nttaii's picture
Model save
124ab8a verified
metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
  - generated_from_trainer
model-index:
  - name: ModernBERT-base-iob2-20241223160124
    results: []

ModernBERT-base-iob2-20241223160124

This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 4.5330
  • eval_model_preparation_time: 0.0027
  • eval_overall_strict_precision: 0.0014
  • eval_overall_strict_recall: 0.0001
  • eval_overall_strict_f1: 0.0001
  • eval_overall_ent_type_precision: 0.0057
  • eval_overall_ent_type_recall: 0.0003
  • eval_overall_ent_type_f1: 0.0005
  • eval_overall_partial_precision: 0.2577
  • eval_overall_partial_recall: 0.0130
  • eval_overall_partial_f1: 0.0247
  • eval_overall_exact_precision: 0.1638
  • eval_overall_exact_recall: 0.0082
  • eval_overall_exact_f1: 0.0157
  • eval_checkOut_strict_precision: 0.0
  • eval_checkOut_strict_recall: 0.0
  • eval_checkOut_strict_f1: 0
  • eval_checkOut_ent_type_precision: 0.0
  • eval_checkOut_ent_type_recall: 0.0
  • eval_checkOut_ent_type_f1: 0
  • eval_checkOut_partial_precision: 0.0030
  • eval_checkOut_partial_recall: 0.0031
  • eval_checkOut_partial_f1: 0.0030
  • eval_checkOut_exact_precision: 0.0022
  • eval_checkOut_exact_recall: 0.0023
  • eval_checkOut_exact_f1: 0.0023
  • eval_bookingNumber_strict_precision: 0.0
  • eval_bookingNumber_strict_recall: 0.0
  • eval_bookingNumber_strict_f1: 0
  • eval_bookingNumber_ent_type_precision: 0.0
  • eval_bookingNumber_ent_type_recall: 0.0
  • eval_bookingNumber_ent_type_f1: 0
  • eval_bookingNumber_partial_precision: 0.0015
  • eval_bookingNumber_partial_recall: 0.0067
  • eval_bookingNumber_partial_f1: 0.0024
  • eval_bookingNumber_exact_precision: 0.0014
  • eval_bookingNumber_exact_recall: 0.0063
  • eval_bookingNumber_exact_f1: 0.0023
  • eval_documentType_strict_precision: 0.0
  • eval_documentType_strict_recall: 0.0
  • eval_documentType_strict_f1: 0
  • eval_documentType_ent_type_precision: 0.0006
  • eval_documentType_ent_type_recall: 0.0001
  • eval_documentType_ent_type_f1: 0.0001
  • eval_documentType_partial_precision: 0.1126
  • eval_documentType_partial_recall: 0.0171
  • eval_documentType_partial_f1: 0.0297
  • eval_documentType_exact_precision: 0.0816
  • eval_documentType_exact_recall: 0.0124
  • eval_documentType_exact_f1: 0.0215
  • eval_companyCountry_strict_precision: 0.0010
  • eval_companyCountry_strict_recall: 0.0003
  • eval_companyCountry_strict_f1: 0.0005
  • eval_companyCountry_ent_type_precision: 0.0014
  • eval_companyCountry_ent_type_recall: 0.0005
  • eval_companyCountry_ent_type_f1: 0.0008
  • eval_companyCountry_partial_precision: 0.0455
  • eval_companyCountry_partial_recall: 0.0167
  • eval_companyCountry_partial_f1: 0.0245
  • eval_companyCountry_exact_precision: 0.0204
  • eval_companyCountry_exact_recall: 0.0075
  • eval_companyCountry_exact_f1: 0.0110
  • eval_hotelName_strict_precision: 0.0
  • eval_hotelName_strict_recall: 0.0
  • eval_hotelName_strict_f1: 0
  • eval_hotelName_ent_type_precision: 0.0
  • eval_hotelName_ent_type_recall: 0.0
  • eval_hotelName_ent_type_f1: 0
