Fizzarolli commited on
Commit
e75df7d
·
verified ·
1 Parent(s): 5112a28

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.49.0.dev0",
25
+ "use_cache": false,
26
+ "vocab_size": 131074
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.49.0.dev0"
7
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a131f81d2b31fefbe344c904e613ef8161baee5036a59888d2b0ab523ad165ec
3
+ size 4865542976
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc8c03a07a6ad678ace3707671d9391c89ebcc147964bf6d6b3d0a071848f356
3
+ size 4907529424
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7cbae7db9bfa9e3ff837283af0743df50d9c2629a332b7f345c6d2ab422df3e
3
+ size 4907529456
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c51ae896ed687e8934920f89ea7975f38fa6fdea0f3a5991ce4bfacef572ada
3
+ size 4907529456
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4794b542a546b181bcc7708a04c4c70d278e13cec5abd20cd74fe12e9b228369
3
+ size 4907516752
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24495605760
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
368
+ "model.norm.weight": "model-00005-of-00005.safetensors"
369
+ }
370
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50266a694b211fadd18da664d3eb9b6e28c3fcb41ddb61f6c707e9eb78fe9811
3
+ size 2699193434
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd39330350021889163b2316b2f18deaaaba1303c3b9e423e3590a077ef322ef
3
+ size 1064
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.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a26d19ba141138e260796b82a35d1e4a783d007706820702ba03ec160c3b2efc
3
+ size 17078679
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,1643 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 920,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008695652173913044,
13
+ "grad_norm": 14.8125,
14
+ "learning_rate": 8.000000000000001e-07,
15
+ "loss": 1.8918,
16
+ "step": 4
17
+ },
18
+ {
19
+ "epoch": 0.017391304347826087,
20
+ "grad_norm": 7.8125,
21
+ "learning_rate": 1.6000000000000001e-06,
22
+ "loss": 1.816,
23
+ "step": 8
24
+ },
25
+ {
26
+ "epoch": 0.02608695652173913,
27
+ "grad_norm": 3.171875,
28
+ "learning_rate": 2.4000000000000003e-06,
29
+ "loss": 1.7715,
30
+ "step": 12
31
+ },
32
+ {
33
+ "epoch": 0.034782608695652174,
34
+ "grad_norm": 4.0,
35
+ "learning_rate": 3.2000000000000003e-06,
36
+ "loss": 1.7775,
37
+ "step": 16
38
+ },
39
+ {
40
+ "epoch": 0.043478260869565216,
41
+ "grad_norm": 4.5625,
42
+ "learning_rate": 4.000000000000001e-06,
43
+ "loss": 1.7134,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.05217391304347826,
48
+ "grad_norm": 5.84375,
49
+ "learning_rate": 4.800000000000001e-06,
50
+ "loss": 1.7756,
51
+ "step": 24
52
+ },
53
+ {
54
+ "epoch": 0.06086956521739131,
55
+ "grad_norm": 6.78125,
56
+ "learning_rate": 5.600000000000001e-06,
57
+ "loss": 1.7208,
58
+ "step": 28
59
+ },
60
+ {
61
+ "epoch": 0.06956521739130435,
62
+ "grad_norm": 6.65625,
63
+ "learning_rate": 6.4000000000000006e-06,
64
+ "loss": 1.6998,
65
+ "step": 32
66
+ },
67
+ {
68
+ "epoch": 0.0782608695652174,
69
+ "grad_norm": 8.75,
70
+ "learning_rate": 7.2000000000000005e-06,
71
+ "loss": 1.8301,
72
+ "step": 36
73
+ },
74
+ {
75
+ "epoch": 0.08695652173913043,
76
+ "grad_norm": 7.0625,
77
+ "learning_rate": 8.000000000000001e-06,
78
+ "loss": 1.7552,
79
+ "step": 40
80
+ },
81
+ {
82
+ "epoch": 0.09565217391304348,
83
+ "grad_norm": 4.5625,
84
+ "learning_rate": 8.8e-06,
85
+ "loss": 1.7062,
86
+ "step": 44
87
+ },
88
+ {
89
+ "epoch": 0.10434782608695652,
90
+ "grad_norm": 5.375,
91
+ "learning_rate": 9.600000000000001e-06,
92
+ "loss": 1.7292,
93
+ "step": 48
94
+ },
95
+ {
96
+ "epoch": 0.11304347826086956,
97
+ "grad_norm": 7.53125,
98
+ "learning_rate": 9.999869605476246e-06,
99
+ "loss": 1.8108,
100
+ "step": 52
101
+ },
102
+ {
103
+ "epoch": 0.12173913043478261,
104
+ "grad_norm": 9.125,
105
+ "learning_rate": 9.99882649009242e-06,
106
+ "loss": 1.8255,
107
+ "step": 56
108
+ },
109
+ {
110
+ "epoch": 0.13043478260869565,
111
+ "grad_norm": 6.78125,
112
+ "learning_rate": 9.996740476948386e-06,
113
+ "loss": 1.7476,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.1391304347826087,
118
+ "grad_norm": 7.09375,
119
+ "learning_rate": 9.99361200124597e-06,
120
+ "loss": 1.7619,
121
+ "step": 64
122
+ },
123
+ {
124
+ "epoch": 0.14782608695652175,
125
+ "grad_norm": 4.75,
126
+ "learning_rate": 9.989441715674422e-06,
127
+ "loss": 1.7593,
128
+ "step": 68
129
+ },
130
+ {
131
+ "epoch": 0.1565217391304348,
132
+ "grad_norm": 6.21875,
133
+ "learning_rate": 9.98423049027424e-06,
134
+ "loss": 1.7353,
135
+ "step": 72
136
+ },
137
+ {
138
+ "epoch": 0.16521739130434782,
139
+ "grad_norm": 6.03125,
140
+ "learning_rate": 9.977979412255651e-06,
141
+ "loss": 1.7301,
142
+ "step": 76
143
+ },
144
+ {
145
+ "epoch": 0.17391304347826086,
146
+ "grad_norm": 6.78125,
147
+ "learning_rate": 9.970689785771798e-06,
148
+ "loss": 1.7558,
149
+ "step": 80
150
+ },
151
+ {
152
+ "epoch": 0.1826086956521739,
153
+ "grad_norm": 5.6875,
154
+ "learning_rate": 9.962363131646649e-06,
155
+ "loss": 1.8001,
156
+ "step": 84
157
+ },
158
+ {
