See axolotl config

axolotl version: 0.8.0

base_model: meta-llama/Llama-3.1-8B-Instruct

load_in_8bit: false
load_in_4bit: false
strict: false

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Sandevistan_cleaned.jsonl
    type: customllama3_stan
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/out

fix_untrained_tokens: true

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

wandb_project: Pneuma
wandb_entity: 
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 8
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.000075
max_grad_norm: 1

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

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
eval_sample_packing: false

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

hub_model_id: Replete-AI/L3-Pneuma-8B
hub_strategy: every_save

warmup_steps: 10
evals_per_epoch: 3
eval_table_size:
saves_per_epoch: 3
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|begin_of_text|>"
  eos_token: "<|end_of_text|>"
  pad_token: "<|end_of_text|>"
tokens:

L3-Pneuma-8B

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the Sandevistan_cleaned.jsonl dataset. It achieves the following results on the evaluation set:

Loss: 0.7796

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: 7.5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 2.0