metadata

library_name: transformers
base_model: fahadqazi/testts1234
tags:
  - generated_from_trainer
model-index:
  - name: testts1234
    results: []

testts1234

This model is a fine-tuned version of fahadqazi/testts1234 on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 64
eval_batch_size: 2
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 200
training_steps: 10000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.4412	1.9231	500	0.4350
0.4381	3.8462	1000	0.4291
0.4361	5.7692	1500	0.4394
0.4382	7.6923	2000	0.4251
0.4304	9.6154	2500	0.4305
0.4321	11.5385	3000	0.4226
0.423	13.4615	3500	0.4271
0.4204	15.3846	4000	0.4234
0.4212	17.3077	4500	0.4218
0.4171	19.2308	5000	0.4209
0.4116	21.1538	5500	0.4145
0.4109	23.0769	6000	0.4083
0.4045	25.0	6500	0.4100
0.4058	26.9231	7000	0.4095
0.3992	28.8462	7500	0.4078
0.402	30.7692	8000	0.4072
0.3987	32.6923	8500	0.4036
0.396	34.6154	9000	0.4030
0.3912	36.5385	9500	0.4010
0.3937	38.4615	10000	0.4003