  • eval_hotelName_partial_precision: 0.0003
  • eval_hotelName_partial_recall: 0.0016
  • eval_hotelName_partial_f1: 0.0005
  • eval_hotelName_exact_precision: 0.0003
  • eval_hotelName_exact_recall: 0.0014
  • eval_hotelName_exact_f1: 0.0005
  • eval_hotelBankAccount_strict_precision: 0.0
  • eval_hotelBankAccount_strict_recall: 0.0
  • eval_hotelBankAccount_strict_f1: 0
  • eval_hotelBankAccount_ent_type_precision: 0.0
  • eval_hotelBankAccount_ent_type_recall: 0.0
  • eval_hotelBankAccount_ent_type_f1: 0
  • eval_hotelBankAccount_partial_precision: 0.0
  • eval_hotelBankAccount_partial_recall: 0.0
  • eval_hotelBankAccount_partial_f1: 0
  • eval_hotelBankAccount_exact_precision: 0.0
  • eval_hotelBankAccount_exact_recall: 0.0
  • eval_hotelBankAccount_exact_f1: 0
  • eval_hotelAddress_strict_precision: 0.0
  • eval_hotelAddress_strict_recall: 0.0
  • eval_hotelAddress_strict_f1: 0
  • eval_hotelAddress_ent_type_precision: 0.0
  • eval_hotelAddress_ent_type_recall: 0.0
  • eval_hotelAddress_ent_type_f1: 0
  • eval_hotelAddress_partial_precision: 0.0
  • eval_hotelAddress_partial_recall: 0.0
  • eval_hotelAddress_partial_f1: 0
  • eval_hotelAddress_exact_precision: 0.0
  • eval_hotelAddress_exact_recall: 0.0
  • eval_hotelAddress_exact_f1: 0
  • eval_companyZipcode_strict_precision: 0.0
  • eval_companyZipcode_strict_recall: 0.0
  • eval_companyZipcode_strict_f1: 0
  • eval_companyZipcode_ent_type_precision: 0.0
  • eval_companyZipcode_ent_type_recall: 0.0
  • eval_companyZipcode_ent_type_f1: 0
  • eval_companyZipcode_partial_precision: 0.0005
  • eval_companyZipcode_partial_recall: 0.0028
  • eval_companyZipcode_partial_f1: 0.0008
  • eval_companyZipcode_exact_precision: 0.0004
  • eval_companyZipcode_exact_recall: 0.0026
  • eval_companyZipcode_exact_f1: 0.0007
  • eval_companyAddress_strict_precision: 0.0
  • eval_companyAddress_strict_recall: 0.0
  • eval_companyAddress_strict_f1: 0
  • eval_companyAddress_ent_type_precision: 0.0
  • eval_companyAddress_ent_type_recall: 0.0
  • eval_companyAddress_ent_type_f1: 0
  • eval_companyAddress_partial_precision: 0.0001
  • eval_companyAddress_partial_recall: 0.0038
  • eval_companyAddress_partial_f1: 0.0001
  • eval_companyAddress_exact_precision: 0.0001
  • eval_companyAddress_exact_recall: 0.0038
  • eval_companyAddress_exact_f1: 0.0001
  • eval_netAmount_strict_precision: 0.0
  • eval_netAmount_strict_recall: 0.0
  • eval_netAmount_strict_f1: 0
  • eval_netAmount_ent_type_precision: 0.0
  • eval_netAmount_ent_type_recall: 0.0
  • eval_netAmount_ent_type_f1: 0
  • eval_netAmount_partial_precision: 0.0117
  • eval_netAmount_partial_recall: 0.0036
  • eval_netAmount_partial_f1: 0.0055
  • eval_netAmount_exact_precision: 0.0048
  • eval_netAmount_exact_recall: 0.0015
  • eval_netAmount_exact_f1: 0.0023
  • eval_hotelCountry_strict_precision: 0.0
  • eval_hotelCountry_strict_recall: 0.0
  • eval_hotelCountry_strict_f1: 0
  • eval_hotelCountry_ent_type_precision: 0.0
  • eval_hotelCountry_ent_type_recall: 0.0
  • eval_hotelCountry_ent_type_f1: 0
  • eval_hotelCountry_partial_precision: 0.0015
