metadata

license: mit
base_model: avsolatorio/GIST-large-Embedding-v0
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: my-clf-microsoft
    results: []

my-clf-microsoft

This model is a fine-tuned version of avsolatorio/GIST-large-Embedding-v0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2381
F1: 0.5822
Roc Auc: 0.7634
Accuracy: 0.1786

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: 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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
No log	1.0	50	0.3147	0.0656	0.5250	0.0
No log	2.0	100	0.2808	0.2809	0.6082	0.0536
No log	3.0	150	0.2539	0.3854	0.6521	0.0357
No log	4.0	200	0.2451	0.4085	0.6582	0.0714
No log	5.0	250	0.2351	0.4365	0.6734	0.1071
No log	6.0	300	0.2361	0.4977	0.7133	0.125
No log	7.0	350	0.2325	0.5629	0.7433	0.1607
No log	8.0	400	0.2294	0.5488	0.7401	0.1964
No log	9.0	450	0.2336	0.5750	0.7567	0.1964
0.1718	10.0	500	0.2342	0.5695	0.7563	0.1964
0.1718	11.0	550	0.2354	0.5809	0.7648	0.1964
0.1718	12.0	600	0.2349	0.5862	0.7658	0.1786
0.1718	13.0	650	0.2390	0.5811	0.7645	0.1786
0.1718	14.0	700	0.2367	0.5841	0.7633	0.2143
0.1718	15.0	750	0.2376	0.5778	0.7606	0.1786
0.1718	16.0	800	0.2381	0.5822	0.7634	0.1786

Framework versions

Transformers 4.38.1
Pytorch 2.1.2
Datasets 2.1.0
Tokenizers 0.15.2