“Sara commited on
Commit
09f36b2
1 Parent(s): 455748a

adding model files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</headline>": 32008,
3
+ "</scratchpad>": 32006,
4
+ "<</SYS>>": 32004,
5
+ "<<SYS>>": 32003,
6
+ "<headline>": 32007,
7
+ "<pad>": 32000,
8
+ "<scratchpad>": 32005,
9
+ "[/INST]": 32002,
10
+ "[INST]": 32001
11
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "teknium/OpenHermes-13B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 40,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.40.2",
27
+ "use_cache": false,
28
+ "vocab_size": 32016
29
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.40.2",
7
+ "use_cache": false
8
+ }
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110fb61c31bbe799ea393dfa670437db06a354642bf1fc78eb8333ae56ce6697
3
+ size 4881575536
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d7a2b1dd4d56388757dac0db1356dccf8a5c417e2a8ff0b9d48fd5bdab2031
3
+ size 4970418112
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4693c5836d2f08b1448491843dc5e4a2c8d40d49ec0c0639b32180139b0c6d58
3
+ size 4970418120
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932a0992c53bf3021e0a39e4658366afa3b91009575b853d4d76eec7cb55611d
3
+ size 4970418144
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3662d6a50af46650a92c6c655f27a22e5d221d2bde22bf105909483d6eb4f1
3
+ size 4970418144
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e9ae50e3a57cc44753c879088eedef95d4f8a3f43fa63006cc5f5fc9049ec3b
3
+ size 4792119040
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4fc1e4344f0718e1cdd5d42c942b168c30c5fd53ce36013befd4473b9de836
3
+ size 4792160232
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8dac82843b566a035dad0f71f6bee25b5dc7737378c287909247a6746e7252
3
+ size 4792160224
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe007c1fd3b8df79e6d90f8a3cbba2734bbfedac2e25033ebacb798ea8e97a7
3
+ size 4970418144
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28abc9f1fc4d5e36aa207f74c91eb91934e20f1866154ac9a3fa83aeecc9e048
3
+ size 4970418144
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848d926f7343ec390db2269761ba7355ce0c7db0c041ee26de753add85f1cfff
3
+ size 2983630864
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 52064112640
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00011-of-00011.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
368
+ "model.norm.weight": "model-00011-of-00011.safetensors"
369
+ }
370
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[INST]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": true
9
+ },
10
+ {
11
+ "content": "[/INST]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": true
16
+ },
17
+ {
18
+ "content": "<<SYS>>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": true
23
+ },
24
+ {
25
+ "content": "<</SYS>>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": true
30
+ },
31
+ {
32
+ "content": "<scratchpad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": true
37
+ },
38
+ {
39
+ "content": "</scratchpad>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": true
44
+ },
45
+ {
46
+ "content": "<headline>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": true
51
+ },
52
+ {
53
+ "content": "</headline>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": true
58
+ }
59
+ ],
60
+ "bos_token": {
61
+ "content": "<s>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "eos_token": {
68
+ "content": "</s>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "pad_token": {
75
