ahmedheakl commited on
Commit
6f36ed6
·
verified ·
1 Parent(s): 8bfb32f

Training in progress, step 1000

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 sha256:51cfdda82d8d1e845a75ca9485008b0bb4a271a190e260ccd42ba728212ed862
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 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 35758, "loss": 0.5416, "lr": 2.7964205816554813e-08, "epoch": 0.0005592997567046058, "percentage": 0.03, "elapsed_time": "0:00:35", "remaining_time": "1 day, 11:24:51"}
2
+ {"current_steps": 20, "total_steps": 35758, "loss": 0.548, "lr": 5.5928411633109626e-08, "epoch": 0.0011185995134092117, "percentage": 0.06, "elapsed_time": "0:01:08", "remaining_time": "1 day, 9:58:53"}
3
+ {"current_steps": 30, "total_steps": 35758, "loss": 0.5323, "lr": 8.389261744966444e-08, "epoch": 0.0016778992701138174, "percentage": 0.08, "elapsed_time": "0:01:44", "remaining_time": "1 day, 10:43:00"}
4
+ {"current_steps": 40, "total_steps": 35758, "loss": 0.5427, "lr": 1.1185682326621925e-07, "epoch": 0.0022371990268184234, "percentage": 0.11, "elapsed_time": "0:02:19", "remaining_time": "1 day, 10:36:24"}
5
+ {"current_steps": 50, "total_steps": 35758, "loss": 0.5325, "lr": 1.3982102908277406e-07, "epoch": 0.002796498783523029, "percentage": 0.14, "elapsed_time": "0:02:56", "remaining_time": "1 day, 10:57:38"}
6
+ {"current_steps": 60, "total_steps": 35758, "loss": 0.5161, "lr": 1.6778523489932889e-07, "epoch": 0.003355798540227635, "percentage": 0.17, "elapsed_time": "0:03:35", "remaining_time": "1 day, 11:38:22"}
7
+ {"current_steps": 70, "total_steps": 35758, "loss": 0.4893, "lr": 1.9574944071588368e-07, "epoch": 0.003915098296932241, "percentage": 0.2, "elapsed_time": "0:04:11", "remaining_time": "1 day, 11:38:38"}
8
+ {"current_steps": 80, "total_steps": 35758, "loss": 0.4752, "lr": 2.237136465324385e-07, "epoch": 0.004474398053636847, "percentage": 0.22, "elapsed_time": "0:04:47", "remaining_time": "1 day, 11:33:26"}
9
+ {"current_steps": 90, "total_steps": 35758, "loss": 0.4121, "lr": 2.516778523489933e-07, "epoch": 0.005033697810341452, "percentage": 0.25, "elapsed_time": "0:05:22", "remaining_time": "1 day, 11:29:12"}
10
+ {"current_steps": 100, "total_steps": 35758, "loss": 0.3797, "lr": 2.796420581655481e-07, "epoch": 0.005592997567046058, "percentage": 0.28, "elapsed_time": "0:05:59", "remaining_time": "1 day, 11:35:09"}
11
+ {"current_steps": 110, "total_steps": 35758, "loss": 0.3043, "lr": 3.076062639821029e-07, "epoch": 0.0061522973237506644, "percentage": 0.31, "elapsed_time": "0:06:34", "remaining_time": "1 day, 11:32:58"}
12
+ {"current_steps": 120, "total_steps": 35758, "loss": 0.2565, "lr": 3.3557046979865777e-07, "epoch": 0.00671159708045527, "percentage": 0.34, "elapsed_time": "0:07:07", "remaining_time": "1 day, 11:18:06"}
13
+ {"current_steps": 130, "total_steps": 35758, "loss": 0.2345, "lr": 3.6353467561521257e-07, "epoch": 0.007270896837159876, "percentage": 0.36, "elapsed_time": "0:07:48", "remaining_time": "1 day, 11:37:41"}
14
+ {"current_steps": 140, "total_steps": 35758, "loss": 0.1944, "lr": 3.9149888143176736e-07, "epoch": 0.007830196593864481, "percentage": 0.39, "elapsed_time": "0:08:23", "remaining_time": "1 day, 11:34:33"}
