Hugging Face's logo

Delta-Vector
/
Holland-4B-V1

Safetensors
llama
chat
Model card Files Community
1
Holland-4B-V1 / README.md
kubernetes-bad's picture
kubernetes-bad
Upload folder using huggingface_hub
74b3681 verified
preview code
|
raw
history blame
No virus
4.04 kB
metadata
library_name: transformers
license: other
base_model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
tags:
  - generated_from_trainer
model-index:
  - name: outputs/out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Gryphe-3.5-16k-Subset
    type: sharegpt
    conversation: chatml
  - path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: sharegpt
    conversation: chatml
  - path: PJMixers/lodrick-the-lafted_OpusStories-ShareGPT
    type: sharegpt
    conversation: chatml

chat_template: chatml

val_set_size: 0.01
output_dir: ./outputs/out

adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:

sequence_len: 16384
# sequence_len: 32768
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: Ohashi4b
wandb_entity:
wandb_watch:
wandb_name: Ohashi4b
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
#optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00002
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: 1

debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
#deepspeed:
fsdp:
fsdp_config:

special_tokens:
  pad_token: <|finetune_right_pad_id|>

outputs/out

This model is a fine-tuned version of IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0118

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: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 64
  • total_eval_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 6
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
1.4992 0.0278 1 1.6105
1.2866 0.25 9 1.2680
1.1737 0.5 18 1.1396
1.1355 0.75 27 1.0766
1.1065 1.0 36 1.0408
0.9673 1.2370 45 1.0272
0.9526 1.4870 54 1.0167
0.9653 1.7370 63 1.0126
0.958 1.9870 72 1.0118

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.4.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1