Rano23 commited on
Commit
45d0f5d
·
verified ·
1 Parent(s): 65eb45d

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
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-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": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "o_proj",
25
+ "v_proj",
26
+ "q_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "gate_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:e16bfbe793912250a4613d688420507f042cb225211fb5e4456d5b5e1fce9dcc
3
+ size 80792880
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 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "extra_special_tokens": {},
203
+ "model_max_length": 16384,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 12207, "loss": 0.7558, "lr": 8.19000819000819e-07, "epoch": 0.002457304337142155, "percentage": 0.08, "elapsed_time": "0:01:26", "remaining_time": "1 day, 5:09:52"}
2
+ {"current_steps": 20, "total_steps": 12207, "loss": 0.7649, "lr": 1.638001638001638e-06, "epoch": 0.00491460867428431, "percentage": 0.16, "elapsed_time": "0:02:41", "remaining_time": "1 day, 3:19:05"}
3
+ {"current_steps": 30, "total_steps": 12207, "loss": 0.7569, "lr": 2.457002457002457e-06, "epoch": 0.007371913011426466, "percentage": 0.25, "elapsed_time": "0:03:54", "remaining_time": "1 day, 2:25:48"}
4
+ {"current_steps": 40, "total_steps": 12207, "loss": 0.7528, "lr": 3.276003276003276e-06, "epoch": 0.00982921734856862, "percentage": 0.33, "elapsed_time": "0:05:04", "remaining_time": "1 day, 1:44:07"}
5
+ {"current_steps": 50, "total_steps": 12207, "loss": 0.7588, "lr": 4.095004095004095e-06, "epoch": 0.012286521685710775, "percentage": 0.41, "elapsed_time": "0:06:13", "remaining_time": "1 day, 1:14:26"}
6
+ {"current_steps": 60, "total_steps": 12207, "loss": 0.7348, "lr": 4.914004914004914e-06, "epoch": 0.014743826022852931, "percentage": 0.49, "elapsed_time": "0:07:30", "remaining_time": "1 day, 1:21:25"}
7
+ {"current_steps": 70, "total_steps": 12207, "loss": 0.7146, "lr": 5.733005733005734e-06, "epoch": 0.017201130359995084, "percentage": 0.57, "elapsed_time": "0:08:54", "remaining_time": "1 day, 1:44:51"}
8
+ {"current_steps": 80, "total_steps": 12207, "loss": 0.6993, "lr": 6.552006552006552e-06, "epoch": 0.01965843469713724, "percentage": 0.66, "elapsed_time": "0:10:06", "remaining_time": "1 day, 1:31:17"}
9
+ {"current_steps": 90, "total_steps": 12207, "loss": 0.6848, "lr": 7.371007371007371e-06, "epoch": 0.022115739034279394, "percentage": 0.74, "elapsed_time": "0:11:23", "remaining_time": "1 day, 1:34:25"}
10
+ {"current_steps": 100, "total_steps": 12207, "loss": 0.6416, "lr": 8.19000819000819e-06, "epoch": 0.02457304337142155, "percentage": 0.82, "elapsed_time": "0:12:35", "remaining_time": "1 day, 1:24:20"}
11
+ {"current_steps": 110, "total_steps": 12207, "loss": 0.6339, "lr": 9.00900900900901e-06, "epoch": 0.027030347708563704, "percentage": 0.9, "elapsed_time": "0:13:50", "remaining_time": "1 day, 1:22:28"}
12
