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 +76 -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:f7fa7bef5d1bd24bc2ed287d24912554726be11d0ed33b62e5f481a0dd71d5f9
|
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 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 10, "total_steps": 236854, "loss": 0.5909, "lr": 4.2219032339778774e-09, "epoch": 8.443984716387663e-05, "percentage": 0.0, "elapsed_time": "0:00:06", "remaining_time": "1 day, 19:06:13"}
|
2 |
+
{"current_steps": 20, "total_steps": 236854, "loss": 0.5496, "lr": 8.443806467955755e-09, "epoch": 0.00016887969432775326, "percentage": 0.01, "elapsed_time": "0:00:14", "remaining_time": "1 day, 22:07:04"}
|
3 |
+
{"current_steps": 30, "total_steps": 236854, "loss": 0.5506, "lr": 1.2665709701933633e-08, "epoch": 0.0002533195414916299, "percentage": 0.01, "elapsed_time": "0:00:20", "remaining_time": "1 day, 20:18:56"}
|
4 |
+
{"current_steps": 40, "total_steps": 236854, "loss": 0.5882, "lr": 1.688761293591151e-08, "epoch": 0.0003377593886555065, "percentage": 0.02, "elapsed_time": "0:00:25", "remaining_time": "1 day, 18:37:36"}
|
5 |
+
{"current_steps": 50, "total_steps": 236854, "loss": 0.5887, "lr": 2.1109516169889388e-08, "epoch": 0.0004221992358193832, "percentage": 0.02, "elapsed_time": "0:00:32", "remaining_time": "1 day, 18:10:27"}
|
6 |
+
{"current_steps": 60, "total_steps": 236854, "loss": 0.6052, "lr": 2.5331419403867266e-08, "epoch": 0.0005066390829832598, "percentage": 0.03, "elapsed_time": "0:00:37", "remaining_time": "1 day, 17:12:27"}
|
7 |
+
{"current_steps": 70, "total_steps": 236854, "loss": 0.6097, "lr": 2.955332263784514e-08, "epoch": 0.0005910789301471365, "percentage": 0.03, "elapsed_time": "0:00:42", "remaining_time": "1 day, 16:18:30"}
|
8 |
+
{"current_steps": 80, "total_steps": 236854, "loss": 0.5666, "lr": 3.377522587182302e-08, "epoch": 0.000675518777311013, "percentage": 0.03, "elapsed_time": "0:00:49", "remaining_time": "1 day, 16:27:41"}
|
9 |
+
{"current_steps": 90, "total_steps": 236854, "loss": 0.5969, "lr": 3.79971291058009e-08, "epoch": 0.0007599586244748897, "percentage": 0.04, "elapsed_time": "0:00:55", "remaining_time": "1 day, 16:45:48"}
|
10 |
+
{"current_steps": 100, "total_steps": 236854, "loss": 0.5078, "lr": 4.2219032339778776e-08, "epoch": 0.0008443984716387663, "percentage": 0.04, "elapsed_time": "0:01:03", "remaining_time": "1 day, 17:29:16"}
|
11 |
+
{"current_steps": 110, "total_steps": 236854, "loss": 0.5559, "lr": 4.6440935573756654e-08, "epoch": 0.000928838318802643, "percentage": 0.05, "elapsed_time": "0:01:10", "remaining_time": "1 day, 17:54:13"}
|
12 |
+
{"current_steps": 120, "total_steps": 236854, "loss": 0.5491, "lr": 5.066283880773453e-08, "epoch": 0.0010132781659665197, "percentage": 0.05, "elapsed_time": "0:01:16", "remaining_time": "1 day, 17:55:51"}
|
13 |
+
{"current_steps": 130, "total_steps": 236854, "loss": 0.5759, "lr": 5.488474204171241e-08, "epoch": 0.0010977180131303962, "percentage": 0.05, "elapsed_time": "0:01:22", "remaining_time": "1 day, 17:48:53"}
|
14 |
+
{"current_steps": 140, "total_steps": 236854, "loss": 0.5362, "lr": 5.910664527569028e-08, "epoch": 0.001182157860294273, "percentage": 0.06, "elapsed_time": "0:01:29", "remaining_time": "1 day, 18:10:32"}
|
15 |
+