+ "content": "<pad>",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ },
81
+ "unk_token": {
82
+ "content": "<unk>",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ }
88
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "[INST]",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": true,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "[/INST]",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": true,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<<SYS>>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": true,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<</SYS>>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": true,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<scratchpad>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": true,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "</scratchpad>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": true,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<headline>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": true,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "</headline>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": true,
100
+ "special": true
101
+ }
102
+ },
103
+ "additional_special_tokens": [
104
+ "[INST]",
105
+ "[/INST]",
106
+ "<<SYS>>",
107
+ "<</SYS>>",
108
+ "<scratchpad>",
109
+ "</scratchpad>",
110
+ "<headline>",
111
+ "</headline>"
112
+ ],
113
+ "bos_token": "<s>",
114
+ "clean_up_tokenization_spaces": false,
115
+ "eos_token": "</s>",
116
+ "legacy": false,
117
+ "model_max_length": 1000000000000000019884624838656,
118
+ "pad_to_multiple_of": 8,
119
+ "pad_token": "<pad>",
120
+ "padding_side": "left",
121
+ "sp_model_kwargs": {},
122
+ "spaces_between_special_tokens": false,
123
+ "tokenizer_class": "LlamaTokenizer",
124
+ "trust_remote_code": false,
125
+ "unk_token": "<unk>",
126
+ "use_default_system_prompt": true,
127
+ "use_fast": true
128
+ }
trainer_state.json ADDED
@@ -0,0 +1,929 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 50,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002,
13
+ "eval_loss": 2.1960251331329346,
14
+ "eval_runtime": 2.1983,
15
+ "eval_samples_per_second": 70.964,
16
+ "eval_steps_per_second": 3.639,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.05,
21
+ "grad_norm": 9.552270889282227,
22
+ "learning_rate": 2.5e-06,
23
+ "loss": 1.3747,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.05,
28
+ "eval_loss": 0.7324444651603699,
29
+ "eval_runtime": 1.9429,
30
+ "eval_samples_per_second": 80.293,
31
+ "eval_steps_per_second": 4.118,
32
+ "step": 50
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "grad_norm": 12.921321868896484,
37
+ "learning_rate": 5e-06,
38
+ "loss": 0.6642,
39
+ "step": 100
40
+ },
41
+ {
42
+ "epoch": 0.1,
43
+ "eval_loss": 0.7477038502693176,
44
+ "eval_runtime": 1.9488,
45
+ "eval_samples_per_second": 80.05,
46
+ "eval_steps_per_second": 4.105,
47
+ "step": 100
48
+ },
49
+ {
50
+ "epoch": 0.15,
51
+ "grad_norm": 6.498777389526367,
52
+ "learning_rate": 7.500000000000001e-06,
53
+ "loss": 0.6259,
54
+ "step": 150
55
+ },
56
+ {
57
+ "epoch": 0.15,
58
+ "eval_loss": 0.6763167977333069,
59
+ "eval_runtime": 1.9355,
60
+ "eval_samples_per_second": 80.601,
61
+ "eval_steps_per_second": 4.133,
62
+ "step": 150
63
+ },
64
+ {
65
+ "epoch": 0.2,
66
+ "grad_norm": 13.172846794128418,
67
+ "learning_rate": 1e-05,
68
+ "loss": 0.665,
69
+ "step": 200
70
+ },
71
+ {
72
+ "epoch": 0.2,
73
+ "eval_loss": 0.679334819316864,
74
