Text Generation
Transformers
PyTorch
English
llama
code
text-generation-inference
Inference Endpoints
Pasta009 commited on
Commit
64596fb
1 Parent(s): 18cc185

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 32004,
3
+ "▁<EOT>": 32003,
4
+ "▁<MID>": 32001,
5
+ "▁<PRE>": 32000,
6
+ "▁<SUF>": 32002
7
+ }
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.40841181026500406,
4
+ "train_runtime": 72622.3244,
5
+ "train_samples_per_second": 5.811,
6
+ "train_steps_per_second": 0.023
7
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/group/30172/kaitongyang/open_models/CodeLlama-34b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 22016,
12
+ "max_position_embeddings": 16384,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 64,
15
+ "num_hidden_layers": 48,
16
+ "num_key_value_heads": 8,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 1000000,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.33.3",
24
+ "use_cache": true,
25
+ "vocab_size": 32005
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.33.3"
6
+ }
log.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42330c622da6ddb618f8a7b633f2f49b835f523c10c87daeaca3d4b55761963
3
+ size 9852719417
pytorch_model-00002-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95122e4795f58e03a242eed59a8db743d0a2867ba4fc2fc679bce9f02386b946
3
+ size 9689093137
pytorch_model-00003-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02b62e0e0fc05919caaf29adbc31857274380c990b64c9aa0db4fe061345ae5
3
+ size 9689093137
pytorch_model-00004-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4131cb2a5823fddfa56f69592b0144e78fb2d50459f395e6fa1521300a9a3468
3
+ size 9689093137
pytorch_model-00005-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2339a0177765e2ae079ce2e7539e5cfee0a2557d78ed96761fb62d436db5d9c2
3
+ size 9689093137
pytorch_model-00006-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c0ffa6bb503945ba67a324f8be2500ee02bb9c49b8ae970aae1343efbb771b
3
+ size 9689093137
pytorch_model-00007-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0581be1cd5cf571d39748a1adec066cb9da40b9b640cd31c49b3ab59bc2fee05
3
+ size 9190067865
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 67488104448
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00007-of-00007.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
323
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
324
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
325
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
326
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
327
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
328
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
329
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
330
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
331
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
332
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
333
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
334
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
335
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
336
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
337
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
338
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
339
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
340
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
341
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
342
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
343
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
344
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
345
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
346
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
347
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
348
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
349
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
350
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
351
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
352
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
353
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
354
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
355
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
356
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
357
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
358
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
359
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
360
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
361
