Hugging Face's logo

tommyp111
/
modernbert-flowlm-tulu

Fill-Mask
Transformers
Safetensors
modernbert
Generated from Trainer
Model card Files Community
tommyp111 commited on
Commit
baaf1ce
·
verified ·
1 Parent(s): 68c6a4c

End of training

Browse files
Files changed (1) hide show
  1. README.md +241 -0
README.md ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: answerdotai/ModernBERT-large
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: modernbert-flowlm-tulu
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # modernbert-flowlm-tulu
16
+
17
+ This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.6810
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 32
40
+ - eval_batch_size: 32
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - total_train_batch_size: 128
45
+ - total_eval_batch_size: 128
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - num_epochs: 6
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:-----:|:---------------:|
54
+ | No log | 0.0332 | 200 | 1.9389 |
55
+ | No log | 0.0664 | 400 | 1.8775 |
56
+ | 1.9745 | 0.0997 | 600 | 1.8439 |
57
+ | 1.9745 | 0.1329 | 800 | 1.8225 |
58
+ | 1.8208 | 0.1661 | 1000 | 1.8054 |
59
+ | 1.8208 | 0.1993 | 1200 | 1.7931 |
60
+ | 1.8208 | 0.2326 | 1400 | 1.7823 |
61
+ | 1.7755 | 0.2658 | 1600 | 1.7738 |
62
+ | 1.7755 | 0.2990 | 1800 | 1.7662 |
63
+ | 1.754 | 0.3322 | 2000 | 1.7595 |
64
+ | 1.754 | 0.3654 | 2200 | 1.7548 |
65
+ | 1.754 | 0.3987 | 2400 | 1.7496 |
66
+ | 1.748 | 0.4319 | 2600 | 1.7454 |
67
+ | 1.748 | 0.4651 | 2800 | 1.7418 |
68
+ | 1.7386 | 0.4983 | 3000 | 1.7375 |
69
+ | 1.7386 | 0.5316 | 3200 | 1.7339 |
70
+ | 1.7386 | 0.5648 | 3400 | 1.7309 |
71
+ | 1.7238 | 0.5980 | 3600 | 1.7283 |
72
+ | 1.7238 | 0.6312 | 3800 | 1.7255 |
73
+ | 1.7212 | 0.6645 | 4000 | 1.7230 |
74
+ | 1.7212 | 0.6977 | 4200 | 1.7210 |
75
+ | 1.7212 | 0.7309 | 4400 | 1.7186 |
76
+ | 1.7097 | 0.7641 | 4600 | 1.7161 |
77
+ | 1.7097 | 0.7973 | 4800 | 1.7144 |
78
+ | 1.6998 | 0.8306 | 5000 | 1.7128 |
79
+ | 1.6998 | 0.8638 | 5200 | 1.7110 |
80
+ | 1.6998 | 0.8970 | 5400 | 1.7095 |
81
+ | 1.7027 | 0.9302 | 5600 | 1.7085 |
82
+ | 1.7027 | 0.9635 | 5800 | 1.7069 |
83
+ | 1.7137 | 0.9967 | 6000 | 1.7053 |
84
+ | 1.7137 | 1.0299 | 6200 | 1.7043 |
85
+ | 1.7137 | 1.0631 | 6400 | 1.7031 |
86
+ | 1.7008 | 1.0963 | 6600 | 1.7021 |
87
+ | 1.7008 | 1.1296 | 6800 | 1.7009 |
88
+ | 1.6911 | 1.1628 | 7000 | 1.7000 |
89
+ | 1.6911 | 1.1960 | 7200 | 1.6990 |
90
+ | 1.6911 | 1.2292 | 7400 | 1.6979 |
91
+ | 1.6869 | 1.2625 | 7600 | 1.6971 |
92
+ | 1.6869 | 1.2957 | 7800 | 1.6963 |
93
+ | 1.6845 | 1.3289 | 8000 | 1.6959 |
94
+ | 1.6845 | 1.3621 | 8200 | 1.6952 |
95
+ | 1.6845 | 1.3953 | 8400 | 1.6943 |
96
+ | 1.6849 | 1.4286 | 8600 | 1.6936 |
97
+ | 1.6849 | 1.4618 | 8800 | 1.6931 |
98
+ | 1.6774 | 1.4950 | 9000 | 1.6924 |
99
+ | 1.6774 | 1.5282 | 9200 | 1.6919 |
100
+ | 1.6774 | 1.5615 | 9400 | 1.6915 |
101
