-of-00007.bin",
108
+ "transformer.h.16.ln_1.weight": "pytorch_model-00003-of-00007.bin",
109
+ "transformer.h.16.ln_2.bias": "pytorch_model-00003-of-00007.bin",
110
+ "transformer.h.16.ln_2.weight": "pytorch_model-00003-of-00007.bin",
111
+ "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
112
+ "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
113
+ "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
114
+ "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
115
+ "transformer.h.17.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
116
+ "transformer.h.17.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
117
+ "transformer.h.17.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
118
+ "transformer.h.17.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
119
+ "transformer.h.17.ln_1.bias": "pytorch_model-00003-of-00007.bin",
120
+ "transformer.h.17.ln_1.weight": "pytorch_model-00003-of-00007.bin",
121
+ "transformer.h.17.ln_2.bias": "pytorch_model-00003-of-00007.bin",
122
+ "transformer.h.17.ln_2.weight": "pytorch_model-00003-of-00007.bin",
123
+ "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
124
+ "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
125
+ "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
126
+ "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
127
+ "transformer.h.18.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
128
+ "transformer.h.18.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
129
+ "transformer.h.18.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
130
+ "transformer.h.18.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
131
+ "transformer.h.18.ln_1.bias": "pytorch_model-00003-of-00007.bin",
132
+ "transformer.h.18.ln_1.weight": "pytorch_model-00003-of-00007.bin",
133
+ "transformer.h.18.ln_2.bias": "pytorch_model-00003-of-00007.bin",
134
+ "transformer.h.18.ln_2.weight": "pytorch_model-00003-of-00007.bin",
135
+ "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
136
+ "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
137
+ "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
138
+ "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
139
+ "transformer.h.19.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
140
+ "transformer.h.19.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
141
+ "transformer.h.19.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
142
+ "transformer.h.19.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
143
+ "transformer.h.19.ln_1.bias": "pytorch_model-00004-of-00007.bin",
144
+ "transformer.h.19.ln_1.weight": "pytorch_model-00004-of-00007.bin",
145
+ "transformer.h.19.ln_2.bias": "pytorch_model-00004-of-00007.bin",
146
+ "transformer.h.19.ln_2.weight": "pytorch_model-00004-of-00007.bin",
147
+ "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
148
+ "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
149
+ "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
150
+ "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
151
+ "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
152
+ "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
153
+ "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
154
+ "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
155
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00007.bin",
156
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00007.bin",
157
+ "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00007.bin",
158
+ "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00007.bin",
159
+ "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
160
+ "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
161
+ "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
162
+ "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
163
+ "transformer.h.20.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
164
+ "transformer.h.20.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
165
+ "transformer.h.20.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
166
+ "transformer.h.20.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
167
+ "transformer.h.20.ln_1.bias": "pytorch_model-00004-of-00007.bin",
168
+ "transformer.h.20.ln_1.weight": "pytorch_model-00004-of-00007.bin",
169
+ "transformer.h.20.ln_2.bias": "pytorch_model-00004-of-00007.bin",
170
+ "transformer.h.20.ln_2.weight": "pytorch_model-00004-of-00007.bin",
171
+ "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
