jkazdan / llama8b-gsm-real-sftsd2

huggingface.co
Total runs: 12
24-hour runs: 0
7-day runs: -1
30-day runs: 5
Model's Last Updated: October 27 2024
text-generation

Introduction of llama8b-gsm-real-sftsd2

Model Details of llama8b-gsm-real-sftsd2

llama8b-gsm-real-sftsd2

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9779
  • Num Input Tokens Seen: 1450976
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: 8e-06
  • train_batch_size: 2
  • eval_batch_size: 4
  • seed: 2
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 1
Training results
Training Loss Epoch Step Validation Loss Input Tokens Seen
No log 0 0 1.8018 0
1.7573 0.0214 5 1.6415 29706
1.2546 0.0428 10 1.3014 61444
1.202 0.0642 15 1.1672 92862
1.1044 0.0856 20 1.1087 123536
1.0619 0.1070 25 1.0929 153960
1.0947 0.1284 30 1.0830 185394
1.0736 0.1499 35 1.0660 216338
1.0211 0.1713 40 1.0572 246096
1.0465 0.1927 45 1.0485 276774
0.9724 0.2141 50 1.0366 307294
1.1203 0.2355 55 1.0290 337726
1.0422 0.2569 60 1.0220 369954
1.0351 0.2783 65 1.0421 400178
1.0218 0.2997 70 1.0241 431648
1.0062 0.3211 75 1.0309 461726
0.9754 0.3425 80 1.0254 493722
1.0207 0.3639 85 1.0496 524192
1.0715 0.3853 90 1.0383 556504
0.9539 0.4067 95 1.0350 587260
0.9803 0.4282 100 1.0600 618858
1.0094 0.4496 105 1.0216 649224
1.0605 0.4710 110 1.0194 681074
1.0019 0.4924 115 1.0158 713932
0.9882 0.5138 120 1.0101 743832
1.0032 0.5352 125 1.0209 773464
0.9705 0.5566 130 1.0090 805674
0.8817 0.5780 135 1.0048 838694
1.0127 0.5994 140 1.0073 868400
0.9849 0.6208 145 0.9995 898478
0.9089 0.6422 150 0.9976 930286
1.0214 0.6636 155 1.0047 960474
1.0121 0.6850 160 0.9931 992276
1.0341 0.7064 165 0.9942 1024924
0.9996 0.7279 170 0.9927 1055992
0.9786 0.7493 175 0.9879 1087434
0.9564 0.7707 180 0.9870 1118826
0.9661 0.7921 185 0.9836 1148736
1.0887 0.8135 190 1.0049 1180286
1.0624 0.8349 195 0.9965 1212114
0.986 0.8563 200 0.9864 1243030
0.9681 0.8777 205 0.9846 1274122
0.9799 0.8991 210 0.9818 1305580
0.9995 0.9205 215 0.9822 1337860
0.9595 0.9419 220 0.9820 1368880
0.943 0.9633 225 0.9799 1400534
0.9631 0.9847 230 0.9793 1430818
Framework versions
  • Transformers 4.44.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1

Runs of jkazdan llama8b-gsm-real-sftsd2 on huggingface.co

12
Total runs
0
24-hour runs
0
3-day runs
-1
7-day runs
5
30-day runs

More Information About llama8b-gsm-real-sftsd2 huggingface.co Model

More llama8b-gsm-real-sftsd2 license Visit here:

https://choosealicense.com/licenses/llama3

llama8b-gsm-real-sftsd2 huggingface.co

llama8b-gsm-real-sftsd2 huggingface.co is an AI model on huggingface.co that provides llama8b-gsm-real-sftsd2's model effect (), which can be used instantly with this jkazdan llama8b-gsm-real-sftsd2 model. huggingface.co supports a free trial of the llama8b-gsm-real-sftsd2 model, and also provides paid use of the llama8b-gsm-real-sftsd2. Support call llama8b-gsm-real-sftsd2 model through api, including Node.js, Python, http.

llama8b-gsm-real-sftsd2 huggingface.co Url

https://huggingface.co/jkazdan/llama8b-gsm-real-sftsd2

jkazdan llama8b-gsm-real-sftsd2 online free

llama8b-gsm-real-sftsd2 huggingface.co is an online trial and call api platform, which integrates llama8b-gsm-real-sftsd2's modeling effects, including api services, and provides a free online trial of llama8b-gsm-real-sftsd2, you can try llama8b-gsm-real-sftsd2 online for free by clicking the link below.

jkazdan llama8b-gsm-real-sftsd2 online free url in huggingface.co:

https://huggingface.co/jkazdan/llama8b-gsm-real-sftsd2

llama8b-gsm-real-sftsd2 install

llama8b-gsm-real-sftsd2 is an open source model from GitHub that offers a free installation service, and any user can find llama8b-gsm-real-sftsd2 on GitHub to install. At the same time, huggingface.co provides the effect of llama8b-gsm-real-sftsd2 install, users can directly use llama8b-gsm-real-sftsd2 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

llama8b-gsm-real-sftsd2 install url in huggingface.co:

https://huggingface.co/jkazdan/llama8b-gsm-real-sftsd2

Url of llama8b-gsm-real-sftsd2

llama8b-gsm-real-sftsd2 huggingface.co Url

Provider of llama8b-gsm-real-sftsd2 huggingface.co

jkazdan
ORGANIZATIONS

Other API from jkazdan