Minbyul commited on
Commit
09dc97f
1 Parent(s): 4ee7edd
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "selfrag/self_rag_critic",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.34.1",
26
+ "use_cache": true,
27
+ "vocab_size": 32001
28
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.34.1"
10
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4285979d70c6c1e3146d51865e4c67d0f211a935f9a046b49b5f9d3794c009
3
+ size 9877998770
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:318b6e5750e87e840739cc3edbf04445e7d9b4cc74de240aae938c8ca78b2329
3
+ size 9894793766
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec6cd01cfb1e43a53ad66985ad7429fefd00c5a342fb4c4ceff721616dd6826
3
+ size 7181002245
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26953695232
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
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 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "[PAD]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": false,
42
+ "model_max_length": 512,
43
+ "pad_token": "[PAD]",
44
+ "padding_side": "right",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": true
50
+ }
trainer_state.json ADDED
@@ -0,0 +1,490 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.994219653179191,
5
+ "eval_steps": 500,
6
+ "global_step": 777,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 1.9999666208982518e-05,
14
+ "loss": 28.454,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.08,
19
+ "learning_rate": 1.9987985862949325e-05,
20
+ "loss": 8.849,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.12,
25
+ "learning_rate": 1.9959638242644855e-05,
26
+ "loss": 8.2489,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.15,
31
+ "learning_rate": 1.991467065265775e-05,
32
+ "loss": 4.2986,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.19,
37
+ "learning_rate": 1.985315813185629e-05,
38
+ "loss": 4.8588,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.23,
43
+ "learning_rate": 1.9775203328168643e-05,
44
+ "loss": 9.355,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.27,
49
+ "learning_rate": 1.9680936327290924e-05,
50
+ "loss": 5.7211,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.31,
55
+ "learning_rate": 1.957051443560902e-05,
56
+ "loss": 10.0795,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.35,
61
+ "learning_rate": 1.9444121917696335e-05,
62
+ "loss": 3.6404,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.39,
67
+ "learning_rate": 1.930196968882556e-05,
68
+ "loss": 30.7862,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.42,
73
+ "learning_rate": 1.9144294963007542e-05,
74
+ "loss": 6.9002,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.46,
79
+ "learning_rate": 1.8971360857144616e-05,
80
+ "loss": 8.5785,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.5,
85
+ "learning_rate": 1.8783455951958948e-05,
86
+ "loss": 5.644,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.54,
91
+ "learning_rate": 1.8580893810428562e-05,
92
+ "loss": 14.8062,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.58,
97
+ "learning_rate": 1.8364012454534687e-05,
98
+ "loss": 14.919,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.62,
103
+ "learning_rate": 1.813317380119356e-05,
104
+ "loss": 6.5775,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.66,
109
+ "learning_rate": 1.7888763058314016e-05,
110
+ "loss": 6.5815,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.69,
115
+ "learning_rate": 1.763118808198859e-05,
116
+ "loss": 4.1731,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.73,
121
+ "learning_rate": 1.736087869589092e-05,
122
+ "loss": 9.1267,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.77,
127
+ "learning_rate": 1.7078285974015103e-05,
128
+ "loss": 3.9908,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.81,
133
+ "learning_rate": 1.678388148795397e-05,
134
+ "loss": 5.6814,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.85,
139
+ "learning_rate": 1.6478156519972354e-05,
140
+ "loss": 5.0232,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.89,
145
+ "learning_rate": 1.6161621243188528e-05,
146
+ "loss": 3.5724,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.92,
151
+ "learning_rate": 1.5834803870231846e-05,
152
+ "loss": 11.7568,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.96,
157
+ "learning_rate": 1.549824977179731e-05,
158
+ "loss": 5.393,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 1.0,
163
+ "learning_rate": 1.5152520566567873e-05,
164
+ "loss": 6.7241,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 1.04,
169
+ "learning_rate": 1.4798193184023233e-05,
170
+ "loss": 3.7898,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 1.08,
175
+ "learning_rate": 1.4435858901698995e-05,
176
+ "loss": 15.7335,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 1.12,
181
+ "learning_rate": 1.4066122358502772e-05,
182
+ "loss": 2.6745,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 1.16,
187
+ "learning_rate": 1.3689600545733713e-05,
188
+ "loss": 5.8789,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 1.19,
193
+ "learning_rate": 1.330692177748925e-05,
194
+ "loss": 2.7451,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 1.23,
199
+ "learning_rate": 1.2918724642177054e-05,
200
+ "loss": 3.0655,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 1.27,
205
+ "learning_rate": 1.252565693688198e-05,
206
+ "loss": 1.6089,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 1.31,
211
+ "learning_rate": 1.2128374586366159e-05,
212
+ "loss": 9.6673,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 1.35,
217
+ "learning_rate": 1.172754054850619e-05,
218
+ "loss": 1.9807,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 1.39,
223
+ "learning_rate": 1.1323823707993937e-05,
224
