Training in progress, step 1000
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- config.json +29 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- trainer_log.jsonl +104 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1536,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8960,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 2,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": true,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.46.1",
|
26 |
+
"use_cache": false,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 151936
|
29 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef9b9a96695ae0c3d6c46b37287272674a17d2ea565e1f745057912a17208989
|
3 |
+
size 3554214752
|
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"model_max_length": 16000,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"padding_side": "right",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
+
"unk_token": null
|
208 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 10, "total_steps": 37092, "loss": 0.6543, "lr": 2.6954177897574127e-08, "epoch": 0.0005391743892165122, "percentage": 0.03, "elapsed_time": "0:00:28", "remaining_time": "1 day, 5:44:34"}
|
2 |
+
{"current_steps": 20, "total_steps": 37092, "loss": 0.6618, "lr": 5.3908355795148254e-08, "epoch": 0.0010783487784330244, "percentage": 0.05, "elapsed_time": "0:01:03", "remaining_time": "1 day, 8:26:43"}
|
3 |
+
{"current_steps": 30, "total_steps": 37092, "loss": 0.659, "lr": 8.086253369272238e-08, "epoch": 0.0016175231676495367, "percentage": 0.08, "elapsed_time": "0:01:32", "remaining_time": "1 day, 7:48:53"}
|
4 |
+
{"current_steps": 40, "total_steps": 37092, "loss": 0.663, "lr": 1.0781671159029651e-07, "epoch": 0.002156697556866049, "percentage": 0.11, "elapsed_time": "0:02:01", "remaining_time": "1 day, 7:10:58"}
|
5 |
+
{"current_steps": 50, "total_steps": 37092, "loss": 0.6439, "lr": 1.3477088948787063e-07, "epoch": 0.002695871946082561, "percentage": 0.13, "elapsed_time": "0:02:30", "remaining_time": "1 day, 7:02:26"}
|
6 |
+
{"current_steps": 60, "total_steps": 37092, "loss": 0.6419, "lr": 1.6172506738544476e-07, "epoch": 0.0032350463352990733, "percentage": 0.16, "elapsed_time": "0:02:59", "remaining_time": "1 day, 6:50:41"}
|
7 |
+
{"current_steps": 70, "total_steps": 37092, "loss": 0.6301, "lr": 1.886792452830189e-07, "epoch": 0.0037742207245155856, "percentage": 0.19, "elapsed_time": "0:03:29", "remaining_time": "1 day, 6:43:03"}
|
8 |
+
{"current_steps": 80, "total_steps": 37092, "loss": 0.5943, "lr": 2.1563342318059302e-07, "epoch": 0.004313395113732098, "percentage": 0.22, "elapsed_time": "0:03:56", "remaining_time": "1 day, 6:21:42"}
|
9 |
+
{"current_steps": 90, "total_steps": 37092, "loss": 0.5371, "lr": 2.4258760107816715e-07, "epoch": 0.00485256950294861, "percentage": 0.24, "elapsed_time": "0:04:25", "remaining_time": "1 day, 6:22:38"}
|
10 |
+
{"current_steps": 100, "total_steps": 37092, "loss": 0.522, "lr": 2.6954177897574125e-07, "epoch": 0.005391743892165122, "percentage": 0.27, "elapsed_time": "0:04:53", "remaining_time": "1 day, 6:10:47"}
|
11 |
+
{"current_steps": 110, "total_steps": 37092, "loss": 0.48, "lr": 2.964959568733154e-07, "epoch": 0.0059309182813816344, "percentage": 0.3, "elapsed_time": "0:05:22", "remaining_time": "1 day, 6:07:07"}
|
12 |
+