15
+ {"current_steps": 150, "total_steps": 35758, "loss": 0.1577, "lr": 4.194630872483222e-07, "epoch": 0.008389496350569087, "percentage": 0.42, "elapsed_time": "0:08:57", "remaining_time": "1 day, 11:26:26"}
16
+ {"current_steps": 160, "total_steps": 35758, "loss": 0.1498, "lr": 4.47427293064877e-07, "epoch": 0.008948796107273694, "percentage": 0.45, "elapsed_time": "0:09:35", "remaining_time": "1 day, 11:35:23"}
17
+ {"current_steps": 170, "total_steps": 35758, "loss": 0.1354, "lr": 4.7539149888143186e-07, "epoch": 0.0095080958639783, "percentage": 0.48, "elapsed_time": "0:10:12", "remaining_time": "1 day, 11:37:25"}
18
+ {"current_steps": 180, "total_steps": 35758, "loss": 0.1286, "lr": 5.033557046979866e-07, "epoch": 0.010067395620682904, "percentage": 0.5, "elapsed_time": "0:10:48", "remaining_time": "1 day, 11:35:55"}
19
+ {"current_steps": 190, "total_steps": 35758, "loss": 0.1168, "lr": 5.313199105145414e-07, "epoch": 0.01062669537738751, "percentage": 0.53, "elapsed_time": "0:11:23", "remaining_time": "1 day, 11:32:19"}
20
+ {"current_steps": 200, "total_steps": 35758, "loss": 0.1219, "lr": 5.592841163310962e-07, "epoch": 0.011185995134092117, "percentage": 0.56, "elapsed_time": "0:11:56", "remaining_time": "1 day, 11:22:39"}
21
+ {"current_steps": 210, "total_steps": 35758, "loss": 0.1059, "lr": 5.87248322147651e-07, "epoch": 0.011745294890796723, "percentage": 0.59, "elapsed_time": "0:12:28", "remaining_time": "1 day, 11:12:54"}
22
+ {"current_steps": 220, "total_steps": 35758, "loss": 0.1056, "lr": 6.152125279642058e-07, "epoch": 0.012304594647501329, "percentage": 0.62, "elapsed_time": "0:13:07", "remaining_time": "1 day, 11:20:35"}
23
+ {"current_steps": 230, "total_steps": 35758, "loss": 0.0966, "lr": 6.431767337807607e-07, "epoch": 0.012863894404205933, "percentage": 0.64, "elapsed_time": "0:13:44", "remaining_time": "1 day, 11:23:43"}
24
+ {"current_steps": 240, "total_steps": 35758, "loss": 0.0896, "lr": 6.711409395973155e-07, "epoch": 0.01342319416091054, "percentage": 0.67, "elapsed_time": "0:14:20", "remaining_time": "1 day, 11:22:31"}
25
+ {"current_steps": 250, "total_steps": 35758, "loss": 0.0932, "lr": 6.991051454138703e-07, "epoch": 0.013982493917615146, "percentage": 0.7, "elapsed_time": "0:14:54", "remaining_time": "1 day, 11:16:31"}
26
+ {"current_steps": 260, "total_steps": 35758, "loss": 0.0832, "lr": 7.270693512304251e-07, "epoch": 0.014541793674319752, "percentage": 0.73, "elapsed_time": "0:15:30", "remaining_time": "1 day, 11:16:54"}
27
+ {"current_steps": 270, "total_steps": 35758, "loss": 0.0837, "lr": 7.5503355704698e-07, "epoch": 0.015101093431024358, "percentage": 0.76, "elapsed_time": "0:16:03", "remaining_time": "1 day, 11:11:41"}
28
+ {"current_steps": 280, "total_steps": 35758, "loss": 0.0818, "lr": 7.829977628635347e-07, "epoch": 0.015660393187728962, "percentage": 0.78, "elapsed_time": "0:16:38", "remaining_time": "1 day, 11:09:07"}
29
+ {"current_steps": 290, "total_steps": 35758, "loss": 0.0791, "lr": 8.109619686800896e-07, "epoch": 0.01621969294443357, "percentage": 0.81, "elapsed_time": "0:17:16", "remaining_time": "1 day, 11:13:33"}
