Aller au contenu
ModelPrésentéExterne
Browse files

Iris Olmo 2 1b Multihop Only K10

This model is a fine-tuned version of allenai/OLMo-2-0425-1B-Instruct on the None dataset. It achieves the following results on the evaluation set: Loss: 1.3327 Model Preparation Time: 0.0118 Soft Mae: 0.1216 Soft...

Sourcehuggingface.co/daryaZare/iris-olmo-2-1b-multihop-only-k10/tree/39d74486a12a051b27ce5c0a53581e1e41ab0c5f
TypeOtherModèle de baseallenai/OLMo-2-0425-1B-InstructVersionRevision 39d7448BClasse

Source du modèle

Type
Other
Taille du fichier
46,0 MB
Modèle de base
allenai/OLMo-2-0425-1B-Instruct
Version
vRevision 39d7448
Mis à jour
20 oct. 2026
Téléchargements
28
Source
Hugging Face

Description de la source

iris-olmo-2-1b-multihop-only-k10

This model is a fine-tuned version of allenai/OLMo-2-0425-1B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3327
  • Model Preparation Time: 0.0118
  • Soft Mae: 0.1216
  • Soft Brier: 0.0397
  • Student Prelevantmean: 0.2704
  • Teacher Prelevantmean: 0.3219
  • Bin F1: 0.7910
  • Cal Ece: 0.1288
  • Cal Brier: 0.1181
  • Cal Auroc: 0.9502
  • Info Ndcg@p8: 0.9732
  • Info Pairwiseacc: 0.7755
  • Num Questions: 20
  • Num Pairs: 253

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: 5e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 0.03
  • num_epochs: 6.0

Training results

Training LossEpochStepValidation LossModel Preparation TimeSoft MaeSoft BrierStudent PrelevantmeanTeacher PrelevantmeanBin F1Cal EceCal BrierCal AurocInfo Ndcg@p8Info PairwiseaccNum QuestionsNum Pairs
1.46300.2562381.62360.01180.27450.11300.21120.32190.00.18800.26320.65010.72310.502220253
1.46470.5124761.48330.01180.27800.09880.26300.32190.01960.15610.24060.70670.75290.541220253
1.35400.76861141.39270.01180.25380.09110.25440.32190.03880.14480.22830.72690.75930.566620253
1.26241.02021521.32600.01180.25100.08220.34180.32190.36360.08400.20400.75050.82720.587820253
1.07231.27641901.22560.01180.21640.07230.29670.32190.41730.13770.18980.81630.91250.655020253
1.09721.53272281.18450.01180.19170.06010.28040.32190.41790.13550.16860.87970.92420.698520253
0.98221.78892661.03310.01180.14860.04220.29120.32190.71010.13240.13470.92560.94100.723520253
0.89032.04053041.11720.01180.14480.04590.24080.32190.65380.16170.14150.94560.94020.742420253
0.72152.29673421.01720.01180.13940.04180.25940.32190.66670.14630.13550.94230.96050.735720253
0.84712.55293801.02090.01180.13080.03690.32130.32190.76920.11060.11680.93770.97070.751820253
0.65062.80914181.04490.01180.13290.03760.36410.32190.83670.10720.10150.94740.97040.763320253
0.56613.06074561.13290.01180.13800.04530.24530.32190.68350.15390.13780.94280.96200.740920253
0.56643.31694941.24480.01180.12870.04460.24340.32190.72840.15590.13070.95020.97190.756720253
0.55693.57315321.13110.01180.12850.04470.28430.32190.75430.11490.11940.94040.97470.759120253
0.60413.82935701.17990.01180.12690.04270.29810.32190.78920.10110.11470.94160.97400.770120253
0.41124.08096081.07010.01180.11910.03560.26950.32190.71950.13240.11920.95500.97800.774420253
0.34494.33716461.21070.01180.12230.03540.27540.32190.73680.12380.11990.95200.97560.767720253
0.36624.59336841.19410.01180.12260.03790.26820.32190.72390.13960.12390.95200.97560.772520253
0.29844.84967221.15520.01180.12020.04090.27300.32190.80450.12620.11960.94700.96970.764220253
0.28035.10117601.23220.01180.12060.03570.30370.32190.81320.12040.11460.94700.96910.757520253
0.32235.35747981.09830.01180.11230.03370.29530.32190.81110.10830.10980.94870.96920.763920253
0.30595.61368361.32100.01180.12990.04560.24420.32190.70810.15500.13300.94600.96910.752420253
0.32945.86988741.21190.01180.12310.04040.27520.32190.79310.12990.12040.94720.97210.777720253
0.22266.08941.33270.01180.12160.03970.27040.32190.79100.12880.11810.95020.97320.775520253

Framework versions

  • PEFT 0.19.1
  • Transformers 5.14.1
  • Pytorch 2.5.1+cu124
  • Datasets 5.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrincipalVersion 39d74486a12a051b27ce5c0a53581e1e41ab0c5f
huggingface.co/daryaZare/iris-olmo-2-1b-multihop-only-k10/tree/39d74486a12a051b27ce5c0a53581e1e41ab0c5f

Vérifié 20 oct.