{"current_steps": 120, "total_steps": 37092, "loss": 0.4014, "lr": 3.234501347708895e-07, "epoch": 0.006470092670598147, "percentage": 0.32, "elapsed_time": "0:05:54", "remaining_time": "1 day, 6:19:29"}
|
13 |
+
{"current_steps": 130, "total_steps": 37092, "loss": 0.3684, "lr": 3.504043126684636e-07, "epoch": 0.007009267059814659, "percentage": 0.35, "elapsed_time": "0:06:26", "remaining_time": "1 day, 6:32:51"}
|
14 |
+
{"current_steps": 140, "total_steps": 37092, "loss": 0.3394, "lr": 3.773584905660378e-07, "epoch": 0.007548441449031171, "percentage": 0.38, "elapsed_time": "0:07:00", "remaining_time": "1 day, 6:51:41"}
|
15 |
+
{"current_steps": 150, "total_steps": 37092, "loss": 0.3166, "lr": 4.043126684636119e-07, "epoch": 0.008087615838247682, "percentage": 0.4, "elapsed_time": "0:07:33", "remaining_time": "1 day, 7:01:52"}
|
16 |
+
{"current_steps": 160, "total_steps": 37092, "loss": 0.29, "lr": 4.3126684636118604e-07, "epoch": 0.008626790227464196, "percentage": 0.43, "elapsed_time": "0:08:02", "remaining_time": "1 day, 6:54:53"}
|
17 |
+
{"current_steps": 170, "total_steps": 37092, "loss": 0.2575, "lr": 4.5822102425876014e-07, "epoch": 0.009165964616680707, "percentage": 0.46, "elapsed_time": "0:08:30", "remaining_time": "1 day, 6:46:16"}
|
18 |
+
{"current_steps": 180, "total_steps": 37092, "loss": 0.2596, "lr": 4.851752021563343e-07, "epoch": 0.00970513900589722, "percentage": 0.49, "elapsed_time": "0:09:03", "remaining_time": "1 day, 6:59:12"}
|
19 |
+
{"current_steps": 190, "total_steps": 37092, "loss": 0.2362, "lr": 5.121293800539083e-07, "epoch": 0.010244313395113731, "percentage": 0.51, "elapsed_time": "0:09:31", "remaining_time": "1 day, 6:50:06"}
|
20 |
+
{"current_steps": 200, "total_steps": 37092, "loss": 0.236, "lr": 5.390835579514825e-07, "epoch": 0.010783487784330244, "percentage": 0.54, "elapsed_time": "0:10:01", "remaining_time": "1 day, 6:48:22"}
|
21 |
+
{"current_steps": 210, "total_steps": 37092, "loss": 0.2396, "lr": 5.660377358490567e-07, "epoch": 0.011322662173546756, "percentage": 0.57, "elapsed_time": "0:10:34", "remaining_time": "1 day, 6:55:56"}
|
22 |
+
{"current_steps": 220, "total_steps": 37092, "loss": 0.2372, "lr": 5.929919137466308e-07, "epoch": 0.011861836562763269, "percentage": 0.59, "elapsed_time": "0:11:05", "remaining_time": "1 day, 6:57:46"}
|
23 |
+
{"current_steps": 230, "total_steps": 37092, "loss": 0.2109, "lr": 6.199460916442049e-07, "epoch": 0.01240101095197978, "percentage": 0.62, "elapsed_time": "0:11:37", "remaining_time": "1 day, 7:03:55"}
|
24 |
+
{"current_steps": 240, "total_steps": 37092, "loss": 0.2123, "lr": 6.46900269541779e-07, "epoch": 0.012940185341196293, "percentage": 0.65, "elapsed_time": "0:12:10", "remaining_time": "1 day, 7:09:08"}
|
25 |
+
{"current_steps": 250, "total_steps": 37092, "loss": 0.2042, "lr": 6.738544474393531e-07, "epoch": 0.013479359730412805, "percentage": 0.67, "elapsed_time": "0:12:37", "remaining_time": "1 day, 7:01:17"}
|
26 |
+
{"current_steps": 260, "total_steps": 37092, "loss": 0.2052, "lr": 7.008086253369272e-07, "epoch": 0.014018534119629318, "percentage": 0.7, "elapsed_time": "0:13:07", "remaining_time": "1 day, 6:59:51"}
|
27 |
+
{"current_steps": 270, "total_steps": 37092, "loss": 0.1883, "lr": 7.277628032345015e-07, "epoch": 0.014557708508845829, "percentage": 0.73, "elapsed_time": "0:13:36", "remaining_time": "1 day, 6:56:29"}