30
+ {"current_steps": 300, "total_steps": 35758, "loss": 0.0782, "lr": 8.389261744966444e-07, "epoch": 0.016778992701138175, "percentage": 0.84, "elapsed_time": "0:17:53", "remaining_time": "1 day, 11:14:07"}
31
+ {"current_steps": 310, "total_steps": 35758, "loss": 0.0764, "lr": 8.668903803131992e-07, "epoch": 0.01733829245784278, "percentage": 0.87, "elapsed_time": "0:18:28", "remaining_time": "1 day, 11:12:45"}
32
+ {"current_steps": 320, "total_steps": 35758, "loss": 0.0731, "lr": 8.94854586129754e-07, "epoch": 0.017897592214547387, "percentage": 0.89, "elapsed_time": "0:19:06", "remaining_time": "1 day, 11:15:42"}
33
+ {"current_steps": 330, "total_steps": 35758, "loss": 0.0738, "lr": 9.228187919463089e-07, "epoch": 0.01845689197125199, "percentage": 0.92, "elapsed_time": "0:19:42", "remaining_time": "1 day, 11:16:18"}
34
+ {"current_steps": 340, "total_steps": 35758, "loss": 0.0715, "lr": 9.507829977628637e-07, "epoch": 0.0190161917279566, "percentage": 0.95, "elapsed_time": "0:20:17", "remaining_time": "1 day, 11:13:28"}
35
+ {"current_steps": 350, "total_steps": 35758, "loss": 0.071, "lr": 9.787472035794185e-07, "epoch": 0.019575491484661204, "percentage": 0.98, "elapsed_time": "0:20:54", "remaining_time": "1 day, 11:14:33"}
36
+ {"current_steps": 360, "total_steps": 35758, "loss": 0.0728, "lr": 1.006711409395973e-06, "epoch": 0.02013479124136581, "percentage": 1.01, "elapsed_time": "0:21:33", "remaining_time": "1 day, 11:20:24"}
37
+ {"current_steps": 370, "total_steps": 35758, "loss": 0.0645, "lr": 1.034675615212528e-06, "epoch": 0.020694090998070416, "percentage": 1.03, "elapsed_time": "0:22:05", "remaining_time": "1 day, 11:13:08"}
38
+ {"current_steps": 380, "total_steps": 35758, "loss": 0.0719, "lr": 1.0626398210290828e-06, "epoch": 0.02125339075477502, "percentage": 1.06, "elapsed_time": "0:22:44", "remaining_time": "1 day, 11:17:04"}
39
+ {"current_steps": 390, "total_steps": 35758, "loss": 0.0654, "lr": 1.0906040268456377e-06, "epoch": 0.02181269051147963, "percentage": 1.09, "elapsed_time": "0:23:17", "remaining_time": "1 day, 11:12:19"}
40
+ {"current_steps": 400, "total_steps": 35758, "loss": 0.0682, "lr": 1.1185682326621925e-06, "epoch": 0.022371990268184233, "percentage": 1.12, "elapsed_time": "0:23:54", "remaining_time": "1 day, 11:13:25"}
41
+ {"current_steps": 410, "total_steps": 35758, "loss": 0.0638, "lr": 1.1465324384787473e-06, "epoch": 0.022931290024888838, "percentage": 1.15, "elapsed_time": "0:24:29", "remaining_time": "1 day, 11:11:40"}
42
+ {"current_steps": 420, "total_steps": 35758, "loss": 0.0643, "lr": 1.174496644295302e-06, "epoch": 0.023490589781593445, "percentage": 1.17, "elapsed_time": "0:25:05", "remaining_time": "1 day, 11:11:02"}
43
+ {"current_steps": 430, "total_steps": 35758, "loss": 0.0629, "lr": 1.2024608501118568e-06, "epoch": 0.02404988953829805, "percentage": 1.2, "elapsed_time": "0:25:43", "remaining_time": "1 day, 11:13:47"}
44
+ {"current_steps": 440, "total_steps": 35758, "loss": 0.0649, "lr": 1.2304250559284117e-06, "epoch": 0.024609189295002658, "percentage": 1.23, "elapsed_time": "0:26:23", "remaining_time": "1 day, 11:17:45"}