+ "loss": 0.7278,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 1.43,
229
+ "learning_rate": 1.091789776014706e-05,
230
+ "loss": 5.7635,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 1.46,
235
+ "learning_rate": 1.0510440086691911e-05,
236
+ "loss": 3.151,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 1.5,
241
+ "learning_rate": 1.0102130625394776e-05,
242
+ "loss": 16.2403,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 1.54,
247
+ "learning_rate": 9.693650735427808e-06,
248
+ "loss": 2.06,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 1.58,
253
+ "learning_rate": 9.285682060362974e-06,
254
+ "loss": 3.2416,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 1.62,
259
+ "learning_rate": 8.878905390691437e-06,
260
+ "loss": 1.7038,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 1.66,
265
+ "learning_rate": 8.473999527766503e-06,
266
+ "loss": 1.4826,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 1.7,
271
+ "learning_rate": 8.071640151065902e-06,
272
+ "loss": 5.8947,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 1.73,
277
+ "learning_rate": 7.672498690663632e-06,
278
+ "loss": 6.4248,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 1.77,
283
+ "learning_rate": 7.277241206792944e-06,
284
+ "loss": 4.6138,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 1.81,
289
+ "learning_rate": 6.886527278370131e-06,
290
+ "loss": 2.0887,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 1.85,
295
+ "learning_rate": 6.501008902333912e-06,
296
+ "loss": 3.9643,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 1.89,
301
+ "learning_rate": 6.121329405637111e-06,
302
+ "loss": 4.3215,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 1.93,
307
+ "learning_rate": 5.748122371706198e-06,
308
+ "loss": 3.4914,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 1.97,
313
+ "learning_rate": 5.382010583160201e-06,
314
+ "loss": 13.7674,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 2.0,
319
+ "learning_rate": 5.0236049825532355e-06,
320
+ "loss": 3.2402,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 2.04,
325
+ "learning_rate": 4.673503652874977e-06,
326
+ "loss": 0.7369,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 2.08,
331
+ "learning_rate": 4.33229081951025e-06,
332
+ "loss": 0.707,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 2.12,
337
+ "learning_rate": 4.000535875323307e-06,
338
+ "loss": 1.7793,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 2.16,
343
+ "learning_rate": 3.6787924304935696e-06,
344
+ "loss": 0.5325,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 2.2,
349
+ "learning_rate": 3.3675973886884506e-06,
350
+ "loss": 0.4873,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 2.24,
355
+ "learning_rate": 3.0674700511149057e-06,
356
+ "loss": 0.3436,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 2.27,
361
+ "learning_rate": 2.7789112499447312e-06,
362
+ "loss": 0.3319,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 2.31,
367
+ "learning_rate": 2.502402512559773e-06,
368
+ "loss": 0.4382,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 2.35,
373
+ "learning_rate": 2.2384052580116465e-06,
374
+ "loss": 0.2655,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 2.39,
379
+ "learning_rate": 1.9873600270368664e-06,
380
+ "loss": 1.3714,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 2.43,
385
+ "learning_rate": 1.749685746912323e-06,
386
+ "loss": 0.1256,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 2.47,
391
+ "learning_rate": 1.52577903237781e-06,
392
+ "loss": 0.2344,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 2.5,
397
+ "learning_rate": 1.3160135237922011e-06,
398
+ "loss": 0.4926,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 2.54,
403
+ "learning_rate": 1.1207392636277502e-06,
404
+ "loss": 0.369,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 2.58,
409
+ "learning_rate": 9.402821123429017e-07,
410
+ "loss": 0.1464,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 2.62,
415
+ "learning_rate": 7.749432046084471e-07,
416
+ "loss": 0.5273,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 2.66,
421
+ "learning_rate": 6.249984467943737e-07,
422
+ "loss": 0.4998,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 2.7,
427
+ "learning_rate": 4.906980565560004e-07,
428
+ "loss": 2.2237,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 2.74,
433
+ "learning_rate": 3.722661452877163e-07,
434
+ "loss": 0.2594,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 2.77,
439
+ "learning_rate": 2.699003441410508e-07,
440
+ "loss": 0.3388,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 2.81,
445
+ "learning_rate": 1.8377147423120467e-07,
446
+ "loss": 0.4497,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 2.85,
451
+ "learning_rate": 1.1402326158234e-07,
452
+ "loss": 0.3246,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 2.89,
457
+ "learning_rate": 6.077209728732492e-08,
458
+ "loss": 2.0268,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 2.93,
463
+ "learning_rate": 2.4106843282165615e-08,
464
+ "loss": 0.1469,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 2.97,
469
+ "learning_rate": 4.088684059220249e-09,
470
+ "loss": 0.5057,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 2.99,
475
+ "step": 777,
476
+ "total_flos": 1.0509820178622054e+17,
477
+ "train_loss": 4.876755037362972,
478
+ "train_runtime": 2316.9087,
479
+ "train_samples_per_second": 21.497,
480
+ "train_steps_per_second": 0.335
481
+ }
482
+ ],
483
+ "logging_steps": 10,
484
+ "max_steps": 777,
485
+ "num_train_epochs": 3,
486
+ "save_steps": 300,
487
+ "total_flos": 1.0509820178622054e+17,
488
+ "trial_name": null,
489
+ "trial_params": null
490
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010b6983f5b136256e0a113af1978de4a0898188569722d3e7a29c9861926681
3
+ size 4283