See axolotl config

axolotl version: 0.8.0.dev0

base_model: unsloth/phi-4
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

# User Liger
plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

chat_template: tokenizer_default
datasets:
  - path: shisa-ai/shisa-v2-best-of-n-athenev2-tulu70b-llama33-only-no-sysprompt
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: shisa-ai/shisa-v2-roleplaying-sft
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      assistant:
        - gpt
        - model
        - assistant
      user:
        - human
        - user
    roles_to_train: ["assistant"]
  - path: shisa-ai/translation_expanded_master_set_filtered
    split: train[:25%]
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      assistant:
        - gpt
        - model
        - assistant
      user:
        - human
        - user
    roles_to_train: ["assistant"]
  - path: shisa-ai/rewild-set-deepseek-subset
    split: train[:25%]
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      assistant:
        - gpt
        - model
        - assistant
      user:
        - human
        - user
    roles_to_train: ["assistant"]
  - path: shisa-ai/magpie-ultra-set
    split: train[:8%]
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      assistant:
        - gpt
        - model
        - assistant
      user:
        - human
        - user
    roles_to_train: ["assistant"]
  - path: shisa-ai/magpie-advanced-questions-set
    split: train[:8%]
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      assistant:
        - gpt
        - model
        - assistant
      user:
        - human
        - user
    roles_to_train: ["assistant"]
  - path: shisa-ai/japan-magpie-set
    split: train
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      assistant:
        - gpt
        - model
        - assistant
      user:
        - human
        - user
    roles_to_train: ["assistant"]

dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/ablation-153-finalsft-shisa-v2-unphi-4-14b

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

# marginal difference
neftune_noise_alpha: 5

use_wandb: true
wandb_project: shisa-v2
wandb_entity: augmxnt
wandb_name: ablation-153-finalsft-shisa-v2-unphi-4-14b

gradient_accumulation_steps: 2
micro_batch_size: 4
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: linear
learning_rate: 7.5e-6

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 0
save_total_limit: 1 # Only store a single checkpoint
debug:
deepspeed: zero3_bf16.json
weight_decay: 0.0001
fsdp:
fsdp_config:
special_tokens:
  # pad_token: "<|dummy_87|>"

outputs/ablation-153-finalsft-shisa-v2-unphi-4-14b

This model is a fine-tuned version of unsloth/phi-4 on the shisa-ai/shisa-v2-best-of-n-athenev2-tulu70b-llama33-only-no-sysprompt, the shisa-ai/shisa-v2-roleplaying-sft, the shisa-ai/translation_expanded_master_set_filtered, the shisa-ai/rewild-set-deepseek-subset, the shisa-ai/magpie-ultra-set, the shisa-ai/magpie-advanced-questions-set and the shisa-ai/japan-magpie-set datasets. It achieves the following results on the evaluation set:

• Loss: 0.4735

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-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 16
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 64
• 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: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7096	0.0020	1	0.7202
0.5031	0.5	246	0.5037
0.4589	1.0	492	0.4841
0.4245	1.5	738	0.4780
0.4423	2.0	984	0.4719
0.3957	2.5	1230	0.4754
0.3923	3.0	1476	0.4735

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1