Rano23 commited on
Commit
759c417
·
verified ·
1 Parent(s): 5691f2a

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/Qwen2.5-3B-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": 16,
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": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "gate_proj",
25
+ "v_proj",
26
+ "o_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "k_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:d00aceae533f09007ae0c29bb07b7e8c21ba391dcc8dcb0ed87790c19235599d
3
+ size 30000384
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": 20345, "loss": 0.8007, "lr": 2.457002457002457e-07, "epoch": 0.002457304337142155, "percentage": 0.05, "elapsed_time": "0:02:43", "remaining_time": "3 days, 20:04:54"}
2
+ {"current_steps": 20, "total_steps": 20345, "loss": 0.8108, "lr": 4.914004914004914e-07, "epoch": 0.00491460867428431, "percentage": 0.1, "elapsed_time": "0:05:04", "remaining_time": "3 days, 14:00:24"}
3
+ {"current_steps": 30, "total_steps": 20345, "loss": 0.8047, "lr": 7.371007371007371e-07, "epoch": 0.007371913011426466, "percentage": 0.15, "elapsed_time": "0:07:16", "remaining_time": "3 days, 10:01:11"}
4
+ {"current_steps": 40, "total_steps": 20345, "loss": 0.8048, "lr": 9.828009828009828e-07, "epoch": 0.00982921734856862, "percentage": 0.2, "elapsed_time": "0:09:22", "remaining_time": "3 days, 7:20:37"}
5
+ {"current_steps": 50, "total_steps": 20345, "loss": 0.8198, "lr": 1.2285012285012285e-06, "epoch": 0.012286521685710775, "percentage": 0.25, "elapsed_time": "0:11:26", "remaining_time": "3 days, 5:23:20"}
6
+ {"current_steps": 60, "total_steps": 20345, "loss": 0.8171, "lr": 1.4742014742014743e-06, "epoch": 0.014743826022852931, "percentage": 0.29, "elapsed_time": "0:13:50", "remaining_time": "3 days, 5:59:36"}
7
+ {"current_steps": 70, "total_steps": 20345, "loss": 0.8231, "lr": 1.71990171990172e-06, "epoch": 0.017201130359995084, "percentage": 0.34, "elapsed_time": "0:16:32", "remaining_time": "3 days, 7:53:10"}
8
+ {"current_steps": 80, "total_steps": 20345, "loss": 0.8332, "lr": 1.9656019656019657e-06, "epoch": 0.01965843469713724, "percentage": 0.39, "elapsed_time": "0:18:43", "remaining_time": "3 days, 7:03:21"}
9
+ {"current_steps": 90, "total_steps": 20345, "loss": 0.833, "lr": 2.211302211302211e-06, "epoch": 0.022115739034279394, "percentage": 0.44, "elapsed_time": "0:21:08", "remaining_time": "3 days, 7:18:36"}
10
+ {"current_steps": 100, "total_steps": 20345, "loss": 0.7927, "lr": 2.457002457002457e-06, "epoch": 0.02457304337142155, "percentage": 0.49, "elapsed_time": "0:23:18", "remaining_time": "3 days, 6:39:44"}
11
+ {"current_steps": 110, "total_steps": 20345, "loss": 0.7942, "lr": 2.702702702702703e-06, "epoch": 0.027030347708563704, "percentage": 0.54, "elapsed_time": "0:25:40", "remaining_time": "3 days, 6:41:35"}
12
+ {"current_steps": 120, "total_steps": 20345, "loss": 0.7577, "lr": 2.9484029484029485e-06, "epoch": 0.029487652045705862, "percentage": 0.59, "elapsed_time": "0:27:57", "remaining_time": "3 days, 6:31:45"}
13