172
+ "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
173
+ "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
174
+ "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
175
+ "transformer.h.21.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
176
+ "transformer.h.21.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
177
+ "transformer.h.21.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
178
+ "transformer.h.21.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
179
+ "transformer.h.21.ln_1.bias": "pytorch_model-00004-of-00007.bin",
180
+ "transformer.h.21.ln_1.weight": "pytorch_model-00004-of-00007.bin",
181
+ "transformer.h.21.ln_2.bias": "pytorch_model-00004-of-00007.bin",
182
+ "transformer.h.21.ln_2.weight": "pytorch_model-00004-of-00007.bin",
183
+ "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
184
+ "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
185
+ "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
186
+ "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
187
+ "transformer.h.22.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
188
+ "transformer.h.22.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
189
+ "transformer.h.22.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
190
+ "transformer.h.22.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
191
+ "transformer.h.22.ln_1.bias": "pytorch_model-00004-of-00007.bin",
192
+ "transformer.h.22.ln_1.weight": "pytorch_model-00004-of-00007.bin",
193
+ "transformer.h.22.ln_2.bias": "pytorch_model-00004-of-00007.bin",
194
+ "transformer.h.22.ln_2.weight": "pytorch_model-00004-of-00007.bin",
195
+ "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
196
+ "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
197
+ "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
198
+ "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
199
+ "transformer.h.23.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
200
+ "transformer.h.23.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
201
+ "transformer.h.23.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
202
+ "transformer.h.23.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
203
+ "transformer.h.23.ln_1.bias": "pytorch_model-00004-of-00007.bin",
204
+ "transformer.h.23.ln_1.weight": "pytorch_model-00004-of-00007.bin",
205
+ "transformer.h.23.ln_2.bias": "pytorch_model-00004-of-00007.bin",
206
+ "transformer.h.23.ln_2.weight": "pytorch_model-00004-of-00007.bin",
207
+ "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
208
+ "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
209
+ "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
210
+ "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
211
+ "transformer.h.24.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
212
+ "transformer.h.24.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
213
+ "transformer.h.24.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
214
+ "transformer.h.24.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
215
+ "transformer.h.24.ln_1.bias": "pytorch_model-00004-of-00007.bin",
216
+ "transformer.h.24.ln_1.weight": "pytorch_model-00004-of-00007.bin",
217
+ "transformer.h.24.ln_2.bias": "pytorch_model-00004-of-00007.bin",
218
+ "transformer.h.24.ln_2.weight": "pytorch_model-00004-of-00007.bin",
219
+ "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
220
+ "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
221
+ "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
222
+ "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
223
+ "transformer.h.25.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
224
+ "transformer.h.25.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
225
+ "transformer.h.25.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
226
+ "transformer.h.25.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
227
+ "transformer.h.25.ln_1.bias": "pytorch_model-00004-of-00007.bin",
228
+ "transformer.h.25.ln_1.weight": "pytorch_model-00004-of-00007.bin",
229
+ "transformer.h.25.ln_2.bias": "pytorch_model-00005-of-00007.bin",
230
+ "transformer.h.25.ln_2.weight": "pytorch_model-00005-of-00007.bin",
231
+ "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
232
+ "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
233
+ "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
234
+ "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
