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: 0.2534

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
1.7092	0.8333	50	1.5127
0.3505	1.6667	100	0.3409
0.2875	2.5	150	0.2940
0.2628	3.3333	200	0.2792
0.2652	4.1667	250	0.2750
0.2506	5.0	300	0.2685
0.2404	5.8333	350	0.2632
0.2347	6.6667	400	0.2582
0.2334	7.5	450	0.2547
0.2465	8.3333	500	0.2542
0.2393	9.1667	550	0.2529
0.2489	10.0	600	0.2534

Framework versions

PEFT 0.17.1
Transformers 4.55.3
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2

hin123123/theralingua-tinyllama-word_ver2

theralingua-tinyllama-word_ver2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hin123123/
theralingua-tinyllama-word_ver2