{"current_steps": 150, "total_steps": 236854, "loss": 0.5264, "lr": 6.332854850966817e-08, "epoch": 0.0012665977074581495, "percentage": 0.06, "elapsed_time": "0:01:36", "remaining_time": "1 day, 18:15:59"}
|
16 |
+
{"current_steps": 160, "total_steps": 236854, "loss": 0.5267, "lr": 6.755045174364604e-08, "epoch": 0.001351037554622026, "percentage": 0.07, "elapsed_time": "0:01:45", "remaining_time": "1 day, 19:19:19"}
|
17 |
+
{"current_steps": 170, "total_steps": 236854, "loss": 0.5315, "lr": 7.177235497762391e-08, "epoch": 0.0014354774017859028, "percentage": 0.07, "elapsed_time": "0:01:51", "remaining_time": "1 day, 19:07:22"}
|
18 |
+
{"current_steps": 180, "total_steps": 236854, "loss": 0.4901, "lr": 7.59942582116018e-08, "epoch": 0.0015199172489497794, "percentage": 0.08, "elapsed_time": "0:01:58", "remaining_time": "1 day, 19:15:06"}
|
19 |
+
{"current_steps": 190, "total_steps": 236854, "loss": 0.5173, "lr": 8.021616144557968e-08, "epoch": 0.001604357096113656, "percentage": 0.08, "elapsed_time": "0:02:04", "remaining_time": "1 day, 19:07:35"}
|
20 |
+
{"current_steps": 200, "total_steps": 236854, "loss": 0.5346, "lr": 8.443806467955755e-08, "epoch": 0.0016887969432775327, "percentage": 0.08, "elapsed_time": "0:02:10", "remaining_time": "1 day, 19:02:24"}
|
21 |
+
{"current_steps": 210, "total_steps": 236854, "loss": 0.4454, "lr": 8.865996791353544e-08, "epoch": 0.0017732367904414092, "percentage": 0.09, "elapsed_time": "0:02:18", "remaining_time": "1 day, 19:15:42"}
|
22 |
+
{"current_steps": 220, "total_steps": 236854, "loss": 0.4284, "lr": 9.288187114751331e-08, "epoch": 0.001857676637605286, "percentage": 0.09, "elapsed_time": "0:02:25", "remaining_time": "1 day, 19:25:41"}
|
23 |
+
{"current_steps": 230, "total_steps": 236854, "loss": 0.4221, "lr": 9.710377438149118e-08, "epoch": 0.0019421164847691626, "percentage": 0.1, "elapsed_time": "0:02:32", "remaining_time": "1 day, 19:36:19"}
|
24 |
+
{"current_steps": 240, "total_steps": 236854, "loss": 0.4477, "lr": 1.0132567761546906e-07, "epoch": 0.0020265563319330393, "percentage": 0.1, "elapsed_time": "0:02:39", "remaining_time": "1 day, 19:42:42"}
|
25 |
+
{"current_steps": 250, "total_steps": 236854, "loss": 0.3981, "lr": 1.0554758084944694e-07, "epoch": 0.0021109961790969156, "percentage": 0.11, "elapsed_time": "0:02:46", "remaining_time": "1 day, 19:42:45"}
|
26 |
+
{"current_steps": 260, "total_steps": 236854, "loss": 0.3956, "lr": 1.0976948408342482e-07, "epoch": 0.0021954360262607924, "percentage": 0.11, "elapsed_time": "0:02:53", "remaining_time": "1 day, 19:46:40"}
|
27 |
+
{"current_steps": 270, "total_steps": 236854, "loss": 0.3685, "lr": 1.1399138731740269e-07, "epoch": 0.002279875873424669, "percentage": 0.11, "elapsed_time": "0:02:59", "remaining_time": "1 day, 19:45:51"}
|
28 |
+
{"current_steps": 280, "total_steps": 236854, "loss": 0.3667, "lr": 1.1821329055138056e-07, "epoch": 0.002364315720588546, "percentage": 0.12, "elapsed_time": "0:03:06", "remaining_time": "1 day, 19:45:48"}
|
29 |
+
{"current_steps": 290, "total_steps": 236854, "loss": 0.3347, "lr": 1.2243519378535845e-07, "epoch": 0.0024487555677524223, "percentage": 0.12, "elapsed_time": "0:03:12", "remaining_time": "1 day, 19:38:21"}
|
30 |
+
{"current_steps": 300, "total_steps": 236854, "loss": 0.3104, "lr": 1.2665709701933633e-07, "epoch": 0.002533195414916299, "percentage": 0.13, "elapsed_time": "0:03:19", "remaining_time": "1 day, 19:44:24"}
|
31 |
+