+ {"current_steps": 130, "total_steps": 20345, "loss": 0.7732, "lr": 3.1941031941031944e-06, "epoch": 0.031944956382848014, "percentage": 0.64, "elapsed_time": "0:30:13", "remaining_time": "3 days, 6:19:56"}
14
+ {"current_steps": 140, "total_steps": 20345, "loss": 0.7794, "lr": 3.43980343980344e-06, "epoch": 0.03440226071999017, "percentage": 0.69, "elapsed_time": "0:32:41", "remaining_time": "3 days, 6:38:28"}
15
+ {"current_steps": 150, "total_steps": 20345, "loss": 0.7623, "lr": 3.6855036855036854e-06, "epoch": 0.036859565057132324, "percentage": 0.74, "elapsed_time": "0:35:11", "remaining_time": "3 days, 6:57:30"}
16
+ {"current_steps": 160, "total_steps": 20345, "loss": 0.7475, "lr": 3.931203931203931e-06, "epoch": 0.03931686939427448, "percentage": 0.79, "elapsed_time": "0:37:21", "remaining_time": "3 days, 6:32:55"}
17
+ {"current_steps": 170, "total_steps": 20345, "loss": 0.7583, "lr": 4.176904176904177e-06, "epoch": 0.04177417373141663, "percentage": 0.84, "elapsed_time": "0:39:30", "remaining_time": "3 days, 6:08:29"}
18
+ {"current_steps": 180, "total_steps": 20345, "loss": 0.7474, "lr": 4.422604422604422e-06, "epoch": 0.04423147806855879, "percentage": 0.88, "elapsed_time": "0:41:37", "remaining_time": "3 days, 5:43:17"}
19
+ {"current_steps": 190, "total_steps": 20345, "loss": 0.7265, "lr": 4.668304668304669e-06, "epoch": 0.04668878240570094, "percentage": 0.93, "elapsed_time": "0:44:09", "remaining_time": "3 days, 6:05:08"}
20
+ {"current_steps": 200, "total_steps": 20345, "loss": 0.7057, "lr": 4.914004914004914e-06, "epoch": 0.0491460867428431, "percentage": 0.98, "elapsed_time": "0:46:29", "remaining_time": "3 days, 6:03:39"}
21
+ {"current_steps": 210, "total_steps": 20345, "loss": 0.7071, "lr": 5.15970515970516e-06, "epoch": 0.05160339107998525, "percentage": 1.03, "elapsed_time": "0:48:48", "remaining_time": "3 days, 5:59:11"}
22
+ {"current_steps": 220, "total_steps": 20345, "loss": 0.7307, "lr": 5.405405405405406e-06, "epoch": 0.05406069541712741, "percentage": 1.08, "elapsed_time": "0:51:10", "remaining_time": "3 days, 6:01:29"}
23
+ {"current_steps": 230, "total_steps": 20345, "loss": 0.725, "lr": 5.6511056511056515e-06, "epoch": 0.05651799975426957, "percentage": 1.13, "elapsed_time": "0:53:27", "remaining_time": "3 days, 5:55:34"}
24
+ {"current_steps": 240, "total_steps": 20345, "loss": 0.7124, "lr": 5.896805896805897e-06, "epoch": 0.058975304091411725, "percentage": 1.18, "elapsed_time": "0:55:38", "remaining_time": "3 days, 5:41:06"}
25
+ {"current_steps": 250, "total_steps": 20345, "loss": 0.7205, "lr": 6.142506142506143e-06, "epoch": 0.06143260842855388, "percentage": 1.23, "elapsed_time": "0:57:41", "remaining_time": "3 days, 5:16:59"}
26
+ {"current_steps": 260, "total_steps": 20345, "loss": 0.6764, "lr": 6.388206388206389e-06, "epoch": 0.06388991276569603, "percentage": 1.28, "elapsed_time": "0:59:59", "remaining_time": "3 days, 5:14:24"}
27
+ {"current_steps": 270, "total_steps": 20345, "loss": 0.6853, "lr": 6.6339066339066335e-06, "epoch": 0.06634721710283818, "percentage": 1.33, "elapsed_time": "1:02:11", "remaining_time": "3 days, 5:03:57"}
28