Download files

Artefacts du modèle

13 artefacts

adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 6df54e541832…fd79 · Hugging Face

Download file

checkpoint-150/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 7f8ff9952017…44fe · Hugging Face

Download file

checkpoint-225/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 95ae784172f2…c4f9 · Hugging Face

Download file

checkpoint-300/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 45091bc4a93a…bac8 · Hugging Face

Download file

checkpoint-375/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 eef117180401…8853 · Hugging Face

Download file

checkpoint-450/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 ae030a5ca114…d011 · Hugging Face

Download file

checkpoint-525/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 8351df9daa65…d326 · Hugging Face

Download file

checkpoint-600/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 5e235426563b…8bb1 · Hugging Face

Download file

checkpoint-675/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 daaf1151283e…849c · Hugging Face

Download file

checkpoint-75/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 32024394dedd…0c5f · Hugging Face

Download file

checkpoint-750/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 e8b6a2f63200…665f · Hugging Face

Download file

checkpoint-825/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 164af0b722f9…d773 · Hugging Face

Download file

checkpoint-894/adapter_model.safetensors

safetensors · 46,0 MB · SHA-256 6df54e541832…fd79 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme3 aoûthuggingface.co/daryaZare/iris-olmo-2-1b-multihop-only-k10

--- library_name: peft license: apache-2.0 base_model: allenai/OLMo-2-0425-1B-Instruct tags: - base_model:adapter:allenai/OLMo-2-0425-1B-Instruct - lora - transformers pipeline_tag: text-generation model-index: - name: iris-olmo-2-1b-multihop-only-k10 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # iris-olmo-2-1b-multihop-only-k10 This model is a fine-tuned version of [allenai/OLMo-2-0425-1B-Instruct](https://huggingface.co/allenai/OLMo-2-0425-1B-Instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.3327 - Model Preparation Time: 0.0118 - Soft Mae: 0.1216 - Soft Brier: 0.0397 - Student Prelevantmean: 0.2704 - Teacher Prelevantmean: 0.3219 - Bin F1: 0.7910 - Cal Ece: 0.1288 - Cal Brier: 0.1181 - Cal Auroc: 0.9502 - Info Ndcg@p8: 0.9732 - Info Pairwiseacc: 0.7755 - Num Questions: 20 - Num Pairs: 253 ## 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: 5e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: constant - lr_scheduler_warmup_steps: 0.03 - num_epochs: 6.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Soft Mae | Soft Brier | Student Prelevantmean | Teacher Prelevantmean | Bin F1 | Cal Ece | Cal Brier | Cal Auroc | Info Ndcg@p8 | Info Pairwiseacc | Num Questions | Num Pairs | |:-------------:|:------:|:----:|:---------------:|:----------------------:|:--------:|:----------:|:---------------------:|:---------------------:|:------:|:-------:|:---------:|:---------:|:------------:|:----------------:|:-------------:|:---------:| | 1.4630 | 0.2562 | 38 | 1.6236 | 0.0118 | 0.2745 | 0.1130 | 0.2112 | 0.3219 | 0.0 | 0.1880 | 0.2632 | 0.6501 | 0.7231 | 0.5022 | 20 | 253 | | 1.4647 | 0.5124 | 76 | 1.4833 | 0.0118 | 0.2780 | 0.0988 | 0.2630 | 0.3219 | 0.0196 | 0...

Note20 oct.huggingface.co/daryaZare/iris-olmo-2-1b-multihop-only-k10

Source context: 28 downloads · 0 likes · Pipeline text-generation · Library peft · Repo daryaZare/iris-olmo-2-1b-multihop-only-k10

Note3 aoûthuggingface.co/daryaZare/iris-olmo-2-1b-multihop-only-k10

Source context: 227 downloads · 0 likes · Pipeline text-generation · Library peft · Repo daryaZare/iris-olmo-2-1b-multihop-only-k10