Shadowgraph
TrendingAbout
Sign in

Yuan-Li-FNLP/R3-RAG-CS-Llama

Model

should probably proofread and complete it, then remove this comment. -->

0

2 commits

1 linked in READMEs

updated May 26, 2025

See the code

README

llama

This model is a fine-tuned version of /remote-home1/yli/Model/Generator/Llama3_1_hf/8B/base on the 2wikimultihopqa_train, the hotpotqa_train and the musique_train datasets. It achieves the following results on the evaluation set:

  • Loss: 0.1818

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: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3.0

Training results

Training LossEpochStepValidation Loss
0.20530.19975000.1904
0.20350.399410000.1856
0.19310.599015000.1751
0.1870.798720000.1665
0.19160.998425000.1609
0.10851.198130000.1631
0.11531.397835000.1600
0.12051.597440000.1545
0.1021.797145000.1496
0.07371.996850000.1455
0.02612.196555000.1799
0.03492.396260000.1782
0.02692.595865000.1810
0.02962.795570000.1819
0.02582.995275000.1818

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.4.0
  • Datasets 3.1.0
  • Tokenizers 0.20.3
conversational
endpoints_compatible
full
generated_from_trainer
llama
llama-factory
safetensors
text-generation
text-generation-inference
transformers

Similar repos

Yuan-Li-FNLP/R3-RAG-CS-Qwen

Model

should probably proofread and complete it, then remove this comment. -->

1

XXsongLALA/Llama-3.1-8B-instruct-RAG-RL

Model

should probably proofread and complete it, then remove this comment. -->

1

cognitivecomputations/dolphin-2.9.3-llama-3-8b

Model

should probably proofread and complete it, then remove this comment. -->

10

Tensoic/Tiny-Llama-openhermes-1.1B-step-715k-1.5T

Model

This model is a fine-tuned version of [PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://hu…

4

HiTZ/alpaca-lora-30b-en-pt-es-ca-eu-gl-at

Model

should probably proofread and complete it, then remove this comment. -->

0

PinzhengWang/Llama_CDG

Model

license: mit

0

HiTZ/alpaca-lora-13b-en-pt-es-ca-eu-gl-at

Model

should probably proofread and complete it, then remove this comment. -->

0

HiTZ/alpaca-lora-65b-en-pt-es-ca

Model

should probably proofread and complete it, then remove this comment. -->

2

Linked in READMEs

Yuan-Li-FNLP/R3-RAG

52

README badge

Yuan-Li-FNLP/R3-RAG-CS-Llama

Model

should probably proofread and complete it, then remove this comment. -->

0

2 commits

1 linked in READMEs

updated May 26, 2025

See the code

README

llama

This model is a fine-tuned version of /remote-home1/yli/Model/Generator/Llama3_1_hf/8B/base on the 2wikimultihopqa_train, the hotpotqa_train and the musique_train datasets. It achieves the following results on the evaluation set:

  • Loss: 0.1818

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: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3.0

Training results

Training LossEpochStepValidation Loss
0.20530.19975000.1904
0.20350.399410000.1856
0.19310.599015000.1751
0.1870.798720000.1665
0.19160.998425000.1609
0.10851.198130000.1631
0.11531.397835000.1600
0.12051.597440000.1545
0.1021.797145000.1496
0.07371.996850000.1455
0.02612.196555000.1799
0.03492.396260000.1782
0.02692.595865000.1810
0.02962.795570000.1819
0.02582.995275000.1818

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.4.0
  • Datasets 3.1.0
  • Tokenizers 0.20.3
conversational
endpoints_compatible
full
generated_from_trainer
llama
llama-factory
safetensors
text-generation
text-generation-inference
transformers

Similar repos

Yuan-Li-FNLP/R3-RAG-CS-Qwen

Model

should probably proofread and complete it, then remove this comment. -->

1

XXsongLALA/Llama-3.1-8B-instruct-RAG-RL

Model

should probably proofread and complete it, then remove this comment. -->

1

cognitivecomputations/dolphin-2.9.3-llama-3-8b

Model

should probably proofread and complete it, then remove this comment. -->

10

Tensoic/Tiny-Llama-openhermes-1.1B-step-715k-1.5T

Model

This model is a fine-tuned version of [PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://hu…

4

HiTZ/alpaca-lora-30b-en-pt-es-ca-eu-gl-at

Model

should probably proofread and complete it, then remove this comment. -->

0

PinzhengWang/Llama_CDG

Model

license: mit

0

HiTZ/alpaca-lora-13b-en-pt-es-ca-eu-gl-at

Model

should probably proofread and complete it, then remove this comment. -->

0

HiTZ/alpaca-lora-65b-en-pt-es-ca

Model

should probably proofread and complete it, then remove this comment. -->

2

Linked in READMEs

Yuan-Li-FNLP/R3-RAG

52

README badge