{"current_steps": 310, "total_steps": 236854, "loss": 0.2668, "lr": 1.308790002533142e-07, "epoch": 0.002617635262080176, "percentage": 0.13, "elapsed_time": "0:03:25", "remaining_time": "1 day, 19:32:47"}
|
32 |
+
{"current_steps": 320, "total_steps": 236854, "loss": 0.2897, "lr": 1.3510090348729208e-07, "epoch": 0.002702075109244052, "percentage": 0.14, "elapsed_time": "0:03:31", "remaining_time": "1 day, 19:30:36"}
|
33 |
+
{"current_steps": 330, "total_steps": 236854, "loss": 0.2712, "lr": 1.3932280672126996e-07, "epoch": 0.002786514956407929, "percentage": 0.14, "elapsed_time": "0:03:37", "remaining_time": "1 day, 19:19:15"}
|
34 |
+
{"current_steps": 340, "total_steps": 236854, "loss": 0.2464, "lr": 1.4354470995524782e-07, "epoch": 0.0028709548035718057, "percentage": 0.14, "elapsed_time": "0:03:44", "remaining_time": "1 day, 19:20:17"}
|
35 |
+
{"current_steps": 350, "total_steps": 236854, "loss": 0.2543, "lr": 1.477666131892257e-07, "epoch": 0.002955394650735682, "percentage": 0.15, "elapsed_time": "0:03:51", "remaining_time": "1 day, 19:31:48"}
|
36 |
+
{"current_steps": 360, "total_steps": 236854, "loss": 0.207, "lr": 1.519885164232036e-07, "epoch": 0.0030398344978995588, "percentage": 0.15, "elapsed_time": "0:03:58", "remaining_time": "1 day, 19:31:49"}
|
37 |
+
{"current_steps": 370, "total_steps": 236854, "loss": 0.1999, "lr": 1.5621041965718148e-07, "epoch": 0.0031242743450634355, "percentage": 0.16, "elapsed_time": "0:04:04", "remaining_time": "1 day, 19:27:38"}
|
38 |
+
{"current_steps": 380, "total_steps": 236854, "loss": 0.1877, "lr": 1.6043232289115936e-07, "epoch": 0.003208714192227312, "percentage": 0.16, "elapsed_time": "0:04:10", "remaining_time": "1 day, 19:18:12"}
|
39 |
+
{"current_steps": 390, "total_steps": 236854, "loss": 0.2076, "lr": 1.6465422612513722e-07, "epoch": 0.0032931540393911886, "percentage": 0.16, "elapsed_time": "0:04:16", "remaining_time": "1 day, 19:16:33"}
|
40 |
+
{"current_steps": 400, "total_steps": 236854, "loss": 0.1771, "lr": 1.688761293591151e-07, "epoch": 0.0033775938865550654, "percentage": 0.17, "elapsed_time": "0:04:23", "remaining_time": "1 day, 19:14:26"}
|
41 |
+
{"current_steps": 410, "total_steps": 236854, "loss": 0.188, "lr": 1.73098032593093e-07, "epoch": 0.003462033733718942, "percentage": 0.17, "elapsed_time": "0:04:29", "remaining_time": "1 day, 19:10:05"}
|
42 |
+
{"current_steps": 420, "total_steps": 236854, "loss": 0.1816, "lr": 1.7731993582707087e-07, "epoch": 0.0035464735808828185, "percentage": 0.18, "elapsed_time": "0:04:35", "remaining_time": "1 day, 19:09:04"}
|
43 |
+
{"current_steps": 430, "total_steps": 236854, "loss": 0.1556, "lr": 1.8154183906104873e-07, "epoch": 0.0036309134280466952, "percentage": 0.18, "elapsed_time": "0:04:41", "remaining_time": "1 day, 19:03:20"}
|
44 |
+
{"current_steps": 440, "total_steps": 236854, "loss": 0.164, "lr": 1.8576374229502662e-07, "epoch": 0.003715353275210572, "percentage": 0.19, "elapsed_time": "0:04:48", "remaining_time": "1 day, 19:03:00"}
|
45 |
+
{"current_steps": 450, "total_steps": 236854, "loss": 0.1647, "lr": 1.8998564552900448e-07, "epoch": 0.0037997931223744483, "percentage": 0.19, "elapsed_time": "0:04:55", "remaining_time": "1 day, 19:04:55"}
|
46 |
+
{"current_steps": 460, "total_steps": 236854, "loss": 0.1419, "lr": 1.9420754876298236e-07, "epoch": 0.003884232969538325, "percentage": 0.19, "elapsed_time": "0:05:01", "remaining_time": "1 day, 19:02:18"}
