See axolotl config

axolotl version: 0.4.1

base_model: jeiku/completion4B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

hub_model_id: jeiku/instructered4B
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

datasets:
  - path: FourOhFour/Instruct_Phase
    type: sharegpt
    conversation: chatml

chat_template: chatml

shuffle_merged_datasets: true
val_set_size: 0.0025
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: EXP4B
wandb_entity:
wandb_watch:
wandb_name: EXP4B
wandb_log_model:

gradient_accumulation_steps: 12
micro_batch_size: 3
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: <|finetune_right_pad_id|>

instructered4B

This model is a fine-tuned version of jeiku/completion4B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3713

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: 3
• eval_batch_size: 3
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 12
• total_train_batch_size: 72
• total_eval_batch_size: 6
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 68
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.336	0.0029	1	1.7114
0.9631	0.2516	86	1.4098
0.9347	0.5032	172	1.3828
0.9142	0.7548	258	1.3693
0.7967	1.0037	344	1.3659
0.7912	1.2551	430	1.3728
0.7957	1.5065	516	1.3730
0.7951	1.7579	602	1.3713

Framework versions

• Transformers 4.46.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.20.0