Incomple commited on
Commit
cd55f3f
·
verified ·
1 Parent(s): e965508

Training in progress, epoch 0

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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "sail/Sailor2-8B-Chat",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "k_proj",
28
+ "o_proj",
29
+ "up_proj",
30
+ "gate_proj",
31
+ "v_proj",
32
+ "q_proj",
33
+ "down_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524206697a60d43cfd8701ba585ea17f0fdb4a6012ef9863937ec06647e08b96
3
+ size 92333848
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 sha256:82bf42f9364aa867b8c9b839e53c829979092b99b8fab5e8dc932d83f965e815
3
+ size 11421995
tokenizer_config.json ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are an AI assistant named Sailor2, created by Sea AI Lab. As an AI assistant, you can answer questions in English, Chinese, and Southeast Asian languages such as Burmese, Cebuano, Ilocano, Indonesian, Javanese, Khmer, Lao, Malay, Sundanese, Tagalog, Thai, Vietnamese, and Waray. Your responses should be friendly, unbiased, informative, detailed, and faithful.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "max_length": 3848,
204
+ "model_max_length": 131072,
205
+ "pad_token": "<|endoftext|>",
206
+ "padding_side": "right",
207
+ "split_special_tokens": false,
208
+ "stride": 0,
209
+ "tokenizer_class": "Qwen2Tokenizer",
210
+ "truncation_side": "right",
211
+ "truncation_strategy": "longest_first",
212
+ "unk_token": null
213
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 67, "total_steps": 1337, "loss": 2.0415, "lr": 4.925373134328357e-07, "epoch": 0.05009345794392523, "percentage": 5.01, "elapsed_time": "0:01:36", "remaining_time": "0:30:33"}
2
+ {"current_steps": 134, "total_steps": 1337, "loss": 1.5231, "lr": 9.925373134328357e-07, "epoch": 0.10018691588785046, "percentage": 10.02, "elapsed_time": "0:03:15", "remaining_time": "0:29:19"}
3
+ {"current_steps": 201, "total_steps": 1337, "loss": 0.4422, "lr": 9.451371571072319e-07, "epoch": 0.1502803738317757, "percentage": 15.03, "elapsed_time": "0:04:53", "remaining_time": "0:27:39"}
4
+ {"current_steps": 250, "total_steps": 1337, "eval_loss": 0.26753509044647217, "epoch": 0.18691588785046728, "percentage": 18.7, "elapsed_time": "0:06:34", "remaining_time": "0:28:36"}
5
+ {"current_steps": 268, "total_steps": 1337, "loss": 0.2826, "lr": 8.894430590191188e-07, "epoch": 0.20037383177570092, "percentage": 20.04, "elapsed_time": "0:07:00", "remaining_time": "0:27:56"}
6
+ {"current_steps": 335, "total_steps": 1337, "loss": 0.2107, "lr": 8.337489609310058e-07, "epoch": 0.2504672897196262, "percentage": 25.06, "elapsed_time": "0:08:38", "remaining_time": "0:25:50"}
7
+ {"current_steps": 402, "total_steps": 1337, "loss": 0.1864, "lr": 7.780548628428927e-07, "epoch": 0.3005607476635514, "percentage": 30.07, "elapsed_time": "0:10:16", "remaining_time": "0:23:53"}
8
+ {"current_steps": 469, "total_steps": 1337, "loss": 0.1727, "lr": 7.223607647547797e-07, "epoch": 0.3506542056074766, "percentage": 35.08, "elapsed_time": "0:11:54", "remaining_time": "0:22:02"}
9
+ {"current_steps": 500, "total_steps": 1337, "eval_loss": 0.16795502603054047, "epoch": 0.37383177570093457, "percentage": 37.4, "elapsed_time": "0:13:08", "remaining_time": "0:22:00"}
10
