This model is a fine-tuned version of W-61/llama-3-8b-base-sft-ultrachat-8xh200 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

Loss: 0.4319
Rewards/chosen: -0.5716
Logps/chosen: -345.0196
Rewards/rejected: -1.4489
Logps/rejected: -411.8449
Rewards/margins: 0.8773
Kl: 0.0
Logits/chosen: -377414720.0
Logits/rejected: -376930848.0

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Logps/chosen	Rewards/rejected	Logps/rejected	Rewards/margins	Logits/chosen	Logits/rejected
1.8447	0.2094	200	0.4646	-0.6301	-350.8658	-0.9983	-366.7805	0.3682	-401673280.0	-397073248.0
1.7296	0.4188	400	0.4408	-0.6904	-356.8998	-1.3983	-406.7836	0.7079	-377831392.0	-377408832.0
1.685	0.6283	600	0.4325	-0.9586	-383.711	-1.8718	-454.1356	0.9133	-388254240.0	-387494368.0
1.7464	0.8377	800	0.4319	-0.5716	-345.0196	-1.4489	-411.8449	0.8773	-377414720.0	-376930848.0

Framework versions

Transformers 4.51.0
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.21.4

jackf857/llama-3-8b-base-kto-ultrafeedback-4xh200-batch-128-20260427-194056

llama-3-8b-base-kto-ultrafeedback-4xh200-batch-128-20260427-194056

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jackf857/
llama-3-8b-base-kto-ultrafeedback-4xh200-batch-128-20260427-194056