|
28 |
+
{"current_steps": 280, "total_steps": 37092, "loss": 0.1897, "lr": 7.547169811320755e-07, "epoch": 0.015096882898062342, "percentage": 0.75, "elapsed_time": "0:14:08", "remaining_time": "1 day, 7:00:06"}
|
29 |
+
{"current_steps": 290, "total_steps": 37092, "loss": 0.1992, "lr": 7.816711590296497e-07, "epoch": 0.015636057287278855, "percentage": 0.78, "elapsed_time": "0:14:40", "remaining_time": "1 day, 7:03:01"}
|
30 |
+
{"current_steps": 300, "total_steps": 37092, "loss": 0.1795, "lr": 8.086253369272238e-07, "epoch": 0.016175231676495365, "percentage": 0.81, "elapsed_time": "0:15:13", "remaining_time": "1 day, 7:06:43"}
|
31 |
+
{"current_steps": 310, "total_steps": 37092, "loss": 0.171, "lr": 8.355795148247979e-07, "epoch": 0.016714406065711878, "percentage": 0.84, "elapsed_time": "0:15:41", "remaining_time": "1 day, 7:02:24"}
|
32 |
+
{"current_steps": 320, "total_steps": 37092, "loss": 0.1773, "lr": 8.625336927223721e-07, "epoch": 0.01725358045492839, "percentage": 0.86, "elapsed_time": "0:16:12", "remaining_time": "1 day, 7:02:00"}
|
33 |
+
{"current_steps": 330, "total_steps": 37092, "loss": 0.1666, "lr": 8.894878706199461e-07, "epoch": 0.017792754844144904, "percentage": 0.89, "elapsed_time": "0:16:38", "remaining_time": "1 day, 6:54:44"}
|
34 |
+
{"current_steps": 340, "total_steps": 37092, "loss": 0.1576, "lr": 9.164420485175203e-07, "epoch": 0.018331929233361414, "percentage": 0.92, "elapsed_time": "0:17:08", "remaining_time": "1 day, 6:52:08"}
|
35 |
+
{"current_steps": 350, "total_steps": 37092, "loss": 0.1636, "lr": 9.433962264150944e-07, "epoch": 0.018871103622577927, "percentage": 0.94, "elapsed_time": "0:17:38", "remaining_time": "1 day, 6:52:44"}
|
36 |
+
{"current_steps": 360, "total_steps": 37092, "loss": 0.1567, "lr": 9.703504043126686e-07, "epoch": 0.01941027801179444, "percentage": 0.97, "elapsed_time": "0:18:09", "remaining_time": "1 day, 6:52:01"}
|
37 |
+
{"current_steps": 370, "total_steps": 37092, "loss": 0.1528, "lr": 9.973045822102428e-07, "epoch": 0.019949452401010953, "percentage": 1.0, "elapsed_time": "0:18:38", "remaining_time": "1 day, 6:50:17"}
|
38 |
+
{"current_steps": 380, "total_steps": 37092, "loss": 0.153, "lr": 1.0242587601078167e-06, "epoch": 0.020488626790227463, "percentage": 1.02, "elapsed_time": "0:19:09", "remaining_time": "1 day, 6:50:53"}
|
39 |
+
{"current_steps": 390, "total_steps": 37092, "loss": 0.1419, "lr": 1.0512129380053909e-06, "epoch": 0.021027801179443976, "percentage": 1.05, "elapsed_time": "0:19:36", "remaining_time": "1 day, 6:45:18"}
|
40 |
+
{"current_steps": 400, "total_steps": 37092, "loss": 0.1461, "lr": 1.078167115902965e-06, "epoch": 0.02156697556866049, "percentage": 1.08, "elapsed_time": "0:20:09", "remaining_time": "1 day, 6:49:39"}
|
41 |
+
{"current_steps": 410, "total_steps": 37092, "loss": 0.1487, "lr": 1.1051212938005392e-06, "epoch": 0.022106149957877002, "percentage": 1.11, "elapsed_time": "0:20:38", "remaining_time": "1 day, 6:46:03"}
|
42 |
+
{"current_steps": 420, "total_steps": 37092, "loss": 0.1468, "lr": 1.1320754716981133e-06, "epoch": 0.02264532434709351, "percentage": 1.13, "elapsed_time": "0:21:06", "remaining_time": "1 day, 6:42:41"}
|
43 |
+
