5 lines
1012 B
Plaintext
5 lines
1012 B
Plaintext
2025-11-09 05:58:50,468 - INFO - Initialising CheckpointManager with config: CheckpointConfig(model_name_or_path='allenai/tulu-2-7b', max_seq_length=8192, learning_rate=2e-05, num_train_epochs=1, per_device_train_batch_size=2, output_base_dir='model_checkpoints', save_total_limit=1, logging_steps=1, seed=42, fp16=False, bf16=True, warmup_steps=0, warmup_ratio=0.0, gradient_accumulation_steps=32, gradient_checkpointing=True, resume_from_checkpoint=True, checkpoint_name='mixed_sft_tulu-2-7b_160ex_10.0pct_e1_lr2e-05', use_trl=True, use_lora=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, apply_chat_template=False, add_generation_prompt=False, packing=False, remove_unused_columns=False)
|
|
2025-11-09 05:58:53,384 - INFO - Fine-tuning with TRL on supplied Dataset (160 rows)
|
|
2025-11-09 05:58:56,703 - INFO - SFTTrainer initialized with max_seq_length=8192
|
|
2025-11-09 06:00:28,957 - INFO - Training complete. Saving model to model_checkpoints/tulu-2-7b_20251109_mixed_sft_tulu-2-7b_160ex_10.0pct_e1_lr2e-05
|