+ | 1.6595 | 1.5947 | 9600 | 1.6908 |
102
+ | 1.6595 | 1.6279 | 9800 | 1.6905 |
103
+ | 1.6812 | 1.6611 | 10000 | 1.6901 |
104
+ | 1.6812 | 1.6944 | 10200 | 1.6893 |
105
+ | 1.6812 | 1.7276 | 10400 | 1.6892 |
106
+ | 1.681 | 1.7608 | 10600 | 1.6889 |
107
+ | 1.681 | 1.7940 | 10800 | 1.6882 |
108
+ | 1.6775 | 1.8272 | 11000 | 1.6877 |
109
+ | 1.6775 | 1.8605 | 11200 | 1.6875 |
110
+ | 1.6775 | 1.8937 | 11400 | 1.6874 |
111
+ | 1.6709 | 1.9269 | 11600 | 1.6868 |
112
+ | 1.6709 | 1.9601 | 11800 | 1.6865 |
113
+ | 1.6713 | 1.9934 | 12000 | 1.6864 |
114
+ | 1.6713 | 2.0266 | 12200 | 1.6861 |
115
+ | 1.6713 | 2.0598 | 12400 | 1.6859 |
116
+ | 1.6751 | 2.0930 | 12600 | 1.6857 |
117
+ | 1.6751 | 2.1262 | 12800 | 1.6856 |
118
+ | 1.6711 | 2.1595 | 13000 | 1.6852 |
119
+ | 1.6711 | 2.1927 | 13200 | 1.6851 |
120
+ | 1.6711 | 2.2259 | 13400 | 1.6847 |
121
+ | 1.6688 | 2.2591 | 13600 | 1.6845 |
122
+ | 1.6688 | 2.2924 | 13800 | 1.6845 |
123
+ | 1.6772 | 2.3256 | 14000 | 1.6843 |
124
+ | 1.6772 | 2.3588 | 14200 | 1.6840 |
125
+ | 1.6772 | 2.3920 | 14400 | 1.6838 |
126
+ | 1.6736 | 2.4252 | 14600 | 1.6838 |
127
+ | 1.6736 | 2.4585 | 14800 | 1.6835 |
128
+ | 1.6706 | 2.4917 | 15000 | 1.6834 |
129
+ | 1.6706 | 2.5249 | 15200 | 1.6833 |
130
+ | 1.6706 | 2.5581 | 15400 | 1.6832 |
131
+ | 1.6875 | 2.5914 | 15600 | 1.6831 |
132
+ | 1.6875 | 2.6246 | 15800 | 1.6830 |
133
+ | 1.6768 | 2.6578 | 16000 | 1.6830 |
134
+ | 1.6768 | 2.6910 | 16200 | 1.6828 |
135
+ | 1.6768 | 2.7243 | 16400 | 1.6827 |
136
+ | 1.6687 | 2.7575 | 16600 | 1.6825 |
137
+ | 1.6687 | 2.7907 | 16800 | 1.6824 |
138
+ | 1.6825 | 2.8239 | 17000 | 1.6824 |
139
+ | 1.6825 | 2.8571 | 17200 | 1.6823 |
140
+ | 1.6825 | 2.8904 | 17400 | 1.6823 |
141
+ | 1.659 | 2.9236 | 17600 | 1.6821 |
142
+ | 1.659 | 2.9568 | 17800 | 1.6821 |
143
+ | 1.6602 | 2.9900 | 18000 | 1.6821 |
144
+ | 1.6602 | 3.0233 | 18200 | 1.6820 |
145
+ | 1.6602 | 3.0565 | 18400 | 1.6819 |
146
+ | 1.6733 | 3.0897 | 18600 | 1.6818 |
147
+ | 1.6733 | 3.1229 | 18800 | 1.6818 |
148
+ | 1.6549 | 3.1561 | 19000 | 1.6818 |
149
+ | 1.6549 | 3.1894 | 19200 | 1.6818 |
150
+ | 1.6549 | 3.2226 | 19400 | 1.6817 |
151
+ | 1.6702 | 3.2558 | 19600 | 1.6817 |
152
+ | 1.6702 | 3.2890 | 19800 | 1.6816 |
153
+ | 1.6834 | 3.3223 | 20000 | 1.6816 |
154
+ | 1.6834 | 3.3555 | 20200 | 1.6816 |
155
+ | 1.6834 | 3.3887 | 20400 | 1.6816 |
156
+ | 1.6614 | 3.4219 | 20600 | 1.6814 |
157
+ | 1.6614 | 3.4551 | 20800 | 1.6815 |
158
+ | 1.6807 | 3.4884 | 21000 | 1.6814 |
159
+ | 1.6807 | 3.5216 | 21200 | 1.6814 |
160
+ | 1.6807 | 3.5548 | 21400 | 1.6814 |
161
+ | 1.6731 | 3.5880 | 21600 | 1.6813 |
162
+ | 1.6731 | 3.6213 | 21800 | 1.6813 |
163
+ | 1.6742 | 3.6545 | 22000 | 1.6813 |
164
+ | 1.6742 | 3.6877 | 22200 | 1.6812 |
165
+ | 1.6742 | 3.7209 | 22400 | 1.6812 |
166
+ | 1.6676 | 3.7542 | 22600 | 1.6812 |
167
+ | 1.6676 | 3.7874 | 22800 | 1.6812 |
168
+ | 1.6521 | 3.8206 | 23000 | 1.6812 |
169
