mistral-7b-expo-7b-L2EXPO-25-1 – AI Model by hZzy | AlphaNeural AI

You can deploy this model and start earning money today!

hZzy/
mistral-7b-expo-7b-L2EXPO-25-1

like

0

generated_from_trainer

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

Views

No views yet

Visualize in Weights & Biases

mistral-7b-expo-7b-L2EXPO-25-1

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: 0.4204
Objective: 0.4141
Reward Accuracy: 0.6985
Logp Accuracy: 0.6711
Log Diff Policy: 18.7330
Chosen Logps: -177.5313
Rejected Logps: -196.2643
Chosen Rewards: -0.8211
Rejected Rewards: -1.0028
Logits: -2.0190

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: 6
gradient_accumulation_steps: 12
total_train_batch_size: 288
total_eval_batch_size: 24
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
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
0.4025	0.3154	100	0.4351	0.4272	0.6762	0.6655	16.2158	-134.4898	-150.7056	-0.3907	-0.5472	-1.9622
0.3317	0.6307	200	0.4248	0.4189	0.6946	0.6723	19.1899	-182.6861	-201.8760	-0.8726	-1.0589	-1.8613
0.2739	0.9461	300	0.4204	0.4141	0.6985	0.6711	18.7330	-177.5313	-196.2643	-0.8211	-1.0028	-2.0190

Framework versions

Transformers 4.42.0
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.19.1