gpt-neo-125m-finetuned-philosopher_rave_20

This model is a fine-tuned version of EleutherAI/gpt-neo-125m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.7097

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

20 epochs

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-07
• 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: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	155	2.8834
No log	2.0	310	2.8606
No log	3.0	465	2.8407
2.8695	4.0	620	2.8228
2.8695	5.0	775	2.8063
2.8695	6.0	930	2.7911
2.8122	7.0	1085	2.7772
2.8122	8.0	1240	2.7650
2.8122	9.0	1395	2.7544
2.7613	10.0	1550	2.7454
2.7613	11.0	1705	2.7378
2.7613	12.0	1860	2.7313
2.7397	13.0	2015	2.7258
2.7397	14.0	2170	2.7211
2.7397	15.0	2325	2.7173
2.7397	16.0	2480	2.7143
2.7214	17.0	2635	2.7121
2.7214	18.0	2790	2.7106
2.7214	19.0	2945	2.7098
2.7104	20.0	3100	2.7097

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2