alvarobartt
/

mistral-7b-orpo-alignment-handbook

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

mistral-7b-orpo-alignment-handbook

File size: 194 Bytes

d1e69a3

{
    "epoch": 2.99,
    "train_loss": 0.8898289559379456,
    "train_runtime": 3406.8155,
    "train_samples": 6750,
    "train_samples_per_second": 5.944,
    "train_steps_per_second": 0.092
}