Training in progress, step 500
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 +84 -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 sha256:0a6d0ece481dfda70433fd616d69f631b5fb9fa4132e4b2fb64c880dc5fbfbee
|
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 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 10, "total_steps": 247180, "loss": 0.757, "lr": 4.045634760093859e-09, "epoch": 8.091269520187717e-05, "percentage": 0.0, "elapsed_time": "0:00:03", "remaining_time": "1 day, 3:20:19"}
|
2 |
+
{"current_steps": 20, "total_steps": 247180, "loss": 0.6757, "lr": 8.091269520187718e-09, "epoch": 0.00016182539040375434, "percentage": 0.01, "elapsed_time": "0:00:08", "remaining_time": "1 day, 4:37:19"}
|
3 |
+
{"current_steps": 30, "total_steps": 247180, "loss": 0.7167, "lr": 1.2136904280281577e-08, "epoch": 0.00024273808560563152, "percentage": 0.01, "elapsed_time": "0:00:12", "remaining_time": "1 day, 4:00:14"}
|
4 |
+
{"current_steps": 40, "total_steps": 247180, "loss": 0.7246, "lr": 1.6182539040375435e-08, "epoch": 0.0003236507808075087, "percentage": 0.02, "elapsed_time": "0:00:17", "remaining_time": "1 day, 5:15:44"}
|
5 |
+
{"current_steps": 50, "total_steps": 247180, "loss": 0.7254, "lr": 2.0228173800469296e-08, "epoch": 0.00040456347600938586, "percentage": 0.02, "elapsed_time": "0:00:21", "remaining_time": "1 day, 5:01:24"}
|
6 |
+
{"current_steps": 60, "total_steps": 247180, "loss": 0.7426, "lr": 2.4273808560563153e-08, "epoch": 0.00048547617121126303, "percentage": 0.02, "elapsed_time": "0:00:24", "remaining_time": "1 day, 3:45:42"}
|
7 |
+
{"current_steps": 70, "total_steps": 247180, "loss": 0.7289, "lr": 2.8319443320657014e-08, "epoch": 0.0005663888664131403, "percentage": 0.03, "elapsed_time": "0:00:27", "remaining_time": "1 day, 3:18:57"}
|
8 |
+
{"current_steps": 80, "total_steps": 247180, "loss": 0.7167, "lr": 3.236507808075087e-08, "epoch": 0.0006473015616150174, "percentage": 0.03, "elapsed_time": "0:00:32", "remaining_time": "1 day, 3:28:57"}
|
9 |
+
{"current_steps": 90, "total_steps": 247180, "loss": 0.7272, "lr": 3.641071284084473e-08, "epoch": 0.0007282142568168946, "percentage": 0.04, "elapsed_time": "0:00:35", "remaining_time": "1 day, 3:04:35"}
|
10 |
+
{"current_steps": 100, "total_steps": 247180, "loss": 0.714, "lr": 4.045634760093859e-08, "epoch": 0.0008091269520187717, "percentage": 0.04, "elapsed_time": "0:00:39", "remaining_time": "1 day, 3:03:34"}
|
11 |
+
{"current_steps": 110, "total_steps": 247180, "loss": 0.7236, "lr": 4.4501982361032446e-08, "epoch": 0.000890039647220649, "percentage": 0.04, "elapsed_time": "0:00:43", "remaining_time": "1 day, 2:57:05"}
|
12 |
+
{"current_steps": 120, "total_steps": 247180, "loss": 0.6626, "lr": 4.8547617121126306e-08, "epoch": 0.0009709523424225261, "percentage": 0.05, "elapsed_time": "0:00:47", "remaining_time": "1 day, 3:11:48"}
|
13 |
+
{"current_steps": 130, "total_steps": 247180, "loss": 0.7119, "lr": 5.2593251881220174e-08, "epoch": 0.0010518650376244033, "percentage": 0.05, "elapsed_time": "0:00:51", "remaining_time": "1 day, 3:06:56"}
