Lakshmi Nair commited on
Commit
44c8d77
1 Parent(s): bd000a9

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_accuracy": 0.5033006287486574,
3
+ "eval_loss": 2.3982996940612793,
4
+ "eval_runtime": 100.7746,
5
+ "eval_samples": 243,
6
+ "eval_samples_per_second": 2.411,
7
+ "eval_steps_per_second": 1.211,
8
+ "perplexity": 11.004449533574345
9
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/checkpoints/backup/opt-2.7B-FP32",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 10240,
16
+ "hidden_size": 2560,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 32,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.27.4",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 2560
31
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_accuracy": 0.5033006287486574,
3
+ "eval_loss": 2.3982996940612793,
4
+ "eval_runtime": 100.7746,
5
+ "eval_samples": 243,
6
+ "eval_samples_per_second": 2.411,
7
+ "eval_steps_per_second": 1.211,
8
+ "perplexity": 11.004449533574345
9
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.27.4"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8550d737dc026fc460c1a2d60bd67e76dcc2bbf5fe7572f4b7478a1d13bc5b
3
+ size 9977150403
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321a9887b7e2ac84b12e7c5ad5b6617c9f5abccd9087f2f5335f9b97ed4959e8
3
+ size 1144208609
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11121172480
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.decoder.embed_positions.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.decoder.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
10
+ "model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00002.bin",
12
+ "model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00002.bin",
14
+ "model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
16
+ "model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
18
+ "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
20
+ "model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
22
+ "model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
24
+ "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
26
+ "model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00002.bin",
28
+ "model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00002.bin",
30
+ "model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
32
+ "model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
34
+ "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
36
+ "model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
38
+ "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
40
+ "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
42
+ "model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.decoder.layers.10.fc1.bias": "pytorch_model-00001-of-00002.bin",
44
+ "model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.decoder.layers.10.fc2.bias": "pytorch_model-00001-of-00002.bin",
46
+ "model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
48
+ "model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
50
+ "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
52
+ "model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
54
+ "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
56
+ "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
58
+ "model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.decoder.layers.11.fc1.bias": "pytorch_model-00001-of-00002.bin",
60
+ "model.decoder.layers.11.fc1.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.decoder.layers.11.fc2.bias": "pytorch_model-00001-of-00002.bin",
62
+ "model.decoder.layers.11.fc2.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
64
+ "model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
66
+ "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
68
+ "model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
70
+ "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
72
+ "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
74
+ "model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.decoder.layers.12.fc1.bias": "pytorch_model-00001-of-00002.bin",
76
+ "model.decoder.layers.12.fc1.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.decoder.layers.12.fc2.bias": "pytorch_model-00001-of-00002.bin",
78
+ "model.decoder.layers.12.fc2.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
80
+ "model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
82
+ "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
84
+ "model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
86
+ "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
88
+ "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
90
+ "model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.decoder.layers.13.fc1.bias": "pytorch_model-00001-of-00002.bin",
92
+ "model.decoder.layers.13.fc1.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.decoder.layers.13.fc2.bias": "pytorch_model-00001-of-00002.bin",
94
+ "model.decoder.layers.13.fc2.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
96
+ "model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
98
+ "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
100
+ "model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
102
+ "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
104
+ "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
106
+ "model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.decoder.layers.14.fc1.bias": "pytorch_model-00001-of-00002.bin",
108
+ "model.decoder.layers.14.fc1.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.decoder.layers.14.fc2.bias": "pytorch_model-00001-of-00002.bin",
110
+ "model.decoder.layers.14.fc2.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
112
+ "model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
114
+ "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
116
+ "model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
118
+ "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
120
+ "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
122
+ "model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.decoder.layers.15.fc1.bias": "pytorch_model-00001-of-00002.bin",
124
+ "model.decoder.layers.15.fc1.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.decoder.layers.15.fc2.bias": "pytorch_model-00001-of-00002.bin",
126
+ "model.decoder.layers.15.fc2.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
128
+ "model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
130
+ "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
132
+ "model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
134
+ "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
136
+ "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
138
+ "model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.decoder.layers.16.fc1.bias": "pytorch_model-00001-of-00002.bin",
140
+ "model.decoder.layers.16.fc1.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.decoder.layers.16.fc2.bias": "pytorch_model-00001-of-00002.bin",
142
+ "model.decoder.layers.16.fc2.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
144
+ "model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
146
+ "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
148
+ "model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
150
+ "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
152
+ "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
154
+ "model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.decoder.layers.17.fc1.bias": "pytorch_model-00001-of-00002.bin",
156
+ "model.decoder.layers.17.fc1.weight": "pytorch_model-00001-of-00002.bin",
157
+ "model.decoder.layers.17.fc2.bias": "pytorch_model-00001-of-00002.bin",
158