235
+ "transformer.h.26.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
236
+ "transformer.h.26.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
237
+ "transformer.h.26.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
238
+ "transformer.h.26.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
239
+ "transformer.h.26.ln_1.bias": "pytorch_model-00005-of-00007.bin",
240
+ "transformer.h.26.ln_1.weight": "pytorch_model-00005-of-00007.bin",
241
+ "transformer.h.26.ln_2.bias": "pytorch_model-00005-of-00007.bin",
242
+ "transformer.h.26.ln_2.weight": "pytorch_model-00005-of-00007.bin",
243
+ "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
244
+ "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
245
+ "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
246
+ "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
247
+ "transformer.h.27.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
248
+ "transformer.h.27.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
249
+ "transformer.h.27.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
250
+ "transformer.h.27.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
251
+ "transformer.h.27.ln_1.bias": "pytorch_model-00005-of-00007.bin",
252
+ "transformer.h.27.ln_1.weight": "pytorch_model-00005-of-00007.bin",
253
+ "transformer.h.27.ln_2.bias": "pytorch_model-00005-of-00007.bin",
254
+ "transformer.h.27.ln_2.weight": "pytorch_model-00005-of-00007.bin",
255
+ "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
256
+ "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
257
+ "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
258
+ "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
259
+ "transformer.h.28.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
260
+ "transformer.h.28.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
261
+ "transformer.h.28.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
262
+ "transformer.h.28.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
263
+ "transformer.h.28.ln_1.bias": "pytorch_model-00005-of-00007.bin",
264
+ "transformer.h.28.ln_1.weight": "pytorch_model-00005-of-00007.bin",
265
+ "transformer.h.28.ln_2.bias": "pytorch_model-00005-of-00007.bin",
266
+ "transformer.h.28.ln_2.weight": "pytorch_model-00005-of-00007.bin",
267
+ "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
268
+ "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
269
+ "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
270
+ "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
271
+ "transformer.h.29.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
272
+ "transformer.h.29.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
273
+ "transformer.h.29.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
274
+ "transformer.h.29.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
275
+ "transformer.h.29.ln_1.bias": "pytorch_model-00005-of-00007.bin",
276
+ "transformer.h.29.ln_1.weight": "pytorch_model-00005-of-00007.bin",
277
+ "transformer.h.29.ln_2.bias": "pytorch_model-00005-of-00007.bin",
278
+ "transformer.h.29.ln_2.weight": "pytorch_model-00005-of-00007.bin",
279
+ "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
280
+ "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
281
+ "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
282
+ "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
283
+ "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
284
+ "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
285
+ "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
286
+ "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
287
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00007.bin",
288
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00007.bin",
289
+ "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00007.bin",
290
+ "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00007.bin",
291
+ "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
292
+ "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
293
+ "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
294
+ "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
295
+ "transformer.h.30.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
296
+ "transformer.h.30.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
297
+ "transformer.h.30.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
298