+ "eval_runtime": 1.9711,
75
+ "eval_samples_per_second": 79.144,
76
+ "eval_steps_per_second": 4.059,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 0.25,
81
+ "grad_norm": 5.069002628326416,
82
+ "learning_rate": 1.25e-05,
83
+ "loss": 0.6586,
84
+ "step": 250
85
+ },
86
+ {
87
+ "epoch": 0.25,
88
+ "eval_loss": 0.6933216452598572,
89
+ "eval_runtime": 1.9422,
90
+ "eval_samples_per_second": 80.321,
91
+ "eval_steps_per_second": 4.119,
92
+ "step": 250
93
+ },
94
+ {
95
+ "epoch": 0.3,
96
+ "grad_norm": 4.540435791015625,
97
+ "learning_rate": 1.5000000000000002e-05,
98
+ "loss": 0.6939,
99
+ "step": 300
100
+ },
101
+ {
102
+ "epoch": 0.3,
103
+ "eval_loss": 0.7091314792633057,
104
+ "eval_runtime": 1.98,
105
+ "eval_samples_per_second": 78.787,
106
+ "eval_steps_per_second": 4.04,
107
+ "step": 300
108
+ },
109
+ {
110
+ "epoch": 0.35,
111
+ "grad_norm": 2.8698132038116455,
112
+ "learning_rate": 1.7500000000000002e-05,
113
+ "loss": 0.6783,
114
+ "step": 350
115
+ },
116
+ {
117
+ "epoch": 0.35,
118
+ "eval_loss": 0.7234737873077393,
119
+ "eval_runtime": 1.9392,
120
+ "eval_samples_per_second": 80.445,
121
+ "eval_steps_per_second": 4.125,
122
+ "step": 350
123
+ },
124
+ {
125
+ "epoch": 0.4,
126
+ "grad_norm": 3.8550472259521484,
127
+ "learning_rate": 2e-05,
128
+ "loss": 0.7386,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.4,
133
+ "eval_loss": 0.7281543016433716,
134
+ "eval_runtime": 1.9771,
135
+ "eval_samples_per_second": 78.905,
136
+ "eval_steps_per_second": 4.046,
137
+ "step": 400
138
+ },
139
+ {
140
+ "epoch": 0.45,
141
+ "grad_norm": 3.354882001876831,
142
+ "learning_rate": 1.999048221581858e-05,
143
+ "loss": 0.7279,
144
+ "step": 450
145
+ },
146
+ {
147
+ "epoch": 0.45,
148
+ "eval_loss": 0.744288444519043,
149
+ "eval_runtime": 1.9696,
150
+ "eval_samples_per_second": 79.203,
151
+ "eval_steps_per_second": 4.062,
152
+ "step": 450
153
+ },
154
+ {
155
+ "epoch": 0.5,
156
+ "grad_norm": 2.7983996868133545,
157
+ "learning_rate": 1.9961946980917457e-05,
158
+ "loss": 0.7591,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 0.5,
163
+ "eval_loss": 0.7486099600791931,
164
+ "eval_runtime": 1.9436,
165
+ "eval_samples_per_second": 80.264,
166
+ "eval_steps_per_second": 4.116,
167
+ "step": 500
168
+ },
169
+ {
170
+ "epoch": 0.55,
171
+ "grad_norm": 4.0514655113220215,
172
+ "learning_rate": 1.9914448613738107e-05,
173
+ "loss": 0.7497,
174
+ "step": 550
175
+ },
176
+ {
177
+ "epoch": 0.55,
178
+ "eval_loss": 0.7431505918502808,
179
+ "eval_runtime": 1.9501,
180
+ "eval_samples_per_second": 79.994,
181
+ "eval_steps_per_second": 4.102,
182
+ "step": 550
183
+ },
184
+ {
185
+ "epoch": 0.6,
186
+ "grad_norm": 2.5434212684631348,
187
+ "learning_rate": 1.9848077530122083e-05,
188
+ "loss": 0.7297,
189
+ "step": 600
190
+ },
191
+ {
192
+ "epoch": 0.6,
193
+ "eval_loss": 0.7465248107910156,
194
+ "eval_runtime": 1.9802,
195
+ "eval_samples_per_second": 78.781,
196
+ "eval_steps_per_second": 4.04,
197
+ "step": 600
198
+ },
199
+ {
200
+ "epoch": 0.65,
201
+ "grad_norm": 3.6651933193206787,
202
+ "learning_rate": 1.9762960071199334e-05,
203
+ "loss": 0.7435,
204
+ "step": 650
205
+ },
206
+ {
207
+ "epoch": 0.65,
208
+ "eval_loss": 0.7544175982475281,
209
+ "eval_runtime": 1.9459,
210
+ "eval_samples_per_second": 80.167,
211
+ "eval_steps_per_second": 4.111,
212
+ "step": 650
213
+ },
214
+ {
215
+ "epoch": 0.7,
216
+ "grad_norm": 2.424015522003174,
217
+ "learning_rate": 1.9659258262890683e-05,
218
+ "loss": 0.7611,
