Hugging Face's logo

HuggingFaceTB
/
smollm2-135M-SFT-Only

TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
smollm2-135M-SFT-Only / README.md
loubnabnl's picture
loubnabnl HF Staff
Update README.md
7952846 verified
preview code
|
raw
history blame contribute delete
2.6 kB
metadata
base_model: HuggingFaceTB/135M-lc-100k-rope-12B
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - HuggingFaceTB/magpie-ultra-v1.0-top-300K-short-H4
  - HuggingFaceTB/OpenHermes-2.5-H4-200k
  - HuggingFaceTB/ifeval-like-data-36k-H4
  - HuggingFaceTB/everyday-conversations-llama3.1-2k
  - HuggingFaceTB/self-oss-instruct-sc2-H4
  - HuggingFaceTB/summarization-data-10k-H4
  - HuggingFaceTB/smollm-v2-summarization
  - HuggingFaceTB/smollm-v2-rewriting-50k-H4
  - HuggingFaceTB/explore-instruct-rewrite-H4
  - HuggingFaceTB/LongAlign-16k-ctx-english-H4
model-index:
  - name: smollm2-135M-8k-lc100k-mix1-ep2
    results: []

smollm2-135M-8k-lc100k-mix1-ep2

This model is a fine-tuned version of HuggingFaceTB/SmoLLM2-135M on Smol-SmolTalk (the HuggingFaceTB/magpie-ultra-v1.0-top-300K-short-H4, the HuggingFaceTB/OpenHermes-2.5-H4-200k, the HuggingFaceTB/ifeval-like-data-36k-H4, the HuggingFaceTB/everyday-conversations-llama3.1-2k, the HuggingFaceTB/self-oss-instruct-sc2-H4, the HuggingFaceTB/summarization-data-10k-H4, the HuggingFaceTB/smollm-v2-summarization, the HuggingFaceTB/smollm-v2-rewriting-50k-H4, the HuggingFaceTB/explore-instruct-rewrite-H4 and the HuggingFaceTB/LongAlign-16k-ctx-english-H4 datasets). It achieves the following results on the evaluation set:

  • Loss: 1.8390

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: 0.001
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
1.2705 1.0 392 1.8649
1.1867 2.0 784 1.8390

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1