159
+ "epoch": 0.19130434782608696,
160
+ "grad_norm": 8.875,
161
+ "learning_rate": 9.953001187057705e-06,
162
+ "loss": 1.751,
163
+ "step": 88
164
+ },
165
+ {
166
+ "epoch": 0.2,
167
+ "grad_norm": 6.3125,
168
+ "learning_rate": 9.942605905173593e-06,
169
+ "loss": 1.7262,
170
+ "step": 92
171
+ },
172
+ {
173
+ "epoch": 0.20869565217391303,
174
+ "grad_norm": 6.28125,
175
+ "learning_rate": 9.931179454746556e-06,
176
+ "loss": 1.8109,
177
+ "step": 96
178
+ },
179
+ {
180
+ "epoch": 0.21739130434782608,
181
+ "grad_norm": 6.46875,
182
+ "learning_rate": 9.918724219660013e-06,
183
+ "loss": 1.9357,
184
+ "step": 100
185
+ },
186
+ {
187
+ "epoch": 0.22608695652173913,
188
+ "grad_norm": 6.25,
189
+ "learning_rate": 9.905242798431196e-06,
190
+ "loss": 1.6968,
191
+ "step": 104
192
+ },
193
+ {
194
+ "epoch": 0.23478260869565218,
195
+ "grad_norm": 7.8125,
196
+ "learning_rate": 9.890738003669029e-06,
197
+ "loss": 1.8129,
198
+ "step": 108
199
+ },
200
+ {
201
+ "epoch": 0.24347826086956523,
202
+ "grad_norm": 5.6875,
203
+ "learning_rate": 9.87521286148734e-06,
204
+ "loss": 1.688,
205
+ "step": 112
206
+ },
207
+ {
208
+ "epoch": 0.25217391304347825,
209
+ "grad_norm": 6.34375,
210
+ "learning_rate": 9.858670610873528e-06,
211
+ "loss": 1.7948,
212
+ "step": 116
213
+ },
214
+ {
215
+ "epoch": 0.2608695652173913,
216
+ "grad_norm": 6.03125,
217
+ "learning_rate": 9.841114703012817e-06,
218
+ "loss": 1.7484,
219
+ "step": 120
220
+ },
221
+ {
222
+ "epoch": 0.26956521739130435,
223
+ "grad_norm": 5.84375,
224
+ "learning_rate": 9.822548800568238e-06,
225
+ "loss": 1.7572,
226
+ "step": 124
227
+ },
228
+ {
229
+ "epoch": 0.2782608695652174,
230
+ "grad_norm": 4.96875,
231
+ "learning_rate": 9.802976776916493e-06,
232
+ "loss": 1.6758,
233
+ "step": 128
234
+ },
235
+ {
236
+ "epoch": 0.28695652173913044,
237
+ "grad_norm": 6.0,
238
+ "learning_rate": 9.782402715339866e-06,
239
+ "loss": 1.7555,
240
+ "step": 132
241
+ },
242
+ {
243
+ "epoch": 0.2956521739130435,
244
+ "grad_norm": 5.75,
245
+ "learning_rate": 9.760830908174323e-06,
246
+ "loss": 1.7926,
247
+ "step": 136
248
+ },
249
+ {
250
+ "epoch": 0.30434782608695654,
251
+ "grad_norm": 5.0625,
252
+ "learning_rate": 9.738265855914014e-06,
253
+ "loss": 1.7392,
254
+ "step": 140
255
+ },
256
+ {
257
+ "epoch": 0.3130434782608696,
258
+ "grad_norm": 6.375,
259
+ "learning_rate": 9.714712266272339e-06,
260
+ "loss": 1.7365,
261
+ "step": 144
262
+ },
263
+ {
264
+ "epoch": 0.3217391304347826,
265
+ "grad_norm": 6.21875,
266
+ "learning_rate": 9.690175053199789e-06,
267
+ "loss": 1.8047,
268
+ "step": 148
269
+ },
270
+ {
271
+ "epoch": 0.33043478260869563,
272
+ "grad_norm": 7.03125,
273
+ "learning_rate": 9.664659335858755e-06,
274
+ "loss": 1.691,
275
+ "step": 152
276
+ },
277
+ {
278
+ "epoch": 0.3391304347826087,
279
+ "grad_norm": 5.8125,
280
+ "learning_rate": 9.63817043755552e-06,
281
+ "loss": 1.635,
282
+ "step": 156
283
+ },
284
+ {
285
+ "epoch": 0.34782608695652173,
286
+ "grad_norm": 12.1875,
287
+ "learning_rate": 9.610713884629667e-06,
288
+ "loss": 1.7294,
289
+ "step": 160
290
+ },
291
+ {
292
+ "epoch": 0.3565217391304348,
293
+ "grad_norm": 7.28125,
294
+ "learning_rate": 9.582295405301131e-06,
295
+ "loss": 1.8021,
296
+ "step": 164
297
+ },
298
+ {
299
+ "epoch": 0.3652173913043478,
300
+ "grad_norm": 6.46875,
301
+ "learning_rate": 9.552920928475127e-06,
302
+ "loss": 1.7255,
303
+ "step": 168
304
+ },
305
+ {
306
+ "epoch": 0.3739130434782609,
307
+ "grad_norm": 4.75,
308
+ "learning_rate": 9.522596582505208e-06,
309
+ "loss": 1.7484,
310
+ "step": 172
311
+ },
312
+ {
313
+ "epoch": 0.3826086956521739,
314
+ "grad_norm": 6.25,
315
+ "learning_rate": 9.491328693914723e-06,
316
+ "loss": 1.8143,
317
+ "step": 176
318
+ },
319
+ {
320
+ "epoch": 0.391304347826087,
321
+ "grad_norm": 3.921875,
322
+ "learning_rate": 9.459123786076911e-06,
323
+ "loss": 1.6716,
324
+ "step": 180
325
+ },
326
+ {
327
+ "epoch": 0.4,
328
+ "grad_norm": 6.71875,
329
+ "learning_rate": 9.425988577853959e-06,
330
+ "loss": 1.8105,
331
+ "step": 184
332
+ },
333
+ {
334
+ "epoch": 0.40869565217391307,
335
+ "grad_norm": 9.375,
336
+ "learning_rate": 9.391929982195233e-06,
337
+ "loss": 1.7907,
338
+ "step": 188
339
+ },
340
+ {
341
+ "epoch": 0.41739130434782606,
342
+ "grad_norm": 3.84375,
343
+ "learning_rate": 9.356955104695057e-06,
344
+ "loss": 1.6777,
345
+ "step": 192
346
+ },
347
+ {
348
+ "epoch": 0.4260869565217391,
349
+ "grad_norm": 5.71875,
350
+ "learning_rate": 9.321071242110275e-06,
351
+ "loss": 1.8068,
352
+ "step": 196
353
+ },
354
+ {
355
+ "epoch": 0.43478260869565216,
356
+ "grad_norm": 5.53125,
357
+ "learning_rate": 9.284285880837947e-06,
358
+ "loss": 1.718,
359
+ "step": 200
360
+ },
361
+ {
362
+ "epoch": 0.4434782608695652,
363
+ "grad_norm": 3.4375,
364
+ "learning_rate": 9.24660669535346e-06,
365
+ "loss": 1.6196,
366
+ "step": 204
367
+ },
368
+ {
369
+ "epoch": 0.45217391304347826,
370
+ "grad_norm": 2.828125,
371
+ "learning_rate": 9.208041546609424e-06,
372
+ "loss": 1.7354,
373
+ "step": 208
374
+ },
375
+ {
376
+ "epoch": 0.4608695652173913,