45
+ {"current_steps": 450, "total_steps": 35758, "loss": 0.0557, "lr": 1.2583892617449667e-06, "epoch": 0.025168489051707262, "percentage": 1.26, "elapsed_time": "0:26:57", "remaining_time": "1 day, 11:15:38"}
46
+ {"current_steps": 460, "total_steps": 35758, "loss": 0.0574, "lr": 1.2863534675615214e-06, "epoch": 0.025727788808411867, "percentage": 1.29, "elapsed_time": "0:27:33", "remaining_time": "1 day, 11:15:08"}
47
+ {"current_steps": 470, "total_steps": 35758, "loss": 0.0553, "lr": 1.3143176733780762e-06, "epoch": 0.026287088565116475, "percentage": 1.31, "elapsed_time": "0:28:08", "remaining_time": "1 day, 11:12:30"}
48
+ {"current_steps": 480, "total_steps": 35758, "loss": 0.0553, "lr": 1.342281879194631e-06, "epoch": 0.02684638832182108, "percentage": 1.34, "elapsed_time": "0:28:39", "remaining_time": "1 day, 11:06:44"}
49
+ {"current_steps": 490, "total_steps": 35758, "loss": 0.0526, "lr": 1.3702460850111857e-06, "epoch": 0.027405688078525687, "percentage": 1.37, "elapsed_time": "0:29:13", "remaining_time": "1 day, 11:03:28"}
50
+ {"current_steps": 500, "total_steps": 35758, "loss": 0.0591, "lr": 1.3982102908277406e-06, "epoch": 0.02796498783523029, "percentage": 1.4, "elapsed_time": "0:29:49", "remaining_time": "1 day, 11:03:14"}
51
+ {"current_steps": 510, "total_steps": 35758, "loss": 0.0496, "lr": 1.4261744966442952e-06, "epoch": 0.028524287591934896, "percentage": 1.43, "elapsed_time": "0:30:25", "remaining_time": "1 day, 11:02:30"}
52
+ {"current_steps": 520, "total_steps": 35758, "loss": 0.0545, "lr": 1.4541387024608503e-06, "epoch": 0.029083587348639504, "percentage": 1.45, "elapsed_time": "0:30:59", "remaining_time": "1 day, 10:59:54"}
53
+ {"current_steps": 530, "total_steps": 35758, "loss": 0.057, "lr": 1.482102908277405e-06, "epoch": 0.029642887105344108, "percentage": 1.48, "elapsed_time": "0:31:36", "remaining_time": "1 day, 11:00:42"}
54
+ {"current_steps": 540, "total_steps": 35758, "loss": 0.0574, "lr": 1.51006711409396e-06, "epoch": 0.030202186862048716, "percentage": 1.51, "elapsed_time": "0:32:12", "remaining_time": "1 day, 11:00:33"}
55
+ {"current_steps": 550, "total_steps": 35758, "loss": 0.051, "lr": 1.5380313199105146e-06, "epoch": 0.03076148661875332, "percentage": 1.54, "elapsed_time": "0:32:44", "remaining_time": "1 day, 10:55:55"}
56
+ {"current_steps": 560, "total_steps": 35758, "loss": 0.0534, "lr": 1.5659955257270695e-06, "epoch": 0.031320786375457925, "percentage": 1.57, "elapsed_time": "0:33:21", "remaining_time": "1 day, 10:56:46"}
57
+ {"current_steps": 570, "total_steps": 35758, "loss": 0.048, "lr": 1.5939597315436243e-06, "epoch": 0.03188008613216253, "percentage": 1.59, "elapsed_time": "0:33:55", "remaining_time": "1 day, 10:54:22"}
58
+ {"current_steps": 580, "total_steps": 35758, "loss": 0.0491, "lr": 1.6219239373601792e-06, "epoch": 0.03243938588886714, "percentage": 1.62, "elapsed_time": "0:34:30", "remaining_time": "1 day, 10:53:27"}
59
+ {"current_steps": 590, "total_steps": 35758, "loss": 0.0487, "lr": 1.6498881431767338e-06, "epoch": 0.03299868564557174, "percentage": 1.65, "elapsed_time": "0:35:09", "remaining_time": "1 day, 10:55:21"}