+ "model.decoder.layers.17.fc2.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
160
+ "model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
162
+ "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
164
+ "model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
166
+ "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
168
+ "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
170
+ "model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.decoder.layers.18.fc1.bias": "pytorch_model-00001-of-00002.bin",
172
+ "model.decoder.layers.18.fc1.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.decoder.layers.18.fc2.bias": "pytorch_model-00001-of-00002.bin",
174
+ "model.decoder.layers.18.fc2.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
176
+ "model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
177
+ "model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
178
+ "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
179
+ "model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
180
+ "model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
181
+ "model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
182
+ "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
183
+ "model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
184
+ "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
185
+ "model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
186
+ "model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
187
+ "model.decoder.layers.19.fc1.bias": "pytorch_model-00001-of-00002.bin",
188
+ "model.decoder.layers.19.fc1.weight": "pytorch_model-00001-of-00002.bin",
189
+ "model.decoder.layers.19.fc2.bias": "pytorch_model-00001-of-00002.bin",
190
+ "model.decoder.layers.19.fc2.weight": "pytorch_model-00001-of-00002.bin",
191
+ "model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
192
+ "model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
193
+ "model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
194
+ "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
195
+ "model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
196
+ "model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
197
+ "model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
198
+ "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
200
+ "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
201
+ "model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
202
+ "model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
203
+ "model.decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00002.bin",
204
+ "model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00002.bin",
205
+ "model.decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00002.bin",
206
+ "model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00002.bin",
207
+ "model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
208
+ "model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
209
+ "model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
210
+ "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
211
+ "model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
212
+ "model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
213
+ "model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
214
+ "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
215
+ "model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
216
+ "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
218
+ "model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.decoder.layers.20.fc1.bias": "pytorch_model-00001-of-00002.bin",
220
+ "model.decoder.layers.20.fc1.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.decoder.layers.20.fc2.bias": "pytorch_model-00001-of-00002.bin",
222
+ "model.decoder.layers.20.fc2.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
224
+ "model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
225
+ "model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
226
+ "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
228
+ "model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
229
+ "model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
230
+ "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
232
+ "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
233
+ "model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
234
+ "model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
235
+ "model.decoder.layers.21.fc1.bias": "pytorch_model-00001-of-00002.bin",
236
+ "model.decoder.layers.21.fc1.weight": "pytorch_model-00001-of-00002.bin",
237
+ "model.decoder.layers.21.fc2.bias": "pytorch_model-00001-of-00002.bin",
238
+ "model.decoder.layers.21.fc2.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
240
+ "model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
242
+ "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
244
+ "model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
246
+ "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
248
+ "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
250
+ "model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
251
+ "model.decoder.layers.22.fc1.bias": "pytorch_model-00001-of-00002.bin",
252
+ "model.decoder.layers.22.fc1.weight": "pytorch_model-00001-of-00002.bin",
253
+ "model.decoder.layers.22.fc2.bias": "pytorch_model-00001-of-00002.bin",
254
+ "model.decoder.layers.22.fc2.weight": "pytorch_model-00001-of-00002.bin",
255
+ "model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
256
+ "model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
257
+ "model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
258
+ "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
260
+ "model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
261
+ "model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
262
+ "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
264
+ "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
265
+ "model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
266
+ "model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
267
+ "model.decoder.layers.23.fc1.bias": "pytorch_model-00001-of-00002.bin",
268
+ "model.decoder.layers.23.fc1.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.decoder.layers.23.fc2.bias": "pytorch_model-00001-of-00002.bin",
270
+ "model.decoder.layers.23.fc2.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
272
+ "model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
274
+ "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
276
+ "model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
278
+ "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
280
+ "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
282
+ "model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.decoder.layers.24.fc1.bias": "pytorch_model-00001-of-00002.bin",
284
+ "model.decoder.layers.24.fc1.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.decoder.layers.24.fc2.bias": "pytorch_model-00001-of-00002.bin",
286
+ "model.decoder.layers.24.fc2.weight": "pytorch_model-00001-of-00002.bin",
287
+ "model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
288
+ "model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
290
+ "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
292
+ "model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
294
+ "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
296
+ "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
297
+ "model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
298
+ "model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.decoder.layers.25.fc1.bias": "pytorch_model-00001-of-00002.bin",
300