377
+ "grad_norm": 3.34375,
378
+ "learning_rate": 9.168598480395653e-06,
379
+ "loss": 1.7442,
380
+ "step": 212
381
+ },
382
+ {
383
+ "epoch": 0.46956521739130436,
384
+ "grad_norm": 3.6875,
385
+ "learning_rate": 9.128285725660577e-06,
386
+ "loss": 1.742,
387
+ "step": 216
388
+ },
389
+ {
390
+ "epoch": 0.4782608695652174,
391
+ "grad_norm": 4.125,
392
+ "learning_rate": 9.08711169279446e-06,
393
+ "loss": 1.8496,
394
+ "step": 220
395
+ },
396
+ {
397
+ "epoch": 0.48695652173913045,
398
+ "grad_norm": 3.5625,
399
+ "learning_rate": 9.045084971874738e-06,
400
+ "loss": 1.6437,
401
+ "step": 224
402
+ },
403
+ {
404
+ "epoch": 0.4956521739130435,
405
+ "grad_norm": 4.28125,
406
+ "learning_rate": 9.002214330873895e-06,
407
+ "loss": 1.7723,
408
+ "step": 228
409
+ },
410
+ {
411
+ "epoch": 0.5043478260869565,
412
+ "grad_norm": 2.921875,
413
+ "learning_rate": 8.958508713830212e-06,
414
+ "loss": 1.5517,
415
+ "step": 232
416
+ },
417
+ {
418
+ "epoch": 0.5130434782608696,
419
+ "grad_norm": 6.625,
420
+ "learning_rate": 8.91397723898178e-06,
421
+ "loss": 1.6924,
422
+ "step": 236
423
+ },
424
+ {
425
+ "epoch": 0.5217391304347826,
426
+ "grad_norm": 3.78125,
427
+ "learning_rate": 8.868629196864182e-06,
428
+ "loss": 1.6444,
429
+ "step": 240
430
+ },
431
+ {
432
+ "epoch": 0.5304347826086957,
433
+ "grad_norm": 3.9375,
434
+ "learning_rate": 8.82247404837222e-06,
435
+ "loss": 1.751,
436
+ "step": 244
437
+ },
438
+ {
439
+ "epoch": 0.5391304347826087,
440
+ "grad_norm": 4.28125,
441
+ "learning_rate": 8.775521422786104e-06,
442
+ "loss": 1.8369,
443
+ "step": 248
444
+ },
445
+ {
446
+ "epoch": 0.5478260869565217,
447
+ "grad_norm": 3.6875,
448
+ "learning_rate": 8.727781115762503e-06,
449
+ "loss": 1.7386,
450
+ "step": 252
451
+ },
452
+ {
453
+ "epoch": 0.5565217391304348,
454
+ "grad_norm": 4.46875,
455
+ "learning_rate": 8.679263087290903e-06,
456
+ "loss": 1.8209,
457
+ "step": 256
458
+ },
459
+ {
460
+ "epoch": 0.5652173913043478,
461
+ "grad_norm": 3.953125,
462
+ "learning_rate": 8.629977459615655e-06,
463
+ "loss": 1.7278,
464
+ "step": 260
465
+ },
466
+ {
467
+ "epoch": 0.5739130434782609,
468
+ "grad_norm": 4.53125,
469
+ "learning_rate": 8.579934515124202e-06,
470
+ "loss": 1.7605,
471
+ "step": 264
472
+ },
473
+ {
474
+ "epoch": 0.5826086956521739,
475
+ "grad_norm": 3.640625,
476
+ "learning_rate": 8.529144694201866e-06,
477
+ "loss": 1.6836,
478
+ "step": 268
479
+ },
480
+ {
481
+ "epoch": 0.591304347826087,
482
+ "grad_norm": 3.375,
483
+ "learning_rate": 8.477618593053693e-06,
484
+ "loss": 1.6158,
485
+ "step": 272
486
+ },
487
+ {
488
+ "epoch": 0.6,
489
+ "grad_norm": 4.40625,
490
+ "learning_rate": 8.425366961493784e-06,
491
+ "loss": 1.821,
492
+ "step": 276
493
+ },
494
+ {
495
+ "epoch": 0.6086956521739131,
496
+ "grad_norm": 3.71875,
497
+ "learning_rate": 8.372400700702569e-06,
498
+ "loss": 1.667,
499
+ "step": 280
500
+ },
501
+ {
502
+ "epoch": 0.6173913043478261,
503
+ "grad_norm": 3.734375,
504
+ "learning_rate": 8.318730860952523e-06,
505
+ "loss": 1.7708,
506
+ "step": 284
507
+ },
508
+ {
509
+ "epoch": 0.6260869565217392,
510
+ "grad_norm": 3.5625,
511
+ "learning_rate": 8.264368639302746e-06,
512
+ "loss": 1.6117,
513
+ "step": 288
514
+ },
515
+ {
516
+ "epoch": 0.6347826086956522,
517
+ "grad_norm": 3.609375,
518
+ "learning_rate": 8.209325377262955e-06,
519
+ "loss": 1.7218,
520
+ "step": 292
521
+ },
522
+ {
523
+ "epoch": 0.6434782608695652,
524
+ "grad_norm": 3.578125,
525
+ "learning_rate": 8.153612558427311e-06,
526
+ "loss": 1.775,
527
+ "step": 296
528
+ },
529
+ {
530
+ "epoch": 0.6521739130434783,
531
+ "grad_norm": 3.1875,
532
+ "learning_rate": 8.097241806078616e-06,
533
+ "loss": 1.5923,
534
+ "step": 300
535
+ },
536
+ {
537
+ "epoch": 0.6608695652173913,
538
+ "grad_norm": 3.78125,
539
+ "learning_rate": 8.040224880763368e-06,
540
+ "loss": 1.6577,
541
+ "step": 304
542
+ },
543
+ {
544
+ "epoch": 0.6695652173913044,
545
+ "grad_norm": 4.90625,
546
+ "learning_rate": 7.982573677838172e-06,
547
+ "loss": 1.7276,
548
+ "step": 308
549
+ },
550
+ {
551
+ "epoch": 0.6782608695652174,
552
+ "grad_norm": 3.390625,
553
+ "learning_rate": 7.92430022498803e-06,
554
+ "loss": 1.6829,
555
+ "step": 312
556
+ },
557
+ {
558
+ "epoch": 0.6869565217391305,
559
+ "grad_norm": 3.671875,
560
+ "learning_rate": 7.865416679717025e-06,
561
+ "loss": 1.7478,
562
+ "step": 316
563
+ },
564
+ {
565
+ "epoch": 0.6956521739130435,
566
+ "grad_norm": 3.46875,
567
+ "learning_rate": 7.805935326811913e-06,
568
+ "loss": 1.7896,
569
+ "step": 320
570
+ },
571
+ {
572
+ "epoch": 0.7043478260869566,
573
+ "grad_norm": 3.234375,
574
+ "learning_rate": 7.745868575779176e-06,
575
+ "loss": 1.6258,
576
+ "step": 324
577
+ },
578
+ {
579
+ "epoch": 0.7130434782608696,
580
+ "grad_norm": 3.296875,
581
+ "learning_rate": 7.685228958256036e-06,
582
+ "loss": 1.6437,
583
+ "step": 328
584
+ },
585
+ {
586
+ "epoch": 0.7217391304347827,
587
+ "grad_norm": 3.9375,
588
+ "learning_rate": 7.624029125396004e-06,
589
+ "loss": 1.7755,
590
+ "step": 332
591
+ },
592
+ {
593
+ "epoch": 0.7304347826086957,