60
+ {"current_steps": 600, "total_steps": 35758, "loss": 0.0534, "lr": 1.6778523489932889e-06, "epoch": 0.03355798540227635, "percentage": 1.68, "elapsed_time": "0:35:47", "remaining_time": "1 day, 10:57:22"}
61
+ {"current_steps": 610, "total_steps": 35758, "loss": 0.0521, "lr": 1.7058165548098435e-06, "epoch": 0.03411728515898096, "percentage": 1.71, "elapsed_time": "0:36:26", "remaining_time": "1 day, 10:59:58"}
62
+ {"current_steps": 620, "total_steps": 35758, "loss": 0.054, "lr": 1.7337807606263983e-06, "epoch": 0.03467658491568556, "percentage": 1.73, "elapsed_time": "0:37:00", "remaining_time": "1 day, 10:57:28"}
63
+ {"current_steps": 630, "total_steps": 35758, "loss": 0.0488, "lr": 1.7617449664429532e-06, "epoch": 0.035235884672390166, "percentage": 1.76, "elapsed_time": "0:37:34", "remaining_time": "1 day, 10:54:45"}
64
+ {"current_steps": 640, "total_steps": 35758, "loss": 0.0523, "lr": 1.789709172259508e-06, "epoch": 0.035795184429094774, "percentage": 1.79, "elapsed_time": "0:38:10", "remaining_time": "1 day, 10:54:51"}
65
+ {"current_steps": 650, "total_steps": 35758, "loss": 0.0483, "lr": 1.8176733780760627e-06, "epoch": 0.03635448418579938, "percentage": 1.82, "elapsed_time": "0:38:47", "remaining_time": "1 day, 10:54:48"}
66
+ {"current_steps": 660, "total_steps": 35758, "loss": 0.0414, "lr": 1.8456375838926177e-06, "epoch": 0.03691378394250398, "percentage": 1.85, "elapsed_time": "0:39:25", "remaining_time": "1 day, 10:56:43"}
67
+ {"current_steps": 670, "total_steps": 35758, "loss": 0.0515, "lr": 1.8736017897091724e-06, "epoch": 0.03747308369920859, "percentage": 1.87, "elapsed_time": "0:40:01", "remaining_time": "1 day, 10:55:54"}
68
+ {"current_steps": 680, "total_steps": 35758, "loss": 0.0551, "lr": 1.9015659955257274e-06, "epoch": 0.0380323834559132, "percentage": 1.9, "elapsed_time": "0:40:35", "remaining_time": "1 day, 10:53:50"}
69
+ {"current_steps": 690, "total_steps": 35758, "loss": 0.0438, "lr": 1.929530201342282e-06, "epoch": 0.0385916832126178, "percentage": 1.93, "elapsed_time": "0:41:12", "remaining_time": "1 day, 10:54:14"}
70
+ {"current_steps": 700, "total_steps": 35758, "loss": 0.0461, "lr": 1.957494407158837e-06, "epoch": 0.03915098296932241, "percentage": 1.96, "elapsed_time": "0:41:46", "remaining_time": "1 day, 10:52:29"}
71
+ {"current_steps": 710, "total_steps": 35758, "loss": 0.0423, "lr": 1.9854586129753916e-06, "epoch": 0.039710282726027016, "percentage": 1.99, "elapsed_time": "0:42:26", "remaining_time": "1 day, 10:55:20"}
72
+ {"current_steps": 720, "total_steps": 35758, "loss": 0.0503, "lr": 2.013422818791946e-06, "epoch": 0.04026958248273162, "percentage": 2.01, "elapsed_time": "0:43:05", "remaining_time": "1 day, 10:56:50"}
73
+ {"current_steps": 730, "total_steps": 35758, "loss": 0.0392, "lr": 2.0413870246085013e-06, "epoch": 0.040828882239436225, "percentage": 2.04, "elapsed_time": "0:43:40", "remaining_time": "1 day, 10:55:57"}
74
+ {"current_steps": 740, "total_steps": 35758, "loss": 0.0443, "lr": 2.069351230425056e-06, "epoch": 0.04138818199614083, "percentage": 2.07, "elapsed_time": "0:44:16", "remaining_time": "1 day, 10:55:20"}