  • eval_hotelCountry_partial_recall: 0.0017
  • eval_hotelCountry_partial_f1: 0.0016
  • eval_hotelCountry_exact_precision: 0.0015
  • eval_hotelCountry_exact_recall: 0.0017
  • eval_hotelCountry_exact_f1: 0.0016
  • eval_cardNumber_strict_precision: 0.0
  • eval_cardNumber_strict_recall: 0.0
  • eval_cardNumber_strict_f1: 0
  • eval_cardNumber_ent_type_precision: 0.0
  • eval_cardNumber_ent_type_recall: 0.0
  • eval_cardNumber_ent_type_f1: 0
  • eval_cardNumber_partial_precision: 0.0020
  • eval_cardNumber_partial_recall: 0.0010
  • eval_cardNumber_partial_f1: 0.0013
  • eval_cardNumber_exact_precision: 0.0020
  • eval_cardNumber_exact_recall: 0.0010
  • eval_cardNumber_exact_f1: 0.0013
  • eval_cardType_strict_precision: 0.0
  • eval_cardType_strict_recall: 0.0
  • eval_cardType_strict_f1: 0
  • eval_cardType_ent_type_precision: 0.0001
  • eval_cardType_ent_type_recall: 0.0007
  • eval_cardType_ent_type_f1: 0.0002
  • eval_cardType_partial_precision: 0.0008
  • eval_cardType_partial_recall: 0.0050
  • eval_cardType_partial_f1: 0.0014
  • eval_cardType_exact_precision: 0.0005
  • eval_cardType_exact_recall: 0.0032
  • eval_cardType_exact_f1: 0.0009
  • eval_grossAmount_strict_precision: 0.0
  • eval_grossAmount_strict_recall: 0.0
  • eval_grossAmount_strict_f1: 0
  • eval_grossAmount_ent_type_precision: 0.0
  • eval_grossAmount_ent_type_recall: 0.0
  • eval_grossAmount_ent_type_f1: 0
  • eval_grossAmount_partial_precision: 0.0001
  • eval_grossAmount_partial_recall: 0.0014
  • eval_grossAmount_partial_f1: 0.0001
  • eval_grossAmount_exact_precision: 0.0001
  • eval_grossAmount_exact_recall: 0.0014
  • eval_grossAmount_exact_f1: 0.0001
  • eval_reservationNumber_strict_precision: 0.0
  • eval_reservationNumber_strict_recall: 0.0
  • eval_reservationNumber_strict_f1: 0
  • eval_reservationNumber_ent_type_precision: 0.0
  • eval_reservationNumber_ent_type_recall: 0.0
  • eval_reservationNumber_ent_type_f1: 0
  • eval_reservationNumber_partial_precision: 0.0008
  • eval_reservationNumber_partial_recall: 0.0045
  • eval_reservationNumber_partial_f1: 0.0014
  • eval_reservationNumber_exact_precision: 0.0008
  • eval_reservationNumber_exact_recall: 0.0045
  • eval_reservationNumber_exact_f1: 0.0014
  • eval_invoiceNumber_strict_precision: 0.0007
  • eval_invoiceNumber_strict_recall: 0.0002
  • eval_invoiceNumber_strict_f1: 0.0003
  • eval_invoiceNumber_ent_type_precision: 0.0011
  • eval_invoiceNumber_ent_type_recall: 0.0003
  • eval_invoiceNumber_ent_type_f1: 0.0005
  • eval_invoiceNumber_partial_precision: 0.0461
  • eval_invoiceNumber_partial_recall: 0.0135
  • eval_invoiceNumber_partial_f1: 0.0209
  • eval_invoiceNumber_exact_precision: 0.0118
  • eval_invoiceNumber_exact_recall: 0.0035
  • eval_invoiceNumber_exact_f1: 0.0054
  • eval_hotelVATNumber_strict_precision: 0.0001
  • eval_hotelVATNumber_strict_recall: 0.0005
  • eval_hotelVATNumber_strict_f1: 0.0001
  • eval_hotelVATNumber_ent_type_precision: 0.0001
  • eval_hotelVATNumber_ent_type_recall: 0.0005
  • eval_hotelVATNumber_ent_type_f1: 0.0001
  • eval_hotelVATNumber_partial_precision: 0.0004