|
47 |
+
{"current_steps": 470, "total_steps": 236854, "loss": 0.1446, "lr": 1.9842945199696027e-07, "epoch": 0.003968672816702202, "percentage": 0.2, "elapsed_time": "0:05:08", "remaining_time": "1 day, 19:02:03"}
|
48 |
+
{"current_steps": 480, "total_steps": 236854, "loss": 0.1573, "lr": 2.0265135523093813e-07, "epoch": 0.004053112663866079, "percentage": 0.2, "elapsed_time": "0:05:15", "remaining_time": "1 day, 19:07:57"}
|
49 |
+
{"current_steps": 490, "total_steps": 236854, "loss": 0.1432, "lr": 2.0687325846491601e-07, "epoch": 0.004137552511029955, "percentage": 0.21, "elapsed_time": "0:05:22", "remaining_time": "1 day, 19:09:50"}
|
50 |
+
{"current_steps": 500, "total_steps": 236854, "loss": 0.1262, "lr": 2.1109516169889387e-07, "epoch": 0.004221992358193831, "percentage": 0.21, "elapsed_time": "0:05:28", "remaining_time": "1 day, 19:10:42"}
|
51 |
+
{"current_steps": 510, "total_steps": 236854, "loss": 0.125, "lr": 2.1531706493287173e-07, "epoch": 0.004306432205357708, "percentage": 0.22, "elapsed_time": "0:05:53", "remaining_time": "1 day, 21:32:18"}
|
52 |
+
{"current_steps": 520, "total_steps": 236854, "loss": 0.1202, "lr": 2.1953896816684964e-07, "epoch": 0.004390872052521585, "percentage": 0.22, "elapsed_time": "0:06:00", "remaining_time": "1 day, 21:33:45"}
|
53 |
+
{"current_steps": 530, "total_steps": 236854, "loss": 0.1248, "lr": 2.2376087140082753e-07, "epoch": 0.004475311899685462, "percentage": 0.22, "elapsed_time": "0:06:07", "remaining_time": "1 day, 21:31:50"}
|
54 |
+
{"current_steps": 540, "total_steps": 236854, "loss": 0.0968, "lr": 2.2798277463480539e-07, "epoch": 0.004559751746849338, "percentage": 0.23, "elapsed_time": "0:06:13", "remaining_time": "1 day, 21:25:45"}
|
55 |
+
{"current_steps": 550, "total_steps": 236854, "loss": 0.1388, "lr": 2.3220467786878327e-07, "epoch": 0.004644191594013215, "percentage": 0.23, "elapsed_time": "0:06:20", "remaining_time": "1 day, 21:25:58"}
|
56 |
+
{"current_steps": 560, "total_steps": 236854, "loss": 0.1081, "lr": 2.3642658110276113e-07, "epoch": 0.004728631441177092, "percentage": 0.24, "elapsed_time": "0:06:26", "remaining_time": "1 day, 21:17:20"}
|
57 |
+
{"current_steps": 570, "total_steps": 236854, "loss": 0.1326, "lr": 2.40648484336739e-07, "epoch": 0.004813071288340968, "percentage": 0.24, "elapsed_time": "0:06:33", "remaining_time": "1 day, 21:16:08"}
|
58 |
+
{"current_steps": 580, "total_steps": 236854, "loss": 0.1271, "lr": 2.448703875707169e-07, "epoch": 0.0048975111355048445, "percentage": 0.24, "elapsed_time": "0:06:40", "remaining_time": "1 day, 21:17:07"}
|
59 |
+
{"current_steps": 590, "total_steps": 236854, "loss": 0.1278, "lr": 2.4909229080469476e-07, "epoch": 0.004981950982668721, "percentage": 0.25, "elapsed_time": "0:06:47", "remaining_time": "1 day, 21:17:16"}
|
60 |
+
{"current_steps": 600, "total_steps": 236854, "loss": 0.1177, "lr": 2.5331419403867267e-07, "epoch": 0.005066390829832598, "percentage": 0.25, "elapsed_time": "0:06:53", "remaining_time": "1 day, 21:14:52"}
|
61 |
+
{"current_steps": 610, "total_steps": 236854, "loss": 0.1503, "lr": 2.5753609727265053e-07, "epoch": 0.005150830676996475, "percentage": 0.26, "elapsed_time": "0:07:01", "remaining_time": "1 day, 21:19:45"}
|
62 |
+
