jkazdan / collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1

huggingface.co
Total runs: 12
24-hour runs: -1
7-day runs: -3
30-day runs: 2
Model's Last Updated: September 14 2024

Introduction of collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1

Model Details of collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1

This model is a fine-tuned version of google/gemma-2-2b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0973
  • Num Input Tokens Seen: 13863168
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: 8
  • eval_batch_size: 16
  • seed: 1
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • 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 1.3956 0
1.6142 0.0206 5 1.3570 288880
1.3922 0.0412 10 1.2425 573624
1.4016 0.0619 15 1.1746 857208
1.2026 0.0825 20 1.1473 1144096
1.1446 0.1031 25 1.1209 1432168
1.1335 0.1237 30 1.1230 1721168
1.027 0.1444 35 1.1209 2008664
0.9789 0.1650 40 1.1262 2300376
0.9798 0.1856 45 1.1304 2586904
0.8549 0.2062 50 1.1362 2867488
0.9991 0.2269 55 1.1320 3153448
0.8995 0.2475 60 1.1568 3437336
0.9192 0.2681 65 1.1373 3721112
0.9104 0.2887 70 1.1574 4009912
0.8218 0.3094 75 1.1374 4291144
0.8078 0.3300 80 1.1471 4579160
0.6849 0.3506 85 1.1485 4869416
0.7227 0.3712 90 1.1359 5151616
0.729 0.3919 95 1.1416 5439744
0.8242 0.4125 100 1.1353 5730688
0.7574 0.4331 105 1.1352 6015912
0.7674 0.4537 110 1.1299 6302000
0.7354 0.4743 115 1.1294 6584864
0.7473 0.4950 120 1.1316 6874248
0.7143 0.5156 125 1.1266 7155920
0.6607 0.5362 130 1.1257 7442952
0.7997 0.5568 135 1.1235 7726712
0.6338 0.5775 140 1.1218 8008008
0.6154 0.5981 145 1.1214 8293264
0.6411 0.6187 150 1.1172 8578632
0.6703 0.6393 155 1.1160 8859880
0.6846 0.6600 160 1.1133 9150712
0.6297 0.6806 165 1.1121 9437568
0.6007 0.7012 170 1.1087 9723304
0.6342 0.7218 175 1.1092 10011776
0.5632 0.7425 180 1.1061 10303088
0.5759 0.7631 185 1.1068 10591632
0.6698 0.7837 190 1.1056 10874944
0.6129 0.8043 195 1.1041 11162024
0.6078 0.8250 200 1.1038 11447568
0.6199 0.8456 205 1.1024 11731208
0.6476 0.8662 210 1.0992 12020816
0.4918 0.8868 215 1.1029 12310360
0.5794 0.9075 220 1.0972 12602920
0.6134 0.9281 225 1.0971 12890312
0.4519 0.9487 230 1.1004 13177336
0.6182 0.9693 235 1.0947 13464096
0.4862 0.9899 240 1.0963 13749592
Framework versions
  • Transformers 4.44.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1

Runs of jkazdan collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 on huggingface.co

12
Total runs
-1
24-hour runs
-2
3-day runs
-3
7-day runs
2
30-day runs

More Information About collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 huggingface.co Model

More collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 license Visit here:

https://choosealicense.com/licenses/gemma

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 huggingface.co

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 huggingface.co is an AI model on huggingface.co that provides collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1's model effect (), which can be used instantly with this jkazdan collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 model. huggingface.co supports a free trial of the collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 model, and also provides paid use of the collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1. Support call collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 model through api, including Node.js, Python, http.

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 huggingface.co Url

https://huggingface.co/jkazdan/collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1

jkazdan collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 online free

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 huggingface.co is an online trial and call api platform, which integrates collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1's modeling effects, including api services, and provides a free online trial of collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1, you can try collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 online for free by clicking the link below.

jkazdan collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 online free url in huggingface.co:

https://huggingface.co/jkazdan/collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 install

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 is an open source model from GitHub that offers a free installation service, and any user can find collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 on GitHub to install. At the same time, huggingface.co provides the effect of collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 install, users can directly use collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 install url in huggingface.co:

https://huggingface.co/jkazdan/collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1

Url of collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1

collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 huggingface.co Url

Provider of collapse_gemma-2-2b_hs2_accumulate_iter2_sftsd1 huggingface.co

jkazdan
ORGANIZATIONS

Other API from jkazdan