594
+ "grad_norm": 3.171875,
595
+ "learning_rate": 7.562281845229483e-06,
596
+ "loss": 1.7433,
597
+ "step": 336
598
+ },
599
+ {
600
+ "epoch": 0.7391304347826086,
601
+ "grad_norm": 3.1875,
602
+ "learning_rate": 7.500000000000001e-06,
603
+ "loss": 1.7589,
604
+ "step": 340
605
+ },
606
+ {
607
+ "epoch": 0.7478260869565218,
608
+ "grad_norm": 3.265625,
609
+ "learning_rate": 7.437196583476597e-06,
610
+ "loss": 1.6831,
611
+ "step": 344
612
+ },
613
+ {
614
+ "epoch": 0.7565217391304347,
615
+ "grad_norm": 3.359375,
616
+ "learning_rate": 7.373884698242959e-06,
617
+ "loss": 1.7514,
618
+ "step": 348
619
+ },
620
+ {
621
+ "epoch": 0.7652173913043478,
622
+ "grad_norm": 3.359375,
623
+ "learning_rate": 7.310077552963849e-06,
624
+ "loss": 1.6971,
625
+ "step": 352
626
+ },
627
+ {
628
+ "epoch": 0.7739130434782608,
629
+ "grad_norm": 3.515625,
630
+ "learning_rate": 7.245788459629397e-06,
631
+ "loss": 1.7533,
632
+ "step": 356
633
+ },
634
+ {
635
+ "epoch": 0.782608695652174,
636
+ "grad_norm": 3.25,
637
+ "learning_rate": 7.181030830777838e-06,
638
+ "loss": 1.6642,
639
+ "step": 360
640
+ },
641
+ {
642
+ "epoch": 0.7913043478260869,
643
+ "grad_norm": 3.453125,
644
+ "learning_rate": 7.115818176697285e-06,
645
+ "loss": 1.7967,
646
+ "step": 364
647
+ },
648
+ {
649
+ "epoch": 0.8,
650
+ "grad_norm": 3.984375,
651
+ "learning_rate": 7.050164102607081e-06,
652
+ "loss": 1.8408,
653
+ "step": 368
654
+ },
655
+ {
656
+ "epoch": 0.808695652173913,
657
+ "grad_norm": 3.015625,
658
+ "learning_rate": 6.984082305819379e-06,
659
+ "loss": 1.5956,
660
+ "step": 372
661
+ },
662
+ {
663
+ "epoch": 0.8173913043478261,
664
+ "grad_norm": 3.078125,
665
+ "learning_rate": 6.9175865728814806e-06,
666
+ "loss": 1.7632,
667
+ "step": 376
668
+ },
669
+ {
670
+ "epoch": 0.8260869565217391,
671
+ "grad_norm": 3.9375,
672
+ "learning_rate": 6.850690776699574e-06,
673
+ "loss": 1.7298,
674
+ "step": 380
675
+ },
676
+ {
677
+ "epoch": 0.8347826086956521,
678
+ "grad_norm": 3.125,
679
+ "learning_rate": 6.7834088736444435e-06,
680
+ "loss": 1.7808,
681
+ "step": 384
682
+ },
683
+ {
684
+ "epoch": 0.8434782608695652,
685
+ "grad_norm": 2.703125,
686
+ "learning_rate": 6.715754900639789e-06,
687
+ "loss": 1.7084,
688
+ "step": 388
689
+ },
690
+ {
691
+ "epoch": 0.8521739130434782,
692
+ "grad_norm": 4.0,
693
+ "learning_rate": 6.647742972233703e-06,
694
+ "loss": 1.8133,
695
+ "step": 392
696
+ },
697
+ {
698
+ "epoch": 0.8608695652173913,
699
+ "grad_norm": 3.40625,
700
+ "learning_rate": 6.579387277653986e-06,
701
+ "loss": 1.7081,
702
+ "step": 396
703
+ },
704
+ {
705
+ "epoch": 0.8695652173913043,
706
+ "grad_norm": 2.953125,
707
+ "learning_rate": 6.510702077847864e-06,
708
+ "loss": 1.8246,
709
+ "step": 400
710
+ },
711
+ {
712
+ "epoch": 0.8782608695652174,
713
+ "grad_norm": 3.015625,
714
+ "learning_rate": 6.441701702506755e-06,
715
+ "loss": 1.6652,
716
+ "step": 404
717
+ },
718
+ {
719
+ "epoch": 0.8869565217391304,
720
+ "grad_norm": 2.78125,
721
+ "learning_rate": 6.372400547076675e-06,
722
+ "loss": 1.7344,
723
+ "step": 408
724
+ },
725
+ {
726
+ "epoch": 0.8956521739130435,
727
+ "grad_norm": 2.9375,
728
+ "learning_rate": 6.302813069754949e-06,
729
+ "loss": 1.7272,
730
+ "step": 412
731
+ },
732
+ {
733
+ "epoch": 0.9043478260869565,
734
+ "grad_norm": 2.9375,
735
+ "learning_rate": 6.2329537884738115e-06,
736
+ "loss": 1.7836,
737
+ "step": 416
738
+ },
739
+ {
740
+ "epoch": 0.9130434782608695,
741
+ "grad_norm": 3.09375,
742
+ "learning_rate": 6.162837277871553e-06,
743
+ "loss": 1.5905,
744
+ "step": 420
745
+ },
746
+ {
747
+ "epoch": 0.9217391304347826,
748
+ "grad_norm": 3.53125,
749
+ "learning_rate": 6.092478166251839e-06,
750
+ "loss": 1.7248,
751
+ "step": 424
752
+ },
753
+ {
754
+ "epoch": 0.9304347826086956,
755
+ "grad_norm": 3.5625,
756
+ "learning_rate": 6.021891132531825e-06,
757
+ "loss": 1.7304,
758
+ "step": 428
759
+ },
760
+ {
761
+ "epoch": 0.9391304347826087,
762
+ "grad_norm": 3.28125,
763
+ "learning_rate": 5.9510909031797135e-06,
764
+ "loss": 1.6762,
765
+ "step": 432
766
+ },
767
+ {
768
+ "epoch": 0.9478260869565217,
769
+ "grad_norm": 3.84375,
770
+ "learning_rate": 5.880092249142401e-06,
771
+ "loss": 1.6284,
772
+ "step": 436
773
+ },
774
+ {
775
+ "epoch": 0.9565217391304348,
776
+ "grad_norm": 2.828125,
777
+ "learning_rate": 5.808909982763825e-06,
778
+ "loss": 1.7868,
779
+ "step": 440
780
+ },
781
+ {
782
+ "epoch": 0.9652173913043478,
783
+ "grad_norm": 3.203125,
784
+ "learning_rate": 5.737558954694698e-06,
785
+ "loss": 1.6698,
786
+ "step": 444
787
+ },
788
+ {
789
+ "epoch": 0.9739130434782609,
790
+ "grad_norm": 3.015625,
791
+ "learning_rate": 5.666054050794234e-06,
792
+ "loss": 1.7537,
793
+ "step": 448
794
+ },
795
+ {
796
+ "epoch": 0.9826086956521739,
797
+ "grad_norm": 2.90625,
798
+ "learning_rate": 5.594410189024533e-06,
799
+ "loss": 1.6714,
800
+ "step": 452
801
+ },
802
+ {
803
+ "epoch": 0.991304347826087,
804
+ "grad_norm": 6.25,
805
+ "learning_rate": 5.522642316338268e-06,
806
+ "loss": 1.7342,
807
+ "step": 456
808
+ },
809
+ {
810
+ "epoch": 1.0,
