3N3G commited on
Commit
d0a42cb
·
verified ·
1 Parent(s): 6495b74

Training in progress, step 420

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 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
27
+ {%- if message.tool_calls %}
28
+ {%- for tool_call in message.tool_calls %}
29
+ {%- if (loop.first and content) or (not loop.first) %}
30
+ {{- '\n' }}
31
+ {%- endif %}
32
+ {%- if tool_call.function %}
33
+ {%- set tool_call = tool_call.function %}
34
+ {%- endif %}
35
+ {{- '<tool_call>\n{"name": "' }}
36
+ {{- tool_call.name }}
37
+ {{- '", "arguments": ' }}
38
+ {%- if tool_call.arguments is string %}
39
+ {{- tool_call.arguments }}
40
+ {%- else %}
41
+ {{- tool_call.arguments | tojson }}
42
+ {%- endif %}
43
+ {{- '}\n</tool_call>' }}
44
+ {%- endfor %}
45
+ {%- endif %}
46
+ {{- '<|im_end|>\n' }}
47
+ {%- elif message.role == "tool" %}
48
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
49
+ {{- '<|im_start|>user' }}
50
+ {%- endif %}
51
+ {{- '\n<tool_response>\n' }}
52
+ {{- content }}
53
+ {{- '\n</tool_response>' }}
54
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
55
+ {{- '<|im_end|>\n' }}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- endfor %}
59
+ {%- if add_generation_prompt %}
60
+ {{- '<|im_start|>assistant\n' }}
61
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 262144,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "rms_norm_eps": 1e-06,
59
+ "rope_scaling": null,
60
+ "rope_theta": 5000000,
61
+ "sliding_window": null,
62
+ "tie_word_embeddings": true,
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.55.0",
65
+ "use_cache": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
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 sha256:2b2a238ce8ff81c7e44636e1c0e073f188ca88da5bdbb8646d3b44f0c4659235
3
+ size 4990095032
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:411a065e94f0b73457df5dacf339efc77f4f9faaa632a11612f8a85d704a5b65
3
+ size 4944309096
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b001d04573fa303c7114053eabb415c7fdab64746ec39260aeac24b70947987
3
+ size 4996758848
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d384e87bbe697fcb8e3e8bfd32234880739ae6dc813dfb98754b39746ed7cc9
3
+ size 1158754848
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4022468096,
4
+ "total_size": 16089872384
5
+ },
6
+ "weight_map": {
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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
338
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
339
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
340
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
341
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
342
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
343
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
344
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
345
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
346
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
347
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
348
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
349
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
350
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
351
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
352
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
354
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
355
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
356
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
357
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
358
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
359
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
360
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
361
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
362
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
363
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
364
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
365
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
366
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
367
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
368
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
369
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
370
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
371
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
372
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
373
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
374
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
375
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
376
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
377
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
378
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
379
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
380
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
381
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
382
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
383
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
384
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
385
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
386
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
387
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
388
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
389
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
390
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
391
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
392
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
393
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
394
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
395
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
396
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
397
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
398
+ "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
399
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
400
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
401
+ "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
402
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
403
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
404
+ "model.norm.weight": "model-00004-of-00004.safetensors"
405
+ }
406
+ }
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": "<|im_end|>",
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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1010000,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 420, "loss": 0.2754, "lr": 0.0, "epoch": 0.02872531418312388, "percentage": 0.24, "elapsed_time": "0:00:20", "remaining_time": "2:23:16"}
2
+ {"current_steps": 2, "total_steps": 420, "loss": 0.2191, "lr": 2.3809523809523807e-08, "epoch": 0.05745062836624776, "percentage": 0.48, "elapsed_time": "0:00:36", "remaining_time": "2:06:48"}
3
+ {"current_steps": 3, "total_steps": 420, "loss": 0.308, "lr": 4.7619047619047613e-08, "epoch": 0.08617594254937164, "percentage": 0.71, "elapsed_time": "0:00:48", "remaining_time": "1:53:29"}
4
+ {"current_steps": 4, "total_steps": 420, "loss": 0.2802, "lr": 7.142857142857142e-08, "epoch": 0.11490125673249552, "percentage": 0.95, "elapsed_time": "0:01:05", "remaining_time": "1:53:02"}
5
+ {"current_steps": 5, "total_steps": 420, "loss": 0.2686, "lr": 9.523809523809523e-08, "epoch": 0.1436265709156194, "percentage": 1.19, "elapsed_time": "0:01:28", "remaining_time": "2:02:58"}
6
+ {"current_steps": 6, "total_steps": 420, "loss": 0.3074, "lr": 1.1904761904761903e-07, "epoch": 0.17235188509874327, "percentage": 1.43, "elapsed_time": "0:01:44", "remaining_time": "2:00:17"}
7
+ {"current_steps": 7, "total_steps": 420, "loss": 0.2911, "lr": 1.4285714285714285e-07, "epoch": 0.20107719928186715, "percentage": 1.67, "elapsed_time": "0:02:05", "remaining_time": "2:03:51"}
8
+ {"current_steps": 8, "total_steps": 420, "loss": 0.2894, "lr": 1.6666666666666665e-07, "epoch": 0.22980251346499103, "percentage": 1.9, "elapsed_time": "0:02:23", "remaining_time": "2:03:21"}
9
+ {"current_steps": 9, "total_steps": 420, "loss": 0.2735, "lr": 1.9047619047619045e-07, "epoch": 0.2585278276481149, "percentage": 2.14, "elapsed_time": "0:02:39", "remaining_time": "2:01:03"}
10
+ {"current_steps": 10, "total_steps": 420, "loss": 0.2652, "lr": 2.1428571428571426e-07, "epoch": 0.2872531418312388, "percentage": 2.38, "elapsed_time": "0:02:57", "remaining_time": "2:01:11"}
11
+ {"current_steps": 11, "total_steps": 420, "loss": 0.3147, "lr": 2.3809523809523806e-07, "epoch": 0.31597845601436264, "percentage": 2.62, "elapsed_time": "0:03:15", "remaining_time": "2:00:57"}
12
+ {"current_steps": 12, "total_steps": 420, "loss": 0.2321, "lr": 2.619047619047619e-07, "epoch": 0.34470377019748655, "percentage": 2.86, "elapsed_time": "0:03:32", "remaining_time": "2:00:18"}
13
+ {"current_steps": 13, "total_steps": 420, "loss": 0.3041, "lr": 2.857142857142857e-07, "epoch": 0.3734290843806104, "percentage": 3.1, "elapsed_time": "0:03:47", "remaining_time": "1:58:37"}
14
+ {"current_steps": 14, "total_steps": 420, "loss": 0.315, "lr": 3.095238095238095e-07, "epoch": 0.4021543985637343, "percentage": 3.33, "elapsed_time": "0:04:05", "remaining_time": "1:58:40"}
15
+ {"current_steps": 15, "total_steps": 420, "loss": 0.281, "lr": 3.333333333333333e-07, "epoch": 0.43087971274685816, "percentage": 3.57, "elapsed_time": "0:04:28", "remaining_time": "2:00:50"}
16
+ {"current_steps": 16, "total_steps": 420, "loss": 0.2979, "lr": 3.5714285714285716e-07, "epoch": 0.45960502692998206, "percentage": 3.81, "elapsed_time": "0:04:45", "remaining_time": "2:00:10"}
17
+ {"current_steps": 17, "total_steps": 420, "loss": 0.2455, "lr": 3.809523809523809e-07, "epoch": 0.4883303411131059, "percentage": 4.05, "elapsed_time": "0:05:02", "remaining_time": "1:59:26"}
18
+ {"current_steps": 18, "total_steps": 420, "loss": 0.3108, "lr": 4.0476190476190476e-07, "epoch": 0.5170556552962298, "percentage": 4.29, "elapsed_time": "0:05:21", "remaining_time": "1:59:50"}
19
+ {"current_steps": 19, "total_steps": 420, "loss": 0.2397, "lr": 4.285714285714285e-07, "epoch": 0.5457809694793537, "percentage": 4.52, "elapsed_time": "0:05:42", "remaining_time": "2:00:31"}
20
+ {"current_steps": 20, "total_steps": 420, "loss": 0.2947, "lr": 4.5238095238095237e-07, "epoch": 0.5745062836624776, "percentage": 4.76, "elapsed_time": "0:06:02", "remaining_time": "2:00:56"}
21
+ {"current_steps": 21, "total_steps": 420, "loss": 0.275, "lr": 4.761904761904761e-07, "epoch": 0.6032315978456014, "percentage": 5.0, "elapsed_time": "0:06:20", "remaining_time": "2:00:35"}
22
+ {"current_steps": 22, "total_steps": 420, "loss": 0.2366, "lr": 5e-07, "epoch": 0.6319569120287253, "percentage": 5.24, "elapsed_time": "0:06:44", "remaining_time": "2:02:00"}
23
+ {"current_steps": 23, "total_steps": 420, "loss": 0.2778, "lr": 5.238095238095238e-07, "epoch": 0.6606822262118492, "percentage": 5.48, "elapsed_time": "0:07:00", "remaining_time": "2:01:00"}
24
+ {"current_steps": 24, "total_steps": 420, "loss": 0.2872, "lr": 5.476190476190477e-07, "epoch": 0.6894075403949731, "percentage": 5.71, "elapsed_time": "0:07:15", "remaining_time": "1:59:48"}
25