+ "transformer.h.30.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
299
+ "transformer.h.30.ln_1.bias": "pytorch_model-00005-of-00007.bin",
300
+ "transformer.h.30.ln_1.weight": "pytorch_model-00005-of-00007.bin",
301
+ "transformer.h.30.ln_2.bias": "pytorch_model-00005-of-00007.bin",
302
+ "transformer.h.30.ln_2.weight": "pytorch_model-00005-of-00007.bin",
303
+ "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
304
+ "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
305
+ "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
306
+ "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
307
+ "transformer.h.31.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
308
+ "transformer.h.31.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
309
+ "transformer.h.31.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
310
+ "transformer.h.31.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
311
+ "transformer.h.31.ln_1.bias": "pytorch_model-00005-of-00007.bin",
312
+ "transformer.h.31.ln_1.weight": "pytorch_model-00005-of-00007.bin",
313
+ "transformer.h.31.ln_2.bias": "pytorch_model-00005-of-00007.bin",
314
+ "transformer.h.31.ln_2.weight": "pytorch_model-00005-of-00007.bin",
315
+ "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
316
+ "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
317
+ "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
318
+ "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
319
+ "transformer.h.32.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
320
+ "transformer.h.32.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
321
+ "transformer.h.32.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
322
+ "transformer.h.32.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
323
+ "transformer.h.32.ln_1.bias": "pytorch_model-00006-of-00007.bin",
324
+ "transformer.h.32.ln_1.weight": "pytorch_model-00006-of-00007.bin",
325
+ "transformer.h.32.ln_2.bias": "pytorch_model-00006-of-00007.bin",
326
+ "transformer.h.32.ln_2.weight": "pytorch_model-00006-of-00007.bin",
327
+ "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
328
+ "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
329
+ "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
330
+ "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
331
+ "transformer.h.33.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
332
+ "transformer.h.33.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
333
+ "transformer.h.33.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
334
+ "transformer.h.33.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
335
+ "transformer.h.33.ln_1.bias": "pytorch_model-00006-of-00007.bin",
336
+ "transformer.h.33.ln_1.weight": "pytorch_model-00006-of-00007.bin",
337
+ "transformer.h.33.ln_2.bias": "pytorch_model-00006-of-00007.bin",
338
+ "transformer.h.33.ln_2.weight": "pytorch_model-00006-of-00007.bin",
339
+ "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
340
+ "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
341
+ "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
342
+ "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
343
+ "transformer.h.34.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
344
+ "transformer.h.34.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
345
+ "transformer.h.34.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
346
+ "transformer.h.34.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
347
+ "transformer.h.34.ln_1.bias": "pytorch_model-00006-of-00007.bin",
348
+ "transformer.h.34.ln_1.weight": "pytorch_model-00006-of-00007.bin",
349
+ "transformer.h.34.ln_2.bias": "pytorch_model-00006-of-00007.bin",
350
+ "transformer.h.34.ln_2.weight": "pytorch_model-00006-of-00007.bin",
351
+ "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
352
+ "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
353
+ "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
354
+ "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
355
+ "transformer.h.35.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
356
+ "transformer.h.35.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
357
+ "transformer.h.35.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
358
+ "transformer.h.35.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
359
+ "transformer.h.35.ln_1.bias": "pytorch_model-00006-of-00007.bin",
360
+ "transformer.h.35.ln_1.weight": "pytorch_model-00006-of-00007.bin",