+ {"current_steps": 536, "total_steps": 1337, "loss": 0.1551, "lr": 6.666666666666666e-07, "epoch": 0.40074766355140184, "percentage": 40.09, "elapsed_time": "0:14:00", "remaining_time": "0:20:55"}
11
+ {"current_steps": 603, "total_steps": 1337, "loss": 0.148, "lr": 6.109725685785536e-07, "epoch": 0.4508411214953271, "percentage": 45.1, "elapsed_time": "0:15:36", "remaining_time": "0:19:00"}
12
+ {"current_steps": 670, "total_steps": 1337, "loss": 0.1521, "lr": 5.552784704904405e-07, "epoch": 0.5009345794392523, "percentage": 50.11, "elapsed_time": "0:17:13", "remaining_time": "0:17:09"}
13
+ {"current_steps": 737, "total_steps": 1337, "loss": 0.1475, "lr": 4.995843724023275e-07, "epoch": 0.5510280373831775, "percentage": 55.12, "elapsed_time": "0:18:51", "remaining_time": "0:15:21"}
14
+ {"current_steps": 750, "total_steps": 1337, "eval_loss": 0.14567767083644867, "epoch": 0.5607476635514018, "percentage": 56.1, "elapsed_time": "0:19:40", "remaining_time": "0:15:23"}
15
+ {"current_steps": 804, "total_steps": 1337, "loss": 0.1327, "lr": 4.438902743142144e-07, "epoch": 0.6011214953271028, "percentage": 60.13, "elapsed_time": "0:20:58", "remaining_time": "0:13:54"}
16
+ {"current_steps": 871, "total_steps": 1337, "loss": 0.1394, "lr": 3.881961762261014e-07, "epoch": 0.6512149532710281, "percentage": 65.15, "elapsed_time": "0:22:37", "remaining_time": "0:12:06"}
17
+ {"current_steps": 938, "total_steps": 1337, "loss": 0.1284, "lr": 3.3250207813798835e-07, "epoch": 0.7013084112149532, "percentage": 70.16, "elapsed_time": "0:24:14", "remaining_time": "0:10:18"}
18
+ {"current_steps": 1000, "total_steps": 1337, "eval_loss": 0.13731907308101654, "epoch": 0.7476635514018691, "percentage": 74.79, "elapsed_time": "0:26:15", "remaining_time": "0:08:50"}
19
+ {"current_steps": 1005, "total_steps": 1337, "loss": 0.1065, "lr": 2.7680798004987534e-07, "epoch": 0.7514018691588785, "percentage": 75.17, "elapsed_time": "0:26:21", "remaining_time": "0:08:42"}
20
+ {"current_steps": 1072, "total_steps": 1337, "loss": 0.1167, "lr": 2.2111388196176226e-07, "epoch": 0.8014953271028037, "percentage": 80.18, "elapsed_time": "0:27:58", "remaining_time": "0:06:54"}
21
+ {"current_steps": 1139, "total_steps": 1337, "loss": 0.1278, "lr": 1.6541978387364923e-07, "epoch": 0.851588785046729, "percentage": 85.19, "elapsed_time": "0:29:35", "remaining_time": "0:05:08"}
22
+ {"current_steps": 1206, "total_steps": 1337, "loss": 0.1066, "lr": 1.0972568578553615e-07, "epoch": 0.9016822429906542, "percentage": 90.2, "elapsed_time": "0:31:11", "remaining_time": "0:03:23"}
23
+ {"current_steps": 1250, "total_steps": 1337, "eval_loss": 0.13475529849529266, "epoch": 0.9345794392523364, "percentage": 93.49, "elapsed_time": "0:32:45", "remaining_time": "0:02:16"}
24
+ {"current_steps": 1273, "total_steps": 1337, "loss": 0.108, "lr": 5.403158769742311e-08, "epoch": 0.9517757009345794, "percentage": 95.21, "elapsed_time": "0:33:19", "remaining_time": "0:01:40"}
25
+ {"current_steps": 1337, "total_steps": 1337, "epoch": 0.9996261682242991, "percentage": 100.0, "elapsed_time": "0:34:54", "remaining_time": "0:00:00"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f336a8b48314702dc309dd67b0d8d5956369c5dd8456b7db6d4e42b3d4a91d2a
3
+ size 5688
vocab.json ADDED
The diff for this file is too large to render. See raw diff