+ {"current_steps": 25, "total_steps": 420, "loss": 0.2292, "lr": 5.714285714285714e-07, "epoch": 0.718132854578097, "percentage": 5.95, "elapsed_time": "0:07:33", "remaining_time": "1:59:20"}
26
+ {"current_steps": 26, "total_steps": 420, "loss": 0.2511, "lr": 5.952380952380952e-07, "epoch": 0.7468581687612208, "percentage": 6.19, "elapsed_time": "0:07:52", "remaining_time": "1:59:17"}
27
+ {"current_steps": 27, "total_steps": 420, "loss": 0.2567, "lr": 6.19047619047619e-07, "epoch": 0.7755834829443446, "percentage": 6.43, "elapsed_time": "0:08:07", "remaining_time": "1:58:17"}
28
+ {"current_steps": 28, "total_steps": 420, "loss": 0.2855, "lr": 6.428571428571429e-07, "epoch": 0.8043087971274686, "percentage": 6.67, "elapsed_time": "0:08:26", "remaining_time": "1:58:17"}
29
+ {"current_steps": 29, "total_steps": 420, "loss": 0.2521, "lr": 6.666666666666666e-07, "epoch": 0.8330341113105925, "percentage": 6.9, "elapsed_time": "0:08:46", "remaining_time": "1:58:25"}
30
+ {"current_steps": 30, "total_steps": 420, "loss": 0.2641, "lr": 6.904761904761904e-07, "epoch": 0.8617594254937163, "percentage": 7.14, "elapsed_time": "0:09:05", "remaining_time": "1:58:08"}
31
+ {"current_steps": 31, "total_steps": 420, "loss": 0.2611, "lr": 7.142857142857143e-07, "epoch": 0.8904847396768402, "percentage": 7.38, "elapsed_time": "0:09:22", "remaining_time": "1:57:41"}
32
+ {"current_steps": 32, "total_steps": 420, "loss": 0.2724, "lr": 7.380952380952381e-07, "epoch": 0.9192100538599641, "percentage": 7.62, "elapsed_time": "0:09:41", "remaining_time": "1:57:29"}
33
+ {"current_steps": 33, "total_steps": 420, "loss": 0.2275, "lr": 7.619047619047618e-07, "epoch": 0.947935368043088, "percentage": 7.86, "elapsed_time": "0:10:01", "remaining_time": "1:57:37"}
34
+ {"current_steps": 34, "total_steps": 420, "loss": 0.2553, "lr": 7.857142857142856e-07, "epoch": 0.9766606822262118, "percentage": 8.1, "elapsed_time": "0:10:18", "remaining_time": "1:56:58"}
35
+ {"current_steps": 35, "total_steps": 420, "loss": 0.2532, "lr": 8.095238095238095e-07, "epoch": 1.0, "percentage": 8.33, "elapsed_time": "0:10:29", "remaining_time": "1:55:19"}
36
+ {"current_steps": 36, "total_steps": 420, "loss": 0.2588, "lr": 8.333333333333333e-07, "epoch": 1.0287253141831239, "percentage": 8.57, "elapsed_time": "0:10:48", "remaining_time": "1:55:19"}
37
+ {"current_steps": 37, "total_steps": 420, "loss": 0.2236, "lr": 8.57142857142857e-07, "epoch": 1.0574506283662477, "percentage": 8.81, "elapsed_time": "0:11:07", "remaining_time": "1:55:05"}
38
+ {"current_steps": 38, "total_steps": 420, "loss": 0.2055, "lr": 8.809523809523809e-07, "epoch": 1.0861759425493716, "percentage": 9.05, "elapsed_time": "0:11:22", "remaining_time": "1:54:21"}
39
+ {"current_steps": 39, "total_steps": 420, "loss": 0.2207, "lr": 9.047619047619047e-07, "epoch": 1.1149012567324954, "percentage": 9.29, "elapsed_time": "0:11:43", "remaining_time": "1:54:33"}
40
+ {"current_steps": 40, "total_steps": 420, "loss": 0.2578, "lr": 9.285714285714285e-07, "epoch": 1.1436265709156195, "percentage": 9.52, "elapsed_time": "0:12:05", "remaining_time": "1:54:51"}
41
+ {"current_steps": 41, "total_steps": 420, "loss": 0.2696, "lr": 9.523809523809522e-07, "epoch": 1.1723518850987433, "percentage": 9.76, "elapsed_time": "0:12:19", "remaining_time": "1:53:53"}
42
+ {"current_steps": 42, "total_steps": 420, "loss": 0.2229, "lr": 9.761904761904762e-07, "epoch": 1.2010771992818672, "percentage": 10.0, "elapsed_time": "0:12:38", "remaining_time": "1:53:42"}
43
+ {"current_steps": 43, "total_steps": 420, "loss": 0.2213, "lr": 1e-06, "epoch": 1.229802513464991, "percentage": 10.24, "elapsed_time": "0:12:59", "remaining_time": "1:53:53"}
44
+ {"current_steps": 44, "total_steps": 420, "loss": 0.2633, "lr": 9.999827315381883e-07, "epoch": 1.2585278276481149, "percentage": 10.48, "elapsed_time": "0:13:15", "remaining_time": "1:53:16"}
45
+ {"current_steps": 45, "total_steps": 420, "loss": 0.2611, "lr": 9.999309273455528e-07, "epoch": 1.2872531418312387, "percentage": 10.71, "elapsed_time": "0:13:32", "remaining_time": "1:52:47"}
46
+ {"current_steps": 46, "total_steps": 420, "loss": 0.2095, "lr": 9.99844591000408e-07, "epoch": 1.3159784560143626, "percentage": 10.95, "elapsed_time": "0:13:49", "remaining_time": "1:52:25"}
47
+ {"current_steps": 47, "total_steps": 420, "loss": 0.2273, "lr": 9.997237284663378e-07, "epoch": 1.3447037701974867, "percentage": 11.19, "elapsed_time": "0:14:08", "remaining_time": "1:52:15"}
48
+ {"current_steps": 48, "total_steps": 420, "loss": 0.2367, "lr": 9.99568348091782e-07, "epoch": 1.3734290843806103, "percentage": 11.43, "elapsed_time": "0:14:27", "remaining_time": "1:52:05"}
49
+ {"current_steps": 49, "total_steps": 420, "loss": 0.2614, "lr": 9.99378460609461e-07, "epoch": 1.4021543985637344, "percentage": 11.67, "elapsed_time": "0:14:42", "remaining_time": "1:51:19"}
50
+ {"current_steps": 50, "total_steps": 420, "loss": 0.1956, "lr": 9.991540791356342e-07, "epoch": 1.4308797127468582, "percentage": 11.9, "elapsed_time": "0:15:02", "remaining_time": "1:51:21"}
51
+ {"current_steps": 51, "total_steps": 420, "loss": 0.2205, "lr": 9.988952191691923e-07, "epoch": 1.459605026929982, "percentage": 12.14, "elapsed_time": "0:15:25", "remaining_time": "1:51:39"}
52
+ {"current_steps": 52, "total_steps": 420, "loss": 0.2445, "lr": 9.986018985905899e-07, "epoch": 1.488330341113106, "percentage": 12.38, "elapsed_time": "0:15:42", "remaining_time": "1:51:13"}
53
+ {"current_steps": 53, "total_steps": 420, "loss": 0.2356, "lr": 9.982741376606077e-07, "epoch": 1.5170556552962298, "percentage": 12.62, "elapsed_time": "0:15:59", "remaining_time": "1:50:46"}
54
+ {"current_steps": 54, "total_steps": 420, "loss": 0.2071, "lr": 9.97911959018954e-07, "epoch": 1.5457809694793538, "percentage": 12.86, "elapsed_time": "0:16:17", "remaining_time": "1:50:22"}
55
+ {"current_steps": 55, "total_steps": 420, "loss": 0.2475, "lr": 9.975153876827007e-07, "epoch": 1.5745062836624775, "percentage": 13.1, "elapsed_time": "0:16:33", "remaining_time": "1:49:52"}
56
+ {"current_steps": 56, "total_steps": 420, "loss": 0.2465, "lr": 9.97084451044556e-07, "epoch": 1.6032315978456015, "percentage": 13.33, "elapsed_time": "0:16:54", "remaining_time": "1:49:52"}
57
+ {"current_steps": 57, "total_steps": 420, "loss": 0.1775, "lr": 9.966191788709714e-07, "epoch": 1.6319569120287252, "percentage": 13.57, "elapsed_time": "0:17:12", "remaining_time": "1:49:35"}
58
+ {"current_steps": 58, "total_steps": 420, "loss": 0.2111, "lr": 9.961196033000861e-07, "epoch": 1.6606822262118492, "percentage": 13.81, "elapsed_time": "0:17:28", "remaining_time": "1:49:06"}
59
+ {"current_steps": 59, "total_steps": 420, "loss": 0.2087, "lr": 9.955857588395063e-07, "epoch": 1.689407540394973, "percentage": 14.05, "elapsed_time": "0:17:46", "remaining_time": "1:48:45"}
60
+ {"current_steps": 60, "total_steps": 420, "loss": 0.213, "lr": 9.950176823639232e-07, "epoch": 1.718132854578097, "percentage": 14.29, "elapsed_time": "0:18:07", "remaining_time": "1:48:42"}
61
+ {"current_steps": 61, "total_steps": 420, "loss": 0.1976, "lr": 9.944154131125642e-07, "epoch": 1.7468581687612208, "percentage": 14.52, "elapsed_time": "0:18:24", "remaining_time": "1:48:18"}
62
+ {"current_steps": 62, "total_steps": 420, "loss": 0.2022, "lr": 9.937789926864837e-07, "epoch": 1.7755834829443446, "percentage": 14.76, "elapsed_time": "0:18:41", "remaining_time": "1:47:56"}
63
+ {"current_steps": 63, "total_steps": 420, "loss": 0.2589, "lr": 9.931084650456891e-07, "epoch": 1.8043087971274687, "percentage": 15.0, "elapsed_time": "0:19:02", "remaining_time": "1:47:54"}
64
+ {"current_steps": 64, "total_steps": 420, "loss": 0.1977, "lr": 9.92403876506104e-07, "epoch": 1.8330341113105924, "percentage": 15.24, "elapsed_time": "0:19:15", "remaining_time": "1:47:09"}
65
+ {"current_steps": 65, "total_steps": 420, "loss": 0.2154, "lr": 9.916652757363697e-07, "epoch": 1.8617594254937164, "percentage": 15.48, "elapsed_time": "0:19:35", "remaining_time": "1:46:58"}
66
+ {"current_steps": 66, "total_steps": 420, "loss": 0.161, "lr": 9.90892713754483e-07, "epoch": 1.89048473967684, "percentage": 15.71, "elapsed_time": "0:19:47", "remaining_time": "1:46:11"}
67
+ {"current_steps": 67, "total_steps": 420, "loss": 0.2235, "lr": 9.900862439242718e-07, "epoch": 1.9192100538599641, "percentage": 15.95, "elapsed_time": "0:20:04", "remaining_time": "1:45:44"}
68
+ {"current_steps": 68, "total_steps": 420, "loss": 0.216, "lr": 9.892459219517106e-07, "epoch": 1.947935368043088, "percentage": 16.19, "elapsed_time": "0:20:21", "remaining_time": "1:45:23"}
69
+ {"current_steps": 69, "total_steps": 420, "loss": 0.1773, "lr": 9.883718058810706e-07, "epoch": 1.9766606822262118, "percentage": 16.43, "elapsed_time": "0:20:39", "remaining_time": "1:45:06"}
70
+ {"current_steps": 70, "total_steps": 420, "loss": 0.1843, "lr": 9.874639560909118e-07, "epoch": 2.0, "percentage": 16.67, "elapsed_time": "0:20:49", "remaining_time": "1:44:06"}
71
+ {"current_steps": 71, "total_steps": 420, "loss": 0.2078, "lr": 9.865224352899118e-07, "epoch": 2.028725314183124, "percentage": 16.9, "elapsed_time": "0:21:05", "remaining_time": "1:43:40"}
72
+ {"current_steps": 72, "total_steps": 420, "loss": 0.2294, "lr": 9.85547308512535e-07, "epoch": 2.0574506283662477, "percentage": 17.14, "elapsed_time": "0:21:24", "remaining_time": "1:43:28"}
73
+ {"current_steps": 73, "total_steps": 420, "loss": 0.1937, "lr": 9.84538643114539e-07, "epoch": 2.0861759425493718, "percentage": 17.38, "elapsed_time": "0:21:39", "remaining_time": "1:42:58"}
74
+ {"current_steps": 74, "total_steps": 420, "loss": 0.1996, "lr": 9.834965087683235e-07, "epoch": 2.1149012567324954, "percentage": 17.62, "elapsed_time": "0:21:59", "remaining_time": "1:42:48"}
75
+ {"current_steps": 75, "total_steps": 420, "loss": 0.1912, "lr": 9.824209774581174e-07, "epoch": 2.1436265709156195, "percentage": 17.86, "elapsed_time": "0:22:18", "remaining_time": "1:42:37"}
76
+ {"current_steps": 76, "total_steps": 420, "loss": 0.2135, "lr": 9.81312123475006e-07, "epoch": 2.172351885098743, "percentage": 18.1, "elapsed_time": "0:22:35", "remaining_time": "1:42:17"}
77
+ {"current_steps": 77, "total_steps": 420, "loss": 0.1912, "lr": 9.801700234117998e-07, "epoch": 2.201077199281867, "percentage": 18.33, "elapsed_time": "0:22:54", "remaining_time": "1:42:03"}
78
+ {"current_steps": 78, "total_steps": 420, "loss": 0.1687, "lr": 9.789947561577443e-07, "epoch": 2.229802513464991, "percentage": 18.57, "elapsed_time": "0:23:10", "remaining_time": "1:41:37"}
79
+ {"current_steps": 79, "total_steps": 420, "loss": 0.1979, "lr": 9.777864028930705e-07, "epoch": 2.258527827648115, "percentage": 18.81, "elapsed_time": "0:23:26", "remaining_time": "1:41:09"}
80
+ {"current_steps": 80, "total_steps": 420, "loss": 0.178, "lr": 9.765450470833865e-07, "epoch": 2.287253141831239, "percentage": 19.05, "elapsed_time": "0:23:44", "remaining_time": "1:40:55"}
81
+ {"current_steps": 81, "total_steps": 420, "loss": 0.2005, "lr": 9.752707744739144e-07, "epoch": 2.3159784560143626, "percentage": 19.29, "elapsed_time": "0:23:58", "remaining_time": "1:40:21"}
82
+ {"current_steps": 82, "total_steps": 420, "loss": 0.1795, "lr": 9.739636730835659e-07, "epoch": 2.3447037701974867, "percentage": 19.52, "elapsed_time": "0:24:11", "remaining_time": "1:39:42"}