{"current_steps": 430, "total_steps": 37092, "loss": 0.1579, "lr": 1.1590296495956873e-06, "epoch": 0.023184498736310025, "percentage": 1.16, "elapsed_time": "0:21:38", "remaining_time": "1 day, 6:45:31"}
|
44 |
+
{"current_steps": 440, "total_steps": 37092, "loss": 0.145, "lr": 1.1859838274932616e-06, "epoch": 0.023723673125526538, "percentage": 1.19, "elapsed_time": "0:22:12", "remaining_time": "1 day, 6:50:10"}
|
45 |
+
{"current_steps": 450, "total_steps": 37092, "loss": 0.1582, "lr": 1.2129380053908358e-06, "epoch": 0.02426284751474305, "percentage": 1.21, "elapsed_time": "0:22:44", "remaining_time": "1 day, 6:52:26"}
|
46 |
+
{"current_steps": 460, "total_steps": 37092, "loss": 0.156, "lr": 1.2398921832884097e-06, "epoch": 0.02480202190395956, "percentage": 1.24, "elapsed_time": "0:23:19", "remaining_time": "1 day, 6:56:53"}
|
47 |
+
{"current_steps": 470, "total_steps": 37092, "loss": 0.135, "lr": 1.266846361185984e-06, "epoch": 0.025341196293176074, "percentage": 1.27, "elapsed_time": "0:23:47", "remaining_time": "1 day, 6:53:40"}
|
48 |
+
{"current_steps": 480, "total_steps": 37092, "loss": 0.1366, "lr": 1.293800539083558e-06, "epoch": 0.025880370682392587, "percentage": 1.29, "elapsed_time": "0:24:16", "remaining_time": "1 day, 6:51:04"}
|
49 |
+
{"current_steps": 490, "total_steps": 37092, "loss": 0.1436, "lr": 1.3207547169811322e-06, "epoch": 0.0264195450716091, "percentage": 1.32, "elapsed_time": "0:24:51", "remaining_time": "1 day, 6:57:09"}
|
50 |
+
{"current_steps": 500, "total_steps": 37092, "loss": 0.1347, "lr": 1.3477088948787062e-06, "epoch": 0.02695871946082561, "percentage": 1.35, "elapsed_time": "0:25:22", "remaining_time": "1 day, 6:56:53"}
|
51 |
+
{"current_steps": 510, "total_steps": 37092, "loss": 0.1417, "lr": 1.3746630727762805e-06, "epoch": 0.027497893850042122, "percentage": 1.37, "elapsed_time": "0:25:54", "remaining_time": "1 day, 6:58:07"}
|
52 |
+
{"current_steps": 520, "total_steps": 37092, "loss": 0.1423, "lr": 1.4016172506738545e-06, "epoch": 0.028037068239258636, "percentage": 1.4, "elapsed_time": "0:26:25", "remaining_time": "1 day, 6:58:18"}
|
53 |
+
{"current_steps": 530, "total_steps": 37092, "loss": 0.1274, "lr": 1.4285714285714286e-06, "epoch": 0.02857624262847515, "percentage": 1.43, "elapsed_time": "0:26:53", "remaining_time": "1 day, 6:54:34"}
|
54 |
+
{"current_steps": 540, "total_steps": 37092, "loss": 0.1319, "lr": 1.455525606469003e-06, "epoch": 0.029115417017691658, "percentage": 1.46, "elapsed_time": "0:27:22", "remaining_time": "1 day, 6:53:27"}
|
55 |
+
{"current_steps": 550, "total_steps": 37092, "loss": 0.125, "lr": 1.482479784366577e-06, "epoch": 0.02965459140690817, "percentage": 1.48, "elapsed_time": "0:27:52", "remaining_time": "1 day, 6:51:58"}
|
56 |
+
{"current_steps": 560, "total_steps": 37092, "loss": 0.1288, "lr": 1.509433962264151e-06, "epoch": 0.030193765796124684, "percentage": 1.51, "elapsed_time": "0:28:24", "remaining_time": "1 day, 6:53:36"}
|
57 |
+
{"current_steps": 570, "total_steps": 37092, "loss": 0.1431, "lr": 1.5363881401617253e-06, "epoch": 0.030732940185341198, "percentage": 1.54, "elapsed_time": "0:28:54", "remaining_time": "1 day, 6:52:28"}
|
58 |
+
{"current_steps": 580, "total_steps": 37092, "loss": 0.1317, "lr": 1.5633423180592994e-06, "epoch": 0.03127211457455771, "percentage": 1.56, "elapsed_time": "0:29:24", "remaining_time": "1 day, 6:51:02"}
