sedrickkeh commited on
Commit
a11d8c8
·
verified ·
1 Parent(s): 044896e

Training in progress, epoch 0

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
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9d0f7c4fea15e262d1e5a95649b16e3b41457b54c6457ea4803a98a4828f01
3
+ size 4877660776
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af32252cb55c98814f2f8d2248749ed2b289167310ce0afc8bd009fc877dcac
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2869b044d4fff34b2dc5027831829d1e567a004a0fb35c7b64dd09220df45846
3
+ size 4330865200
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234db9e98a1ca15ba4edb31e04f5c31fa8faaf18ad1a69c43dcd6f9667ebf1d9
3
+ size 1089994880
model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,536 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 1560, "loss": 0.5493, "lr": 6.41025641025641e-08, "epoch": 0.00192, "percentage": 0.06, "elapsed_time": "0:00:19", "remaining_time": "8:25:02"}
2
+ {"current_steps": 2, "total_steps": 1560, "loss": 0.5359, "lr": 1.282051282051282e-07, "epoch": 0.00384, "percentage": 0.13, "elapsed_time": "0:00:28", "remaining_time": "6:08:59"}
3
+ {"current_steps": 3, "total_steps": 1560, "loss": 0.5124, "lr": 1.9230769230769234e-07, "epoch": 0.00576, "percentage": 0.19, "elapsed_time": "0:00:37", "remaining_time": "5:23:00"}
4
+ {"current_steps": 4, "total_steps": 1560, "loss": 0.5201, "lr": 2.564102564102564e-07, "epoch": 0.00768, "percentage": 0.26, "elapsed_time": "0:00:46", "remaining_time": "4:59:39"}
5
+ {"current_steps": 5, "total_steps": 1560, "loss": 0.5266, "lr": 3.205128205128205e-07, "epoch": 0.0096, "percentage": 0.32, "elapsed_time": "0:00:55", "remaining_time": "4:45:52"}
6
+ {"current_steps": 6, "total_steps": 1560, "loss": 0.5315, "lr": 3.846153846153847e-07, "epoch": 0.01152, "percentage": 0.38, "elapsed_time": "0:01:04", "remaining_time": "4:36:43"}
7
+ {"current_steps": 7, "total_steps": 1560, "loss": 0.5782, "lr": 4.4871794871794876e-07, "epoch": 0.01344, "percentage": 0.45, "elapsed_time": "0:01:13", "remaining_time": "4:30:03"}
8
+ {"current_steps": 8, "total_steps": 1560, "loss": 0.4984, "lr": 5.128205128205128e-07, "epoch": 0.01536, "percentage": 0.51, "elapsed_time": "0:01:22", "remaining_time": "4:25:08"}
9
+ {"current_steps": 9, "total_steps": 1560, "loss": 0.5174, "lr": 5.76923076923077e-07, "epoch": 0.01728, "percentage": 0.58, "elapsed_time": "0:01:30", "remaining_time": "4:21:12"}
10
+ {"current_steps": 10, "total_steps": 1560, "loss": 0.5407, "lr": 6.41025641025641e-07, "epoch": 0.0192, "percentage": 0.64, "elapsed_time": "0:01:40", "remaining_time": "4:18:49"}
11
+ {"current_steps": 11, "total_steps": 1560, "loss": 0.5321, "lr": 7.051282051282052e-07, "epoch": 0.02112, "percentage": 0.71, "elapsed_time": "0:01:49", "remaining_time": "4:17:03"}
12
+ {"current_steps": 12, "total_steps": 1560, "loss": 0.4483, "lr": 7.692307692307694e-07, "epoch": 0.02304, "percentage": 0.77, "elapsed_time": "0:01:58", "remaining_time": "4:15:28"}
13
+ {"current_steps": 13, "total_steps": 1560, "loss": 0.5007, "lr": 8.333333333333333e-07, "epoch": 0.02496, "percentage": 0.83, "elapsed_time": "0:02:07", "remaining_time": "4:13:50"}
14
+ {"current_steps": 14, "total_steps": 1560, "loss": 0.5853, "lr": 8.974358974358975e-07, "epoch": 0.02688, "percentage": 0.9, "elapsed_time": "0:02:17", "remaining_time": "4:12:30"}
15
+ {"current_steps": 15, "total_steps": 1560, "loss": 0.3934, "lr": 9.615384615384617e-07, "epoch": 0.0288, "percentage": 0.96, "elapsed_time": "0:02:26", "remaining_time": "4:11:21"}
16
+ {"current_steps": 16, "total_steps": 1560, "loss": 0.4438, "lr": 1.0256410256410257e-06, "epoch": 0.03072, "percentage": 1.03, "elapsed_time": "0:02:35", "remaining_time": "4:10:19"}
17
+ {"current_steps": 17, "total_steps": 1560, "loss": 0.4139, "lr": 1.0897435897435899e-06, "epoch": 0.03264, "percentage": 1.09, "elapsed_time": "0:02:44", "remaining_time": "4:09:27"}
18
+ {"current_steps": 18, "total_steps": 1560, "loss": 0.4922, "lr": 1.153846153846154e-06, "epoch": 0.03456, "percentage": 1.15, "elapsed_time": "0:02:54", "remaining_time": "4:08:36"}
19
+ {"current_steps": 19, "total_steps": 1560, "loss": 0.393, "lr": 1.217948717948718e-06, "epoch": 0.03648, "percentage": 1.22, "elapsed_time": "0:03:03", "remaining_time": "4:07:46"}
20
+ {"current_steps": 20, "total_steps": 1560, "loss": 0.4256, "lr": 1.282051282051282e-06, "epoch": 0.0384, "percentage": 1.28, "elapsed_time": "0:03:12", "remaining_time": "4:07:02"}
21
+ {"current_steps": 21, "total_steps": 1560, "loss": 0.455, "lr": 1.3461538461538462e-06, "epoch": 0.04032, "percentage": 1.35, "elapsed_time": "0:03:21", "remaining_time": "4:06:23"}
22
+ {"current_steps": 22, "total_steps": 1560, "loss": 0.4876, "lr": 1.4102564102564104e-06, "epoch": 0.04224, "percentage": 1.41, "elapsed_time": "0:03:30", "remaining_time": "4:05:42"}
23
+ {"current_steps": 23, "total_steps": 1560, "loss": 0.4725, "lr": 1.4743589743589745e-06, "epoch": 0.04416, "percentage": 1.47, "elapsed_time": "0:03:40", "remaining_time": "4:05:07"}
24
+ {"current_steps": 24, "total_steps": 1560, "loss": 0.4131, "lr": 1.5384615384615387e-06, "epoch": 0.04608, "percentage": 1.54, "elapsed_time": "0:03:49", "remaining_time": "4:04:36"}
25
+ {"current_steps": 25, "total_steps": 1560, "loss": 0.4049, "lr": 1.602564102564103e-06, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:03:58", "remaining_time": "4:04:03"}
26
+ {"current_steps": 26, "total_steps": 1560, "loss": 0.4275, "lr": 1.6666666666666667e-06, "epoch": 0.04992, "percentage": 1.67, "elapsed_time": "0:04:07", "remaining_time": "4:03:36"}
27
+ {"current_steps": 27, "total_steps": 1560, "loss": 0.4186, "lr": 1.7307692307692308e-06, "epoch": 0.05184, "percentage": 1.73, "elapsed_time": "0:04:16", "remaining_time": "4:03:09"}
28
+ {"current_steps": 28, "total_steps": 1560, "loss": 0.4181, "lr": 1.794871794871795e-06, "epoch": 0.05376, "percentage": 1.79, "elapsed_time": "0:04:25", "remaining_time": "4:02:30"}
29
+ {"current_steps": 29, "total_steps": 1560, "loss": 0.5068, "lr": 1.8589743589743592e-06, "epoch": 0.05568, "percentage": 1.86, "elapsed_time": "0:04:34", "remaining_time": "4:01:54"}
30
+ {"current_steps": 30, "total_steps": 1560, "loss": 0.4608, "lr": 1.9230769230769234e-06, "epoch": 0.0576, "percentage": 1.92, "elapsed_time": "0:04:43", "remaining_time": "4:01:21"}
31
+ {"current_steps": 31, "total_steps": 1560, "loss": 0.4053, "lr": 1.987179487179487e-06, "epoch": 0.05952, "percentage": 1.99, "elapsed_time": "0:04:52", "remaining_time": "4:00:49"}
32
+ {"current_steps": 32, "total_steps": 1560, "loss": 0.455, "lr": 2.0512820512820513e-06, "epoch": 0.06144, "percentage": 2.05, "elapsed_time": "0:05:01", "remaining_time": "4:00:18"}
33
+ {"current_steps": 33, "total_steps": 1560, "loss": 0.3993, "lr": 2.1153846153846155e-06, "epoch": 0.06336, "percentage": 2.12, "elapsed_time": "0:05:11", "remaining_time": "3:59:51"}
34
+ {"current_steps": 34, "total_steps": 1560, "loss": 0.4102, "lr": 2.1794871794871797e-06, "epoch": 0.06528, "percentage": 2.18, "elapsed_time": "0:05:20", "remaining_time": "3:59:23"}
35
+ {"current_steps": 35, "total_steps": 1560, "loss": 0.4073, "lr": 2.243589743589744e-06, "epoch": 0.0672, "percentage": 2.24, "elapsed_time": "0:05:29", "remaining_time": "3:59:12"}
36
+ {"current_steps": 36, "total_steps": 1560, "loss": 0.3914, "lr": 2.307692307692308e-06, "epoch": 0.06912, "percentage": 2.31, "elapsed_time": "0:05:38", "remaining_time": "3:59:02"}
37
+ {"current_steps": 37, "total_steps": 1560, "loss": 0.4304, "lr": 2.371794871794872e-06, "epoch": 0.07104, "percentage": 2.37, "elapsed_time": "0:05:48", "remaining_time": "3:58:51"}
38
+ {"current_steps": 38, "total_steps": 1560, "loss": 0.3819, "lr": 2.435897435897436e-06, "epoch": 0.07296, "percentage": 2.44, "elapsed_time": "0:05:57", "remaining_time": "3:58:39"}
39
+ {"current_steps": 39, "total_steps": 1560, "loss": 0.3576, "lr": 2.5e-06, "epoch": 0.07488, "percentage": 2.5, "elapsed_time": "0:06:06", "remaining_time": "3:58:28"}
40
+ {"current_steps": 40, "total_steps": 1560, "loss": 0.3762, "lr": 2.564102564102564e-06, "epoch": 0.0768, "percentage": 2.56, "elapsed_time": "0:06:15", "remaining_time": "3:58:06"}
41
+ {"current_steps": 41, "total_steps": 1560, "loss": 0.3585, "lr": 2.6282051282051286e-06, "epoch": 0.07872, "percentage": 2.63, "elapsed_time": "0:06:25", "remaining_time": "3:57:57"}
42
+ {"current_steps": 42, "total_steps": 1560, "loss": 0.3879, "lr": 2.6923076923076923e-06, "epoch": 0.08064, "percentage": 2.69, "elapsed_time": "0:06:34", "remaining_time": "3:57:43"}
43
+ {"current_steps": 43, "total_steps": 1560, "loss": 0.349, "lr": 2.756410256410257e-06, "epoch": 0.08256, "percentage": 2.76, "elapsed_time": "0:06:43", "remaining_time": "3:57:31"}
44
+ {"current_steps": 44, "total_steps": 1560, "loss": 0.4085, "lr": 2.8205128205128207e-06, "epoch": 0.08448, "percentage": 2.82, "elapsed_time": "0:06:53", "remaining_time": "3:57:15"}
45
+ {"current_steps": 45, "total_steps": 1560, "loss": 0.3565, "lr": 2.8846153846153845e-06, "epoch": 0.0864, "percentage": 2.88, "elapsed_time": "0:07:02", "remaining_time": "3:57:02"}
46
+ {"current_steps": 46, "total_steps": 1560, "loss": 0.3814, "lr": 2.948717948717949e-06, "epoch": 0.08832, "percentage": 2.95, "elapsed_time": "0:07:11", "remaining_time": "3:56:49"}
47
+ {"current_steps": 47, "total_steps": 1560, "loss": 0.3918, "lr": 3.012820512820513e-06, "epoch": 0.09024, "percentage": 3.01, "elapsed_time": "0:07:20", "remaining_time": "3:56:29"}
48
+ {"current_steps": 48, "total_steps": 1560, "loss": 0.3505, "lr": 3.0769230769230774e-06, "epoch": 0.09216, "percentage": 3.08, "elapsed_time": "0:07:30", "remaining_time": "3:56:16"}
49
+ {"current_steps": 49, "total_steps": 1560, "loss": 0.4587, "lr": 3.141025641025641e-06, "epoch": 0.09408, "percentage": 3.14, "elapsed_time": "0:07:39", "remaining_time": "3:56:02"}
50
+ {"current_steps": 50, "total_steps": 1560, "loss": 0.3878, "lr": 3.205128205128206e-06, "epoch": 0.096, "percentage": 3.21, "elapsed_time": "0:07:48", "remaining_time": "3:55:47"}
51
+ {"current_steps": 51, "total_steps": 1560, "loss": 0.4149, "lr": 3.2692307692307696e-06, "epoch": 0.09792, "percentage": 3.27, "elapsed_time": "0:07:57", "remaining_time": "3:55:29"}
52
+ {"current_steps": 52, "total_steps": 1560, "loss": 0.3882, "lr": 3.3333333333333333e-06, "epoch": 0.09984, "percentage": 3.33, "elapsed_time": "0:08:06", "remaining_time": "3:55:12"}
53
+ {"current_steps": 53, "total_steps": 1560, "loss": 0.3934, "lr": 3.397435897435898e-06, "epoch": 0.10176, "percentage": 3.4, "elapsed_time": "0:08:15", "remaining_time": "3:54:55"}
54
+ {"current_steps": 54, "total_steps": 1560, "loss": 0.3919, "lr": 3.4615384615384617e-06, "epoch": 0.10368, "percentage": 3.46, "elapsed_time": "0:08:25", "remaining_time": "3:54:46"}
55
+ {"current_steps": 55, "total_steps": 1560, "loss": 0.3899, "lr": 3.5256410256410263e-06, "epoch": 0.1056, "percentage": 3.53, "elapsed_time": "0:08:34", "remaining_time": "3:54:36"}
56
+ {"current_steps": 56, "total_steps": 1560, "loss": 0.4202, "lr": 3.58974358974359e-06, "epoch": 0.10752, "percentage": 3.59, "elapsed_time": "0:08:43", "remaining_time": "3:54:28"}
57
+ {"current_steps": 57, "total_steps": 1560, "loss": 0.4503, "lr": 3.653846153846154e-06, "epoch": 0.10944, "percentage": 3.65, "elapsed_time": "0:08:53", "remaining_time": "3:54:19"}
58
+ {"current_steps": 58, "total_steps": 1560, "loss": 0.3917, "lr": 3.7179487179487184e-06, "epoch": 0.11136, "percentage": 3.72, "elapsed_time": "0:09:02", "remaining_time": "3:54:10"}
59
+ {"current_steps": 59, "total_steps": 1560, "loss": 0.3865, "lr": 3.782051282051282e-06, "epoch": 0.11328, "percentage": 3.78, "elapsed_time": "0:09:11", "remaining_time": "3:53:59"}
60
+ {"current_steps": 60, "total_steps": 1560, "loss": 0.4044, "lr": 3.846153846153847e-06, "epoch": 0.1152, "percentage": 3.85, "elapsed_time": "0:09:21", "remaining_time": "3:53:51"}
61
+ {"current_steps": 61, "total_steps": 1560, "loss": 0.3848, "lr": 3.910256410256411e-06, "epoch": 0.11712, "percentage": 3.91, "elapsed_time": "0:09:30", "remaining_time": "3:53:43"}
62
+ {"current_steps": 62, "total_steps": 1560, "loss": 0.4134, "lr": 3.974358974358974e-06, "epoch": 0.11904, "percentage": 3.97, "elapsed_time": "0:09:39", "remaining_time": "3:53:30"}
63
+ {"current_steps": 63, "total_steps": 1560, "loss": 0.3736, "lr": 4.0384615384615385e-06, "epoch": 0.12096, "percentage": 4.04, "elapsed_time": "0:09:49", "remaining_time": "3:53:18"}
64
+ {"current_steps": 64, "total_steps": 1560, "loss": 0.3907, "lr": 4.102564102564103e-06, "epoch": 0.12288, "percentage": 4.1, "elapsed_time": "0:09:58", "remaining_time": "3:53:06"}
65