811
+ "grad_norm": 2.53125,
812
+ "learning_rate": 5.450765405560328e-06,
813
+ "loss": 1.7088,
814
+ "step": 460
815
+ },
816
+ {
817
+ "epoch": 1.008695652173913,
818
+ "grad_norm": 2.875,
819
+ "learning_rate": 5.378794452264053e-06,
820
+ "loss": 1.6256,
821
+ "step": 464
822
+ },
823
+ {
824
+ "epoch": 1.017391304347826,
825
+ "grad_norm": 3.46875,
826
+ "learning_rate": 5.30674447164274e-06,
827
+ "loss": 1.7419,
828
+ "step": 468
829
+ },
830
+ {
831
+ "epoch": 1.0260869565217392,
832
+ "grad_norm": 3.109375,
833
+ "learning_rate": 5.234630495377035e-06,
834
+ "loss": 1.6345,
835
+ "step": 472
836
+ },
837
+ {
838
+ "epoch": 1.0347826086956522,
839
+ "grad_norm": 2.609375,
840
+ "learning_rate": 5.1624675684989035e-06,
841
+ "loss": 1.668,
842
+ "step": 476
843
+ },
844
+ {
845
+ "epoch": 1.0434782608695652,
846
+ "grad_norm": 3.03125,
847
+ "learning_rate": 5.090270746252803e-06,
848
+ "loss": 1.8276,
849
+ "step": 480
850
+ },
851
+ {
852
+ "epoch": 1.0521739130434782,
853
+ "grad_norm": 2.859375,
854
+ "learning_rate": 5.018055090954733e-06,
855
+ "loss": 1.6851,
856
+ "step": 484
857
+ },
858
+ {
859
+ "epoch": 1.0608695652173914,
860
+ "grad_norm": 2.875,
861
+ "learning_rate": 4.945835668849801e-06,
862
+ "loss": 1.7474,
863
+ "step": 488
864
+ },
865
+ {
866
+ "epoch": 1.0695652173913044,
867
+ "grad_norm": 2.96875,
868
+ "learning_rate": 4.873627546968983e-06,
869
+ "loss": 1.7416,
870
+ "step": 492
871
+ },
872
+ {
873
+ "epoch": 1.0782608695652174,
874
+ "grad_norm": 3.421875,
875
+ "learning_rate": 4.801445789985703e-06,
876
+ "loss": 1.6386,
877
+ "step": 496
878
+ },
879
+ {
880
+ "epoch": 1.0869565217391304,
881
+ "grad_norm": 2.84375,
882
+ "learning_rate": 4.729305457072913e-06,
883
+ "loss": 1.6194,
884
+ "step": 500
885
+ },
886
+ {
887
+ "epoch": 1.0956521739130434,
888
+ "grad_norm": 2.546875,
889
+ "learning_rate": 4.657221598761329e-06,
890
+ "loss": 1.6924,
891
+ "step": 504
892
+ },
893
+ {
894
+ "epoch": 1.1043478260869566,
895
+ "grad_norm": 3.109375,
896
+ "learning_rate": 4.585209253799451e-06,
897
+ "loss": 1.6767,
898
+ "step": 508
899
+ },
900
+ {
901
+ "epoch": 1.1130434782608696,
902
+ "grad_norm": 3.046875,
903
+ "learning_rate": 4.513283446016052e-06,
904
+ "loss": 1.7603,
905
+ "step": 512
906
+ },
907
+ {
908
+ "epoch": 1.1217391304347826,
909
+ "grad_norm": 2.46875,
910
+ "learning_rate": 4.441459181185786e-06,
911
+ "loss": 1.758,
912
+ "step": 516
913
+ },
914
+ {
915
+ "epoch": 1.1304347826086956,
916
+ "grad_norm": 2.859375,
917
+ "learning_rate": 4.369751443898554e-06,
918
+ "loss": 1.6899,
919
+ "step": 520
920
+ },
921
+ {
922
+ "epoch": 1.1391304347826088,
923
+ "grad_norm": 2.875,
924
+ "learning_rate": 4.298175194433279e-06,
925
+ "loss": 1.7596,
926
+ "step": 524
927
+ },
928
+ {
929
+ "epoch": 1.1478260869565218,
930
+ "grad_norm": 2.984375,
931
+ "learning_rate": 4.226745365636783e-06,
932
+ "loss": 1.7741,
933
+ "step": 528
934
+ },
935
+ {
936
+ "epoch": 1.1565217391304348,
937
+ "grad_norm": 2.71875,
938
+ "learning_rate": 4.155476859808356e-06,
939
+ "loss": 1.7412,
940
+ "step": 532
941
+ },
942
+ {
943
+ "epoch": 1.1652173913043478,
944
+ "grad_norm": 2.78125,
945
+ "learning_rate": 4.0843845455907195e-06,
946
+ "loss": 1.7079,
947
+ "step": 536
948
+ },
949
+ {
950
+ "epoch": 1.1739130434782608,
951
+ "grad_norm": 3.03125,
952
+ "learning_rate": 4.013483254868001e-06,
953
+ "loss": 1.6852,
954
+ "step": 540
955
+ },
956
+ {
957
+ "epoch": 1.182608695652174,
958
+ "grad_norm": 3.0,
959
+ "learning_rate": 3.942787779671376e-06,
960
+ "loss": 1.781,
961
+ "step": 544
962
+ },
963
+ {
964
+ "epoch": 1.191304347826087,
965
+ "grad_norm": 3.25,
966
+ "learning_rate": 3.87231286909303e-06,
967
+ "loss": 1.64,
968
+ "step": 548
969
+ },
970
+ {
971
+ "epoch": 1.2,
972
+ "grad_norm": 2.671875,
973
+ "learning_rate": 3.8020732262090876e-06,
974
+ "loss": 1.5995,
975
+ "step": 552
976
+ },
977
+ {
978
+ "epoch": 1.208695652173913,
979
+ "grad_norm": 2.875,
980
+ "learning_rate": 3.732083505012118e-06,
981
+ "loss": 1.5924,
982
+ "step": 556
983
+ },
984
+ {
985
+ "epoch": 1.2173913043478262,
986
+ "grad_norm": 2.671875,
987
+ "learning_rate": 3.662358307353897e-06,
988
+ "loss": 1.5588,
989
+ "step": 560
990
+ },
991
+ {
992
+ "epoch": 1.2260869565217392,
993
+ "grad_norm": 2.59375,
994
+ "learning_rate": 3.5929121798990494e-06,
995
+ "loss": 1.6359,
996
+ "step": 564
997
+ },
998
+ {
999
+ "epoch": 1.2347826086956522,
1000
+ "grad_norm": 2.6875,
1001
+ "learning_rate": 3.5237596110902007e-06,
1002
+ "loss": 1.6286,
1003
+ "step": 568
1004
+ },
1005
+ {
1006
+ "epoch": 1.2434782608695651,
1007
+ "grad_norm": 2.21875,
1008
+ "learning_rate": 3.4549150281252635e-06,
1009
+ "loss": 1.7253,
1010
+ "step": 572
1011
+ },
1012
+ {
1013
+ "epoch": 1.2521739130434781,
1014
+ "grad_norm": 2.71875,
1015
+ "learning_rate": 3.3863927939475274e-06,
1016
+ "loss": 1.8196,
1017
+ "step": 576
1018
+ },
1019
+ {
1020
+ "epoch": 1.2608695652173914,
1021
+ "grad_norm": 2.59375,
1022
+ "learning_rate": 3.3182072042491244e-06,
1023
+ "loss": 1.8091,
1024
+ "step": 580
1025
+ },
1026
+ {
1027