+ "model.decoder.layers.25.fc1.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.decoder.layers.25.fc2.bias": "pytorch_model-00001-of-00002.bin",
302
+ "model.decoder.layers.25.fc2.weight": "pytorch_model-00001-of-00002.bin",
303
+ "model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
304
+ "model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
306
+ "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
307
+ "model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
308
+ "model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
309
+ "model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
310
+ "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
312
+ "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
314
+ "model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
315
+ "model.decoder.layers.26.fc1.bias": "pytorch_model-00001-of-00002.bin",
316
+ "model.decoder.layers.26.fc1.weight": "pytorch_model-00001-of-00002.bin",
317
+ "model.decoder.layers.26.fc2.bias": "pytorch_model-00001-of-00002.bin",
318
+ "model.decoder.layers.26.fc2.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
320
+ "model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
321
+ "model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
322
+ "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
323
+ "model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
324
+ "model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
326
+ "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
327
+ "model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
328
+ "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
329
+ "model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
330
+ "model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
331
+ "model.decoder.layers.27.fc1.bias": "pytorch_model-00001-of-00002.bin",
332
+ "model.decoder.layers.27.fc1.weight": "pytorch_model-00001-of-00002.bin",
333
+ "model.decoder.layers.27.fc2.bias": "pytorch_model-00001-of-00002.bin",
334
+ "model.decoder.layers.27.fc2.weight": "pytorch_model-00001-of-00002.bin",
335
+ "model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
336
+ "model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
337
+ "model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
338
+ "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
339
+ "model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
340
+ "model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
341
+ "model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
342
+ "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
344
+ "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
345
+ "model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
346
+ "model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
347
+ "model.decoder.layers.28.fc1.bias": "pytorch_model-00001-of-00002.bin",
348
+ "model.decoder.layers.28.fc1.weight": "pytorch_model-00001-of-00002.bin",
349
+ "model.decoder.layers.28.fc2.bias": "pytorch_model-00001-of-00002.bin",
350
+ "model.decoder.layers.28.fc2.weight": "pytorch_model-00001-of-00002.bin",
351
+ "model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
352
+ "model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
353
+ "model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
354
+ "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
355
+ "model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
356
+ "model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
357
+ "model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
358
+ "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
359
+ "model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
360
+ "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
361
+ "model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
362
+ "model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
363
+ "model.decoder.layers.29.fc1.bias": "pytorch_model-00001-of-00002.bin",
364
+ "model.decoder.layers.29.fc1.weight": "pytorch_model-00001-of-00002.bin",
365
+ "model.decoder.layers.29.fc2.bias": "pytorch_model-00001-of-00002.bin",
366
+ "model.decoder.layers.29.fc2.weight": "pytorch_model-00001-of-00002.bin",
367
+ "model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
368
+ "model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
369
+ "model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
370
+ "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
371
+ "model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
372
+ "model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
373
+ "model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
374
+ "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
375
+ "model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
376
+ "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
377
+ "model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
378
+ "model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
379
+ "model.decoder.layers.3.fc1.bias": "pytorch_model-00001-of-00002.bin",
380
+ "model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00002.bin",
381
+ "model.decoder.layers.3.fc2.bias": "pytorch_model-00001-of-00002.bin",
382
+ "model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00002.bin",
383
+ "model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
384
+ "model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
385
+ "model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
386
+ "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
387
+ "model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
388
+ "model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
389
+ "model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
390
+ "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
391
+ "model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
392
+ "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
393
+ "model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
394
+ "model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
395
+ "model.decoder.layers.30.fc1.bias": "pytorch_model-00002-of-00002.bin",
396
+ "model.decoder.layers.30.fc1.weight": "pytorch_model-00002-of-00002.bin",
397
+ "model.decoder.layers.30.fc2.bias": "pytorch_model-00002-of-00002.bin",
398
+ "model.decoder.layers.30.fc2.weight": "pytorch_model-00002-of-00002.bin",
399
+ "model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
400
+ "model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
401
+ "model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
402
+ "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
403
+ "model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
404
+ "model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
405
+ "model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
406
+ "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
407
+ "model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
408
+ "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
409
+ "model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
410
+ "model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
411
+ "model.decoder.layers.31.fc1.bias": "pytorch_model-00002-of-00002.bin",
412
+ "model.decoder.layers.31.fc1.weight": "pytorch_model-00002-of-00002.bin",
413
+ "model.decoder.layers.31.fc2.bias": "pytorch_model-00002-of-00002.bin",
414
+ "model.decoder.layers.31.fc2.weight": "pytorch_model-00002-of-00002.bin",
415
+ "model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
416
+ "model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
417
+ "model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
418
+ "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
419