+ {"current_steps": 65, "total_steps": 1560, "loss": 0.4155, "lr": 4.166666666666667e-06, "epoch": 0.1248, "percentage": 4.17, "elapsed_time": "0:10:07", "remaining_time": "3:52:55"}
66
+ {"current_steps": 66, "total_steps": 1560, "loss": 0.4125, "lr": 4.230769230769231e-06, "epoch": 0.12672, "percentage": 4.23, "elapsed_time": "0:10:16", "remaining_time": "3:52:44"}
67
+ {"current_steps": 67, "total_steps": 1560, "loss": 0.3752, "lr": 4.294871794871795e-06, "epoch": 0.12864, "percentage": 4.29, "elapsed_time": "0:10:26", "remaining_time": "3:52:34"}
68
+ {"current_steps": 68, "total_steps": 1560, "loss": 0.406, "lr": 4.358974358974359e-06, "epoch": 0.13056, "percentage": 4.36, "elapsed_time": "0:10:35", "remaining_time": "3:52:23"}
69
+ {"current_steps": 69, "total_steps": 1560, "loss": 0.4277, "lr": 4.423076923076924e-06, "epoch": 0.13248, "percentage": 4.42, "elapsed_time": "0:10:44", "remaining_time": "3:52:11"}
70
+ {"current_steps": 70, "total_steps": 1560, "loss": 0.3533, "lr": 4.487179487179488e-06, "epoch": 0.1344, "percentage": 4.49, "elapsed_time": "0:10:53", "remaining_time": "3:51:59"}
71
+ {"current_steps": 71, "total_steps": 1560, "loss": 0.4062, "lr": 4.551282051282052e-06, "epoch": 0.13632, "percentage": 4.55, "elapsed_time": "0:11:04", "remaining_time": "3:52:23"}
72
+ {"current_steps": 72, "total_steps": 1560, "loss": 0.3478, "lr": 4.615384615384616e-06, "epoch": 0.13824, "percentage": 4.62, "elapsed_time": "0:11:14", "remaining_time": "3:52:10"}
73
+ {"current_steps": 73, "total_steps": 1560, "loss": 0.3493, "lr": 4.6794871794871795e-06, "epoch": 0.14016, "percentage": 4.68, "elapsed_time": "0:11:23", "remaining_time": "3:51:57"}
74
+ {"current_steps": 74, "total_steps": 1560, "loss": 0.3708, "lr": 4.743589743589744e-06, "epoch": 0.14208, "percentage": 4.74, "elapsed_time": "0:11:32", "remaining_time": "3:51:46"}
75
+ {"current_steps": 75, "total_steps": 1560, "loss": 0.4064, "lr": 4.807692307692308e-06, "epoch": 0.144, "percentage": 4.81, "elapsed_time": "0:11:41", "remaining_time": "3:51:34"}
76
+ {"current_steps": 76, "total_steps": 1560, "loss": 0.3823, "lr": 4.871794871794872e-06, "epoch": 0.14592, "percentage": 4.87, "elapsed_time": "0:11:50", "remaining_time": "3:51:22"}
77
+ {"current_steps": 77, "total_steps": 1560, "loss": 0.4104, "lr": 4.935897435897436e-06, "epoch": 0.14784, "percentage": 4.94, "elapsed_time": "0:12:00", "remaining_time": "3:51:09"}
78
+ {"current_steps": 78, "total_steps": 1560, "loss": 0.3838, "lr": 5e-06, "epoch": 0.14976, "percentage": 5.0, "elapsed_time": "0:12:09", "remaining_time": "3:50:54"}
79
+ {"current_steps": 79, "total_steps": 1560, "loss": 0.3381, "lr": 5.064102564102565e-06, "epoch": 0.15168, "percentage": 5.06, "elapsed_time": "0:12:18", "remaining_time": "3:50:39"}
80
+ {"current_steps": 80, "total_steps": 1560, "loss": 0.3962, "lr": 5.128205128205128e-06, "epoch": 0.1536, "percentage": 5.13, "elapsed_time": "0:12:27", "remaining_time": "3:50:25"}
81
+ {"current_steps": 81, "total_steps": 1560, "loss": 0.3483, "lr": 5.192307692307693e-06, "epoch": 0.15552, "percentage": 5.19, "elapsed_time": "0:12:36", "remaining_time": "3:50:13"}
82
+ {"current_steps": 82, "total_steps": 1560, "loss": 0.3535, "lr": 5.256410256410257e-06, "epoch": 0.15744, "percentage": 5.26, "elapsed_time": "0:12:45", "remaining_time": "3:50:00"}
83
+ {"current_steps": 83, "total_steps": 1560, "loss": 0.3955, "lr": 5.320512820512821e-06, "epoch": 0.15936, "percentage": 5.32, "elapsed_time": "0:12:54", "remaining_time": "3:49:47"}
84
+ {"current_steps": 84, "total_steps": 1560, "loss": 0.3937, "lr": 5.384615384615385e-06, "epoch": 0.16128, "percentage": 5.38, "elapsed_time": "0:13:03", "remaining_time": "3:49:35"}
85
+ {"current_steps": 85, "total_steps": 1560, "loss": 0.3356, "lr": 5.448717948717949e-06, "epoch": 0.1632, "percentage": 5.45, "elapsed_time": "0:13:13", "remaining_time": "3:49:21"}
86
+ {"current_steps": 86, "total_steps": 1560, "loss": 0.4137, "lr": 5.512820512820514e-06, "epoch": 0.16512, "percentage": 5.51, "elapsed_time": "0:13:22", "remaining_time": "3:49:09"}
87
+ {"current_steps": 87, "total_steps": 1560, "loss": 0.3712, "lr": 5.576923076923077e-06, "epoch": 0.16704, "percentage": 5.58, "elapsed_time": "0:13:31", "remaining_time": "3:48:56"}
88
+ {"current_steps": 88, "total_steps": 1560, "loss": 0.3757, "lr": 5.641025641025641e-06, "epoch": 0.16896, "percentage": 5.64, "elapsed_time": "0:13:40", "remaining_time": "3:48:43"}
89
+ {"current_steps": 89, "total_steps": 1560, "loss": 0.3856, "lr": 5.705128205128206e-06, "epoch": 0.17088, "percentage": 5.71, "elapsed_time": "0:13:49", "remaining_time": "3:48:32"}
90
+ {"current_steps": 90, "total_steps": 1560, "loss": 0.3546, "lr": 5.769230769230769e-06, "epoch": 0.1728, "percentage": 5.77, "elapsed_time": "0:13:58", "remaining_time": "3:48:19"}
91
+ {"current_steps": 91, "total_steps": 1560, "loss": 0.3301, "lr": 5.833333333333334e-06, "epoch": 0.17472, "percentage": 5.83, "elapsed_time": "0:14:07", "remaining_time": "3:48:07"}
92
+ {"current_steps": 92, "total_steps": 1560, "loss": 0.3856, "lr": 5.897435897435898e-06, "epoch": 0.17664, "percentage": 5.9, "elapsed_time": "0:14:16", "remaining_time": "3:47:54"}
93
+ {"current_steps": 93, "total_steps": 1560, "loss": 0.3684, "lr": 5.961538461538462e-06, "epoch": 0.17856, "percentage": 5.96, "elapsed_time": "0:14:25", "remaining_time": "3:47:39"}
94
+ {"current_steps": 94, "total_steps": 1560, "loss": 0.2943, "lr": 6.025641025641026e-06, "epoch": 0.18048, "percentage": 6.03, "elapsed_time": "0:14:34", "remaining_time": "3:47:25"}
95
+ {"current_steps": 95, "total_steps": 1560, "loss": 0.3202, "lr": 6.08974358974359e-06, "epoch": 0.1824, "percentage": 6.09, "elapsed_time": "0:14:43", "remaining_time": "3:47:12"}
96
+ {"current_steps": 96, "total_steps": 1560, "loss": 0.3953, "lr": 6.153846153846155e-06, "epoch": 0.18432, "percentage": 6.15, "elapsed_time": "0:14:53", "remaining_time": "3:47:00"}
97
+ {"current_steps": 97, "total_steps": 1560, "loss": 0.3055, "lr": 6.217948717948718e-06, "epoch": 0.18624, "percentage": 6.22, "elapsed_time": "0:15:02", "remaining_time": "3:46:48"}
98
+ {"current_steps": 98, "total_steps": 1560, "loss": 0.4025, "lr": 6.282051282051282e-06, "epoch": 0.18816, "percentage": 6.28, "elapsed_time": "0:15:11", "remaining_time": "3:46:35"}
99
+ {"current_steps": 99, "total_steps": 1560, "loss": 0.3681, "lr": 6.3461538461538466e-06, "epoch": 0.19008, "percentage": 6.35, "elapsed_time": "0:15:20", "remaining_time": "3:46:20"}
100
+ {"current_steps": 100, "total_steps": 1560, "loss": 0.3443, "lr": 6.410256410256412e-06, "epoch": 0.192, "percentage": 6.41, "elapsed_time": "0:15:29", "remaining_time": "3:46:07"}
101
+ {"current_steps": 101, "total_steps": 1560, "loss": 0.3197, "lr": 6.474358974358975e-06, "epoch": 0.19392, "percentage": 6.47, "elapsed_time": "0:15:38", "remaining_time": "3:45:53"}
102
+ {"current_steps": 102, "total_steps": 1560, "loss": 0.3228, "lr": 6.538461538461539e-06, "epoch": 0.19584, "percentage": 6.54, "elapsed_time": "0:15:47", "remaining_time": "3:45:39"}
103
+ {"current_steps": 103, "total_steps": 1560, "loss": 0.4075, "lr": 6.602564102564103e-06, "epoch": 0.19776, "percentage": 6.6, "elapsed_time": "0:15:56", "remaining_time": "3:45:27"}
104
+ {"current_steps": 104, "total_steps": 1560, "loss": 0.3847, "lr": 6.666666666666667e-06, "epoch": 0.19968, "percentage": 6.67, "elapsed_time": "0:16:05", "remaining_time": "3:45:15"}
105
+ {"current_steps": 105, "total_steps": 1560, "loss": 0.3406, "lr": 6.730769230769232e-06, "epoch": 0.2016, "percentage": 6.73, "elapsed_time": "0:16:14", "remaining_time": "3:45:03"}
106
+ {"current_steps": 106, "total_steps": 1560, "loss": 0.338, "lr": 6.794871794871796e-06, "epoch": 0.20352, "percentage": 6.79, "elapsed_time": "0:16:23", "remaining_time": "3:44:51"}
107
+ {"current_steps": 107, "total_steps": 1560, "loss": 0.3888, "lr": 6.858974358974359e-06, "epoch": 0.20544, "percentage": 6.86, "elapsed_time": "0:16:32", "remaining_time": "3:44:38"}
108
+ {"current_steps": 108, "total_steps": 1560, "loss": 0.3949, "lr": 6.923076923076923e-06, "epoch": 0.20736, "percentage": 6.92, "elapsed_time": "0:16:41", "remaining_time": "3:44:24"}
109
+ {"current_steps": 109, "total_steps": 1560, "loss": 0.3561, "lr": 6.9871794871794876e-06, "epoch": 0.20928, "percentage": 6.99, "elapsed_time": "0:16:50", "remaining_time": "3:44:10"}
110
+ {"current_steps": 110, "total_steps": 1560, "loss": 0.3353, "lr": 7.051282051282053e-06, "epoch": 0.2112, "percentage": 7.05, "elapsed_time": "0:16:59", "remaining_time": "3:43:56"}
111
+ {"current_steps": 111, "total_steps": 1560, "loss": 0.3533, "lr": 7.115384615384616e-06, "epoch": 0.21312, "percentage": 7.12, "elapsed_time": "0:17:08", "remaining_time": "3:43:43"}
112
+ {"current_steps": 112, "total_steps": 1560, "loss": 0.3955, "lr": 7.17948717948718e-06, "epoch": 0.21504, "percentage": 7.18, "elapsed_time": "0:17:17", "remaining_time": "3:43:32"}
113
+ {"current_steps": 113, "total_steps": 1560, "loss": 0.3824, "lr": 7.243589743589744e-06, "epoch": 0.21696, "percentage": 7.24, "elapsed_time": "0:17:26", "remaining_time": "3:43:19"}
114
+ {"current_steps": 114, "total_steps": 1560, "loss": 0.4012, "lr": 7.307692307692308e-06, "epoch": 0.21888, "percentage": 7.31, "elapsed_time": "0:17:35", "remaining_time": "3:43:06"}
115
+ {"current_steps": 115, "total_steps": 1560, "loss": 0.3737, "lr": 7.371794871794873e-06, "epoch": 0.2208, "percentage": 7.37, "elapsed_time": "0:17:44", "remaining_time": "3:42:53"}
116
+ {"current_steps": 116, "total_steps": 1560, "loss": 0.4697, "lr": 7.435897435897437e-06, "epoch": 0.22272, "percentage": 7.44, "elapsed_time": "0:17:53", "remaining_time": "3:42:40"}
117
+ {"current_steps": 117, "total_steps": 1560, "loss": 0.3952, "lr": 7.500000000000001e-06, "epoch": 0.22464, "percentage": 7.5, "elapsed_time": "0:18:02", "remaining_time": "3:42:27"}
118
+ {"current_steps": 118, "total_steps": 1560, "loss": 0.4034, "lr": 7.564102564102564e-06, "epoch": 0.22656, "percentage": 7.56, "elapsed_time": "0:18:11", "remaining_time": "3:42:18"}
119
+ {"current_steps": 119, "total_steps": 1560, "loss": 0.3438, "lr": 7.6282051282051286e-06, "epoch": 0.22848, "percentage": 7.63, "elapsed_time": "0:18:20", "remaining_time": "3:42:08"}
120
+ {"current_steps": 120, "total_steps": 1560, "loss": 0.3902, "lr": 7.692307692307694e-06, "epoch": 0.2304, "percentage": 7.69, "elapsed_time": "0:18:29", "remaining_time": "3:41:59"}
121
+ {"current_steps": 121, "total_steps": 1560, "loss": 0.3516, "lr": 7.756410256410258e-06, "epoch": 0.23232, "percentage": 7.76, "elapsed_time": "0:18:39", "remaining_time": "3:41:49"}
122
+ {"current_steps": 122, "total_steps": 1560, "loss": 0.4017, "lr": 7.820512820512822e-06, "epoch": 0.23424, "percentage": 7.82, "elapsed_time": "0:18:48", "remaining_time": "3:41:41"}
123
+ {"current_steps": 123, "total_steps": 1560, "loss": 0.3661, "lr": 7.884615384615384e-06, "epoch": 0.23616, "percentage": 7.88, "elapsed_time": "0:18:57", "remaining_time": "3:41:30"}
124
+ {"current_steps": 124, "total_steps": 1560, "loss": 0.3761, "lr": 7.948717948717949e-06, "epoch": 0.23808, "percentage": 7.95, "elapsed_time": "0:19:06", "remaining_time": "3:41:20"}
125
+ {"current_steps": 125, "total_steps": 1560, "loss": 0.371, "lr": 8.012820512820515e-06, "epoch": 0.24, "percentage": 8.01, "elapsed_time": "0:19:16", "remaining_time": "3:41:14"}
126
+ {"current_steps": 126, "total_steps": 1560, "loss": 0.3582, "lr": 8.076923076923077e-06, "epoch": 0.24192, "percentage": 8.08, "elapsed_time": "0:19:25", "remaining_time": "3:41:06"}
127
+ {"current_steps": 127, "total_steps": 1560, "loss": 0.345, "lr": 8.141025641025641e-06, "epoch": 0.24384, "percentage": 8.14, "elapsed_time": "0:19:35", "remaining_time": "3:40:58"}
128
+ {"current_steps": 128, "total_steps": 1560, "loss": 0.3742, "lr": 8.205128205128205e-06, "epoch": 0.24576, "percentage": 8.21, "elapsed_time": "0:19:44", "remaining_time": "3:40:51"}
129
+ {"current_steps": 129, "total_steps": 1560, "loss": 0.3421, "lr": 8.26923076923077e-06, "epoch": 0.24768, "percentage": 8.27, "elapsed_time": "0:19:53", "remaining_time": "3:40:43"}
130
+ {"current_steps": 130, "total_steps": 1560, "loss": 0.3806, "lr": 8.333333333333334e-06, "epoch": 0.2496, "percentage": 8.33, "elapsed_time": "0:20:03", "remaining_time": "3:40:35"}
131
+ {"current_steps": 131, "total_steps": 1560, "loss": 0.3748, "lr": 8.397435897435898e-06, "epoch": 0.25152, "percentage": 8.4, "elapsed_time": "0:20:12", "remaining_time": "3:40:26"}
132
+ {"current_steps": 132, "total_steps": 1560, "loss": 0.4747, "lr": 8.461538461538462e-06, "epoch": 0.25344, "percentage": 8.46, "elapsed_time": "0:20:21", "remaining_time": "3:40:18"}
133
