Text Generation
Transformers
PyTorch
English
llama
code
text-generation-inference
Inference Endpoints
Pasta009 commited on
Commit
4cf3a8a
1 Parent(s): 57ed3f6

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": 0.3541707301474347,
4
+ "train_runtime": 33786.0741,
5
+ "train_samples_per_second": 5.938,
6
+ "train_steps_per_second": 0.023
7
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/group/20025/jiuding/LLM_ZOO/CodeLlama-34b-Python-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": false,
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 sha256:446c9047f1db54ce3f2d085b8277cbfa011929ef82c670b72c6ecb4de719d668
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:c63e5caad98d2db21a5fd382f11a94c46898f5f8550b6ea28a730bd81c7aa9fa
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 sha256:8d926954ff03de606f61d7efa4eaf48fb1b9487e3ea63e72f4d1abeb7054f623
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:d0780201263b032dd7e3783775d4354091b5d662e03a990a22768fc782237e51
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:a8b1fbfa500525514298041fd945181e647f49e548c8ca286a1fd100d9d85368
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 sha256:11a058765e8f9dab381253e1c5c7f82c90b6c7771ceb531c67eda1b8cfc84e4b
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 sha256:41e744e7a4e50327b48d1a2259ee51330d4d52f59376d86b6251605d73013b73
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": 0.3541707301474347,
4
+ "train_runtime": 33786.0741,
5
+ "train_samples_per_second": 5.938,
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 +1,496 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 784,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 1.99919725148484e-05,
14
+ "loss": 0.5476,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 1.9967902947497158e-05,
20
+ "loss": 0.4891,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 1.9927829941565187e-05,
26
+ "loss": 0.4573,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 1.9871817834144506e-05,
32
+ "loss": 0.4521,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 1.9799956552507235e-05,
38
+ "loss": 0.4565,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.15,
43
+ "learning_rate": 1.971236146972764e-05,
44
+ "loss": 0.4528,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.18,
49
+ "learning_rate": 1.9609173219450998e-05,
50
+ "loss": 0.4456,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.2,
55
+ "learning_rate": 1.949055747010669e-05,
56
+ "loss": 0.4407,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.23,
61
+ "learning_rate": 1.9356704658928036e-05,
62
+ "loss": 0.4251,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.26,
67
+ "learning_rate": 1.9207829686205882e-05,
68
+ "loss": 0.4372,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.28,
73
+ "learning_rate": 1.904417157026683e-05,
74
+ "loss": 0.4439,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.31,
79
+ "learning_rate": 1.8865993063730003e-05,
80
+ "loss": 0.4305,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.33,
85
+ "learning_rate": 1.867358023165851e-05,
86
+ "loss": 0.4395,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.36,
91
+ "learning_rate": 1.8467241992282842e-05,
92
+ "loss": 0.4402,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.38,
97
+ "learning_rate": 1.824730962103356e-05,
98
+ "loss": 0.4382,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.41,
103
+ "learning_rate": 1.8014136218679566e-05,
104
+ "loss": 0.4359,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.43,
109
+ "learning_rate": 1.7768096144425903e-05,
110
+ "loss": 0.4202,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.46,
115
+ "learning_rate": 1.7509584414881114e-05,
116
+ "loss": 0.4181,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.48,
121
+ "learning_rate": 1.7239016069859292e-05,
122
+ "loss": 0.4263,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.51,
127
+ "learning_rate": 1.6956825506034866e-05,
128
+ "loss": 0.4227,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.54,
133
+ "learning_rate": 1.6663465779520042e-05,
134
+ "loss": 0.4165,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.56,
139
+ "learning_rate": 1.635940787848455e-05,
140
+ "loss": 0.4213,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.59,
145
+ "learning_rate": 1.6045139966985562e-05,
146
+ "loss": 0.4197,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.61,
151
+ "learning_rate": 1.5721166601221697e-05,
152
+ "loss": 0.4257,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.64,
157
+ "learning_rate": 1.5388007919469604e-05,
158
+ "loss": 0.4216,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.66,
163
+ "learning_rate": 1.504619880700346e-05,
164
+ "loss": 0.4171,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.69,
169
+ "learning_rate": 1.4696288037338258e-05,
170
+ "loss": 0.42,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.71,
175
+ "learning_rate": 1.4338837391175582e-05,
176
+ "loss": 0.4179,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.74,
181
+ "learning_rate": 1.397442075446633e-05,
182
+ "loss": 0.4183,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.77,
187
+ "learning_rate": 1.3603623197038536e-05,
188
+ "loss": 0.4291,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.79,
193
+ "learning_rate": 1.3227040033269501e-05,
194
+ "loss": 0.4142,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.82,
199
+ "learning_rate": 1.2845275866310325e-05,
200
+ "loss": 0.4154,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.84,
205
+ "learning_rate": 1.2458943617397346e-05,
206
+ "loss": 0.4199,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.87,
211
+ "learning_rate": 1.206866354180891e-05,
212
+ "loss": 0.4213,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.89,
217
+ "learning_rate": 1.1675062233047365e-05,
218
+ "loss": 0.4039,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.92,
223
+ "learning_rate": 1.1278771616845061e-05,
224
