chat_150STEPS_1e7rate_01beta_DPO – AI Model by tsavage68 | AlphaNeural AI

You can deploy this model and start earning money today!

tsavage68/
chat_150STEPS_1e7rate_01beta_DPO

like

0

text-generation

generated_from_trainer

meta-llama/Llama-2-7b-chat-hf

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

chat_150STEPS_1e7rate_01beta

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6933
Rewards/chosen: -0.0025
Rewards/rejected: -0.0022
Rewards/accuracies: 0.4022
Rewards/margins: -0.0003
Logps/rejected: -18.8131
Logps/chosen: -16.7695
Logits/rejected: -0.5968
Logits/chosen: -0.5967

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: 1e-07
train_batch_size: 4
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6931	0.1	50	0.6934	-0.0010	-0.0005	0.4110	-0.0005	-18.7964	-16.7546	-0.5967	-0.5965
0.6923	0.2	100	0.6935	-0.0018	-0.0012	0.4044	-0.0006	-18.8033	-16.7622	-0.5978	-0.5977
0.6939	0.29	150	0.6933	-0.0025	-0.0022	0.4022	-0.0003	-18.8131	-16.7695	-0.5968	-0.5967

Framework versions

Transformers 4.37.2
Pytorch 2.0.0+cu117
Datasets 2.17.0
Tokenizers 0.15.2