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
362
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
363
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
364
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
365
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
366
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
367
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
368
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
369
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
370
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
371
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
372
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
373
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
374
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
375
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
376
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
377
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
378
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
379
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
380
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
381
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
382
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
383
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
384
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
385
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
386
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
387
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
388
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
389
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
390
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
391
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
392
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
393
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
394
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
395
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
396
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
397
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
398
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
399
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
400
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
401
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
402
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
403
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
404
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
405
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
406
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
407
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
408
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
409
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
410
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
411
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
412
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
413
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
414
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
415
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
416
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
417
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
418
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
419
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
420
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
421
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
422
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
423
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
424
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
425
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
426
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
427
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
428
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
429
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
430
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
431
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
432
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
433
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
434
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
435
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
436
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
437
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
438
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
439
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
440
+ "model.norm.weight": "pytorch_model-00007-of-00007.bin"
441
+ }
442
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": true,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": "[PAD]",
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "additional_special_tokens": [
5
+ "▁<PRE>",
6
+ "▁<MID>",
7
+ "▁<SUF>",
8
+ "▁<EOT>"
9
+ ],
10
+ "bos_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "clean_up_tokenization_spaces": false,
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "eot_token": "▁<EOT>",
28
+ "fill_token": "<FILL_ME>",
29
+ "legacy": null,
30
+ "middle_token": "▁<MID>",
31
+ "model_max_length": 1000000000000000019884624838656,
32
+ "pad_token": null,
33
+ "padding_side": "left",
34
+ "prefix_token": "▁<PRE>",
35
+ "sp_model_kwargs": {},
36
+ "suffix_first": false,
37
+ "suffix_token": "▁<SUF>",
38
+ "tokenizer_class": "CodeLlamaTokenizer",
39
+ "unk_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<unk>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "use_default_system_prompt": false
48
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.40841181026500406,
4
+ "train_runtime": 72622.3244,
5
+ "train_samples_per_second": 5.811,
6
+ "train_steps_per_second": 0.023
7
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,1012 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9987871437234688,
5
+ "eval_steps": 500,
6
+ "global_step": 1648,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 1.9998183053318547e-05,
14
+ "loss": 0.6109,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 1.9992732873533223e-05,
20
+ "loss": 0.5587,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.04,
25
+ "learning_rate": 1.9983651441181253e-05,
26
+ "loss": 0.5352,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.05,
31
+ "learning_rate": 1.997094205635831e-05,
32
+ "loss": 0.5315,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.06,
37
+ "learning_rate": 1.99546093375193e-05,
38
+ "loss": 0.5115,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.07,
43
+ "learning_rate": 1.99346592198001e-05,
44
+ "loss": 0.5241,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.08,
49
+ "learning_rate": 1.9911098952860726e-05,
50
+ "loss": 0.5085,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.1,
55
+ "learning_rate": 1.9883937098250962e-05,
56
+ "loss": 0.4903,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.11,
61
+ "learning_rate": 1.985318352629912e-05,
62
+ "loss": 0.5028,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.12,
67
+ "learning_rate": 1.9818849412525294e-05,
68
+ "loss": 0.5097,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.13,
73
+ "learning_rate": 1.978094723358031e-05,
74
+ "loss": 0.5015,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.15,
79
+ "learning_rate": 1.9739490762711812e-05,
80
+ "loss": 0.5086,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.16,
85
+ "learning_rate": 1.969449506475924e-05,
86
+ "loss": 0.497,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.17,
91
+ "learning_rate": 1.9645976490679402e-05,
92
+ "loss": 0.5085,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.18,
97
+ "learning_rate": 1.9593952671604737e-05,
98
+ "loss": 0.4994,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.19,
103
+ "learning_rate": 1.953844251243633e-05,
104
+ "loss": 0.4923,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.21,
109
+ "learning_rate": 1.947946618497407e-05,
110
+ "loss": 0.4887,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.22,
115
+ "learning_rate": 1.941704512058646e-05,
116
+ "loss": 0.496,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.23,
121
+ "learning_rate": 1.9351202002422654e-05,
122
+ "loss": 0.5039,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.24,
127
+ "learning_rate": 1.928196075716966e-05,
128
+ "loss": 0.4888,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.25,
133
+ "learning_rate": 1.920934654635764e-05,
134
+ "loss": 0.4972,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.27,
139
+ "learning_rate": 1.9133385757216458e-05,
140
+ "loss": 0.4968,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.28,
145
+ "learning_rate": 1.905410599308687e-05,
146
+ "loss": 0.4952,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.29,
151
+ "learning_rate": 1.8971536063389745e-05,
152
+ "loss": 0.4831,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.3,
157
+ "learning_rate": 1.888570597315703e-05,
158
+ "loss": 0.4836,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.32,
