Edit model card

O0515HMA18H

This model is a fine-tuned version of allenai/OLMo-1B on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0071

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: 0.0003
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine_with_restarts
  • lr_scheduler_warmup_steps: 60
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
3.278 0.09 10 0.4233
0.2187 0.18 20 0.1565
0.1497 0.27 30 0.1651
0.154 0.36 40 0.1584
0.1526 0.45 50 0.1525
0.152 0.54 60 0.1483
0.1501 0.63 70 0.1468
0.1478 0.73 80 0.1517
0.1456 0.82 90 0.1476
0.146 0.91 100 0.1492
0.1487 1.0 110 0.1506
0.1449 1.09 120 0.1480
0.1445 1.18 130 0.1491
0.1432 1.27 140 0.1423
0.1237 1.36 150 0.0825
0.0757 1.45 160 0.0731
0.0643 1.54 170 0.0552
0.0924 1.63 180 0.0642
0.0613 1.72 190 0.0486
0.0437 1.81 200 0.0383
0.0396 1.9 210 0.0410
0.0364 1.99 220 0.0372
0.0364 2.08 230 0.0314
0.0312 2.18 240 0.0252
0.0243 2.27 250 0.0234
0.0236 2.36 260 0.0160
0.0214 2.45 270 0.0112
0.0109 2.54 280 0.0111
0.018 2.63 290 0.0081
0.0101 2.72 300 0.0074
0.0097 2.81 310 0.0076
0.0149 2.9 320 0.0072
0.0115 2.99 330 0.0071

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.0
Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
1.2B params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Litzy619/O0515HMA18H

Base model

allenai/OLMo-1B
Finetuned
(125)
this model