|
14 |
+
{"current_steps": 140, "total_steps": 247180, "loss": 0.691, "lr": 5.663888664131403e-08, "epoch": 0.0011327777328262805, "percentage": 0.06, "elapsed_time": "0:00:55", "remaining_time": "1 day, 3:20:48"}
|
15 |
+
{"current_steps": 150, "total_steps": 247180, "loss": 0.7035, "lr": 6.068452140140788e-08, "epoch": 0.0012136904280281575, "percentage": 0.06, "elapsed_time": "0:00:59", "remaining_time": "1 day, 3:08:30"}
|
16 |
+
{"current_steps": 160, "total_steps": 247180, "loss": 0.6775, "lr": 6.473015616150174e-08, "epoch": 0.0012946031232300348, "percentage": 0.06, "elapsed_time": "0:01:02", "remaining_time": "1 day, 2:56:54"}
|
17 |
+
{"current_steps": 170, "total_steps": 247180, "loss": 0.6397, "lr": 6.87757909215956e-08, "epoch": 0.001375515818431912, "percentage": 0.07, "elapsed_time": "0:01:06", "remaining_time": "1 day, 2:51:26"}
|
18 |
+
{"current_steps": 180, "total_steps": 247180, "loss": 0.6441, "lr": 7.282142568168946e-08, "epoch": 0.0014564285136337892, "percentage": 0.07, "elapsed_time": "0:01:10", "remaining_time": "1 day, 2:41:15"}
|
19 |
+
{"current_steps": 190, "total_steps": 247180, "loss": 0.6136, "lr": 7.686706044178332e-08, "epoch": 0.0015373412088356662, "percentage": 0.08, "elapsed_time": "0:01:13", "remaining_time": "1 day, 2:42:36"}
|
20 |
+
{"current_steps": 200, "total_steps": 247180, "loss": 0.6242, "lr": 8.091269520187718e-08, "epoch": 0.0016182539040375434, "percentage": 0.08, "elapsed_time": "0:01:18", "remaining_time": "1 day, 2:56:57"}
|
21 |
+
{"current_steps": 210, "total_steps": 247180, "loss": 0.6183, "lr": 8.495832996197104e-08, "epoch": 0.0016991665992394207, "percentage": 0.08, "elapsed_time": "0:01:22", "remaining_time": "1 day, 3:00:54"}
|
22 |
+
{"current_steps": 220, "total_steps": 247180, "loss": 0.5846, "lr": 8.900396472206489e-08, "epoch": 0.001780079294441298, "percentage": 0.09, "elapsed_time": "0:01:26", "remaining_time": "1 day, 2:58:29"}
|
23 |
+
{"current_steps": 230, "total_steps": 247180, "loss": 0.5563, "lr": 9.304959948215877e-08, "epoch": 0.001860991989643175, "percentage": 0.09, "elapsed_time": "0:01:30", "remaining_time": "1 day, 2:50:38"}
|
24 |
+
{"current_steps": 240, "total_steps": 247180, "loss": 0.5659, "lr": 9.709523424225261e-08, "epoch": 0.0019419046848450521, "percentage": 0.1, "elapsed_time": "0:01:34", "remaining_time": "1 day, 3:02:42"}
|
25 |
+
{"current_steps": 250, "total_steps": 247180, "loss": 0.5424, "lr": 1.0114086900234647e-07, "epoch": 0.0020228173800469294, "percentage": 0.1, "elapsed_time": "0:01:38", "remaining_time": "1 day, 3:04:42"}
|
26 |
+
{"current_steps": 260, "total_steps": 247180, "loss": 0.5453, "lr": 1.0518650376244035e-07, "epoch": 0.0021037300752488066, "percentage": 0.11, "elapsed_time": "0:01:42", "remaining_time": "1 day, 2:56:01"}
|
27 |
+
{"current_steps": 270, "total_steps": 247180, "loss": 0.4841, "lr": 1.092321385225342e-07, "epoch": 0.002184642770450684, "percentage": 0.11, "elapsed_time": "0:01:47", "remaining_time": "1 day, 3:15:12"}
|
28 |
+