219
+ "step": 700
220
+ },
221
+ {
222
+ "epoch": 0.7,
223
+ "eval_loss": 0.7523372173309326,
224
+ "eval_runtime": 2.0693,
225
+ "eval_samples_per_second": 75.388,
226
+ "eval_steps_per_second": 3.866,
227
+ "step": 700
228
+ },
229
+ {
230
+ "epoch": 0.75,
231
+ "grad_norm": 2.423607587814331,
232
+ "learning_rate": 1.953716950748227e-05,
233
+ "loss": 0.7622,
234
+ "step": 750
235
+ },
236
+ {
237
+ "epoch": 0.75,
238
+ "eval_loss": 0.7510794401168823,
239
+ "eval_runtime": 1.9388,
240
+ "eval_samples_per_second": 80.462,
241
+ "eval_steps_per_second": 4.126,
242
+ "step": 750
243
+ },
244
+ {
245
+ "epoch": 0.8,
246
+ "grad_norm": 2.693723678588867,
247
+ "learning_rate": 1.9396926207859085e-05,
248
+ "loss": 0.7068,
249
+ "step": 800
250
+ },
251
+ {
252
+ "epoch": 0.8,
253
+ "eval_loss": 0.7511183619499207,
254
+ "eval_runtime": 1.9737,
255
+ "eval_samples_per_second": 79.04,
256
+ "eval_steps_per_second": 4.053,
257
+ "step": 800
258
+ },
259
+ {
260
+ "epoch": 0.85,
261
+ "grad_norm": 3.4280779361724854,
262
+ "learning_rate": 1.9238795325112867e-05,
263
+ "loss": 0.7297,
264
+ "step": 850
265
+ },
266
+ {
267
+ "epoch": 0.85,
268
+ "eval_loss": 0.7428472638130188,
269
+ "eval_runtime": 1.9385,
270
+ "eval_samples_per_second": 80.476,
271
+ "eval_steps_per_second": 4.127,
272
+ "step": 850
273
+ },
274
+ {
275
+ "epoch": 0.9,
276
+ "grad_norm": 2.3453116416931152,
277
+ "learning_rate": 1.9063077870366504e-05,
278
+ "loss": 0.7415,
279
+ "step": 900
280
+ },
281
+ {
282
+ "epoch": 0.9,
283
+ "eval_loss": 0.7462921142578125,
284
+ "eval_runtime": 1.9445,
285
+ "eval_samples_per_second": 80.225,
286
+ "eval_steps_per_second": 4.114,
287
+ "step": 900
288
+ },
289
+ {
290
+ "epoch": 0.95,
291
+ "grad_norm": 2.466562271118164,
292
+ "learning_rate": 1.887010833178222e-05,
293
+ "loss": 0.7309,
294
+ "step": 950
295
+ },
296
+ {
297
+ "epoch": 0.95,
298
+ "eval_loss": 0.7448516488075256,
299
+ "eval_runtime": 1.9649,
300
+ "eval_samples_per_second": 79.392,
301
+ "eval_steps_per_second": 4.071,
302
+ "step": 950
303
+ },
304
+ {
305
+ "epoch": 1.0,
306
+ "grad_norm": 2.566894292831421,
307
+ "learning_rate": 1.866025403784439e-05,
308
+ "loss": 0.7362,
309
+ "step": 1000
310
+ },
311
+ {
312
+ "epoch": 1.0,
313
+ "eval_loss": 0.7468461394309998,
314
+ "eval_runtime": 1.9409,
315
+ "eval_samples_per_second": 80.377,
316
+ "eval_steps_per_second": 4.122,
317
+ "step": 1000
318
+ },
319
+ {
320
+ "epoch": 1.05,
321
+ "grad_norm": 2.3160593509674072,
322
+ "learning_rate": 1.843391445812886e-05,
323
+ "loss": 0.3678,
324
+ "step": 1050
325
+ },
326
+ {
327
+ "epoch": 1.05,
328
+ "eval_loss": 0.7951092720031738,
329
+ "eval_runtime": 1.9636,
330
+ "eval_samples_per_second": 79.445,
331
+ "eval_steps_per_second": 4.074,
332
+ "step": 1050
333
+ },
334
+ {
335
+ "epoch": 1.1,
336
+ "grad_norm": 2.5666403770446777,
337
+ "learning_rate": 1.819152044288992e-05,
338
+ "loss": 0.3964,
339
+ "step": 1100
340
+ },
341
+ {
342
+ "epoch": 1.1,
343
+ "eval_loss": 0.78642338514328,
344
+ "eval_runtime": 1.9832,
345
+ "eval_samples_per_second": 78.66,
346
+ "eval_steps_per_second": 4.034,
347
+ "step": 1100
348
+ },
349
+ {
350
+ "epoch": 1.15,
351
+ "grad_norm": 2.0465054512023926,
352
+ "learning_rate": 1.7933533402912354e-05,
353
+ "loss": 0.3784,
354
+ "step": 1150
355
+ },
356
+ {
357
+ "epoch": 1.15,
358
+ "eval_loss": 0.7795366644859314,
359
+ "eval_runtime": 1.9712,
360
+ "eval_samples_per_second": 79.139,
361
+ "eval_steps_per_second": 4.058,
