base_model: /home/alex/Workspace/sllama/out_5/checkpoint-1722000
trust_remote_code: true
resize_token_embeddings_to_32x: true
plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_layer_norm: true

unfrozen_parameters:
  - ^(?![\s\S]*embed_tokens)[\s\S]+$

datasets:
  - path: fw_merged
    type: input_output
    shards: 8
    shards_idx: 0

dataloader_num_workers: 0
group_by_length: false
dataset_prepared_path: data_prep
output_dir: ./out_6
dataloader_pin_memory: true
shuffle_merged_datasets: false

sequence_len: 2048
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: true

use_tensorboard: true
use_wandb: true
wandb_project: sllama

gradient_accumulation_steps: 16

micro_batch_size: 1
num_epochs: 1
#max_steps: 1_000_000
save_steps: 500
save_total_limit: 2
save_only_model: true
optimizer: sgd
optim_args:
  momentum: 0.98
lr_scheduler: constant
learning_rate: 0.1
#embedding_lr: 5e-7
#cosine_constant_lr_ratio: 0.1
max_grad_norm: 1.0

bf16: auto
fp8: false

gradient_checkpointing: false
gradient_checkpointing_kwargs:
  use_reentrant: false

logging_steps: 10
torch_compile: false
torch_compile_backend: inductor
torch_compile_mode: default
flash_attention: true

#warmup_ratio: 0.05
weight_decay: 0.01

out_6

This model was trained from scratch 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: 0.1
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Use OptimizerNames.SGD and the args are: momentum=0.98
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 100
training_steps: 133451

Training results

Framework versions

Transformers 4.56.1
Pytorch 2.7.1+cu128
Datasets 4.0.0
Tokenizers 0.22.1

AlexHung29629/sllama-v6

out_6

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

AlexHung29629/
sllama-v6