+ {"current_steps": 280, "total_steps": 20345, "loss": 0.6694, "lr": 6.87960687960688e-06, "epoch": 0.06880452143998034, "percentage": 1.38, "elapsed_time": "1:04:21", "remaining_time": "3 days, 4:52:12"}
29
+ {"current_steps": 290, "total_steps": 20345, "loss": 0.6724, "lr": 7.125307125307126e-06, "epoch": 0.07126182577712249, "percentage": 1.43, "elapsed_time": "1:06:21", "remaining_time": "3 days, 4:28:40"}
30
+ {"current_steps": 300, "total_steps": 20345, "loss": 0.6687, "lr": 7.371007371007371e-06, "epoch": 0.07371913011426465, "percentage": 1.47, "elapsed_time": "1:08:48", "remaining_time": "3 days, 4:37:03"}
31
+ {"current_steps": 310, "total_steps": 20345, "loss": 0.6677, "lr": 7.616707616707617e-06, "epoch": 0.0761764344514068, "percentage": 1.52, "elapsed_time": "1:10:58", "remaining_time": "3 days, 4:26:37"}
32
+ {"current_steps": 320, "total_steps": 20345, "loss": 0.6807, "lr": 7.862407862407863e-06, "epoch": 0.07863373878854896, "percentage": 1.57, "elapsed_time": "1:13:09", "remaining_time": "3 days, 4:17:54"}
33
+ {"current_steps": 330, "total_steps": 20345, "loss": 0.6663, "lr": 8.108108108108109e-06, "epoch": 0.08109104312569111, "percentage": 1.62, "elapsed_time": "1:15:14", "remaining_time": "3 days, 4:03:54"}
34
+ {"current_steps": 340, "total_steps": 20345, "loss": 0.6705, "lr": 8.353808353808354e-06, "epoch": 0.08354834746283327, "percentage": 1.67, "elapsed_time": "1:17:49", "remaining_time": "3 days, 4:19:06"}
35
+ {"current_steps": 350, "total_steps": 20345, "loss": 0.6684, "lr": 8.5995085995086e-06, "epoch": 0.08600565179997542, "percentage": 1.72, "elapsed_time": "1:20:17", "remaining_time": "3 days, 4:27:17"}
36
+ {"current_steps": 360, "total_steps": 20345, "loss": 0.6561, "lr": 8.845208845208845e-06, "epoch": 0.08846295613711758, "percentage": 1.77, "elapsed_time": "1:22:36", "remaining_time": "3 days, 4:25:51"}
37
+ {"current_steps": 370, "total_steps": 20345, "loss": 0.6375, "lr": 9.090909090909091e-06, "epoch": 0.09092026047425973, "percentage": 1.82, "elapsed_time": "1:24:47", "remaining_time": "3 days, 4:17:36"}
38
+ {"current_steps": 380, "total_steps": 20345, "loss": 0.6477, "lr": 9.336609336609337e-06, "epoch": 0.09337756481140189, "percentage": 1.87, "elapsed_time": "1:27:04", "remaining_time": "3 days, 4:14:39"}
39
+ {"current_steps": 390, "total_steps": 20345, "loss": 0.6351, "lr": 9.582309582309584e-06, "epoch": 0.09583486914854404, "percentage": 1.92, "elapsed_time": "1:29:44", "remaining_time": "3 days, 4:31:28"}
40
+ {"current_steps": 400, "total_steps": 20345, "loss": 0.6134, "lr": 9.828009828009828e-06, "epoch": 0.0982921734856862, "percentage": 1.97, "elapsed_time": "1:31:53", "remaining_time": "3 days, 4:21:31"}
41
+ {"current_steps": 410, "total_steps": 20345, "loss": 0.595, "lr": 1.0073710073710075e-05, "epoch": 0.10074947782282835, "percentage": 2.02, "elapsed_time": "1:34:07", "remaining_time": "3 days, 4:16:22"}
42
+ {"current_steps": 420, "total_steps": 20345, "loss": 0.6392, "lr": 1.031941031941032e-05, "epoch": 0.1032067821599705, "percentage": 2.06, "elapsed_time": "1:36:32", "remaining_time": "3 days, 4:20:06"}
