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: 5.8378

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: 2.4e-05
train_batch_size: 96
eval_batch_size: 96
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: polynomial
lr_scheduler_warmup_steps: 250
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
10.1753	0.04	100	9.3900
9.0259	0.07	200	8.5694
8.0861	0.11	300	7.5814
7.2827	0.15	400	7.0210
6.9154	0.18	500	6.7973
6.738	0.22	600	6.6274
6.6074	0.26	700	6.5311
6.5101	0.29	800	6.4338
6.4433	0.33	900	6.3696
6.382	0.36	1000	6.3051
6.3157	0.4	1100	6.2578
6.2805	0.44	1200	6.2139
6.2317	0.47	1300	6.1715
6.2085	0.51	1400	6.1438
6.1702	0.55	1500	6.1099
6.1337	0.58	1600	6.0789
6.113	0.62	1700	6.0530
6.0663	0.66	1800	6.0150
6.0446	0.69	1900	5.9880
6.0267	0.73	2000	5.9568
5.9972	0.77	2100	5.9274
5.9599	0.8	2200	5.9109
5.9369	0.84	2300	5.8884
5.9266	0.88	2400	5.8689
5.9068	0.91	2500	5.8548
5.9091	0.95	2600	5.8462
5.879	0.99	2700	5.8378

Framework versions

Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

HachiML/myBit-Llama2-jp-127M-test-3

myBit-Llama2-jp-127M-test-3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

HachiML/
myBit-Llama2-jp-127M-test-3