metadata

base_model: xxxxxxxxx
tags:
  - generated_from_trainer
datasets:
  - AmazonScience/massive
metrics:
  - f1
model-index:
  - name: massive_indo
    results: []

massive_indo

This model is a fine-tuned version of xxxxxxxxx on the massive dataset. It achieves the following results on the evaluation set:

Loss: 0.6883
F1: 0.8201

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1
2.1343	0.11	2000	1.7374	0.2664
1.2506	0.22	4000	1.1294	0.5441
0.9268	0.33	6000	0.8991	0.6547
0.7993	0.44	8000	0.8401	0.6819
0.6985	0.54	10000	0.7629	0.7245
0.6418	0.65	12000	0.7507	0.7559
0.5887	0.76	14000	0.6858	0.7796
0.5462	0.87	16000	0.6852	0.7872
0.508	0.98	18000	0.6731	0.7836
0.4222	1.09	20000	0.6884	0.7902
0.3948	1.2	22000	0.6809	0.7897
0.3947	1.31	24000	0.6894	0.7935
0.3779	1.42	26000	0.6702	0.8026
0.3488	1.53	28000	0.6762	0.7935
0.3461	1.63	30000	0.6737	0.8054
0.3372	1.74	32000	0.6720	0.8062
0.3275	1.85	34000	0.6526	0.8156
0.3224	1.96	36000	0.6717	0.8068
0.2425	2.07	38000	0.6810	0.8143
0.2423	2.18	40000	0.6668	0.8196
0.2394	2.29	42000	0.7014	0.8125
0.2247	2.4	44000	0.6842	0.8167
0.2253	2.51	46000	0.7012	0.8130
0.2225	2.62	48000	0.6907	0.8178
0.2074	2.72	50000	0.6814	0.8206
0.2095	2.83	52000	0.6928	0.8192
0.2018	2.94	54000	0.6883	0.8201

Framework versions

Transformers 4.34.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.0