75
+ {"current_steps": 750, "total_steps": 35758, "loss": 0.0438, "lr": 2.097315436241611e-06, "epoch": 0.04194748175284544, "percentage": 2.1, "elapsed_time": "0:44:53", "remaining_time": "1 day, 10:55:29"}
76
+ {"current_steps": 760, "total_steps": 35758, "loss": 0.0446, "lr": 2.1252796420581656e-06, "epoch": 0.04250678150955004, "percentage": 2.13, "elapsed_time": "0:45:32", "remaining_time": "1 day, 10:56:55"}
77
+ {"current_steps": 770, "total_steps": 35758, "loss": 0.0418, "lr": 2.1532438478747207e-06, "epoch": 0.04306608126625465, "percentage": 2.15, "elapsed_time": "0:46:07", "remaining_time": "1 day, 10:55:50"}
78
+ {"current_steps": 780, "total_steps": 35758, "loss": 0.0413, "lr": 2.1812080536912753e-06, "epoch": 0.04362538102295926, "percentage": 2.18, "elapsed_time": "0:46:40", "remaining_time": "1 day, 10:53:21"}
79
+ {"current_steps": 790, "total_steps": 35758, "loss": 0.0435, "lr": 2.2091722595078304e-06, "epoch": 0.04418468077966386, "percentage": 2.21, "elapsed_time": "0:47:21", "remaining_time": "1 day, 10:56:21"}
80
+ {"current_steps": 800, "total_steps": 35758, "loss": 0.0438, "lr": 2.237136465324385e-06, "epoch": 0.044743980536368466, "percentage": 2.24, "elapsed_time": "0:48:01", "remaining_time": "1 day, 10:58:16"}
81
+ {"current_steps": 810, "total_steps": 35758, "loss": 0.0377, "lr": 2.2651006711409396e-06, "epoch": 0.045303280293073074, "percentage": 2.27, "elapsed_time": "0:48:31", "remaining_time": "1 day, 10:53:46"}
82
+ {"current_steps": 820, "total_steps": 35758, "loss": 0.0417, "lr": 2.2930648769574947e-06, "epoch": 0.045862580049777675, "percentage": 2.29, "elapsed_time": "0:49:06", "remaining_time": "1 day, 10:52:18"}
83
+ {"current_steps": 830, "total_steps": 35758, "loss": 0.0386, "lr": 2.3210290827740493e-06, "epoch": 0.04642187980648228, "percentage": 2.32, "elapsed_time": "0:49:43", "remaining_time": "1 day, 10:52:32"}
84
+ {"current_steps": 840, "total_steps": 35758, "loss": 0.0377, "lr": 2.348993288590604e-06, "epoch": 0.04698117956318689, "percentage": 2.35, "elapsed_time": "0:50:19", "remaining_time": "1 day, 10:51:51"}
85
+ {"current_steps": 850, "total_steps": 35758, "loss": 0.0385, "lr": 2.376957494407159e-06, "epoch": 0.0475404793198915, "percentage": 2.38, "elapsed_time": "0:50:54", "remaining_time": "1 day, 10:50:45"}
86
+ {"current_steps": 860, "total_steps": 35758, "loss": 0.0354, "lr": 2.4049217002237137e-06, "epoch": 0.0480997790765961, "percentage": 2.41, "elapsed_time": "0:51:29", "remaining_time": "1 day, 10:49:10"}
87
+ {"current_steps": 870, "total_steps": 35758, "loss": 0.0435, "lr": 2.4328859060402687e-06, "epoch": 0.04865907883330071, "percentage": 2.43, "elapsed_time": "0:52:06", "remaining_time": "1 day, 10:49:48"}
88
+ {"current_steps": 880, "total_steps": 35758, "loss": 0.0395, "lr": 2.4608501118568234e-06, "epoch": 0.049218378590005316, "percentage": 2.46, "elapsed_time": "0:52:43", "remaining_time": "1 day, 10:50:00"}
89
+ {"current_steps": 890, "total_steps": 35758, "loss": 0.035, "lr": 2.4888143176733784e-06, "epoch": 0.04977767834670992, "percentage": 2.49, "elapsed_time": "0:53:18", "remaining_time": "1 day, 10:48:41"}
