Hugging Face's logo

sumuks
/
qwen2.5-72b-utility-evaluator-r128

Safetensors
Model card Files Community
sumuks commited on
Commit
8582945
·
verified ·
1 Parent(s): e07d917

Training in progress, step 500

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 +51 -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/Qwen2.5-72B",
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": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "k_proj",
26
+ "down_proj",
27
+ "o_proj",
28
+ "q_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": true
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a51a4b4bb16b47c962bc104cfacda7510d0eedc226edd0475b52b5583e2fdba
3
+ size 3368705968
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": "<|endoftext|>",
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 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 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": "<|endoftext|>",
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 4974, "loss": 1.6618, "lr": 1.0040160642570282e-06, "epoch": 0.006028181749679753, "percentage": 0.2, "elapsed_time": "0:04:24", "remaining_time": "1 day, 12:25:17"}
2
+ {"current_steps": 20, "total_steps": 4974, "loss": 1.6698, "lr": 2.0080321285140564e-06, "epoch": 0.012056363499359506, "percentage": 0.4, "elapsed_time": "0:08:28", "remaining_time": "1 day, 11:00:39"}
3
+ {"current_steps": 30, "total_steps": 4974, "loss": 1.6264, "lr": 3.0120481927710846e-06, "epoch": 0.01808454524903926, "percentage": 0.6, "elapsed_time": "0:12:33", "remaining_time": "1 day, 10:28:29"}
4
+ {"current_steps": 40, "total_steps": 4974, "loss": 1.6025, "lr": 4.016064257028113e-06, "epoch": 0.02411272699871901, "percentage": 0.8, "elapsed_time": "0:16:39", "remaining_time": "1 day, 10:15:14"}
5
+ {"current_steps": 50, "total_steps": 4974, "loss": 1.5584, "lr": 5.020080321285141e-06, "epoch": 0.030140908748398764, "percentage": 1.01, "elapsed_time": "0:20:43", "remaining_time": "1 day, 10:01:40"}
6
+ {"current_steps": 60, "total_steps": 4974, "loss": 1.5604, "lr": 6.024096385542169e-06, "epoch": 0.03616909049807852, "percentage": 1.21, "elapsed_time": "0:24:48", "remaining_time": "1 day, 9:51:27"}
7
+ {"current_steps": 70, "total_steps": 4974, "loss": 1.5057, "lr": 7.028112449799197e-06, "epoch": 0.04219727224775827, "percentage": 1.41, "elapsed_time": "0:28:54", "remaining_time": "1 day, 9:45:25"}
8
+ {"current_steps": 80, "total_steps": 4974, "loss": 1.4724, "lr": 8.032128514056226e-06, "epoch": 0.04822545399743802, "percentage": 1.61, "elapsed_time": "0:32:58", "remaining_time": "1 day, 9:36:47"}
9
+ {"current_steps": 90, "total_steps": 4974, "loss": 1.4962, "lr": 9.036144578313253e-06, "epoch": 0.05425363574711778, "percentage": 1.81, "elapsed_time": "0:37:01", "remaining_time": "1 day, 9:29:35"}
10
+ {"current_steps": 100, "total_steps": 4974, "loss": 1.4765, "lr": 1.0040160642570281e-05, "epoch": 0.06028181749679753, "percentage": 2.01, "elapsed_time": "0:41:07", "remaining_time": "1 day, 9:24:15"}
11
+ {"current_steps": 110, "total_steps": 4974, "loss": 1.4468, "lr": 1.104417670682731e-05, "epoch": 0.06630999924647728, "percentage": 2.21, "elapsed_time": "0:45:10", "remaining_time": "1 day, 9:17:54"}
12
+ {"current_steps": 120, "total_steps": 4974, "loss": 1.4134, "lr": 1.2048192771084338e-05, "epoch": 0.07233818099615703, "percentage": 2.41, "elapsed_time": "0:49:15", "remaining_time": "1 day, 9:12:12"}
13
+ {"current_steps": 130, "total_steps": 4974, "loss": 1.4191, "lr": 1.3052208835341367e-05, "epoch": 0.07836636274583679, "percentage": 2.61, "elapsed_time": "0:53:20", "remaining_time": "1 day, 9:07:19"}
14
+ {"current_steps": 140, "total_steps": 4974, "loss": 1.397, "lr": 1.4056224899598394e-05, "epoch": 0.08439454449551655, "percentage": 2.81, "elapsed_time": "0:57:23", "remaining_time": "1 day, 9:01:46"}
15
+ {"current_steps": 150, "total_steps": 4974, "loss": 1.3818, "lr": 1.5060240963855424e-05, "epoch": 0.09042272624519629, "percentage": 3.02, "elapsed_time": "1:01:28", "remaining_time": "1 day, 8:57:10"}
16
+ {"current_steps": 160, "total_steps": 4974, "loss": 1.4002, "lr": 1.606425702811245e-05, "epoch": 0.09645090799487605, "percentage": 3.22, "elapsed_time": "1:05:33", "remaining_time": "1 day, 8:52:20"}
17
+ {"current_steps": 170, "total_steps": 4974, "loss": 1.4123, "lr": 1.706827309236948e-05, "epoch": 0.1024790897445558, "percentage": 3.42, "elapsed_time": "1:09:36", "remaining_time": "1 day, 8:47:05"}
18
+ {"current_steps": 180, "total_steps": 4974, "loss": 1.4016, "lr": 1.8072289156626505e-05, "epoch": 0.10850727149423556, "percentage": 3.62, "elapsed_time": "1:13:43", "remaining_time": "1 day, 8:43:19"}
19
+ {"current_steps": 190, "total_steps": 4974, "loss": 1.404, "lr": 1.9076305220883535e-05, "epoch": 0.1145354532439153, "percentage": 3.82, "elapsed_time": "1:17:47", "remaining_time": "1 day, 8:38:48"}
20
+ {"current_steps": 200, "total_steps": 4974, "loss": 1.4019, "lr": 2.0080321285140562e-05, "epoch": 0.12056363499359506, "percentage": 4.02, "elapsed_time": "1:21:51", "remaining_time": "1 day, 8:33:57"}
21
+ {"current_steps": 210, "total_steps": 4974, "loss": 1.393, "lr": 2.1084337349397593e-05, "epoch": 0.1265918167432748, "percentage": 4.22, "elapsed_time": "1:25:56", "remaining_time": "1 day, 8:29:46"}
22
+ {"current_steps": 220, "total_steps": 4974, "loss": 1.3876, "lr": 2.208835341365462e-05, "epoch": 0.13261999849295456, "percentage": 4.42, "elapsed_time": "1:30:00", "remaining_time": "1 day, 8:25:09"}
23
+ {"current_steps": 230, "total_steps": 4974, "loss": 1.3916, "lr": 2.309236947791165e-05, "epoch": 0.1386481802426343, "percentage": 4.62, "elapsed_time": "1:34:04", "remaining_time": "1 day, 8:20:13"}
24
+ {"current_steps": 240, "total_steps": 4974, "loss": 1.4056, "lr": 2.4096385542168677e-05, "epoch": 0.14467636199231407, "percentage": 4.83, "elapsed_time": "1:38:09", "remaining_time": "1 day, 8:16:01"}
25
+ {"current_steps": 250, "total_steps": 4974, "loss": 1.3935, "lr": 2.5100401606425704e-05, "epoch": 0.15070454374199382, "percentage": 5.03, "elapsed_time": "1:42:13", "remaining_time": "1 day, 8:11:30"}
26
+ {"current_steps": 260, "total_steps": 4974, "loss": 1.3826, "lr": 2.6104417670682734e-05, "epoch": 0.15673272549167358, "percentage": 5.23, "elapsed_time": "1:46:16", "remaining_time": "1 day, 8:06:54"}
27
+ {"current_steps": 270, "total_steps": 4974, "loss": 1.3999, "lr": 2.7108433734939758e-05, "epoch": 0.16276090724135334, "percentage": 5.43, "elapsed_time": "1:50:21", "remaining_time": "1 day, 8:02:36"}
28
+ {"current_steps": 280, "total_steps": 4974, "loss": 1.4047, "lr": 2.8112449799196788e-05, "epoch": 0.1687890889910331, "percentage": 5.63, "elapsed_time": "1:54:24", "remaining_time": "1 day, 7:57:58"}
29
+ {"current_steps": 290, "total_steps": 4974, "loss": 1.3935, "lr": 2.911646586345382e-05, "epoch": 0.17481727074071282, "percentage": 5.83, "elapsed_time": "1:58:28", "remaining_time": "1 day, 7:53:42"}
30
+ {"current_steps": 300, "total_steps": 4974, "loss": 1.3736, "lr": 3.012048192771085e-05, "epoch": 0.18084545249039258, "percentage": 6.03, "elapsed_time": "2:02:33", "remaining_time": "1 day, 7:49:24"}
31
+ {"current_steps": 310, "total_steps": 4974, "loss": 1.3927, "lr": 3.112449799196787e-05, "epoch": 0.18687363424007233, "percentage": 6.23, "elapsed_time": "2:06:36", "remaining_time": "1 day, 7:44:53"}
32
+ {"current_steps": 320, "total_steps": 4974, "loss": 1.3636, "lr": 3.21285140562249e-05, "epoch": 0.1929018159897521, "percentage": 6.43, "elapsed_time": "2:10:41", "remaining_time": "1 day, 7:40:43"}
33
+ {"current_steps": 330, "total_steps": 4974, "loss": 1.3892, "lr": 3.313253012048193e-05, "epoch": 0.19892999773943185, "percentage": 6.63, "elapsed_time": "2:14:46", "remaining_time": "1 day, 7:36:33"}
34