362
+ "step": 1150
363
+ },
364
+ {
365
+ "epoch": 1.2,
366
+ "grad_norm": 2.862433910369873,
367
+ "learning_rate": 1.766044443118978e-05,
368
+ "loss": 0.3834,
369
+ "step": 1200
370
+ },
371
+ {
372
+ "epoch": 1.2,
373
+ "eval_loss": 0.7931370139122009,
374
+ "eval_runtime": 1.9437,
375
+ "eval_samples_per_second": 80.26,
376
+ "eval_steps_per_second": 4.116,
377
+ "step": 1200
378
+ },
379
+ {
380
+ "epoch": 1.25,
381
+ "grad_norm": 2.331970691680908,
382
+ "learning_rate": 1.737277336810124e-05,
383
+ "loss": 0.3578,
384
+ "step": 1250
385
+ },
386
+ {
387
+ "epoch": 1.25,
388
+ "eval_loss": 0.7878620624542236,
389
+ "eval_runtime": 1.9394,
390
+ "eval_samples_per_second": 80.438,
391
+ "eval_steps_per_second": 4.125,
392
+ "step": 1250
393
+ },
394
+ {
395
+ "epoch": 1.3,
396
+ "grad_norm": 2.595731496810913,
397
+ "learning_rate": 1.7071067811865477e-05,
398
+ "loss": 0.3719,
399
+ "step": 1300
400
+ },
401
+ {
402
+ "epoch": 1.3,
403
+ "eval_loss": 0.7958313226699829,
404
+ "eval_runtime": 1.9743,
405
+ "eval_samples_per_second": 79.014,
406
+ "eval_steps_per_second": 4.052,
407
+ "step": 1300
408
+ },
409
+ {
410
+ "epoch": 1.35,
411
+ "grad_norm": 2.6935150623321533,
412
+ "learning_rate": 1.6755902076156606e-05,
413
+ "loss": 0.3733,
414
+ "step": 1350
415
+ },
416
+ {
417
+ "epoch": 1.35,
418
+ "eval_loss": 0.786521852016449,
419
+ "eval_runtime": 1.9731,
420
+ "eval_samples_per_second": 79.063,
421
+ "eval_steps_per_second": 4.055,
422
+ "step": 1350
423
+ },
424
+ {
425
+ "epoch": 1.4,
426
+ "grad_norm": 2.2424511909484863,
427
+ "learning_rate": 1.6427876096865394e-05,
428
+ "loss": 0.3759,
429
+ "step": 1400
430
+ },
431
+ {
432
+ "epoch": 1.4,
433
+ "eval_loss": 0.7788485884666443,
434
+ "eval_runtime": 1.9496,
435
+ "eval_samples_per_second": 80.016,
436
+ "eval_steps_per_second": 4.103,
437
+ "step": 1400
438
+ },
439
+ {
440
+ "epoch": 1.45,
441
+ "grad_norm": 1.8085654973983765,
442
+ "learning_rate": 1.608761429008721e-05,
443
+ "loss": 0.3821,
444
+ "step": 1450
445
+ },
446
+ {
447
+ "epoch": 1.45,
448
+ "eval_loss": 0.791174054145813,
449
+ "eval_runtime": 1.968,
450
+ "eval_samples_per_second": 79.27,
451
+ "eval_steps_per_second": 4.065,
452
+ "step": 1450
453
+ },
454
+ {
455
+ "epoch": 1.5,
456
+ "grad_norm": 2.0668280124664307,
457
+ "learning_rate": 1.573576436351046e-05,
458
+ "loss": 0.3863,
459
+ "step": 1500
460
+ },
461
+ {
462
+ "epoch": 1.5,
463
+ "eval_loss": 0.7752686738967896,
464
+ "eval_runtime": 1.9725,
465
+ "eval_samples_per_second": 79.087,
466
+ "eval_steps_per_second": 4.056,
467
+ "step": 1500
468
+ },
469
+ {
470
+ "epoch": 1.55,
471
+ "grad_norm": 2.206247091293335,
472
+ "learning_rate": 1.5372996083468242e-05,
473
+ "loss": 0.388,
474
+ "step": 1550
475
+ },
476
+ {
477
+ "epoch": 1.55,
478
+ "eval_loss": 0.7804670929908752,
479
+ "eval_runtime": 1.9824,
480
+ "eval_samples_per_second": 78.692,
481
+ "eval_steps_per_second": 4.035,
482
+ "step": 1550
483
+ },
484
+ {
485
+ "epoch": 1.6,
486
+ "grad_norm": 2.0638809204101562,
487
+ "learning_rate": 1.5000000000000002e-05,
488
+ "loss": 0.3747,
489
+ "step": 1600
490
+ },
491
+ {
492
+ "epoch": 1.6,
493
+ "eval_loss": 0.7704665660858154,
494
+ "eval_runtime": 1.9518,
495
+ "eval_samples_per_second": 79.928,
496
+ "eval_steps_per_second": 4.099,
497
+ "step": 1600
498
+ },
499
+ {
500
+ "epoch": 1.65,
501
+ "grad_norm": 2.225670337677002,
502
+ "learning_rate": 1.4617486132350343e-05,
503
+ "loss": 0.3843,
504
+ "step": 1650
505
+ },
506