+ {"current_steps": 133, "total_steps": 1560, "loss": 0.3586, "lr": 8.525641025641026e-06, "epoch": 0.25536, "percentage": 8.53, "elapsed_time": "0:20:31", "remaining_time": "3:40:10"}
134
+ {"current_steps": 134, "total_steps": 1560, "loss": 0.4203, "lr": 8.58974358974359e-06, "epoch": 0.25728, "percentage": 8.59, "elapsed_time": "0:20:40", "remaining_time": "3:40:01"}
135
+ {"current_steps": 135, "total_steps": 1560, "loss": 0.3596, "lr": 8.653846153846155e-06, "epoch": 0.2592, "percentage": 8.65, "elapsed_time": "0:20:49", "remaining_time": "3:39:53"}
136
+ {"current_steps": 136, "total_steps": 1560, "loss": 0.51, "lr": 8.717948717948719e-06, "epoch": 0.26112, "percentage": 8.72, "elapsed_time": "0:20:59", "remaining_time": "3:39:44"}
137
+ {"current_steps": 137, "total_steps": 1560, "loss": 0.3638, "lr": 8.782051282051283e-06, "epoch": 0.26304, "percentage": 8.78, "elapsed_time": "0:21:08", "remaining_time": "3:39:34"}
138
+ {"current_steps": 138, "total_steps": 1560, "loss": 0.3991, "lr": 8.846153846153847e-06, "epoch": 0.26496, "percentage": 8.85, "elapsed_time": "0:21:17", "remaining_time": "3:39:24"}
139
+ {"current_steps": 139, "total_steps": 1560, "loss": 0.3069, "lr": 8.910256410256411e-06, "epoch": 0.26688, "percentage": 8.91, "elapsed_time": "0:21:26", "remaining_time": "3:39:15"}
140
+ {"current_steps": 140, "total_steps": 1560, "loss": 0.3706, "lr": 8.974358974358976e-06, "epoch": 0.2688, "percentage": 8.97, "elapsed_time": "0:21:36", "remaining_time": "3:39:05"}
141
+ {"current_steps": 141, "total_steps": 1560, "loss": 0.3833, "lr": 9.03846153846154e-06, "epoch": 0.27072, "percentage": 9.04, "elapsed_time": "0:21:45", "remaining_time": "3:38:56"}
142
+ {"current_steps": 142, "total_steps": 1560, "loss": 0.3355, "lr": 9.102564102564104e-06, "epoch": 0.27264, "percentage": 9.1, "elapsed_time": "0:21:54", "remaining_time": "3:38:46"}
143
+ {"current_steps": 143, "total_steps": 1560, "loss": 0.3444, "lr": 9.166666666666666e-06, "epoch": 0.27456, "percentage": 9.17, "elapsed_time": "0:22:03", "remaining_time": "3:38:37"}
144
+ {"current_steps": 144, "total_steps": 1560, "loss": 0.392, "lr": 9.230769230769232e-06, "epoch": 0.27648, "percentage": 9.23, "elapsed_time": "0:22:13", "remaining_time": "3:38:27"}
145
+ {"current_steps": 145, "total_steps": 1560, "loss": 0.4964, "lr": 9.294871794871796e-06, "epoch": 0.2784, "percentage": 9.29, "elapsed_time": "0:22:22", "remaining_time": "3:38:16"}
146
+ {"current_steps": 146, "total_steps": 1560, "loss": 0.4025, "lr": 9.358974358974359e-06, "epoch": 0.28032, "percentage": 9.36, "elapsed_time": "0:22:31", "remaining_time": "3:38:04"}
147
+ {"current_steps": 147, "total_steps": 1560, "loss": 0.3976, "lr": 9.423076923076923e-06, "epoch": 0.28224, "percentage": 9.42, "elapsed_time": "0:22:40", "remaining_time": "3:37:53"}
148
+ {"current_steps": 148, "total_steps": 1560, "loss": 0.3805, "lr": 9.487179487179487e-06, "epoch": 0.28416, "percentage": 9.49, "elapsed_time": "0:22:49", "remaining_time": "3:37:42"}
149
+ {"current_steps": 149, "total_steps": 1560, "loss": 0.376, "lr": 9.551282051282053e-06, "epoch": 0.28608, "percentage": 9.55, "elapsed_time": "0:22:58", "remaining_time": "3:37:31"}
150
+ {"current_steps": 150, "total_steps": 1560, "loss": 0.4057, "lr": 9.615384615384616e-06, "epoch": 0.288, "percentage": 9.62, "elapsed_time": "0:23:07", "remaining_time": "3:37:20"}
151
+ {"current_steps": 151, "total_steps": 1560, "loss": 0.384, "lr": 9.67948717948718e-06, "epoch": 0.28992, "percentage": 9.68, "elapsed_time": "0:23:16", "remaining_time": "3:37:10"}
152
+ {"current_steps": 152, "total_steps": 1560, "loss": 0.3663, "lr": 9.743589743589744e-06, "epoch": 0.29184, "percentage": 9.74, "elapsed_time": "0:23:25", "remaining_time": "3:36:58"}
153
+ {"current_steps": 153, "total_steps": 1560, "loss": 0.4624, "lr": 9.807692307692308e-06, "epoch": 0.29376, "percentage": 9.81, "elapsed_time": "0:23:34", "remaining_time": "3:36:48"}
154
+ {"current_steps": 154, "total_steps": 1560, "loss": 0.355, "lr": 9.871794871794872e-06, "epoch": 0.29568, "percentage": 9.87, "elapsed_time": "0:23:43", "remaining_time": "3:36:37"}
155
+ {"current_steps": 155, "total_steps": 1560, "loss": 0.3462, "lr": 9.935897435897437e-06, "epoch": 0.2976, "percentage": 9.94, "elapsed_time": "0:23:52", "remaining_time": "3:36:26"}
156
+ {"current_steps": 156, "total_steps": 1560, "loss": 0.3602, "lr": 1e-05, "epoch": 0.29952, "percentage": 10.0, "elapsed_time": "0:24:01", "remaining_time": "3:36:15"}
157
+ {"current_steps": 157, "total_steps": 1560, "loss": 0.3357, "lr": 9.999987482852865e-06, "epoch": 0.30144, "percentage": 10.06, "elapsed_time": "0:24:10", "remaining_time": "3:36:03"}
158
+ {"current_steps": 158, "total_steps": 1560, "loss": 0.3705, "lr": 9.99994993147413e-06, "epoch": 0.30336, "percentage": 10.13, "elapsed_time": "0:24:19", "remaining_time": "3:35:51"}
159
+ {"current_steps": 159, "total_steps": 1560, "loss": 0.3738, "lr": 9.99988734605181e-06, "epoch": 0.30528, "percentage": 10.19, "elapsed_time": "0:24:28", "remaining_time": "3:35:38"}
160
+ {"current_steps": 160, "total_steps": 1560, "loss": 0.4117, "lr": 9.999799726899261e-06, "epoch": 0.3072, "percentage": 10.26, "elapsed_time": "0:24:37", "remaining_time": "3:35:27"}
161
+ {"current_steps": 161, "total_steps": 1560, "loss": 0.3629, "lr": 9.999687074455182e-06, "epoch": 0.30912, "percentage": 10.32, "elapsed_time": "0:24:46", "remaining_time": "3:35:15"}
162
+ {"current_steps": 162, "total_steps": 1560, "loss": 0.3889, "lr": 9.999549389283605e-06, "epoch": 0.31104, "percentage": 10.38, "elapsed_time": "0:24:55", "remaining_time": "3:35:04"}
163
+ {"current_steps": 163, "total_steps": 1560, "loss": 0.4319, "lr": 9.999386672073902e-06, "epoch": 0.31296, "percentage": 10.45, "elapsed_time": "0:25:04", "remaining_time": "3:34:53"}
164
+ {"current_steps": 164, "total_steps": 1560, "loss": 0.3416, "lr": 9.999198923640774e-06, "epoch": 0.31488, "percentage": 10.51, "elapsed_time": "0:25:13", "remaining_time": "3:34:42"}
165
+ {"current_steps": 165, "total_steps": 1560, "loss": 0.3828, "lr": 9.998986144924253e-06, "epoch": 0.3168, "percentage": 10.58, "elapsed_time": "0:25:22", "remaining_time": "3:34:31"}
166
+ {"current_steps": 166, "total_steps": 1560, "loss": 0.3372, "lr": 9.998748336989687e-06, "epoch": 0.31872, "percentage": 10.64, "elapsed_time": "0:25:31", "remaining_time": "3:34:19"}
167
+ {"current_steps": 167, "total_steps": 1560, "loss": 0.4141, "lr": 9.998485501027752e-06, "epoch": 0.32064, "percentage": 10.71, "elapsed_time": "0:25:40", "remaining_time": "3:34:08"}
168
+ {"current_steps": 168, "total_steps": 1560, "loss": 0.4076, "lr": 9.998197638354428e-06, "epoch": 0.32256, "percentage": 10.77, "elapsed_time": "0:25:49", "remaining_time": "3:33:57"}
169
+ {"current_steps": 169, "total_steps": 1560, "loss": 0.3889, "lr": 9.997884750411004e-06, "epoch": 0.32448, "percentage": 10.83, "elapsed_time": "0:25:58", "remaining_time": "3:33:46"}
170
+ {"current_steps": 170, "total_steps": 1560, "loss": 0.3734, "lr": 9.997546838764066e-06, "epoch": 0.3264, "percentage": 10.9, "elapsed_time": "0:26:07", "remaining_time": "3:33:35"}
171
+ {"current_steps": 171, "total_steps": 1560, "loss": 0.3454, "lr": 9.997183905105487e-06, "epoch": 0.32832, "percentage": 10.96, "elapsed_time": "0:26:16", "remaining_time": "3:33:24"}
172
+ {"current_steps": 172, "total_steps": 1560, "loss": 0.3476, "lr": 9.996795951252427e-06, "epoch": 0.33024, "percentage": 11.03, "elapsed_time": "0:26:25", "remaining_time": "3:33:13"}
173
+ {"current_steps": 173, "total_steps": 1560, "loss": 0.4322, "lr": 9.996382979147316e-06, "epoch": 0.33216, "percentage": 11.09, "elapsed_time": "0:26:34", "remaining_time": "3:33:02"}
174
+ {"current_steps": 174, "total_steps": 1560, "loss": 0.3639, "lr": 9.995944990857848e-06, "epoch": 0.33408, "percentage": 11.15, "elapsed_time": "0:26:43", "remaining_time": "3:32:51"}
175
+ {"current_steps": 175, "total_steps": 1560, "loss": 0.3756, "lr": 9.995481988576968e-06, "epoch": 0.336, "percentage": 11.22, "elapsed_time": "0:26:52", "remaining_time": "3:32:40"}
176
+ {"current_steps": 176, "total_steps": 1560, "loss": 0.3779, "lr": 9.994993974622863e-06, "epoch": 0.33792, "percentage": 11.28, "elapsed_time": "0:27:01", "remaining_time": "3:32:29"}
177
+ {"current_steps": 177, "total_steps": 1560, "loss": 0.3693, "lr": 9.994480951438948e-06, "epoch": 0.33984, "percentage": 11.35, "elapsed_time": "0:27:10", "remaining_time": "3:32:18"}
178
+ {"current_steps": 178, "total_steps": 1560, "loss": 0.4075, "lr": 9.993942921593858e-06, "epoch": 0.34176, "percentage": 11.41, "elapsed_time": "0:27:19", "remaining_time": "3:32:07"}
179
+ {"current_steps": 179, "total_steps": 1560, "loss": 0.3784, "lr": 9.993379887781436e-06, "epoch": 0.34368, "percentage": 11.47, "elapsed_time": "0:27:28", "remaining_time": "3:31:57"}
180
+ {"current_steps": 180, "total_steps": 1560, "loss": 0.4057, "lr": 9.992791852820709e-06, "epoch": 0.3456, "percentage": 11.54, "elapsed_time": "0:27:37", "remaining_time": "3:31:45"}
181
+ {"current_steps": 181, "total_steps": 1560, "loss": 0.3276, "lr": 9.992178819655889e-06, "epoch": 0.34752, "percentage": 11.6, "elapsed_time": "0:27:46", "remaining_time": "3:31:34"}
182
+ {"current_steps": 182, "total_steps": 1560, "loss": 0.3374, "lr": 9.991540791356342e-06, "epoch": 0.34944, "percentage": 11.67, "elapsed_time": "0:27:55", "remaining_time": "3:31:24"}
183
+ {"current_steps": 183, "total_steps": 1560, "loss": 0.3753, "lr": 9.990877771116588e-06, "epoch": 0.35136, "percentage": 11.73, "elapsed_time": "0:28:04", "remaining_time": "3:31:14"}
184
+ {"current_steps": 184, "total_steps": 1560, "loss": 0.3478, "lr": 9.990189762256275e-06, "epoch": 0.35328, "percentage": 11.79, "elapsed_time": "0:28:13", "remaining_time": "3:31:03"}
185
+ {"current_steps": 185, "total_steps": 1560, "loss": 0.3078, "lr": 9.98947676822017e-06, "epoch": 0.3552, "percentage": 11.86, "elapsed_time": "0:28:22", "remaining_time": "3:30:52"}
186
+ {"current_steps": 186, "total_steps": 1560, "loss": 0.3838, "lr": 9.988738792578126e-06, "epoch": 0.35712, "percentage": 11.92, "elapsed_time": "0:28:31", "remaining_time": "3:30:42"}
187
+ {"current_steps": 187, "total_steps": 1560, "loss": 0.434, "lr": 9.987975839025091e-06, "epoch": 0.35904, "percentage": 11.99, "elapsed_time": "0:28:40", "remaining_time": "3:30:33"}
188
+ {"current_steps": 188, "total_steps": 1560, "loss": 0.3555, "lr": 9.987187911381059e-06, "epoch": 0.36096, "percentage": 12.05, "elapsed_time": "0:28:49", "remaining_time": "3:30:23"}
189
+ {"current_steps": 189, "total_steps": 1560, "loss": 0.4495, "lr": 9.986375013591077e-06, "epoch": 0.36288, "percentage": 12.12, "elapsed_time": "0:28:58", "remaining_time": "3:30:13"}
190
+ {"current_steps": 190, "total_steps": 1560, "loss": 0.3805, "lr": 9.985537149725207e-06, "epoch": 0.3648, "percentage": 12.18, "elapsed_time": "0:29:07", "remaining_time": "3:30:03"}
191
+ {"current_steps": 191, "total_steps": 1560, "loss": 0.4188, "lr": 9.984674323978517e-06, "epoch": 0.36672, "percentage": 12.24, "elapsed_time": "0:29:17", "remaining_time": "3:29:54"}
192
+ {"current_steps": 192, "total_steps": 1560, "loss": 0.3306, "lr": 9.983786540671052e-06, "epoch": 0.36864, "percentage": 12.31, "elapsed_time": "0:29:26", "remaining_time": "3:29:43"}
193
+ {"current_steps": 193, "total_steps": 1560, "loss": 0.4316, "lr": 9.982873804247817e-06, "epoch": 0.37056, "percentage": 12.37, "elapsed_time": "0:29:35", "remaining_time": "3:29:33"}
194
+ {"current_steps": 194, "total_steps": 1560, "loss": 0.3696, "lr": 9.981936119278758e-06, "epoch": 0.37248, "percentage": 12.44, "elapsed_time": "0:29:44", "remaining_time": "3:29:22"}
195
+ {"current_steps": 195, "total_steps": 1560, "loss": 0.3152, "lr": 9.980973490458728e-06, "epoch": 0.3744, "percentage": 12.5, "elapsed_time": "0:29:53", "remaining_time": "3:29:13"}
196
+ {"current_steps": 196, "total_steps": 1560, "loss": 0.4064, "lr": 9.979985922607476e-06, "epoch": 0.37632, "percentage": 12.56, "elapsed_time": "0:30:02", "remaining_time": "3:29:04"}
197
+ {"current_steps": 197, "total_steps": 1560, "loss": 0.3626, "lr": 9.978973420669613e-06, "epoch": 0.37824, "percentage": 12.63, "elapsed_time": "0:30:11", "remaining_time": "3:28:54"}
198
+ {"current_steps": 198, "total_steps": 1560, "loss": 0.3498, "lr": 9.977935989714594e-06, "epoch": 0.38016, "percentage": 12.69, "elapsed_time": "0:30:20", "remaining_time": "3:28:45"}
199
+ {"current_steps": 199, "total_steps": 1560, "loss": 0.3433, "lr": 9.97687363493669e-06, "epoch": 0.38208, "percentage": 12.76, "elapsed_time": "0:30:30", "remaining_time": "3:28:36"}
200
+ {"current_steps": 200, "total_steps": 1560, "loss": 0.4168, "lr": 9.975786361654959e-06, "epoch": 0.384, "percentage": 12.82, "elapsed_time": "0:30:39", "remaining_time": "3:28:26"}
201