163
+ "learning_rate": 1.8796646912128247e-05,
164
+ "loss": 0.4873,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.33,
169
+ "learning_rate": 1.8704391243416478e-05,
170
+ "loss": 0.4773,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.34,
175
+ "learning_rate": 1.8608972491747946e-05,
176
+ "loss": 0.49,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.35,
181
+ "learning_rate": 1.8510425331279488e-05,
182
+ "loss": 0.4892,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.36,
187
+ "learning_rate": 1.8408785572998335e-05,
188
+ "loss": 0.4794,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.38,
193
+ "learning_rate": 1.8304090151708797e-05,
194
+ "loss": 0.4829,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.39,
199
+ "learning_rate": 1.8196377112610524e-05,
200
+ "loss": 0.4814,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.4,
205
+ "learning_rate": 1.808568559747331e-05,
206
+ "loss": 0.4871,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.41,
211
+ "learning_rate": 1.7972055830413372e-05,
212
+ "loss": 0.4824,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.42,
217
+ "learning_rate": 1.7855529103276337e-05,
218
+ "loss": 0.483,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.44,
223
+ "learning_rate": 1.773614776063225e-05,
224
+ "loss": 0.4701,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.45,
229
+ "learning_rate": 1.761395518438797e-05,
230
+ "loss": 0.4859,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.46,
235
+ "learning_rate": 1.7488995778022687e-05,
236
+ "loss": 0.4622,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.47,
241
+ "learning_rate": 1.7361314950452137e-05,
242
+ "loss": 0.4784,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.49,
247
+ "learning_rate": 1.7230959099527512e-05,
248
+ "loss": 0.4888,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 0.5,
253
+ "learning_rate": 1.709797559517496e-05,
254
+ "loss": 0.4734,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 0.51,
259
+ "learning_rate": 1.6962412762181867e-05,
260
+ "loss": 0.4801,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 0.52,
265
+ "learning_rate": 1.6824319862636137e-05,
266
+ "loss": 0.4895,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 0.53,
271
+ "learning_rate": 1.6683747078024887e-05,
272
+ "loss": 0.4671,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 0.55,
277
+ "learning_rate": 1.654074549099901e-05,
278
+ "loss": 0.4881,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 0.56,
283
+ "learning_rate": 1.6395367066810312e-05,
284
+ "loss": 0.4781,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 0.57,
289
+ "learning_rate": 1.6247664634427866e-05,
290
+ "loss": 0.488,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 0.58,
295
+ "learning_rate": 1.6097691867340547e-05,
296
+ "loss": 0.4708,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 0.59,
301
+ "learning_rate": 1.5945503264052638e-05,
302
+ "loss": 0.4811,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 0.61,
307
+ "learning_rate": 1.5791154128279694e-05,
308
+ "loss": 0.4651,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 0.62,
313
+ "learning_rate": 1.5634700548851713e-05,
314
+ "loss": 0.463,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 0.63,
319
+ "learning_rate": 1.547619937933108e-05,
320
+ "loss": 0.4769,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 0.64,
325
+ "learning_rate": 1.53157082173526e-05,
326
+ "loss": 0.4791,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 0.65,
331
+ "learning_rate": 1.5153285383693091e-05,
332
+ "loss": 0.4905,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 0.67,
337
+ "learning_rate": 1.4988989901078286e-05,
338
+ "loss": 0.4607,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 0.68,
343
+ "learning_rate": 1.4822881472734563e-05,
344
+ "loss": 0.4764,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 0.69,
349
+ "learning_rate": 1.4655020460693452e-05,
350
+ "loss": 0.489,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 0.7,
355
+ "learning_rate": 1.4485467863856704e-05,
356
+ "loss": 0.4744,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 0.72,
361
+ "learning_rate": 1.4314285295829957e-05,
362
+ "loss": 0.4722,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 0.73,
367
+ "learning_rate": 1.4141534962532986e-05,
368
+ "loss": 0.4588,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 0.74,
373
+ "learning_rate": 1.3967279639594753e-05,
374
+ "loss": 0.4779,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 0.75,