{"current_steps": 280, "total_steps": 247180, "loss": 0.5116, "lr": 1.1327777328262805e-07, "epoch": 0.002265555465652561, "percentage": 0.11, "elapsed_time": "0:01:50", "remaining_time": "1 day, 3:08:47"}
|
29 |
+
{"current_steps": 290, "total_steps": 247180, "loss": 0.4909, "lr": 1.173234080427219e-07, "epoch": 0.0023464681608544383, "percentage": 0.12, "elapsed_time": "0:01:54", "remaining_time": "1 day, 3:10:41"}
|
30 |
+
{"current_steps": 300, "total_steps": 247180, "loss": 0.4196, "lr": 1.2136904280281576e-07, "epoch": 0.002427380856056315, "percentage": 0.12, "elapsed_time": "0:01:58", "remaining_time": "1 day, 3:07:23"}
|
31 |
+
{"current_steps": 310, "total_steps": 247180, "loss": 0.4117, "lr": 1.2541467756290965e-07, "epoch": 0.0025082935512581923, "percentage": 0.13, "elapsed_time": "0:02:02", "remaining_time": "1 day, 3:09:35"}
|
32 |
+
{"current_steps": 320, "total_steps": 247180, "loss": 0.4483, "lr": 1.2946031232300348e-07, "epoch": 0.0025892062464600695, "percentage": 0.13, "elapsed_time": "0:02:06", "remaining_time": "1 day, 3:06:11"}
|
33 |
+
{"current_steps": 330, "total_steps": 247180, "loss": 0.4065, "lr": 1.3350594708309734e-07, "epoch": 0.0026701189416619467, "percentage": 0.13, "elapsed_time": "0:02:10", "remaining_time": "1 day, 3:06:51"}
|
34 |
+
{"current_steps": 340, "total_steps": 247180, "loss": 0.3833, "lr": 1.375515818431912e-07, "epoch": 0.002751031636863824, "percentage": 0.14, "elapsed_time": "0:02:14", "remaining_time": "1 day, 3:06:44"}
|
35 |
+
{"current_steps": 350, "total_steps": 247180, "loss": 0.3677, "lr": 1.4159721660328507e-07, "epoch": 0.002831944332065701, "percentage": 0.14, "elapsed_time": "0:02:18", "remaining_time": "1 day, 3:02:32"}
|
36 |
+
{"current_steps": 360, "total_steps": 247180, "loss": 0.35, "lr": 1.4564285136337893e-07, "epoch": 0.0029128570272675784, "percentage": 0.15, "elapsed_time": "0:02:21", "remaining_time": "1 day, 2:59:07"}
|
37 |
+
{"current_steps": 370, "total_steps": 247180, "loss": 0.3837, "lr": 1.4968848612347279e-07, "epoch": 0.0029937697224694556, "percentage": 0.15, "elapsed_time": "0:02:25", "remaining_time": "1 day, 3:00:52"}
|
38 |
+
{"current_steps": 380, "total_steps": 247180, "loss": 0.3692, "lr": 1.5373412088356665e-07, "epoch": 0.0030746824176713324, "percentage": 0.15, "elapsed_time": "0:02:29", "remaining_time": "1 day, 3:01:22"}
|
39 |
+
{"current_steps": 390, "total_steps": 247180, "loss": 0.3554, "lr": 1.577797556436605e-07, "epoch": 0.0031555951128732097, "percentage": 0.16, "elapsed_time": "0:02:33", "remaining_time": "1 day, 2:57:57"}
|
40 |
+
{"current_steps": 400, "total_steps": 247180, "loss": 0.3335, "lr": 1.6182539040375437e-07, "epoch": 0.003236507808075087, "percentage": 0.16, "elapsed_time": "0:02:36", "remaining_time": "1 day, 2:54:06"}
|
41 |
+
{"current_steps": 410, "total_steps": 247180, "loss": 0.2995, "lr": 1.658710251638482e-07, "epoch": 0.003317420503276964, "percentage": 0.17, "elapsed_time": "0:02:40", "remaining_time": "1 day, 2:48:22"}
|
42 |
+
{"current_steps": 420, "total_steps": 247180, "loss": 0.303, "lr": 1.699166599239421e-07, "epoch": 0.0033983331984788413, "percentage": 0.17, "elapsed_time": "0:02:43", "remaining_time": "1 day, 2:42:57"}