+ "model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
420
+ "model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
421
+ "model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
422
+ "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
423
+ "model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
424
+ "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
425
+ "model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
426
+ "model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
427
+ "model.decoder.layers.4.fc1.bias": "pytorch_model-00001-of-00002.bin",
428
+ "model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00002.bin",
429
+ "model.decoder.layers.4.fc2.bias": "pytorch_model-00001-of-00002.bin",
430
+ "model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00002.bin",
431
+ "model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
432
+ "model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
433
+ "model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
434
+ "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
435
+ "model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
436
+ "model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
437
+ "model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
438
+ "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
439
+ "model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
440
+ "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
441
+ "model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
442
+ "model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
443
+ "model.decoder.layers.5.fc1.bias": "pytorch_model-00001-of-00002.bin",
444
+ "model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00002.bin",
445
+ "model.decoder.layers.5.fc2.bias": "pytorch_model-00001-of-00002.bin",
446
+ "model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00002.bin",
447
+ "model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
448
+ "model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
449
+ "model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
450
+ "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
451
+ "model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
452
+ "model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
453
+ "model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
454
+ "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
455
+ "model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
456
+ "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
457
+ "model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
458
+ "model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
459
+ "model.decoder.layers.6.fc1.bias": "pytorch_model-00001-of-00002.bin",
460
+ "model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00002.bin",
461
+ "model.decoder.layers.6.fc2.bias": "pytorch_model-00001-of-00002.bin",
462
+ "model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00002.bin",
463
+ "model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
464
+ "model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
465
+ "model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
466
+ "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
467
+ "model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
468
+ "model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
469
+ "model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
470
+ "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
471
+ "model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
472
+ "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
473
+ "model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
474
+ "model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
475
+ "model.decoder.layers.7.fc1.bias": "pytorch_model-00001-of-00002.bin",
476
+ "model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00002.bin",
477
+ "model.decoder.layers.7.fc2.bias": "pytorch_model-00001-of-00002.bin",
478
+ "model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00002.bin",
479
+ "model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
480
+ "model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
481
+ "model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
482
+ "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
483
+ "model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
484
+ "model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
485
+ "model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
486
+ "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
487
+ "model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
488
+ "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
489
+ "model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
490
+ "model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
491
+ "model.decoder.layers.8.fc1.bias": "pytorch_model-00001-of-00002.bin",
492
+ "model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00002.bin",
493
+ "model.decoder.layers.8.fc2.bias": "pytorch_model-00001-of-00002.bin",
494
+ "model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00002.bin",
495
+ "model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
496
+ "model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
497
+ "model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
498
+ "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
499
+ "model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
500
+ "model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
501
+ "model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
502
+ "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
503
+ "model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
504
+ "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
505
+ "model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
506
+ "model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
507
+ "model.decoder.layers.9.fc1.bias": "pytorch_model-00001-of-00002.bin",
508
+ "model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00002.bin",
509
+ "model.decoder.layers.9.fc2.bias": "pytorch_model-00001-of-00002.bin",
510
+ "model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00002.bin",
511
+ "model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
512
+ "model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
513
+ "model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
514
+ "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
515
+ "model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
516
+ "model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
517
+ "model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
518
+ "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
519
+ "model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
520
+ "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
521
+ "model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
522
+ "model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin"
523
+ }
524
+ }
runs/Apr13_12-43-32_nomster/events.out.tfevents.1681415144.nomster.87961.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53389baff8d63d0fe8286d4bcb8932e983326e3fa270bc12582f17b3520a623
3
+ size 346
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "</s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": {
23
+ "__type": "AddedToken",
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "special_tokens_map_file": null,
31
+ "tokenizer_class": "GPT2Tokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0212e4ffefdbac3eb038461a97f9ad06d3eb6ad4212ac204e70aa02bd02cbd
3
+ size 3579
vocab.json ADDED
The diff for this file is too large to render. See raw diff