83
+ {"current_steps": 83, "total_steps": 420, "loss": 0.1738, "lr": 9.726238331988623e-07, "epoch": 2.3734290843806103, "percentage": 19.76, "elapsed_time": "0:24:29", "remaining_time": "1:39:25"}
84
+ {"current_steps": 84, "total_steps": 420, "loss": 0.2224, "lr": 9.712513473676995e-07, "epoch": 2.4021543985637344, "percentage": 20.0, "elapsed_time": "0:24:48", "remaining_time": "1:39:12"}
85
+ {"current_steps": 85, "total_steps": 420, "loss": 0.1907, "lr": 9.698463103929541e-07, "epoch": 2.430879712746858, "percentage": 20.24, "elapsed_time": "0:25:07", "remaining_time": "1:39:03"}
86
+ {"current_steps": 86, "total_steps": 420, "loss": 0.2033, "lr": 9.684088193259353e-07, "epoch": 2.459605026929982, "percentage": 20.48, "elapsed_time": "0:25:27", "remaining_time": "1:38:50"}
87
+ {"current_steps": 87, "total_steps": 420, "loss": 0.1858, "lr": 9.669389734596819e-07, "epoch": 2.488330341113106, "percentage": 20.71, "elapsed_time": "0:25:44", "remaining_time": "1:38:33"}
88
+ {"current_steps": 88, "total_steps": 420, "loss": 0.2039, "lr": 9.65436874322102e-07, "epoch": 2.5170556552962298, "percentage": 20.95, "elapsed_time": "0:26:00", "remaining_time": "1:38:09"}
89
+ {"current_steps": 89, "total_steps": 420, "loss": 0.2209, "lr": 9.639026256689626e-07, "epoch": 2.545780969479354, "percentage": 21.19, "elapsed_time": "0:26:19", "remaining_time": "1:37:54"}
90
+ {"current_steps": 90, "total_steps": 420, "loss": 0.1787, "lr": 9.623363334767208e-07, "epoch": 2.5745062836624775, "percentage": 21.43, "elapsed_time": "0:26:39", "remaining_time": "1:37:43"}
91
+ {"current_steps": 91, "total_steps": 420, "loss": 0.2024, "lr": 9.607381059352038e-07, "epoch": 2.6032315978456015, "percentage": 21.67, "elapsed_time": "0:26:57", "remaining_time": "1:37:29"}
92
+ {"current_steps": 92, "total_steps": 420, "loss": 0.1829, "lr": 9.591080534401371e-07, "epoch": 2.631956912028725, "percentage": 21.9, "elapsed_time": "0:27:12", "remaining_time": "1:36:59"}
93
+ {"current_steps": 93, "total_steps": 420, "loss": 0.2117, "lr": 9.574462885855172e-07, "epoch": 2.6606822262118492, "percentage": 22.14, "elapsed_time": "0:27:33", "remaining_time": "1:36:52"}
94
+ {"current_steps": 94, "total_steps": 420, "loss": 0.2155, "lr": 9.557529261558366e-07, "epoch": 2.6894075403949733, "percentage": 22.38, "elapsed_time": "0:27:51", "remaining_time": "1:36:38"}
95
+ {"current_steps": 95, "total_steps": 420, "loss": 0.1934, "lr": 9.540280831181524e-07, "epoch": 2.718132854578097, "percentage": 22.62, "elapsed_time": "0:28:09", "remaining_time": "1:36:19"}
96
+ {"current_steps": 96, "total_steps": 420, "loss": 0.1778, "lr": 9.522718786140096e-07, "epoch": 2.7468581687612206, "percentage": 22.86, "elapsed_time": "0:28:28", "remaining_time": "1:36:07"}
97
+ {"current_steps": 97, "total_steps": 420, "loss": 0.1844, "lr": 9.504844339512094e-07, "epoch": 2.7755834829443446, "percentage": 23.1, "elapsed_time": "0:28:44", "remaining_time": "1:35:43"}
98
+ {"current_steps": 98, "total_steps": 420, "loss": 0.1823, "lr": 9.48665872595432e-07, "epoch": 2.8043087971274687, "percentage": 23.33, "elapsed_time": "0:29:03", "remaining_time": "1:35:27"}
99
+ {"current_steps": 99, "total_steps": 420, "loss": 0.1963, "lr": 9.468163201617061e-07, "epoch": 2.8330341113105924, "percentage": 23.57, "elapsed_time": "0:29:25", "remaining_time": "1:35:23"}
100
+ {"current_steps": 100, "total_steps": 420, "loss": 0.1809, "lr": 9.449359044057343e-07, "epoch": 2.8617594254937164, "percentage": 23.81, "elapsed_time": "0:29:44", "remaining_time": "1:35:09"}
101
+ {"current_steps": 101, "total_steps": 420, "loss": 0.1843, "lr": 9.430247552150672e-07, "epoch": 2.89048473967684, "percentage": 24.05, "elapsed_time": "0:29:59", "remaining_time": "1:34:42"}
102
+ {"current_steps": 102, "total_steps": 420, "loss": 0.1666, "lr": 9.41083004600132e-07, "epoch": 2.919210053859964, "percentage": 24.29, "elapsed_time": "0:30:16", "remaining_time": "1:34:23"}
103
+ {"current_steps": 103, "total_steps": 420, "loss": 0.1977, "lr": 9.391107866851142e-07, "epoch": 2.9479353680430878, "percentage": 24.52, "elapsed_time": "0:30:34", "remaining_time": "1:34:06"}
104
+ {"current_steps": 104, "total_steps": 420, "loss": 0.1783, "lr": 9.371082376986927e-07, "epoch": 2.976660682226212, "percentage": 24.76, "elapsed_time": "0:30:50", "remaining_time": "1:33:43"}
105
+ {"current_steps": 105, "total_steps": 420, "loss": 0.2088, "lr": 9.350754959646306e-07, "epoch": 3.0, "percentage": 25.0, "elapsed_time": "0:31:08", "remaining_time": "1:33:26"}
106
+ {"current_steps": 106, "total_steps": 420, "loss": 0.1901, "lr": 9.330127018922193e-07, "epoch": 3.028725314183124, "percentage": 25.24, "elapsed_time": "0:31:24", "remaining_time": "1:33:01"}
107
+ {"current_steps": 107, "total_steps": 420, "loss": 0.1987, "lr": 9.30919997966582e-07, "epoch": 3.0574506283662477, "percentage": 25.48, "elapsed_time": "0:31:39", "remaining_time": "1:32:36"}
108
+ {"current_steps": 108, "total_steps": 420, "loss": 0.1798, "lr": 9.287975287388296e-07, "epoch": 3.0861759425493718, "percentage": 25.71, "elapsed_time": "0:31:55", "remaining_time": "1:32:12"}
109
+ {"current_steps": 109, "total_steps": 420, "loss": 0.1918, "lr": 9.266454408160777e-07, "epoch": 3.1149012567324954, "percentage": 25.95, "elapsed_time": "0:32:14", "remaining_time": "1:31:59"}
110
+ {"current_steps": 110, "total_steps": 420, "loss": 0.1915, "lr": 9.244638828513187e-07, "epoch": 3.1436265709156195, "percentage": 26.19, "elapsed_time": "0:32:34", "remaining_time": "1:31:48"}
111
+ {"current_steps": 111, "total_steps": 420, "loss": 0.1794, "lr": 9.222530055331539e-07, "epoch": 3.172351885098743, "percentage": 26.43, "elapsed_time": "0:32:51", "remaining_time": "1:31:27"}
112
+ {"current_steps": 112, "total_steps": 420, "loss": 0.193, "lr": 9.200129615753858e-07, "epoch": 3.201077199281867, "percentage": 26.67, "elapsed_time": "0:33:08", "remaining_time": "1:31:07"}
113
+ {"current_steps": 113, "total_steps": 420, "loss": 0.1844, "lr": 9.177439057064682e-07, "epoch": 3.229802513464991, "percentage": 26.9, "elapsed_time": "0:33:24", "remaining_time": "1:30:47"}
114
+ {"current_steps": 114, "total_steps": 420, "loss": 0.1518, "lr": 9.154459946588198e-07, "epoch": 3.258527827648115, "percentage": 27.14, "elapsed_time": "0:33:39", "remaining_time": "1:30:22"}
115
+ {"current_steps": 115, "total_steps": 420, "loss": 0.1796, "lr": 9.131193871579974e-07, "epoch": 3.287253141831239, "percentage": 27.38, "elapsed_time": "0:33:56", "remaining_time": "1:30:01"}
116
+ {"current_steps": 116, "total_steps": 420, "loss": 0.1923, "lr": 9.10764243911732e-07, "epoch": 3.3159784560143626, "percentage": 27.62, "elapsed_time": "0:34:14", "remaining_time": "1:29:44"}
117
+ {"current_steps": 117, "total_steps": 420, "loss": 0.2229, "lr": 9.083807275988283e-07, "epoch": 3.3447037701974867, "percentage": 27.86, "elapsed_time": "0:34:28", "remaining_time": "1:29:16"}
118
+ {"current_steps": 118, "total_steps": 420, "loss": 0.1804, "lr": 9.059690028579283e-07, "epoch": 3.3734290843806103, "percentage": 28.1, "elapsed_time": "0:34:52", "remaining_time": "1:29:14"}
119
+ {"current_steps": 119, "total_steps": 420, "loss": 0.1547, "lr": 9.03529236276138e-07, "epoch": 3.4021543985637344, "percentage": 28.33, "elapsed_time": "0:35:09", "remaining_time": "1:28:54"}
120
+ {"current_steps": 120, "total_steps": 420, "loss": 0.1947, "lr": 9.010615963775219e-07, "epoch": 3.430879712746858, "percentage": 28.57, "elapsed_time": "0:35:27", "remaining_time": "1:28:39"}
121
+ {"current_steps": 121, "total_steps": 420, "loss": 0.1593, "lr": 8.985662536114612e-07, "epoch": 3.459605026929982, "percentage": 28.81, "elapsed_time": "0:35:46", "remaining_time": "1:28:23"}
122
+ {"current_steps": 122, "total_steps": 420, "loss": 0.1911, "lr": 8.960433803408811e-07, "epoch": 3.488330341113106, "percentage": 29.05, "elapsed_time": "0:36:05", "remaining_time": "1:28:09"}
123
+ {"current_steps": 123, "total_steps": 420, "loss": 0.1585, "lr": 8.934931508303445e-07, "epoch": 3.5170556552962298, "percentage": 29.29, "elapsed_time": "0:36:24", "remaining_time": "1:27:55"}
124
+ {"current_steps": 124, "total_steps": 420, "loss": 0.1605, "lr": 8.909157412340149e-07, "epoch": 3.545780969479354, "percentage": 29.52, "elapsed_time": "0:36:40", "remaining_time": "1:27:33"}
125
+ {"current_steps": 125, "total_steps": 420, "loss": 0.1657, "lr": 8.883113295834892e-07, "epoch": 3.5745062836624775, "percentage": 29.76, "elapsed_time": "0:37:00", "remaining_time": "1:27:21"}
126
+ {"current_steps": 126, "total_steps": 420, "loss": 0.1543, "lr": 8.856800957754998e-07, "epoch": 3.6032315978456015, "percentage": 30.0, "elapsed_time": "0:37:19", "remaining_time": "1:27:04"}
127
+ {"current_steps": 127, "total_steps": 420, "loss": 0.1856, "lr": 8.83022221559489e-07, "epoch": 3.631956912028725, "percentage": 30.24, "elapsed_time": "0:37:35", "remaining_time": "1:26:42"}
128
+ {"current_steps": 128, "total_steps": 420, "loss": 0.1617, "lr": 8.803378905250542e-07, "epoch": 3.6606822262118492, "percentage": 30.48, "elapsed_time": "0:37:54", "remaining_time": "1:26:29"}
129
+ {"current_steps": 129, "total_steps": 420, "loss": 0.2072, "lr": 8.776272880892675e-07, "epoch": 3.6894075403949733, "percentage": 30.71, "elapsed_time": "0:38:09", "remaining_time": "1:26:04"}
130
+ {"current_steps": 130, "total_steps": 420, "loss": 0.1846, "lr": 8.74890601483867e-07, "epoch": 3.718132854578097, "percentage": 30.95, "elapsed_time": "0:38:29", "remaining_time": "1:25:51"}
131
+ {"current_steps": 131, "total_steps": 420, "loss": 0.1926, "lr": 8.721280197423258e-07, "epoch": 3.7468581687612206, "percentage": 31.19, "elapsed_time": "0:38:44", "remaining_time": "1:25:28"}
132
+ {"current_steps": 132, "total_steps": 420, "loss": 0.2021, "lr": 8.693397336867929e-07, "epoch": 3.7755834829443446, "percentage": 31.43, "elapsed_time": "0:39:02", "remaining_time": "1:25:10"}
133
+ {"current_steps": 133, "total_steps": 420, "loss": 0.1688, "lr": 8.66525935914913e-07, "epoch": 3.8043087971274687, "percentage": 31.67, "elapsed_time": "0:39:23", "remaining_time": "1:24:59"}
134
+ {"current_steps": 134, "total_steps": 420, "loss": 0.1841, "lr": 8.636868207865243e-07, "epoch": 3.8330341113105924, "percentage": 31.9, "elapsed_time": "0:39:38", "remaining_time": "1:24:35"}
135
+ {"current_steps": 135, "total_steps": 420, "loss": 0.1881, "lr": 8.60822584410231e-07, "epoch": 3.8617594254937164, "percentage": 32.14, "elapsed_time": "0:39:55", "remaining_time": "1:24:16"}
136
+ {"current_steps": 136, "total_steps": 420, "loss": 0.2054, "lr": 8.579334246298592e-07, "epoch": 3.89048473967684, "percentage": 32.38, "elapsed_time": "0:40:16", "remaining_time": "1:24:05"}
137
+ {"current_steps": 137, "total_steps": 420, "loss": 0.1661, "lr": 8.550195410107901e-07, "epoch": 3.919210053859964, "percentage": 32.62, "elapsed_time": "0:40:37", "remaining_time": "1:23:55"}
138
+ {"current_steps": 138, "total_steps": 420, "loss": 0.1428, "lr": 8.520811348261758e-07, "epoch": 3.9479353680430878, "percentage": 32.86, "elapsed_time": "0:40:57", "remaining_time": "1:23:41"}
139
