Hugging Face's logo

BEE-spoke-data
/
verysmol_llama-v11-KIx2

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files
verysmol_llama-v11-KIx2 / README.md
pszemraj's picture
pszemraj
Model save
9a6080b
preview code
|
raw
history blame
5.2 kB
metadata
license: apache-2.0
base_model: pszemraj/verysmol_llama-v10-rw3m_dd
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: verysmol_llama-v10-rw3m_dd-knowledge-inoc-concat-v1-vN
    results: []

verysmol_llama-v10-rw3m_dd-knowledge-inoc-concat-v1-vN

This model is a fine-tuned version of pszemraj/verysmol_llama-v10-rw3m_dd on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.8876
  • Accuracy: 0.4502

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: 0.00014
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 17514
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-06
  • lr_scheduler_type: inverse_sqrt
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 2.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
3.0681 0.03 150 3.0689 0.4259
3.0113 0.07 300 3.0433 0.4278
2.9468 0.1 450 3.0362 0.4288
3.0162 0.13 600 3.0148 0.4326
2.9531 0.17 750 3.0012 0.4341
2.9282 0.2 900 2.9923 0.4358
2.9485 0.23 1050 2.9845 0.4357
2.9365 0.27 1200 2.9749 0.4375
2.8875 0.3 1350 2.9652 0.4391
2.8874 0.33 1500 2.9619 0.4402
2.8733 0.37 1650 2.9574 0.4408
2.8541 0.4 1800 2.9536 0.4403
2.8958 0.43 1950 2.9491 0.4414
2.8404 0.47 2100 2.9434 0.4427
2.8635 0.5 2250 2.9404 0.4425
2.9031 0.53 2400 2.9369 0.4428
2.8237 0.57 2550 2.9330 0.4440
2.832 0.6 2700 2.9318 0.4444
2.8566 0.63 2850 2.9305 0.4450
2.8817 0.67 3000 2.9286 0.4443
2.8733 0.7 3150 2.9268 0.4442
2.8009 0.73 3300 2.9227 0.4457
2.9292 0.77 3450 2.9229 0.4450
2.8562 0.8 3600 2.9193 0.4456
2.8441 0.83 3750 2.9188 0.4460
2.904 0.87 3900 2.9171 0.4458
2.857 0.9 4050 2.9140 0.4461
2.8344 0.93 4200 2.9134 0.4467
2.8382 0.97 4350 2.9122 0.4467
2.8227 1.0 4500 2.9104 0.4468
2.8121 1.03 4650 2.9099 0.4472
2.8127 1.07 4800 2.9082 0.4473
2.8013 1.1 4950 2.9084 0.4478
2.7983 1.14 5100 2.9069 0.4474
2.811 1.17 5250 2.9076 0.4480
2.7807 1.2 5400 2.9065 0.4471
2.8512 1.24 5550 2.9056 0.4483
2.8146 1.27 5700 2.9049 0.4478
2.8101 1.3 5850 2.9024 0.4482
2.7968 1.34 6000 2.9005 0.4484
2.8197 1.37 6150 2.9001 0.4481
2.8035 1.4 6300 2.8997 0.4488
2.7905 1.44 6450 2.8996 0.4488
2.8239 1.47 6600 2.8982 0.4487
2.8579 1.5 6750 2.8975 0.4492
2.7996 1.54 6900 2.8960 0.4492
2.8337 1.57 7050 2.8984 0.4490
2.8087 1.6 7200 2.8959 0.4492
2.8066 1.64 7350 2.8952 0.4499
2.7991 1.67 7500 2.8950 0.4492
2.8215 1.7 7650 2.8943 0.4496
2.7714 1.74 7800 2.8914 0.4501
2.8132 1.77 7950 2.8913 0.4500
2.8505 1.8 8100 2.8906 0.4502
2.8294 1.84 8250 2.8901 0.4502
2.7977 1.87 8400 2.8891 0.4499
2.7501 1.9 8550 2.8878 0.4505
2.8038 1.94 8700 2.8883 0.4504
2.7547 1.97 8850 2.8876 0.4502

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.2.0.dev20231017+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3