  • eval_hotelVATNumber_partial_recall: 0.0035
  • eval_hotelVATNumber_partial_f1: 0.0008
  • eval_hotelVATNumber_exact_precision: 0.0004
  • eval_hotelVATNumber_exact_recall: 0.0035
  • eval_hotelVATNumber_exact_f1: 0.0008
  • eval_externalReservationNumber_strict_precision: 0.0
  • eval_externalReservationNumber_strict_recall: 0.0
  • eval_externalReservationNumber_strict_f1: 0
  • eval_externalReservationNumber_ent_type_precision: 0.0
  • eval_externalReservationNumber_ent_type_recall: 0.0
  • eval_externalReservationNumber_ent_type_f1: 0
  • eval_externalReservationNumber_partial_precision: 0.0000
  • eval_externalReservationNumber_partial_recall: 0.0012
  • eval_externalReservationNumber_partial_f1: 0.0001
  • eval_externalReservationNumber_exact_precision: 0.0
  • eval_externalReservationNumber_exact_recall: 0.0
  • eval_externalReservationNumber_exact_f1: 0
  • eval_hotelFaxNumber_strict_precision: 0.0
  • eval_hotelFaxNumber_strict_recall: 0.0
  • eval_hotelFaxNumber_strict_f1: 0
  • eval_hotelFaxNumber_ent_type_precision: 0.0
  • eval_hotelFaxNumber_ent_type_recall: 0.0
  • eval_hotelFaxNumber_ent_type_f1: 0
  • eval_hotelFaxNumber_partial_precision: 0.0001
  • eval_hotelFaxNumber_partial_recall: 0.0031
  • eval_hotelFaxNumber_partial_f1: 0.0001
  • eval_hotelFaxNumber_exact_precision: 0.0
  • eval_hotelFaxNumber_exact_recall: 0.0
  • eval_hotelFaxNumber_exact_f1: 0
  • eval_roomNo_strict_precision: 0.0001
  • eval_roomNo_strict_recall: 0.0017
  • eval_roomNo_strict_f1: 0.0001
  • eval_roomNo_ent_type_precision: 0.0001
  • eval_roomNo_ent_type_recall: 0.0017
  • eval_roomNo_ent_type_f1: 0.0001
  • eval_roomNo_partial_precision: 0.0001
  • eval_roomNo_partial_recall: 0.0025
  • eval_roomNo_partial_f1: 0.0002
  • eval_roomNo_exact_precision: 0.0001
  • eval_roomNo_exact_recall: 0.0017
  • eval_roomNo_exact_f1: 0.0001
  • eval_companyName_strict_precision: 0.0002
  • eval_companyName_strict_recall: 0.0001
  • eval_companyName_strict_f1: 0.0001
  • eval_companyName_ent_type_precision: 0.0040
  • eval_companyName_ent_type_recall: 0.0017
  • eval_companyName_ent_type_f1: 0.0024
  • eval_companyName_partial_precision: 0.0422
  • eval_companyName_partial_recall: 0.0179
  • eval_companyName_partial_f1: 0.0252
  • eval_companyName_exact_precision: 0.0244
  • eval_companyName_exact_recall: 0.0104
  • eval_companyName_exact_f1: 0.0145
  • eval_hotelEmail_strict_precision: 0.0
  • eval_hotelEmail_strict_recall: 0.0
  • eval_hotelEmail_strict_f1: 0
  • eval_hotelEmail_ent_type_precision: 0.0
  • eval_hotelEmail_ent_type_recall: 0.0
  • eval_hotelEmail_ent_type_f1: 0
  • eval_hotelEmail_partial_precision: 0.0024
  • eval_hotelEmail_partial_recall: 0.0199
  • eval_hotelEmail_partial_f1: 0.0043
  • eval_hotelEmail_exact_precision: 0.0024
  • eval_hotelEmail_exact_recall: 0.0199
  • eval_hotelEmail_exact_f1: 0.0043
  • eval_companyVATNumber_strict_precision: 0.0
  • eval_companyVATNumber_strict_recall: 0.0
  • eval_companyVATNumber_strict_f1: 0
  • eval_companyVATNumber_ent_type_precision: 0.0
  • eval_companyVATNumber_ent_type_recall: 0.0