+ {"current_steps": 139, "total_steps": 420, "loss": 0.1662, "lr": 8.491184090430363e-07, "epoch": 3.976660682226212, "percentage": 33.1, "elapsed_time": "0:41:15", "remaining_time": "1:23:24"}
140
+ {"current_steps": 140, "total_steps": 420, "loss": 0.1585, "lr": 8.461315683082397e-07, "epoch": 4.0, "percentage": 33.33, "elapsed_time": "0:41:30", "remaining_time": "1:23:00"}
141
+ {"current_steps": 141, "total_steps": 420, "loss": 0.177, "lr": 8.431208189343669e-07, "epoch": 4.028725314183124, "percentage": 33.57, "elapsed_time": "0:41:46", "remaining_time": "1:22:40"}
142
+ {"current_steps": 142, "total_steps": 420, "loss": 0.1634, "lr": 8.400863688854596e-07, "epoch": 4.057450628366248, "percentage": 33.81, "elapsed_time": "0:42:02", "remaining_time": "1:22:17"}
143
+ {"current_steps": 143, "total_steps": 420, "loss": 0.1466, "lr": 8.370284277626575e-07, "epoch": 4.086175942549372, "percentage": 34.05, "elapsed_time": "0:42:24", "remaining_time": "1:22:09"}
144
+ {"current_steps": 144, "total_steps": 420, "loss": 0.1802, "lr": 8.339472067897187e-07, "epoch": 4.114901256732495, "percentage": 34.29, "elapsed_time": "0:42:40", "remaining_time": "1:21:48"}
145
+ {"current_steps": 145, "total_steps": 420, "loss": 0.1789, "lr": 8.308429187984298e-07, "epoch": 4.143626570915619, "percentage": 34.52, "elapsed_time": "0:42:57", "remaining_time": "1:21:28"}
146
+ {"current_steps": 146, "total_steps": 420, "loss": 0.1563, "lr": 8.27715778213905e-07, "epoch": 4.1723518850987436, "percentage": 34.76, "elapsed_time": "0:43:16", "remaining_time": "1:21:12"}
147
+ {"current_steps": 147, "total_steps": 420, "loss": 0.1642, "lr": 8.24566001039776e-07, "epoch": 4.201077199281867, "percentage": 35.0, "elapsed_time": "0:43:30", "remaining_time": "1:20:48"}
148
+ {"current_steps": 148, "total_steps": 420, "loss": 0.1571, "lr": 8.213938048432696e-07, "epoch": 4.229802513464991, "percentage": 35.24, "elapsed_time": "0:43:49", "remaining_time": "1:20:33"}
149
+ {"current_steps": 149, "total_steps": 420, "loss": 0.193, "lr": 8.181994087401818e-07, "epoch": 4.258527827648114, "percentage": 35.48, "elapsed_time": "0:44:06", "remaining_time": "1:20:13"}
150
+ {"current_steps": 150, "total_steps": 420, "loss": 0.1785, "lr": 8.149830333797406e-07, "epoch": 4.287253141831239, "percentage": 35.71, "elapsed_time": "0:44:24", "remaining_time": "1:19:56"}
151
+ {"current_steps": 151, "total_steps": 420, "loss": 0.1828, "lr": 8.117449009293668e-07, "epoch": 4.315978456014363, "percentage": 35.95, "elapsed_time": "0:44:45", "remaining_time": "1:19:44"}
152
+ {"current_steps": 152, "total_steps": 420, "loss": 0.162, "lr": 8.084852350593263e-07, "epoch": 4.344703770197486, "percentage": 36.19, "elapsed_time": "0:45:02", "remaining_time": "1:19:25"}
153
+ {"current_steps": 153, "total_steps": 420, "loss": 0.1832, "lr": 8.052042609272815e-07, "epoch": 4.373429084380611, "percentage": 36.43, "elapsed_time": "0:45:22", "remaining_time": "1:19:10"}
154
+ {"current_steps": 154, "total_steps": 420, "loss": 0.1962, "lr": 8.019022051627387e-07, "epoch": 4.402154398563734, "percentage": 36.67, "elapsed_time": "0:45:36", "remaining_time": "1:18:46"}
155
+ {"current_steps": 155, "total_steps": 420, "loss": 0.1671, "lr": 7.985792958513931e-07, "epoch": 4.430879712746858, "percentage": 36.9, "elapsed_time": "0:45:54", "remaining_time": "1:18:29"}
156
+ {"current_steps": 156, "total_steps": 420, "loss": 0.1961, "lr": 7.952357625193748e-07, "epoch": 4.459605026929982, "percentage": 37.14, "elapsed_time": "0:46:12", "remaining_time": "1:18:12"}
157
+ {"current_steps": 157, "total_steps": 420, "loss": 0.1927, "lr": 7.91871836117395e-07, "epoch": 4.488330341113106, "percentage": 37.38, "elapsed_time": "0:46:30", "remaining_time": "1:17:54"}
158
+ {"current_steps": 158, "total_steps": 420, "loss": 0.1949, "lr": 7.884877490047914e-07, "epoch": 4.51705565529623, "percentage": 37.62, "elapsed_time": "0:46:43", "remaining_time": "1:17:28"}
159
+ {"current_steps": 159, "total_steps": 420, "loss": 0.1629, "lr": 7.850837349334809e-07, "epoch": 4.545780969479353, "percentage": 37.86, "elapsed_time": "0:47:05", "remaining_time": "1:17:18"}
160
+ {"current_steps": 160, "total_steps": 420, "loss": 0.1459, "lr": 7.81660029031811e-07, "epoch": 4.574506283662478, "percentage": 38.1, "elapsed_time": "0:47:20", "remaining_time": "1:16:55"}
161
+ {"current_steps": 161, "total_steps": 420, "loss": 0.1466, "lr": 7.782168677883205e-07, "epoch": 4.6032315978456015, "percentage": 38.33, "elapsed_time": "0:47:38", "remaining_time": "1:16:39"}
162
+ {"current_steps": 162, "total_steps": 420, "loss": 0.1451, "lr": 7.74754489035403e-07, "epoch": 4.631956912028725, "percentage": 38.57, "elapsed_time": "0:47:56", "remaining_time": "1:16:20"}
163
+ {"current_steps": 163, "total_steps": 420, "loss": 0.1772, "lr": 7.712731319328797e-07, "epoch": 4.660682226211849, "percentage": 38.81, "elapsed_time": "0:48:15", "remaining_time": "1:16:04"}
164
+ {"current_steps": 164, "total_steps": 420, "loss": 0.1572, "lr": 7.677730369514792e-07, "epoch": 4.689407540394973, "percentage": 39.05, "elapsed_time": "0:48:38", "remaining_time": "1:15:55"}
165
+ {"current_steps": 165, "total_steps": 420, "loss": 0.1621, "lr": 7.642544458562277e-07, "epoch": 4.718132854578097, "percentage": 39.29, "elapsed_time": "0:48:55", "remaining_time": "1:15:36"}
166
+ {"current_steps": 166, "total_steps": 420, "loss": 0.1743, "lr": 7.60717601689749e-07, "epoch": 4.746858168761221, "percentage": 39.52, "elapsed_time": "0:49:14", "remaining_time": "1:15:20"}
167
+ {"current_steps": 167, "total_steps": 420, "loss": 0.1476, "lr": 7.571627487554768e-07, "epoch": 4.775583482944345, "percentage": 39.76, "elapsed_time": "0:49:28", "remaining_time": "1:14:57"}
168
+ {"current_steps": 168, "total_steps": 420, "loss": 0.1515, "lr": 7.535901326007796e-07, "epoch": 4.804308797127469, "percentage": 40.0, "elapsed_time": "0:49:49", "remaining_time": "1:14:44"}
169
+ {"current_steps": 169, "total_steps": 420, "loss": 0.1822, "lr": 7.5e-07, "epoch": 4.833034111310592, "percentage": 40.24, "elapsed_time": "0:50:07", "remaining_time": "1:14:26"}
170
+ {"current_steps": 170, "total_steps": 420, "loss": 0.1582, "lr": 7.463925989374088e-07, "epoch": 4.861759425493716, "percentage": 40.48, "elapsed_time": "0:50:27", "remaining_time": "1:14:12"}
171
+ {"current_steps": 171, "total_steps": 420, "loss": 0.1477, "lr": 7.427681785900761e-07, "epoch": 4.8904847396768405, "percentage": 40.71, "elapsed_time": "0:50:50", "remaining_time": "1:14:01"}
172
+ {"current_steps": 172, "total_steps": 420, "loss": 0.1079, "lr": 7.391269893106591e-07, "epoch": 4.919210053859964, "percentage": 40.95, "elapsed_time": "0:51:03", "remaining_time": "1:13:37"}
173
+ {"current_steps": 173, "total_steps": 420, "loss": 0.1601, "lr": 7.3546928261011e-07, "epoch": 4.947935368043088, "percentage": 41.19, "elapsed_time": "0:51:14", "remaining_time": "1:13:09"}
174
+ {"current_steps": 174, "total_steps": 420, "loss": 0.1908, "lr": 7.317953111403028e-07, "epoch": 4.976660682226212, "percentage": 41.43, "elapsed_time": "0:51:32", "remaining_time": "1:12:52"}
175
+ {"current_steps": 175, "total_steps": 420, "loss": 0.1554, "lr": 7.281053286765815e-07, "epoch": 5.0, "percentage": 41.67, "elapsed_time": "0:51:49", "remaining_time": "1:12:33"}
176
+ {"current_steps": 176, "total_steps": 420, "loss": 0.1835, "lr": 7.243995901002311e-07, "epoch": 5.028725314183124, "percentage": 41.9, "elapsed_time": "0:52:05", "remaining_time": "1:12:13"}
177
+ {"current_steps": 177, "total_steps": 420, "loss": 0.1691, "lr": 7.206783513808719e-07, "epoch": 5.057450628366248, "percentage": 42.14, "elapsed_time": "0:52:27", "remaining_time": "1:12:01"}
178
+ {"current_steps": 178, "total_steps": 420, "loss": 0.1526, "lr": 7.16941869558779e-07, "epoch": 5.086175942549372, "percentage": 42.38, "elapsed_time": "0:52:44", "remaining_time": "1:11:42"}
179
+ {"current_steps": 179, "total_steps": 420, "loss": 0.1627, "lr": 7.13190402727127e-07, "epoch": 5.114901256732495, "percentage": 42.62, "elapsed_time": "0:53:01", "remaining_time": "1:11:23"}
180
+ {"current_steps": 180, "total_steps": 420, "loss": 0.1444, "lr": 7.094242100141624e-07, "epoch": 5.143626570915619, "percentage": 42.86, "elapsed_time": "0:53:17", "remaining_time": "1:11:03"}
181
+ {"current_steps": 181, "total_steps": 420, "loss": 0.1399, "lr": 7.056435515653058e-07, "epoch": 5.1723518850987436, "percentage": 43.1, "elapsed_time": "0:53:35", "remaining_time": "1:10:46"}
182
+ {"current_steps": 182, "total_steps": 420, "loss": 0.1483, "lr": 7.018486885251811e-07, "epoch": 5.201077199281867, "percentage": 43.33, "elapsed_time": "0:53:54", "remaining_time": "1:10:30"}
183
+ {"current_steps": 183, "total_steps": 420, "loss": 0.1742, "lr": 6.980398830195784e-07, "epoch": 5.229802513464991, "percentage": 43.57, "elapsed_time": "0:54:13", "remaining_time": "1:10:12"}
184
+ {"current_steps": 184, "total_steps": 420, "loss": 0.1425, "lr": 6.942173981373474e-07, "epoch": 5.258527827648114, "percentage": 43.81, "elapsed_time": "0:54:28", "remaining_time": "1:09:52"}
185
+ {"current_steps": 185, "total_steps": 420, "loss": 0.1584, "lr": 6.903814979122247e-07, "epoch": 5.287253141831239, "percentage": 44.05, "elapsed_time": "0:54:48", "remaining_time": "1:09:36"}
186
+ {"current_steps": 186, "total_steps": 420, "loss": 0.1445, "lr": 6.865324473045969e-07, "epoch": 5.315978456014363, "percentage": 44.29, "elapsed_time": "0:55:04", "remaining_time": "1:09:17"}
187
+ {"current_steps": 187, "total_steps": 420, "loss": 0.1837, "lr": 6.826705121831976e-07, "epoch": 5.344703770197486, "percentage": 44.52, "elapsed_time": "0:55:27", "remaining_time": "1:09:05"}
188
+ {"current_steps": 188, "total_steps": 420, "loss": 0.1519, "lr": 6.78795959306743e-07, "epoch": 5.373429084380611, "percentage": 44.76, "elapsed_time": "0:55:47", "remaining_time": "1:08:50"}
189
+ {"current_steps": 189, "total_steps": 420, "loss": 0.1926, "lr": 6.749090563055074e-07, "epoch": 5.402154398563734, "percentage": 45.0, "elapsed_time": "0:56:04", "remaining_time": "1:08:32"}
190
+ {"current_steps": 190, "total_steps": 420, "loss": 0.1869, "lr": 6.710100716628344e-07, "epoch": 5.430879712746858, "percentage": 45.24, "elapsed_time": "0:56:21", "remaining_time": "1:08:13"}
191
+ {"current_steps": 191, "total_steps": 420, "loss": 0.1596, "lr": 6.670992746965938e-07, "epoch": 5.459605026929982, "percentage": 45.48, "elapsed_time": "0:56:43", "remaining_time": "1:08:00"}
192
+ {"current_steps": 192, "total_steps": 420, "loss": 0.1387, "lr": 6.631769355405778e-07, "epoch": 5.488330341113106, "percentage": 45.71, "elapsed_time": "0:56:56", "remaining_time": "1:07:37"}
193
+ {"current_steps": 193, "total_steps": 420, "loss": 0.1637, "lr": 6.592433251258422e-07, "epoch": 5.51705565529623, "percentage": 45.95, "elapsed_time": "0:57:14", "remaining_time": "1:07:19"}
194
+ {"current_steps": 194, "total_steps": 420, "loss": 0.1392, "lr": 6.552987151619919e-07, "epoch": 5.545780969479353, "percentage": 46.19, "elapsed_time": "0:57:35", "remaining_time": "1:07:05"}
195
+ {"current_steps": 195, "total_steps": 420, "loss": 0.1523, "lr": 6.51343378118413e-07, "epoch": 5.574506283662478, "percentage": 46.43, "elapsed_time": "0:57:53", "remaining_time": "1:06:47"}
196
