jonathanjordan21 commited on
Commit
cfbeb0a
·
verified ·
1 Parent(s): 92752bc

End of training

Browse files
README.md CHANGED
@@ -1,11 +1,12 @@
1
  ---
2
- license: apache-2.0
3
  library_name: peft
 
4
  tags:
5
  - trl
6
  - sft
 
7
  - generated_from_trainer
8
- base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.1
9
  model-index:
10
  - name: outputs
11
  results: []
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # outputs
18
 
19
- This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.1](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.1) on the None dataset.
20
 
21
  ## Model description
22
 
@@ -38,7 +39,7 @@ The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
- - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - num_epochs: 3.0
@@ -46,8 +47,8 @@ The following hyperparameters were used during training:
46
 
47
  ### Framework versions
48
 
49
- - PEFT 0.10.0
50
- - Transformers 4.40.2
51
- - Pytorch 2.1.2
52
- - Datasets 2.19.1
53
  - Tokenizers 0.19.1
 
1
  ---
2
+ base_model: unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit
3
  library_name: peft
4
+ license: apache-2.0
5
  tags:
6
  - trl
7
  - sft
8
+ - unsloth
9
  - generated_from_trainer
 
10
  model-index:
11
  - name: outputs
12
  results: []
 
17
 
18
  # outputs
19
 
20
+ This model is a fine-tuned version of [unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit) on the None dataset.
21
 
22
  ## Model description
23
 
 
39
  - learning_rate: 5e-05
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
+ - seed: 3407
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - num_epochs: 3.0
 
47
 
48
  ### Framework versions
49
 
50
+ - PEFT 0.13.2
51
+ - Transformers 4.44.2
52
+ - Pytorch 2.5.1+cu124
53
+ - Datasets 3.1.0
54
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": null,
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -10,22 +10,23 @@
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
- "lora_alpha": 32,
14
- "lora_dropout": 0.01,
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
  "k_proj",
 
 
24
  "q_proj",
25
- "up_proj",
26
  "v_proj",
27
- "down_proj",
28
- "o_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
18
  "peft_type": "LORA",
19
+ "r": 4,
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "down_proj",
24
  "k_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
  "q_proj",
 
28
  "v_proj",
29
+ "up_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:090d762725b6c79552fe41ebe8a71d8b143aa5d8653536489b2ceefa5aaf47cd
3
- size 19868224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01408348966eaf5ec6d9e2c1374d8fd8a43e6ef8c12c3a5ff46093c65cd7cc0
3
+ size 8841592
added_tokens.json CHANGED
@@ -1,3 +1,25 @@
1
  {
2
- "[PAD]": 32000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  }
 
1
  {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|PAD_TOKEN|>": 151665,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Nov01_02-04-54_ed00fb51711b/events.out.tfevents.1730426880.ed00fb51711b.984.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6eaf96f13cbf4142fa7cc8549ab819f04ca5e6d7e4e503eb2406fb841fdb561
3
+ size 16472
runs/Nov01_02-10-57_ed00fb51711b/events.out.tfevents.1730427061.ed00fb51711b.7670.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2444fc11a5f52c1904e5589f679bd0e3872687cd853b08031ed55b23bfa69984
3
+ size 16472
runs/Nov01_02-16-40_ed00fb51711b/events.out.tfevents.1730427575.ed00fb51711b.8477.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe5f8a888a4c29f4de609a792da4242c1df81972148682438e8a8e195bb9e8d
3
+ size 16472
runs/Nov01_02-22-43_ed00fb51711b/events.out.tfevents.1730427767.ed00fb51711b.10817.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b816adddda78889499edf70af13cf238e472d7b49ecdd359bdeaafa24625f95
3
+ size 16472
runs/Nov01_02-25-11_ed00fb51711b/events.out.tfevents.1730428081.ed00fb51711b.11768.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81388adbbcbe3df19fe380b45669fd696eb4064155c377961df82d5884ed17ea
3
+ size 16472
runs/Nov01_02-31-46_ed00fb51711b/events.out.tfevents.1730428472.ed00fb51711b.13250.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69232913a46230aec0f3feb899c6d8cf9f0dcdf292c01a6d12b76fc473353b26
3
+ size 16472
runs/Nov01_03-09-35_ed00fb51711b/events.out.tfevents.1730430611.ed00fb51711b.15044.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:740a53d84a9c038a845ed05e9591501ad2855c38f66ab4b1d9edf167a7192f91
3
+ size 55329
special_tokens_map.json CHANGED
@@ -1,27 +1,28 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
 
 
 
 
 
 
 
 
9
  "eos_token": {
10
- "content": "</s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
  "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
 
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": "<|PAD_TOKEN|>",
 
 
 
 
 
 
 
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,33 +1,185 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
- "1": {
14
- "content": "<s>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "2": {
22
- "content": "</s>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
- "32000": {
30
- "content": "[PAD]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
@@ -35,15 +187,30 @@
35
  "special": true
36
  }
37
  },
38
- "bos_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  "clean_up_tokenization_spaces": false,
40
- "eos_token": "</s>",
41
- "legacy": false,
42
- "model_max_length": 1000000000000000019884624838656,
43
- "pad_token": "[PAD]",
44
  "padding_side": "right",
45
- "sp_model_kwargs": {},
46
- "tokenizer_class": "LlamaTokenizer",
47
- "unk_token": "<unk>",
48
- "use_default_system_prompt": true
49
  }
 
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
+ "151665": {
182
+ "content": "<|PAD_TOKEN|>",
183
  "lstrip": false,
184
  "normalized": false,
185
  "rstrip": false,
 
187
  "special": true
188
  }
189
  },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
+ ],
205
+ "bos_token": null,
206
+ "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",
207
  "clean_up_tokenization_spaces": false,
208
+ "eos_token": "<|im_end|>",
209
+ "errors": "replace",
210
+ "model_max_length": 32768,
211
+ "pad_token": "<|PAD_TOKEN|>",
212
  "padding_side": "right",
213
+ "split_special_tokens": false,
214
+ "tokenizer_class": "Qwen2Tokenizer",
215
+ "unk_token": null
 
216
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ce2eb543bd9dd5c3ceb22856b057a4a873376353a95d9530bcdfdefc3aba681
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229c5346ba2acc37c21964c71d41295ad9a7308643e3d992344cb624b0e1a384
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff