Hugging Face's logo

SKNahin
/
Qwen2.5-14B-Instruct-Math-Lora-2

Safetensors
Model card Files Community
SKNahin commited on
Commit
ba325e1
•
1 Parent(s): 506cde4

Training in progress, step 50

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +24 -0
  5. merges.txt +0 -0
  6. special_tokens_map.json +31 -0
  7. tokenizer.json +3 -0
  8. tokenizer_config.json +208 -0
  9. trainer_log.jsonl +50 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "k_proj",
25
+ "gate_proj",
26
+ "up_proj",
27
+ "v_proj",
28
+ "q_proj",
29
+ "down_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 sha256:0cdc9a1c82a1b754d361d177d0daa6ec2ddc318a458860285fa253ef3eef6ddd
3
+ size 275342392
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 1625, "loss": 0.5941, "learning_rate": 2.3529411764705884e-05, "epoch": 0.0006153846153846154, "percentage": 0.06, "elapsed_time": "0:00:41", "remaining_time": "18:32:01"}
2
+ {"current_steps": 2, "total_steps": 1625, "loss": 0.6489, "learning_rate": 4.705882352941177e-05, "epoch": 0.0012307692307692308, "percentage": 0.12, "elapsed_time": "0:01:11", "remaining_time": "16:12:48"}
3
+ {"current_steps": 3, "total_steps": 1625, "loss": 0.6197, "learning_rate": 7.058823529411765e-05, "epoch": 0.0018461538461538461, "percentage": 0.18, "elapsed_time": "0:01:40", "remaining_time": "15:08:16"}
4
+ {"current_steps": 4, "total_steps": 1625, "loss": 0.5972, "learning_rate": 9.411764705882353e-05, "epoch": 0.0024615384615384616, "percentage": 0.25, "elapsed_time": "0:02:09", "remaining_time": "14:32:03"}
5
+ {"current_steps": 5, "total_steps": 1625, "loss": 0.574, "learning_rate": 0.00011764705882352942, "epoch": 0.003076923076923077, "percentage": 0.31, "elapsed_time": "0:02:39", "remaining_time": "14:21:16"}
6
+ {"current_steps": 6, "total_steps": 1625, "loss": 0.5362, "learning_rate": 0.0001411764705882353, "epoch": 0.0036923076923076922, "percentage": 0.37, "elapsed_time": "0:03:11", "remaining_time": "14:19:33"}
7
+ {"current_steps": 7, "total_steps": 1625, "loss": 0.4851, "learning_rate": 0.0001647058823529412, "epoch": 0.0043076923076923075, "percentage": 0.43, "elapsed_time": "0:03:40", "remaining_time": "14:08:54"}
8
+ {"current_steps": 8, "total_steps": 1625, "loss": 0.4898, "learning_rate": 0.00018823529411764707, "epoch": 0.004923076923076923, "percentage": 0.49, "elapsed_time": "0:04:09", "remaining_time": "14:01:04"}
9
+ {"current_steps": 9, "total_steps": 1625, "loss": 0.4718, "learning_rate": 0.00021176470588235295, "epoch": 0.005538461538461538, "percentage": 0.55, "elapsed_time": "0:04:40", "remaining_time": "13:58:18"}
10
+ {"current_steps": 10, "total_steps": 1625, "loss": 0.4813, "learning_rate": 0.00023529411764705883, "epoch": 0.006153846153846154, "percentage": 0.62, "elapsed_time": "0:05:13", "remaining_time": "14:03:38"}
11
+ {"current_steps": 11, "total_steps": 1625, "loss": 0.4915, "learning_rate": 0.00025882352941176474, "epoch": 0.00676923076923077, "percentage": 0.68, "elapsed_time": "0:05:42", "remaining_time": "13:57:29"}
12
+ {"current_steps": 12, "total_steps": 1625, "loss": 0.4559, "learning_rate": 0.0002823529411764706, "epoch": 0.0073846153846153844, "percentage": 0.74, "elapsed_time": "0:06:13", "remaining_time": "13:57:07"}
13
+ {"current_steps": 13, "total_steps": 1625, "loss": 0.4628, "learning_rate": 0.00030588235294117644, "epoch": 0.008, "percentage": 0.8, "elapsed_time": "0:06:44", "remaining_time": "13:55:13"}
14
+ {"current_steps": 14, "total_steps": 1625, "loss": 0.4777, "learning_rate": 0.0003294117647058824, "epoch": 0.008615384615384615, "percentage": 0.86, "elapsed_time": "0:07:15", "remaining_time": "13:54:54"}
15
+ {"current_steps": 15, "total_steps": 1625, "loss": 0.4696, "learning_rate": 0.00035294117647058826, "epoch": 0.009230769230769232, "percentage": 0.92, "elapsed_time": "0:07:43", "remaining_time": "13:48:34"}
16
+ {"current_steps": 16, "total_steps": 1625, "loss": 0.4532, "learning_rate": 0.00037647058823529414, "epoch": 0.009846153846153846, "percentage": 0.98, "elapsed_time": "0:08:13", "remaining_time": "13:46:35"}
17
+ {"current_steps": 17, "total_steps": 1625, "loss": 0.4627, "learning_rate": 0.0004, "epoch": 0.010461538461538461, "percentage": 1.05, "elapsed_time": "0:08:40", "remaining_time": "13:40:42"}
18
+ {"current_steps": 18, "total_steps": 1625, "loss": 0.4469, "learning_rate": 0.00039999961829529046, "epoch": 0.011076923076923076, "percentage": 1.11, "elapsed_time": "0:09:12", "remaining_time": "13:41:54"}
19
+ {"current_steps": 19, "total_steps": 1625, "loss": 0.4253, "learning_rate": 0.00039999847318261867, "epoch": 0.011692307692307693, "percentage": 1.17, "elapsed_time": "0:09:40", "remaining_time": "13:38:12"}
20
+ {"current_steps": 20, "total_steps": 1625, "loss": 0.4272, "learning_rate": 0.0003999965646663558, "epoch": 0.012307692307692308, "percentage": 1.23, "elapsed_time": "0:10:13", "remaining_time": "13:40:44"}
21
+ {"current_steps": 21, "total_steps": 1625, "loss": 0.4251, "learning_rate": 0.00039999389275378655, "epoch": 0.012923076923076923, "percentage": 1.29, "elapsed_time": "0:10:43", "remaining_time": "13:39:36"}
22
+ {"current_steps": 22, "total_steps": 1625, "loss": 0.4454, "learning_rate": 0.0003999904574551098, "epoch": 0.01353846153846154, "percentage": 1.35, "elapsed_time": "0:11:11", "remaining_time": "13:35:04"}
23
+ {"current_steps": 23, "total_steps": 1625, "loss": 0.4114, "learning_rate": 0.00039998625878343827, "epoch": 0.014153846153846154, "percentage": 1.42, "elapsed_time": "0:11:42", "remaining_time": "13:35:22"}
24
+ {"current_steps": 24, "total_steps": 1625, "loss": 0.4347, "learning_rate": 0.0003999812967547984, "epoch": 0.014769230769230769, "percentage": 1.48, "elapsed_time": "0:12:18", "remaining_time": "13:41:15"}
25
+ {"current_steps": 25, "total_steps": 1625, "loss": 0.4329, "learning_rate": 0.0003999755713881306, "epoch": 0.015384615384615385, "percentage": 1.54, "elapsed_time": "0:12:49", "remaining_time": "13:40:16"}
26
+ {"current_steps": 26, "total_steps": 1625, "loss": 0.4211, "learning_rate": 0.00039996908270528887, "epoch": 0.016, "percentage": 1.6, "elapsed_time": "0:13:16", "remaining_time": "13:35:59"}
27
+ {"current_steps": 27, "total_steps": 1625, "loss": 0.4187, "learning_rate": 0.0003999618307310407, "epoch": 0.016615384615384615, "percentage": 1.66, "elapsed_time": "0:13:45", "remaining_time": "13:33:51"}
28
+ {"current_steps": 28, "total_steps": 1625, "loss": 0.4073, "learning_rate": 0.0003999538154930673, "epoch": 0.01723076923076923, "percentage": 1.72, "elapsed_time": "0:14:12", "remaining_time": "13:30:42"}
29
+ {"current_steps": 29, "total_steps": 1625, "loss": 0.4093, "learning_rate": 0.0003999450370219632, "epoch": 0.017846153846153845, "percentage": 1.78, "elapsed_time": "0:14:39", "remaining_time": "13:26:51"}
30
+ {"current_steps": 30, "total_steps": 1625, "loss": 0.4134, "learning_rate": 0.00039993549535123624, "epoch": 0.018461538461538463, "percentage": 1.85, "elapsed_time": "0:15:05", "remaining_time": "13:22:09"}
31
+ {"current_steps": 31, "total_steps": 1625, "loss": 0.428, "learning_rate": 0.0003999251905173074, "epoch": 0.019076923076923078, "percentage": 1.91, "elapsed_time": "0:15:32", "remaining_time": "13:19:13"}
32
+ {"current_steps": 32, "total_steps": 1625, "loss": 0.4116, "learning_rate": 0.00039991412255951074, "epoch": 0.019692307692307693, "percentage": 1.97, "elapsed_time": "0:16:03", "remaining_time": "13:19:34"}
33
+ {"current_steps": 33, "total_steps": 1625, "loss": 0.3889, "learning_rate": 0.0003999022915200932, "epoch": 0.020307692307692308, "percentage": 2.03, "elapsed_time": "0:16:31", "remaining_time": "13:17:00"}
34
+ {"current_steps": 34, "total_steps": 1625, "loss": 0.4105, "learning_rate": 0.0003998896974442143, "epoch": 0.020923076923076923, "percentage": 2.09, "elapsed_time": "0:16:59", "remaining_time": "13:15:16"}
35
+ {"current_steps": 35, "total_steps": 1625, "loss": 0.4075, "learning_rate": 0.00039987634037994647, "epoch": 0.021538461538461538, "percentage": 2.15, "elapsed_time": "0:17:27", "remaining_time": "13:13:00"}
36
+ {"current_steps": 36, "total_steps": 1625, "loss": 0.4188, "learning_rate": 0.00039986222037827397, "epoch": 0.022153846153846152, "percentage": 2.22, "elapsed_time": "0:17:59", "remaining_time": "13:14:22"}
37
+ {"current_steps": 37, "total_steps": 1625, "loss": 0.4251, "learning_rate": 0.0003998473374930937, "epoch": 0.02276923076923077, "percentage": 2.28, "elapsed_time": "0:18:32", "remaining_time": "13:15:54"}
38
+ {"current_steps": 38, "total_steps": 1625, "loss": 0.4074, "learning_rate": 0.0003998316917812142, "epoch": 0.023384615384615386, "percentage": 2.34, "elapsed_time": "0:19:01", "remaining_time": "13:14:23"}
39
+ {"current_steps": 39, "total_steps": 1625, "loss": 0.4203, "learning_rate": 0.000399815283302356, "epoch": 0.024, "percentage": 2.4, "elapsed_time": "0:19:28", "remaining_time": "13:12:12"}
40
+ {"current_steps": 40, "total_steps": 1625, "loss": 0.3935, "learning_rate": 0.0003997981121191509, "epoch": 0.024615384615384615, "percentage": 2.46, "elapsed_time": "0:19:53", "remaining_time": "13:08:30"}
41
+ {"current_steps": 41, "total_steps": 1625, "loss": 0.4072, "learning_rate": 0.0003997801782971423, "epoch": 0.02523076923076923, "percentage": 2.52, "elapsed_time": "0:20:21", "remaining_time": "13:06:40"}
42
+ {"current_steps": 42, "total_steps": 1625, "loss": 0.41, "learning_rate": 0.00039976148190478436, "epoch": 0.025846153846153845, "percentage": 2.58, "elapsed_time": "0:20:52", "remaining_time": "13:06:49"}
43
+ {"current_steps": 43, "total_steps": 1625, "loss": 0.4067, "learning_rate": 0.00039974202301344203, "epoch": 0.02646153846153846, "percentage": 2.65, "elapsed_time": "0:21:23", "remaining_time": "13:07:02"}
44
+ {"current_steps": 44, "total_steps": 1625, "loss": 0.4041, "learning_rate": 0.0003997218016973909, "epoch": 0.02707692307692308, "percentage": 2.71, "elapsed_time": "0:21:50", "remaining_time": "13:05:05"}
45
+ {"current_steps": 45, "total_steps": 1625, "loss": 0.433, "learning_rate": 0.0003997008180338166, "epoch": 0.027692307692307693, "percentage": 2.77, "elapsed_time": "0:22:17", "remaining_time": "13:02:26"}
46
+ {"current_steps": 46, "total_steps": 1625, "loss": 0.4096, "learning_rate": 0.00039967907210281483, "epoch": 0.028307692307692308, "percentage": 2.83, "elapsed_time": "0:22:45", "remaining_time": "13:01:24"}
47
+ {"current_steps": 47, "total_steps": 1625, "loss": 0.413, "learning_rate": 0.00039965656398739083, "epoch": 0.028923076923076923, "percentage": 2.89, "elapsed_time": "0:23:16", "remaining_time": "13:01:42"}
48
+ {"current_steps": 48, "total_steps": 1625, "loss": 0.4159, "learning_rate": 0.0003996332937734591, "epoch": 0.029538461538461538, "percentage": 2.95, "elapsed_time": "0:23:47", "remaining_time": "13:01:48"}
49
+ {"current_steps": 49, "total_steps": 1625, "loss": 0.394, "learning_rate": 0.0003996092615498432, "epoch": 0.030153846153846153, "percentage": 3.02, "elapsed_time": "0:24:20", "remaining_time": "13:02:45"}
50
+ {"current_steps": 50, "total_steps": 1625, "loss": 0.4104, "learning_rate": 0.00039958446740827525, "epoch": 0.03076923076923077, "percentage": 3.08, "elapsed_time": "0:24:47", "remaining_time": "13:00:50"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c2a9aa964d521fc61b05b14e3205c612cfe318bdc8f62098f51376ebcbd935d
3
+ size 7096
vocab.json ADDED
The diff for this file is too large to render. See raw diff