+ | 1.6521 | 3.8538 | 23200 | 1.6812 |
170
+ | 1.6521 | 3.8870 | 23400 | 1.6812 |
171
+ | 1.6715 | 3.9203 | 23600 | 1.6812 |
172
+ | 1.6715 | 3.9535 | 23800 | 1.6812 |
173
+ | 1.6681 | 3.9867 | 24000 | 1.6811 |
174
+ | 1.6681 | 4.0199 | 24200 | 1.6811 |
175
+ | 1.6681 | 4.0532 | 24400 | 1.6811 |
176
+ | 1.6582 | 4.0864 | 24600 | 1.6811 |
177
+ | 1.6582 | 4.1196 | 24800 | 1.6811 |
178
+ | 1.6742 | 4.1528 | 25000 | 1.6810 |
179
+ | 1.6742 | 4.1860 | 25200 | 1.6810 |
180
+ | 1.6742 | 4.2193 | 25400 | 1.6810 |
181
+ | 1.6789 | 4.2525 | 25600 | 1.6811 |
182
+ | 1.6789 | 4.2857 | 25800 | 1.6810 |
183
+ | 1.6629 | 4.3189 | 26000 | 1.6810 |
184
+ | 1.6629 | 4.3522 | 26200 | 1.6811 |
185
+ | 1.6629 | 4.3854 | 26400 | 1.6810 |
186
+ | 1.6597 | 4.4186 | 26600 | 1.6810 |
187
+ | 1.6597 | 4.4518 | 26800 | 1.6810 |
188
+ | 1.6652 | 4.4850 | 27000 | 1.6810 |
189
+ | 1.6652 | 4.5183 | 27200 | 1.6810 |
190
+ | 1.6652 | 4.5515 | 27400 | 1.6810 |
191
+ | 1.6695 | 4.5847 | 27600 | 1.6810 |
192
+ | 1.6695 | 4.6179 | 27800 | 1.6810 |
193
+ | 1.6708 | 4.6512 | 28000 | 1.6810 |
194
+ | 1.6708 | 4.6844 | 28200 | 1.6810 |
195
+ | 1.6708 | 4.7176 | 28400 | 1.6810 |
196
+ | 1.6652 | 4.7508 | 28600 | 1.6810 |
197
+ | 1.6652 | 4.7841 | 28800 | 1.6810 |
198
+ | 1.6595 | 4.8173 | 29000 | 1.6810 |
199
+ | 1.6595 | 4.8505 | 29200 | 1.6810 |
200
+ | 1.6595 | 4.8837 | 29400 | 1.6810 |
201
+ | 1.6703 | 4.9169 | 29600 | 1.6810 |
202
+ | 1.6703 | 4.9502 | 29800 | 1.6810 |
203
+ | 1.6695 | 4.9834 | 30000 | 1.6810 |
204
+ | 1.6695 | 5.0166 | 30200 | 1.6810 |
205
+ | 1.6695 | 5.0498 | 30400 | 1.6810 |
206
+ | 1.6569 | 5.0831 | 30600 | 1.6810 |
207
+ | 1.6569 | 5.1163 | 30800 | 1.6810 |
208
+ | 1.6733 | 5.1495 | 31000 | 1.6810 |
209
+ | 1.6733 | 5.1827 | 31200 | 1.6810 |
210
+ | 1.6733 | 5.2159 | 31400 | 1.6810 |
211
+ | 1.6808 | 5.2492 | 31600 | 1.6810 |
212
+ | 1.6808 | 5.2824 | 31800 | 1.6810 |
213
+ | 1.6678 | 5.3156 | 32000 | 1.6810 |
214
+ | 1.6678 | 5.3488 | 32200 | 1.6810 |
215
+ | 1.6678 | 5.3821 | 32400 | 1.6810 |
216
+ | 1.6737 | 5.4153 | 32600 | 1.6810 |
217
+ | 1.6737 | 5.4485 | 32800 | 1.6810 |
218
+ | 1.6751 | 5.4817 | 33000 | 1.6810 |
219
+ | 1.6751 | 5.5150 | 33200 | 1.6810 |
220
+ | 1.6751 | 5.5482 | 33400 | 1.6810 |
221
+ | 1.6709 | 5.5814 | 33600 | 1.6810 |
222
+ | 1.6709 | 5.6146 | 33800 | 1.6810 |
223
+ | 1.657 | 5.6478 | 34000 | 1.6810 |
224
+ | 1.657 | 5.6811 | 34200 | 1.6810 |
225
+ | 1.657 | 5.7143 | 34400 | 1.6810 |
226
+ | 1.6678 | 5.7475 | 34600 | 1.6810 |
227
+ | 1.6678 | 5.7807 | 34800 | 1.6810 |
228
+ | 1.6635 | 5.8140 | 35000 | 1.6810 |
229
+ | 1.6635 | 5.8472 | 35200 | 1.6810 |
230
+ | 1.6635 | 5.8804 | 35400 | 1.6810 |
231
+ | 1.6781 | 5.9136 | 35600 | 1.6810 |
232
+ | 1.6781 | 5.9468 | 35800 | 1.6810 |
233
+ | 1.6722 | 5.9801 | 36000 | 1.6810 |
234
+
235
+
236
+ ### Framework versions
237
+
238
+ - Transformers 4.53.0
239
+ - Pytorch 2.7.1+cu126
240
+ - Datasets 3.6.0
241
+ - Tokenizers 0.21.2