Training in progress, step 50
Browse files- .gitattributes +1 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- merges.txt +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- trainer_log.jsonl +50 -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
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"down_proj",
|
27 |
+
"v_proj",
|
28 |
+
"up_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8363e7299ff4add82c74a3161d837ba0601b176704b4b5e9571ff0035b0ede84
|
3 |
+
size 275342392
|
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 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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": 131072,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"padding_side": "right",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
+
"unk_token": null
|
208 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 1218, "loss": 0.6, "learning_rate": 3.0769230769230774e-05, "epoch": 0.0008205128205128205, "percentage": 0.08, "elapsed_time": "0:00:51", "remaining_time": "17:29:37"}
|
2 |
+
{"current_steps": 2, "total_steps": 1218, "loss": 0.6399, "learning_rate": 6.153846153846155e-05, "epoch": 0.001641025641025641, "percentage": 0.16, "elapsed_time": "0:01:28", "remaining_time": "14:56:44"}
|
3 |
+
{"current_steps": 3, "total_steps": 1218, "loss": 0.5966, "learning_rate": 9.230769230769232e-05, "epoch": 0.0024615384615384616, "percentage": 0.25, "elapsed_time": "0:02:07", "remaining_time": "14:20:36"}
|
4 |
+
{"current_steps": 4, "total_steps": 1218, "loss": 0.5884, "learning_rate": 0.0001230769230769231, "epoch": 0.003282051282051282, "percentage": 0.33, "elapsed_time": "0:02:46", "remaining_time": "14:00:08"}
|
5 |
+
{"current_steps": 5, "total_steps": 1218, "loss": 0.5449, "learning_rate": 0.00015384615384615385, "epoch": 0.0041025641025641026, "percentage": 0.41, "elapsed_time": "0:03:29", "remaining_time": "14:07:49"}
|
6 |
+
{"current_steps": 6, "total_steps": 1218, "loss": 0.509, "learning_rate": 0.00018461538461538463, "epoch": 0.004923076923076923, "percentage": 0.49, "elapsed_time": "0:04:06", "remaining_time": "13:49:11"}
|
7 |
+
{"current_steps": 7, "total_steps": 1218, "loss": 0.4909, "learning_rate": 0.0002153846153846154, "epoch": 0.005743589743589744, "percentage": 0.57, "elapsed_time": "0:04:46", "remaining_time": "13:45:30"}
|
8 |
+
{"current_steps": 8, "total_steps": 1218, "loss": 0.4851, "learning_rate": 0.0002461538461538462, "epoch": 0.006564102564102564, "percentage": 0.66, "elapsed_time": "0:05:28", "remaining_time": "13:48:58"}
|
9 |
+
{"current_steps": 9, "total_steps": 1218, "loss": 0.4744, "learning_rate": 0.00027692307692307695, "epoch": 0.0073846153846153844, "percentage": 0.74, "elapsed_time": "0:06:07", "remaining_time": "13:42:50"}
|
10 |
+
{"current_steps": 10, "total_steps": 1218, "loss": 0.4786, "learning_rate": 0.0003076923076923077, "epoch": 0.008205128205128205, "percentage": 0.82, "elapsed_time": "0:06:45", "remaining_time": "13:36:27"}
|
11 |
+
{"current_steps": 11, "total_steps": 1218, "loss": 0.5042, "learning_rate": 0.00033846153846153846, "epoch": 0.009025641025641025, "percentage": 0.9, "elapsed_time": "0:07:25", "remaining_time": "13:34:21"}
|
12 |
+
{"current_steps": 12, "total_steps": 1218, "loss": 0.4492, "learning_rate": 0.00036923076923076927, "epoch": 0.009846153846153846, "percentage": 0.99, "elapsed_time": "0:08:04", "remaining_time": "13:31:17"}
|
13 |
+
{"current_steps": 13, "total_steps": 1218, "loss": 0.4638, "learning_rate": 0.0004, "epoch": 0.010666666666666666, "percentage": 1.07, "elapsed_time": "0:08:41", "remaining_time": "13:25:48"}
|
14 |
+
{"current_steps": 14, "total_steps": 1218, "loss": 0.4555, "learning_rate": 0.0003999993202872671, "epoch": 0.011487179487179488, "percentage": 1.15, "elapsed_time": "0:09:20", "remaining_time": "13:23:47"}
|
15 |
+