+ {"current_steps": 340, "total_steps": 4974, "loss": 1.3756, "lr": 3.413654618473896e-05, "epoch": 0.2049581794891116, "percentage": 6.84, "elapsed_time": "2:18:49", "remaining_time": "1 day, 7:32:10"}
35
+ {"current_steps": 350, "total_steps": 4974, "loss": 1.3935, "lr": 3.5140562248995983e-05, "epoch": 0.21098636123879136, "percentage": 7.04, "elapsed_time": "2:22:55", "remaining_time": "1 day, 7:28:10"}
36
+ {"current_steps": 360, "total_steps": 4974, "loss": 1.3698, "lr": 3.614457831325301e-05, "epoch": 0.21701454298847112, "percentage": 7.24, "elapsed_time": "2:26:59", "remaining_time": "1 day, 7:23:57"}
37
+ {"current_steps": 370, "total_steps": 4974, "loss": 1.3771, "lr": 3.7148594377510044e-05, "epoch": 0.22304272473815084, "percentage": 7.44, "elapsed_time": "2:31:04", "remaining_time": "1 day, 7:19:50"}
38
+ {"current_steps": 380, "total_steps": 4974, "loss": 1.3768, "lr": 3.815261044176707e-05, "epoch": 0.2290709064878306, "percentage": 7.64, "elapsed_time": "2:35:09", "remaining_time": "1 day, 7:15:52"}
39
+ {"current_steps": 390, "total_steps": 4974, "loss": 1.3795, "lr": 3.91566265060241e-05, "epoch": 0.23509908823751036, "percentage": 7.84, "elapsed_time": "2:39:15", "remaining_time": "1 day, 7:11:55"}
40
+ {"current_steps": 400, "total_steps": 4974, "loss": 1.3987, "lr": 4.0160642570281125e-05, "epoch": 0.2411272699871901, "percentage": 8.04, "elapsed_time": "2:43:20", "remaining_time": "1 day, 7:07:47"}
41
+ {"current_steps": 400, "total_steps": 4974, "eval_loss": 1.3548544645309448, "epoch": 0.2411272699871901, "percentage": 8.04, "elapsed_time": "2:45:48", "remaining_time": "1 day, 7:36:02"}
42
+ {"current_steps": 410, "total_steps": 4974, "loss": 1.3886, "lr": 4.116465863453816e-05, "epoch": 0.24715545173686987, "percentage": 8.24, "elapsed_time": "2:49:54", "remaining_time": "1 day, 7:31:19"}
43
+ {"current_steps": 420, "total_steps": 4974, "loss": 1.3645, "lr": 4.2168674698795186e-05, "epoch": 0.2531836334865496, "percentage": 8.44, "elapsed_time": "2:53:57", "remaining_time": "1 day, 7:26:16"}
44
+ {"current_steps": 430, "total_steps": 4974, "loss": 1.3591, "lr": 4.317269076305221e-05, "epoch": 0.2592118152362294, "percentage": 8.64, "elapsed_time": "2:58:01", "remaining_time": "1 day, 7:21:19"}
45
+ {"current_steps": 440, "total_steps": 4974, "loss": 1.3805, "lr": 4.417670682730924e-05, "epoch": 0.2652399969859091, "percentage": 8.85, "elapsed_time": "3:02:07", "remaining_time": "1 day, 7:16:46"}
46
+ {"current_steps": 450, "total_steps": 4974, "loss": 1.3888, "lr": 4.5180722891566266e-05, "epoch": 0.2712681787355889, "percentage": 9.05, "elapsed_time": "3:06:12", "remaining_time": "1 day, 7:12:02"}
47
+ {"current_steps": 460, "total_steps": 4974, "loss": 1.3935, "lr": 4.61847389558233e-05, "epoch": 0.2772963604852686, "percentage": 9.25, "elapsed_time": "3:10:17", "remaining_time": "1 day, 7:07:22"}
48
+ {"current_steps": 470, "total_steps": 4974, "loss": 1.3659, "lr": 4.718875502008032e-05, "epoch": 0.2833245422349484, "percentage": 9.45, "elapsed_time": "3:14:22", "remaining_time": "1 day, 7:02:40"}
49
+ {"current_steps": 480, "total_steps": 4974, "loss": 1.371, "lr": 4.8192771084337354e-05, "epoch": 0.28935272398462814, "percentage": 9.65, "elapsed_time": "3:18:26", "remaining_time": "1 day, 6:57:55"}
50
+ {"current_steps": 490, "total_steps": 4974, "loss": 1.3647, "lr": 4.919678714859438e-05, "epoch": 0.29538090573430786, "percentage": 9.85, "elapsed_time": "3:22:30", "remaining_time": "1 day, 6:53:13"}
51
+ {"current_steps": 500, "total_steps": 4974, "loss": 1.3606, "lr": 4.999997536857586e-05, "epoch": 0.30140908748398765, "percentage": 10.05, "elapsed_time": "3:26:35", "remaining_time": "1 day, 6:48:33"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2923841ae243af669d09fc75f56460b83329158b7b6379ad1b1afd5c369cdb7a
3
+ size 7224
vocab.json ADDED
The diff for this file is too large to render. See raw diff