|
43 |
+
{"current_steps": 430, "total_steps": 247180, "loss": 0.301, "lr": 1.7396229468403595e-07, "epoch": 0.0034792458936807186, "percentage": 0.17, "elapsed_time": "0:02:47", "remaining_time": "1 day, 2:45:55"}
|
44 |
+
{"current_steps": 440, "total_steps": 247180, "loss": 0.277, "lr": 1.7800792944412978e-07, "epoch": 0.003560158588882596, "percentage": 0.18, "elapsed_time": "0:02:51", "remaining_time": "1 day, 2:41:51"}
|
45 |
+
{"current_steps": 450, "total_steps": 247180, "loss": 0.2813, "lr": 1.8205356420422367e-07, "epoch": 0.003641071284084473, "percentage": 0.18, "elapsed_time": "0:02:54", "remaining_time": "1 day, 2:34:03"}
|
46 |
+
{"current_steps": 460, "total_steps": 247180, "loss": 0.3122, "lr": 1.8609919896431753e-07, "epoch": 0.00372198397928635, "percentage": 0.19, "elapsed_time": "0:02:58", "remaining_time": "1 day, 2:37:18"}
|
47 |
+
{"current_steps": 470, "total_steps": 247180, "loss": 0.3129, "lr": 1.9014483372441137e-07, "epoch": 0.003802896674488227, "percentage": 0.19, "elapsed_time": "0:03:02", "remaining_time": "1 day, 2:37:04"}
|
48 |
+
{"current_steps": 480, "total_steps": 247180, "loss": 0.271, "lr": 1.9419046848450523e-07, "epoch": 0.0038838093696901043, "percentage": 0.19, "elapsed_time": "0:03:06", "remaining_time": "1 day, 2:37:39"}
|
49 |
+
{"current_steps": 490, "total_steps": 247180, "loss": 0.246, "lr": 1.982361032445991e-07, "epoch": 0.003964722064891982, "percentage": 0.2, "elapsed_time": "0:03:10", "remaining_time": "1 day, 2:36:29"}
|
50 |
+
{"current_steps": 500, "total_steps": 247180, "loss": 0.2549, "lr": 2.0228173800469295e-07, "epoch": 0.004045634760093859, "percentage": 0.2, "elapsed_time": "0:03:13", "remaining_time": "1 day, 2:34:09"}
|
51 |
+
{"current_steps": 510, "total_steps": 247180, "loss": 0.2478, "lr": 2.063273727647868e-07, "epoch": 0.0041265474552957355, "percentage": 0.21, "elapsed_time": "0:03:38", "remaining_time": "1 day, 5:17:28"}
|
52 |
+
{"current_steps": 520, "total_steps": 247180, "loss": 0.2173, "lr": 2.103730075248807e-07, "epoch": 0.004207460150497613, "percentage": 0.21, "elapsed_time": "0:03:42", "remaining_time": "1 day, 5:15:25"}
|
53 |
+
{"current_steps": 530, "total_steps": 247180, "loss": 0.2799, "lr": 2.1441864228497453e-07, "epoch": 0.00428837284569949, "percentage": 0.21, "elapsed_time": "0:03:46", "remaining_time": "1 day, 5:13:10"}
|
54 |
+
{"current_steps": 540, "total_steps": 247180, "loss": 0.2994, "lr": 2.184642770450684e-07, "epoch": 0.004369285540901368, "percentage": 0.22, "elapsed_time": "0:03:49", "remaining_time": "1 day, 5:10:00"}
|
55 |
+
{"current_steps": 550, "total_steps": 247180, "loss": 0.2922, "lr": 2.2250991180516228e-07, "epoch": 0.004450198236103244, "percentage": 0.22, "elapsed_time": "0:03:53", "remaining_time": "1 day, 5:03:28"}
|
56 |
+
{"current_steps": 560, "total_steps": 247180, "loss": 0.2611, "lr": 2.265555465652561e-07, "epoch": 0.004531110931305122, "percentage": 0.23, "elapsed_time": "0:03:56", "remaining_time": "1 day, 4:58:04"}
|
57 |
+