43
+ {"current_steps": 430, "total_steps": 20345, "loss": 0.6015, "lr": 1.0565110565110566e-05, "epoch": 0.10566408649711266, "percentage": 2.11, "elapsed_time": "1:38:48", "remaining_time": "3 days, 4:15:51"}
44
+ {"current_steps": 440, "total_steps": 20345, "loss": 0.6229, "lr": 1.0810810810810812e-05, "epoch": 0.10812139083425482, "percentage": 2.16, "elapsed_time": "1:41:09", "remaining_time": "3 days, 4:16:06"}
45
+ {"current_steps": 450, "total_steps": 20345, "loss": 0.6237, "lr": 1.1056511056511057e-05, "epoch": 0.11057869517139697, "percentage": 2.21, "elapsed_time": "1:43:24", "remaining_time": "3 days, 4:11:59"}
46
+ {"current_steps": 460, "total_steps": 20345, "loss": 0.5975, "lr": 1.1302211302211303e-05, "epoch": 0.11303599950853914, "percentage": 2.26, "elapsed_time": "1:45:50", "remaining_time": "3 days, 4:15:19"}
47
+ {"current_steps": 470, "total_steps": 20345, "loss": 0.6081, "lr": 1.1547911547911548e-05, "epoch": 0.1154933038456813, "percentage": 2.31, "elapsed_time": "1:48:03", "remaining_time": "3 days, 4:09:28"}
48
+ {"current_steps": 480, "total_steps": 20345, "loss": 0.6182, "lr": 1.1793611793611794e-05, "epoch": 0.11795060818282345, "percentage": 2.36, "elapsed_time": "1:50:19", "remaining_time": "3 days, 4:05:38"}
49
+ {"current_steps": 490, "total_steps": 20345, "loss": 0.6193, "lr": 1.2039312039312039e-05, "epoch": 0.1204079125199656, "percentage": 2.41, "elapsed_time": "1:52:47", "remaining_time": "3 days, 4:10:21"}
50
+ {"current_steps": 500, "total_steps": 20345, "loss": 0.5726, "lr": 1.2285012285012287e-05, "epoch": 0.12286521685710776, "percentage": 2.46, "elapsed_time": "1:54:56", "remaining_time": "3 days, 4:02:02"}
51
+ {"current_steps": 510, "total_steps": 20345, "loss": 0.6096, "lr": 1.2530712530712533e-05, "epoch": 0.12532252119424991, "percentage": 2.51, "elapsed_time": "1:57:15", "remaining_time": "3 days, 4:00:10"}
52
+ {"current_steps": 520, "total_steps": 20345, "loss": 0.5902, "lr": 1.2776412776412778e-05, "epoch": 0.12777982553139206, "percentage": 2.56, "elapsed_time": "1:59:32", "remaining_time": "3 days, 3:57:39"}
53
+ {"current_steps": 530, "total_steps": 20345, "loss": 0.6, "lr": 1.3022113022113022e-05, "epoch": 0.13023712986853422, "percentage": 2.61, "elapsed_time": "2:01:37", "remaining_time": "3 days, 3:47:03"}
54
+ {"current_steps": 540, "total_steps": 20345, "loss": 0.6042, "lr": 1.3267813267813267e-05, "epoch": 0.13269443420567636, "percentage": 2.65, "elapsed_time": "2:03:43", "remaining_time": "3 days, 3:37:53"}
55
+ {"current_steps": 550, "total_steps": 20345, "loss": 0.5922, "lr": 1.3513513513513515e-05, "epoch": 0.13515173854281853, "percentage": 2.7, "elapsed_time": "2:05:53", "remaining_time": "3 days, 3:31:00"}
56
+ {"current_steps": 560, "total_steps": 20345, "loss": 0.6025, "lr": 1.375921375921376e-05, "epoch": 0.13760904287996067, "percentage": 2.75, "elapsed_time": "2:08:03", "remaining_time": "3 days, 3:24:32"}
57
+ {"current_steps": 570, "total_steps": 20345, "loss": 0.5768, "lr": 1.4004914004914004e-05, "epoch": 0.14006634721710284, "percentage": 2.8, "elapsed_time": "2:10:32", "remaining_time": "3 days, 3:29:08"}