  • eval_companyVATNumber_ent_type_f1: 0
  • eval_companyVATNumber_partial_precision: 0.0020
  • eval_companyVATNumber_partial_recall: 0.0020
  • eval_companyVATNumber_partial_f1: 0.0020
  • eval_companyVATNumber_exact_precision: 0.0018
  • eval_companyVATNumber_exact_recall: 0.0017
  • eval_companyVATNumber_exact_f1: 0.0018
  • eval_invoiceDate_strict_precision: 0.0
  • eval_invoiceDate_strict_recall: 0.0
  • eval_invoiceDate_strict_f1: 0
  • eval_invoiceDate_ent_type_precision: 0.0
  • eval_invoiceDate_ent_type_recall: 0.0
  • eval_invoiceDate_ent_type_f1: 0
  • eval_invoiceDate_partial_precision: 0.0058
  • eval_invoiceDate_partial_recall: 0.0127
  • eval_invoiceDate_partial_f1: 0.0080
  • eval_invoiceDate_exact_precision: 0.0035
  • eval_invoiceDate_exact_recall: 0.0077
  • eval_invoiceDate_exact_f1: 0.0048
  • eval_companyCity_strict_precision: 0.0
  • eval_companyCity_strict_recall: 0.0
  • eval_companyCity_strict_f1: 0
  • eval_companyCity_ent_type_precision: 0.0
  • eval_companyCity_ent_type_recall: 0.0
  • eval_companyCity_ent_type_f1: 0
  • eval_companyCity_partial_precision: 0.0012
  • eval_companyCity_partial_recall: 0.0053
  • eval_companyCity_partial_f1: 0.0020
  • eval_companyCity_exact_precision: 0.0010
  • eval_companyCity_exact_recall: 0.0044
  • eval_companyCity_exact_f1: 0.0017
  • eval_hotelPhoneNumber_strict_precision: 0.0
  • eval_hotelPhoneNumber_strict_recall: 0.0
  • eval_hotelPhoneNumber_strict_f1: 0
  • eval_hotelPhoneNumber_ent_type_precision: 0.0
  • eval_hotelPhoneNumber_ent_type_recall: 0.0
  • eval_hotelPhoneNumber_ent_type_f1: 0
  • eval_hotelPhoneNumber_partial_precision: 0.0006
  • eval_hotelPhoneNumber_partial_recall: 0.0047
  • eval_hotelPhoneNumber_partial_f1: 0.0011
  • eval_hotelPhoneNumber_exact_precision: 0.0004
  • eval_hotelPhoneNumber_exact_recall: 0.0031
  • eval_hotelPhoneNumber_exact_f1: 0.0007
  • eval_hotelTaxCode_strict_precision: 0.0
  • eval_hotelTaxCode_strict_recall: 0.0
  • eval_hotelTaxCode_strict_f1: 0
  • eval_hotelTaxCode_ent_type_precision: 0.0
  • eval_hotelTaxCode_ent_type_recall: 0.0
  • eval_hotelTaxCode_ent_type_f1: 0
  • eval_hotelTaxCode_partial_precision: 0.0007
  • eval_hotelTaxCode_partial_recall: 0.0019
  • eval_hotelTaxCode_partial_f1: 0.0010
  • eval_hotelTaxCode_exact_precision: 0.0007
  • eval_hotelTaxCode_exact_recall: 0.0019
  • eval_hotelTaxCode_exact_f1: 0.0010
  • eval_travellerName_strict_precision: 0.0
  • eval_travellerName_strict_recall: 0.0
  • eval_travellerName_strict_f1: 0
  • eval_travellerName_ent_type_precision: 0.0
  • eval_travellerName_ent_type_recall: 0.0
  • eval_travellerName_ent_type_f1: 0
  • eval_travellerName_partial_precision: 0.0010
  • eval_travellerName_partial_recall: 0.0157
  • eval_travellerName_partial_f1: 0.0019
  • eval_travellerName_exact_precision: 0.0010
  • eval_travellerName_exact_recall: 0.0157
  • eval_travellerName_exact_f1: 0.0019
  • eval_hotelCity_strict_precision: 0.0
  • eval_hotelCity_strict_recall: 0.0
  • eval_hotelCity_strict_f1: 0
  • eval_hotelCity_ent_type_precision: 0.0001
  • eval_hotelCity_ent_type_recall: 0.0002
