Hugging Face's logo

Litzy619
/
O0428HMA11

Safetensors
Generated from Trainer
Model card Files Community
Litzy619 commited on
Commit
19eb5d7
•
1 Parent(s): cd43dcb

End of training

Browse files
Files changed (8) hide show
  1. README.md +93 -0
  2. adapter_config.json +43 -0
  3. adapter_model.bin +3 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +10 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +242 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: allenai/OLMo-1B
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: O0428HMA11
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # O0428HMA11
15
+
16
+ This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0353
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0003
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 128
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine_with_restarts
45
+ - lr_scheduler_warmup_steps: 100
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.6441 | 0.09 | 10 | 0.2795 |
54
+ | 0.1859 | 0.18 | 20 | 0.1565 |
55
+ | 0.1509 | 0.27 | 30 | 0.1657 |
56
+ | 0.1581 | 0.36 | 40 | 0.1509 |
57
+ | 0.1497 | 0.45 | 50 | 0.1504 |
58
+ | 0.1514 | 0.54 | 60 | 0.1496 |
59
+ | 0.1497 | 0.63 | 70 | 0.1472 |
60
+ | 0.1487 | 0.73 | 80 | 0.1529 |
61
+ | 0.1465 | 0.82 | 90 | 0.1488 |
62
+ | 0.149 | 0.91 | 100 | 0.1478 |
63
+ | 0.1511 | 1.0 | 110 | 0.1483 |
64
+ | 0.1438 | 1.09 | 120 | 0.1352 |
65
+ | 0.1382 | 1.18 | 130 | 0.1203 |
66
+ | 0.59 | 1.27 | 140 | 2.9085 |
67
+ | 0.602 | 1.36 | 150 | 1.5195 |
68
+ | 6.4792 | 1.45 | 160 | 5.2383 |
69
+ | 2.3451 | 1.54 | 170 | 0.7049 |
70
+ | 1.0846 | 1.63 | 180 | 0.6462 |
71
+ | 0.5224 | 1.72 | 190 | 0.3806 |
72
+ | 0.3875 | 1.81 | 200 | 0.2835 |
73
+ | 0.2533 | 1.9 | 210 | 0.2670 |
74
+ | 0.2265 | 1.99 | 220 | 0.2117 |
75
+ | 0.1544 | 2.08 | 230 | 0.1180 |
76
+ | 0.1085 | 2.18 | 240 | 0.0898 |
77
+ | 0.0812 | 2.27 | 250 | 0.0735 |
78
+ | 0.0721 | 2.36 | 260 | 0.0757 |
79
+ | 0.0719 | 2.45 | 270 | 0.0617 |
80
+ | 0.0545 | 2.54 | 280 | 0.0565 |
81
+ | 0.0479 | 2.63 | 290 | 0.0479 |
82
+ | 0.0458 | 2.72 | 300 | 0.0403 |
83
+ | 0.0316 | 2.81 | 310 | 0.0371 |
84
+ | 0.0298 | 2.9 | 320 | 0.0362 |
85
+ | 0.0346 | 2.99 | 330 | 0.0353 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.36.0.dev0
91
+ - Pytorch 2.1.2+cu121
92
+ - Datasets 2.14.6
93
+ - Tokenizers 0.14.1
adapter_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adaptive_ratio": 0.01,
3
+ "adaptive_ratio_decay": 1.0,
4
+ "additive_modeling": false,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "allenai/OLMo-1B",
7
+ "bias": "none",
8
+ "curr_learning": true,
9
+ "detached_training": true,
10
+ "dynamic_adapter_pool": true,
11
+ "enable_lora": null,
12
+ "encoder_hidden_size": 2048,
13
+ "fan_in_fan_out": false,
14
+ "hypernetwork": true,
15
+ "inference_mode": true,
16
+ "input_based_adapter_selection": true,
17
+ "lora_alpha": 16,
18
+ "lora_dropout": 0.05,
19
+ "merge_weights": false,
20
+ "modules_to_save": null,
21
+ "num_attention_heads": 16,
22
+ "num_layers": 16,
23
+ "num_prefix_set": 3,
24
+ "num_transformer_submodules": 1,
25
+ "num_virtual_tokens": 30,
26
+ "number_of_adapter_pre_layer": 8,
27
+ "ot_diversified_dispatcher": false,
28
+ "ot_diversified_prefix": false,
29
+ "peft_type": "PREFIX_MA_LORA",
30
+ "pool_selective_inference": true,
31
+ "pool_selective_training": true,
32
+ "prefix_projection": true,
33
+ "r": 16,
34
+ "scale": 64,
35
+ "selective_num": 8,
36
+ "simple_hidden_matching": false,
37
+ "simple_instance_matching": true,
38
+ "target_modules": [
39
+ "attn_out"
40
+ ],
41
+ "task_type": "CAUSAL_LM",
42
+ "token_dim": 2048
43
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df52ad83c8d5005f7218d64e38c05e1e4cf696b63045dd5302f31683dc47d40e
3
+ size 101036502
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6f6951ed46750c33fe9807ea664c4c7596a256372306b9970f768610e490f0
3
+ size 4774383804
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": "|||IP_ADDRESS|||"
10
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ }
227
+ },
228
+ "auto_map": {
229
+ "AutoConfig": "allenai/OLMo-1B--configuration_olmo.OLMoConfig",
230
+ "AutoTokenizer": [
231
+ "allenai/OLMo-1B--tokenization_olmo_fast.OLMoTokenizerFast",
232
+ "allenai/OLMo-1B--tokenization_olmo_fast.OLMoTokenizerFast"
233
+ ]
234
+ },
235
+ "clean_up_tokenization_spaces": true,
236
+ "eos_token": "<|endoftext|>",
237
+ "max_length": null,
238
+ "model_max_length": 1000000000000000019884624838656,
239
+ "pad_token": "|||IP_ADDRESS|||",
240
+ "tokenizer_class": "OLMoTokenizer",
241
+ "truncation": "right"
242
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be832087b5c11512c2e6cd10de9287b0ea3930231259ac17edc67bd1fbcc4363
3
+ size 5176