+ {"current_steps": 120, "total_steps": 12207, "loss": 0.6021, "lr": 9.828009828009828e-06, "epoch": 0.029487652045705862, "percentage": 0.98, "elapsed_time": "0:15:05", "remaining_time": "1 day, 1:19:18"}
13
+ {"current_steps": 130, "total_steps": 12207, "loss": 0.6104, "lr": 1.0647010647010649e-05, "epoch": 0.031944956382848014, "percentage": 1.06, "elapsed_time": "0:16:18", "remaining_time": "1 day, 1:15:28"}
14
+ {"current_steps": 140, "total_steps": 12207, "loss": 0.6114, "lr": 1.1466011466011468e-05, "epoch": 0.03440226071999017, "percentage": 1.15, "elapsed_time": "0:17:37", "remaining_time": "1 day, 1:18:34"}
15
+ {"current_steps": 150, "total_steps": 12207, "loss": 0.5917, "lr": 1.2285012285012287e-05, "epoch": 0.036859565057132324, "percentage": 1.23, "elapsed_time": "0:18:56", "remaining_time": "1 day, 1:21:52"}
16
+ {"current_steps": 160, "total_steps": 12207, "loss": 0.5706, "lr": 1.3104013104013104e-05, "epoch": 0.03931686939427448, "percentage": 1.31, "elapsed_time": "0:20:06", "remaining_time": "1 day, 1:13:43"}
17
+ {"current_steps": 170, "total_steps": 12207, "loss": 0.5775, "lr": 1.3923013923013925e-05, "epoch": 0.04177417373141663, "percentage": 1.39, "elapsed_time": "0:21:16", "remaining_time": "1 day, 1:06:55"}
18
+ {"current_steps": 180, "total_steps": 12207, "loss": 0.5637, "lr": 1.4742014742014742e-05, "epoch": 0.04423147806855879, "percentage": 1.47, "elapsed_time": "0:22:27", "remaining_time": "1 day, 1:00:11"}
19
+ {"current_steps": 190, "total_steps": 12207, "loss": 0.5446, "lr": 1.5561015561015562e-05, "epoch": 0.04668878240570094, "percentage": 1.56, "elapsed_time": "0:23:47", "remaining_time": "1 day, 1:04:38"}
20
+ {"current_steps": 200, "total_steps": 12207, "loss": 0.5269, "lr": 1.638001638001638e-05, "epoch": 0.0491460867428431, "percentage": 1.64, "elapsed_time": "0:25:03", "remaining_time": "1 day, 1:04:00"}
21
+ {"current_steps": 210, "total_steps": 12207, "loss": 0.5232, "lr": 1.71990171990172e-05, "epoch": 0.05160339107998525, "percentage": 1.72, "elapsed_time": "0:26:17", "remaining_time": "1 day, 1:01:38"}
22
+ {"current_steps": 220, "total_steps": 12207, "loss": 0.5444, "lr": 1.801801801801802e-05, "epoch": 0.05406069541712741, "percentage": 1.8, "elapsed_time": "0:27:32", "remaining_time": "1 day, 1:00:50"}
23
+ {"current_steps": 230, "total_steps": 12207, "loss": 0.5398, "lr": 1.8837018837018838e-05, "epoch": 0.05651799975426957, "percentage": 1.88, "elapsed_time": "0:28:46", "remaining_time": "1 day, 0:58:42"}
24
+ {"current_steps": 240, "total_steps": 12207, "loss": 0.5267, "lr": 1.9656019656019657e-05, "epoch": 0.058975304091411725, "percentage": 1.97, "elapsed_time": "0:29:59", "remaining_time": "1 day, 0:55:17"}
25
+ {"current_steps": 250, "total_steps": 12207, "loss": 0.5334, "lr": 2.0475020475020476e-05, "epoch": 0.06143260842855388, "percentage": 2.05, "elapsed_time": "0:31:08", "remaining_time": "1 day, 0:49:19"}
26
+ {"current_steps": 260, "total_steps": 12207, "loss": 0.5016, "lr": 2.1294021294021298e-05, "epoch": 0.06388991276569603, "percentage": 2.13, "elapsed_time": "0:32:22", "remaining_time": "1 day, 0:47:37"}
27