+ {"current_steps": 196, "total_steps": 420, "loss": 0.146, "lr": 6.473775872054521e-07, "epoch": 5.6032315978456015, "percentage": 46.67, "elapsed_time": "0:58:06", "remaining_time": "1:06:24"}
197
+ {"current_steps": 197, "total_steps": 420, "loss": 0.1421, "lr": 6.434016163555451e-07, "epoch": 5.631956912028725, "percentage": 46.9, "elapsed_time": "0:58:24", "remaining_time": "1:06:06"}
198
+ {"current_steps": 198, "total_steps": 420, "loss": 0.142, "lr": 6.394157402042951e-07, "epoch": 5.660682226211849, "percentage": 47.14, "elapsed_time": "0:58:39", "remaining_time": "1:05:46"}
199
+ {"current_steps": 199, "total_steps": 420, "loss": 0.1512, "lr": 6.354202340715026e-07, "epoch": 5.689407540394973, "percentage": 47.38, "elapsed_time": "0:58:59", "remaining_time": "1:05:31"}
200
+ {"current_steps": 200, "total_steps": 420, "loss": 0.1703, "lr": 6.314153739421476e-07, "epoch": 5.718132854578097, "percentage": 47.62, "elapsed_time": "0:59:15", "remaining_time": "1:05:11"}
201
+ {"current_steps": 201, "total_steps": 420, "loss": 0.143, "lr": 6.274014364473274e-07, "epoch": 5.746858168761221, "percentage": 47.86, "elapsed_time": "0:59:36", "remaining_time": "1:04:57"}
202
+ {"current_steps": 202, "total_steps": 420, "loss": 0.1639, "lr": 6.233786988451467e-07, "epoch": 5.775583482944345, "percentage": 48.1, "elapsed_time": "0:59:56", "remaining_time": "1:04:41"}
203
+ {"current_steps": 203, "total_steps": 420, "loss": 0.1788, "lr": 6.193474390015689e-07, "epoch": 5.804308797127469, "percentage": 48.33, "elapsed_time": "1:00:15", "remaining_time": "1:04:25"}
204
+ {"current_steps": 204, "total_steps": 420, "loss": 0.1719, "lr": 6.153079353712201e-07, "epoch": 5.833034111310592, "percentage": 48.57, "elapsed_time": "1:00:33", "remaining_time": "1:04:07"}
205
+ {"current_steps": 205, "total_steps": 420, "loss": 0.1686, "lr": 6.112604669781572e-07, "epoch": 5.861759425493716, "percentage": 48.81, "elapsed_time": "1:00:49", "remaining_time": "1:03:47"}
206
+ {"current_steps": 206, "total_steps": 420, "loss": 0.1774, "lr": 6.072053133965937e-07, "epoch": 5.8904847396768405, "percentage": 49.05, "elapsed_time": "1:01:07", "remaining_time": "1:03:30"}
207
+ {"current_steps": 207, "total_steps": 420, "loss": 0.1368, "lr": 6.031427547315888e-07, "epoch": 5.919210053859964, "percentage": 49.29, "elapsed_time": "1:01:18", "remaining_time": "1:03:05"}
208
+ {"current_steps": 208, "total_steps": 420, "loss": 0.1176, "lr": 5.990730715996987e-07, "epoch": 5.947935368043088, "percentage": 49.52, "elapsed_time": "1:01:36", "remaining_time": "1:02:47"}
209
+ {"current_steps": 209, "total_steps": 420, "loss": 0.1457, "lr": 5.94996545109595e-07, "epoch": 5.976660682226212, "percentage": 49.76, "elapsed_time": "1:01:55", "remaining_time": "1:02:30"}
210
+ {"current_steps": 210, "total_steps": 420, "loss": 0.1465, "lr": 5.909134568426453e-07, "epoch": 6.0, "percentage": 50.0, "elapsed_time": "1:02:08", "remaining_time": "1:02:08"}
211
+ {"current_steps": 211, "total_steps": 420, "loss": 0.1544, "lr": 5.868240888334652e-07, "epoch": 6.028725314183124, "percentage": 50.24, "elapsed_time": "1:02:23", "remaining_time": "1:01:48"}
212
+ {"current_steps": 212, "total_steps": 420, "loss": 0.1314, "lr": 5.827287235504355e-07, "epoch": 6.057450628366248, "percentage": 50.48, "elapsed_time": "1:02:42", "remaining_time": "1:01:31"}
213
+ {"current_steps": 213, "total_steps": 420, "loss": 0.1672, "lr": 5.786276438761927e-07, "epoch": 6.086175942549372, "percentage": 50.71, "elapsed_time": "1:03:01", "remaining_time": "1:01:15"}
214
+ {"current_steps": 214, "total_steps": 420, "loss": 0.1507, "lr": 5.745211330880872e-07, "epoch": 6.114901256732495, "percentage": 50.95, "elapsed_time": "1:03:18", "remaining_time": "1:00:56"}
215
+ {"current_steps": 215, "total_steps": 420, "loss": 0.1459, "lr": 5.704094748386183e-07, "epoch": 6.143626570915619, "percentage": 51.19, "elapsed_time": "1:03:38", "remaining_time": "1:00:40"}
216
+ {"current_steps": 216, "total_steps": 420, "loss": 0.1694, "lr": 5.662929531358397e-07, "epoch": 6.1723518850987436, "percentage": 51.43, "elapsed_time": "1:03:54", "remaining_time": "1:00:21"}
217
+ {"current_steps": 217, "total_steps": 420, "loss": 0.1585, "lr": 5.621718523237426e-07, "epoch": 6.201077199281867, "percentage": 51.67, "elapsed_time": "1:04:08", "remaining_time": "0:59:59"}
218
+ {"current_steps": 218, "total_steps": 420, "loss": 0.1536, "lr": 5.580464570626151e-07, "epoch": 6.229802513464991, "percentage": 51.9, "elapsed_time": "1:04:28", "remaining_time": "0:59:44"}
219
+ {"current_steps": 219, "total_steps": 420, "loss": 0.1537, "lr": 5.539170523093793e-07, "epoch": 6.258527827648114, "percentage": 52.14, "elapsed_time": "1:04:44", "remaining_time": "0:59:25"}
220
+ {"current_steps": 220, "total_steps": 420, "loss": 0.1495, "lr": 5.497839232979083e-07, "epoch": 6.287253141831239, "percentage": 52.38, "elapsed_time": "1:05:04", "remaining_time": "0:59:09"}
221
+ {"current_steps": 221, "total_steps": 420, "loss": 0.1346, "lr": 5.456473555193242e-07, "epoch": 6.315978456014363, "percentage": 52.62, "elapsed_time": "1:05:22", "remaining_time": "0:58:52"}
222
+ {"current_steps": 222, "total_steps": 420, "loss": 0.1504, "lr": 5.415076347022775e-07, "epoch": 6.344703770197486, "percentage": 52.86, "elapsed_time": "1:05:36", "remaining_time": "0:58:31"}
223
+ {"current_steps": 223, "total_steps": 420, "loss": 0.1612, "lr": 5.373650467932121e-07, "epoch": 6.373429084380611, "percentage": 53.1, "elapsed_time": "1:05:51", "remaining_time": "0:58:11"}
224
+ {"current_steps": 224, "total_steps": 420, "loss": 0.141, "lr": 5.332198779366121e-07, "epoch": 6.402154398563734, "percentage": 53.33, "elapsed_time": "1:06:11", "remaining_time": "0:57:54"}
225
+ {"current_steps": 225, "total_steps": 420, "loss": 0.1419, "lr": 5.290724144552379e-07, "epoch": 6.430879712746858, "percentage": 53.57, "elapsed_time": "1:06:27", "remaining_time": "0:57:35"}
226
+ {"current_steps": 226, "total_steps": 420, "loss": 0.1531, "lr": 5.249229428303486e-07, "epoch": 6.459605026929982, "percentage": 53.81, "elapsed_time": "1:06:47", "remaining_time": "0:57:19"}
227
+ {"current_steps": 227, "total_steps": 420, "loss": 0.16, "lr": 5.207717496819134e-07, "epoch": 6.488330341113106, "percentage": 54.05, "elapsed_time": "1:07:10", "remaining_time": "0:57:06"}
228
+ {"current_steps": 228, "total_steps": 420, "loss": 0.1375, "lr": 5.166191217488133e-07, "epoch": 6.51705565529623, "percentage": 54.29, "elapsed_time": "1:07:25", "remaining_time": "0:56:46"}
229
+ {"current_steps": 229, "total_steps": 420, "loss": 0.1405, "lr": 5.124653458690365e-07, "epoch": 6.545780969479353, "percentage": 54.52, "elapsed_time": "1:07:41", "remaining_time": "0:56:27"}
230
+ {"current_steps": 230, "total_steps": 420, "loss": 0.1352, "lr": 5.083107089598632e-07, "epoch": 6.574506283662478, "percentage": 54.76, "elapsed_time": "1:08:01", "remaining_time": "0:56:11"}
231
+ {"current_steps": 231, "total_steps": 420, "loss": 0.1514, "lr": 5.041554979980486e-07, "epoch": 6.6032315978456015, "percentage": 55.0, "elapsed_time": "1:08:18", "remaining_time": "0:55:53"}
232
+ {"current_steps": 232, "total_steps": 420, "loss": 0.168, "lr": 5e-07, "epoch": 6.631956912028725, "percentage": 55.24, "elapsed_time": "1:08:37", "remaining_time": "0:55:36"}
233
+ {"current_steps": 233, "total_steps": 420, "loss": 0.1543, "lr": 4.958445020019515e-07, "epoch": 6.660682226211849, "percentage": 55.48, "elapsed_time": "1:08:52", "remaining_time": "0:55:17"}
234
+ {"current_steps": 234, "total_steps": 420, "loss": 0.1572, "lr": 4.916892910401369e-07, "epoch": 6.689407540394973, "percentage": 55.71, "elapsed_time": "1:09:07", "remaining_time": "0:54:56"}
235
+ {"current_steps": 235, "total_steps": 420, "loss": 0.1661, "lr": 4.875346541309636e-07, "epoch": 6.718132854578097, "percentage": 55.95, "elapsed_time": "1:09:25", "remaining_time": "0:54:39"}
236
+ {"current_steps": 236, "total_steps": 420, "loss": 0.1616, "lr": 4.833808782511867e-07, "epoch": 6.746858168761221, "percentage": 56.19, "elapsed_time": "1:09:42", "remaining_time": "0:54:20"}
237
+ {"current_steps": 237, "total_steps": 420, "loss": 0.1296, "lr": 4.792282503180867e-07, "epoch": 6.775583482944345, "percentage": 56.43, "elapsed_time": "1:10:05", "remaining_time": "0:54:07"}
238
+ {"current_steps": 238, "total_steps": 420, "loss": 0.1477, "lr": 4.7507705716965134e-07, "epoch": 6.804308797127469, "percentage": 56.67, "elapsed_time": "1:10:20", "remaining_time": "0:53:47"}
239
+ {"current_steps": 239, "total_steps": 420, "loss": 0.1681, "lr": 4.7092758554476206e-07, "epoch": 6.833034111310592, "percentage": 56.9, "elapsed_time": "1:10:40", "remaining_time": "0:53:31"}
240
+ {"current_steps": 240, "total_steps": 420, "loss": 0.1149, "lr": 4.667801220633879e-07, "epoch": 6.861759425493716, "percentage": 57.14, "elapsed_time": "1:10:56", "remaining_time": "0:53:12"}
241
+ {"current_steps": 241, "total_steps": 420, "loss": 0.1217, "lr": 4.626349532067879e-07, "epoch": 6.8904847396768405, "percentage": 57.38, "elapsed_time": "1:11:14", "remaining_time": "0:52:54"}
242
+ {"current_steps": 242, "total_steps": 420, "loss": 0.1429, "lr": 4.584923652977223e-07, "epoch": 6.919210053859964, "percentage": 57.62, "elapsed_time": "1:11:32", "remaining_time": "0:52:37"}
243
+ {"current_steps": 243, "total_steps": 420, "loss": 0.1606, "lr": 4.543526444806759e-07, "epoch": 6.947935368043088, "percentage": 57.86, "elapsed_time": "1:11:51", "remaining_time": "0:52:20"}
244
+ {"current_steps": 244, "total_steps": 420, "loss": 0.1662, "lr": 4.502160767020917e-07, "epoch": 6.976660682226212, "percentage": 58.1, "elapsed_time": "1:12:10", "remaining_time": "0:52:03"}
245
+ {"current_steps": 245, "total_steps": 420, "loss": 0.15, "lr": 4.460829476906207e-07, "epoch": 7.0, "percentage": 58.33, "elapsed_time": "1:12:28", "remaining_time": "0:51:46"}
246
+ {"current_steps": 246, "total_steps": 420, "loss": 0.1409, "lr": 4.419535429373848e-07, "epoch": 7.028725314183124, "percentage": 58.57, "elapsed_time": "1:12:47", "remaining_time": "0:51:29"}
247
+ {"current_steps": 247, "total_steps": 420, "loss": 0.1647, "lr": 4.3782814767625755e-07, "epoch": 7.057450628366248, "percentage": 58.81, "elapsed_time": "1:13:04", "remaining_time": "0:51:10"}
248
+ {"current_steps": 248, "total_steps": 420, "loss": 0.1636, "lr": 4.3370704686416034e-07, "epoch": 7.086175942549372, "percentage": 59.05, "elapsed_time": "1:13:20", "remaining_time": "0:50:52"}
249
+ {"current_steps": 249, "total_steps": 420, "loss": 0.1485, "lr": 4.2959052516138166e-07, "epoch": 7.114901256732495, "percentage": 59.29, "elapsed_time": "1:13:34", "remaining_time": "0:50:31"}
250
+ {"current_steps": 250, "total_steps": 420, "loss": 0.1332, "lr": 4.254788669119127e-07, "epoch": 7.143626570915619, "percentage": 59.52, "elapsed_time": "1:13:52", "remaining_time": "0:50:14"}
251
+ {"current_steps": 251, "total_steps": 420, "loss": 0.142, "lr": 4.213723561238074e-07, "epoch": 7.1723518850987436, "percentage": 59.76, "elapsed_time": "1:14:11", "remaining_time": "0:49:57"}
252
+ {"current_steps": 252, "total_steps": 420, "loss": 0.1483, "lr": 4.172712764495644e-07, "epoch": 7.201077199281867, "percentage": 60.0, "elapsed_time": "1:14:30", "remaining_time": "0:49:40"}
253