361
+ "transformer.h.35.ln_2.bias": "pytorch_model-00006-of-00007.bin",
362
+ "transformer.h.35.ln_2.weight": "pytorch_model-00006-of-00007.bin",
363
+ "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
364
+ "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
365
+ "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
366
+ "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
367
+ "transformer.h.36.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
368
+ "transformer.h.36.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
369
+ "transformer.h.36.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
370
+ "transformer.h.36.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
371
+ "transformer.h.36.ln_1.bias": "pytorch_model-00006-of-00007.bin",
372
+ "transformer.h.36.ln_1.weight": "pytorch_model-00006-of-00007.bin",
373
+ "transformer.h.36.ln_2.bias": "pytorch_model-00006-of-00007.bin",
374
+ "transformer.h.36.ln_2.weight": "pytorch_model-00006-of-00007.bin",
375
+ "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
376
+ "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
377
+ "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
378
+ "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
379
+ "transformer.h.37.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
380
+ "transformer.h.37.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
381
+ "transformer.h.37.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
382
+ "transformer.h.37.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
383
+ "transformer.h.37.ln_1.bias": "pytorch_model-00006-of-00007.bin",
384
+ "transformer.h.37.ln_1.weight": "pytorch_model-00006-of-00007.bin",
385
+ "transformer.h.37.ln_2.bias": "pytorch_model-00006-of-00007.bin",
386
+ "transformer.h.37.ln_2.weight": "pytorch_model-00006-of-00007.bin",
387
+ "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
388
+ "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
389
+ "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
390
+ "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
391
+ "transformer.h.38.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
392
+ "transformer.h.38.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
393
+ "transformer.h.38.attn.c_proj.bias": "pytorch_model-00007-of-00007.bin",
394
+ "transformer.h.38.attn.c_proj.weight": "pytorch_model-00007-of-00007.bin",
395
+ "transformer.h.38.ln_1.bias": "pytorch_model-00006-of-00007.bin",
396
+ "transformer.h.38.ln_1.weight": "pytorch_model-00006-of-00007.bin",
397
+ "transformer.h.38.ln_2.bias": "pytorch_model-00007-of-00007.bin",
398
+ "transformer.h.38.ln_2.weight": "pytorch_model-00007-of-00007.bin",
399
+ "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00007-of-00007.bin",
400
+ "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00007-of-00007.bin",
401
+ "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00007-of-00007.bin",
402
+ "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00007-of-00007.bin",
403
+ "transformer.h.39.attn.c_attn.bias": "pytorch_model-00007-of-00007.bin",
404
+ "transformer.h.39.attn.c_attn.weight": "pytorch_model-00007-of-00007.bin",
405
+ "transformer.h.39.attn.c_proj.bias": "pytorch_model-00007-of-00007.bin",
406
+ "transformer.h.39.attn.c_proj.weight": "pytorch_model-00007-of-00007.bin",
407
+ "transformer.h.39.ln_1.bias": "pytorch_model-00007-of-00007.bin",
408
+ "transformer.h.39.ln_1.weight": "pytorch_model-00007-of-00007.bin",
409
+ "transformer.h.39.ln_2.bias": "pytorch_model-00007-of-00007.bin",
410
+ "transformer.h.39.ln_2.weight": "pytorch_model-00007-of-00007.bin",
411
+ "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00007-of-00007.bin",
412
+ "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00007-of-00007.bin",
413
+ "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00007-of-00007.bin",
414
+ "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00007-of-00007.bin",
415
+ "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
416
+ "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
417
+ "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
418
+ "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
419
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00007.bin",
420
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00007.bin",
421
+ "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00007.bin",
422