+ "epoch": 1.2695652173913043,
1028
+ "grad_norm": 2.53125,
1029
+ "learning_rate": 3.250372484488558e-06,
1030
+ "loss": 1.772,
1031
+ "step": 584
1032
+ },
1033
+ {
1034
+ "epoch": 1.2782608695652173,
1035
+ "grad_norm": 2.8125,
1036
+ "learning_rate": 3.1829027869228506e-06,
1037
+ "loss": 1.6914,
1038
+ "step": 588
1039
+ },
1040
+ {
1041
+ "epoch": 1.2869565217391306,
1042
+ "grad_norm": 2.671875,
1043
+ "learning_rate": 3.1158121876549853e-06,
1044
+ "loss": 1.8261,
1045
+ "step": 592
1046
+ },
1047
+ {
1048
+ "epoch": 1.2956521739130435,
1049
+ "grad_norm": 2.671875,
1050
+ "learning_rate": 3.0491146836972273e-06,
1051
+ "loss": 1.712,
1052
+ "step": 596
1053
+ },
1054
+ {
1055
+ "epoch": 1.3043478260869565,
1056
+ "grad_norm": 2.609375,
1057
+ "learning_rate": 2.982824190050958e-06,
1058
+ "loss": 1.7076,
1059
+ "step": 600
1060
+ },
1061
+ {
1062
+ "epoch": 1.3130434782608695,
1063
+ "grad_norm": 1.9609375,
1064
+ "learning_rate": 2.9169545368035933e-06,
1065
+ "loss": 1.6249,
1066
+ "step": 604
1067
+ },
1068
+ {
1069
+ "epoch": 1.3217391304347825,
1070
+ "grad_norm": 2.265625,
1071
+ "learning_rate": 2.8515194662432423e-06,
1072
+ "loss": 1.6602,
1073
+ "step": 608
1074
+ },
1075
+ {
1076
+ "epoch": 1.3304347826086955,
1077
+ "grad_norm": 2.3125,
1078
+ "learning_rate": 2.7865326299916736e-06,
1079
+ "loss": 1.72,
1080
+ "step": 612
1081
+ },
1082
+ {
1083
+ "epoch": 1.3391304347826087,
1084
+ "grad_norm": 1.8828125,
1085
+ "learning_rate": 2.7220075861561956e-06,
1086
+ "loss": 1.6759,
1087
+ "step": 616
1088
+ },
1089
+ {
1090
+ "epoch": 1.3478260869565217,
1091
+ "grad_norm": 2.046875,
1092
+ "learning_rate": 2.65795779650105e-06,
1093
+ "loss": 1.8399,
1094
+ "step": 620
1095
+ },
1096
+ {
1097
+ "epoch": 1.3565217391304347,
1098
+ "grad_norm": 1.90625,
1099
+ "learning_rate": 2.5943966236389028e-06,
1100
+ "loss": 1.736,
1101
+ "step": 624
1102
+ },
1103
+ {
1104
+ "epoch": 1.365217391304348,
1105
+ "grad_norm": 2.0625,
1106
+ "learning_rate": 2.5313373282430244e-06,
1107
+ "loss": 1.7337,
1108
+ "step": 628
1109
+ },
1110
+ {
1111
+ "epoch": 1.373913043478261,
1112
+ "grad_norm": 2.15625,
1113
+ "learning_rate": 2.46879306628073e-06,
1114
+ "loss": 1.7536,
1115
+ "step": 632
1116
+ },
1117
+ {
1118
+ "epoch": 1.382608695652174,
1119
+ "grad_norm": 2.015625,
1120
+ "learning_rate": 2.406776886268677e-06,
1121
+ "loss": 1.6754,
1122
+ "step": 636
1123
+ },
1124
+ {
1125
+ "epoch": 1.391304347826087,
1126
+ "grad_norm": 2.015625,
1127
+ "learning_rate": 2.345301726550567e-06,
1128
+ "loss": 1.8216,
1129
+ "step": 640
1130
+ },
1131
+ {
1132
+ "epoch": 1.4,
1133
+ "grad_norm": 1.8515625,
1134
+ "learning_rate": 2.2843804125978356e-06,
1135
+ "loss": 1.6752,
1136
+ "step": 644
1137
+ },
1138
+ {
1139
+ "epoch": 1.4086956521739131,
1140
+ "grad_norm": 2.125,
1141
+ "learning_rate": 2.224025654333905e-06,
1142
+ "loss": 1.7638,
1143
+ "step": 648
1144
+ },
1145
+ {
1146
+ "epoch": 1.4173913043478261,
1147
+ "grad_norm": 1.890625,
1148
+ "learning_rate": 2.1642500434825207e-06,
1149
+ "loss": 1.6406,
1150
+ "step": 652
1151
+ },
1152
+ {
1153
+ "epoch": 1.4260869565217391,
1154
+ "grad_norm": 1.7578125,
1155
+ "learning_rate": 2.105066050940758e-06,
1156
+ "loss": 1.695,
1157
+ "step": 656
1158
+ },
1159
+ {
1160
+ "epoch": 1.434782608695652,
1161
+ "grad_norm": 1.96875,
1162
+ "learning_rate": 2.0464860241772454e-06,
1163
+ "loss": 1.7199,
1164
+ "step": 660
1165
+ },
1166
+ {
1167
+ "epoch": 1.4434782608695653,
1168
+ "grad_norm": 1.8984375,
1169
+ "learning_rate": 1.9885221846561267e-06,
1170
+ "loss": 1.7604,
1171
+ "step": 664
1172
+ },
1173
+ {
1174
+ "epoch": 1.4521739130434783,
1175
+ "grad_norm": 1.8203125,
1176
+ "learning_rate": 1.931186625287313e-06,
1177
+ "loss": 1.592,
1178
+ "step": 668
1179
+ },
1180
+ {
1181
+ "epoch": 1.4608695652173913,
1182
+ "grad_norm": 1.796875,
1183
+ "learning_rate": 1.8744913079035598e-06,
1184
+ "loss": 1.654,
1185
+ "step": 672
1186
+ },
1187
+ {
1188
+ "epoch": 1.4695652173913043,
1189
+ "grad_norm": 1.9609375,
1190
+ "learning_rate": 1.8184480607648863e-06,
1191
+ "loss": 1.6098,
1192
+ "step": 676
1193
+ },
1194
+ {
1195
+ "epoch": 1.4782608695652173,
1196
+ "grad_norm": 1.9140625,
1197
+ "learning_rate": 1.7630685760908623e-06,
1198
+ "loss": 1.6708,
1199
+ "step": 680
1200
+ },
1201
+ {
1202
+ "epoch": 1.4869565217391305,
1203
+ "grad_norm": 2.59375,
1204
+ "learning_rate": 1.7083644076212785e-06,
1205
+ "loss": 1.6816,
1206
+ "step": 684
1207
+ },
1208
+ {
1209
+ "epoch": 1.4956521739130435,
1210
+ "grad_norm": 2.46875,
1211
+ "learning_rate": 1.6543469682057105e-06,
1212
+ "loss": 1.6811,
1213
+ "step": 688
1214
+ },
1215
+ {
1216
+ "epoch": 1.5043478260869565,
1217
+ "grad_norm": 2.015625,
1218
+ "learning_rate": 1.6010275274224607e-06,
1219
+ "loss": 1.7303,
1220
+ "step": 692
1221
+ },
1222
+ {
1223
+ "epoch": 1.5130434782608697,
1224
+ "grad_norm": 1.8046875,
1225
+ "learning_rate": 1.548417209227422e-06,
1226
+ "loss": 1.7151,
1227
+ "step": 696
1228
+ },
1229
+ {
1230
+ "epoch": 1.5217391304347827,
1231
+ "grad_norm": 1.9453125,
1232
+ "learning_rate": 1.4965269896332884e-06,