+ {"current_steps": 201, "total_steps": 1560, "loss": 0.3813, "lr": 9.974674175313228e-06, "epoch": 0.38592, "percentage": 12.88, "elapsed_time": "0:30:48", "remaining_time": "3:28:17"}
202
+ {"current_steps": 202, "total_steps": 1560, "loss": 0.383, "lr": 9.973537081480056e-06, "epoch": 0.38784, "percentage": 12.95, "elapsed_time": "0:30:57", "remaining_time": "3:28:07"}
203
+ {"current_steps": 203, "total_steps": 1560, "loss": 0.4439, "lr": 9.972375085848712e-06, "epoch": 0.38976, "percentage": 13.01, "elapsed_time": "0:31:06", "remaining_time": "3:27:56"}
204
+ {"current_steps": 204, "total_steps": 1560, "loss": 0.3816, "lr": 9.971188194237141e-06, "epoch": 0.39168, "percentage": 13.08, "elapsed_time": "0:31:15", "remaining_time": "3:27:46"}
205
+ {"current_steps": 205, "total_steps": 1560, "loss": 0.3457, "lr": 9.969976412587943e-06, "epoch": 0.3936, "percentage": 13.14, "elapsed_time": "0:31:24", "remaining_time": "3:27:36"}
206
+ {"current_steps": 206, "total_steps": 1560, "loss": 0.364, "lr": 9.96873974696834e-06, "epoch": 0.39552, "percentage": 13.21, "elapsed_time": "0:31:33", "remaining_time": "3:27:26"}
207
+ {"current_steps": 207, "total_steps": 1560, "loss": 0.4336, "lr": 9.967478203570143e-06, "epoch": 0.39744, "percentage": 13.27, "elapsed_time": "0:31:42", "remaining_time": "3:27:15"}
208
+ {"current_steps": 208, "total_steps": 1560, "loss": 0.3289, "lr": 9.966191788709716e-06, "epoch": 0.39936, "percentage": 13.33, "elapsed_time": "0:31:51", "remaining_time": "3:27:05"}
209
+ {"current_steps": 209, "total_steps": 1560, "loss": 0.4399, "lr": 9.96488050882796e-06, "epoch": 0.40128, "percentage": 13.4, "elapsed_time": "0:32:00", "remaining_time": "3:26:56"}
210
+ {"current_steps": 210, "total_steps": 1560, "loss": 0.3315, "lr": 9.96354437049027e-06, "epoch": 0.4032, "percentage": 13.46, "elapsed_time": "0:32:09", "remaining_time": "3:26:46"}
211
+ {"current_steps": 211, "total_steps": 1560, "loss": 0.3384, "lr": 9.9621833803865e-06, "epoch": 0.40512, "percentage": 13.53, "elapsed_time": "0:32:19", "remaining_time": "3:26:38"}
212
+ {"current_steps": 212, "total_steps": 1560, "loss": 0.4014, "lr": 9.960797545330936e-06, "epoch": 0.40704, "percentage": 13.59, "elapsed_time": "0:32:28", "remaining_time": "3:26:28"}
213
+ {"current_steps": 213, "total_steps": 1560, "loss": 0.4723, "lr": 9.95938687226226e-06, "epoch": 0.40896, "percentage": 13.65, "elapsed_time": "0:32:37", "remaining_time": "3:26:19"}
214
+ {"current_steps": 214, "total_steps": 1560, "loss": 0.4281, "lr": 9.95795136824351e-06, "epoch": 0.41088, "percentage": 13.72, "elapsed_time": "0:32:46", "remaining_time": "3:26:10"}
215
+ {"current_steps": 215, "total_steps": 1560, "loss": 0.3892, "lr": 9.956491040462051e-06, "epoch": 0.4128, "percentage": 13.78, "elapsed_time": "0:32:55", "remaining_time": "3:26:00"}
216
+ {"current_steps": 216, "total_steps": 1560, "loss": 0.4637, "lr": 9.955005896229543e-06, "epoch": 0.41472, "percentage": 13.85, "elapsed_time": "0:33:05", "remaining_time": "3:25:51"}
217
+ {"current_steps": 217, "total_steps": 1560, "loss": 0.3726, "lr": 9.95349594298189e-06, "epoch": 0.41664, "percentage": 13.91, "elapsed_time": "0:33:14", "remaining_time": "3:25:42"}
218
+ {"current_steps": 218, "total_steps": 1560, "loss": 0.4246, "lr": 9.951961188279216e-06, "epoch": 0.41856, "percentage": 13.97, "elapsed_time": "0:33:23", "remaining_time": "3:25:32"}
219
+ {"current_steps": 219, "total_steps": 1560, "loss": 0.3605, "lr": 9.950401639805822e-06, "epoch": 0.42048, "percentage": 14.04, "elapsed_time": "0:33:32", "remaining_time": "3:25:21"}
220
+ {"current_steps": 220, "total_steps": 1560, "loss": 0.4032, "lr": 9.948817305370145e-06, "epoch": 0.4224, "percentage": 14.1, "elapsed_time": "0:33:41", "remaining_time": "3:25:11"}
221
+ {"current_steps": 221, "total_steps": 1560, "loss": 0.3182, "lr": 9.947208192904722e-06, "epoch": 0.42432, "percentage": 14.17, "elapsed_time": "0:33:50", "remaining_time": "3:25:01"}
222
+ {"current_steps": 222, "total_steps": 1560, "loss": 0.3706, "lr": 9.94557431046616e-06, "epoch": 0.42624, "percentage": 14.23, "elapsed_time": "0:33:59", "remaining_time": "3:24:50"}
223
+ {"current_steps": 223, "total_steps": 1560, "loss": 0.4278, "lr": 9.943915666235068e-06, "epoch": 0.42816, "percentage": 14.29, "elapsed_time": "0:34:08", "remaining_time": "3:24:40"}
224
+ {"current_steps": 224, "total_steps": 1560, "loss": 0.4167, "lr": 9.942232268516051e-06, "epoch": 0.43008, "percentage": 14.36, "elapsed_time": "0:34:17", "remaining_time": "3:24:30"}
225
+ {"current_steps": 225, "total_steps": 1560, "loss": 0.3763, "lr": 9.940524125737641e-06, "epoch": 0.432, "percentage": 14.42, "elapsed_time": "0:34:26", "remaining_time": "3:24:20"}
226
+ {"current_steps": 226, "total_steps": 1560, "loss": 0.3436, "lr": 9.938791246452267e-06, "epoch": 0.43392, "percentage": 14.49, "elapsed_time": "0:34:35", "remaining_time": "3:24:10"}
227
+ {"current_steps": 227, "total_steps": 1560, "loss": 0.3805, "lr": 9.937033639336212e-06, "epoch": 0.43584, "percentage": 14.55, "elapsed_time": "0:34:44", "remaining_time": "3:24:01"}
228
+ {"current_steps": 228, "total_steps": 1560, "loss": 0.3772, "lr": 9.935251313189564e-06, "epoch": 0.43776, "percentage": 14.62, "elapsed_time": "0:34:53", "remaining_time": "3:23:52"}
229
+ {"current_steps": 229, "total_steps": 1560, "loss": 0.5889, "lr": 9.933444276936185e-06, "epoch": 0.43968, "percentage": 14.68, "elapsed_time": "0:35:04", "remaining_time": "3:23:49"}
230
+ {"current_steps": 230, "total_steps": 1560, "loss": 0.3584, "lr": 9.931612539623643e-06, "epoch": 0.4416, "percentage": 14.74, "elapsed_time": "0:35:13", "remaining_time": "3:23:41"}
231
+ {"current_steps": 231, "total_steps": 1560, "loss": 0.3739, "lr": 9.929756110423195e-06, "epoch": 0.44352, "percentage": 14.81, "elapsed_time": "0:35:22", "remaining_time": "3:23:32"}
232
+ {"current_steps": 232, "total_steps": 1560, "loss": 0.4055, "lr": 9.927874998629714e-06, "epoch": 0.44544, "percentage": 14.87, "elapsed_time": "0:35:31", "remaining_time": "3:23:23"}
233
+ {"current_steps": 233, "total_steps": 1560, "loss": 0.3732, "lr": 9.925969213661664e-06, "epoch": 0.44736, "percentage": 14.94, "elapsed_time": "0:35:41", "remaining_time": "3:23:14"}
234
+ {"current_steps": 234, "total_steps": 1560, "loss": 0.3459, "lr": 9.924038765061042e-06, "epoch": 0.44928, "percentage": 15.0, "elapsed_time": "0:35:50", "remaining_time": "3:23:04"}
235
+ {"current_steps": 235, "total_steps": 1560, "loss": 0.369, "lr": 9.92208366249333e-06, "epoch": 0.4512, "percentage": 15.06, "elapsed_time": "0:35:59", "remaining_time": "3:22:56"}
236
+ {"current_steps": 236, "total_steps": 1560, "loss": 0.3854, "lr": 9.920103915747452e-06, "epoch": 0.45312, "percentage": 15.13, "elapsed_time": "0:36:08", "remaining_time": "3:22:48"}
237
+ {"current_steps": 237, "total_steps": 1560, "loss": 0.3451, "lr": 9.91809953473572e-06, "epoch": 0.45504, "percentage": 15.19, "elapsed_time": "0:36:18", "remaining_time": "3:22:40"}
238
+ {"current_steps": 238, "total_steps": 1560, "loss": 0.3381, "lr": 9.916070529493785e-06, "epoch": 0.45696, "percentage": 15.26, "elapsed_time": "0:36:27", "remaining_time": "3:22:32"}
239
+ {"current_steps": 239, "total_steps": 1560, "loss": 0.3743, "lr": 9.914016910180593e-06, "epoch": 0.45888, "percentage": 15.32, "elapsed_time": "0:36:37", "remaining_time": "3:22:23"}
240
+ {"current_steps": 240, "total_steps": 1560, "loss": 0.3299, "lr": 9.911938687078324e-06, "epoch": 0.4608, "percentage": 15.38, "elapsed_time": "0:36:46", "remaining_time": "3:22:15"}
241
+ {"current_steps": 241, "total_steps": 1560, "loss": 0.3504, "lr": 9.90983587059235e-06, "epoch": 0.46272, "percentage": 15.45, "elapsed_time": "0:36:55", "remaining_time": "3:22:06"}
242
+ {"current_steps": 242, "total_steps": 1560, "loss": 0.3755, "lr": 9.907708471251173e-06, "epoch": 0.46464, "percentage": 15.51, "elapsed_time": "0:37:04", "remaining_time": "3:21:57"}
243
+ {"current_steps": 243, "total_steps": 1560, "loss": 0.4054, "lr": 9.905556499706384e-06, "epoch": 0.46656, "percentage": 15.58, "elapsed_time": "0:37:14", "remaining_time": "3:21:48"}
244
+ {"current_steps": 244, "total_steps": 1560, "loss": 0.3475, "lr": 9.9033799667326e-06, "epoch": 0.46848, "percentage": 15.64, "elapsed_time": "0:37:23", "remaining_time": "3:21:38"}
245
+ {"current_steps": 245, "total_steps": 1560, "loss": 0.4128, "lr": 9.901178883227413e-06, "epoch": 0.4704, "percentage": 15.71, "elapsed_time": "0:37:32", "remaining_time": "3:21:29"}
246
+ {"current_steps": 246, "total_steps": 1560, "loss": 0.3957, "lr": 9.89895326021134e-06, "epoch": 0.47232, "percentage": 15.77, "elapsed_time": "0:37:41", "remaining_time": "3:21:19"}
247
+ {"current_steps": 247, "total_steps": 1560, "loss": 0.4228, "lr": 9.896703108827758e-06, "epoch": 0.47424, "percentage": 15.83, "elapsed_time": "0:37:50", "remaining_time": "3:21:10"}
248
+ {"current_steps": 248, "total_steps": 1560, "loss": 0.362, "lr": 9.89442844034286e-06, "epoch": 0.47616, "percentage": 15.9, "elapsed_time": "0:37:59", "remaining_time": "3:21:01"}
249
+ {"current_steps": 249, "total_steps": 1560, "loss": 0.3671, "lr": 9.89212926614559e-06, "epoch": 0.47808, "percentage": 15.96, "elapsed_time": "0:38:08", "remaining_time": "3:20:51"}
250
+ {"current_steps": 250, "total_steps": 1560, "loss": 0.3974, "lr": 9.889805597747588e-06, "epoch": 0.48, "percentage": 16.03, "elapsed_time": "0:38:17", "remaining_time": "3:20:41"}
251
+ {"current_steps": 251, "total_steps": 1560, "loss": 0.3442, "lr": 9.887457446783133e-06, "epoch": 0.48192, "percentage": 16.09, "elapsed_time": "0:38:27", "remaining_time": "3:20:32"}
252
+ {"current_steps": 252, "total_steps": 1560, "loss": 0.4141, "lr": 9.885084825009085e-06, "epoch": 0.48384, "percentage": 16.15, "elapsed_time": "0:38:36", "remaining_time": "3:20:21"}
253
+ {"current_steps": 253, "total_steps": 1560, "loss": 0.3812, "lr": 9.88268774430483e-06, "epoch": 0.48576, "percentage": 16.22, "elapsed_time": "0:38:45", "remaining_time": "3:20:12"}
254
+ {"current_steps": 254, "total_steps": 1560, "loss": 0.4309, "lr": 9.88026621667221e-06, "epoch": 0.48768, "percentage": 16.28, "elapsed_time": "0:38:54", "remaining_time": "3:20:02"}
255
+ {"current_steps": 255, "total_steps": 1560, "loss": 0.3897, "lr": 9.87782025423547e-06, "epoch": 0.4896, "percentage": 16.35, "elapsed_time": "0:39:03", "remaining_time": "3:19:52"}
256
+ {"current_steps": 256, "total_steps": 1560, "loss": 0.3883, "lr": 9.875349869241202e-06, "epoch": 0.49152, "percentage": 16.41, "elapsed_time": "0:39:12", "remaining_time": "3:19:43"}
257
+ {"current_steps": 257, "total_steps": 1560, "loss": 0.3998, "lr": 9.872855074058274e-06, "epoch": 0.49344, "percentage": 16.47, "elapsed_time": "0:39:21", "remaining_time": "3:19:32"}
258
+ {"current_steps": 258, "total_steps": 1560, "loss": 0.3887, "lr": 9.870335881177774e-06, "epoch": 0.49536, "percentage": 16.54, "elapsed_time": "0:39:30", "remaining_time": "3:19:22"}
259
+ {"current_steps": 259, "total_steps": 1560, "loss": 0.336, "lr": 9.867792303212944e-06, "epoch": 0.49728, "percentage": 16.6, "elapsed_time": "0:39:39", "remaining_time": "3:19:12"}
260
+ {"current_steps": 260, "total_steps": 1560, "loss": 0.3696, "lr": 9.86522435289912e-06, "epoch": 0.4992, "percentage": 16.67, "elapsed_time": "0:39:48", "remaining_time": "3:19:02"}
261
+ {"current_steps": 261, "total_steps": 1560, "loss": 0.4792, "lr": 9.862632043093667e-06, "epoch": 0.50112, "percentage": 16.73, "elapsed_time": "0:39:57", "remaining_time": "3:18:53"}
262
+ {"current_steps": 262, "total_steps": 1560, "loss": 0.398, "lr": 9.860015386775915e-06, "epoch": 0.50304, "percentage": 16.79, "elapsed_time": "0:40:06", "remaining_time": "3:18:43"}
263
+ {"current_steps": 263, "total_steps": 1560, "loss": 0.3413, "lr": 9.857374397047093e-06, "epoch": 0.50496, "percentage": 16.86, "elapsed_time": "0:40:15", "remaining_time": "3:18:33"}
264
+ {"current_steps": 264, "total_steps": 1560, "loss": 0.3925, "lr": 9.854709087130261e-06, "epoch": 0.50688, "percentage": 16.92, "elapsed_time": "0:40:25", "remaining_time": "3:18:25"}
265
+ {"current_steps": 265, "total_steps": 1560, "loss": 0.3816, "lr": 9.852019470370254e-06, "epoch": 0.5088, "percentage": 16.99, "elapsed_time": "0:40:34", "remaining_time": "3:18:16"}
266
+ {"current_steps": 266, "total_steps": 1560, "loss": 0.3822, "lr": 9.849305560233598e-06, "epoch": 0.51072, "percentage": 17.05, "elapsed_time": "0:40:43", "remaining_time": "3:18:08"}
267
+ {"current_steps": 267, "total_steps": 1560, "loss": 0.45, "lr": 9.846567370308462e-06, "epoch": 0.51264, "percentage": 17.12, "elapsed_time": "0:40:53", "remaining_time": "3:18:00"}
268
