Modelpublic

FourOhFour/Magic_v2_8B

sourceHugging Faceupdated 2y agoView on Hugging Face

1likes11downloads

Model Card

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.4.1

yaml

base_model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: sharegpt
    conversation: chatml
  - path: NewEden/Kalo-Opus-Instruct-22k-Refusal-Murdered
    type: sharegpt
    conversation: chatml
  - path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: NewEden/Gryphe-Sonnet-3.5-35k-Subset
    type: sharegpt
    conversation: chatml
  - path: Nitral-AI/Reasoning-1shot_ShareGPT
    type: sharegpt
    conversation: chatml
  - path: Nitral-AI/GU_Instruct-ShareGPT
    type: sharegpt
    conversation: chatml
  - path: Nitral-AI/Medical_Instruct-ShareGPT
    type: sharegpt
    conversation: chatml
  - path: AquaV/Resistance-Sharegpt
    type: sharegpt
    conversation: chatml
  - path: AquaV/US-Army-Survival-Sharegpt
    type: sharegpt
    conversation: chatml
  - path: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
    type: sharegpt
    conversation: chatml

chat_template: chatml

val_set_size: 0.002
output_dir: ./outputs/out

adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:

sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

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

wandb_project: mini8B
wandb_entity:
wandb_watch:
wandb_name: mini8B
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
weight_decay: 0.05

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

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

warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2

debug:
deepspeed: deepspeed_configs/zero3_bf16.json
fsdp:
fsdp_config:

special_tokens:
  pad_token: <pad>

</details><br>

outputs/out

This model is a fine-tuned version of Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML on the None dataset. It achieves the following results on the evaluation set:

—Loss: 1.5341

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
—trainbatchsize: 2
—evalbatchsize: 2
—seed: 42
—distributed_type: multi-GPU
—num_devices: 8
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 64
—totalevalbatch_size: 16
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: cosine
—lrschedulerwarmup_steps: 91
—num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.2548	0.0022	1	2.0884
0.7712	0.2503	114	1.6165
0.7566	0.5005	228	1.5734
0.7241	0.7508	342	1.5579
0.6994	1.0011	456	1.5401
0.6186	1.2499	570	1.5433
0.6102	1.5003	684	1.5366
0.5926	1.7507	798	1.5341

Framework versions

—Transformers 4.45.0.dev0
—Pytorch 2.4.0+cu121
—Datasets 2.21.0
—Tokenizers 0.19.1