sft-zephyr-7b-beta-v1 – AI Model by hllj | AlphaNeural AI

You can deploy this model and start earning money today!

hllj/
sft-zephyr-7b-beta-v1

like

0

text-generation

generated_from_trainer

HuggingFaceH4/zephyr-7b-beta

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

sft-zephyr-7b-beta-v1

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4927

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: 3e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0538	0.19	50	1.1364
0.7744	0.37	100	0.7777
0.5936	0.56	150	0.6507
0.5449	0.74	200	0.6087
0.501	0.93	250	0.5840
0.5752	1.12	300	0.5552
0.4542	1.3	350	0.5419
0.5115	1.49	400	0.5243
0.4224	1.67	450	0.5188
0.4486	1.86	500	0.5055
0.3865	2.04	550	0.5038
0.4193	2.23	600	0.5048
0.4294	2.42	650	0.4995
0.4077	2.6	700	0.5014
0.4667	2.79	750	0.4985
0.4226	2.97	800	0.4937
0.4195	3.16	850	0.4920
0.338	3.35	900	0.4923
0.3943	3.53	950	0.4926
0.3953	3.72	1000	0.4927

Framework versions

Transformers 4.35.2
Pytorch 2.1.0
Datasets 2.15.0
Tokenizers 0.15.0