base_model: Qwen/Qwen3-1.7B

load_in_8bit: false
load_in_4bit: false

chat_template: qwen3
datasets:
  - path: train_YS.jsonl
    type: chat_template

dataset_prepared_path: preprocess
val_set_size: 0.01
output_dir: ./outputs

adapter: 
lora_model_dir:

sequence_len: 16384
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: false

wandb_project: FC-T2J
wandb_entity: 
wandb_watch:
wandb_name: 
wandb_log_model:
hub_model_id: amphora/FC-T2J-SFT-1_7B 

gradient_accumulation_steps: 32
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 2e-5

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
  - axolotl.integrations.liger.LigerPlugin
strict: false
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

bf16: auto
tf32: false

gradient_checkpointing:
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_ratio: 0.05
weight_decay: 0.01
evals_per_epoch: 0
saves_per_epoch: 1

fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_transformer_layer_cls_to_wrap:  Qwen3DecoderLayer
  # fsdp_activation_checkpointing: true
  

FC-T2J-SFT-1_7B

This model is a fine-tuned version of Qwen/Qwen3-1.7B on the train_YS.jsonl 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: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 256
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 87
training_steps: 1751

Training results

Framework versions

Transformers 5.0.0
Pytorch 2.9.1+cu128
Datasets 4.5.0
Tokenizers 0.22.2