+ {
507
+ "epoch": 1.65,
508
+ "eval_loss": 0.7650146484375,
509
+ "eval_runtime": 1.9688,
510
+ "eval_samples_per_second": 79.235,
511
+ "eval_steps_per_second": 4.063,
512
+ "step": 1650
513
+ },
514
+ {
515
+ "epoch": 1.7,
516
+ "grad_norm": 2.266324043273926,
517
+ "learning_rate": 1.4226182617406996e-05,
518
+ "loss": 0.382,
519
+ "step": 1700
520
+ },
521
+ {
522
+ "epoch": 1.7,
523
+ "eval_loss": 0.7695351839065552,
524
+ "eval_runtime": 1.9796,
525
+ "eval_samples_per_second": 78.804,
526
+ "eval_steps_per_second": 4.041,
527
+ "step": 1700
528
+ },
529
+ {
530
+ "epoch": 1.75,
531
+ "grad_norm": 3.5260887145996094,
532
+ "learning_rate": 1.3826834323650899e-05,
533
+ "loss": 0.3728,
534
+ "step": 1750
535
+ },
536
+ {
537
+ "epoch": 1.75,
538
+ "eval_loss": 0.7620097398757935,
539
+ "eval_runtime": 1.94,
540
+ "eval_samples_per_second": 80.411,
541
+ "eval_steps_per_second": 4.124,
542
+ "step": 1750
543
+ },
544
+ {
545
+ "epoch": 1.8,
546
+ "grad_norm": 2.2748708724975586,
547
+ "learning_rate": 1.342020143325669e-05,
548
+ "loss": 0.3633,
549
+ "step": 1800
550
+ },
551
+ {
552
+ "epoch": 1.8,
553
+ "eval_loss": 0.7597982287406921,
554
+ "eval_runtime": 1.9492,
555
+ "eval_samples_per_second": 80.035,
556
+ "eval_steps_per_second": 4.104,
557
+ "step": 1800
558
+ },
559
+ {
560
+ "epoch": 1.85,
561
+ "grad_norm": 2.0982842445373535,
562
+ "learning_rate": 1.300705799504273e-05,
563
+ "loss": 0.365,
564
+ "step": 1850
565
+ },
566
+ {
567
+ "epoch": 1.85,
568
+ "eval_loss": 0.7562901973724365,
569
+ "eval_runtime": 1.9752,
570
+ "eval_samples_per_second": 78.981,
571
+ "eval_steps_per_second": 4.05,
572
+ "step": 1850
573
+ },
574
+ {
575
+ "epoch": 1.9,
576
+ "grad_norm": 2.122321367263794,
577
+ "learning_rate": 1.2588190451025209e-05,
578
+ "loss": 0.3941,
579
+ "step": 1900
580
+ },
581
+ {
582
+ "epoch": 1.9,
583
+ "eval_loss": 0.7595393061637878,
584
+ "eval_runtime": 3.6677,
585
+ "eval_samples_per_second": 42.533,
586
+ "eval_steps_per_second": 2.181,
587
+ "step": 1900
588
+ },
589
+ {
590
+ "epoch": 1.95,
591
+ "grad_norm": 1.7221115827560425,
592
+ "learning_rate": 1.2164396139381029e-05,
593
+ "loss": 0.3929,
594
+ "step": 1950
595
+ },
596
+ {
597
+ "epoch": 1.95,
598
+ "eval_loss": 0.7426199316978455,
599
+ "eval_runtime": 1.9437,
600
+ "eval_samples_per_second": 80.258,
601
+ "eval_steps_per_second": 4.116,
602
+ "step": 1950
603
+ },
604
+ {
605
+ "epoch": 2.0,
606
+ "grad_norm": 2.285029888153076,
607
+ "learning_rate": 1.1736481776669307e-05,
608
+ "loss": 0.377,
609
+ "step": 2000
610
+ },
611
+ {
612
+ "epoch": 2.0,
613
+ "eval_loss": 0.7527384161949158,
614
+ "eval_runtime": 1.9813,
615
+ "eval_samples_per_second": 78.738,
616
+ "eval_steps_per_second": 4.038,
617
+ "step": 2000
618
+ },
619
+ {
620
+ "epoch": 2.05,
621
+ "grad_norm": 1.6015441417694092,
622
+ "learning_rate": 1.130526192220052e-05,
623
+ "loss": 0.1718,
624
+ "step": 2050
625
+ },
626
+ {
627
+ "epoch": 2.05,
628
+ "eval_loss": 0.8362773060798645,
629
+ "eval_runtime": 1.951,
630
+ "eval_samples_per_second": 79.961,
631
+ "eval_steps_per_second": 4.101,
632
+ "step": 2050
633
+ },
634
+ {
635
+ "epoch": 2.1,
636
+ "grad_norm": 1.6940577030181885,
637
+ "learning_rate": 1.0871557427476585e-05,
638
+ "loss": 0.1756,
639
+ "step": 2100
640
+ },
641
+ {
642
+ "epoch": 2.1,
643
+ "eval_loss": 0.8487461805343628,
644
+ "eval_runtime": 1.9498,
645
+ "eval_samples_per_second": 80.006,
646
+ "eval_steps_per_second": 4.103,
647
+ "step": 2100
648