+ {"current_steps": 253, "total_steps": 420, "loss": 0.1328, "lr": 4.131759111665348e-07, "epoch": 7.229802513464991, "percentage": 60.24, "elapsed_time": "1:14:46", "remaining_time": "0:49:21"}
254
+ {"current_steps": 254, "total_steps": 420, "loss": 0.1463, "lr": 4.0908654315735466e-07, "epoch": 7.258527827648114, "percentage": 60.48, "elapsed_time": "1:15:05", "remaining_time": "0:49:04"}
255
+ {"current_steps": 255, "total_steps": 420, "loss": 0.1398, "lr": 4.050034548904051e-07, "epoch": 7.287253141831239, "percentage": 60.71, "elapsed_time": "1:15:24", "remaining_time": "0:48:47"}
256
+ {"current_steps": 256, "total_steps": 420, "loss": 0.1354, "lr": 4.0092692840030126e-07, "epoch": 7.315978456014363, "percentage": 60.95, "elapsed_time": "1:15:39", "remaining_time": "0:48:28"}
257
+ {"current_steps": 257, "total_steps": 420, "loss": 0.1654, "lr": 3.968572452684112e-07, "epoch": 7.344703770197486, "percentage": 61.19, "elapsed_time": "1:15:58", "remaining_time": "0:48:11"}
258
+ {"current_steps": 258, "total_steps": 420, "loss": 0.1472, "lr": 3.927946866034062e-07, "epoch": 7.373429084380611, "percentage": 61.43, "elapsed_time": "1:16:11", "remaining_time": "0:47:50"}
259
+ {"current_steps": 259, "total_steps": 420, "loss": 0.1282, "lr": 3.8873953302184283e-07, "epoch": 7.402154398563734, "percentage": 61.67, "elapsed_time": "1:16:30", "remaining_time": "0:47:33"}
260
+ {"current_steps": 260, "total_steps": 420, "loss": 0.1464, "lr": 3.846920646287799e-07, "epoch": 7.430879712746858, "percentage": 61.9, "elapsed_time": "1:16:49", "remaining_time": "0:47:16"}
261
+ {"current_steps": 261, "total_steps": 420, "loss": 0.1538, "lr": 3.806525609984311e-07, "epoch": 7.459605026929982, "percentage": 62.14, "elapsed_time": "1:17:05", "remaining_time": "0:46:57"}
262
+ {"current_steps": 262, "total_steps": 420, "loss": 0.161, "lr": 3.7662130115485314e-07, "epoch": 7.488330341113106, "percentage": 62.38, "elapsed_time": "1:17:23", "remaining_time": "0:46:40"}
263
+ {"current_steps": 263, "total_steps": 420, "loss": 0.1481, "lr": 3.725985635526727e-07, "epoch": 7.51705565529623, "percentage": 62.62, "elapsed_time": "1:17:45", "remaining_time": "0:46:24"}
264
+ {"current_steps": 264, "total_steps": 420, "loss": 0.1385, "lr": 3.6858462605785233e-07, "epoch": 7.545780969479353, "percentage": 62.86, "elapsed_time": "1:18:06", "remaining_time": "0:46:09"}
265
+ {"current_steps": 265, "total_steps": 420, "loss": 0.1496, "lr": 3.645797659284975e-07, "epoch": 7.574506283662478, "percentage": 63.1, "elapsed_time": "1:18:25", "remaining_time": "0:45:52"}
266
+ {"current_steps": 266, "total_steps": 420, "loss": 0.14, "lr": 3.6058425979570477e-07, "epoch": 7.6032315978456015, "percentage": 63.33, "elapsed_time": "1:18:42", "remaining_time": "0:45:34"}
267
+ {"current_steps": 267, "total_steps": 420, "loss": 0.1225, "lr": 3.56598383644455e-07, "epoch": 7.631956912028725, "percentage": 63.57, "elapsed_time": "1:19:01", "remaining_time": "0:45:17"}
268
+ {"current_steps": 268, "total_steps": 420, "loss": 0.1327, "lr": 3.526224127945478e-07, "epoch": 7.660682226211849, "percentage": 63.81, "elapsed_time": "1:19:16", "remaining_time": "0:44:57"}
269
+ {"current_steps": 269, "total_steps": 420, "loss": 0.149, "lr": 3.4865662188158705e-07, "epoch": 7.689407540394973, "percentage": 64.05, "elapsed_time": "1:19:34", "remaining_time": "0:44:40"}
270
+ {"current_steps": 270, "total_steps": 420, "loss": 0.1296, "lr": 3.447012848380081e-07, "epoch": 7.718132854578097, "percentage": 64.29, "elapsed_time": "1:19:53", "remaining_time": "0:44:22"}
271
+ {"current_steps": 271, "total_steps": 420, "loss": 0.148, "lr": 3.4075667487415785e-07, "epoch": 7.746858168761221, "percentage": 64.52, "elapsed_time": "1:20:08", "remaining_time": "0:44:03"}
272
+ {"current_steps": 272, "total_steps": 420, "loss": 0.1467, "lr": 3.368230644594222e-07, "epoch": 7.775583482944345, "percentage": 64.76, "elapsed_time": "1:20:25", "remaining_time": "0:43:45"}
273
+ {"current_steps": 273, "total_steps": 420, "loss": 0.1383, "lr": 3.3290072530340625e-07, "epoch": 7.804308797127469, "percentage": 65.0, "elapsed_time": "1:20:45", "remaining_time": "0:43:29"}
274
+ {"current_steps": 274, "total_steps": 420, "loss": 0.1068, "lr": 3.2898992833716563e-07, "epoch": 7.833034111310592, "percentage": 65.24, "elapsed_time": "1:21:00", "remaining_time": "0:43:10"}
275
+ {"current_steps": 275, "total_steps": 420, "loss": 0.1529, "lr": 3.2509094369449273e-07, "epoch": 7.861759425493716, "percentage": 65.48, "elapsed_time": "1:21:21", "remaining_time": "0:42:53"}
276
+ {"current_steps": 276, "total_steps": 420, "loss": 0.1748, "lr": 3.212040406932569e-07, "epoch": 7.8904847396768405, "percentage": 65.71, "elapsed_time": "1:21:40", "remaining_time": "0:42:36"}
277
+ {"current_steps": 277, "total_steps": 420, "loss": 0.1538, "lr": 3.173294878168025e-07, "epoch": 7.919210053859964, "percentage": 65.95, "elapsed_time": "1:22:00", "remaining_time": "0:42:20"}
278
+ {"current_steps": 278, "total_steps": 420, "loss": 0.1419, "lr": 3.1346755269540296e-07, "epoch": 7.947935368043088, "percentage": 66.19, "elapsed_time": "1:22:16", "remaining_time": "0:42:01"}
279
+ {"current_steps": 279, "total_steps": 420, "loss": 0.1333, "lr": 3.0961850208777523e-07, "epoch": 7.976660682226212, "percentage": 66.43, "elapsed_time": "1:22:35", "remaining_time": "0:41:44"}
280
+ {"current_steps": 280, "total_steps": 420, "loss": 0.1299, "lr": 3.0578260186265265e-07, "epoch": 8.0, "percentage": 66.67, "elapsed_time": "1:22:49", "remaining_time": "0:41:24"}
281
+ {"current_steps": 281, "total_steps": 420, "loss": 0.1421, "lr": 3.0196011698042156e-07, "epoch": 8.028725314183124, "percentage": 66.9, "elapsed_time": "1:23:03", "remaining_time": "0:41:05"}
282
+ {"current_steps": 282, "total_steps": 420, "loss": 0.149, "lr": 2.981513114748189e-07, "epoch": 8.057450628366247, "percentage": 67.14, "elapsed_time": "1:23:24", "remaining_time": "0:40:48"}
283
+ {"current_steps": 283, "total_steps": 420, "loss": 0.137, "lr": 2.943564484346943e-07, "epoch": 8.08617594254937, "percentage": 67.38, "elapsed_time": "1:23:43", "remaining_time": "0:40:31"}
284
+ {"current_steps": 284, "total_steps": 420, "loss": 0.1414, "lr": 2.9057578998583764e-07, "epoch": 8.114901256732496, "percentage": 67.62, "elapsed_time": "1:23:59", "remaining_time": "0:40:13"}
285
+ {"current_steps": 285, "total_steps": 420, "loss": 0.1471, "lr": 2.868095972728731e-07, "epoch": 8.14362657091562, "percentage": 67.86, "elapsed_time": "1:24:18", "remaining_time": "0:39:56"}
286
+ {"current_steps": 286, "total_steps": 420, "loss": 0.1372, "lr": 2.8305813044122093e-07, "epoch": 8.172351885098744, "percentage": 68.1, "elapsed_time": "1:24:35", "remaining_time": "0:39:37"}
287
+ {"current_steps": 287, "total_steps": 420, "loss": 0.1269, "lr": 2.7932164861912797e-07, "epoch": 8.201077199281867, "percentage": 68.33, "elapsed_time": "1:24:54", "remaining_time": "0:39:20"}
288
+ {"current_steps": 288, "total_steps": 420, "loss": 0.1388, "lr": 2.756004098997689e-07, "epoch": 8.22980251346499, "percentage": 68.57, "elapsed_time": "1:25:09", "remaining_time": "0:39:01"}
289
+ {"current_steps": 289, "total_steps": 420, "loss": 0.1217, "lr": 2.718946713234185e-07, "epoch": 8.258527827648114, "percentage": 68.81, "elapsed_time": "1:25:25", "remaining_time": "0:38:43"}
290
+ {"current_steps": 290, "total_steps": 420, "loss": 0.1329, "lr": 2.6820468885969714e-07, "epoch": 8.287253141831238, "percentage": 69.05, "elapsed_time": "1:25:43", "remaining_time": "0:38:25"}
291
+ {"current_steps": 291, "total_steps": 420, "loss": 0.1502, "lr": 2.6453071738989007e-07, "epoch": 8.315978456014363, "percentage": 69.29, "elapsed_time": "1:26:02", "remaining_time": "0:38:08"}
292
+ {"current_steps": 292, "total_steps": 420, "loss": 0.1406, "lr": 2.6087301068934103e-07, "epoch": 8.344703770197487, "percentage": 69.52, "elapsed_time": "1:26:19", "remaining_time": "0:37:50"}
293
+ {"current_steps": 293, "total_steps": 420, "loss": 0.1482, "lr": 2.5723182140992384e-07, "epoch": 8.37342908438061, "percentage": 69.76, "elapsed_time": "1:26:38", "remaining_time": "0:37:33"}
294
+ {"current_steps": 294, "total_steps": 420, "loss": 0.1538, "lr": 2.53607401062591e-07, "epoch": 8.402154398563734, "percentage": 70.0, "elapsed_time": "1:26:55", "remaining_time": "0:37:15"}
295
+ {"current_steps": 295, "total_steps": 420, "loss": 0.122, "lr": 2.500000000000001e-07, "epoch": 8.430879712746858, "percentage": 70.24, "elapsed_time": "1:27:11", "remaining_time": "0:36:56"}
296
+ {"current_steps": 296, "total_steps": 420, "loss": 0.1164, "lr": 2.464098673992205e-07, "epoch": 8.459605026929982, "percentage": 70.48, "elapsed_time": "1:27:27", "remaining_time": "0:36:38"}
297
+ {"current_steps": 297, "total_steps": 420, "loss": 0.1443, "lr": 2.428372512445233e-07, "epoch": 8.488330341113105, "percentage": 70.71, "elapsed_time": "1:27:45", "remaining_time": "0:36:20"}
298
+ {"current_steps": 298, "total_steps": 420, "loss": 0.1305, "lr": 2.39282398310251e-07, "epoch": 8.517055655296229, "percentage": 70.95, "elapsed_time": "1:28:05", "remaining_time": "0:36:03"}
299
+ {"current_steps": 299, "total_steps": 420, "loss": 0.1539, "lr": 2.357455541437723e-07, "epoch": 8.545780969479354, "percentage": 71.19, "elapsed_time": "1:28:26", "remaining_time": "0:35:47"}
300
+ {"current_steps": 300, "total_steps": 420, "loss": 0.1534, "lr": 2.322269630485208e-07, "epoch": 8.574506283662478, "percentage": 71.43, "elapsed_time": "1:28:46", "remaining_time": "0:35:30"}
301
+ {"current_steps": 301, "total_steps": 420, "loss": 0.1233, "lr": 2.2872686806712032e-07, "epoch": 8.603231597845602, "percentage": 71.67, "elapsed_time": "1:29:06", "remaining_time": "0:35:13"}
302
+ {"current_steps": 302, "total_steps": 420, "loss": 0.1231, "lr": 2.25245510964597e-07, "epoch": 8.631956912028725, "percentage": 71.9, "elapsed_time": "1:29:21", "remaining_time": "0:34:54"}
303
+ {"current_steps": 303, "total_steps": 420, "loss": 0.1617, "lr": 2.2178313221167965e-07, "epoch": 8.660682226211849, "percentage": 72.14, "elapsed_time": "1:29:40", "remaining_time": "0:34:37"}
304
+ {"current_steps": 304, "total_steps": 420, "loss": 0.1243, "lr": 2.1833997096818895e-07, "epoch": 8.689407540394972, "percentage": 72.38, "elapsed_time": "1:29:59", "remaining_time": "0:34:20"}
305
+ {"current_steps": 305, "total_steps": 420, "loss": 0.1498, "lr": 2.149162650665191e-07, "epoch": 8.718132854578098, "percentage": 72.62, "elapsed_time": "1:30:19", "remaining_time": "0:34:03"}
306
+ {"current_steps": 306, "total_steps": 420, "loss": 0.1579, "lr": 2.1151225099520847e-07, "epoch": 8.746858168761221, "percentage": 72.86, "elapsed_time": "1:30:35", "remaining_time": "0:33:44"}
307
+ {"current_steps": 307, "total_steps": 420, "loss": 0.1171, "lr": 2.0812816388260519e-07, "epoch": 8.775583482944345, "percentage": 73.1, "elapsed_time": "1:30:51", "remaining_time": "0:33:26"}
308
+ {"current_steps": 308, "total_steps": 420, "loss": 0.1673, "lr": 2.0476423748062516e-07, "epoch": 8.804308797127469, "percentage": 73.33, "elapsed_time": "1:31:08", "remaining_time": "0:33:08"}
309
+ {"current_steps": 309, "total_steps": 420, "loss": 0.1451, "lr": 2.01420704148607e-07, "epoch": 8.833034111310592, "percentage": 73.57, "elapsed_time": "1:31:25", "remaining_time": "0:32:50"}