90
+ {"current_steps": 900, "total_steps": 35758, "loss": 0.0403, "lr": 2.5167785234899335e-06, "epoch": 0.050336978103414524, "percentage": 2.52, "elapsed_time": "0:53:55", "remaining_time": "1 day, 10:48:27"}
91
+ {"current_steps": 910, "total_steps": 35758, "loss": 0.0456, "lr": 2.544742729306488e-06, "epoch": 0.05089627786011913, "percentage": 2.54, "elapsed_time": "0:54:31", "remaining_time": "1 day, 10:47:45"}
92
+ {"current_steps": 920, "total_steps": 35758, "loss": 0.0391, "lr": 2.5727069351230428e-06, "epoch": 0.05145557761682373, "percentage": 2.57, "elapsed_time": "0:55:10", "remaining_time": "1 day, 10:49:20"}
93
+ {"current_steps": 930, "total_steps": 35758, "loss": 0.0394, "lr": 2.6006711409395974e-06, "epoch": 0.05201487737352834, "percentage": 2.6, "elapsed_time": "0:55:51", "remaining_time": "1 day, 10:51:56"}
94
+ {"current_steps": 940, "total_steps": 35758, "loss": 0.039, "lr": 2.6286353467561525e-06, "epoch": 0.05257417713023295, "percentage": 2.63, "elapsed_time": "0:56:26", "remaining_time": "1 day, 10:50:29"}
95
+ {"current_steps": 950, "total_steps": 35758, "loss": 0.0352, "lr": 2.656599552572707e-06, "epoch": 0.05313347688693756, "percentage": 2.66, "elapsed_time": "0:56:59", "remaining_time": "1 day, 10:47:55"}
96
+ {"current_steps": 960, "total_steps": 35758, "loss": 0.0401, "lr": 2.684563758389262e-06, "epoch": 0.05369277664364216, "percentage": 2.68, "elapsed_time": "0:57:35", "remaining_time": "1 day, 10:47:28"}
97
+ {"current_steps": 970, "total_steps": 35758, "loss": 0.0378, "lr": 2.712527964205817e-06, "epoch": 0.054252076400346766, "percentage": 2.71, "elapsed_time": "0:58:10", "remaining_time": "1 day, 10:46:39"}
98
+ {"current_steps": 980, "total_steps": 35758, "loss": 0.0363, "lr": 2.7404921700223714e-06, "epoch": 0.054811376157051374, "percentage": 2.74, "elapsed_time": "0:58:48", "remaining_time": "1 day, 10:46:57"}
99
+ {"current_steps": 990, "total_steps": 35758, "loss": 0.0386, "lr": 2.7684563758389265e-06, "epoch": 0.055370675913755975, "percentage": 2.77, "elapsed_time": "0:59:27", "remaining_time": "1 day, 10:48:15"}
100
+ {"current_steps": 1000, "total_steps": 35758, "loss": 0.0409, "lr": 2.796420581655481e-06, "epoch": 0.05592997567046058, "percentage": 2.8, "elapsed_time": "1:00:08", "remaining_time": "1 day, 10:50:21"}
101
+ {"current_steps": 1010, "total_steps": 35758, "loss": 0.0364, "lr": 2.8243847874720358e-06, "epoch": 0.05648927542716519, "percentage": 2.82, "elapsed_time": "1:01:06", "remaining_time": "1 day, 11:02:20"}
102
+ {"current_steps": 1020, "total_steps": 35758, "loss": 0.037, "lr": 2.8523489932885904e-06, "epoch": 0.05704857518386979, "percentage": 2.85, "elapsed_time": "1:01:43", "remaining_time": "1 day, 11:02:02"}
103
+ {"current_steps": 1030, "total_steps": 35758, "loss": 0.0356, "lr": 2.880313199105146e-06, "epoch": 0.0576078749405744, "percentage": 2.88, "elapsed_time": "1:02:17", "remaining_time": "1 day, 11:00:15"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e15e062379452bf0f32316d08f3408417940c09d0f457fdb2b0c1272038ad32
3
+ size 7416
vocab.json ADDED
The diff for this file is too large to render. See raw diff