58
+ {"current_steps": 580, "total_steps": 20345, "loss": 0.5993, "lr": 1.4250614250614252e-05, "epoch": 0.14252365155424498, "percentage": 2.85, "elapsed_time": "2:12:52", "remaining_time": "3 days, 3:27:54"}
59
+ {"current_steps": 590, "total_steps": 20345, "loss": 0.5776, "lr": 1.4496314496314497e-05, "epoch": 0.14498095589138715, "percentage": 2.9, "elapsed_time": "2:15:11", "remaining_time": "3 days, 3:26:24"}
60
+ {"current_steps": 600, "total_steps": 20345, "loss": 0.5651, "lr": 1.4742014742014742e-05, "epoch": 0.1474382602285293, "percentage": 2.95, "elapsed_time": "2:17:08", "remaining_time": "3 days, 3:12:52"}
61
+ {"current_steps": 610, "total_steps": 20345, "loss": 0.5595, "lr": 1.4987714987714988e-05, "epoch": 0.14989556456567146, "percentage": 3.0, "elapsed_time": "2:19:23", "remaining_time": "3 days, 3:09:39"}
62
+ {"current_steps": 620, "total_steps": 20345, "loss": 0.5706, "lr": 1.5233415233415234e-05, "epoch": 0.1523528689028136, "percentage": 3.05, "elapsed_time": "2:21:55", "remaining_time": "3 days, 3:15:30"}
63
+ {"current_steps": 630, "total_steps": 20345, "loss": 0.5755, "lr": 1.547911547911548e-05, "epoch": 0.15481017323995577, "percentage": 3.1, "elapsed_time": "2:24:26", "remaining_time": "3 days, 3:20:11"}
64
+ {"current_steps": 640, "total_steps": 20345, "loss": 0.567, "lr": 1.5724815724815725e-05, "epoch": 0.1572674775770979, "percentage": 3.15, "elapsed_time": "2:26:26", "remaining_time": "3 days, 3:08:41"}
65
+ {"current_steps": 650, "total_steps": 20345, "loss": 0.5725, "lr": 1.5970515970515972e-05, "epoch": 0.15972478191424008, "percentage": 3.19, "elapsed_time": "2:28:34", "remaining_time": "3 days, 3:02:04"}
66
+ {"current_steps": 660, "total_steps": 20345, "loss": 0.5854, "lr": 1.6216216216216218e-05, "epoch": 0.16218208625138222, "percentage": 3.24, "elapsed_time": "2:30:58", "remaining_time": "3 days, 3:02:46"}
67
+ {"current_steps": 670, "total_steps": 20345, "loss": 0.56, "lr": 1.6461916461916464e-05, "epoch": 0.1646393905885244, "percentage": 3.29, "elapsed_time": "2:33:30", "remaining_time": "3 days, 3:07:45"}
68
+ {"current_steps": 680, "total_steps": 20345, "loss": 0.5527, "lr": 1.6707616707616707e-05, "epoch": 0.16709669492566653, "percentage": 3.34, "elapsed_time": "2:35:28", "remaining_time": "3 days, 2:56:16"}
69
+ {"current_steps": 690, "total_steps": 20345, "loss": 0.556, "lr": 1.6953316953316954e-05, "epoch": 0.1695539992628087, "percentage": 3.39, "elapsed_time": "2:38:03", "remaining_time": "3 days, 3:02:16"}
70
+ {"current_steps": 700, "total_steps": 20345, "loss": 0.5704, "lr": 1.71990171990172e-05, "epoch": 0.17201130359995084, "percentage": 3.44, "elapsed_time": "2:40:26", "remaining_time": "3 days, 3:02:41"}
71
+ {"current_steps": 710, "total_steps": 20345, "loss": 0.5654, "lr": 1.7444717444717446e-05, "epoch": 0.174468607937093, "percentage": 3.49, "elapsed_time": "2:42:36", "remaining_time": "3 days, 2:56:54"}
72
