Hugging Face's logo

kinokokoro
/
cyberagent-mistral-nemo-webnovels

Text Generation
Transformers
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
cyberagent-mistral-nemo-webnovels / README.md
leonardlin's picture
leonardlin
Update README.md
a2f95cd verified
preview code
|
raw
history blame
3.56 kB
metadata
library_name: transformers
license: apache-2.0
base_model: cyberagent/Mistral-Nemo-Japanese-Instruct-2408
tags:
  - generated_from_trainer
model-index:
  - name: outputs/mistral-nemo-webnovels
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: cyberagent/Mistral-Nemo-Japanese-Instruct-2408
tokenizer_type: AutoTokenizer


load_in_8bit: false
load_in_4bit: false
strict: false


chat_template: chatml
datasets:
  - path: falche/paradox_test_set_200k_sharegpt
    type: sharegpt
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/mistral-nemo-webnovels

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

use_wandb: true
wandb_project: mistral-nemo-webnovels
wandb_entity: augmxnt
wandb_name: mi300x-cyberagent_mistral_nemo_webnovels-fft-dsz3

gradient_accumulation_steps: 1
micro_batch_size: 8
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: linear
learning_rate: 8e-6

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

outputs/mistral-nemo-webnovels

This model is a fine-tuned version of cyberagent/Mistral-Nemo-Japanese-Instruct-2408 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6891

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: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 64
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
2.6086 0.0008 1 2.5794
1.8703 0.5 615 1.8224
1.7873 1.0 1230 1.7534
1.6708 1.4976 1845 1.7214
1.6567 1.9976 2460 1.6919
1.501 2.4951 3075 1.6984
1.5237 2.9951 3690 1.6891

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.5.0+rocm6.2
  • Datasets 3.0.1
  • Tokenizers 0.20.1

Training Infra

Compute sponsored by []HotAisle](https://huggingface.co/hotaisle) on an 8 x MI300X node. See the WandB Run Logs for additional details.