mistral-7b-expo-7b-L2EXPO-25-2 – AI Model by hZzy | AlphaNeural AI

You can deploy this model and start earning money today!

hZzy/
mistral-7b-expo-7b-L2EXPO-25-2

like

0

generated_from_trainer

hZzy/mistral-7b-sft-25-1

Views

No views yet

Visualize in Weights & Biases

mistral-7b-expo-7b-L2EXPO-25-2

This model is a fine-tuned version of hZzy/mistral-7b-sft-25-1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4237
Objective: 0.4183
Reward Accuracy: 0.6893
Logp Accuracy: 0.6748
Log Diff Policy: 20.0390
Chosen Logps: -170.4489
Rejected Logps: -190.4880
Chosen Rewards: -0.7578
Rejected Rewards: -0.9545
Logits: -2.6172

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-07
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 3
gradient_accumulation_steps: 12
total_train_batch_size: 144
total_eval_batch_size: 12
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Objective	Reward Accuracy	Logp Accuracy	Log Diff Policy	Chosen Logps	Rejected Logps	Chosen Rewards	Rejected Rewards	Logits
0.5322	0.1011	50	0.4794	0.4737	0.6242	0.6141	10.0662	-107.6857	-117.7519	-0.1301	-0.2272	-1.9215
0.4818	0.2022	100	0.4558	0.4491	0.6675	0.6560	18.7962	-149.1258	-167.9220	-0.5445	-0.7289	-2.4450
0.4328	0.3033	150	0.4360	0.4292	0.6798	0.6614	16.5764	-176.1400	-192.7165	-0.8147	-0.9768	-2.6197
0.4089	0.4044	200	0.4318	0.4250	0.6843	0.6641	17.5044	-182.0551	-199.5595	-0.8738	-1.0453	-2.4940
0.3847	0.5056	250	0.4282	0.4234	0.6890	0.6700	19.1352	-166.7106	-185.8459	-0.7204	-0.9081	-2.6205
0.3439	0.6067	300	0.4263	0.4218	0.6868	0.6675	17.8780	-154.9931	-172.8710	-0.6032	-0.7784	-2.5720
0.3596	0.7078	350	0.4223	0.4173	0.6910	0.6714	18.3252	-161.3730	-179.6982	-0.6670	-0.8467	-2.5881
0.3392	0.8089	400	0.4230	0.4174	0.6876	0.6697	19.0882	-165.8985	-184.9868	-0.7122	-0.8995	-2.6111
0.3338	0.9100	450	0.4237	0.4183	0.6893	0.6748	20.0390	-170.4489	-190.4880	-0.7578	-0.9545	-2.6172

Framework versions

Transformers 4.42.0
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.19.1