379
+ "learning_rate": 1.3791582649541404e-05,
380
+ "loss": 0.4629,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 0.76,
385
+ "learning_rate": 1.3614507838785547e-05,
386
+ "loss": 0.4826,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 0.78,
391
+ "learning_rate": 1.3436119554425133e-05,
392
+ "loss": 0.4615,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 0.79,
397
+ "learning_rate": 1.3256482620860415e-05,
398
+ "loss": 0.476,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 0.8,
403
+ "learning_rate": 1.3075662316237466e-05,
404
+ "loss": 0.4746,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 0.81,
409
+ "learning_rate": 1.2893724348726757e-05,
410
+ "loss": 0.4627,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 0.82,
415
+ "learning_rate": 1.2710734832645557e-05,
416
+ "loss": 0.4645,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 0.84,
421
+ "learning_rate": 1.2526760264432658e-05,
422
+ "loss": 0.472,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 0.85,
427
+ "learning_rate": 1.2341867498484303e-05,
428
+ "loss": 0.4653,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 0.86,
433
+ "learning_rate": 1.2156123722859989e-05,
434
+ "loss": 0.4713,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 0.87,
439
+ "learning_rate": 1.1969596434867063e-05,
440
+ "loss": 0.4661,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 0.89,
445
+ "learning_rate": 1.1782353416532908e-05,
446
+ "loss": 0.4761,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 0.9,
451
+ "learning_rate": 1.1594462709973684e-05,
452
+ "loss": 0.4617,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 0.91,
457
+ "learning_rate": 1.140599259266854e-05,
458
+ "loss": 0.4595,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 0.92,
463
+ "learning_rate": 1.1217011552648316e-05,
464
+ "loss": 0.4677,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 0.93,
469
+ "learning_rate": 1.102758826360772e-05,
470
+ "loss": 0.4712,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 0.95,
475
+ "learning_rate": 1.0837791559950029e-05,
476
+ "loss": 0.4613,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 0.96,
481
+ "learning_rate": 1.0647690411773415e-05,
482
+ "loss": 0.4598,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 0.97,
487
+ "learning_rate": 1.0457353899807947e-05,
488
+ "loss": 0.4803,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 0.98,
493
+ "learning_rate": 1.0266851190312375e-05,
494
+ "loss": 0.4549,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 0.99,
499
+ "learning_rate": 1.0076251509939867e-05,
500
+ "loss": 0.463,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 1.01,
505
+ "learning_rate": 9.885624120581772e-06,
506
+ "loss": 0.4129,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 1.02,
511
+ "learning_rate": 9.695038294198588e-06,
512
+ "loss": 0.3427,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 1.03,
517
+ "learning_rate": 9.504563287647265e-06,
518
+ "loss": 0.3457,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 1.04,
523
+ "learning_rate": 9.314268317514023e-06,
524
+ "loss": 0.3401,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 1.06,
529
+ "learning_rate": 9.12422253496175e-06,
530
+ "loss": 0.3354,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 1.07,
535
+ "learning_rate": 8.934495000601241e-06,
536
+ "loss": 0.3391,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 1.08,
541
+ "learning_rate": 8.745154659395273e-06,
542
+ "loss": 0.3428,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 1.09,
547
+ "learning_rate": 8.556270315604779e-06,
548
+ "loss": 0.3339,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 1.1,
553
+ "learning_rate": 8.36791060778608e-06,
554
+ "loss": 0.328,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 1.12,
559
+ "learning_rate": 8.180143983848388e-06,
560
+ "loss": 0.3328,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 1.13,
565
+ "learning_rate": 7.993038676180546e-06,
566
+ "loss": 0.3288,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 1.14,
571
+ "learning_rate": 7.806662676856134e-06,
572
+ "loss": 0.3327,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 1.15,
577
+ "learning_rate": 7.62108371292584e-06,
578
+ "loss": 0.3421,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 1.16,
583
+ "learning_rate": 7.436369221806201e-06,
584
+ "loss": 0.3462,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 1.18,
589
+ "learning_rate": 7.2525863267735405e-06,