+ },
649
+ {
650
+ "epoch": 2.15,
651
+ "grad_norm": 2.2040927410125732,
652
+ "learning_rate": 1.0436193873653362e-05,
653
+ "loss": 0.1732,
654
+ "step": 2150
655
+ },
656
+ {
657
+ "epoch": 2.15,
658
+ "eval_loss": 0.8493539094924927,
659
+ "eval_runtime": 1.9411,
660
+ "eval_samples_per_second": 80.366,
661
+ "eval_steps_per_second": 4.121,
662
+ "step": 2150
663
+ },
664
+ {
665
+ "epoch": 2.2,
666
+ "grad_norm": 1.932246446609497,
667
+ "learning_rate": 1e-05,
668
+ "loss": 0.1697,
669
+ "step": 2200
670
+ },
671
+ {
672
+ "epoch": 2.2,
673
+ "eval_loss": 0.8528260588645935,
674
+ "eval_runtime": 1.943,
675
+ "eval_samples_per_second": 80.289,
676
+ "eval_steps_per_second": 4.117,
677
+ "step": 2200
678
+ },
679
+ {
680
+ "epoch": 2.25,
681
+ "grad_norm": 1.6120601892471313,
682
+ "learning_rate": 9.563806126346643e-06,
683
+ "loss": 0.1751,
684
+ "step": 2250
685
+ },
686
+ {
687
+ "epoch": 2.25,
688
+ "eval_loss": 0.8474267721176147,
689
+ "eval_runtime": 1.9441,
690
+ "eval_samples_per_second": 80.244,
691
+ "eval_steps_per_second": 4.115,
692
+ "step": 2250
693
+ },
694
+ {
695
+ "epoch": 2.3,
696
+ "grad_norm": 1.7986987829208374,
697
+ "learning_rate": 9.128442572523418e-06,
698
+ "loss": 0.1823,
699
+ "step": 2300
700
+ },
701
+ {
702
+ "epoch": 2.3,
703
+ "eval_loss": 0.8338098526000977,
704
+ "eval_runtime": 1.9366,
705
+ "eval_samples_per_second": 80.555,
706
+ "eval_steps_per_second": 4.131,
707
+ "step": 2300
708
+ },
709
+ {
710
+ "epoch": 2.35,
711
+ "grad_norm": 1.5987346172332764,
712
+ "learning_rate": 8.694738077799487e-06,
713
+ "loss": 0.1766,
714
+ "step": 2350
715
+ },
716
+ {
717
+ "epoch": 2.35,
718
+ "eval_loss": 0.8440003991127014,
719
+ "eval_runtime": 1.9724,
720
+ "eval_samples_per_second": 79.09,
721
+ "eval_steps_per_second": 4.056,
722
+ "step": 2350
723
+ },
724
+ {
725
+ "epoch": 2.4,
726
+ "grad_norm": 1.1890445947647095,
727
+ "learning_rate": 8.263518223330698e-06,
728
+ "loss": 0.1726,
729
+ "step": 2400
730
+ },
731
+ {
732
+ "epoch": 2.4,
733
+ "eval_loss": 0.8430134654045105,
734
+ "eval_runtime": 1.9429,
735
+ "eval_samples_per_second": 80.292,
736
+ "eval_steps_per_second": 4.118,
737
+ "step": 2400
738
+ },
739
+ {
740
+ "epoch": 2.45,
741
+ "grad_norm": 1.1193804740905762,
742
+ "learning_rate": 7.835603860618973e-06,
743
+ "loss": 0.1801,
744
+ "step": 2450
745
+ },
746
+ {
747
+ "epoch": 2.45,
748
+ "eval_loss": 0.8422533869743347,
749
+ "eval_runtime": 1.9378,
750
+ "eval_samples_per_second": 80.504,
751
+ "eval_steps_per_second": 4.128,
752
+ "step": 2450
753
+ },
754
+ {
755
+ "epoch": 2.5,
756
+ "grad_norm": 1.293116807937622,
757
+ "learning_rate": 7.411809548974792e-06,
758
+ "loss": 0.1738,
759
+ "step": 2500
760
+ },
761
+ {
762
+ "epoch": 2.5,
763
+ "eval_loss": 0.8328295946121216,
764
+ "eval_runtime": 1.9499,
765
+ "eval_samples_per_second": 80.005,
766
+ "eval_steps_per_second": 4.103,
767
+ "step": 2500
768
+ },
769
+ {
770
+ "epoch": 2.55,
771
+ "grad_norm": 1.0970814228057861,
772
+ "learning_rate": 6.992942004957271e-06,
773
+ "loss": 0.1721,
774
+ "step": 2550
775
+ },
776
+ {
777
+ "epoch": 2.55,
778
+ "eval_loss": 0.8437429666519165,
779
+ "eval_runtime": 1.9535,
780
+ "eval_samples_per_second": 79.856,
781
+ "eval_steps_per_second": 4.095,
782
+ "step": 2550
783
+ },
784
+ {
785
+ "epoch": 2.6,
786
+ "grad_norm": 1.5809910297393799,
787
+ "learning_rate": 6.579798566743314e-06,
788
+ "loss": 0.1773,
789
+ "step": 2600
790
+ },
791
+ {
792
+ "epoch": 2.6,
793