+ "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00007.bin",
423
+ "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
424
+ "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
425
+ "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
426
+ "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
427
+ "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
428
+ "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
429
+ "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
430
+ "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
431
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00007.bin",
432
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00007.bin",
433
+ "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00007.bin",
434
+ "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00007.bin",
435
+ "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
436
+ "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
437
+ "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
438
+ "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
439
+ "transformer.h.6.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
440
+ "transformer.h.6.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
441
+ "transformer.h.6.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
442
+ "transformer.h.6.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
443
+ "transformer.h.6.ln_1.bias": "pytorch_model-00002-of-00007.bin",
444
+ "transformer.h.6.ln_1.weight": "pytorch_model-00002-of-00007.bin",
445
+ "transformer.h.6.ln_2.bias": "pytorch_model-00002-of-00007.bin",
446
+ "transformer.h.6.ln_2.weight": "pytorch_model-00002-of-00007.bin",
447
+ "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
448
+ "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
449
+ "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
450
+ "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
451
+ "transformer.h.7.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
452
+ "transformer.h.7.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
453
+ "transformer.h.7.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
454
+ "transformer.h.7.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
455
+ "transformer.h.7.ln_1.bias": "pytorch_model-00002-of-00007.bin",
456
+ "transformer.h.7.ln_1.weight": "pytorch_model-00002-of-00007.bin",
457
+ "transformer.h.7.ln_2.bias": "pytorch_model-00002-of-00007.bin",
458
+ "transformer.h.7.ln_2.weight": "pytorch_model-00002-of-00007.bin",
459
+ "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
460
+ "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
461
+ "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
462
+ "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
463
+ "transformer.h.8.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
464
+ "transformer.h.8.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
465
+ "transformer.h.8.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
466
+ "transformer.h.8.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
467
+ "transformer.h.8.ln_1.bias": "pytorch_model-00002-of-00007.bin",
468
+ "transformer.h.8.ln_1.weight": "pytorch_model-00002-of-00007.bin",
469
+ "transformer.h.8.ln_2.bias": "pytorch_model-00002-of-00007.bin",
470
+ "transformer.h.8.ln_2.weight": "pytorch_model-00002-of-00007.bin",
471
+ "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
472
+ "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
473
+ "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
474
+ "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
475
+ "transformer.h.9.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
476
+ "transformer.h.9.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
477
+ "transformer.h.9.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
478
+ "transformer.h.9.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
479
+ "transformer.h.9.ln_1.bias": "pytorch_model-00002-of-00007.bin",
480
+ "transformer.h.9.ln_1.weight": "pytorch_model-00002-of-00007.bin",
481
+ "transformer.h.9.ln_2.bias": "pytorch_model-00002-of-00007.bin",
482
+ "transformer.h.9.ln_2.weight": "pytorch_model-00002-of-00007.bin",
483
+ "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
484
+ "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
485
+ "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
486
+ "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
487