590
+ "loss": 0.3302,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 1.19,
595
+ "learning_rate": 7.069801812572117e-06,
596
+ "loss": 0.3278,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 1.2,
601
+ "learning_rate": 6.888082101145222e-06,
602
+ "loss": 0.3402,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 1.21,
607
+ "learning_rate": 6.707493227498187e-06,
608
+ "loss": 0.344,
609
+ "step": 1000
610
+ },
611
+ {
612
+ "epoch": 1.22,
613
+ "learning_rate": 6.5281008157019425e-06,
614
+ "loss": 0.3349,
615
+ "step": 1010
616
+ },
617
+ {
618
+ "epoch": 1.24,
619
+ "learning_rate": 6.3499700550459554e-06,
620
+ "loss": 0.3379,
621
+ "step": 1020
622
+ },
623
+ {
624
+ "epoch": 1.25,
625
+ "learning_rate": 6.173165676349103e-06,
626
+ "loss": 0.3398,
627
+ "step": 1030
628
+ },
629
+ {
630
+ "epoch": 1.26,
631
+ "learning_rate": 5.99775192843722e-06,
632
+ "loss": 0.3362,
633
+ "step": 1040
634
+ },
635
+ {
636
+ "epoch": 1.27,
637
+ "learning_rate": 5.823792554795738e-06,
638
+ "loss": 0.3316,
639
+ "step": 1050
640
+ },
641
+ {
642
+ "epoch": 1.29,
643
+ "learning_rate": 5.6513507704059835e-06,
644
+ "loss": 0.3406,
645
+ "step": 1060
646
+ },
647
+ {
648
+ "epoch": 1.3,
649
+ "learning_rate": 5.480489238773536e-06,
650
+ "loss": 0.3266,
651
+ "step": 1070
652
+ },
653
+ {
654
+ "epoch": 1.31,
655
+ "learning_rate": 5.311270049156967e-06,
656
+ "loss": 0.3393,
657
+ "step": 1080
658
+ },
659
+ {
660
+ "epoch": 1.32,
661
+ "learning_rate": 5.14375469400529e-06,
662
+ "loss": 0.3286,
663
+ "step": 1090
664
+ },
665
+ {
666
+ "epoch": 1.33,
667
+ "learning_rate": 4.978004046612224e-06,
668
+ "loss": 0.3338,
669
+ "step": 1100
670
+ },
671
+ {
672
+ "epoch": 1.35,
673
+ "learning_rate": 4.814078338995516e-06,
674
+ "loss": 0.3247,
675
+ "step": 1110
676
+ },
677
+ {
678
+ "epoch": 1.36,
679
+ "learning_rate": 4.652037140009259e-06,
680
+ "loss": 0.3184,
681
+ "step": 1120
682
+ },
683
+ {
684
+ "epoch": 1.37,
685
+ "learning_rate": 4.491939333697205e-06,
686
+ "loss": 0.3297,
687
+ "step": 1130
688
+ },
689
+ {
690
+ "epoch": 1.38,
691
+ "learning_rate": 4.333843097894932e-06,
692
+ "loss": 0.3378,
693
+ "step": 1140
694
+ },
695
+ {
696
+ "epoch": 1.39,
697
+ "learning_rate": 4.177805883088641e-06,
698
+ "loss": 0.3426,
699
+ "step": 1150
700
+ },
701
+ {
702
+ "epoch": 1.41,
703
+ "learning_rate": 4.023884391538244e-06,
704
+ "loss": 0.3354,
705
+ "step": 1160
706
+ },
707
+ {
708
+ "epoch": 1.42,
709
+ "learning_rate": 3.8721345566724156e-06,
710
+ "loss": 0.3348,
711
+ "step": 1170
712
+ },
713
+ {
714
+ "epoch": 1.43,
715
+ "learning_rate": 3.722611522762917e-06,
716
+ "loss": 0.3314,
717
+ "step": 1180
718
+ },
719
+ {
720
+ "epoch": 1.44,
721
+ "learning_rate": 3.575369624885803e-06,
722
+ "loss": 0.3358,
723
+ "step": 1190
724
+ },
725
+ {
726
+ "epoch": 1.46,
727
+ "learning_rate": 3.4304623691766193e-06,
728
+ "loss": 0.3258,
729
+ "step": 1200
730
+ },
731
+ {
732
+ "epoch": 1.47,
733
+ "learning_rate": 3.287942413386841e-06,
734
+ "loss": 0.3296,
735
+ "step": 1210
736
+ },
737
+ {
738
+ "epoch": 1.48,
739
+ "learning_rate": 3.147861547748612e-06,
740
+ "loss": 0.3364,
741
+ "step": 1220
742
+ },
743
+ {
744
+ "epoch": 1.49,
745
+ "learning_rate": 3.0102706761547264e-06,
746
+ "loss": 0.3206,
747
+ "step": 1230
748
+ },
749
+ {
750
+ "epoch": 1.5,
751
+ "learning_rate": 2.875219797660681e-06,
752
+ "loss": 0.3214,
753
+ "step": 1240
754
+ },
755
+ {
756
+ "epoch": 1.52,
757
+ "learning_rate": 2.7427579883155895e-06,
758
+ "loss": 0.3307,
759
+ "step": 1250
760
+ },
761
+ {
762
+ "epoch": 1.53,
763
+ "learning_rate": 2.612933383328432e-06,
764
+ "loss": 0.33,
765
+ "step": 1260
766
+ },
767
+ {
768
+ "epoch": 1.54,
769
+ "learning_rate": 2.4857931595762406e-06,
770
+ "loss": 0.3343,
771
+ "step": 1270
772
+ },
773
+ {
774
+ "epoch": 1.55,
775
+ "learning_rate": 2.3613835184605527e-06,
776
+ "loss": 0.3258,
777
+ "step": 1280
778
+ },
779
+ {
780
+ "epoch": 1.56,
781
+ "learning_rate": 2.239749669118272e-06,
782
+ "loss": 0.3277,
783
+ "step": 1290
784
+ },
785
+ {
786
+ "epoch": 1.58,
787
+ "learning_rate": 2.1209358119931845e-06,
788
+ "loss": 0.3368,
789
+ "step": 1300
790
+ },
791
+ {
792
+ "epoch": 1.59,
793
+ "learning_rate": 2.0049851227739746e-06,
794
+ "loss": 0.3297,
795
+ "step": 1310
796
+ },
797
+ {
798
+ "epoch": 1.6,
799
+ "learning_rate": 1.891939736704641e-06,
800
+ "loss": 0.3367,
801
+ "step": 1320
802
+ },
803
+ {
804
+ "epoch": 1.61,
805
+ "learning_rate": 1.7818407332729914e-06,
806
+ "loss": 0.3344,
807