|
59 |
+
{"current_steps": 590, "total_steps": 37092, "loss": 0.1247, "lr": 1.5902964959568734e-06, "epoch": 0.03181128896377422, "percentage": 1.59, "elapsed_time": "0:29:52", "remaining_time": "1 day, 6:48:33"}
|
60 |
+
{"current_steps": 600, "total_steps": 37092, "loss": 0.1239, "lr": 1.6172506738544475e-06, "epoch": 0.03235046335299073, "percentage": 1.62, "elapsed_time": "0:30:24", "remaining_time": "1 day, 6:49:41"}
|
61 |
+
{"current_steps": 610, "total_steps": 37092, "loss": 0.1349, "lr": 1.6442048517520217e-06, "epoch": 0.032889637742207246, "percentage": 1.64, "elapsed_time": "0:30:54", "remaining_time": "1 day, 6:48:44"}
|
62 |
+
{"current_steps": 620, "total_steps": 37092, "loss": 0.124, "lr": 1.6711590296495958e-06, "epoch": 0.033428812131423756, "percentage": 1.67, "elapsed_time": "0:31:23", "remaining_time": "1 day, 6:46:51"}
|
63 |
+
{"current_steps": 630, "total_steps": 37092, "loss": 0.1238, "lr": 1.6981132075471698e-06, "epoch": 0.03396798652064027, "percentage": 1.7, "elapsed_time": "0:31:55", "remaining_time": "1 day, 6:47:57"}
|
64 |
+
{"current_steps": 640, "total_steps": 37092, "loss": 0.1306, "lr": 1.7250673854447441e-06, "epoch": 0.03450716090985678, "percentage": 1.73, "elapsed_time": "0:32:28", "remaining_time": "1 day, 6:50:02"}
|
65 |
+
{"current_steps": 650, "total_steps": 37092, "loss": 0.1034, "lr": 1.7520215633423183e-06, "epoch": 0.03504633529907329, "percentage": 1.75, "elapsed_time": "0:32:54", "remaining_time": "1 day, 6:44:55"}
|
66 |
+
{"current_steps": 660, "total_steps": 37092, "loss": 0.1292, "lr": 1.7789757412398922e-06, "epoch": 0.03558550968828981, "percentage": 1.78, "elapsed_time": "0:33:25", "remaining_time": "1 day, 6:45:11"}
|
67 |
+
{"current_steps": 670, "total_steps": 37092, "loss": 0.1246, "lr": 1.8059299191374666e-06, "epoch": 0.03612468407750632, "percentage": 1.81, "elapsed_time": "0:33:59", "remaining_time": "1 day, 6:47:26"}
|
68 |
+
{"current_steps": 680, "total_steps": 37092, "loss": 0.1151, "lr": 1.8328840970350406e-06, "epoch": 0.03666385846672283, "percentage": 1.83, "elapsed_time": "0:34:31", "remaining_time": "1 day, 6:48:23"}
|
69 |
+
{"current_steps": 690, "total_steps": 37092, "loss": 0.1123, "lr": 1.8598382749326147e-06, "epoch": 0.037203032855939344, "percentage": 1.86, "elapsed_time": "0:34:59", "remaining_time": "1 day, 6:46:28"}
|
70 |
+
{"current_steps": 700, "total_steps": 37092, "loss": 0.1173, "lr": 1.8867924528301889e-06, "epoch": 0.037742207245155854, "percentage": 1.89, "elapsed_time": "0:35:31", "remaining_time": "1 day, 6:47:00"}
|
71 |
+
{"current_steps": 710, "total_steps": 37092, "loss": 0.104, "lr": 1.913746630727763e-06, "epoch": 0.03828138163437237, "percentage": 1.91, "elapsed_time": "0:36:00", "remaining_time": "1 day, 6:45:03"}
|
72 |
+
{"current_steps": 720, "total_steps": 37092, "loss": 0.1097, "lr": 1.940700808625337e-06, "epoch": 0.03882055602358888, "percentage": 1.94, "elapsed_time": "0:36:28", "remaining_time": "1 day, 6:42:56"}
|
73 |
+
{"current_steps": 730, "total_steps": 37092, "loss": 0.1045, "lr": 1.967654986522911e-06, "epoch": 0.03935973041280539, "percentage": 1.97, "elapsed_time": "0:36:59", "remaining_time": "1 day, 6:42:32"}
|
74 |
+
{"current_steps": 740, "total_steps": 37092, "loss": 0.1295, "lr": 1.9946091644204855e-06, "epoch": 0.039898904802021906, "percentage": 2.0, "elapsed_time": "0:37:32", "remaining_time": "1 day, 6:44:02"}