+ "transformer.ln_f.bias": "pytorch_model-00007-of-00007.bin",
488
+ "transformer.ln_f.weight": "pytorch_model-00007-of-00007.bin",
489
+ "transformer.wpe.weight": "pytorch_model-00001-of-00007.bin",
490
+ "transformer.wte.weight": "pytorch_model-00001-of-00007.bin"
491
+ }
492
+ }
trainer_state.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 10,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 6.47685462377997e-07,
14
+ "loss": 1.1777,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 9.266284080291269e-07,
20
+ "loss": 1.1847,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.05,
25
+ "eval_loss": 1.1642409563064575,
26
+ "eval_runtime": 70.6255,
27
+ "eval_samples_per_second": 0.212,
28
+ "eval_steps_per_second": 0.028,
29
+ "step": 10
30
+ },
31
+ {
32
+ "epoch": 0.07,
33
+ "learning_rate": 1e-06,
34
+ "loss": 1.1025,
35
+ "step": 15
36
+ },
37
+ {
38
+ "epoch": 0.1,
39
+ "learning_rate": 1e-06,
40
+ "loss": 1.0968,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 0.1,
45
+ "eval_loss": 1.1332802772521973,
46
+ "eval_runtime": 70.733,
47
+ "eval_samples_per_second": 0.212,
48
+ "eval_steps_per_second": 0.028,
49
+ "step": 20
50
+ },
51
+ {
52
+ "epoch": 0.12,
53
+ "learning_rate": 1e-06,
54
+ "loss": 1.0927,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 0.15,
59
+ "learning_rate": 1e-06,
60
+ "loss": 1.1003,
61
+ "step": 30
62
+ },
63
+ {
64
+ "epoch": 0.15,
65
+ "eval_loss": 1.1125657558441162,
66
+ "eval_runtime": 70.756,
67
+ "eval_samples_per_second": 0.212,
68
+ "eval_steps_per_second": 0.028,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.17,
73
+ "learning_rate": 1e-06,
74
+ "loss": 1.0657,
75
+ "step": 35
76
+ },
77
+ {
78
+ "epoch": 0.2,
79
+ "learning_rate": 1e-06,
80
+ "loss": 1.0789,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.2,
85
+ "eval_loss": 1.0948463678359985,
86
+ "eval_runtime": 70.7686,
87
+ "eval_samples_per_second": 0.212,
88
+ "eval_steps_per_second": 0.028,
89
+ "step": 40
90
+ },
91
+ {
92
+ "epoch": 0.23,
93
+ "learning_rate": 1e-06,
94
+ "loss": 1.0963,
95
+ "step": 45
96
+ },
97
+ {
98
+ "epoch": 0.25,
99
+ "learning_rate": 1e-06,
100
+ "loss": 1.0648,
101
+ "step": 50
102
+ },
103
+ {
104
+ "epoch": 0.25,
105
+ "eval_loss": 1.087746262550354,
106
+ "eval_runtime": 70.9688,
107
+ "eval_samples_per_second": 0.211,
108
+ "eval_steps_per_second": 0.028,
109
+ "step": 50
110
+ },
111
+ {
112
+ "epoch": 0.28,
113
+ "learning_rate": 1e-06,
114
+ "loss": 1.0504,
115
+ "step": 55
116
+ },
117
+ {
118
+ "epoch": 0.3,
119
+ "learning_rate": 1e-06,
120
+ "loss": 1.0568,
121
+ "step": 60
122
+ },
123
+ {
124
+ "epoch": 0.3,
125
+ "eval_loss": 1.083579659461975,
126
+ "eval_runtime": 70.7858,
127
+ "eval_samples_per_second": 0.212,
128
+ "eval_steps_per_second": 0.028,
129
+ "step": 60
130
+ },
131
+ {
132
+ "epoch": 0.33,
133
+ "learning_rate": 1e-06,
134
+ "loss": 1.0472,
135
+ "step": 65
136
+ },
137
+ {
138
+ "epoch": 0.35,
139
+ "learning_rate": 1e-06,
140
+ "loss": 1.0587,
141
+ "step": 70
142
+ },
143
+ {
144
+ "epoch": 0.35,
145
+ "eval_loss": 1.080450177192688,
146
+ "eval_runtime": 70.8142,
147
+ "eval_samples_per_second": 0.212,
148
+ "eval_steps_per_second": 0.028,
149
+ "step": 70
150
+ },
151
+ {
152
+ "epoch": 0.38,
153
+ "learning_rate": 1e-06,
154
+ "loss": 1.0609,
155
+ "step": 75
156
+ },
157
+ {
158
+ "epoch": 0.4,
159
+ "learning_rate": 1e-06,
160
+ "loss": 1.021,
161
+ "step": 80
162
+ },
163
+ {
164
+ "epoch": 0.4,
165
+ "eval_loss": 1.0777862071990967,
166
+ "eval_runtime": 70.7864,
167
+ "eval_samples_per_second": 0.212,
168
+ "eval_steps_per_second": 0.028,
169
+ "step": 80
170
+ },
171
+ {
172
+ "epoch": 0.42,
173
+ "learning_rate": 1e-06,
174
+ "loss": 1.048,
175
+ "step": 85
176
+ },
177
+ {
178
+ "epoch": 0.45,
179
+ "learning_rate": 1e-06,
180
+ "loss": 1.0857,
181
+ "step": 90
182
+ },
183
+ {
184
+ "epoch": 0.45,
185
+ "eval_loss": 1.075345516204834,
186
+ "eval_runtime": 70.7802,
187
+ "eval_samples_per_second": 0.212,
188
+ "eval_steps_per_second": 0.028,
189
+ "step": 90
190
+ },
191
+ {
192
+ "epoch": 0.47,
193
+ "learning_rate": 1e-06,
194
+ "loss": 1.0077,
195
+ "step": 95
196
+ },
197
+ {
198
+ "epoch": 0.5,
199
+ "learning_rate": 1e-06,
200
+ "loss": 1.035,
201
+ "step": 100
202
+ },
203
+ {
204
+ "epoch": 0.5,
205
+ "eval_loss": 1.0735156536102295,
206
+ "eval_runtime": 70.9576,
207
+ "eval_samples_per_second": 0.211,
208
+ "eval_steps_per_second": 0.028,
209