1233
+ "loss": 1.6849,
1234
+ "step": 700
1235
+ },
1236
+ {
1237
+ "epoch": 1.5304347826086957,
1238
+ "grad_norm": 2.421875,
1239
+ "learning_rate": 1.4453676944196477e-06,
1240
+ "loss": 1.7114,
1241
+ "step": 704
1242
+ },
1243
+ {
1244
+ "epoch": 1.5391304347826087,
1245
+ "grad_norm": 3.015625,
1246
+ "learning_rate": 1.3949499968744208e-06,
1247
+ "loss": 1.7589,
1248
+ "step": 708
1249
+ },
1250
+ {
1251
+ "epoch": 1.5478260869565217,
1252
+ "grad_norm": 1.890625,
1253
+ "learning_rate": 1.3452844155671052e-06,
1254
+ "loss": 1.6126,
1255
+ "step": 712
1256
+ },
1257
+ {
1258
+ "epoch": 1.5565217391304347,
1259
+ "grad_norm": 1.8203125,
1260
+ "learning_rate": 1.296381312154305e-06,
1261
+ "loss": 1.7336,
1262
+ "step": 716
1263
+ },
1264
+ {
1265
+ "epoch": 1.5652173913043477,
1266
+ "grad_norm": 1.890625,
1267
+ "learning_rate": 1.2482508892179884e-06,
1268
+ "loss": 1.7618,
1269
+ "step": 720
1270
+ },
1271
+ {
1272
+ "epoch": 1.5739130434782609,
1273
+ "grad_norm": 1.75,
1274
+ "learning_rate": 1.2009031881369431e-06,
1275
+ "loss": 1.7413,
1276
+ "step": 724
1277
+ },
1278
+ {
1279
+ "epoch": 1.5826086956521739,
1280
+ "grad_norm": 1.8046875,
1281
+ "learning_rate": 1.1543480869918555e-06,
1282
+ "loss": 1.6844,
1283
+ "step": 728
1284
+ },
1285
+ {
1286
+ "epoch": 1.591304347826087,
1287
+ "grad_norm": 1.921875,
1288
+ "learning_rate": 1.1085952985044636e-06,
1289
+ "loss": 1.7543,
1290
+ "step": 732
1291
+ },
1292
+ {
1293
+ "epoch": 1.6,
1294
+ "grad_norm": 1.9453125,
1295
+ "learning_rate": 1.0636543680112043e-06,
1296
+ "loss": 1.7416,
1297
+ "step": 736
1298
+ },
1299
+ {
1300
+ "epoch": 1.608695652173913,
1301
+ "grad_norm": 1.8203125,
1302
+ "learning_rate": 1.0195346714717813e-06,
1303
+ "loss": 1.6915,
1304
+ "step": 740
1305
+ },
1306
+ {
1307
+ "epoch": 1.617391304347826,
1308
+ "grad_norm": 1.8828125,
1309
+ "learning_rate": 9.762454135130828e-07,
1310
+ "loss": 1.6498,
1311
+ "step": 744
1312
+ },
1313
+ {
1314
+ "epoch": 1.626086956521739,
1315
+ "grad_norm": 2.421875,
1316
+ "learning_rate": 9.337956255088238e-07,
1317
+ "loss": 1.7677,
1318
+ "step": 748
1319
+ },
1320
+ {
1321
+ "epoch": 1.634782608695652,
1322
+ "grad_norm": 1.984375,
1323
+ "learning_rate": 8.921941636953435e-07,
1324
+ "loss": 1.7559,
1325
+ "step": 752
1326
+ },
1327
+ {
1328
+ "epoch": 1.643478260869565,
1329
+ "grad_norm": 1.7890625,
1330
+ "learning_rate": 8.514497073239491e-07,
1331
+ "loss": 1.8024,
1332
+ "step": 756
1333
+ },
1334
+ {
1335
+ "epoch": 1.6521739130434783,
1336
+ "grad_norm": 1.8125,
1337
+ "learning_rate": 8.115707568501768e-07,
1338
+ "loss": 1.7869,
1339
+ "step": 760
1340
+ },
1341
+ {
1342
+ "epoch": 1.6608695652173913,
1343
+ "grad_norm": 1.890625,
1344
+ "learning_rate": 7.725656321603414e-07,
1345
+ "loss": 1.6925,
1346
+ "step": 764
1347
+ },
1348
+ {
1349
+ "epoch": 1.6695652173913045,
1350
+ "grad_norm": 2.859375,
1351
+ "learning_rate": 7.344424708357867e-07,
1352
+ "loss": 1.6703,
1353
+ "step": 768
1354
+ },
1355
+ {
1356
+ "epoch": 1.6782608695652175,
1357
+ "grad_norm": 2.03125,
1358
+ "learning_rate": 6.972092264551439e-07,
1359
+ "loss": 1.745,
1360
+ "step": 772
1361
+ },
1362
+ {
1363
+ "epoch": 1.6869565217391305,
1364
+ "grad_norm": 2.3125,
1365
+ "learning_rate": 6.60873666934993e-07,
1366
+ "loss": 1.714,
1367
+ "step": 776
1368
+ },
1369
+ {
1370
+ "epoch": 1.6956521739130435,
1371
+ "grad_norm": 1.8828125,
1372
+ "learning_rate": 6.254433729092518e-07,
1373
+ "loss": 1.724,
1374
+ "step": 780
1375
+ },
1376
+ {
1377
+ "epoch": 1.7043478260869565,
1378
+ "grad_norm": 1.9375,
1379
+ "learning_rate": 5.909257361476406e-07,
1380
+ "loss": 1.7012,
1381
+ "step": 784
1382
+ },
1383
+ {
1384
+ "epoch": 1.7130434782608694,
1385
+ "grad_norm": 3.65625,
1386
+ "learning_rate": 5.573279580135438e-07,
1387
+ "loss": 1.5692,
1388
+ "step": 788
1389
+ },
1390
+ {
1391
+ "epoch": 1.7217391304347827,
1392
+ "grad_norm": 1.890625,
1393
+ "learning_rate": 5.246570479616103e-07,
1394
+ "loss": 1.753,
1395
+ "step": 792
1396
+ },
1397
+ {
1398
+ "epoch": 1.7304347826086957,
1399
+ "grad_norm": 1.7421875,
1400
+ "learning_rate": 4.929198220753723e-07,
1401
+ "loss": 1.6207,
1402
+ "step": 796
1403
+ },
1404
+ {
1405
+ "epoch": 1.7391304347826086,
1406
+ "grad_norm": 2.171875,
1407
+ "learning_rate": 4.6212290164521554e-07,
1408
+ "loss": 1.7742,
1409
+ "step": 800
1410
+ },
1411
+ {
1412
+ "epoch": 1.7478260869565219,
1413
+ "grad_norm": 1.7734375,
1414
+ "learning_rate": 4.322727117869951e-07,
1415
+ "loss": 1.832,
1416
+ "step": 804
1417
+ },
1418
+ {
1419
+ "epoch": 1.7565217391304349,
1420
+ "grad_norm": 1.9609375,
1421
+ "learning_rate": 4.0337548010157324e-07,
1422
+ "loss": 1.7819,
1423
+ "step": 808
1424
+ },
1425
+ {
1426
+ "epoch": 1.7652173913043478,
1427
+ "grad_norm": 2.5,
1428
+ "learning_rate": 3.754372353755559e-07,
1429
+ "loss": 1.6899,
1430
+ "step": 812
1431
+ },
1432
+ {
1433
+ "epoch": 1.7739130434782608,
1434
+ "grad_norm": 2.0,
1435
+ "learning_rate": 3.4846380632352463e-07,
1436
+ "loss": 1.7287,
1437
+ "step": 816
1438
+ },
1439
+ {
1440
+ "epoch": 1.7826086956521738,
