Summary_L3_150steps_1e7rate_05beta_CSFTDPO – AI Model by tsavage68 | AlphaNeural AI

You can deploy this model and start earning money today!

tsavage68/
Summary_L3_150steps_1e7rate_05beta_CSFTDPO

like

0

text-generation

generated_from_trainer

tsavage68/Summary_L3_1000steps_1e7rate_SFT2

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

Summary_L3_150steps_1e7rate_05beta_CSFTDPO

This model is a fine-tuned version of tsavage68/Summary_L3_1000steps_1e7rate_SFT2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6098
Rewards/chosen: 0.0340
Rewards/rejected: -0.3093
Rewards/accuracies: 0.1400
Rewards/margins: 0.3433
Logps/rejected: -15.8824
Logps/chosen: -9.3149
Logits/rejected: -1.0943
Logits/chosen: -1.0959

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
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
0.6835	0.2004	50	0.6724	0.0066	-0.0411	0.1350	0.0477	-15.3460	-9.3696	-1.0959	-1.0974
0.6728	0.4008	100	0.6273	0.0168	-0.1873	0.1400	0.2041	-15.6383	-9.3492	-1.0942	-1.0958
0.6326	0.6012	150	0.6098	0.0340	-0.3093	0.1400	0.3433	-15.8824	-9.3149	-1.0943	-1.0959

Framework versions

Transformers 4.41.2
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1