You can deploy this model and start earning money today!

xshubhamx/
tiny-llama-lora-no-grad

Name: tiny-llama-lora-no-grad
Availability: InStock

tensorboard

safetensors

generated_from_trainer

TinyLlama/TinyLlama-1.1B-Chat-v1.0

finetune

apache-2.0

Views

No views yet

tiny-llama-lora-no-grad

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7206
Accuracy: 0.8164
Precision: 0.8231
Recall: 0.8164
Precision Macro: 0.7396
Recall Macro: 0.7117
Macro Fpr: 0.0159
Weighted Fpr: 0.0152
Weighted Specificity: 0.9752
Macro Specificity: 0.9865
Weighted Sensitivity: 0.8226
Macro Sensitivity: 0.7117
F1 Micro: 0.8226
F1 Macro: 0.7177
F1 Weighted: 0.8190

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	Precision Macro	Recall Macro	Macro Fpr	Weighted Fpr	Weighted Specificity	Macro Specificity	Weighted Sensitivity	Macro Sensitivity	F1 Micro	F1 Macro	F1 Weighted
1.1276	1.0	643	0.6705	0.8087	0.8055	0.8087	0.7053	0.6853	0.0172	0.0166	0.9742	0.9855	0.8087	0.6853	0.8087	0.6806	0.8034
0.503	2.0	1286	0.7206	0.8164	0.8231	0.8164	0.7746	0.7641	0.0163	0.0158	0.9773	0.9862	0.8164	0.7641	0.8164	0.7610	0.8154
0.3617	3.0	1929	0.8819	0.8164	0.8137	0.8164	0.7499	0.7170	0.0164	0.0158	0.9752	0.9861	0.8164	0.7170	0.8164	0.7242	0.8124
0.0618	4.0	2572	1.1434	0.8087	0.8107	0.8087	0.7673	0.7293	0.0173	0.0166	0.9727	0.9854	0.8087	0.7293	0.8087	0.7401	0.8074
0.0243	5.0	3215	1.2966	0.8110	0.8112	0.8110	0.7489	0.7164	0.0171	0.0164	0.9754	0.9858	0.8110	0.7164	0.8110	0.7228	0.8086
0.0121	6.0	3858	1.2965	0.8195	0.8175	0.8195	0.7312	0.7077	0.0162	0.0155	0.9752	0.9863	0.8195	0.7077	0.8195	0.7143	0.8170
0.0021	7.0	4501	1.3710	0.8187	0.8168	0.8187	0.7519	0.7112	0.0162	0.0156	0.9756	0.9863	0.8187	0.7112	0.8187	0.7165	0.8152
0.003	8.0	5144	1.3348	0.8203	0.8171	0.8203	0.7417	0.7073	0.0162	0.0154	0.9749	0.9863	0.8203	0.7073	0.8203	0.7159	0.8173
0.0023	9.0	5787	1.4038	0.8187	0.8149	0.8187	0.7548	0.7030	0.0163	0.0156	0.9742	0.9862	0.8187	0.7030	0.8187	0.7121	0.8141
0.0033	10.0	6430	1.4021	0.8203	0.8151	0.8203	0.7330	0.7110	0.0162	0.0154	0.9746	0.9863	0.8203	0.7110	0.8203	0.7152	0.8163
0.0017	11.0	7073	1.4001	0.8211	0.8178	0.8211	0.7361	0.7110	0.0160	0.0153	0.9753	0.9864	0.8211	0.7110	0.8211	0.7155	0.8179
0.0023	12.0	7716	1.4100	0.8226	0.8189	0.8226	0.7386	0.7127	0.0158	0.0152	0.9754	0.9865	0.8226	0.7127	0.8226	0.7177	0.8195
0.0034	13.0	8359	1.4273	0.8234	0.8192	0.8234	0.7385	0.7115	0.0158	0.0151	0.9757	0.9866	0.8234	0.7115	0.8234	0.7171	0.8201
0.0016	14.0	9002	1.4322	0.8226	0.8183	0.8226	0.7382	0.7111	0.0159	0.0152	0.9754	0.9865	0.8226	0.7111	0.8226	0.7168	0.8192
0.0006	15.0	9645	1.4401	0.8226	0.8178	0.8226	0.7396	0.7117	0.0159	0.0152	0.9752	0.9865	0.8226	0.7117	0.8226	0.7177	0.8190

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.1

xshubhamx/tiny-llama-lora-no-grad

tiny-llama-lora-no-grad

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

xshubhamx/
tiny-llama-lora-no-grad