biobart-MTS-30-epochs

tanatapanun/biobart-MTS-30-epochs

biobart-MTS-30-epochs is a machine learning model from tanatapanun. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

22% of all-time downloads

All-time downloads

Public

Parameters

166M

17.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors666 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: bart
Access: Public
Created: Nov 21, 2023
Updated: Nov 30, 2023
SHA: b7af658e

Base models

GanjinZero/biobart-v2-base

Model card

From the Hugging Face model README

my_model

This model is a fine-tuned version of GanjinZero/biobart-v2-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.8150
Rouge1: 0.3094
Rouge2: 0.127
Rougel: 0.2872
Rougelsum: 0.2875
Gen Len: 15.49

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	151	0.7399	0.2645	0.0955	0.2335	0.2333	14.82
No log	2.0	302	0.6992	0.2218	0.0735	0.1903	0.1897	13.26
No log	3.0	453	0.6809	0.2555	0.093	0.231	0.2317	13.99
0.7206	4.0	604	0.6811	0.2785	0.1111	0.2494	0.25	14.09
0.7206	5.0	755	0.6812	0.2806	0.1024	0.2519	0.2526	14.4
0.7206	6.0	906	0.6853	0.2803	0.1023	0.2548	0.2553	14.24
0.5025	7.0	1057	0.6963	0.2501	0.0894	0.2279	0.2296	14.04
0.5025	8.0	1208	0.6970	0.2709	0.1012	0.2445	0.2448	14.68
0.5025	9.0	1359	0.7107	0.2898	0.1024	0.2604	0.2604	14.62
0.3683	10.0	1510	0.7172	0.2955	0.1132	0.2668	0.2677	15.04
0.3683	11.0	1661	0.7243	0.3225	0.1294	0.289	0.2914	14.87
0.3683	12.0	1812	0.7329	0.312	0.1295	0.2838	0.2867	15.11
0.3683	13.0	1963	0.7364	0.3332	0.1277	0.2981	0.3001	15.3
0.2807	14.0	2114	0.7480	0.3584	0.1608	0.3257	0.3267	15.16
0.2807	15.0	2265	0.7609	0.3138	0.1177	0.2868	0.2876	15.19
0.2807	16.0	2416	0.7648	0.3083	0.1195	0.2767	0.279	15.02
0.2214	17.0	2567	0.7689	0.3088	0.1252	0.2798	0.2816	15.42
0.2214	18.0	2718	0.7761	0.3071	0.1229	0.2815	0.2831	15.31
0.2214	19.0	2869	0.7787	0.3129	0.1215	0.2839	0.2846	15.13
0.182	20.0	3020	0.7871	0.3291	0.1265	0.2992	0.301	15.3
0.182	21.0	3171	0.7863	0.299	0.1085	0.2704	0.2722	15.32
0.182	22.0	3322	0.7959	0.3181	0.1185	0.2883	0.2902	15.23
0.182	23.0	3473	0.8026	0.3352	0.1255	0.3043	0.3049	15.45
0.153	24.0	3624	0.8031	0.3232	0.1338	0.2934	0.293	15.43
0.153	25.0	3775	0.8103	0.2997	0.1231	0.2745	0.276	15.5
0.153	26.0	3926	0.8122	0.3057	0.1188	0.2813	0.2824	15.4
0.1312	27.0	4077	0.8131	0.3151	0.1271	0.2895	0.2907	15.46
0.1312	28.0	4228	0.8155	0.3089	0.1266	0.2868	0.2878	15.5
0.1312	29.0	4379	0.8152	0.3154	0.1277	0.2909	0.2908	15.46
0.1217	30.0	4530	0.8150	0.3094	0.127	0.2872	0.2875	15.49

Framework versions

Transformers 4.35.2
Pytorch 1.12.1+cu113
Datasets 2.15.0
Tokenizers 0.15.0

Library: transformers
Type: bart
License: apache-2.0
Created: Nov 21, 2023
Updated: Nov 30, 2023