+ {"current_steps": 720, "total_steps": 20345, "loss": 0.5626, "lr": 1.769041769041769e-05, "epoch": 0.17692591227423515, "percentage": 3.54, "elapsed_time": "2:44:55", "remaining_time": "3 days, 2:55:18"}
73
+ {"current_steps": 730, "total_steps": 20345, "loss": 0.5479, "lr": 1.793611793611794e-05, "epoch": 0.17938321661137732, "percentage": 3.59, "elapsed_time": "2:46:56", "remaining_time": "3 days, 2:45:46"}
74
+ {"current_steps": 740, "total_steps": 20345, "loss": 0.5548, "lr": 1.8181818181818182e-05, "epoch": 0.18184052094851946, "percentage": 3.64, "elapsed_time": "2:49:06", "remaining_time": "3 days, 2:40:10"}
75
+ {"current_steps": 750, "total_steps": 20345, "loss": 0.5754, "lr": 1.842751842751843e-05, "epoch": 0.18429782528566163, "percentage": 3.69, "elapsed_time": "2:51:00", "remaining_time": "3 days, 2:27:42"}
76
+ {"current_steps": 760, "total_steps": 20345, "loss": 0.5816, "lr": 1.8673218673218675e-05, "epoch": 0.18675512962280377, "percentage": 3.74, "elapsed_time": "2:53:24", "remaining_time": "3 days, 2:28:51"}
77
+ {"current_steps": 770, "total_steps": 20345, "loss": 0.5779, "lr": 1.891891891891892e-05, "epoch": 0.18921243395994594, "percentage": 3.78, "elapsed_time": "2:55:55", "remaining_time": "3 days, 2:32:32"}
78
+ {"current_steps": 780, "total_steps": 20345, "loss": 0.5542, "lr": 1.9164619164619167e-05, "epoch": 0.19166973829708808, "percentage": 3.83, "elapsed_time": "2:58:21", "remaining_time": "3 days, 2:33:58"}
79
+ {"current_steps": 790, "total_steps": 20345, "loss": 0.5568, "lr": 1.941031941031941e-05, "epoch": 0.19412704263423025, "percentage": 3.88, "elapsed_time": "3:00:45", "remaining_time": "3 days, 2:34:19"}
80
+ {"current_steps": 800, "total_steps": 20345, "loss": 0.5604, "lr": 1.9656019656019657e-05, "epoch": 0.1965843469713724, "percentage": 3.93, "elapsed_time": "3:02:53", "remaining_time": "3 days, 2:28:05"}
81
+ {"current_steps": 810, "total_steps": 20345, "loss": 0.5635, "lr": 1.9901719901719903e-05, "epoch": 0.19904165130851456, "percentage": 3.98, "elapsed_time": "3:05:02", "remaining_time": "3 days, 2:22:38"}
82
+ {"current_steps": 820, "total_steps": 20345, "loss": 0.5906, "lr": 2.014742014742015e-05, "epoch": 0.2014989556456567, "percentage": 4.03, "elapsed_time": "3:07:35", "remaining_time": "3 days, 2:26:51"}
83
+ {"current_steps": 830, "total_steps": 20345, "loss": 0.5674, "lr": 2.0393120393120392e-05, "epoch": 0.20395625998279887, "percentage": 4.08, "elapsed_time": "3:10:14", "remaining_time": "3 days, 2:33:06"}
84
+ {"current_steps": 840, "total_steps": 20345, "loss": 0.555, "lr": 2.063882063882064e-05, "epoch": 0.206413564319941, "percentage": 4.13, "elapsed_time": "3:12:28", "remaining_time": "3 days, 2:29:29"}
85
+ {"current_steps": 850, "total_steps": 20345, "loss": 0.5468, "lr": 2.0884520884520885e-05, "epoch": 0.20887086865708318, "percentage": 4.18, "elapsed_time": "3:14:37", "remaining_time": "3 days, 2:23:51"}
86
+ {"current_steps": 860, "total_steps": 20345, "loss": 0.5533, "lr": 2.113022113022113e-05, "epoch": 0.21132817299422532, "percentage": 4.23, "elapsed_time": "3:17:08", "remaining_time": "3 days, 2:26:26"}
87