+ "eval_loss": 0.8351316452026367,
794
+ "eval_runtime": 1.9853,
795
+ "eval_samples_per_second": 78.576,
796
+ "eval_steps_per_second": 4.03,
797
+ "step": 2600
798
+ },
799
+ {
800
+ "epoch": 2.65,
801
+ "grad_norm": 1.7653720378875732,
802
+ "learning_rate": 6.173165676349103e-06,
803
+ "loss": 0.1716,
804
+ "step": 2650
805
+ },
806
+ {
807
+ "epoch": 2.65,
808
+ "eval_loss": 0.8409612774848938,
809
+ "eval_runtime": 1.9672,
810
+ "eval_samples_per_second": 79.301,
811
+ "eval_steps_per_second": 4.067,
812
+ "step": 2650
813
+ },
814
+ {
815
+ "epoch": 2.7,
816
+ "grad_norm": 2.1679255962371826,
817
+ "learning_rate": 5.773817382593008e-06,
818
+ "loss": 0.1677,
819
+ "step": 2700
820
+ },
821
+ {
822
+ "epoch": 2.7,
823
+ "eval_loss": 0.8521665930747986,
824
+ "eval_runtime": 1.9722,
825
+ "eval_samples_per_second": 79.098,
826
+ "eval_steps_per_second": 4.056,
827
+ "step": 2700
828
+ },
829
+ {
830
+ "epoch": 2.75,
831
+ "grad_norm": 1.1089847087860107,
832
+ "learning_rate": 5.382513867649663e-06,
833
+ "loss": 0.173,
834
+ "step": 2750
835
+ },
836
+ {
837
+ "epoch": 2.75,
838
+ "eval_loss": 0.8496531248092651,
839
+ "eval_runtime": 1.9402,
840
+ "eval_samples_per_second": 80.405,
841
+ "eval_steps_per_second": 4.123,
842
+ "step": 2750
843
+ },
844
+ {
845
+ "epoch": 2.8,
846
+ "grad_norm": 2.194023609161377,
847
+ "learning_rate": 5.000000000000003e-06,
848
+ "loss": 0.1759,
849
+ "step": 2800
850
+ },
851
+ {
852
+ "epoch": 2.8,
853
+ "eval_loss": 0.8479322791099548,
854
+ "eval_runtime": 1.9504,
855
+ "eval_samples_per_second": 79.982,
856
+ "eval_steps_per_second": 4.102,
857
+ "step": 2800
858
+ },
859
+ {
860
+ "epoch": 2.85,
861
+ "grad_norm": 1.9135856628417969,
862
+ "learning_rate": 4.627003916531761e-06,
863
+ "loss": 0.1727,
864
+ "step": 2850
865
+ },
866
+ {
867
+ "epoch": 2.85,
868
+ "eval_loss": 0.8385621309280396,
869
+ "eval_runtime": 1.9425,
870
+ "eval_samples_per_second": 80.31,
871
+ "eval_steps_per_second": 4.118,
872
+ "step": 2850
873
+ },
874
+ {
875
+ "epoch": 2.9,
876
+ "grad_norm": 1.567000389099121,
877
+ "learning_rate": 4.264235636489542e-06,
878
+ "loss": 0.1797,
879
+ "step": 2900
880
+ },
881
+ {
882
+ "epoch": 2.9,
883
+ "eval_loss": 0.8441168069839478,
884
+ "eval_runtime": 1.9451,
885
+ "eval_samples_per_second": 80.2,
886
+ "eval_steps_per_second": 4.113,
887
+ "step": 2900
888
+ },
889
+ {
890
+ "epoch": 2.95,
891
+ "grad_norm": 0.9476852416992188,
892
+ "learning_rate": 3.912385709912794e-06,
893
+ "loss": 0.1692,
894
+ "step": 2950
895
+ },
896
+ {
897
+ "epoch": 2.95,
898
+ "eval_loss": 0.8405532836914062,
899
+ "eval_runtime": 1.9399,
900
+ "eval_samples_per_second": 80.414,
901
+ "eval_steps_per_second": 4.124,
902
+ "step": 2950
903
+ },
904
+ {
905
+ "epoch": 3.0,
906
+ "grad_norm": 1.281925082206726,
907
+ "learning_rate": 3.5721239031346067e-06,
908
+ "loss": 0.1657,
909
+ "step": 3000
910
+ },
911
+ {
912
+ "epoch": 3.0,
913
+ "eval_loss": 0.8360433578491211,
914
+ "eval_runtime": 1.9471,
915
+ "eval_samples_per_second": 80.118,
916
+ "eval_steps_per_second": 4.109,
917
+ "step": 3000
918
+ }
919
+ ],
920
+ "logging_steps": 50,
921
+ "max_steps": 4000,
922
+ "num_input_tokens_seen": 0,
923
+ "num_train_epochs": 4,
924
+ "save_steps": 500,
925
+ "total_flos": 1.1708404112293888e+17,
926
+ "train_batch_size": 1,
927
+ "trial_name": null,
928
+ "trial_params": null
929
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7469b1119efa4b15b4fbf2bab3668338d70242f105b8dfae0c7309d583dc755
3
+ size 5112