1441
+ "grad_norm": 1.8359375,
1442
+ "learning_rate": 3.224608203719953e-07,
1443
+ "loss": 1.7088,
1444
+ "step": 820
1445
+ },
1446
+ {
1447
+ "epoch": 1.7913043478260868,
1448
+ "grad_norm": 1.8984375,
1449
+ "learning_rate": 2.974337024853802e-07,
1450
+ "loss": 1.7639,
1451
+ "step": 824
1452
+ },
1453
+ {
1454
+ "epoch": 1.8,
1455
+ "grad_norm": 1.90625,
1456
+ "learning_rate": 2.733876740341829e-07,
1457
+ "loss": 1.787,
1458
+ "step": 828
1459
+ },
1460
+ {
1461
+ "epoch": 1.808695652173913,
1462
+ "grad_norm": 1.8125,
1463
+ "learning_rate": 2.5032775170567293e-07,
1464
+ "loss": 1.7659,
1465
+ "step": 832
1466
+ },
1467
+ {
1468
+ "epoch": 1.8173913043478263,
1469
+ "grad_norm": 1.8125,
1470
+ "learning_rate": 2.2825874645725942e-07,
1471
+ "loss": 1.7699,
1472
+ "step": 836
1473
+ },
1474
+ {
1475
+ "epoch": 1.8260869565217392,
1476
+ "grad_norm": 2.625,
1477
+ "learning_rate": 2.0718526251279346e-07,
1478
+ "loss": 1.7371,
1479
+ "step": 840
1480
+ },
1481
+ {
1482
+ "epoch": 1.8347826086956522,
1483
+ "grad_norm": 2.046875,
1484
+ "learning_rate": 1.871116964019898e-07,
1485
+ "loss": 1.7021,
1486
+ "step": 844
1487
+ },
1488
+ {
1489
+ "epoch": 1.8434782608695652,
1490
+ "grad_norm": 1.9765625,
1491
+ "learning_rate": 1.6804223604318825e-07,
1492
+ "loss": 1.69,
1493
+ "step": 848
1494
+ },
1495
+ {
1496
+ "epoch": 1.8521739130434782,
1497
+ "grad_norm": 1.8671875,
1498
+ "learning_rate": 1.4998085986963283e-07,
1499
+ "loss": 1.639,
1500
+ "step": 852
1501
+ },
1502
+ {
1503
+ "epoch": 1.8608695652173912,
1504
+ "grad_norm": 2.0,
1505
+ "learning_rate": 1.329313359994633e-07,
1506
+ "loss": 1.7022,
1507
+ "step": 856
1508
+ },
1509
+ {
1510
+ "epoch": 1.8695652173913042,
1511
+ "grad_norm": 1.828125,
1512
+ "learning_rate": 1.1689722144956672e-07,
1513
+ "loss": 1.695,
1514
+ "step": 860
1515
+ },
1516
+ {
1517
+ "epoch": 1.8782608695652174,
1518
+ "grad_norm": 1.859375,
1519
+ "learning_rate": 1.0188186139349355e-07,
1520
+ "loss": 1.7447,
1521
+ "step": 864
1522
+ },
1523
+ {
1524
+ "epoch": 1.8869565217391304,
1525
+ "grad_norm": 1.78125,
1526
+ "learning_rate": 8.788838846355341e-08,
1527
+ "loss": 1.7429,
1528
+ "step": 868
1529
+ },
1530
+ {
1531
+ "epoch": 1.8956521739130436,
1532
+ "grad_norm": 2.6875,
1533
+ "learning_rate": 7.491972209725807e-08,
1534
+ "loss": 1.7296,
1535
+ "step": 872
1536
+ },
1537
+ {
1538
+ "epoch": 1.9043478260869566,
1539
+ "grad_norm": 1.75,
1540
+ "learning_rate": 6.297856792824741e-08,
1541
+ "loss": 1.6088,
1542
+ "step": 876
1543
+ },
1544
+ {
1545
+ "epoch": 1.9130434782608696,
1546
+ "grad_norm": 1.78125,
1547
+ "learning_rate": 5.206741722181385e-08,
1548
+ "loss": 1.6972,
1549
+ "step": 880
1550
+ },
1551
+ {
1552
+ "epoch": 1.9217391304347826,
1553
+ "grad_norm": 1.75,
1554
+ "learning_rate": 4.2188546355153016e-08,
1555
+ "loss": 1.7105,
1556
+ "step": 884
1557
+ },
1558
+ {
1559
+ "epoch": 1.9304347826086956,
1560
+ "grad_norm": 1.8359375,
1561
+ "learning_rate": 3.334401634245033e-08,
1562
+ "loss": 1.6165,
1563
+ "step": 888
1564
+ },
1565
+ {
1566
+ "epoch": 1.9391304347826086,
1567
+ "grad_norm": 1.828125,
1568
+ "learning_rate": 2.5535672404890523e-08,
1569
+ "loss": 1.7325,
1570
+ "step": 892
1571
+ },
1572
+ {
1573
+ "epoch": 1.9478260869565216,
1574
+ "grad_norm": 2.140625,
1575
+ "learning_rate": 1.8765143585693924e-08,
1576
+ "loss": 1.6871,
1577
+ "step": 896
1578
+ },
1579
+ {
1580
+ "epoch": 1.9565217391304348,
1581
+ "grad_norm": 1.828125,
1582
+ "learning_rate": 1.3033842410251074e-08,
1583
+ "loss": 1.7506,
1584
+ "step": 900
1585
+ },
1586
+ {
1587
+ "epoch": 1.9652173913043478,
1588
+ "grad_norm": 1.75,
1589
+ "learning_rate": 8.342964591430137e-09,
1590
+ "loss": 1.6842,
1591
+ "step": 904
1592
+ },
1593
+ {
1594
+ "epoch": 1.973913043478261,
1595
+ "grad_norm": 1.7578125,
1596
+ "learning_rate": 4.69348878011644e-09,
1597
+ "loss": 1.6753,
1598
+ "step": 908
1599
+ },
1600
+ {
1601
+ "epoch": 1.982608695652174,
1602
+ "grad_norm": 2.140625,
1603
+ "learning_rate": 2.0861763610385834e-09,
1604
+ "loss": 1.6069,
1605
+ "step": 912
1606
+ },
1607
+ {
1608
+ "epoch": 1.991304347826087,
1609
+ "grad_norm": 1.890625,
1610
+ "learning_rate": 5.215712939210527e-10,
1611
+ "loss": 1.7117,
1612
+ "step": 916
1613
+ },
1614
+ {
1615
+ "epoch": 2.0,
1616
+ "grad_norm": 2.578125,
1617
+ "learning_rate": 0.0,
1618
+ "loss": 1.7504,
1619
+ "step": 920
1620
+ }
1621
+ ],
1622
+ "logging_steps": 4,
1623
+ "max_steps": 920,
1624
+ "num_input_tokens_seen": 0,
1625
+ "num_train_epochs": 2,
1626
+ "save_steps": 230,
1627
+ "stateful_callbacks": {
1628
+ "TrainerControl": {
1629
+ "args": {
1630
+ "should_epoch_stop": false,
1631
+ "should_evaluate": false,
1632
+ "should_log": false,
1633
+ "should_save": true,
1634
+ "should_training_stop": true
1635
+ },
1636
+ "attributes": {}
1637
+ }
1638
+ },
1639
+ "total_flos": 8.371395096477696e+18,
1640
+ "train_batch_size": 16,
1641
+ "trial_name": null,
1642
+ "trial_params": null
1643
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b1f48258219e0e5bf091a8804b1298f02c2be67a1b0e4b5996a62ae2a4fc17
3
+ size 7032