+ "step": 1330
808
+ },
809
+ {
810
+ "epoch": 1.63,
811
+ "learning_rate": 1.6747281212828193e-06,
812
+ "loss": 0.3388,
813
+ "step": 1340
814
+ },
815
+ {
816
+ "epoch": 1.64,
817
+ "learning_rate": 1.570640824315095e-06,
818
+ "loss": 0.3333,
819
+ "step": 1350
820
+ },
821
+ {
822
+ "epoch": 1.65,
823
+ "learning_rate": 1.4696166665835853e-06,
824
+ "loss": 0.3313,
825
+ "step": 1360
826
+ },
827
+ {
828
+ "epoch": 1.66,
829
+ "learning_rate": 1.3716923591899167e-06,
830
+ "loss": 0.3355,
831
+ "step": 1370
832
+ },
833
+ {
834
+ "epoch": 1.67,
835
+ "learning_rate": 1.2769034867831588e-06,
836
+ "loss": 0.3287,
837
+ "step": 1380
838
+ },
839
+ {
840
+ "epoch": 1.69,
841
+ "learning_rate": 1.1852844946287434e-06,
842
+ "loss": 0.3294,
843
+ "step": 1390
844
+ },
845
+ {
846
+ "epoch": 1.7,
847
+ "learning_rate": 1.0968686760914248e-06,
848
+ "loss": 0.3369,
849
+ "step": 1400
850
+ },
851
+ {
852
+ "epoch": 1.71,
853
+ "learning_rate": 1.0116881605368112e-06,
854
+ "loss": 0.3289,
855
+ "step": 1410
856
+ },
857
+ {
858
+ "epoch": 1.72,
859
+ "learning_rate": 9.297739016559226e-07,
860
+ "loss": 0.3242,
861
+ "step": 1420
862
+ },
863
+ {
864
+ "epoch": 1.73,
865
+ "learning_rate": 8.511556662169218e-07,
866
+ "loss": 0.3295,
867
+ "step": 1430
868
+ },
869
+ {
870
+ "epoch": 1.75,
871
+ "learning_rate": 7.758620232482083e-07,
872
+ "loss": 0.3257,
873
+ "step": 1440
874
+ },
875
+ {
876
+ "epoch": 1.76,
877
+ "learning_rate": 7.039203336567247e-07,
878
+ "loss": 0.3278,
879
+ "step": 1450
880
+ },
881
+ {
882
+ "epoch": 1.77,
883
+ "learning_rate": 6.353567402853056e-07,
884
+ "loss": 0.3199,
885
+ "step": 1460
886
+ },
887
+ {
888
+ "epoch": 1.78,
889
+ "learning_rate": 5.701961584126392e-07,
890
+ "loss": 0.3378,
891
+ "step": 1470
892
+ },
893
+ {
894
+ "epoch": 1.8,
895
+ "learning_rate": 5.084622666993244e-07,
896
+ "loss": 0.3218,
897
+ "step": 1480
898
+ },
899
+ {
900
+ "epoch": 1.81,
901
+ "learning_rate": 4.501774985832974e-07,
902
+ "loss": 0.326,
903
+ "step": 1490
904
+ },
905
+ {
906
+ "epoch": 1.82,
907
+ "learning_rate": 3.953630341277603e-07,
908
+ "loss": 0.3359,
909
+ "step": 1500
910
+ },
911
+ {
912
+ "epoch": 1.83,
913
+ "learning_rate": 3.440387923245714e-07,
914
+ "loss": 0.3304,
915
+ "step": 1510
916
+ },
917
+ {
918
+ "epoch": 1.84,
919
+ "learning_rate": 2.9622342385589256e-07,
920
+ "loss": 0.3239,
921
+ "step": 1520
922
+ },
923
+ {
924
+ "epoch": 1.86,
925
+ "learning_rate": 2.519343043167399e-07,
926
+ "loss": 0.333,
927
+ "step": 1530
928
+ },
929
+ {
930
+ "epoch": 1.87,
931
+ "learning_rate": 2.111875279008657e-07,
932
+ "loss": 0.316,
933
+ "step": 1540
934
+ },
935
+ {
936
+ "epoch": 1.88,
937
+ "learning_rate": 1.7399790155230633e-07,
938
+ "loss": 0.3345,
939
+ "step": 1550
940
+ },
941
+ {
942
+ "epoch": 1.89,
943
+ "learning_rate": 1.4037893958469994e-07,
944
+ "loss": 0.3284,
945
+ "step": 1560
946
+ },
947
+ {
948
+ "epoch": 1.9,
949
+ "learning_rate": 1.1034285877032147e-07,
950
+ "loss": 0.3235,
951
+ "step": 1570
952
+ },
953
+ {
954
+ "epoch": 1.92,
955
+ "learning_rate": 8.390057390064266e-08,
956
+ "loss": 0.3304,
957
+ "step": 1580
958
+ },
959
+ {
960
+ "epoch": 1.93,
961
+ "learning_rate": 6.10616938200137e-08,
962
+ "loss": 0.3197,
963
+ "step": 1590
964
+ },
965
+ {
966
+ "epoch": 1.94,
967
+ "learning_rate": 4.183451793390747e-08,
968
+ "loss": 0.3394,
969
+ "step": 1600
970
+ },
971
+ {
972
+ "epoch": 1.95,
973
+ "learning_rate": 2.6226033193007538e-08,
974
+ "loss": 0.3267,
975
+ "step": 1610
976
+ },
977
+ {
978
+ "epoch": 1.96,
979
+ "learning_rate": 1.424191155422583e-08,
980
+ "loss": 0.3329,
981
+ "step": 1620
982
+ },
983
+ {
984
+ "epoch": 1.98,
985
+ "learning_rate": 5.886507919570239e-09,
986
+ "loss": 0.3307,
987
+ "step": 1630
988
+ },
989
+ {
990
+ "epoch": 1.99,
991
+ "learning_rate": 1.1628585536216374e-09,
992
+ "loss": 0.3305,
993
+ "step": 1640
994
+ },
995
+ {
996
+ "epoch": 2.0,
997
+ "step": 1648,
998
+ "total_flos": 2536021641658368.0,
999
+ "train_loss": 0.40841181026500406,
1000
+ "train_runtime": 72622.3244,
1001
+ "train_samples_per_second": 5.811,
1002
+ "train_steps_per_second": 0.023
1003
+ }
1004
+ ],
1005
+ "logging_steps": 10,
1006
+ "max_steps": 1648,
1007
+ "num_train_epochs": 2,
1008
+ "save_steps": 500,
1009
+ "total_flos": 2536021641658368.0,
1010
+ "trial_name": null,
1011
+ "trial_params": null
1012
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b85d34cc533f3f5fddb5941f884162bb74b6dbe40848d3c61f0c8ed8cdc42064
3
+ size 6075
training_loss.svg ADDED