+ {"current_steps": 268, "total_steps": 1560, "loss": 0.3872, "lr": 9.843804914304578e-06, "epoch": 0.51456, "percentage": 17.18, "elapsed_time": "0:41:02", "remaining_time": "3:17:51"}
269
+ {"current_steps": 269, "total_steps": 1560, "loss": 0.3882, "lr": 9.841018206053167e-06, "epoch": 0.51648, "percentage": 17.24, "elapsed_time": "0:41:11", "remaining_time": "3:17:42"}
270
+ {"current_steps": 270, "total_steps": 1560, "loss": 0.402, "lr": 9.838207259506891e-06, "epoch": 0.5184, "percentage": 17.31, "elapsed_time": "0:41:20", "remaining_time": "3:17:32"}
271
+ {"current_steps": 271, "total_steps": 1560, "loss": 0.4031, "lr": 9.835372088739758e-06, "epoch": 0.52032, "percentage": 17.37, "elapsed_time": "0:41:30", "remaining_time": "3:17:23"}
272
+ {"current_steps": 272, "total_steps": 1560, "loss": 0.3165, "lr": 9.83251270794707e-06, "epoch": 0.52224, "percentage": 17.44, "elapsed_time": "0:41:39", "remaining_time": "3:17:14"}
273
+ {"current_steps": 273, "total_steps": 1560, "loss": 0.3923, "lr": 9.829629131445342e-06, "epoch": 0.52416, "percentage": 17.5, "elapsed_time": "0:41:48", "remaining_time": "3:17:05"}
274
+ {"current_steps": 274, "total_steps": 1560, "loss": 0.4312, "lr": 9.826721373672235e-06, "epoch": 0.52608, "percentage": 17.56, "elapsed_time": "0:41:57", "remaining_time": "3:16:56"}
275
+ {"current_steps": 275, "total_steps": 1560, "loss": 0.4073, "lr": 9.82378944918648e-06, "epoch": 0.528, "percentage": 17.63, "elapsed_time": "0:42:06", "remaining_time": "3:16:47"}
276
+ {"current_steps": 276, "total_steps": 1560, "loss": 0.4063, "lr": 9.820833372667813e-06, "epoch": 0.52992, "percentage": 17.69, "elapsed_time": "0:42:16", "remaining_time": "3:16:38"}
277
+ {"current_steps": 277, "total_steps": 1560, "loss": 0.4243, "lr": 9.817853158916889e-06, "epoch": 0.53184, "percentage": 17.76, "elapsed_time": "0:42:25", "remaining_time": "3:16:29"}
278
+ {"current_steps": 278, "total_steps": 1560, "loss": 0.3838, "lr": 9.814848822855216e-06, "epoch": 0.53376, "percentage": 17.82, "elapsed_time": "0:42:34", "remaining_time": "3:16:19"}
279
+ {"current_steps": 279, "total_steps": 1560, "loss": 0.3591, "lr": 9.811820379525085e-06, "epoch": 0.53568, "percentage": 17.88, "elapsed_time": "0:42:43", "remaining_time": "3:16:10"}
280
+ {"current_steps": 280, "total_steps": 1560, "loss": 0.3793, "lr": 9.80876784408948e-06, "epoch": 0.5376, "percentage": 17.95, "elapsed_time": "0:42:52", "remaining_time": "3:16:01"}
281
+ {"current_steps": 281, "total_steps": 1560, "loss": 0.3321, "lr": 9.805691231832018e-06, "epoch": 0.53952, "percentage": 18.01, "elapsed_time": "0:43:02", "remaining_time": "3:15:52"}
282
+ {"current_steps": 282, "total_steps": 1560, "loss": 0.3836, "lr": 9.802590558156863e-06, "epoch": 0.54144, "percentage": 18.08, "elapsed_time": "0:43:11", "remaining_time": "3:15:43"}
283
+ {"current_steps": 283, "total_steps": 1560, "loss": 0.3241, "lr": 9.799465838588646e-06, "epoch": 0.54336, "percentage": 18.14, "elapsed_time": "0:43:20", "remaining_time": "3:15:35"}
284
+ {"current_steps": 284, "total_steps": 1560, "loss": 0.3454, "lr": 9.796317088772402e-06, "epoch": 0.54528, "percentage": 18.21, "elapsed_time": "0:43:29", "remaining_time": "3:15:26"}
285
+ {"current_steps": 285, "total_steps": 1560, "loss": 0.3702, "lr": 9.793144324473473e-06, "epoch": 0.5472, "percentage": 18.27, "elapsed_time": "0:43:39", "remaining_time": "3:15:17"}
286
+ {"current_steps": 286, "total_steps": 1560, "loss": 0.4264, "lr": 9.789947561577445e-06, "epoch": 0.54912, "percentage": 18.33, "elapsed_time": "0:43:48", "remaining_time": "3:15:08"}
287
+ {"current_steps": 287, "total_steps": 1560, "loss": 0.3619, "lr": 9.786726816090058e-06, "epoch": 0.55104, "percentage": 18.4, "elapsed_time": "0:43:57", "remaining_time": "3:14:59"}
288
+ {"current_steps": 288, "total_steps": 1560, "loss": 0.3716, "lr": 9.783482104137127e-06, "epoch": 0.55296, "percentage": 18.46, "elapsed_time": "0:44:06", "remaining_time": "3:14:50"}
289
+ {"current_steps": 289, "total_steps": 1560, "loss": 0.3619, "lr": 9.78021344196447e-06, "epoch": 0.55488, "percentage": 18.53, "elapsed_time": "0:44:16", "remaining_time": "3:14:41"}
290
+ {"current_steps": 290, "total_steps": 1560, "loss": 0.3504, "lr": 9.776920845937816e-06, "epoch": 0.5568, "percentage": 18.59, "elapsed_time": "0:44:25", "remaining_time": "3:14:32"}
291
+ {"current_steps": 291, "total_steps": 1560, "loss": 0.3575, "lr": 9.77360433254273e-06, "epoch": 0.55872, "percentage": 18.65, "elapsed_time": "0:44:34", "remaining_time": "3:14:23"}
292
+ {"current_steps": 292, "total_steps": 1560, "loss": 0.3255, "lr": 9.770263918384523e-06, "epoch": 0.56064, "percentage": 18.72, "elapsed_time": "0:44:43", "remaining_time": "3:14:14"}
293
+ {"current_steps": 293, "total_steps": 1560, "loss": 0.3696, "lr": 9.766899620188181e-06, "epoch": 0.56256, "percentage": 18.78, "elapsed_time": "0:44:52", "remaining_time": "3:14:04"}
294
+ {"current_steps": 294, "total_steps": 1560, "loss": 0.3148, "lr": 9.763511454798268e-06, "epoch": 0.56448, "percentage": 18.85, "elapsed_time": "0:45:02", "remaining_time": "3:13:55"}
295
+ {"current_steps": 295, "total_steps": 1560, "loss": 0.4024, "lr": 9.760099439178852e-06, "epoch": 0.5664, "percentage": 18.91, "elapsed_time": "0:45:11", "remaining_time": "3:13:45"}
296
+ {"current_steps": 296, "total_steps": 1560, "loss": 0.3515, "lr": 9.75666359041341e-06, "epoch": 0.56832, "percentage": 18.97, "elapsed_time": "0:45:20", "remaining_time": "3:13:36"}
297
+ {"current_steps": 297, "total_steps": 1560, "loss": 0.3752, "lr": 9.753203925704756e-06, "epoch": 0.57024, "percentage": 19.04, "elapsed_time": "0:45:29", "remaining_time": "3:13:26"}
298
+ {"current_steps": 298, "total_steps": 1560, "loss": 0.3364, "lr": 9.749720462374939e-06, "epoch": 0.57216, "percentage": 19.1, "elapsed_time": "0:45:38", "remaining_time": "3:13:17"}
299
+ {"current_steps": 299, "total_steps": 1560, "loss": 0.3891, "lr": 9.74621321786517e-06, "epoch": 0.57408, "percentage": 19.17, "elapsed_time": "0:45:47", "remaining_time": "3:13:08"}
300
+ {"current_steps": 300, "total_steps": 1560, "loss": 0.3786, "lr": 9.742682209735727e-06, "epoch": 0.576, "percentage": 19.23, "elapsed_time": "0:45:56", "remaining_time": "3:12:58"}
301
+ {"current_steps": 301, "total_steps": 1560, "loss": 0.3938, "lr": 9.739127455665872e-06, "epoch": 0.57792, "percentage": 19.29, "elapsed_time": "0:46:05", "remaining_time": "3:12:49"}
302
+ {"current_steps": 302, "total_steps": 1560, "loss": 0.3741, "lr": 9.735548973453753e-06, "epoch": 0.57984, "percentage": 19.36, "elapsed_time": "0:46:15", "remaining_time": "3:12:39"}
303
+ {"current_steps": 303, "total_steps": 1560, "loss": 0.3514, "lr": 9.731946781016328e-06, "epoch": 0.58176, "percentage": 19.42, "elapsed_time": "0:46:24", "remaining_time": "3:12:30"}
304
+ {"current_steps": 304, "total_steps": 1560, "loss": 0.4221, "lr": 9.728320896389263e-06, "epoch": 0.58368, "percentage": 19.49, "elapsed_time": "0:46:33", "remaining_time": "3:12:21"}
305
+ {"current_steps": 305, "total_steps": 1560, "loss": 0.4323, "lr": 9.724671337726855e-06, "epoch": 0.5856, "percentage": 19.55, "elapsed_time": "0:46:42", "remaining_time": "3:12:11"}
306
+ {"current_steps": 306, "total_steps": 1560, "loss": 0.44, "lr": 9.720998123301924e-06, "epoch": 0.58752, "percentage": 19.62, "elapsed_time": "0:46:51", "remaining_time": "3:12:00"}
307
+ {"current_steps": 307, "total_steps": 1560, "loss": 0.4329, "lr": 9.717301271505739e-06, "epoch": 0.58944, "percentage": 19.68, "elapsed_time": "0:47:00", "remaining_time": "3:11:51"}
308
+ {"current_steps": 308, "total_steps": 1560, "loss": 0.3793, "lr": 9.713580800847917e-06, "epoch": 0.59136, "percentage": 19.74, "elapsed_time": "0:47:09", "remaining_time": "3:11:42"}
309
+ {"current_steps": 309, "total_steps": 1560, "loss": 0.3416, "lr": 9.709836729956326e-06, "epoch": 0.59328, "percentage": 19.81, "elapsed_time": "0:47:18", "remaining_time": "3:11:33"}
310
+ {"current_steps": 310, "total_steps": 1560, "loss": 0.3438, "lr": 9.706069077577e-06, "epoch": 0.5952, "percentage": 19.87, "elapsed_time": "0:47:27", "remaining_time": "3:11:23"}
311
+ {"current_steps": 311, "total_steps": 1560, "loss": 0.3778, "lr": 9.702277862574048e-06, "epoch": 0.59712, "percentage": 19.94, "elapsed_time": "0:47:37", "remaining_time": "3:11:14"}
312
+ {"current_steps": 312, "total_steps": 1560, "loss": 0.4919, "lr": 9.698463103929542e-06, "epoch": 0.59904, "percentage": 20.0, "elapsed_time": "0:47:46", "remaining_time": "3:11:04"}
313
+ {"current_steps": 313, "total_steps": 1560, "loss": 0.3572, "lr": 9.694624820743446e-06, "epoch": 0.60096, "percentage": 20.06, "elapsed_time": "0:47:55", "remaining_time": "3:10:55"}
314
+ {"current_steps": 314, "total_steps": 1560, "loss": 0.3612, "lr": 9.690763032233498e-06, "epoch": 0.60288, "percentage": 20.13, "elapsed_time": "0:48:04", "remaining_time": "3:10:46"}
315
+ {"current_steps": 315, "total_steps": 1560, "loss": 0.4081, "lr": 9.686877757735126e-06, "epoch": 0.6048, "percentage": 20.19, "elapsed_time": "0:48:13", "remaining_time": "3:10:37"}
316
+ {"current_steps": 316, "total_steps": 1560, "loss": 0.3175, "lr": 9.682969016701357e-06, "epoch": 0.60672, "percentage": 20.26, "elapsed_time": "0:48:22", "remaining_time": "3:10:28"}
317
+ {"current_steps": 317, "total_steps": 1560, "loss": 0.3512, "lr": 9.679036828702704e-06, "epoch": 0.60864, "percentage": 20.32, "elapsed_time": "0:48:32", "remaining_time": "3:10:19"}
318
+ {"current_steps": 318, "total_steps": 1560, "loss": 0.3535, "lr": 9.675081213427076e-06, "epoch": 0.61056, "percentage": 20.38, "elapsed_time": "0:48:41", "remaining_time": "3:10:09"}
319
+ {"current_steps": 319, "total_steps": 1560, "loss": 0.3733, "lr": 9.671102190679678e-06, "epoch": 0.61248, "percentage": 20.45, "elapsed_time": "0:48:50", "remaining_time": "3:10:00"}
320
+ {"current_steps": 320, "total_steps": 1560, "loss": 0.3156, "lr": 9.66709978038292e-06, "epoch": 0.6144, "percentage": 20.51, "elapsed_time": "0:48:59", "remaining_time": "3:09:50"}
321
+ {"current_steps": 321, "total_steps": 1560, "loss": 0.3844, "lr": 9.663074002576303e-06, "epoch": 0.61632, "percentage": 20.58, "elapsed_time": "0:49:08", "remaining_time": "3:09:41"}
322
+ {"current_steps": 322, "total_steps": 1560, "loss": 0.3659, "lr": 9.659024877416328e-06, "epoch": 0.61824, "percentage": 20.64, "elapsed_time": "0:49:17", "remaining_time": "3:09:32"}
323
+ {"current_steps": 323, "total_steps": 1560, "loss": 0.3785, "lr": 9.654952425176392e-06, "epoch": 0.62016, "percentage": 20.71, "elapsed_time": "0:49:27", "remaining_time": "3:09:22"}
324
+ {"current_steps": 324, "total_steps": 1560, "loss": 0.2969, "lr": 9.650856666246693e-06, "epoch": 0.62208, "percentage": 20.77, "elapsed_time": "0:49:36", "remaining_time": "3:09:13"}
325
+ {"current_steps": 325, "total_steps": 1560, "loss": 0.405, "lr": 9.646737621134112e-06, "epoch": 0.624, "percentage": 20.83, "elapsed_time": "0:49:45", "remaining_time": "3:09:03"}
326
+ {"current_steps": 326, "total_steps": 1560, "loss": 0.382, "lr": 9.642595310462133e-06, "epoch": 0.62592, "percentage": 20.9, "elapsed_time": "0:49:54", "remaining_time": "3:08:54"}
327
+ {"current_steps": 327, "total_steps": 1560, "loss": 0.314, "lr": 9.638429754970715e-06, "epoch": 0.62784, "percentage": 20.96, "elapsed_time": "0:50:03", "remaining_time": "3:08:45"}
328
+ {"current_steps": 328, "total_steps": 1560, "loss": 0.3856, "lr": 9.63424097551621e-06, "epoch": 0.62976, "percentage": 21.03, "elapsed_time": "0:50:12", "remaining_time": "3:08:36"}
329
+ {"current_steps": 329, "total_steps": 1560, "loss": 0.4276, "lr": 9.630028993071244e-06, "epoch": 0.63168, "percentage": 21.09, "elapsed_time": "0:50:21", "remaining_time": "3:08:26"}
330
+ {"current_steps": 330, "total_steps": 1560, "loss": 0.4114, "lr": 9.62579382872462e-06, "epoch": 0.6336, "percentage": 21.15, "elapsed_time": "0:50:30", "remaining_time": "3:08:17"}
331
+ {"current_steps": 331, "total_steps": 1560, "loss": 0.3903, "lr": 9.621535503681205e-06, "epoch": 0.63552, "percentage": 21.22, "elapsed_time": "0:50:40", "remaining_time": "3:08:07"}
332
+ {"current_steps": 332, "total_steps": 1560, "loss": 0.3729, "lr": 9.617254039261835e-06, "epoch": 0.63744, "percentage": 21.28, "elapsed_time": "0:50:49", "remaining_time": "3:07:58"}
333
+ {"current_steps": 333, "total_steps": 1560, "loss": 0.4528, "lr": 9.612949456903195e-06, "epoch": 0.63936, "percentage": 21.35, "elapsed_time": "0:50:58", "remaining_time": "3:07:49"}
334
+ {"current_steps": 334, "total_steps": 1560, "loss": 0.3773, "lr": 9.608621778157722e-06, "epoch": 0.64128, "percentage": 21.41, "elapsed_time": "0:51:07", "remaining_time": "3:07:39"}
335
+ {"current_steps": 335, "total_steps": 1560, "loss": 0.376, "lr": 9.604271024693495e-06, "epoch": 0.6432, "percentage": 21.47, "elapsed_time": "0:51:16", "remaining_time": "3:07:30"}
