You can deploy this model and start earning money today!

Flock2Moooooo/
task-4-microsoft-Phi-3-mini-4k-instruct

Name: task-4-microsoft-Phi-3-mini-4k-instruct
Availability: InStock

generated_from_trainer

microsoft/Phi-3-mini-4k-instruct

adapter

other

Views

No views yet

lora

This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the flock_task4_tranning dataset. It achieves the following results on the evaluation set:

Loss: 1.1633

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: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 2
total_train_batch_size: 8
total_eval_batch_size: 2
optimizer: Use 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: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.0954	0.0501	50	1.2925
1.0622	0.1002	100	1.2432
0.9452	0.1502	150	1.2492
1.0231	0.2003	200	1.2214
1.0069	0.2504	250	1.2120
0.9887	0.3005	300	1.1978
0.8736	0.3505	350	1.1946
0.9229	0.4006	400	1.1957
0.9746	0.4507	450	1.1893
0.9217	0.5008	500	1.1827
0.9055	0.5508	550	1.1768
0.9332	0.6009	600	1.1708
0.8994	0.6510	650	1.1739
0.9139	0.7011	700	1.1631
0.9447	0.7511	750	1.1687
0.9196	0.8012	800	1.1653
0.8767	0.8513	850	1.1638
0.8826	0.9014	900	1.1622
0.9803	0.9514	950	1.1631

Framework versions

PEFT 0.12.0
Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Flock2Moooooo/task-4-microsoft-Phi-3-mini-4k-instruct

lora

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Flock2Moooooo/
task-4-microsoft-Phi-3-mini-4k-instruct