|
75 |
+
{"current_steps": 750, "total_steps": 37092, "loss": 0.1212, "lr": 2.0215633423180597e-06, "epoch": 0.040438079191238416, "percentage": 2.02, "elapsed_time": "0:38:05", "remaining_time": "1 day, 6:45:41"}
|
76 |
+
{"current_steps": 760, "total_steps": 37092, "loss": 0.1083, "lr": 2.0485175202156334e-06, "epoch": 0.040977253580454925, "percentage": 2.05, "elapsed_time": "0:38:34", "remaining_time": "1 day, 6:44:19"}
|
77 |
+
{"current_steps": 770, "total_steps": 37092, "loss": 0.116, "lr": 2.075471698113208e-06, "epoch": 0.04151642796967144, "percentage": 2.08, "elapsed_time": "0:39:06", "remaining_time": "1 day, 6:44:32"}
|
78 |
+
{"current_steps": 780, "total_steps": 37092, "loss": 0.1131, "lr": 2.1024258760107817e-06, "epoch": 0.04205560235888795, "percentage": 2.1, "elapsed_time": "0:39:38", "remaining_time": "1 day, 6:45:13"}
|
79 |
+
{"current_steps": 790, "total_steps": 37092, "loss": 0.1128, "lr": 2.129380053908356e-06, "epoch": 0.04259477674810447, "percentage": 2.13, "elapsed_time": "0:40:13", "remaining_time": "1 day, 6:48:05"}
|
80 |
+
{"current_steps": 800, "total_steps": 37092, "loss": 0.1015, "lr": 2.15633423180593e-06, "epoch": 0.04313395113732098, "percentage": 2.16, "elapsed_time": "0:40:42", "remaining_time": "1 day, 6:46:25"}
|
81 |
+
{"current_steps": 810, "total_steps": 37092, "loss": 0.1205, "lr": 2.183288409703504e-06, "epoch": 0.04367312552653749, "percentage": 2.18, "elapsed_time": "0:41:13", "remaining_time": "1 day, 6:46:55"}
|
82 |
+
{"current_steps": 820, "total_steps": 37092, "loss": 0.1108, "lr": 2.2102425876010783e-06, "epoch": 0.044212299915754004, "percentage": 2.21, "elapsed_time": "0:41:42", "remaining_time": "1 day, 6:45:06"}
|
83 |
+
{"current_steps": 830, "total_steps": 37092, "loss": 0.1179, "lr": 2.2371967654986525e-06, "epoch": 0.044751474304970514, "percentage": 2.24, "elapsed_time": "0:42:14", "remaining_time": "1 day, 6:45:35"}
|
84 |
+
{"current_steps": 840, "total_steps": 37092, "loss": 0.1109, "lr": 2.2641509433962266e-06, "epoch": 0.04529064869418702, "percentage": 2.26, "elapsed_time": "0:42:43", "remaining_time": "1 day, 6:43:46"}
|
85 |
+
{"current_steps": 850, "total_steps": 37092, "loss": 0.1138, "lr": 2.291105121293801e-06, "epoch": 0.04582982308340354, "percentage": 2.29, "elapsed_time": "0:43:10", "remaining_time": "1 day, 6:41:07"}
|
86 |
+
{"current_steps": 860, "total_steps": 37092, "loss": 0.1115, "lr": 2.3180592991913745e-06, "epoch": 0.04636899747262005, "percentage": 2.32, "elapsed_time": "0:43:40", "remaining_time": "1 day, 6:40:04"}
|
87 |
+
{"current_steps": 870, "total_steps": 37092, "loss": 0.1126, "lr": 2.345013477088949e-06, "epoch": 0.046908171861836566, "percentage": 2.35, "elapsed_time": "0:44:11", "remaining_time": "1 day, 6:40:11"}
|
88 |
+
{"current_steps": 880, "total_steps": 37092, "loss": 0.1051, "lr": 2.3719676549865233e-06, "epoch": 0.047447346251053076, "percentage": 2.37, "elapsed_time": "0:44:41", "remaining_time": "1 day, 6:39:15"}
|
89 |
+
{"current_steps": 890, "total_steps": 37092, "loss": 0.0954, "lr": 2.398921832884097e-06, "epoch": 0.047986520640269585, "percentage": 2.4, "elapsed_time": "0:45:11", "remaining_time": "1 day, 6:38:02"}
|
90 |
+