310
+ {"current_steps": 310, "total_steps": 420, "loss": 0.1521, "lr": 1.9809779483726118e-07, "epoch": 8.861759425493716, "percentage": 73.81, "elapsed_time": "1:31:44", "remaining_time": "0:32:33"}
311
+ {"current_steps": 311, "total_steps": 420, "loss": 0.1458, "lr": 1.9479573907271847e-07, "epoch": 8.89048473967684, "percentage": 74.05, "elapsed_time": "1:32:00", "remaining_time": "0:32:14"}
312
+ {"current_steps": 312, "total_steps": 420, "loss": 0.1422, "lr": 1.9151476494067376e-07, "epoch": 8.919210053859963, "percentage": 74.29, "elapsed_time": "1:32:17", "remaining_time": "0:31:56"}
313
+ {"current_steps": 313, "total_steps": 420, "loss": 0.1242, "lr": 1.8825509907063326e-07, "epoch": 8.947935368043089, "percentage": 74.52, "elapsed_time": "1:32:33", "remaining_time": "0:31:38"}
314
+ {"current_steps": 314, "total_steps": 420, "loss": 0.1388, "lr": 1.8501696662025933e-07, "epoch": 8.976660682226212, "percentage": 74.76, "elapsed_time": "1:32:53", "remaining_time": "0:31:21"}
315
+ {"current_steps": 315, "total_steps": 420, "loss": 0.1225, "lr": 1.8180059125981822e-07, "epoch": 9.0, "percentage": 75.0, "elapsed_time": "1:33:09", "remaining_time": "0:31:03"}
316
+ {"current_steps": 316, "total_steps": 420, "loss": 0.1149, "lr": 1.7860619515673032e-07, "epoch": 9.028725314183124, "percentage": 75.24, "elapsed_time": "1:33:25", "remaining_time": "0:30:44"}
317
+ {"current_steps": 317, "total_steps": 420, "loss": 0.1322, "lr": 1.7543399896022405e-07, "epoch": 9.057450628366247, "percentage": 75.48, "elapsed_time": "1:33:42", "remaining_time": "0:30:27"}
318
+ {"current_steps": 318, "total_steps": 420, "loss": 0.1412, "lr": 1.7228422178609487e-07, "epoch": 9.08617594254937, "percentage": 75.71, "elapsed_time": "1:34:01", "remaining_time": "0:30:09"}
319
+ {"current_steps": 319, "total_steps": 420, "loss": 0.1221, "lr": 1.691570812015704e-07, "epoch": 9.114901256732496, "percentage": 75.95, "elapsed_time": "1:34:13", "remaining_time": "0:29:49"}
320
+ {"current_steps": 320, "total_steps": 420, "loss": 0.15, "lr": 1.6605279321028138e-07, "epoch": 9.14362657091562, "percentage": 76.19, "elapsed_time": "1:34:33", "remaining_time": "0:29:33"}
321
+ {"current_steps": 321, "total_steps": 420, "loss": 0.1448, "lr": 1.6297157223734225e-07, "epoch": 9.172351885098744, "percentage": 76.43, "elapsed_time": "1:34:52", "remaining_time": "0:29:15"}
322
+ {"current_steps": 322, "total_steps": 420, "loss": 0.1476, "lr": 1.599136311145402e-07, "epoch": 9.201077199281867, "percentage": 76.67, "elapsed_time": "1:35:08", "remaining_time": "0:28:57"}
323
+ {"current_steps": 323, "total_steps": 420, "loss": 0.1343, "lr": 1.5687918106563325e-07, "epoch": 9.22980251346499, "percentage": 76.9, "elapsed_time": "1:35:26", "remaining_time": "0:28:39"}
324
+ {"current_steps": 324, "total_steps": 420, "loss": 0.1263, "lr": 1.5386843169176023e-07, "epoch": 9.258527827648114, "percentage": 77.14, "elapsed_time": "1:35:42", "remaining_time": "0:28:21"}
325
+ {"current_steps": 325, "total_steps": 420, "loss": 0.1235, "lr": 1.5088159095696362e-07, "epoch": 9.287253141831238, "percentage": 77.38, "elapsed_time": "1:35:59", "remaining_time": "0:28:03"}
326
+ {"current_steps": 326, "total_steps": 420, "loss": 0.1291, "lr": 1.4791886517382413e-07, "epoch": 9.315978456014363, "percentage": 77.62, "elapsed_time": "1:36:14", "remaining_time": "0:27:44"}
327
+ {"current_steps": 327, "total_steps": 420, "loss": 0.1405, "lr": 1.4498045898920985e-07, "epoch": 9.344703770197487, "percentage": 77.86, "elapsed_time": "1:36:37", "remaining_time": "0:27:28"}
328
+ {"current_steps": 328, "total_steps": 420, "loss": 0.1639, "lr": 1.4206657537014076e-07, "epoch": 9.37342908438061, "percentage": 78.1, "elapsed_time": "1:36:56", "remaining_time": "0:27:11"}
329
+ {"current_steps": 329, "total_steps": 420, "loss": 0.1206, "lr": 1.3917741558976892e-07, "epoch": 9.402154398563734, "percentage": 78.33, "elapsed_time": "1:37:15", "remaining_time": "0:26:54"}
330
+ {"current_steps": 330, "total_steps": 420, "loss": 0.1472, "lr": 1.3631317921347562e-07, "epoch": 9.430879712746858, "percentage": 78.57, "elapsed_time": "1:37:30", "remaining_time": "0:26:35"}
331
+ {"current_steps": 331, "total_steps": 420, "loss": 0.1319, "lr": 1.3347406408508694e-07, "epoch": 9.459605026929982, "percentage": 78.81, "elapsed_time": "1:37:49", "remaining_time": "0:26:18"}
332
+ {"current_steps": 332, "total_steps": 420, "loss": 0.1288, "lr": 1.306602663132073e-07, "epoch": 9.488330341113105, "percentage": 79.05, "elapsed_time": "1:38:09", "remaining_time": "0:26:01"}
333
+ {"current_steps": 333, "total_steps": 420, "loss": 0.1451, "lr": 1.2787198025767415e-07, "epoch": 9.517055655296229, "percentage": 79.29, "elapsed_time": "1:38:24", "remaining_time": "0:25:42"}
334
+ {"current_steps": 334, "total_steps": 420, "loss": 0.14, "lr": 1.2510939851613283e-07, "epoch": 9.545780969479354, "percentage": 79.52, "elapsed_time": "1:38:41", "remaining_time": "0:25:24"}
335
+ {"current_steps": 335, "total_steps": 420, "loss": 0.1492, "lr": 1.2237271191073267e-07, "epoch": 9.574506283662478, "percentage": 79.76, "elapsed_time": "1:38:59", "remaining_time": "0:25:07"}
336
+ {"current_steps": 336, "total_steps": 420, "loss": 0.1254, "lr": 1.1966210947494583e-07, "epoch": 9.603231597845602, "percentage": 80.0, "elapsed_time": "1:39:16", "remaining_time": "0:24:49"}
337
+ {"current_steps": 337, "total_steps": 420, "loss": 0.1344, "lr": 1.1697777844051104e-07, "epoch": 9.631956912028725, "percentage": 80.24, "elapsed_time": "1:39:36", "remaining_time": "0:24:31"}
338
+ {"current_steps": 338, "total_steps": 420, "loss": 0.1467, "lr": 1.1431990422450017e-07, "epoch": 9.660682226211849, "percentage": 80.48, "elapsed_time": "1:39:54", "remaining_time": "0:24:14"}
339
+ {"current_steps": 339, "total_steps": 420, "loss": 0.1439, "lr": 1.116886704165108e-07, "epoch": 9.689407540394972, "percentage": 80.71, "elapsed_time": "1:40:12", "remaining_time": "0:23:56"}
340
+ {"current_steps": 340, "total_steps": 420, "loss": 0.1346, "lr": 1.090842587659851e-07, "epoch": 9.718132854578098, "percentage": 80.95, "elapsed_time": "1:40:29", "remaining_time": "0:23:38"}
341
+ {"current_steps": 341, "total_steps": 420, "loss": 0.141, "lr": 1.0650684916965557e-07, "epoch": 9.746858168761221, "percentage": 81.19, "elapsed_time": "1:40:50", "remaining_time": "0:23:21"}
342
+ {"current_steps": 342, "total_steps": 420, "loss": 0.1418, "lr": 1.0395661965911889e-07, "epoch": 9.775583482944345, "percentage": 81.43, "elapsed_time": "1:41:12", "remaining_time": "0:23:05"}
343
+ {"current_steps": 343, "total_steps": 420, "loss": 0.1177, "lr": 1.0143374638853891e-07, "epoch": 9.804308797127469, "percentage": 81.67, "elapsed_time": "1:41:29", "remaining_time": "0:22:46"}
344
+ {"current_steps": 344, "total_steps": 420, "loss": 0.1413, "lr": 9.893840362247807e-08, "epoch": 9.833034111310592, "percentage": 81.9, "elapsed_time": "1:41:45", "remaining_time": "0:22:28"}
345
+ {"current_steps": 345, "total_steps": 420, "loss": 0.1476, "lr": 9.647076372386192e-08, "epoch": 9.861759425493716, "percentage": 82.14, "elapsed_time": "1:42:02", "remaining_time": "0:22:10"}
346
+ {"current_steps": 346, "total_steps": 420, "loss": 0.1458, "lr": 9.403099714207174e-08, "epoch": 9.89048473967684, "percentage": 82.38, "elapsed_time": "1:42:24", "remaining_time": "0:21:54"}
347
+ {"current_steps": 347, "total_steps": 420, "loss": 0.1224, "lr": 9.161927240117173e-08, "epoch": 9.919210053859963, "percentage": 82.62, "elapsed_time": "1:42:42", "remaining_time": "0:21:36"}
348
+ {"current_steps": 348, "total_steps": 420, "loss": 0.1539, "lr": 8.92357560882681e-08, "epoch": 9.947935368043089, "percentage": 82.86, "elapsed_time": "1:43:00", "remaining_time": "0:21:18"}
349
+ {"current_steps": 349, "total_steps": 420, "loss": 0.1359, "lr": 8.688061284200265e-08, "epoch": 9.976660682226212, "percentage": 83.1, "elapsed_time": "1:43:17", "remaining_time": "0:21:00"}
350
+ {"current_steps": 350, "total_steps": 420, "loss": 0.1231, "lr": 8.455400534118006e-08, "epoch": 10.0, "percentage": 83.33, "elapsed_time": "1:43:30", "remaining_time": "0:20:42"}
351
+ {"current_steps": 351, "total_steps": 420, "loss": 0.1532, "lr": 8.225609429353186e-08, "epoch": 10.028725314183124, "percentage": 83.57, "elapsed_time": "1:43:47", "remaining_time": "0:20:24"}
352
+ {"current_steps": 352, "total_steps": 420, "loss": 0.1401, "lr": 7.99870384246143e-08, "epoch": 10.057450628366247, "percentage": 83.81, "elapsed_time": "1:44:08", "remaining_time": "0:20:07"}
353
+ {"current_steps": 353, "total_steps": 420, "loss": 0.1502, "lr": 7.774699446684607e-08, "epoch": 10.08617594254937, "percentage": 84.05, "elapsed_time": "1:44:29", "remaining_time": "0:19:49"}
354
+ {"current_steps": 354, "total_steps": 420, "loss": 0.1319, "lr": 7.553611714868136e-08, "epoch": 10.114901256732496, "percentage": 84.29, "elapsed_time": "1:44:46", "remaining_time": "0:19:32"}
355
+ {"current_steps": 355, "total_steps": 420, "loss": 0.1354, "lr": 7.335455918392219e-08, "epoch": 10.14362657091562, "percentage": 84.52, "elapsed_time": "1:45:07", "remaining_time": "0:19:14"}
356
+ {"current_steps": 356, "total_steps": 420, "loss": 0.1215, "lr": 7.120247126117024e-08, "epoch": 10.172351885098744, "percentage": 84.76, "elapsed_time": "1:45:28", "remaining_time": "0:18:57"}
357
+ {"current_steps": 357, "total_steps": 420, "loss": 0.1473, "lr": 6.908000203341802e-08, "epoch": 10.201077199281867, "percentage": 85.0, "elapsed_time": "1:45:48", "remaining_time": "0:18:40"}
358
+ {"current_steps": 358, "total_steps": 420, "loss": 0.143, "lr": 6.698729810778064e-08, "epoch": 10.22980251346499, "percentage": 85.24, "elapsed_time": "1:46:06", "remaining_time": "0:18:22"}
359
+ {"current_steps": 359, "total_steps": 420, "loss": 0.1509, "lr": 6.492450403536959e-08, "epoch": 10.258527827648114, "percentage": 85.48, "elapsed_time": "1:46:25", "remaining_time": "0:18:05"}
360
+ {"current_steps": 360, "total_steps": 420, "loss": 0.1247, "lr": 6.289176230130728e-08, "epoch": 10.287253141831238, "percentage": 85.71, "elapsed_time": "1:46:43", "remaining_time": "0:17:47"}
361
+ {"current_steps": 361, "total_steps": 420, "loss": 0.1595, "lr": 6.088921331488566e-08, "epoch": 10.315978456014363, "percentage": 85.95, "elapsed_time": "1:46:56", "remaining_time": "0:17:28"}
362
+ {"current_steps": 362, "total_steps": 420, "loss": 0.1528, "lr": 5.891699539986789e-08, "epoch": 10.344703770197487, "percentage": 86.19, "elapsed_time": "1:47:14", "remaining_time": "0:17:10"}
363
+ {"current_steps": 363, "total_steps": 420, "loss": 0.1228, "lr": 5.6975244784932876e-08, "epoch": 10.37342908438061, "percentage": 86.43, "elapsed_time": "1:47:34", "remaining_time": "0:16:53"}
364
+ {"current_steps": 364, "total_steps": 420, "loss": 0.1335, "lr": 5.5064095594265726e-08, "epoch": 10.402154398563734, "percentage": 86.67, "elapsed_time": "1:47:51", "remaining_time": "0:16:35"}
365
+ {"current_steps": 365, "total_steps": 420, "loss": 0.1235, "lr": 5.318367983829392e-08, "epoch": 10.430879712746858, "percentage": 86.9, "elapsed_time": "1:48:07", "remaining_time": "0:16:17"}
366
