financeLM_outputpath_Sentiment_Analysis_Balanced__15

This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5191

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
2.0424	1.0	358	1.6885
1.3339	2.0	717	1.7008
1.0278	3.0	1076	1.7622
0.819	4.0	1435	1.8862
0.6674	5.0	1793	2.0067
0.5544	6.0	2152	2.1500
0.4702	7.0	2511	2.2106
0.4061	8.0	2870	2.3040
0.3599	9.0	3228	2.3646
0.3226	10.0	3587	2.4215
0.2939	11.0	3946	2.4431
0.2728	12.0	4305	2.4787
0.2577	13.0	4663	2.4998
0.2442	14.0	5022	2.5109
0.2368	14.97	5370	2.5191

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.2+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1