{"current_steps": 570, "total_steps": 247180, "loss": 0.2256, "lr": 2.3060118132534997e-07, "epoch": 0.004612023626506999, "percentage": 0.23, "elapsed_time": "0:04:00", "remaining_time": "1 day, 4:51:56"}
|
58 |
+
{"current_steps": 580, "total_steps": 247180, "loss": 0.2675, "lr": 2.346468160854438e-07, "epoch": 0.0046929363217088765, "percentage": 0.23, "elapsed_time": "0:04:04", "remaining_time": "1 day, 4:50:52"}
|
59 |
+
{"current_steps": 590, "total_steps": 247180, "loss": 0.238, "lr": 2.386924508455377e-07, "epoch": 0.004773849016910753, "percentage": 0.24, "elapsed_time": "0:04:08", "remaining_time": "1 day, 4:53:37"}
|
60 |
+
{"current_steps": 600, "total_steps": 247180, "loss": 0.1819, "lr": 2.427380856056315e-07, "epoch": 0.00485476171211263, "percentage": 0.24, "elapsed_time": "0:04:12", "remaining_time": "1 day, 4:47:06"}
|
61 |
+
{"current_steps": 610, "total_steps": 247180, "loss": 0.2621, "lr": 2.467837203657254e-07, "epoch": 0.004935674407314508, "percentage": 0.25, "elapsed_time": "0:04:15", "remaining_time": "1 day, 4:43:17"}
|
62 |
+
{"current_steps": 620, "total_steps": 247180, "loss": 0.2399, "lr": 2.508293551258193e-07, "epoch": 0.005016587102516385, "percentage": 0.25, "elapsed_time": "0:04:19", "remaining_time": "1 day, 4:40:36"}
|
63 |
+
{"current_steps": 630, "total_steps": 247180, "loss": 0.2172, "lr": 2.5487498988591313e-07, "epoch": 0.005097499797718262, "percentage": 0.25, "elapsed_time": "0:04:22", "remaining_time": "1 day, 4:32:38"}
|
64 |
+
{"current_steps": 640, "total_steps": 247180, "loss": 0.2224, "lr": 2.5892062464600697e-07, "epoch": 0.005178412492920139, "percentage": 0.26, "elapsed_time": "0:04:27", "remaining_time": "1 day, 4:34:20"}
|
65 |
+
{"current_steps": 650, "total_steps": 247180, "loss": 0.2253, "lr": 2.6296625940610085e-07, "epoch": 0.005259325188122017, "percentage": 0.26, "elapsed_time": "0:04:31", "remaining_time": "1 day, 4:35:57"}
|
66 |
+
{"current_steps": 660, "total_steps": 247180, "loss": 0.1957, "lr": 2.670118941661947e-07, "epoch": 0.0053402378833238935, "percentage": 0.27, "elapsed_time": "0:04:35", "remaining_time": "1 day, 4:33:10"}
|
67 |
+
{"current_steps": 670, "total_steps": 247180, "loss": 0.2124, "lr": 2.710575289262886e-07, "epoch": 0.00542115057852577, "percentage": 0.27, "elapsed_time": "0:04:38", "remaining_time": "1 day, 4:28:12"}
|
68 |
+
{"current_steps": 680, "total_steps": 247180, "loss": 0.1996, "lr": 2.751031636863824e-07, "epoch": 0.005502063273727648, "percentage": 0.28, "elapsed_time": "0:04:41", "remaining_time": "1 day, 4:21:24"}
|
69 |
+
{"current_steps": 690, "total_steps": 247180, "loss": 0.2853, "lr": 2.791487984464763e-07, "epoch": 0.005582975968929525, "percentage": 0.28, "elapsed_time": "0:04:46", "remaining_time": "1 day, 4:26:39"}
|
70 |
+
{"current_steps": 700, "total_steps": 247180, "loss": 0.2274, "lr": 2.8319443320657013e-07, "epoch": 0.005663888664131402, "percentage": 0.28, "elapsed_time": "0:04:50", "remaining_time": "1 day, 4:25:23"}
|
71 |
+