{"current_steps": 620, "total_steps": 236854, "loss": 0.1224, "lr": 2.617580005066284e-07, "epoch": 0.005235270524160352, "percentage": 0.26, "elapsed_time": "0:07:08", "remaining_time": "1 day, 21:23:05"}
|
63 |
+
{"current_steps": 630, "total_steps": 236854, "loss": 0.1046, "lr": 2.659799037406063e-07, "epoch": 0.0053197103713242275, "percentage": 0.27, "elapsed_time": "0:07:15", "remaining_time": "1 day, 21:21:46"}
|
64 |
+
{"current_steps": 640, "total_steps": 236854, "loss": 0.1256, "lr": 2.7020180697458416e-07, "epoch": 0.005404150218488104, "percentage": 0.27, "elapsed_time": "0:07:22", "remaining_time": "1 day, 21:22:34"}
|
65 |
+
{"current_steps": 650, "total_steps": 236854, "loss": 0.1098, "lr": 2.7442371020856207e-07, "epoch": 0.005488590065651981, "percentage": 0.27, "elapsed_time": "0:07:28", "remaining_time": "1 day, 21:16:44"}
|
66 |
+
{"current_steps": 660, "total_steps": 236854, "loss": 0.1057, "lr": 2.786456134425399e-07, "epoch": 0.005573029912815858, "percentage": 0.28, "elapsed_time": "0:07:34", "remaining_time": "1 day, 21:11:32"}
|
67 |
+
{"current_steps": 670, "total_steps": 236854, "loss": 0.1282, "lr": 2.828675166765178e-07, "epoch": 0.0056574697599797346, "percentage": 0.28, "elapsed_time": "0:07:41", "remaining_time": "1 day, 21:13:24"}
|
68 |
+
{"current_steps": 680, "total_steps": 236854, "loss": 0.0993, "lr": 2.8708941991049564e-07, "epoch": 0.005741909607143611, "percentage": 0.29, "elapsed_time": "0:07:48", "remaining_time": "1 day, 21:14:23"}
|
69 |
+
{"current_steps": 690, "total_steps": 236854, "loss": 0.1217, "lr": 2.9131132314447355e-07, "epoch": 0.005826349454307488, "percentage": 0.29, "elapsed_time": "0:07:57", "remaining_time": "1 day, 21:24:18"}
|
70 |
+
{"current_steps": 700, "total_steps": 236854, "loss": 0.0987, "lr": 2.955332263784514e-07, "epoch": 0.005910789301471364, "percentage": 0.3, "elapsed_time": "0:08:04", "remaining_time": "1 day, 21:22:50"}
|
71 |
+
{"current_steps": 710, "total_steps": 236854, "loss": 0.0726, "lr": 2.997551296124293e-07, "epoch": 0.005995229148635241, "percentage": 0.3, "elapsed_time": "0:08:11", "remaining_time": "1 day, 21:23:17"}
|
72 |
+
{"current_steps": 720, "total_steps": 236854, "loss": 0.1077, "lr": 3.039770328464072e-07, "epoch": 0.0060796689957991175, "percentage": 0.3, "elapsed_time": "0:08:17", "remaining_time": "1 day, 21:20:40"}
|
73 |
+
{"current_steps": 730, "total_steps": 236854, "loss": 0.1106, "lr": 3.0819893608038504e-07, "epoch": 0.006164108842962994, "percentage": 0.31, "elapsed_time": "0:08:24", "remaining_time": "1 day, 21:21:16"}
|
74 |
+
{"current_steps": 740, "total_steps": 236854, "loss": 0.1017, "lr": 3.1242083931436295e-07, "epoch": 0.006248548690126871, "percentage": 0.31, "elapsed_time": "0:08:30", "remaining_time": "1 day, 21:17:03"}
|
75 |
+
{"current_steps": 750, "total_steps": 236854, "loss": 0.0935, "lr": 3.166427425483408e-07, "epoch": 0.006332988537290748, "percentage": 0.32, "elapsed_time": "0:08:37", "remaining_time": "1 day, 21:15:02"}
|
76 |
+
{"current_steps": 760, "total_steps": 236854, "loss": 0.0849, "lr": 3.208646457823187e-07, "epoch": 0.006417428384454624, "percentage": 0.32, "elapsed_time": "0:08:43", "remaining_time": "1 day, 21:10:37"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7acb7263827a0e5408139ebbe72118dfb7517e8929fa2b148ba67ce311c9957e
|
3 |
+
size 7352
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|