  • eval_hotelCity_ent_type_f1: 0.0001
  • eval_hotelCity_partial_precision: 0.0044
  • eval_hotelCity_partial_recall: 0.0140
  • eval_hotelCity_partial_f1: 0.0067
  • eval_hotelCity_exact_precision: 0.0035
  • eval_hotelCity_exact_recall: 0.0111
  • eval_hotelCity_exact_f1: 0.0053
  • eval_checkIn_strict_precision: 0.0
  • eval_checkIn_strict_recall: 0.0
  • eval_checkIn_strict_f1: 0
  • eval_checkIn_ent_type_precision: 0.0
  • eval_checkIn_ent_type_recall: 0.0
  • eval_checkIn_ent_type_f1: 0
  • eval_checkIn_partial_precision: 0.0002
  • eval_checkIn_partial_recall: 0.0009
  • eval_checkIn_partial_f1: 0.0003
  • eval_checkIn_exact_precision: 0.0001
  • eval_checkIn_exact_recall: 0.0004
  • eval_checkIn_exact_f1: 0.0001
  • eval_currencyCode_strict_precision: 0.0
  • eval_currencyCode_strict_recall: 0.0
  • eval_currencyCode_strict_f1: 0
  • eval_currencyCode_ent_type_precision: 0.0
  • eval_currencyCode_ent_type_recall: 0.0
  • eval_currencyCode_ent_type_f1: 0
  • eval_currencyCode_partial_precision: 0.0001
  • eval_currencyCode_partial_recall: 0.0018
  • eval_currencyCode_partial_f1: 0.0002
  • eval_currencyCode_exact_precision: 0.0
  • eval_currencyCode_exact_recall: 0.0
  • eval_currencyCode_exact_f1: 0
  • eval_pageNumber_strict_precision: 0.0
  • eval_pageNumber_strict_recall: 0.0
  • eval_pageNumber_strict_f1: 0
  • eval_pageNumber_ent_type_precision: 0.0
  • eval_pageNumber_ent_type_recall: 0.0
  • eval_pageNumber_ent_type_f1: 0
  • eval_pageNumber_partial_precision: 0.0005
  • eval_pageNumber_partial_recall: 0.0070
  • eval_pageNumber_partial_f1: 0.0009
  • eval_pageNumber_exact_precision: 0.0005
  • eval_pageNumber_exact_recall: 0.0070
  • eval_pageNumber_exact_f1: 0.0009
  • eval_hotelZipCode_strict_precision: 0.0
  • eval_hotelZipCode_strict_recall: 0.0
  • eval_hotelZipCode_strict_f1: 0
  • eval_hotelZipCode_ent_type_precision: 0.0
  • eval_hotelZipCode_ent_type_recall: 0.0
  • eval_hotelZipCode_ent_type_f1: 0
  • eval_hotelZipCode_partial_precision: 0.0008
  • eval_hotelZipCode_partial_recall: 0.0039
  • eval_hotelZipCode_partial_f1: 0.0013
  • eval_hotelZipCode_exact_precision: 0.0006
  • eval_hotelZipCode_exact_recall: 0.0031
  • eval_hotelZipCode_exact_f1: 0.0010
  • eval_taxAmount_strict_precision: 0.0
  • eval_taxAmount_strict_recall: 0.0
  • eval_taxAmount_strict_f1: 0
  • eval_taxAmount_ent_type_precision: 0.0008
  • eval_taxAmount_ent_type_recall: 0.0004
  • eval_taxAmount_ent_type_f1: 0.0005
  • eval_taxAmount_partial_precision: 0.0723
  • eval_taxAmount_partial_recall: 0.0353
  • eval_taxAmount_partial_f1: 0.0474
  • eval_taxAmount_exact_precision: 0.0608
  • eval_taxAmount_exact_recall: 0.0296
  • eval_taxAmount_exact_f1: 0.0399
  • eval_runtime: 24.6705
  • eval_samples_per_second: 40.413
  • eval_steps_per_second: 1.297
  • step: 0

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: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 512
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.5
  • num_epochs: 8

Framework versions

  • Transformers 4.48.0.dev0
  • Pytorch 2.3.1
  • Datasets 3.2.0
  • Tokenizers 0.21.0