+ {"current_steps": 270, "total_steps": 12207, "loss": 0.5076, "lr": 2.2113022113022113e-05, "epoch": 0.06634721710283818, "percentage": 2.21, "elapsed_time": "0:33:34", "remaining_time": "1 day, 0:44:27"}
28
+ {"current_steps": 280, "total_steps": 12207, "loss": 0.4965, "lr": 2.2932022932022936e-05, "epoch": 0.06880452143998034, "percentage": 2.29, "elapsed_time": "0:34:46", "remaining_time": "1 day, 0:41:06"}
29
+ {"current_steps": 290, "total_steps": 12207, "loss": 0.5017, "lr": 2.375102375102375e-05, "epoch": 0.07126182577712249, "percentage": 2.38, "elapsed_time": "0:35:53", "remaining_time": "1 day, 0:34:49"}
30
+ {"current_steps": 300, "total_steps": 12207, "loss": 0.499, "lr": 2.4570024570024573e-05, "epoch": 0.07371913011426465, "percentage": 2.46, "elapsed_time": "0:37:10", "remaining_time": "1 day, 0:35:40"}
31
+ {"current_steps": 310, "total_steps": 12207, "loss": 0.4997, "lr": 2.538902538902539e-05, "epoch": 0.0761764344514068, "percentage": 2.54, "elapsed_time": "0:38:22", "remaining_time": "1 day, 0:32:32"}
32
+ {"current_steps": 320, "total_steps": 12207, "loss": 0.5131, "lr": 2.6208026208026208e-05, "epoch": 0.07863373878854896, "percentage": 2.62, "elapsed_time": "0:39:34", "remaining_time": "1 day, 0:29:51"}
33
+ {"current_steps": 330, "total_steps": 12207, "loss": 0.5032, "lr": 2.702702702702703e-05, "epoch": 0.08109104312569111, "percentage": 2.7, "elapsed_time": "0:40:43", "remaining_time": "1 day, 0:26:00"}
34
+ {"current_steps": 340, "total_steps": 12207, "loss": 0.5087, "lr": 2.784602784602785e-05, "epoch": 0.08354834746283327, "percentage": 2.79, "elapsed_time": "0:42:04", "remaining_time": "1 day, 0:28:30"}
35
+ {"current_steps": 350, "total_steps": 12207, "loss": 0.5077, "lr": 2.8665028665028665e-05, "epoch": 0.08600565179997542, "percentage": 2.87, "elapsed_time": "0:43:22", "remaining_time": "1 day, 0:29:41"}
36
+ {"current_steps": 360, "total_steps": 12207, "loss": 0.4981, "lr": 2.9484029484029483e-05, "epoch": 0.08846295613711758, "percentage": 2.95, "elapsed_time": "0:44:37", "remaining_time": "1 day, 0:28:31"}
37
+ {"current_steps": 370, "total_steps": 12207, "loss": 0.4851, "lr": 3.0303030303030306e-05, "epoch": 0.09092026047425973, "percentage": 3.03, "elapsed_time": "0:45:49", "remaining_time": "1 day, 0:26:12"}
38
+ {"current_steps": 380, "total_steps": 12207, "loss": 0.4952, "lr": 3.1122031122031125e-05, "epoch": 0.09337756481140189, "percentage": 3.11, "elapsed_time": "0:47:06", "remaining_time": "1 day, 0:26:09"}
39
+ {"current_steps": 390, "total_steps": 12207, "loss": 0.4862, "lr": 3.1941031941031943e-05, "epoch": 0.09583486914854404, "percentage": 3.19, "elapsed_time": "0:48:29", "remaining_time": "1 day, 0:29:25"}
40
+ {"current_steps": 400, "total_steps": 12207, "loss": 0.4715, "lr": 3.276003276003276e-05, "epoch": 0.0982921734856862, "percentage": 3.28, "elapsed_time": "0:49:40", "remaining_time": "1 day, 0:26:10"}
41
+ {"current_steps": 410, "total_steps": 12207, "loss": 0.4573, "lr": 3.357903357903358e-05, "epoch": 0.10074947782282835, "percentage": 3.36, "elapsed_time": "0:50:53", "remaining_time": "1 day, 0:24:23"}