{"current_steps": 15, "total_steps": 1218, "loss": 0.4237, "learning_rate": 0.0003999972811536883, "epoch": 0.012307692307692308, "percentage": 1.23, "elapsed_time": "0:10:03", "remaining_time": "13:27:11"}
|
16 |
+
{"current_steps": 16, "total_steps": 1218, "loss": 0.4276, "learning_rate": 0.00039999388261312393, "epoch": 0.013128205128205127, "percentage": 1.31, "elapsed_time": "0:10:43", "remaining_time": "13:25:50"}
|
17 |
+
{"current_steps": 17, "total_steps": 1218, "loss": 0.4508, "learning_rate": 0.0003999891246886744, "epoch": 0.013948717948717949, "percentage": 1.4, "elapsed_time": "0:11:20", "remaining_time": "13:21:17"}
|
18 |
+
{"current_steps": 18, "total_steps": 1218, "loss": 0.4323, "learning_rate": 0.00039998300741267976, "epoch": 0.014769230769230769, "percentage": 1.48, "elapsed_time": "0:12:09", "remaining_time": "13:30:15"}
|
19 |
+
{"current_steps": 19, "total_steps": 1218, "loss": 0.4279, "learning_rate": 0.00039997553082672004, "epoch": 0.01558974358974359, "percentage": 1.56, "elapsed_time": "0:12:48", "remaining_time": "13:28:39"}
|
20 |
+
{"current_steps": 20, "total_steps": 1218, "loss": 0.4276, "learning_rate": 0.00039996669498161444, "epoch": 0.01641025641025641, "percentage": 1.64, "elapsed_time": "0:13:26", "remaining_time": "13:25:19"}
|
21 |
+
{"current_steps": 21, "total_steps": 1218, "loss": 0.4275, "learning_rate": 0.0003999564999374214, "epoch": 0.01723076923076923, "percentage": 1.72, "elapsed_time": "0:14:03", "remaining_time": "13:21:12"}
|
22 |
+
{"current_steps": 22, "total_steps": 1218, "loss": 0.417, "learning_rate": 0.00039994494576343795, "epoch": 0.01805128205128205, "percentage": 1.81, "elapsed_time": "0:14:38", "remaining_time": "13:16:06"}
|
23 |
+
{"current_steps": 23, "total_steps": 1218, "loss": 0.4355, "learning_rate": 0.00039993203253819927, "epoch": 0.018871794871794873, "percentage": 1.89, "elapsed_time": "0:15:12", "remaining_time": "13:10:05"}
|
24 |
+
{"current_steps": 24, "total_steps": 1218, "loss": 0.4266, "learning_rate": 0.00039991776034947816, "epoch": 0.019692307692307693, "percentage": 1.97, "elapsed_time": "0:15:51", "remaining_time": "13:08:35"}
|
25 |
+
{"current_steps": 25, "total_steps": 1218, "loss": 0.4029, "learning_rate": 0.0003999021292942845, "epoch": 0.020512820512820513, "percentage": 2.05, "elapsed_time": "0:16:26", "remaining_time": "13:04:45"}
|
26 |
+
{"current_steps": 26, "total_steps": 1218, "loss": 0.4192, "learning_rate": 0.00039988513947886454, "epoch": 0.021333333333333333, "percentage": 2.13, "elapsed_time": "0:17:04", "remaining_time": "13:02:31"}
|
27 |
+
{"current_steps": 27, "total_steps": 1218, "loss": 0.4177, "learning_rate": 0.0003998667910187003, "epoch": 0.022153846153846152, "percentage": 2.22, "elapsed_time": "0:17:47", "remaining_time": "13:04:26"}
|
28 |
+
{"current_steps": 28, "total_steps": 1218, "loss": 0.4348, "learning_rate": 0.00039984708403850857, "epoch": 0.022974358974358976, "percentage": 2.3, "elapsed_time": "0:18:29", "remaining_time": "13:05:51"}
|
29 |
+
{"current_steps": 29, "total_steps": 1218, "loss": 0.418, "learning_rate": 0.0003998260186722401, "epoch": 0.023794871794871796, "percentage": 2.38, "elapsed_time": "0:19:08", "remaining_time": "13:04:48"}
|
30 |
+
{"current_steps": 30, "total_steps": 1218, "loss": 0.4053, "learning_rate": 0.0003998035950630791, "epoch": 0.024615384615384615, "percentage": 2.46, "elapsed_time": "0:19:44", "remaining_time": "13:01:27"}
|
31 |
+
{"current_steps": 31, "total_steps": 1218, "loss": 0.4155, "learning_rate": 0.00039977981336344155, "epoch": 0.025435897435897435, "percentage": 2.55, "elapsed_time": "0:20:20", "remaining_time": "12:59:04"}
|
32 |
+
{"current_steps": 32, "total_steps": 1218, "loss": 0.4202, "learning_rate": 0.0003997546737349746, "epoch": 0.026256410256410255, "percentage": 2.63, "elapsed_time": "0:21:03", "remaining_time": "13:00:33"}
|
33 |
+
{"current_steps": 33, "total_steps": 1218, "loss": 0.4081, "learning_rate": 0.0003997281763485556, "epoch": 0.02707692307692308, "percentage": 2.71, "elapsed_time": "0:21:39", "remaining_time": "12:57:50"}
