Hugging Face's logo

eternis
/
eternis_router_encoder_sft_9Sep

Transformers
Safetensors
Generated from Trainer
Model card Files
xet
 Community
eternis commited on
Commit
c0b4ea1
·
verified ·
1 Parent(s): 17f378c

Model save

Browse files
Files changed (2) hide show
  1. README.md +120 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: FacebookAI/roberta-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: eternis_router_encoder_sft_9Sep
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
+ # eternis_router_encoder_sft_9Sep
16
+
17
+ This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.7641
20
+ - Mse: 0.4879
21
+ - Mae: 0.4952
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
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: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 20
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Mse | Mae |
54
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
55
+ | 8.5061 | 0.3429 | 300 | 1.7282 | 1.0945 | 0.8522 |
56
+ | 8.1139 | 0.6857 | 600 | 1.6352 | 1.0425 | 0.8249 |
57
+ | 7.7043 | 1.0286 | 900 | 1.5126 | 0.9853 | 0.8051 |
58
+ | 6.9404 | 1.3714 | 1200 | 1.3621 | 0.8932 | 0.7625 |
59
+ | 6.6003 | 1.7143 | 1500 | 1.2822 | 0.8509 | 0.7413 |
60
+ | 5.8303 | 2.0571 | 1800 | 1.1538 | 0.7647 | 0.7005 |
61
+ | 5.4533 | 2.4 | 2100 | 1.1136 | 0.7337 | 0.6812 |
62
+ | 5.0087 | 2.7429 | 2400 | 1.0895 | 0.7149 | 0.6684 |
63
+ | 4.8301 | 3.0857 | 2700 | 1.0786 | 0.7060 | 0.6610 |
64
+ | 4.676 | 3.4286 | 3000 | 1.0654 | 0.6971 | 0.6550 |
65
+ | 4.6187 | 3.7714 | 3300 | 1.0473 | 0.6842 | 0.6447 |
66
+ | 4.3955 | 4.1143 | 3600 | 1.0129 | 0.6608 | 0.6308 |
67
+ | 4.4388 | 4.4571 | 3900 | 1.0255 | 0.6688 | 0.6355 |
68
+ | 4.3574 | 4.8 | 4200 | 0.9843 | 0.6405 | 0.6154 |
69
+ | 4.384 | 5.1429 | 4500 | 0.9835 | 0.6403 | 0.6153 |
70
+ | 4.4066 | 5.4857 | 4800 | 1.0027 | 0.6535 | 0.6256 |
71
+ | 4.4052 | 5.8286 | 5100 | 0.9643 | 0.6275 | 0.6050 |
72
+ | 4.3846 | 6.1714 | 5400 | 0.9507 | 0.6175 | 0.5982 |
73
+ | 4.31 | 6.5143 | 5700 | 0.9536 | 0.6193 | 0.5989 |
74
+ | 4.2701 | 6.8571 | 6000 | 0.9481 | 0.6159 | 0.5943 |
75
+ | 4.2284 | 7.2 | 6300 | 0.9181 | 0.5951 | 0.5815 |
76
+ | 4.1039 | 7.5429 | 6600 | 0.9036 | 0.5857 | 0.5731 |
77
+ | 4.2027 | 7.8857 | 6900 | 0.8906 | 0.5758 | 0.5655 |
78
+ | 4.1092 | 8.2286 | 7200 | 0.8899 | 0.5761 | 0.5653 |
79
+ | 4.213 | 8.5714 | 7500 | 0.8903 | 0.5778 | 0.5658 |
80