{"current_steps": 900, "total_steps": 37092, "loss": 0.0927, "lr": 2.4258760107816716e-06, "epoch": 0.0485256950294861, "percentage": 2.43, "elapsed_time": "0:45:41", "remaining_time": "1 day, 6:37:44"}
|
91 |
+
{"current_steps": 910, "total_steps": 37092, "loss": 0.1015, "lr": 2.4528301886792453e-06, "epoch": 0.04906486941870261, "percentage": 2.45, "elapsed_time": "0:46:14", "remaining_time": "1 day, 6:38:22"}
|
92 |
+
{"current_steps": 920, "total_steps": 37092, "loss": 0.0877, "lr": 2.4797843665768195e-06, "epoch": 0.04960404380791912, "percentage": 2.48, "elapsed_time": "0:46:44", "remaining_time": "1 day, 6:37:27"}
|
93 |
+
{"current_steps": 930, "total_steps": 37092, "loss": 0.0939, "lr": 2.5067385444743936e-06, "epoch": 0.05014321819713564, "percentage": 2.51, "elapsed_time": "0:47:12", "remaining_time": "1 day, 6:35:46"}
|
94 |
+
{"current_steps": 940, "total_steps": 37092, "loss": 0.1022, "lr": 2.533692722371968e-06, "epoch": 0.05068239258635215, "percentage": 2.53, "elapsed_time": "0:47:46", "remaining_time": "1 day, 6:37:25"}
|
95 |
+
{"current_steps": 950, "total_steps": 37092, "loss": 0.0982, "lr": 2.5606469002695424e-06, "epoch": 0.051221566975568664, "percentage": 2.56, "elapsed_time": "0:48:18", "remaining_time": "1 day, 6:37:51"}
|
96 |
+
{"current_steps": 960, "total_steps": 37092, "loss": 0.099, "lr": 2.587601078167116e-06, "epoch": 0.05176074136478517, "percentage": 2.59, "elapsed_time": "0:48:49", "remaining_time": "1 day, 6:37:42"}
|
97 |
+
{"current_steps": 970, "total_steps": 37092, "loss": 0.1131, "lr": 2.6145552560646903e-06, "epoch": 0.05229991575400168, "percentage": 2.62, "elapsed_time": "0:49:25", "remaining_time": "1 day, 6:40:28"}
|
98 |
+
{"current_steps": 980, "total_steps": 37092, "loss": 0.1011, "lr": 2.6415094339622644e-06, "epoch": 0.0528390901432182, "percentage": 2.64, "elapsed_time": "0:49:59", "remaining_time": "1 day, 6:41:58"}
|
99 |
+
{"current_steps": 990, "total_steps": 37092, "loss": 0.1097, "lr": 2.6684636118598386e-06, "epoch": 0.05337826453243471, "percentage": 2.67, "elapsed_time": "0:50:30", "remaining_time": "1 day, 6:41:44"}
|
100 |
+
{"current_steps": 1000, "total_steps": 37092, "loss": 0.1043, "lr": 2.6954177897574123e-06, "epoch": 0.05391743892165122, "percentage": 2.7, "elapsed_time": "0:51:02", "remaining_time": "1 day, 6:42:08"}
|
101 |
+
{"current_steps": 1010, "total_steps": 37092, "loss": 0.1017, "lr": 2.722371967654987e-06, "epoch": 0.054456613310867735, "percentage": 2.72, "elapsed_time": "0:51:54", "remaining_time": "1 day, 6:54:31"}
|
102 |
+
{"current_steps": 1020, "total_steps": 37092, "loss": 0.0933, "lr": 2.749326145552561e-06, "epoch": 0.054995787700084245, "percentage": 2.75, "elapsed_time": "0:52:22", "remaining_time": "1 day, 6:52:23"}
|
103 |
+
{"current_steps": 1030, "total_steps": 37092, "loss": 0.0949, "lr": 2.776280323450135e-06, "epoch": 0.05553496208930076, "percentage": 2.78, "elapsed_time": "0:52:53", "remaining_time": "1 day, 6:51:41"}
|
104 |
+
{"current_steps": 1040, "total_steps": 37092, "loss": 0.0897, "lr": 2.803234501347709e-06, "epoch": 0.05607413647851727, "percentage": 2.8, "elapsed_time": "0:53:20", "remaining_time": "1 day, 6:48:52"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2716443116ce5dd35c0a2ebcedfa1619f6a6e0ccf0f377c451f01aa3c84b34b3
|
3 |
+
size 7416
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|