Hugging Face's logo

anthracite-org
/
magnum-v4-12b

Text Generation
Transformers
Safetensors
English
mistral
chat
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
4
magnum-v4-12b / README.md
lucyknada's picture
lucyknada
Upload folder using huggingface_hub
81d2cdb verified
preview code
|
raw
history blame
3.72 kB
metadata
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-Nemo-Instruct-2407
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: magnum-v4-12b-r2
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: mistralai/Mistral-Nemo-Instruct-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: anthracite-core/magnum-v4-12b-r2
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-core/c2_logs_32k_llama3_qwen2_v1.2_no_system
    type: custommistralv3tekken
  - path: anthracite-core/kalo-opus-instruct-22k-no-refusal-no-system
    type: custommistralv3tekken
  - path: anthracite-core/kalo-opus-instruct-3k-filtered-no-system
    type: custommistralv3tekken
  - path: anthracite-org/nopm_claude_writing_fixed
    type: custommistralv3tekken
  - path: anthracite-core/kalo_opus_misc_240827_no_system
    type: custommistralv3tekken
  - path: anthracite-core/kalo_misc_part2_no_system
    type: custommistralv3tekken
#chat_template: chatml
shuffle_merged_datasets: true
#default_system_message: "You are an assistant that responds to the user."
dataset_prepared_path: /workspace/data/magnum-12b-data
val_set_size: 0.0
output_dir: /workspace/data/12b-fft-out

sequence_len: 32768
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project: 12b-magnum-fft
wandb_entity:
wandb_watch:
wandb_name: v4-r2-attempt-01
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: deepspeed_configs/zero2.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  pad_token: <pad>

magnum-v4-12b-r2

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the None dataset.

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: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 40
  • num_epochs: 2

Training results

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1