42
+ {"current_steps": 420, "total_steps": 12207, "loss": 0.4948, "lr": 3.43980343980344e-05, "epoch": 0.1032067821599705, "percentage": 3.44, "elapsed_time": "0:52:11", "remaining_time": "1 day, 0:24:30"}
43
+ {"current_steps": 430, "total_steps": 12207, "loss": 0.4646, "lr": 3.521703521703522e-05, "epoch": 0.10566408649711266, "percentage": 3.52, "elapsed_time": "0:53:24", "remaining_time": "1 day, 0:22:51"}
44
+ {"current_steps": 440, "total_steps": 12207, "loss": 0.4859, "lr": 3.603603603603604e-05, "epoch": 0.10812139083425482, "percentage": 3.6, "elapsed_time": "0:54:40", "remaining_time": "1 day, 0:22:14"}
45
+ {"current_steps": 450, "total_steps": 12207, "loss": 0.4857, "lr": 3.685503685503686e-05, "epoch": 0.11057869517139697, "percentage": 3.69, "elapsed_time": "0:55:54", "remaining_time": "1 day, 0:20:32"}
46
+ {"current_steps": 460, "total_steps": 12207, "loss": 0.4636, "lr": 3.7674037674037676e-05, "epoch": 0.11303599950853914, "percentage": 3.77, "elapsed_time": "0:57:11", "remaining_time": "1 day, 0:20:37"}
47
+ {"current_steps": 470, "total_steps": 12207, "loss": 0.4742, "lr": 3.8493038493038495e-05, "epoch": 0.1154933038456813, "percentage": 3.85, "elapsed_time": "0:58:24", "remaining_time": "1 day, 0:18:29"}
48
+ {"current_steps": 480, "total_steps": 12207, "loss": 0.4814, "lr": 3.9312039312039314e-05, "epoch": 0.11795060818282345, "percentage": 3.93, "elapsed_time": "0:59:37", "remaining_time": "1 day, 0:16:52"}
49
+ {"current_steps": 490, "total_steps": 12207, "loss": 0.4856, "lr": 4.013104013104013e-05, "epoch": 0.1204079125199656, "percentage": 4.01, "elapsed_time": "1:00:56", "remaining_time": "1 day, 0:17:13"}
50
+ {"current_steps": 500, "total_steps": 12207, "loss": 0.4477, "lr": 4.095004095004095e-05, "epoch": 0.12286521685710776, "percentage": 4.1, "elapsed_time": "1:02:07", "remaining_time": "1 day, 0:14:24"}
51
+ {"current_steps": 510, "total_steps": 12207, "loss": 0.4794, "lr": 4.176904176904177e-05, "epoch": 0.12532252119424991, "percentage": 4.18, "elapsed_time": "1:03:22", "remaining_time": "1 day, 0:13:20"}
52
+ {"current_steps": 520, "total_steps": 12207, "loss": 0.4643, "lr": 4.2588042588042596e-05, "epoch": 0.12777982553139206, "percentage": 4.26, "elapsed_time": "1:04:36", "remaining_time": "1 day, 0:12:04"}
53
+ {"current_steps": 530, "total_steps": 12207, "loss": 0.4742, "lr": 4.340704340704341e-05, "epoch": 0.13023712986853422, "percentage": 4.34, "elapsed_time": "1:05:47", "remaining_time": "1 day, 0:09:42"}
54
+ {"current_steps": 540, "total_steps": 12207, "loss": 0.4778, "lr": 4.422604422604423e-05, "epoch": 0.13269443420567636, "percentage": 4.42, "elapsed_time": "1:06:58", "remaining_time": "1 day, 0:06:56"}
55
+ {"current_steps": 550, "total_steps": 12207, "loss": 0.4686, "lr": 4.5045045045045046e-05, "epoch": 0.13515173854281853, "percentage": 4.51, "elapsed_time": "1:08:09", "remaining_time": "1 day, 0:04:34"}
56
+ {"current_steps": 560, "total_steps": 12207, "loss": 0.479, "lr": 4.586404586404587e-05, "epoch": 0.13760904287996067, "percentage": 4.59, "elapsed_time": "1:09:21", "remaining_time": "1 day, 0:02:29"}