+ "step": 100
210
+ },
211
+ {
212
+ "epoch": 0.53,
213
+ "learning_rate": 1e-06,
214
+ "loss": 1.0042,
215
+ "step": 105
216
+ },
217
+ {
218
+ "epoch": 0.55,
219
+ "learning_rate": 1e-06,
220
+ "loss": 1.0547,
221
+ "step": 110
222
+ },
223
+ {
224
+ "epoch": 0.55,
225
+ "eval_loss": 1.0722615718841553,
226
+ "eval_runtime": 70.7348,
227
+ "eval_samples_per_second": 0.212,
228
+ "eval_steps_per_second": 0.028,
229
+ "step": 110
230
+ },
231
+ {
232
+ "epoch": 0.57,
233
+ "learning_rate": 1e-06,
234
+ "loss": 1.0077,
235
+ "step": 115
236
+ },
237
+ {
238
+ "epoch": 0.6,
239
+ "learning_rate": 1e-06,
240
+ "loss": 1.0646,
241
+ "step": 120
242
+ },
243
+ {
244
+ "epoch": 0.6,
245
+ "eval_loss": 1.07070791721344,
246
+ "eval_runtime": 70.8054,
247
+ "eval_samples_per_second": 0.212,
248
+ "eval_steps_per_second": 0.028,
249
+ "step": 120
250
+ },
251
+ {
252
+ "epoch": 0.62,
253
+ "learning_rate": 1e-06,
254
+ "loss": 0.9997,
255
+ "step": 125
256
+ },
257
+ {
258
+ "epoch": 0.65,
259
+ "learning_rate": 1e-06,
260
+ "loss": 1.0396,
261
+ "step": 130
262
+ },
263
+ {
264
+ "epoch": 0.65,
265
+ "eval_loss": 1.0689507722854614,
266
+ "eval_runtime": 70.8505,
267
+ "eval_samples_per_second": 0.212,
268
+ "eval_steps_per_second": 0.028,
269
+ "step": 130
270
+ },
271
+ {
272
+ "epoch": 0.68,
273
+ "learning_rate": 1e-06,
274
+ "loss": 1.0387,
275
+ "step": 135
276
+ },
277
+ {
278
+ "epoch": 0.7,
279
+ "learning_rate": 1e-06,
280
+ "loss": 1.0197,
281
+ "step": 140
282
+ },
283
+ {
284
+ "epoch": 0.7,
285
+ "eval_loss": 1.0676530599594116,
286
+ "eval_runtime": 70.7124,
287
+ "eval_samples_per_second": 0.212,
288
+ "eval_steps_per_second": 0.028,
289
+ "step": 140
290
+ },
291
+ {
292
+ "epoch": 0.72,
293
+ "learning_rate": 1e-06,
294
+ "loss": 1.0274,
295
+ "step": 145
296
+ },
297
+ {
298
+ "epoch": 0.75,
299
+ "learning_rate": 1e-06,
300
+ "loss": 1.0331,
301
+ "step": 150
302
+ },
303
+ {
304
+ "epoch": 0.75,
305
+ "eval_loss": 1.066578984260559,
306
+ "eval_runtime": 70.851,
307
+ "eval_samples_per_second": 0.212,
308
+ "eval_steps_per_second": 0.028,
309
+ "step": 150
310
+ },
311
+ {
312
+ "epoch": 0.78,
313
+ "learning_rate": 1e-06,
314
+ "loss": 0.9796,
315
+ "step": 155
316
+ },
317
+ {
318
+ "epoch": 0.8,
319
+ "learning_rate": 1e-06,
320
+ "loss": 0.9945,
321
+ "step": 160
322
+ },
323
+ {
324
+ "epoch": 0.8,
325
+ "eval_loss": 1.0656859874725342,
326
+ "eval_runtime": 70.6043,
327
+ "eval_samples_per_second": 0.212,
328
+ "eval_steps_per_second": 0.028,
329
+ "step": 160
330
+ },
331
+ {
332
+ "epoch": 0.82,
333
+ "learning_rate": 1e-06,
334
+ "loss": 1.0549,
335
+ "step": 165
336
+ },
337
+ {
338
+ "epoch": 0.85,
339
+ "learning_rate": 1e-06,
340
+ "loss": 1.0134,
341
+ "step": 170
342
+ },
343
+ {
344
+ "epoch": 0.85,
345
+ "eval_loss": 1.0651814937591553,
346
+ "eval_runtime": 70.8302,
347
+ "eval_samples_per_second": 0.212,
348
+ "eval_steps_per_second": 0.028,
349
+ "step": 170
350
+ },
351
+ {
352
+ "epoch": 0.88,
353
+ "learning_rate": 1e-06,
354
+ "loss": 0.9615,
355
+ "step": 175
356
+ },
357
+ {
358
+ "epoch": 0.9,
359
+ "learning_rate": 1e-06,
360
+ "loss": 0.9737,
361
+ "step": 180
362
+ },
363
+ {
364
+ "epoch": 0.9,
365
+ "eval_loss": 1.0644478797912598,
366
+ "eval_runtime": 70.9689,
367
+ "eval_samples_per_second": 0.211,
368
+ "eval_steps_per_second": 0.028,
369
+ "step": 180
370
+ },
371
+ {
372
+ "epoch": 0.93,
373
+ "learning_rate": 1e-06,
374
+ "loss": 1.0104,
375
+ "step": 185
376
+ },
377
+ {
378
+ "epoch": 0.95,
379
+ "learning_rate": 1e-06,
380
+ "loss": 1.027,
381
+ "step": 190
382
+ },
383
+ {
384
+ "epoch": 0.95,
385
+ "eval_loss": 1.0634864568710327,
386
+ "eval_runtime": 71.0057,
387
+ "eval_samples_per_second": 0.211,
388
+ "eval_steps_per_second": 0.028,
389
+ "step": 190
390
+ },
391
+ {
392
+ "epoch": 0.97,
393
+ "learning_rate": 1e-06,
394
+ "loss": 1.028,
395
+ "step": 195
396
+ },
397
+ {
398
+ "epoch": 1.0,
399
+ "learning_rate": 1e-06,
400
+ "loss": 0.9929,
401
+ "step": 200
402
+ },
403
+ {
404
+ "epoch": 1.0,
405
+ "eval_loss": 1.062495470046997,
406
+ "eval_runtime": 71.1183,
407
+ "eval_samples_per_second": 0.211,
408
+ "eval_steps_per_second": 0.028,
409
+ "step": 200
410
+ }
411
+ ],
412
+ "logging_steps": 5,
413
+ "max_steps": 200,
414
+ "num_train_epochs": 9223372036854775807,
415
+ "save_steps": 10,
416
+ "total_flos": 214104589467648.0,
417
+ "trial_name": null,
418
+ "trial_params": null
419
+ }