chavinlo commited on
Commit
7c42067
1 Parent(s): f2b738d

Training in progress, step 1000

Browse files
checkpoint-1000/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/ubuntu/stanford_alpaca/alpaca-cleaned",
3
+ "architectures": [
4
+ "LLaMAForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 1,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_sequence_length": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "pad_token_id": -1,
17
+ "rms_norm_eps": 1e-06,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.27.0.dev0",
21
+ "use_cache": true,
22
+ "vocab_size": 32001
23
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.27.0.dev0"
7
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29c85621126018190c03de69d20a1426bf41c4dcb727abc6de20fb91b8ba269
3
+ size 13476876030
checkpoint-1000/pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31894eb947ce48329de8a0872296e4d095ef167cc129dd57fc4a77d90aa6cb4e
3
+ size 9878006034
checkpoint-1000/pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8707759ea34c5f868c62b454774e1197e5de0e02e37f0e3b914384eab0c0eac5
3
+ size 9894801206
checkpoint-1000/pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9394c97bb299b15f7f13e1da39aed079a9eb9e425051524362fdac180f2c701
3
+ size 7181007225
checkpoint-1000/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26953699328
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
328
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
329
+ }
330
+ }
checkpoint-1000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e75c96f06b249e57a701db73ce821398e69672027a86d3a44063830602a29ab4
3
+ size 14583
checkpoint-1000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dae7f45b6bac644ac207a61f43cba6d4b919a4cac22022bbb02907914422f5d
3
+ size 14583
checkpoint-1000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53c770fe48635faad7fa341007d771781f1397cd47daab5b58f879ffb65f178
3
+ size 14583
checkpoint-1000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68692af1001e65d02e07ac9974ccf4c332cfb23bc8f89566e1a908b1f2c4a1ed
3
+ size 14583
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0218b7b6ff7e5387eb84f6665b22d062937d98e6c93b07319881dc6b5842349
3
+ size 627
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "</s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "</s>"
6
+ }
checkpoint-1000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "",
3
+ "eos_token": "",
4
+ "model_max_length": 1024,
5
+ "padding_side": "right",
6
+ "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--decapoda-research--llama-7b-hf/snapshots/5f98eefcc80e437ef68d457ad7bf167c2c6a1348/special_tokens_map.json",
7
+ "tokenizer_class": "LLaMATokenizer",
8
+ "unk_token": ""
9
+ }
checkpoint-1000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a52f9b0047b3906b156d34a4924346c934d856c9f2ee35c75d5183b10ee46ab
3
+ size 3771