57
+ {"current_steps": 570, "total_steps": 12207, "loss": 0.4567, "lr": 4.6683046683046684e-05, "epoch": 0.14006634721710284, "percentage": 4.67, "elapsed_time": "1:10:39", "remaining_time": "1 day, 0:02:37"}
58
+ {"current_steps": 580, "total_steps": 12207, "loss": 0.4787, "lr": 4.75020475020475e-05, "epoch": 0.14252365155424498, "percentage": 4.75, "elapsed_time": "1:11:55", "remaining_time": "1 day, 0:01:41"}
59
+ {"current_steps": 590, "total_steps": 12207, "loss": 0.4605, "lr": 4.832104832104832e-05, "epoch": 0.14498095589138715, "percentage": 4.83, "elapsed_time": "1:13:09", "remaining_time": "1 day, 0:00:37"}
60
+ {"current_steps": 600, "total_steps": 12207, "loss": 0.4511, "lr": 4.914004914004915e-05, "epoch": 0.1474382602285293, "percentage": 4.92, "elapsed_time": "1:14:16", "remaining_time": "23:56:55"}
61
+ {"current_steps": 610, "total_steps": 12207, "loss": 0.4458, "lr": 4.9959049959049966e-05, "epoch": 0.14989556456567146, "percentage": 5.0, "elapsed_time": "1:15:30", "remaining_time": "23:55:30"}
62
+ {"current_steps": 620, "total_steps": 12207, "loss": 0.4555, "lr": 5.077805077805078e-05, "epoch": 0.1523528689028136, "percentage": 5.08, "elapsed_time": "1:16:50", "remaining_time": "23:56:10"}
63
+ {"current_steps": 630, "total_steps": 12207, "loss": 0.4617, "lr": 5.1597051597051604e-05, "epoch": 0.15481017323995577, "percentage": 5.16, "elapsed_time": "1:18:09", "remaining_time": "23:56:20"}
64
+ {"current_steps": 640, "total_steps": 12207, "loss": 0.453, "lr": 5.2416052416052416e-05, "epoch": 0.1572674775770979, "percentage": 5.24, "elapsed_time": "1:19:17", "remaining_time": "23:52:55"}
65
+ {"current_steps": 650, "total_steps": 12207, "loss": 0.4597, "lr": 5.3235053235053235e-05, "epoch": 0.15972478191424008, "percentage": 5.32, "elapsed_time": "1:20:28", "remaining_time": "23:50:55"}
66
+ {"current_steps": 660, "total_steps": 12207, "loss": 0.4708, "lr": 5.405405405405406e-05, "epoch": 0.16218208625138222, "percentage": 5.41, "elapsed_time": "1:21:44", "remaining_time": "23:50:14"}
67
+ {"current_steps": 670, "total_steps": 12207, "loss": 0.4503, "lr": 5.487305487305487e-05, "epoch": 0.1646393905885244, "percentage": 5.49, "elapsed_time": "1:23:06", "remaining_time": "23:50:59"}
68
+ {"current_steps": 680, "total_steps": 12207, "loss": 0.4464, "lr": 5.56920556920557e-05, "epoch": 0.16709669492566653, "percentage": 5.57, "elapsed_time": "1:24:13", "remaining_time": "23:47:48"}
69
+ {"current_steps": 690, "total_steps": 12207, "loss": 0.4483, "lr": 5.651105651105652e-05, "epoch": 0.1695539992628087, "percentage": 5.65, "elapsed_time": "1:25:34", "remaining_time": "23:48:17"}
70
+ {"current_steps": 700, "total_steps": 12207, "loss": 0.4628, "lr": 5.733005733005733e-05, "epoch": 0.17201130359995084, "percentage": 5.73, "elapsed_time": "1:26:51", "remaining_time": "23:47:44"}
71
+ {"current_steps": 710, "total_steps": 12207, "loss": 0.4561, "lr": 5.8149058149058155e-05, "epoch": 0.174468607937093, "percentage": 5.82, "elapsed_time": "1:28:03", "remaining_time": "23:45:49"}
