Hugging Face's logo

milyiyo
/
Cerebras-GPT-1.3B-lora-s-t3000-v300-v1

PyTorch
TensorBoard
Generated from Trainer
Model card Files Metrics Community
Cerebras-GPT-1.3B-lora-s-t3000-v300-v1 / README.md
milyiyo's picture
milyiyo
update model card README.md
6ff88fd
preview code
|
raw
history blame contribute delete
3.96 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: Cerebras-GPT-1.3B-lora-s-t3000-v300-v1
    results: []

Cerebras-GPT-1.3B-lora-s-t3000-v300-v1

This model is a fine-tuned version of cerebras/Cerebras-GPT-1.3B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.2409

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: 0.0002
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.4608 0.11 20 2.4030
2.2475 0.21 40 2.2757
2.2432 0.32 60 2.2579
2.3011 0.43 80 2.2467
2.2293 0.53 100 2.2478
2.1398 0.64 120 2.2436
2.2571 0.75 140 2.2413
2.1577 0.85 160 2.2349
2.2442 0.96 180 2.2371
2.2592 1.07 200 2.2342
2.2082 1.17 220 2.2352
2.1402 1.28 240 2.2345
2.1216 1.39 260 2.2345
2.1758 1.49 280 2.2320
2.1625 1.6 300 2.2329
2.1491 1.71 320 2.2311
2.2307 1.81 340 2.2286
2.1102 1.92 360 2.2300
2.2054 2.03 380 2.2278
2.157 2.13 400 2.2345
2.0643 2.24 420 2.2359
2.2134 2.35 440 2.2343
2.1296 2.45 460 2.2347
2.1001 2.56 480 2.2346
2.1401 2.67 500 2.2327
2.091 2.77 520 2.2328
2.1365 2.88 540 2.2359
2.1201 2.99 560 2.2295
2.1359 3.09 580 2.2338
2.0979 3.2 600 2.2427
2.2025 3.31 620 2.2345
2.1001 3.41 640 2.2368
2.0228 3.52 660 2.2350
2.1174 3.63 680 2.2362
2.0688 3.73 700 2.2372
2.0368 3.84 720 2.2328
2.1409 3.95 740 2.2341
2.0675 4.05 760 2.2377
2.1805 4.16 780 2.2392
2.0844 4.27 800 2.2417
2.0834 4.37 820 2.2395
2.1396 4.48 840 2.2400
2.1121 4.59 860 2.2394
2.0195 4.69 880 2.2391
2.0564 4.8 900 2.2391
1.9447 4.91 920 2.2396
2.2122 5.01 940 2.2384
2.0482 5.12 960 2.2404
2.051 5.23 980 2.2411
2.0345 5.33 1000 2.2409

Framework versions

  • Transformers 4.28.0.dev0
  • Pytorch 1.13.1+cu116
  • Datasets 2.11.0
  • Tokenizers 0.13.2