+ "loss": 0.4065,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.94,
229
+ "learning_rate": 1.0880427936609455e-05,
230
+ "loss": 0.4117,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.97,
235
+ "learning_rate": 1.0480670731936209e-05,
236
+ "loss": 0.4132,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.99,
241
+ "learning_rate": 1.0080141811830277e-05,
242
+ "loss": 0.4099,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 1.02,
247
+ "learning_rate": 9.67948422428345e-06,
248
+ "loss": 0.3254,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 1.05,
253
+ "learning_rate": 9.279341223862705e-06,
254
+ "loss": 0.2853,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 1.07,
259
+ "learning_rate": 8.880355238966923e-06,
260
+ "loss": 0.2822,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 1.1,
265
+ "learning_rate": 8.483166840409996e-06,
266
+ "loss": 0.2859,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 1.12,
271
+ "learning_rate": 8.08841371298628e-06,
272
+ "loss": 0.2797,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 1.15,
277
+ "learning_rate": 7.696729631669563e-06,
278
+ "loss": 0.2731,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 1.17,
283
+ "learning_rate": 7.308743444089232e-06,
284
+ "loss": 0.27,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 1.2,
289
+ "learning_rate": 6.925078060917245e-06,
290
+ "loss": 0.2809,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 1.22,
295
+ "learning_rate": 6.546349455786926e-06,
296
+ "loss": 0.28,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 1.25,
301
+ "learning_rate": 6.173165676349103e-06,
302
+ "loss": 0.2863,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 1.28,
307
+ "learning_rate": 5.806125868053433e-06,
308
+ "loss": 0.2804,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 1.3,
313
+ "learning_rate": 5.4458193122221405e-06,
314
+ "loss": 0.2797,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 1.33,
319
+ "learning_rate": 5.092824479960625e-06,
320
+ "loss": 0.2861,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 1.35,
325
+ "learning_rate": 4.747708103423791e-06,
326
+ "loss": 0.2777,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 1.38,
331
+ "learning_rate": 4.411024265929283e-06,
332
+ "loss": 0.2791,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 1.4,
337
+ "learning_rate": 4.083313512378368e-06,
338
+ "loss": 0.275,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 1.43,
343
+ "learning_rate": 3.7651019814126656e-06,
344
+ "loss": 0.2787,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 1.45,
349
+ "learning_rate": 3.456900560700158e-06,
350
+ "loss": 0.2777,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 1.48,
355
+ "learning_rate": 3.1592040667065393e-06,
356
+ "loss": 0.2727,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 1.51,
361
+ "learning_rate": 2.8724904502688566e-06,
362
+ "loss": 0.2748,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 1.53,
367
+ "learning_rate": 2.597220029246846e-06,
368
+ "loss": 0.2809,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 1.56,
373
+ "learning_rate": 2.333834749484e-06,
374
+ "loss": 0.2706,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 1.58,
379
+ "learning_rate": 2.082757475264804e-06,
380
+ "loss": 0.2748,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 1.61,
385
+ "learning_rate": 1.8443913104073984e-06,
386
+ "loss": 0.273,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 1.63,
391
+ "learning_rate": 1.6191189510815942e-06,
392
+ "loss": 0.2788,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 1.66,
397
+ "learning_rate": 1.4073020713912988e-06,
398
+ "loss": 0.2741,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 1.68,
403
+ "learning_rate": 1.209280742707828e-06,
404
+ "loss": 0.2749,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 1.71,
409
+ "learning_rate": 1.0253728876863256e-06,
410
+ "loss": 0.2739,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 1.73,
415
+ "learning_rate": 8.558737698418762e-07,
416
+ "loss": 0.27,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 1.76,
421
+ "learning_rate": 7.010555195048241e-07,
422
+ "loss": 0.2683,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 1.79,
427
+ "learning_rate": 5.611666969163243e-07,
428
+ "loss": 0.2701,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 1.81,
433
+ "learning_rate": 4.3643189316561864e-07,
434
+ "loss": 0.2705,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 1.84,
439
+ "learning_rate": 3.2705136960970554e-07,
440
+ "loss": 0.2695,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 1.86,
445
+ "learning_rate": 2.3320073635432984e-07,
446
+ "loss": 0.2747,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 1.89,
451
+ "learning_rate": 1.55030670312476e-07,
452
+ "loss": 0.273,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 1.91,
457
+ "learning_rate": 9.26666732930348e-08,
458
+ "loss": 0.2721,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 1.94,
463
+ "learning_rate": 4.6208870508017703e-08,
464
+ "loss": 0.2798,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 1.96,
469
+ "learning_rate": 1.5731849821833955e-08,
470
+ "loss": 0.2738,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 1.99,
475
+ "learning_rate": 1.2845420006879494e-09,
476
+ "loss": 0.2722,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 2.0,
481
+ "step": 784,
482
+ "total_flos": 1134283296079872.0,
483
+ "train_loss": 0.3541707301474347,
484
+ "train_runtime": 33786.0741,
485
+ "train_samples_per_second": 5.938,
486
+ "train_steps_per_second": 0.023
487
+ }
488
+ ],
489
+ "logging_steps": 10,
490
+ "max_steps": 784,
491
+ "num_train_epochs": 2,
492
+ "save_steps": 500,
493
+ "total_flos": 1134283296079872.0,
494
+ "trial_name": null,
495
+ "trial_params": null
496
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1b00e10f91422ac2a1bcad396c0d1fec9e31735d2a4149fe48e727c6c8e57f2
3
+ size 6075
training_loss.svg ADDED