72
+ {"current_steps": 720, "total_steps": 12207, "loss": 0.4547, "lr": 5.896805896805897e-05, "epoch": 0.17692591227423515, "percentage": 5.9, "elapsed_time": "1:29:17", "remaining_time": "23:44:40"}
73
+ {"current_steps": 730, "total_steps": 12207, "loss": 0.4433, "lr": 5.9787059787059786e-05, "epoch": 0.17938321661137732, "percentage": 5.98, "elapsed_time": "1:30:26", "remaining_time": "23:41:51"}
74
+ {"current_steps": 740, "total_steps": 12207, "loss": 0.4511, "lr": 6.060606060606061e-05, "epoch": 0.18184052094851946, "percentage": 6.06, "elapsed_time": "1:31:37", "remaining_time": "23:39:56"}
75
+ {"current_steps": 750, "total_steps": 12207, "loss": 0.4692, "lr": 6.142506142506142e-05, "epoch": 0.18429782528566163, "percentage": 6.14, "elapsed_time": "1:32:43", "remaining_time": "23:36:30"}
76
+ {"current_steps": 760, "total_steps": 12207, "loss": 0.4743, "lr": 6.224406224406225e-05, "epoch": 0.18675512962280377, "percentage": 6.23, "elapsed_time": "1:34:00", "remaining_time": "23:35:55"}
77
+ {"current_steps": 770, "total_steps": 12207, "loss": 0.4701, "lr": 6.306306306306306e-05, "epoch": 0.18921243395994594, "percentage": 6.31, "elapsed_time": "1:35:20", "remaining_time": "23:36:00"}
78
+ {"current_steps": 780, "total_steps": 12207, "loss": 0.4514, "lr": 6.388206388206389e-05, "epoch": 0.19166973829708808, "percentage": 6.39, "elapsed_time": "1:36:37", "remaining_time": "23:35:32"}
79
+ {"current_steps": 790, "total_steps": 12207, "loss": 0.4544, "lr": 6.470106470106471e-05, "epoch": 0.19412704263423025, "percentage": 6.47, "elapsed_time": "1:37:53", "remaining_time": "23:34:42"}
80
+ {"current_steps": 800, "total_steps": 12207, "loss": 0.4584, "lr": 6.552006552006552e-05, "epoch": 0.1965843469713724, "percentage": 6.55, "elapsed_time": "1:39:03", "remaining_time": "23:32:29"}
81
+ {"current_steps": 810, "total_steps": 12207, "loss": 0.4623, "lr": 6.633906633906635e-05, "epoch": 0.19904165130851456, "percentage": 6.64, "elapsed_time": "1:40:14", "remaining_time": "23:30:32"}
82
+ {"current_steps": 820, "total_steps": 12207, "loss": 0.4837, "lr": 6.715806715806716e-05, "epoch": 0.2014989556456567, "percentage": 6.72, "elapsed_time": "1:41:35", "remaining_time": "23:30:49"}
83
+ {"current_steps": 830, "total_steps": 12207, "loss": 0.4651, "lr": 6.797706797706797e-05, "epoch": 0.20395625998279887, "percentage": 6.8, "elapsed_time": "1:42:58", "remaining_time": "23:31:28"}
84
+ {"current_steps": 840, "total_steps": 12207, "loss": 0.453, "lr": 6.87960687960688e-05, "epoch": 0.206413564319941, "percentage": 6.88, "elapsed_time": "1:44:11", "remaining_time": "23:29:59"}
85
+ {"current_steps": 850, "total_steps": 12207, "loss": 0.4482, "lr": 6.961506961506961e-05, "epoch": 0.20887086865708318, "percentage": 6.96, "elapsed_time": "1:45:22", "remaining_time": "23:27:58"}
86
+ {"current_steps": 860, "total_steps": 12207, "loss": 0.4548, "lr": 7.043407043407044e-05, "epoch": 0.21132817299422532, "percentage": 7.05, "elapsed_time": "1:46:41", "remaining_time": "23:27:43"}
