thesisv1

goldi1111/thesisv1

thesisv1 is a machine learning model from goldi1111. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated Jun 12, 2024

Repo size

23.7 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors9.4 MB · 99%

At a glance

License: mit
Access: Public
Created: Jun 12, 2024
Updated: Jun 12, 2024
SHA: bb32eb1b

Base models

Model card

From the Hugging Face model README

thesisv1

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.5156

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: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
6.755	0.02	25	7.7148
5.59	0.04	50	4.6562
3.5625	0.06	75	3.1660
3.4125	0.08	100	2.6152
3.2925	0.1	125	2.6309
2.92	0.12	150	2.5371
2.965	0.14	175	2.4902
2.6725	0.16	200	2.4902
2.74	0.18	225	2.4961
2.8425	0.2	250	2.4883
2.81	0.22	275	2.4961
2.6925	0.24	300	2.6406
2.805	0.26	325	2.5137
2.7925	0.28	350	2.4453
2.8675	0.3	375	2.6113
2.7675	0.32	400	2.5566
2.6975	0.35	425	2.6602
2.6775	0.37	450	2.6699
2.575	0.39	475	2.4766
2.705	0.41	500	2.7617
2.555	0.43	525	2.5469
2.6825	0.45	550	2.5215
2.59	0.47	575	2.4824
2.8	0.49	600	2.5801
2.5625	0.51	625	2.6797
2.5175	0.53	650	2.6328
2.5625	0.55	675	2.5449
2.4137	0.57	700	2.5254
2.5162	0.59	725	2.5449
2.5975	0.61	750	2.5938
2.655	0.63	775	2.5098
2.53	0.65	800	2.5898
2.5587	0.67	825	2.5547
2.635	0.69	850	2.5723
2.5475	0.71	875	2.6152
2.5975	0.73	900	2.5488
2.6725	0.75	925	2.5430
2.6375	0.77	950	2.5312
2.565	0.79	975	2.5312
2.5187	0.81	1000	2.5371
2.6225	0.83	1025	2.5703
2.53	0.85	1050	2.5410
2.515	0.87	1075	2.5410
2.48	0.89	1100	2.5137
2.5775	0.91	1125	2.5098
2.655	0.93	1150	2.5137
2.7175	0.95	1175	2.5156
2.5238	0.97	1200	2.5156
2.3838	1.0	1225	2.5156

Framework versions

Transformers 4.38.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.15.2

License: mit
Created: Jun 12, 2024
Updated: Jun 12, 2024