+ {"current_steps": 366, "total_steps": 420, "loss": 0.12, "lr": 5.133412740456805e-08, "epoch": 10.459605026929982, "percentage": 87.14, "elapsed_time": "1:48:26", "remaining_time": "0:15:59"}
367
+ {"current_steps": 367, "total_steps": 420, "loss": 0.1226, "lr": 4.951556604879048e-08, "epoch": 10.488330341113105, "percentage": 87.38, "elapsed_time": "1:48:43", "remaining_time": "0:15:42"}
368
+ {"current_steps": 368, "total_steps": 420, "loss": 0.108, "lr": 4.772812138599042e-08, "epoch": 10.517055655296229, "percentage": 87.62, "elapsed_time": "1:49:00", "remaining_time": "0:15:24"}
369
+ {"current_steps": 369, "total_steps": 420, "loss": 0.1363, "lr": 4.597191688184754e-08, "epoch": 10.545780969479354, "percentage": 87.86, "elapsed_time": "1:49:16", "remaining_time": "0:15:06"}
370
+ {"current_steps": 370, "total_steps": 420, "loss": 0.1175, "lr": 4.424707384416343e-08, "epoch": 10.574506283662478, "percentage": 88.1, "elapsed_time": "1:49:33", "remaining_time": "0:14:48"}
371
+ {"current_steps": 371, "total_steps": 420, "loss": 0.1158, "lr": 4.255371141448272e-08, "epoch": 10.603231597845602, "percentage": 88.33, "elapsed_time": "1:49:53", "remaining_time": "0:14:30"}
372
+ {"current_steps": 372, "total_steps": 420, "loss": 0.1572, "lr": 4.089194655986306e-08, "epoch": 10.631956912028725, "percentage": 88.57, "elapsed_time": "1:50:10", "remaining_time": "0:14:13"}
373
+ {"current_steps": 373, "total_steps": 420, "loss": 0.1481, "lr": 3.926189406479613e-08, "epoch": 10.660682226211849, "percentage": 88.81, "elapsed_time": "1:50:28", "remaining_time": "0:13:55"}
374
+ {"current_steps": 374, "total_steps": 420, "loss": 0.1349, "lr": 3.766366652327924e-08, "epoch": 10.689407540394972, "percentage": 89.05, "elapsed_time": "1:50:43", "remaining_time": "0:13:37"}
375
+ {"current_steps": 375, "total_steps": 420, "loss": 0.1246, "lr": 3.609737433103732e-08, "epoch": 10.718132854578098, "percentage": 89.29, "elapsed_time": "1:51:01", "remaining_time": "0:13:19"}
376
+ {"current_steps": 376, "total_steps": 420, "loss": 0.1416, "lr": 3.456312567789793e-08, "epoch": 10.746858168761221, "percentage": 89.52, "elapsed_time": "1:51:21", "remaining_time": "0:13:01"}
377
+ {"current_steps": 377, "total_steps": 420, "loss": 0.1341, "lr": 3.306102654031822e-08, "epoch": 10.775583482944345, "percentage": 89.76, "elapsed_time": "1:51:33", "remaining_time": "0:12:43"}
378
+ {"current_steps": 378, "total_steps": 420, "loss": 0.1361, "lr": 3.159118067406458e-08, "epoch": 10.804308797127469, "percentage": 90.0, "elapsed_time": "1:51:50", "remaining_time": "0:12:25"}
379
+ {"current_steps": 379, "total_steps": 420, "loss": 0.1296, "lr": 3.015368960704584e-08, "epoch": 10.833034111310592, "percentage": 90.24, "elapsed_time": "1:52:06", "remaining_time": "0:12:07"}
380
+ {"current_steps": 380, "total_steps": 420, "loss": 0.1287, "lr": 2.8748652632300364e-08, "epoch": 10.861759425493716, "percentage": 90.48, "elapsed_time": "1:52:22", "remaining_time": "0:11:49"}
381
+ {"current_steps": 381, "total_steps": 420, "loss": 0.1299, "lr": 2.737616680113758e-08, "epoch": 10.89048473967684, "percentage": 90.71, "elapsed_time": "1:52:35", "remaining_time": "0:11:31"}
382
+ {"current_steps": 382, "total_steps": 420, "loss": 0.1442, "lr": 2.603632691643415e-08, "epoch": 10.919210053859963, "percentage": 90.95, "elapsed_time": "1:52:53", "remaining_time": "0:11:13"}
383
+ {"current_steps": 383, "total_steps": 420, "loss": 0.1404, "lr": 2.4729225526085584e-08, "epoch": 10.947935368043089, "percentage": 91.19, "elapsed_time": "1:53:09", "remaining_time": "0:10:55"}
384
+ {"current_steps": 384, "total_steps": 420, "loss": 0.1398, "lr": 2.345495291661348e-08, "epoch": 10.976660682226212, "percentage": 91.43, "elapsed_time": "1:53:31", "remaining_time": "0:10:38"}
385
+ {"current_steps": 385, "total_steps": 420, "loss": 0.1443, "lr": 2.2213597106929605e-08, "epoch": 11.0, "percentage": 91.67, "elapsed_time": "1:53:51", "remaining_time": "0:10:21"}
386
+ {"current_steps": 386, "total_steps": 420, "loss": 0.1545, "lr": 2.100524384225555e-08, "epoch": 11.028725314183124, "percentage": 91.9, "elapsed_time": "1:54:10", "remaining_time": "0:10:03"}
387
+ {"current_steps": 387, "total_steps": 420, "loss": 0.1192, "lr": 1.9829976588200125e-08, "epoch": 11.057450628366247, "percentage": 92.14, "elapsed_time": "1:54:31", "remaining_time": "0:09:45"}
388
+ {"current_steps": 388, "total_steps": 420, "loss": 0.1276, "lr": 1.8687876524993984e-08, "epoch": 11.08617594254937, "percentage": 92.38, "elapsed_time": "1:54:50", "remaining_time": "0:09:28"}
389
+ {"current_steps": 389, "total_steps": 420, "loss": 0.1147, "lr": 1.7579022541882537e-08, "epoch": 11.114901256732496, "percentage": 92.62, "elapsed_time": "1:55:10", "remaining_time": "0:09:10"}
390
+ {"current_steps": 390, "total_steps": 420, "loss": 0.1471, "lr": 1.6503491231676382e-08, "epoch": 11.14362657091562, "percentage": 92.86, "elapsed_time": "1:55:27", "remaining_time": "0:08:52"}
391
+ {"current_steps": 391, "total_steps": 420, "loss": 0.1236, "lr": 1.5461356885461075e-08, "epoch": 11.172351885098744, "percentage": 93.1, "elapsed_time": "1:55:46", "remaining_time": "0:08:35"}
392
+ {"current_steps": 392, "total_steps": 420, "loss": 0.1393, "lr": 1.4452691487465085e-08, "epoch": 11.201077199281867, "percentage": 93.33, "elapsed_time": "1:56:01", "remaining_time": "0:08:17"}
393
+ {"current_steps": 393, "total_steps": 420, "loss": 0.1522, "lr": 1.3477564710088096e-08, "epoch": 11.22980251346499, "percentage": 93.57, "elapsed_time": "1:56:20", "remaining_time": "0:07:59"}
394
+ {"current_steps": 394, "total_steps": 420, "loss": 0.1282, "lr": 1.253604390908819e-08, "epoch": 11.258527827648114, "percentage": 93.81, "elapsed_time": "1:56:34", "remaining_time": "0:07:41"}
395
+ {"current_steps": 395, "total_steps": 420, "loss": 0.1566, "lr": 1.1628194118929402e-08, "epoch": 11.287253141831238, "percentage": 94.05, "elapsed_time": "1:56:51", "remaining_time": "0:07:23"}
396
+ {"current_steps": 396, "total_steps": 420, "loss": 0.1244, "lr": 1.0754078048289373e-08, "epoch": 11.315978456014363, "percentage": 94.29, "elapsed_time": "1:57:12", "remaining_time": "0:07:06"}
397
+ {"current_steps": 397, "total_steps": 420, "loss": 0.1076, "lr": 9.913756075728086e-09, "epoch": 11.344703770197487, "percentage": 94.52, "elapsed_time": "1:57:27", "remaining_time": "0:06:48"}
398
+ {"current_steps": 398, "total_steps": 420, "loss": 0.1476, "lr": 9.107286245517099e-09, "epoch": 11.37342908438061, "percentage": 94.76, "elapsed_time": "1:57:48", "remaining_time": "0:06:30"}
399
+ {"current_steps": 399, "total_steps": 420, "loss": 0.1207, "lr": 8.334724263630299e-09, "epoch": 11.402154398563734, "percentage": 95.0, "elapsed_time": "1:58:05", "remaining_time": "0:06:12"}
400
+ {"current_steps": 400, "total_steps": 420, "loss": 0.1461, "lr": 7.59612349389599e-09, "epoch": 11.430879712746858, "percentage": 95.24, "elapsed_time": "1:58:22", "remaining_time": "0:05:55"}
401
+ {"current_steps": 401, "total_steps": 420, "loss": 0.1465, "lr": 6.8915349543108844e-09, "epoch": 11.459605026929982, "percentage": 95.48, "elapsed_time": "1:58:43", "remaining_time": "0:05:37"}
402
+ {"current_steps": 402, "total_steps": 420, "loss": 0.148, "lr": 6.2210073135161574e-09, "epoch": 11.488330341113105, "percentage": 95.71, "elapsed_time": "1:59:04", "remaining_time": "0:05:19"}
403
+ {"current_steps": 403, "total_steps": 420, "loss": 0.1451, "lr": 5.5845868874357385e-09, "epoch": 11.517055655296229, "percentage": 95.95, "elapsed_time": "1:59:25", "remaining_time": "0:05:02"}
404
+ {"current_steps": 404, "total_steps": 420, "loss": 0.1501, "lr": 4.9823176360768156e-09, "epoch": 11.545780969479354, "percentage": 96.19, "elapsed_time": "1:59:39", "remaining_time": "0:04:44"}
405
+ {"current_steps": 405, "total_steps": 420, "loss": 0.1347, "lr": 4.414241160493659e-09, "epoch": 11.574506283662478, "percentage": 96.43, "elapsed_time": "1:59:56", "remaining_time": "0:04:26"}
406
+ {"current_steps": 406, "total_steps": 420, "loss": 0.1556, "lr": 3.880396699913968e-09, "epoch": 11.603231597845602, "percentage": 96.67, "elapsed_time": "2:00:14", "remaining_time": "0:04:08"}
407
+ {"current_steps": 407, "total_steps": 420, "loss": 0.1326, "lr": 3.380821129028488e-09, "epoch": 11.631956912028725, "percentage": 96.9, "elapsed_time": "2:00:30", "remaining_time": "0:03:50"}
408
+ {"current_steps": 408, "total_steps": 420, "loss": 0.1181, "lr": 2.915548955443936e-09, "epoch": 11.660682226211849, "percentage": 97.14, "elapsed_time": "2:00:50", "remaining_time": "0:03:33"}
409
+ {"current_steps": 409, "total_steps": 420, "loss": 0.1289, "lr": 2.484612317299295e-09, "epoch": 11.689407540394972, "percentage": 97.38, "elapsed_time": "2:01:08", "remaining_time": "0:03:15"}
410
+ {"current_steps": 410, "total_steps": 420, "loss": 0.1189, "lr": 2.0880409810460906e-09, "epoch": 11.718132854578098, "percentage": 97.62, "elapsed_time": "2:01:29", "remaining_time": "0:02:57"}
411
+ {"current_steps": 411, "total_steps": 420, "loss": 0.1202, "lr": 1.725862339392259e-09, "epoch": 11.746858168761221, "percentage": 97.86, "elapsed_time": "2:01:47", "remaining_time": "0:02:40"}
412
+ {"current_steps": 412, "total_steps": 420, "loss": 0.1373, "lr": 1.3981014094099353e-09, "epoch": 11.775583482944345, "percentage": 98.1, "elapsed_time": "2:02:06", "remaining_time": "0:02:22"}
413
+ {"current_steps": 413, "total_steps": 420, "loss": 0.1364, "lr": 1.1047808308075057e-09, "epoch": 11.804308797127469, "percentage": 98.33, "elapsed_time": "2:02:23", "remaining_time": "0:02:04"}
414
+ {"current_steps": 414, "total_steps": 420, "loss": 0.1264, "lr": 8.459208643659121e-10, "epoch": 11.833034111310592, "percentage": 98.57, "elapsed_time": "2:02:42", "remaining_time": "0:01:46"}
415
+ {"current_steps": 415, "total_steps": 420, "loss": 0.1358, "lr": 6.215393905388278e-10, "epoch": 11.861759425493716, "percentage": 98.81, "elapsed_time": "2:02:59", "remaining_time": "0:01:28"}
416
+ {"current_steps": 416, "total_steps": 420, "loss": 0.146, "lr": 4.3165190821792264e-10, "epoch": 11.89048473967684, "percentage": 99.05, "elapsed_time": "2:03:14", "remaining_time": "0:01:11"}
417
+ {"current_steps": 417, "total_steps": 420, "loss": 0.1208, "lr": 2.762715336622201e-10, "epoch": 11.919210053859963, "percentage": 99.29, "elapsed_time": "2:03:30", "remaining_time": "0:00:53"}
418
+ {"current_steps": 418, "total_steps": 420, "loss": 0.142, "lr": 1.5540899959187725e-10, "epoch": 11.947935368043089, "percentage": 99.52, "elapsed_time": "2:03:45", "remaining_time": "0:00:35"}
419
+ {"current_steps": 419, "total_steps": 420, "loss": 0.1694, "lr": 6.907265444716648e-11, "epoch": 11.976660682226212, "percentage": 99.76, "elapsed_time": "2:04:00", "remaining_time": "0:00:17"}
420
+ {"current_steps": 420, "total_steps": 420, "loss": 0.1326, "lr": 1.7268461811548174e-11, "epoch": 12.0, "percentage": 100.0, "elapsed_time": "2:04:12", "remaining_time": "0:00:00"}
421
+ {"current_steps": 420, "total_steps": 420, "epoch": 12.0, "percentage": 100.0, "elapsed_time": "2:05:33", "remaining_time": "0:00:00"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8da7f055f72a8c41e1d87a4a7864843bb00ea5cb4873b037bd9b1a09f4176684
3
+ size 5816
vocab.json ADDED
The diff for this file is too large to render. See raw diff