+ {"current_steps": 870, "total_steps": 20345, "loss": 0.5566, "lr": 2.1375921375921378e-05, "epoch": 0.2137854773313675, "percentage": 4.28, "elapsed_time": "3:19:38", "remaining_time": "3 days, 2:28:56"}
88
+ {"current_steps": 880, "total_steps": 20345, "loss": 0.5609, "lr": 2.1621621621621624e-05, "epoch": 0.21624278166850963, "percentage": 4.33, "elapsed_time": "3:21:45", "remaining_time": "3 days, 2:22:42"}
89
+ {"current_steps": 890, "total_steps": 20345, "loss": 0.5404, "lr": 2.186732186732187e-05, "epoch": 0.2187000860056518, "percentage": 4.37, "elapsed_time": "3:24:09", "remaining_time": "3 days, 2:22:45"}
90
+ {"current_steps": 900, "total_steps": 20345, "loss": 0.5541, "lr": 2.2113022113022113e-05, "epoch": 0.22115739034279394, "percentage": 4.42, "elapsed_time": "3:26:22", "remaining_time": "3 days, 2:18:51"}
91
+ {"current_steps": 910, "total_steps": 20345, "loss": 0.5488, "lr": 2.235872235872236e-05, "epoch": 0.2236146946799361, "percentage": 4.47, "elapsed_time": "3:28:49", "remaining_time": "3 days, 2:19:54"}
92
+ {"current_steps": 920, "total_steps": 20345, "loss": 0.5437, "lr": 2.2604422604422606e-05, "epoch": 0.22607199901707828, "percentage": 4.52, "elapsed_time": "3:30:44", "remaining_time": "3 days, 2:09:32"}
93
+ {"current_steps": 930, "total_steps": 20345, "loss": 0.5543, "lr": 2.2850122850122852e-05, "epoch": 0.22852930335422042, "percentage": 4.57, "elapsed_time": "3:33:09", "remaining_time": "3 days, 2:09:55"}
94
+ {"current_steps": 940, "total_steps": 20345, "loss": 0.5658, "lr": 2.3095823095823095e-05, "epoch": 0.2309866076913626, "percentage": 4.62, "elapsed_time": "3:35:09", "remaining_time": "3 days, 2:01:43"}
95
+ {"current_steps": 950, "total_steps": 20345, "loss": 0.5418, "lr": 2.3341523341523342e-05, "epoch": 0.23344391202850473, "percentage": 4.67, "elapsed_time": "3:37:38", "remaining_time": "3 days, 2:03:23"}
96
+ {"current_steps": 960, "total_steps": 20345, "loss": 0.5355, "lr": 2.3587223587223588e-05, "epoch": 0.2359012163656469, "percentage": 4.72, "elapsed_time": "3:39:51", "remaining_time": "3 days, 1:59:40"}
97
+ {"current_steps": 970, "total_steps": 20345, "loss": 0.5445, "lr": 2.3832923832923834e-05, "epoch": 0.23835852070278904, "percentage": 4.77, "elapsed_time": "3:42:06", "remaining_time": "3 days, 1:56:28"}
98
+ {"current_steps": 980, "total_steps": 20345, "loss": 0.5619, "lr": 2.4078624078624077e-05, "epoch": 0.2408158250399312, "percentage": 4.82, "elapsed_time": "3:44:38", "remaining_time": "3 days, 1:58:51"}
99
+ {"current_steps": 990, "total_steps": 20345, "loss": 0.5642, "lr": 2.4324324324324327e-05, "epoch": 0.24327312937707335, "percentage": 4.87, "elapsed_time": "3:46:50", "remaining_time": "3 days, 1:54:48"}
100
+ {"current_steps": 1000, "total_steps": 20345, "loss": 0.5453, "lr": 2.4570024570024573e-05, "epoch": 0.24573043371421552, "percentage": 4.92, "elapsed_time": "3:49:28", "remaining_time": "3 days, 1:59:16"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe309d438c28b0303ca38f6e8630a94efd0337dc6160c65304806b7eac02bb0
3
+ size 7672
vocab.json ADDED
The diff for this file is too large to render. See raw diff