336
+ {"current_steps": 336, "total_steps": 1560, "loss": 0.3589, "lr": 9.599897218294122e-06, "epoch": 0.64512, "percentage": 21.54, "elapsed_time": "0:51:25", "remaining_time": "3:07:21"}
337
+ {"current_steps": 337, "total_steps": 1560, "loss": 0.3944, "lr": 9.595500380858632e-06, "epoch": 0.64704, "percentage": 21.6, "elapsed_time": "0:51:35", "remaining_time": "3:07:12"}
338
+ {"current_steps": 338, "total_steps": 1560, "loss": 0.3872, "lr": 9.591080534401371e-06, "epoch": 0.64896, "percentage": 21.67, "elapsed_time": "0:51:44", "remaining_time": "3:07:02"}
339
+ {"current_steps": 339, "total_steps": 1560, "loss": 0.4554, "lr": 9.586637701051886e-06, "epoch": 0.65088, "percentage": 21.73, "elapsed_time": "0:51:53", "remaining_time": "3:06:53"}
340
+ {"current_steps": 340, "total_steps": 1560, "loss": 0.3402, "lr": 9.582171903054815e-06, "epoch": 0.6528, "percentage": 21.79, "elapsed_time": "0:52:02", "remaining_time": "3:06:44"}
341
+ {"current_steps": 341, "total_steps": 1560, "loss": 0.3641, "lr": 9.577683162769781e-06, "epoch": 0.65472, "percentage": 21.86, "elapsed_time": "0:52:11", "remaining_time": "3:06:34"}
342
+ {"current_steps": 342, "total_steps": 1560, "loss": 0.3481, "lr": 9.573171502671273e-06, "epoch": 0.65664, "percentage": 21.92, "elapsed_time": "0:52:20", "remaining_time": "3:06:24"}
343
+ {"current_steps": 343, "total_steps": 1560, "loss": 0.3718, "lr": 9.568636945348534e-06, "epoch": 0.65856, "percentage": 21.99, "elapsed_time": "0:52:29", "remaining_time": "3:06:14"}
344
+ {"current_steps": 344, "total_steps": 1560, "loss": 0.3845, "lr": 9.564079513505455e-06, "epoch": 0.66048, "percentage": 22.05, "elapsed_time": "0:52:38", "remaining_time": "3:06:04"}
345
+ {"current_steps": 345, "total_steps": 1560, "loss": 0.2939, "lr": 9.55949922996045e-06, "epoch": 0.6624, "percentage": 22.12, "elapsed_time": "0:52:47", "remaining_time": "3:05:54"}
346
+ {"current_steps": 346, "total_steps": 1560, "loss": 0.3488, "lr": 9.554896117646357e-06, "epoch": 0.66432, "percentage": 22.18, "elapsed_time": "0:52:56", "remaining_time": "3:05:44"}
347
+ {"current_steps": 347, "total_steps": 1560, "loss": 0.3641, "lr": 9.550270199610307e-06, "epoch": 0.66624, "percentage": 22.24, "elapsed_time": "0:53:05", "remaining_time": "3:05:33"}
348
+ {"current_steps": 348, "total_steps": 1560, "loss": 0.3881, "lr": 9.54562149901362e-06, "epoch": 0.66816, "percentage": 22.31, "elapsed_time": "0:53:13", "remaining_time": "3:05:23"}
349
+ {"current_steps": 349, "total_steps": 1560, "loss": 0.3822, "lr": 9.54095003913168e-06, "epoch": 0.67008, "percentage": 22.37, "elapsed_time": "0:53:22", "remaining_time": "3:05:13"}
350
+ {"current_steps": 350, "total_steps": 1560, "loss": 0.3686, "lr": 9.536255843353832e-06, "epoch": 0.672, "percentage": 22.44, "elapsed_time": "0:53:31", "remaining_time": "3:05:03"}
351
+ {"current_steps": 351, "total_steps": 1560, "loss": 0.3642, "lr": 9.531538935183252e-06, "epoch": 0.67392, "percentage": 22.5, "elapsed_time": "0:53:40", "remaining_time": "3:04:53"}
352
+ {"current_steps": 352, "total_steps": 1560, "loss": 0.328, "lr": 9.526799338236828e-06, "epoch": 0.67584, "percentage": 22.56, "elapsed_time": "0:53:49", "remaining_time": "3:04:43"}
353
+ {"current_steps": 353, "total_steps": 1560, "loss": 0.3872, "lr": 9.522037076245057e-06, "epoch": 0.67776, "percentage": 22.63, "elapsed_time": "0:53:58", "remaining_time": "3:04:33"}
354
+ {"current_steps": 354, "total_steps": 1560, "loss": 0.384, "lr": 9.517252173051912e-06, "epoch": 0.67968, "percentage": 22.69, "elapsed_time": "0:54:07", "remaining_time": "3:04:23"}
355
+ {"current_steps": 355, "total_steps": 1560, "loss": 0.4314, "lr": 9.512444652614728e-06, "epoch": 0.6816, "percentage": 22.76, "elapsed_time": "0:54:16", "remaining_time": "3:04:12"}
356
+ {"current_steps": 356, "total_steps": 1560, "loss": 0.3645, "lr": 9.507614539004082e-06, "epoch": 0.68352, "percentage": 22.82, "elapsed_time": "0:54:25", "remaining_time": "3:04:02"}
357
+ {"current_steps": 357, "total_steps": 1560, "loss": 0.3773, "lr": 9.502761856403668e-06, "epoch": 0.68544, "percentage": 22.88, "elapsed_time": "0:54:34", "remaining_time": "3:03:52"}
358
+ {"current_steps": 358, "total_steps": 1560, "loss": 0.3587, "lr": 9.497886629110187e-06, "epoch": 0.68736, "percentage": 22.95, "elapsed_time": "0:54:43", "remaining_time": "3:03:42"}
359
+ {"current_steps": 359, "total_steps": 1560, "loss": 0.3574, "lr": 9.49298888153321e-06, "epoch": 0.68928, "percentage": 23.01, "elapsed_time": "0:54:52", "remaining_time": "3:03:33"}
360
+ {"current_steps": 360, "total_steps": 1560, "loss": 0.442, "lr": 9.488068638195072e-06, "epoch": 0.6912, "percentage": 23.08, "elapsed_time": "0:55:01", "remaining_time": "3:03:23"}
361
+ {"current_steps": 361, "total_steps": 1560, "loss": 0.4005, "lr": 9.483125923730731e-06, "epoch": 0.69312, "percentage": 23.14, "elapsed_time": "0:55:10", "remaining_time": "3:03:14"}
362
+ {"current_steps": 362, "total_steps": 1560, "loss": 0.3446, "lr": 9.478160762887668e-06, "epoch": 0.69504, "percentage": 23.21, "elapsed_time": "0:55:19", "remaining_time": "3:03:05"}
363
+ {"current_steps": 363, "total_steps": 1560, "loss": 0.3803, "lr": 9.473173180525737e-06, "epoch": 0.69696, "percentage": 23.27, "elapsed_time": "0:55:28", "remaining_time": "3:02:56"}
364
+ {"current_steps": 364, "total_steps": 1560, "loss": 0.3744, "lr": 9.468163201617063e-06, "epoch": 0.69888, "percentage": 23.33, "elapsed_time": "0:55:37", "remaining_time": "3:02:46"}
365
+ {"current_steps": 365, "total_steps": 1560, "loss": 0.3869, "lr": 9.463130851245899e-06, "epoch": 0.7008, "percentage": 23.4, "elapsed_time": "0:55:46", "remaining_time": "3:02:37"}
366
+ {"current_steps": 366, "total_steps": 1560, "loss": 0.3589, "lr": 9.458076154608515e-06, "epoch": 0.70272, "percentage": 23.46, "elapsed_time": "0:55:56", "remaining_time": "3:02:29"}
367
+ {"current_steps": 367, "total_steps": 1560, "loss": 0.402, "lr": 9.452999137013064e-06, "epoch": 0.70464, "percentage": 23.53, "elapsed_time": "0:56:05", "remaining_time": "3:02:20"}
368
+ {"current_steps": 368, "total_steps": 1560, "loss": 0.4345, "lr": 9.447899823879456e-06, "epoch": 0.70656, "percentage": 23.59, "elapsed_time": "0:56:14", "remaining_time": "3:02:10"}
369
+ {"current_steps": 369, "total_steps": 1560, "loss": 0.3758, "lr": 9.442778240739234e-06, "epoch": 0.70848, "percentage": 23.65, "elapsed_time": "0:56:24", "remaining_time": "3:02:02"}
370
+ {"current_steps": 370, "total_steps": 1560, "loss": 0.353, "lr": 9.437634413235437e-06, "epoch": 0.7104, "percentage": 23.72, "elapsed_time": "0:56:33", "remaining_time": "3:01:54"}
371
+ {"current_steps": 371, "total_steps": 1560, "loss": 0.387, "lr": 9.43246836712249e-06, "epoch": 0.71232, "percentage": 23.78, "elapsed_time": "0:56:42", "remaining_time": "3:01:46"}
372
+ {"current_steps": 372, "total_steps": 1560, "loss": 0.3687, "lr": 9.427280128266049e-06, "epoch": 0.71424, "percentage": 23.85, "elapsed_time": "0:56:52", "remaining_time": "3:01:38"}
373
+ {"current_steps": 373, "total_steps": 1560, "loss": 0.4196, "lr": 9.4220697226429e-06, "epoch": 0.71616, "percentage": 23.91, "elapsed_time": "0:57:01", "remaining_time": "3:01:28"}
374
+ {"current_steps": 374, "total_steps": 1560, "loss": 0.3736, "lr": 9.416837176340807e-06, "epoch": 0.71808, "percentage": 23.97, "elapsed_time": "0:57:10", "remaining_time": "3:01:20"}
375
+ {"current_steps": 375, "total_steps": 1560, "loss": 0.4458, "lr": 9.411582515558391e-06, "epoch": 0.72, "percentage": 24.04, "elapsed_time": "0:57:20", "remaining_time": "3:01:10"}
376
+ {"current_steps": 376, "total_steps": 1560, "loss": 0.3642, "lr": 9.406305766604996e-06, "epoch": 0.72192, "percentage": 24.1, "elapsed_time": "0:57:29", "remaining_time": "3:01:01"}
377
+ {"current_steps": 377, "total_steps": 1560, "loss": 0.3311, "lr": 9.401006955900555e-06, "epoch": 0.72384, "percentage": 24.17, "elapsed_time": "0:57:38", "remaining_time": "3:00:51"}
378
+ {"current_steps": 378, "total_steps": 1560, "loss": 0.3451, "lr": 9.395686109975475e-06, "epoch": 0.72576, "percentage": 24.23, "elapsed_time": "0:57:47", "remaining_time": "3:00:41"}
379
+ {"current_steps": 379, "total_steps": 1560, "loss": 0.4346, "lr": 9.390343255470471e-06, "epoch": 0.72768, "percentage": 24.29, "elapsed_time": "0:57:56", "remaining_time": "3:00:32"}
380
+ {"current_steps": 380, "total_steps": 1560, "loss": 0.414, "lr": 9.384978419136469e-06, "epoch": 0.7296, "percentage": 24.36, "elapsed_time": "0:58:05", "remaining_time": "3:00:22"}
381
+ {"current_steps": 381, "total_steps": 1560, "loss": 0.4397, "lr": 9.37959162783444e-06, "epoch": 0.73152, "percentage": 24.42, "elapsed_time": "0:58:14", "remaining_time": "3:00:12"}
382
+ {"current_steps": 382, "total_steps": 1560, "loss": 0.3505, "lr": 9.374182908535293e-06, "epoch": 0.73344, "percentage": 24.49, "elapsed_time": "0:58:23", "remaining_time": "3:00:03"}
383
+ {"current_steps": 383, "total_steps": 1560, "loss": 0.4072, "lr": 9.368752288319722e-06, "epoch": 0.73536, "percentage": 24.55, "elapsed_time": "0:58:32", "remaining_time": "2:59:53"}
384
+ {"current_steps": 384, "total_steps": 1560, "loss": 0.3804, "lr": 9.363299794378072e-06, "epoch": 0.73728, "percentage": 24.62, "elapsed_time": "0:58:41", "remaining_time": "2:59:43"}
385
+ {"current_steps": 385, "total_steps": 1560, "loss": 0.3791, "lr": 9.357825454010214e-06, "epoch": 0.7392, "percentage": 24.68, "elapsed_time": "0:58:50", "remaining_time": "2:59:34"}
386
+ {"current_steps": 386, "total_steps": 1560, "loss": 0.3465, "lr": 9.352329294625397e-06, "epoch": 0.74112, "percentage": 24.74, "elapsed_time": "0:58:59", "remaining_time": "2:59:24"}
387
+ {"current_steps": 387, "total_steps": 1560, "loss": 0.3209, "lr": 9.346811343742115e-06, "epoch": 0.74304, "percentage": 24.81, "elapsed_time": "0:59:08", "remaining_time": "2:59:15"}
388
+ {"current_steps": 388, "total_steps": 1560, "loss": 0.4478, "lr": 9.34127162898797e-06, "epoch": 0.74496, "percentage": 24.87, "elapsed_time": "0:59:17", "remaining_time": "2:59:06"}
389
+ {"current_steps": 389, "total_steps": 1560, "loss": 0.3523, "lr": 9.335710178099528e-06, "epoch": 0.74688, "percentage": 24.94, "elapsed_time": "0:59:26", "remaining_time": "2:58:57"}
390
+ {"current_steps": 390, "total_steps": 1560, "loss": 0.3315, "lr": 9.330127018922195e-06, "epoch": 0.7488, "percentage": 25.0, "elapsed_time": "0:59:35", "remaining_time": "2:58:47"}
391
+ {"current_steps": 391, "total_steps": 1560, "loss": 0.3546, "lr": 9.324522179410054e-06, "epoch": 0.75072, "percentage": 25.06, "elapsed_time": "0:59:44", "remaining_time": "2:58:37"}
392
+ {"current_steps": 392, "total_steps": 1560, "loss": 0.465, "lr": 9.318895687625752e-06, "epoch": 0.75264, "percentage": 25.13, "elapsed_time": "0:59:53", "remaining_time": "2:58:28"}
393
+ {"current_steps": 393, "total_steps": 1560, "loss": 0.3681, "lr": 9.313247571740336e-06, "epoch": 0.75456, "percentage": 25.19, "elapsed_time": "1:00:03", "remaining_time": "2:58:19"}
394
+ {"current_steps": 394, "total_steps": 1560, "loss": 0.3666, "lr": 9.307577860033123e-06, "epoch": 0.75648, "percentage": 25.26, "elapsed_time": "1:00:12", "remaining_time": "2:58:10"}
395
+ {"current_steps": 395, "total_steps": 1560, "loss": 0.3998, "lr": 9.301886580891563e-06, "epoch": 0.7584, "percentage": 25.32, "elapsed_time": "1:00:21", "remaining_time": "2:58:00"}
396
+ {"current_steps": 396, "total_steps": 1560, "loss": 0.372, "lr": 9.296173762811084e-06, "epoch": 0.76032, "percentage": 25.38, "elapsed_time": "1:00:30", "remaining_time": "2:57:51"}
397
+ {"current_steps": 397, "total_steps": 1560, "loss": 0.3533, "lr": 9.290439434394965e-06, "epoch": 0.76224, "percentage": 25.45, "elapsed_time": "1:00:39", "remaining_time": "2:57:42"}
398
+ {"current_steps": 398, "total_steps": 1560, "loss": 0.4271, "lr": 9.284683624354172e-06, "epoch": 0.76416, "percentage": 25.51, "elapsed_time": "1:00:48", "remaining_time": "2:57:33"}
399
+ {"current_steps": 399, "total_steps": 1560, "loss": 0.3983, "lr": 9.278906361507238e-06, "epoch": 0.76608, "percentage": 25.58, "elapsed_time": "1:00:58", "remaining_time": "2:57:24"}
400
+ {"current_steps": 400, "total_steps": 1560, "loss": 0.3924, "lr": 9.273107674780102e-06, "epoch": 0.768, "percentage": 25.64, "elapsed_time": "1:01:07", "remaining_time": "2:57:14"}
401
+ {"current_steps": 401, "total_steps": 1560, "loss": 0.3588, "lr": 9.26728759320597e-06, "epoch": 0.76992, "percentage": 25.71, "elapsed_time": "1:01:16", "remaining_time": "2:57:05"}
402
+ {"current_steps": 402, "total_steps": 1560, "loss": 0.3982, "lr": 9.261446145925167e-06, "epoch": 0.77184, "percentage": 25.77, "elapsed_time": "1:01:25", "remaining_time": "2:56:56"}
403
