ruadapt_qwen2.5_3B_u48_full_lr3e4_bs256

RefalMachine/ruadapt_qwen2.5_3B_u48_full_lr3e4_bs256

ruadapt_qwen2.5_3B_u48_full_lr3e4_bs256 is a machine learning model from RefalMachine. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

18% of all-time downloads

All-time downloads

Public

Parameters

2.9B

11.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors11.5 GB · 92%

At a glance

Model type: qwen2
Access: Public
Created: Oct 14, 2024
Updated: Oct 14, 2024
SHA: c67d4166

Base models

RefalMachine/ruadapt_qwen2.5_3B_u48_mean_init

Model card

From the Hugging Face model README

ruadapt_qwen2.5_3B_u48_full_lr3e4_bs256

This model is a fine-tuned version of RefalMachine/ruadapt_qwen2.5_3B_u48_mean_init on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.4520
Accuracy: 0.5011

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	0.0	1	6.0677	0.1658
2.621	0.17	2000	2.4938	0.4960
2.5772	0.34	4000	2.4647	0.4995
2.573	0.51	6000	2.4562	0.5005
2.5707	0.68	8000	2.4528	0.5010
2.5741	0.84	10000	2.4521	0.5010

Framework versions

Transformers 4.37.2
Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
Datasets 2.18.0
Tokenizers 0.15.2

Type: qwen2
Created: Oct 14, 2024
Updated: Oct 14, 2024