87
+ {"current_steps": 870, "total_steps": 12207, "loss": 0.4558, "lr": 7.125307125307126e-05, "epoch": 0.2137854773313675, "percentage": 7.13, "elapsed_time": "1:48:00", "remaining_time": "23:27:30"}
88
+ {"current_steps": 880, "total_steps": 12207, "loss": 0.4614, "lr": 7.207207207207208e-05, "epoch": 0.21624278166850963, "percentage": 7.21, "elapsed_time": "1:49:10", "remaining_time": "23:25:16"}
89
+ {"current_steps": 890, "total_steps": 12207, "loss": 0.4437, "lr": 7.28910728910729e-05, "epoch": 0.2187000860056518, "percentage": 7.29, "elapsed_time": "1:50:28", "remaining_time": "23:24:39"}
90
+ {"current_steps": 900, "total_steps": 12207, "loss": 0.4557, "lr": 7.371007371007371e-05, "epoch": 0.22115739034279394, "percentage": 7.37, "elapsed_time": "1:51:40", "remaining_time": "23:23:02"}
91
+ {"current_steps": 910, "total_steps": 12207, "loss": 0.4516, "lr": 7.452907452907453e-05, "epoch": 0.2236146946799361, "percentage": 7.45, "elapsed_time": "1:52:58", "remaining_time": "23:22:33"}
92
+ {"current_steps": 920, "total_steps": 12207, "loss": 0.4466, "lr": 7.534807534807535e-05, "epoch": 0.22607199901707828, "percentage": 7.54, "elapsed_time": "1:54:04", "remaining_time": "23:19:27"}
93
+ {"current_steps": 930, "total_steps": 12207, "loss": 0.4568, "lr": 7.616707616707616e-05, "epoch": 0.22852930335422042, "percentage": 7.62, "elapsed_time": "1:55:21", "remaining_time": "23:18:47"}
94
+ {"current_steps": 940, "total_steps": 12207, "loss": 0.4665, "lr": 7.698607698607699e-05, "epoch": 0.2309866076913626, "percentage": 7.7, "elapsed_time": "1:56:29", "remaining_time": "23:16:16"}
95
+ {"current_steps": 950, "total_steps": 12207, "loss": 0.4464, "lr": 7.780507780507781e-05, "epoch": 0.23344391202850473, "percentage": 7.78, "elapsed_time": "1:57:48", "remaining_time": "23:15:53"}
96
+ {"current_steps": 960, "total_steps": 12207, "loss": 0.4411, "lr": 7.862407862407863e-05, "epoch": 0.2359012163656469, "percentage": 7.86, "elapsed_time": "1:59:02", "remaining_time": "23:14:34"}
97
+ {"current_steps": 970, "total_steps": 12207, "loss": 0.4497, "lr": 7.944307944307945e-05, "epoch": 0.23835852070278904, "percentage": 7.95, "elapsed_time": "2:00:15", "remaining_time": "23:13:13"}
98
+ {"current_steps": 980, "total_steps": 12207, "loss": 0.4637, "lr": 8.026208026208026e-05, "epoch": 0.2408158250399312, "percentage": 8.03, "elapsed_time": "2:01:35", "remaining_time": "23:12:56"}
99
+ {"current_steps": 990, "total_steps": 12207, "loss": 0.4666, "lr": 8.108108108108109e-05, "epoch": 0.24327312937707335, "percentage": 8.11, "elapsed_time": "2:02:47", "remaining_time": "23:11:20"}
100
+ {"current_steps": 1000, "total_steps": 12207, "loss": 0.4491, "lr": 8.19000819000819e-05, "epoch": 0.24573043371421552, "percentage": 8.19, "elapsed_time": "2:04:10", "remaining_time": "23:11:32"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb3423622c602d85acc45ad89a63971681009057825b92f7d3f2415ffdf40be5
3
+ size 7608
vocab.json ADDED
The diff for this file is too large to render. See raw diff