+ {"current_steps": 403, "total_steps": 1560, "loss": 0.3557, "lr": 9.255583362184998e-06, "epoch": 0.77376, "percentage": 25.83, "elapsed_time": "1:01:34", "remaining_time": "2:56:47"}
404
+ {"current_steps": 404, "total_steps": 1560, "loss": 0.3328, "lr": 9.249699271339594e-06, "epoch": 0.77568, "percentage": 25.9, "elapsed_time": "1:01:43", "remaining_time": "2:56:38"}
405
+ {"current_steps": 405, "total_steps": 1560, "loss": 0.4001, "lr": 9.243793902849764e-06, "epoch": 0.7776, "percentage": 25.96, "elapsed_time": "1:01:53", "remaining_time": "2:56:29"}
406
+ {"current_steps": 406, "total_steps": 1560, "loss": 0.349, "lr": 9.237867286282855e-06, "epoch": 0.77952, "percentage": 26.03, "elapsed_time": "1:02:02", "remaining_time": "2:56:20"}
407
+ {"current_steps": 407, "total_steps": 1560, "loss": 0.378, "lr": 9.231919451312603e-06, "epoch": 0.78144, "percentage": 26.09, "elapsed_time": "1:02:11", "remaining_time": "2:56:10"}
408
+ {"current_steps": 408, "total_steps": 1560, "loss": 0.4029, "lr": 9.225950427718974e-06, "epoch": 0.78336, "percentage": 26.15, "elapsed_time": "1:02:20", "remaining_time": "2:56:00"}
409
+ {"current_steps": 409, "total_steps": 1560, "loss": 0.413, "lr": 9.21996024538803e-06, "epoch": 0.78528, "percentage": 26.22, "elapsed_time": "1:02:29", "remaining_time": "2:55:51"}
410
+ {"current_steps": 410, "total_steps": 1560, "loss": 0.3736, "lr": 9.213948934311767e-06, "epoch": 0.7872, "percentage": 26.28, "elapsed_time": "1:02:38", "remaining_time": "2:55:41"}
411
+ {"current_steps": 411, "total_steps": 1560, "loss": 0.3831, "lr": 9.207916524587971e-06, "epoch": 0.78912, "percentage": 26.35, "elapsed_time": "1:02:47", "remaining_time": "2:55:31"}
412
+ {"current_steps": 412, "total_steps": 1560, "loss": 0.3708, "lr": 9.201863046420065e-06, "epoch": 0.79104, "percentage": 26.41, "elapsed_time": "1:02:56", "remaining_time": "2:55:21"}
413
+ {"current_steps": 413, "total_steps": 1560, "loss": 0.3881, "lr": 9.195788530116962e-06, "epoch": 0.79296, "percentage": 26.47, "elapsed_time": "1:03:05", "remaining_time": "2:55:12"}
414
+ {"current_steps": 414, "total_steps": 1560, "loss": 0.4388, "lr": 9.189693006092907e-06, "epoch": 0.79488, "percentage": 26.54, "elapsed_time": "1:03:13", "remaining_time": "2:55:02"}
415
+ {"current_steps": 415, "total_steps": 1560, "loss": 0.352, "lr": 9.183576504867328e-06, "epoch": 0.7968, "percentage": 26.6, "elapsed_time": "1:03:22", "remaining_time": "2:54:52"}
416
+ {"current_steps": 416, "total_steps": 1560, "loss": 0.3673, "lr": 9.177439057064684e-06, "epoch": 0.79872, "percentage": 26.67, "elapsed_time": "1:03:31", "remaining_time": "2:54:42"}
417
+ {"current_steps": 417, "total_steps": 1560, "loss": 0.3419, "lr": 9.171280693414307e-06, "epoch": 0.80064, "percentage": 26.73, "elapsed_time": "1:03:40", "remaining_time": "2:54:32"}
418
+ {"current_steps": 418, "total_steps": 1560, "loss": 0.4062, "lr": 9.165101444750259e-06, "epoch": 0.80256, "percentage": 26.79, "elapsed_time": "1:03:49", "remaining_time": "2:54:22"}
419
+ {"current_steps": 419, "total_steps": 1560, "loss": 0.3893, "lr": 9.158901342011163e-06, "epoch": 0.80448, "percentage": 26.86, "elapsed_time": "1:03:58", "remaining_time": "2:54:12"}
420
+ {"current_steps": 420, "total_steps": 1560, "loss": 0.3598, "lr": 9.152680416240059e-06, "epoch": 0.8064, "percentage": 26.92, "elapsed_time": "1:04:07", "remaining_time": "2:54:03"}
421
+ {"current_steps": 421, "total_steps": 1560, "loss": 0.4084, "lr": 9.146438698584245e-06, "epoch": 0.80832, "percentage": 26.99, "elapsed_time": "1:04:16", "remaining_time": "2:53:53"}
422
+ {"current_steps": 422, "total_steps": 1560, "loss": 0.3065, "lr": 9.140176220295118e-06, "epoch": 0.81024, "percentage": 27.05, "elapsed_time": "1:04:25", "remaining_time": "2:53:44"}
423
+ {"current_steps": 423, "total_steps": 1560, "loss": 0.2882, "lr": 9.133893012728027e-06, "epoch": 0.81216, "percentage": 27.12, "elapsed_time": "1:04:34", "remaining_time": "2:53:35"}
424
+ {"current_steps": 424, "total_steps": 1560, "loss": 0.3236, "lr": 9.1275891073421e-06, "epoch": 0.81408, "percentage": 27.18, "elapsed_time": "1:04:44", "remaining_time": "2:53:26"}
425
+ {"current_steps": 425, "total_steps": 1560, "loss": 0.4256, "lr": 9.121264535700107e-06, "epoch": 0.816, "percentage": 27.24, "elapsed_time": "1:04:53", "remaining_time": "2:53:17"}
426
+ {"current_steps": 426, "total_steps": 1560, "loss": 0.3828, "lr": 9.114919329468283e-06, "epoch": 0.81792, "percentage": 27.31, "elapsed_time": "1:05:02", "remaining_time": "2:53:08"}
427
+ {"current_steps": 427, "total_steps": 1560, "loss": 0.3162, "lr": 9.10855352041618e-06, "epoch": 0.81984, "percentage": 27.37, "elapsed_time": "1:05:11", "remaining_time": "2:52:59"}
428
+ {"current_steps": 428, "total_steps": 1560, "loss": 0.3505, "lr": 9.102167140416503e-06, "epoch": 0.82176, "percentage": 27.44, "elapsed_time": "1:05:20", "remaining_time": "2:52:49"}
429
+ {"current_steps": 429, "total_steps": 1560, "loss": 0.3222, "lr": 9.09576022144496e-06, "epoch": 0.82368, "percentage": 27.5, "elapsed_time": "1:05:29", "remaining_time": "2:52:40"}
430
+ {"current_steps": 430, "total_steps": 1560, "loss": 0.3844, "lr": 9.089332795580085e-06, "epoch": 0.8256, "percentage": 27.56, "elapsed_time": "1:05:38", "remaining_time": "2:52:30"}
431
+ {"current_steps": 431, "total_steps": 1560, "loss": 0.3823, "lr": 9.082884895003098e-06, "epoch": 0.82752, "percentage": 27.63, "elapsed_time": "1:05:47", "remaining_time": "2:52:21"}
432
+ {"current_steps": 432, "total_steps": 1560, "loss": 0.3846, "lr": 9.076416551997721e-06, "epoch": 0.82944, "percentage": 27.69, "elapsed_time": "1:05:56", "remaining_time": "2:52:11"}
433
+ {"current_steps": 433, "total_steps": 1560, "loss": 0.5272, "lr": 9.06992779895004e-06, "epoch": 0.83136, "percentage": 27.76, "elapsed_time": "1:06:05", "remaining_time": "2:52:01"}
434
+ {"current_steps": 434, "total_steps": 1560, "loss": 0.3567, "lr": 9.063418668348323e-06, "epoch": 0.83328, "percentage": 27.82, "elapsed_time": "1:06:14", "remaining_time": "2:51:52"}
435
+ {"current_steps": 435, "total_steps": 1560, "loss": 0.4301, "lr": 9.056889192782865e-06, "epoch": 0.8352, "percentage": 27.88, "elapsed_time": "1:06:23", "remaining_time": "2:51:42"}
436
+ {"current_steps": 436, "total_steps": 1560, "loss": 0.364, "lr": 9.050339404945834e-06, "epoch": 0.83712, "percentage": 27.95, "elapsed_time": "1:06:33", "remaining_time": "2:51:34"}
437
+ {"current_steps": 437, "total_steps": 1560, "loss": 0.4051, "lr": 9.04376933763109e-06, "epoch": 0.83904, "percentage": 28.01, "elapsed_time": "1:06:42", "remaining_time": "2:51:25"}
438
+ {"current_steps": 438, "total_steps": 1560, "loss": 0.3661, "lr": 9.037179023734036e-06, "epoch": 0.84096, "percentage": 28.08, "elapsed_time": "1:06:51", "remaining_time": "2:51:16"}
439
+ {"current_steps": 439, "total_steps": 1560, "loss": 0.4567, "lr": 9.030568496251437e-06, "epoch": 0.84288, "percentage": 28.14, "elapsed_time": "1:07:01", "remaining_time": "2:51:08"}
440
+ {"current_steps": 440, "total_steps": 1560, "loss": 0.3955, "lr": 9.023937788281278e-06, "epoch": 0.8448, "percentage": 28.21, "elapsed_time": "1:07:10", "remaining_time": "2:50:59"}
441
+ {"current_steps": 441, "total_steps": 1560, "loss": 0.3705, "lr": 9.017286933022573e-06, "epoch": 0.84672, "percentage": 28.27, "elapsed_time": "1:07:19", "remaining_time": "2:50:50"}
442
+ {"current_steps": 442, "total_steps": 1560, "loss": 0.3553, "lr": 9.01061596377522e-06, "epoch": 0.84864, "percentage": 28.33, "elapsed_time": "1:07:29", "remaining_time": "2:50:41"}
443
+ {"current_steps": 443, "total_steps": 1560, "loss": 0.4073, "lr": 9.003924913939816e-06, "epoch": 0.85056, "percentage": 28.4, "elapsed_time": "1:07:38", "remaining_time": "2:50:33"}
444
+ {"current_steps": 444, "total_steps": 1560, "loss": 0.3966, "lr": 8.997213817017508e-06, "epoch": 0.85248, "percentage": 28.46, "elapsed_time": "1:07:47", "remaining_time": "2:50:24"}
445
+ {"current_steps": 445, "total_steps": 1560, "loss": 0.3839, "lr": 8.990482706609805e-06, "epoch": 0.8544, "percentage": 28.53, "elapsed_time": "1:07:57", "remaining_time": "2:50:15"}
446
+ {"current_steps": 446, "total_steps": 1560, "loss": 0.4054, "lr": 8.98373161641843e-06, "epoch": 0.85632, "percentage": 28.59, "elapsed_time": "1:08:06", "remaining_time": "2:50:06"}
447
+ {"current_steps": 447, "total_steps": 1560, "loss": 0.4418, "lr": 8.97696058024514e-06, "epoch": 0.85824, "percentage": 28.65, "elapsed_time": "1:08:15", "remaining_time": "2:49:57"}
448
+ {"current_steps": 448, "total_steps": 1560, "loss": 0.3277, "lr": 8.970169631991556e-06, "epoch": 0.86016, "percentage": 28.72, "elapsed_time": "1:08:24", "remaining_time": "2:49:48"}
449
+ {"current_steps": 449, "total_steps": 1560, "loss": 0.3804, "lr": 8.963358805658998e-06, "epoch": 0.86208, "percentage": 28.78, "elapsed_time": "1:08:34", "remaining_time": "2:49:40"}
450
+ {"current_steps": 450, "total_steps": 1560, "loss": 0.4163, "lr": 8.95652813534831e-06, "epoch": 0.864, "percentage": 28.85, "elapsed_time": "1:08:43", "remaining_time": "2:49:30"}
451
+ {"current_steps": 451, "total_steps": 1560, "loss": 0.4105, "lr": 8.949677655259696e-06, "epoch": 0.86592, "percentage": 28.91, "elapsed_time": "1:08:52", "remaining_time": "2:49:22"}
452
+ {"current_steps": 452, "total_steps": 1560, "loss": 0.3751, "lr": 8.942807399692543e-06, "epoch": 0.86784, "percentage": 28.97, "elapsed_time": "1:09:02", "remaining_time": "2:49:13"}
453
+ {"current_steps": 453, "total_steps": 1560, "loss": 0.3322, "lr": 8.935917403045251e-06, "epoch": 0.86976, "percentage": 29.04, "elapsed_time": "1:09:11", "remaining_time": "2:49:04"}
454
+ {"current_steps": 454, "total_steps": 1560, "loss": 0.3765, "lr": 8.92900769981506e-06, "epoch": 0.87168, "percentage": 29.1, "elapsed_time": "1:09:20", "remaining_time": "2:48:55"}
455
+ {"current_steps": 455, "total_steps": 1560, "loss": 0.3494, "lr": 8.92207832459788e-06, "epoch": 0.8736, "percentage": 29.17, "elapsed_time": "1:09:30", "remaining_time": "2:48:47"}
456
+ {"current_steps": 456, "total_steps": 1560, "loss": 0.4156, "lr": 8.915129312088112e-06, "epoch": 0.87552, "percentage": 29.23, "elapsed_time": "1:09:39", "remaining_time": "2:48:38"}
457
+ {"current_steps": 457, "total_steps": 1560, "loss": 0.3605, "lr": 8.908160697078482e-06, "epoch": 0.87744, "percentage": 29.29, "elapsed_time": "1:09:48", "remaining_time": "2:48:30"}
458
+ {"current_steps": 458, "total_steps": 1560, "loss": 0.3958, "lr": 8.901172514459864e-06, "epoch": 0.87936, "percentage": 29.36, "elapsed_time": "1:09:58", "remaining_time": "2:48:21"}
459
+ {"current_steps": 459, "total_steps": 1560, "loss": 0.3392, "lr": 8.894164799221099e-06, "epoch": 0.88128, "percentage": 29.42, "elapsed_time": "1:10:07", "remaining_time": "2:48:13"}
460
+ {"current_steps": 460, "total_steps": 1560, "loss": 0.3889, "lr": 8.88713758644883e-06, "epoch": 0.8832, "percentage": 29.49, "elapsed_time": "1:10:17", "remaining_time": "2:48:04"}
461
+ {"current_steps": 461, "total_steps": 1560, "loss": 0.4466, "lr": 8.88009091132732e-06, "epoch": 0.88512, "percentage": 29.55, "elapsed_time": "1:10:26", "remaining_time": "2:47:56"}
462
+ {"current_steps": 462, "total_steps": 1560, "loss": 0.3807, "lr": 8.873024809138272e-06, "epoch": 0.88704, "percentage": 29.62, "elapsed_time": "1:10:36", "remaining_time": "2:47:47"}
463
+ {"current_steps": 463, "total_steps": 1560, "loss": 0.3975, "lr": 8.86593931526067e-06, "epoch": 0.88896, "percentage": 29.68, "elapsed_time": "1:10:45", "remaining_time": "2:47:39"}
464
+ {"current_steps": 464, "total_steps": 1560, "loss": 0.3533, "lr": 8.858834465170576e-06, "epoch": 0.89088, "percentage": 29.74, "elapsed_time": "1:10:55", "remaining_time": "2:47:30"}
465
+ {"current_steps": 465, "total_steps": 1560, "loss": 0.5506, "lr": 8.851710294440974e-06, "epoch": 0.8928, "percentage": 29.81, "elapsed_time": "1:11:04", "remaining_time": "2:47:22"}
466
+ {"current_steps": 466, "total_steps": 1560, "loss": 0.3879, "lr": 8.84456683874158e-06, "epoch": 0.89472, "percentage": 29.87, "elapsed_time": "1:11:13", "remaining_time": "2:47:13"}
467
+ {"current_steps": 467, "total_steps": 1560, "loss": 0.3421, "lr": 8.837404133838667e-06, "epoch": 0.89664, "percentage": 29.94, "elapsed_time": "1:11:23", "remaining_time": "2:47:04"}
468
+ {"current_steps": 468, "total_steps": 1560, "loss": 0.3449, "lr": 8.83022221559489e-06, "epoch": 0.89856, "percentage": 30.0, "elapsed_time": "1:11:32", "remaining_time": "2:46:56"}
469
+ {"current_steps": 469, "total_steps": 1560, "loss": 0.336, "lr": 8.823021119969102e-06, "epoch": 0.90048, "percentage": 30.06, "elapsed_time": "1:11:41", "remaining_time": "2:46:47"}
470
+ {"current_steps": 470, "total_steps": 1560, "loss": 0.3793, "lr": 8.815800883016168e-06, "epoch": 0.9024, "percentage": 30.13, "elapsed_time": "1:11:50", "remaining_time": "2:46:37"}