+ | 4.1775 | 8.9143 | 7800 | 0.8766 | 0.5663 | 0.5582 |
81
+ | 4.1293 | 9.2571 | 8100 | 0.8891 | 0.5739 | 0.5637 |
82
+ | 4.135 | 9.6 | 8400 | 0.8823 | 0.5701 | 0.5599 |
83
+ | 4.1324 | 9.9429 | 8700 | 0.8633 | 0.5590 | 0.5546 |
84
+ | 4.0383 | 10.2857 | 9000 | 0.8562 | 0.5524 | 0.5462 |
85
+ | 4.0424 | 10.6286 | 9300 | 0.8390 | 0.5403 | 0.5376 |
86
+ | 4.0851 | 10.9714 | 9600 | 0.8455 | 0.5446 | 0.5421 |
87
+ | 3.9225 | 11.3143 | 9900 | 0.8190 | 0.5283 | 0.5305 |
88
+ | 4.0771 | 11.6571 | 10200 | 0.8195 | 0.5261 | 0.5268 |
89
+ | 3.9188 | 12.0 | 10500 | 0.8112 | 0.5218 | 0.5233 |
90
+ | 3.9961 | 12.3429 | 10800 | 0.8157 | 0.5247 | 0.5241 |
91
+ | 3.9793 | 12.6857 | 11100 | 0.7877 | 0.5059 | 0.5097 |
92
+ | 4.0327 | 13.0286 | 11400 | 0.8180 | 0.5256 | 0.5242 |
93
+ | 3.9755 | 13.3714 | 11700 | 0.8043 | 0.5173 | 0.5183 |
94
+ | 3.9531 | 13.7143 | 12000 | 0.7860 | 0.5035 | 0.5060 |
95
+ | 3.9182 | 14.0571 | 12300 | 0.7914 | 0.5070 | 0.5123 |
96
+ | 3.8201 | 14.4 | 12600 | 0.7873 | 0.5033 | 0.5095 |
97
+ | 3.8887 | 14.7429 | 12900 | 0.7868 | 0.5039 | 0.5077 |
98
+ | 3.9021 | 15.0857 | 13200 | 0.7736 | 0.4964 | 0.5016 |
99
+ | 3.8241 | 15.4286 | 13500 | 0.7677 | 0.4903 | 0.5002 |
100
+ | 3.8387 | 15.7714 | 13800 | 0.7751 | 0.4953 | 0.5025 |
101
+ | 3.8344 | 16.1143 | 14100 | 0.7802 | 0.5004 | 0.5023 |
102
+ | 3.8173 | 16.4571 | 14400 | 0.7588 | 0.4853 | 0.4958 |
103
+ | 3.9998 | 16.8 | 14700 | 0.7556 | 0.4828 | 0.4915 |
104
+ | 3.838 | 17.1429 | 15000 | 0.7690 | 0.4916 | 0.4988 |
105
+ | 3.7549 | 17.4857 | 15300 | 0.7545 | 0.4819 | 0.4920 |
106
+ | 3.8553 | 17.8286 | 15600 | 0.7901 | 0.5058 | 0.5077 |
107
+ | 3.7462 | 18.1714 | 15900 | 0.7558 | 0.4829 | 0.4947 |
108
+ | 3.7608 | 18.5143 | 16200 | 0.7518 | 0.4796 | 0.4890 |
109
+ | 3.9487 | 18.8571 | 16500 | 0.7590 | 0.4836 | 0.4915 |
110
+ | 3.9489 | 19.2 | 16800 | 0.7278 | 0.4639 | 0.4758 |
111
+ | 3.8653 | 19.5429 | 17100 | 0.7498 | 0.4786 | 0.4914 |
112
+ | 3.7533 | 19.8857 | 17400 | 0.7641 | 0.4879 | 0.4952 |
113
+
114
+
115
+ ### Framework versions
116
+
117
+ - Transformers 4.56.1
118
+ - Pytorch 2.7.0
119
+ - Datasets 4.0.0
120
+ - Tokenizers 0.22.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d480c64a79023b3077d688cce0868a938fc6c4cd486e9dd50c24cf59ac9f30a3
3
  size 500173232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6d970344f0fc3e7f585e4af273f8887472b78e7aa030118186b0587f78bb06
3
  size 500173232