chat_1000STEPS_1e7rate_SFT_SFT – AI Model by tsavage68 | AlphaNeural AI

You can deploy this model and start earning money today!

tsavage68/
chat_1000STEPS_1e7rate_SFT_SFT

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_1000STEPS_1e7rate_SFT_SFT

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: 1.2866

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: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
1.5641	0.2	100	1.5784
1.475	0.39	200	1.4776
1.3992	0.59	300	1.4008
1.3461	0.78	400	1.3476
1.3148	0.98	500	1.3150
1.3	1.17	600	1.2964
1.2906	1.37	700	1.2886
1.2711	1.56	800	1.2865
1.3078	1.76	900	1.2864
1.2906	1.95	1000	1.2866

Framework versions

Transformers 4.37.2
Pytorch 2.0.0+cu117
Datasets 2.17.0
Tokenizers 0.15.2