471
+ {"current_steps": 471, "total_steps": 1560, "loss": 0.344, "lr": 8.808561540886796e-06, "epoch": 0.90432, "percentage": 30.19, "elapsed_time": "1:12:00", "remaining_time": "2:46:28"}
472
+ {"current_steps": 472, "total_steps": 1560, "loss": 0.4073, "lr": 8.801303129827352e-06, "epoch": 0.90624, "percentage": 30.26, "elapsed_time": "1:12:09", "remaining_time": "2:46:19"}
473
+ {"current_steps": 473, "total_steps": 1560, "loss": 0.5028, "lr": 8.794025686179677e-06, "epoch": 0.90816, "percentage": 30.32, "elapsed_time": "1:12:18", "remaining_time": "2:46:10"}
474
+ {"current_steps": 474, "total_steps": 1560, "loss": 0.407, "lr": 8.786729246380901e-06, "epoch": 0.91008, "percentage": 30.38, "elapsed_time": "1:12:27", "remaining_time": "2:46:00"}
475
+ {"current_steps": 475, "total_steps": 1560, "loss": 0.3154, "lr": 8.779413846963267e-06, "epoch": 0.912, "percentage": 30.45, "elapsed_time": "1:12:36", "remaining_time": "2:45:51"}
476
+ {"current_steps": 476, "total_steps": 1560, "loss": 0.3318, "lr": 8.772079524553951e-06, "epoch": 0.91392, "percentage": 30.51, "elapsed_time": "1:12:45", "remaining_time": "2:45:42"}
477
+ {"current_steps": 477, "total_steps": 1560, "loss": 0.3646, "lr": 8.764726315874872e-06, "epoch": 0.91584, "percentage": 30.58, "elapsed_time": "1:12:54", "remaining_time": "2:45:33"}
478
+ {"current_steps": 478, "total_steps": 1560, "loss": 0.3566, "lr": 8.757354257742501e-06, "epoch": 0.91776, "percentage": 30.64, "elapsed_time": "1:13:04", "remaining_time": "2:45:23"}
479
+ {"current_steps": 479, "total_steps": 1560, "loss": 0.3879, "lr": 8.749963387067697e-06, "epoch": 0.91968, "percentage": 30.71, "elapsed_time": "1:13:13", "remaining_time": "2:45:14"}
480
+ {"current_steps": 480, "total_steps": 1560, "loss": 0.4335, "lr": 8.742553740855507e-06, "epoch": 0.9216, "percentage": 30.77, "elapsed_time": "1:13:22", "remaining_time": "2:45:05"}
481
+ {"current_steps": 481, "total_steps": 1560, "loss": 0.3796, "lr": 8.735125356204982e-06, "epoch": 0.92352, "percentage": 30.83, "elapsed_time": "1:13:31", "remaining_time": "2:44:55"}
482
+ {"current_steps": 482, "total_steps": 1560, "loss": 0.4007, "lr": 8.727678270308994e-06, "epoch": 0.92544, "percentage": 30.9, "elapsed_time": "1:13:40", "remaining_time": "2:44:46"}
483
+ {"current_steps": 483, "total_steps": 1560, "loss": 0.3697, "lr": 8.720212520454054e-06, "epoch": 0.92736, "percentage": 30.96, "elapsed_time": "1:13:49", "remaining_time": "2:44:37"}
484
+ {"current_steps": 484, "total_steps": 1560, "loss": 0.3192, "lr": 8.712728144020118e-06, "epoch": 0.92928, "percentage": 31.03, "elapsed_time": "1:13:58", "remaining_time": "2:44:28"}
485
+ {"current_steps": 485, "total_steps": 1560, "loss": 0.3591, "lr": 8.705225178480397e-06, "epoch": 0.9312, "percentage": 31.09, "elapsed_time": "1:14:08", "remaining_time": "2:44:19"}
486
+ {"current_steps": 486, "total_steps": 1560, "loss": 0.4018, "lr": 8.697703661401187e-06, "epoch": 0.93312, "percentage": 31.15, "elapsed_time": "1:14:17", "remaining_time": "2:44:09"}
487
+ {"current_steps": 487, "total_steps": 1560, "loss": 0.4189, "lr": 8.69016363044166e-06, "epoch": 0.93504, "percentage": 31.22, "elapsed_time": "1:14:26", "remaining_time": "2:44:00"}
488
+ {"current_steps": 488, "total_steps": 1560, "loss": 0.4096, "lr": 8.682605123353685e-06, "epoch": 0.93696, "percentage": 31.28, "elapsed_time": "1:14:35", "remaining_time": "2:43:51"}
489
+ {"current_steps": 489, "total_steps": 1560, "loss": 0.3816, "lr": 8.675028177981643e-06, "epoch": 0.93888, "percentage": 31.35, "elapsed_time": "1:14:44", "remaining_time": "2:43:41"}
490
+ {"current_steps": 490, "total_steps": 1560, "loss": 0.3716, "lr": 8.66743283226223e-06, "epoch": 0.9408, "percentage": 31.41, "elapsed_time": "1:14:53", "remaining_time": "2:43:32"}
491
+ {"current_steps": 491, "total_steps": 1560, "loss": 0.3883, "lr": 8.659819124224266e-06, "epoch": 0.94272, "percentage": 31.47, "elapsed_time": "1:15:02", "remaining_time": "2:43:23"}
492
+ {"current_steps": 492, "total_steps": 1560, "loss": 0.3341, "lr": 8.652187091988516e-06, "epoch": 0.94464, "percentage": 31.54, "elapsed_time": "1:15:11", "remaining_time": "2:43:13"}
493
+ {"current_steps": 493, "total_steps": 1560, "loss": 0.3841, "lr": 8.644536773767488e-06, "epoch": 0.94656, "percentage": 31.6, "elapsed_time": "1:15:20", "remaining_time": "2:43:04"}
494
+ {"current_steps": 494, "total_steps": 1560, "loss": 0.368, "lr": 8.636868207865244e-06, "epoch": 0.94848, "percentage": 31.67, "elapsed_time": "1:15:29", "remaining_time": "2:42:54"}
495
+ {"current_steps": 495, "total_steps": 1560, "loss": 0.3644, "lr": 8.629181432677213e-06, "epoch": 0.9504, "percentage": 31.73, "elapsed_time": "1:15:39", "remaining_time": "2:42:45"}
496
+ {"current_steps": 496, "total_steps": 1560, "loss": 0.3889, "lr": 8.621476486689991e-06, "epoch": 0.95232, "percentage": 31.79, "elapsed_time": "1:15:48", "remaining_time": "2:42:36"}
497
+ {"current_steps": 497, "total_steps": 1560, "loss": 0.3731, "lr": 8.613753408481158e-06, "epoch": 0.95424, "percentage": 31.86, "elapsed_time": "1:15:57", "remaining_time": "2:42:27"}
498
+ {"current_steps": 498, "total_steps": 1560, "loss": 0.3358, "lr": 8.606012236719073e-06, "epoch": 0.95616, "percentage": 31.92, "elapsed_time": "1:16:06", "remaining_time": "2:42:18"}
499
+ {"current_steps": 499, "total_steps": 1560, "loss": 0.414, "lr": 8.598253010162693e-06, "epoch": 0.95808, "percentage": 31.99, "elapsed_time": "1:16:15", "remaining_time": "2:42:08"}
500
+ {"current_steps": 500, "total_steps": 1560, "loss": 0.3677, "lr": 8.590475767661371e-06, "epoch": 0.96, "percentage": 32.05, "elapsed_time": "1:16:24", "remaining_time": "2:41:59"}
501
+ {"current_steps": 501, "total_steps": 1560, "loss": 0.3405, "lr": 8.58268054815466e-06, "epoch": 0.96192, "percentage": 32.12, "elapsed_time": "1:16:33", "remaining_time": "2:41:50"}
502
+ {"current_steps": 502, "total_steps": 1560, "loss": 0.345, "lr": 8.574867390672124e-06, "epoch": 0.96384, "percentage": 32.18, "elapsed_time": "1:16:43", "remaining_time": "2:41:41"}
503
+ {"current_steps": 503, "total_steps": 1560, "loss": 0.4048, "lr": 8.567036334333142e-06, "epoch": 0.96576, "percentage": 32.24, "elapsed_time": "1:16:52", "remaining_time": "2:41:31"}
504
+ {"current_steps": 504, "total_steps": 1560, "loss": 0.3936, "lr": 8.559187418346703e-06, "epoch": 0.96768, "percentage": 32.31, "elapsed_time": "1:17:01", "remaining_time": "2:41:22"}
505
+ {"current_steps": 505, "total_steps": 1560, "loss": 0.3372, "lr": 8.551320682011227e-06, "epoch": 0.9696, "percentage": 32.37, "elapsed_time": "1:17:10", "remaining_time": "2:41:12"}
506
+ {"current_steps": 506, "total_steps": 1560, "loss": 0.3637, "lr": 8.543436164714351e-06, "epoch": 0.97152, "percentage": 32.44, "elapsed_time": "1:17:19", "remaining_time": "2:41:03"}
507
+ {"current_steps": 507, "total_steps": 1560, "loss": 0.3928, "lr": 8.535533905932739e-06, "epoch": 0.97344, "percentage": 32.5, "elapsed_time": "1:17:28", "remaining_time": "2:40:53"}
508
+ {"current_steps": 508, "total_steps": 1560, "loss": 0.4191, "lr": 8.527613945231886e-06, "epoch": 0.97536, "percentage": 32.56, "elapsed_time": "1:17:37", "remaining_time": "2:40:44"}
509
+ {"current_steps": 509, "total_steps": 1560, "loss": 0.369, "lr": 8.519676322265914e-06, "epoch": 0.97728, "percentage": 32.63, "elapsed_time": "1:17:46", "remaining_time": "2:40:35"}
510
+ {"current_steps": 510, "total_steps": 1560, "loss": 0.3451, "lr": 8.511721076777388e-06, "epoch": 0.9792, "percentage": 32.69, "elapsed_time": "1:17:55", "remaining_time": "2:40:26"}
511
+ {"current_steps": 511, "total_steps": 1560, "loss": 0.3263, "lr": 8.503748248597095e-06, "epoch": 0.98112, "percentage": 32.76, "elapsed_time": "1:18:04", "remaining_time": "2:40:16"}
512
+ {"current_steps": 512, "total_steps": 1560, "loss": 0.4522, "lr": 8.495757877643857e-06, "epoch": 0.98304, "percentage": 32.82, "elapsed_time": "1:18:13", "remaining_time": "2:40:07"}
513
+ {"current_steps": 513, "total_steps": 1560, "loss": 0.4172, "lr": 8.487750003924341e-06, "epoch": 0.98496, "percentage": 32.88, "elapsed_time": "1:18:22", "remaining_time": "2:39:58"}
514
+ {"current_steps": 514, "total_steps": 1560, "loss": 0.3667, "lr": 8.479724667532836e-06, "epoch": 0.98688, "percentage": 32.95, "elapsed_time": "1:18:32", "remaining_time": "2:39:49"}
515
+ {"current_steps": 515, "total_steps": 1560, "loss": 0.2908, "lr": 8.471681908651067e-06, "epoch": 0.9888, "percentage": 33.01, "elapsed_time": "1:18:41", "remaining_time": "2:39:40"}
516
+ {"current_steps": 516, "total_steps": 1560, "loss": 0.4177, "lr": 8.463621767547998e-06, "epoch": 0.99072, "percentage": 33.08, "elapsed_time": "1:18:50", "remaining_time": "2:39:31"}
517
+ {"current_steps": 517, "total_steps": 1560, "loss": 0.3326, "lr": 8.455544284579614e-06, "epoch": 0.99264, "percentage": 33.14, "elapsed_time": "1:18:59", "remaining_time": "2:39:22"}
518
+ {"current_steps": 518, "total_steps": 1560, "loss": 0.379, "lr": 8.447449500188731e-06, "epoch": 0.99456, "percentage": 33.21, "elapsed_time": "1:19:09", "remaining_time": "2:39:13"}
519
+ {"current_steps": 519, "total_steps": 1560, "loss": 0.3728, "lr": 8.439337454904794e-06, "epoch": 0.99648, "percentage": 33.27, "elapsed_time": "1:19:18", "remaining_time": "2:39:04"}
520
+ {"current_steps": 520, "total_steps": 1560, "loss": 0.3305, "lr": 8.43120818934367e-06, "epoch": 0.9984, "percentage": 33.33, "elapsed_time": "1:19:27", "remaining_time": "2:38:55"}
521
+ {"current_steps": 521, "total_steps": 1560, "loss": 0.5778, "lr": 8.42306174420744e-06, "epoch": 1.00128, "percentage": 33.4, "elapsed_time": "1:20:27", "remaining_time": "2:40:26"}
522
+ {"current_steps": 522, "total_steps": 1560, "loss": 0.3022, "lr": 8.414898160284208e-06, "epoch": 1.0032, "percentage": 33.46, "elapsed_time": "1:20:37", "remaining_time": "2:40:19"}
523
+ {"current_steps": 523, "total_steps": 1560, "loss": 0.2895, "lr": 8.406717478447889e-06, "epoch": 1.00512, "percentage": 33.53, "elapsed_time": "1:20:47", "remaining_time": "2:40:11"}
524
+ {"current_steps": 524, "total_steps": 1560, "loss": 0.3462, "lr": 8.398519739657997e-06, "epoch": 1.00704, "percentage": 33.59, "elapsed_time": "1:20:57", "remaining_time": "2:40:03"}
525
+ {"current_steps": 525, "total_steps": 1560, "loss": 0.2661, "lr": 8.390304984959455e-06, "epoch": 1.00896, "percentage": 33.65, "elapsed_time": "1:21:07", "remaining_time": "2:39:55"}
526
+ {"current_steps": 526, "total_steps": 1560, "loss": 0.3121, "lr": 8.382073255482381e-06, "epoch": 1.01088, "percentage": 33.72, "elapsed_time": "1:21:16", "remaining_time": "2:39:46"}
527
+ {"current_steps": 527, "total_steps": 1560, "loss": 0.3718, "lr": 8.373824592441884e-06, "epoch": 1.0128, "percentage": 33.78, "elapsed_time": "1:21:26", "remaining_time": "2:39:38"}
528
+ {"current_steps": 528, "total_steps": 1560, "loss": 0.3446, "lr": 8.36555903713785e-06, "epoch": 1.01472, "percentage": 33.85, "elapsed_time": "1:21:36", "remaining_time": "2:39:29"}
529
+ {"current_steps": 529, "total_steps": 1560, "loss": 0.3164, "lr": 8.357276630954756e-06, "epoch": 1.01664, "percentage": 33.91, "elapsed_time": "1:21:45", "remaining_time": "2:39:21"}
530
+ {"current_steps": 530, "total_steps": 1560, "loss": 0.3402, "lr": 8.348977415361435e-06, "epoch": 1.01856, "percentage": 33.97, "elapsed_time": "1:21:55", "remaining_time": "2:39:12"}
531
+ {"current_steps": 531, "total_steps": 1560, "loss": 0.304, "lr": 8.340661431910888e-06, "epoch": 1.02048, "percentage": 34.04, "elapsed_time": "1:22:04", "remaining_time": "2:39:03"}
532
+ {"current_steps": 532, "total_steps": 1560, "loss": 0.2542, "lr": 8.332328722240072e-06, "epoch": 1.0224, "percentage": 34.1, "elapsed_time": "1:22:14", "remaining_time": "2:38:55"}
533
+ {"current_steps": 533, "total_steps": 1560, "loss": 0.4216, "lr": 8.323979328069689e-06, "epoch": 1.02432, "percentage": 34.17, "elapsed_time": "1:22:24", "remaining_time": "2:38:46"}
534
+ {"current_steps": 534, "total_steps": 1560, "loss": 0.2848, "lr": 8.315613291203977e-06, "epoch": 1.02624, "percentage": 34.23, "elapsed_time": "1:22:33", "remaining_time": "2:38:37"}
535
+ {"current_steps": 535, "total_steps": 1560, "loss": 0.3351, "lr": 8.307230653530501e-06, "epoch": 1.02816, "percentage": 34.29, "elapsed_time": "1:22:43", "remaining_time": "2:38:28"}
536
+ {"current_steps": 536, "total_steps": 1560, "loss": 0.3382, "lr": 8.298831457019943e-06, "epoch": 1.03008, "percentage": 34.36, "elapsed_time": "1:22:52", "remaining_time": "2:38:18"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d842ed0e1367e3e7326fe1ab8884d3e1b8410c9b40999f9d6377e03f5183e2
3
+ size 7352
vocab.json ADDED
The diff for this file is too large to render. See raw diff