{"current_steps": 710, "total_steps": 247180, "loss": 0.2118, "lr": 2.8724006796666396e-07, "epoch": 0.005744801359333279, "percentage": 0.29, "elapsed_time": "0:04:54", "remaining_time": "1 day, 4:22:22"}
|
72 |
+
{"current_steps": 720, "total_steps": 247180, "loss": 0.2416, "lr": 2.9128570272675785e-07, "epoch": 0.005825714054535157, "percentage": 0.29, "elapsed_time": "0:04:58", "remaining_time": "1 day, 4:25:05"}
|
73 |
+
{"current_steps": 730, "total_steps": 247180, "loss": 0.2322, "lr": 2.9533133748685174e-07, "epoch": 0.005906626749737034, "percentage": 0.3, "elapsed_time": "0:05:03", "remaining_time": "1 day, 4:27:09"}
|
74 |
+
{"current_steps": 740, "total_steps": 247180, "loss": 0.1997, "lr": 2.9937697224694557e-07, "epoch": 0.005987539444938911, "percentage": 0.3, "elapsed_time": "0:05:07", "remaining_time": "1 day, 4:26:31"}
|
75 |
+
{"current_steps": 750, "total_steps": 247180, "loss": 0.1816, "lr": 3.0342260700703946e-07, "epoch": 0.006068452140140788, "percentage": 0.3, "elapsed_time": "0:05:11", "remaining_time": "1 day, 4:23:51"}
|
76 |
+
{"current_steps": 760, "total_steps": 247180, "loss": 0.2006, "lr": 3.074682417671333e-07, "epoch": 0.006149364835342665, "percentage": 0.31, "elapsed_time": "0:05:15", "remaining_time": "1 day, 4:23:22"}
|
77 |
+
{"current_steps": 770, "total_steps": 247180, "loss": 0.2258, "lr": 3.1151387652722713e-07, "epoch": 0.0062302775305445425, "percentage": 0.31, "elapsed_time": "0:05:19", "remaining_time": "1 day, 4:22:26"}
|
78 |
+
{"current_steps": 780, "total_steps": 247180, "loss": 0.1988, "lr": 3.15559511287321e-07, "epoch": 0.006311190225746419, "percentage": 0.32, "elapsed_time": "0:05:23", "remaining_time": "1 day, 4:22:37"}
|
79 |
+
{"current_steps": 790, "total_steps": 247180, "loss": 0.1856, "lr": 3.1960514604741485e-07, "epoch": 0.006392102920948297, "percentage": 0.32, "elapsed_time": "0:05:27", "remaining_time": "1 day, 4:20:10"}
|
80 |
+
{"current_steps": 800, "total_steps": 247180, "loss": 0.2152, "lr": 3.2365078080750874e-07, "epoch": 0.006473015616150174, "percentage": 0.32, "elapsed_time": "0:05:30", "remaining_time": "1 day, 4:17:31"}
|
81 |
+
{"current_steps": 810, "total_steps": 247180, "loss": 0.2085, "lr": 3.276964155676026e-07, "epoch": 0.0065539283113520514, "percentage": 0.33, "elapsed_time": "0:05:35", "remaining_time": "1 day, 4:21:06"}
|
82 |
+
{"current_steps": 820, "total_steps": 247180, "loss": 0.2256, "lr": 3.317420503276964e-07, "epoch": 0.006634841006553928, "percentage": 0.33, "elapsed_time": "0:05:39", "remaining_time": "1 day, 4:20:18"}
|
83 |
+
{"current_steps": 830, "total_steps": 247180, "loss": 0.2189, "lr": 3.357876850877903e-07, "epoch": 0.006715753701755806, "percentage": 0.34, "elapsed_time": "0:05:43", "remaining_time": "1 day, 4:20:16"}
|
84 |
+
{"current_steps": 840, "total_steps": 247180, "loss": 0.2038, "lr": 3.398333198478842e-07, "epoch": 0.006796666396957683, "percentage": 0.34, "elapsed_time": "0:05:47", "remaining_time": "1 day, 4:17:53"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb567ab5f0fee44ec7e6ca413288a773d7e62f09cd7d50d5d520ea23b789cadb
|
3 |
+
size 7352
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|