|
34 |
+
{"current_steps": 34, "total_steps": 1218, "loss": 0.4442, "learning_rate": 0.0003997003213842907, "epoch": 0.027897435897435898, "percentage": 2.79, "elapsed_time": "0:22:12", "remaining_time": "12:53:36"}
|
35 |
+
{"current_steps": 35, "total_steps": 1218, "loss": 0.3976, "learning_rate": 0.0003996711090315136, "epoch": 0.028717948717948718, "percentage": 2.87, "elapsed_time": "0:22:54", "remaining_time": "12:54:06"}
|
36 |
+
{"current_steps": 36, "total_steps": 1218, "loss": 0.4337, "learning_rate": 0.00039964053948878447, "epoch": 0.029538461538461538, "percentage": 2.96, "elapsed_time": "0:23:35", "remaining_time": "12:54:35"}
|
37 |
+
{"current_steps": 37, "total_steps": 1218, "loss": 0.4038, "learning_rate": 0.0003996086129638882, "epoch": 0.030358974358974358, "percentage": 3.04, "elapsed_time": "0:24:18", "remaining_time": "12:55:46"}
|
38 |
+
{"current_steps": 38, "total_steps": 1218, "loss": 0.4219, "learning_rate": 0.00039957532967383353, "epoch": 0.03117948717948718, "percentage": 3.12, "elapsed_time": "0:24:53", "remaining_time": "12:52:50"}
|
39 |
+
{"current_steps": 39, "total_steps": 1218, "loss": 0.379, "learning_rate": 0.0003995406898448513, "epoch": 0.032, "percentage": 3.2, "elapsed_time": "0:25:28", "remaining_time": "12:49:54"}
|
40 |
+
{"current_steps": 40, "total_steps": 1218, "loss": 0.3993, "learning_rate": 0.0003995046937123927, "epoch": 0.03282051282051282, "percentage": 3.28, "elapsed_time": "0:26:03", "remaining_time": "12:47:38"}
|
41 |
+
{"current_steps": 41, "total_steps": 1218, "loss": 0.4252, "learning_rate": 0.00039946734152112814, "epoch": 0.03364102564102564, "percentage": 3.37, "elapsed_time": "0:26:33", "remaining_time": "12:42:27"}
|
42 |
+
{"current_steps": 42, "total_steps": 1218, "loss": 0.4045, "learning_rate": 0.0003994286335249452, "epoch": 0.03446153846153846, "percentage": 3.45, "elapsed_time": "0:27:11", "remaining_time": "12:41:12"}
|
43 |
+
{"current_steps": 43, "total_steps": 1218, "loss": 0.4187, "learning_rate": 0.000399388569986947, "epoch": 0.03528205128205128, "percentage": 3.53, "elapsed_time": "0:27:53", "remaining_time": "12:41:58"}
|
44 |
+
{"current_steps": 44, "total_steps": 1218, "loss": 0.4023, "learning_rate": 0.0003993471511794505, "epoch": 0.0361025641025641, "percentage": 3.61, "elapsed_time": "0:28:30", "remaining_time": "12:40:27"}
|
45 |
+
{"current_steps": 45, "total_steps": 1218, "loss": 0.3831, "learning_rate": 0.0003993043773839847, "epoch": 0.036923076923076927, "percentage": 3.69, "elapsed_time": "0:29:04", "remaining_time": "12:37:46"}
|
46 |
+
{"current_steps": 46, "total_steps": 1218, "loss": 0.3777, "learning_rate": 0.0003992602488912885, "epoch": 0.037743589743589746, "percentage": 3.78, "elapsed_time": "0:29:44", "remaining_time": "12:37:57"}
|
47 |
+
{"current_steps": 47, "total_steps": 1218, "loss": 0.4055, "learning_rate": 0.00039921476600130883, "epoch": 0.038564102564102566, "percentage": 3.86, "elapsed_time": "0:30:25", "remaining_time": "12:38:03"}
|
48 |
+
{"current_steps": 48, "total_steps": 1218, "loss": 0.4221, "learning_rate": 0.0003991679290231987, "epoch": 0.039384615384615386, "percentage": 3.94, "elapsed_time": "0:31:03", "remaining_time": "12:37:14"}
|
49 |
+
{"current_steps": 49, "total_steps": 1218, "loss": 0.3974, "learning_rate": 0.00039911973827531515, "epoch": 0.040205128205128206, "percentage": 4.02, "elapsed_time": "0:31:43", "remaining_time": "12:36:50"}
|
50 |
+
{"current_steps": 50, "total_steps": 1218, "loss": 0.4075, "learning_rate": 0.00039907019408521666, "epoch": 0.041025641025641026, "percentage": 4.11, "elapsed_time": "0:32:18", "remaining_time": "12:34:47"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e5275859a968a431da333d20d3230e8bcdd34ff84040401bb3857b6c764899d
|
3 |
+
size 7096
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|