RefalMachine_-_ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_bs256-8bits – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
RefalMachine_-_ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_bs256-8bits

like

0

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_bs256 - bnb 8bits

Model creator: https://huggingface.co/RefalMachine/
Original model: https://huggingface.co/RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_bs256/

Original model description:

library_name: transformers base_model: RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init tags:

generated_from_trainer metrics:
accuracy model-index:
name: ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_bs256 results: []

ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_bs256

This model is a fine-tuned version of RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.4832
Accuracy: 0.4983

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: 0.0003
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 64
gradient_accumulation_steps: 2
total_train_batch_size: 256
total_eval_batch_size: 128
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.0001	1	5.8817	0.3107
2.6497	0.1765	2000	2.5180	0.4939
2.6174	0.3531	4000	2.4940	0.4966
2.5972	0.5296	6000	2.4866	0.4977
2.6022	0.7062	8000	2.4836	0.4982
2.5999	0.8827	10000	2.4831	0.4983

Framework versions

Transformers 4.45.2
Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
Datasets 2.18.0
Tokenizers 0.20.1