See axolotl config

axolotl version: 0.8.0.dev0

base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-1
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 0.2

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

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

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>

4b-inst

This model was trained from scratch on the NewEden/Helpsteer-3-Filtered, the NewEden/GSM8K-R1-filtered, the NewEden/Hydrus-R1-Thinking-Sharegpt, the NewEden/Hydrus-SonnetOrca, the NewEden/Hydrus-HelpSteer2, the NewEden/Claude-Instruct-5K, the PocketDoc/Dans-MemoryCore-CoreCurriculum-Small, the Nitral-AI/ARES-ShareGPT, the NewEden/Hydrus-Instruct-SmolTalk, the NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt, the NewEden/Claude-Instruct-2.7K and the PocketDoc/Dans-Assistantmaxx-Tulu3-IF datasets.

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: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• total_eval_batch_size: 4
• 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: 40
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0