google/flan_t5_small_twitter/README.md

metadata

license: apache-2.0
base_model: google/flan-t5-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: flan_t5_small_twitter
    results: []

flan_t5_small_twitter

This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4985
• Accuracy: 0.7472
• F1 Macro: 0.6954
• F1 Micro: 0.7472

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Micro
0.5055	0.18	50	0.5210	0.7537	0.7230	0.7537
0.5045	0.37	100	0.5018	0.7445	0.6934	0.7445
0.4727	0.55	150	0.5356	0.7243	0.6002	0.7243
0.4924	0.74	200	0.4985	0.7472	0.6954	0.7472
0.4847	0.92	250	0.4992	0.7528	0.7107	0.7528
0.4107	1.1	300	0.5264	0.75	0.7086	0.75
0.4197	1.29	350	0.5231	0.7436	0.7126	0.7436
0.4002	1.47	400	0.5312	0.7509	0.7009	0.7509
0.4381	1.65	450	0.5216	0.7482	0.7000	0.7482
0.4125	1.84	500	0.5262	0.7509	0.7161	0.7509
0.3665	2.02	550	0.5205	0.7546	0.7190	0.7546
0.3855	2.21	600	0.5672	0.7537	0.7161	0.7537
0.3125	2.39	650	0.5732	0.7509	0.7066	0.7509
0.2955	2.57	700	0.5928	0.7555	0.7122	0.7555
0.3556	2.76	750	0.5704	0.7537	0.7174	0.7537
0.3578	2.94	800	0.5706	0.7518	0.7069	0.7518

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2