Training in progress, step 100

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d211335cf46bd679965fd8bdd8760e7a71457fa53e4d87ace9ac0be288ac87
-size 3554214752
+oid sha256:4189ed01c9dc0f95ac8f8a3bc2383699968f43e81dff36c62b669fd5542b66e5
+size 3087467144

training.log

@@ -0,0 +1,157 @@
+2025-03-31 14:28:07 - INFO - __main__ - Model parameters ModelConfig(model_name_or_path='Qwen/Qwen2.5-1.5B-Instruct', model_revision='main', torch_dtype='bfloat16', trust_remote_code=False, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, lora_task_type='CAUSAL_LM', use_rslora=False, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False)
+2025-03-31 14:28:07 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='open-r1/OpenR1-Math-220k', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False)
+2025-03-31 14:28:07 - INFO - __main__ - Training parameters SFTConfig(
+_n_gpu=1,
+accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+average_tokens_across_devices=False,
+batch_eval_metrics=False,
+benchmarks=[],
+bf16=True,
+bf16_full_eval=False,
+callbacks=[],
+chars_per_token=<CHARS_PER_TOKEN>,
+chat_template=None,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+dataset_batch_size=None,
+dataset_kwargs=None,
+dataset_num_proc=8,
+dataset_text_field=text,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+dispatch_batches=None,
+do_eval=False,
+do_predict=False,
+do_train=False,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_on_start=False,
+eval_packing=None,
+eval_steps=None,
+eval_strategy=IntervalStrategy.NO,
+eval_use_gather_object=False,
+evaluation_strategy=None,
+fp16=False,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+gradient_accumulation_steps=1,
+gradient_checkpointing=True,
+gradient_checkpointing_kwargs={'use_reentrant': False},
+greater_is_better=None,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=Qwen2.5-1.5B-Open-R1-Distill,
+hub_model_revision=main,
+hub_private_repo=None,
+hub_strategy=HubStrategy.EVERY_SAVE,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_for_metrics=[],
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=5e-05,
+length_column_name=length,
+load_best_model_at_end=False,
+local_rank=0,
+log_level=info,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=data/Qwen2.5-1.5B-Open-R1-Distill/runs/Mar31_14-28-06_w004.ib.bridges2.psc.edu,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=5,
+logging_strategy=IntervalStrategy.STEPS,
+lr_scheduler_kwargs={'min_lr_rate': 0.1},
+lr_scheduler_type=SchedulerType.COSINE_WITH_MIN_LR,
+max_grad_norm=1.0,
+max_length=16384,
+max_seq_length=None,
+max_steps=-1,
+metric_for_best_model=None,
+model_init_kwargs=None,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_of_sequences=None,
+num_train_epochs=1,
+optim=OptimizerNames.ADAMW_TORCH,
+optim_args=None,
+optim_target_modules=None,
+output_dir=data/Qwen2.5-1.5B-Open-R1-Distill,
+overwrite_hub_revision=False,
+overwrite_output_dir=True,
+packing=True,
+past_index=-1,
+per_device_eval_batch_size=16,
+per_device_train_batch_size=16,
+prediction_loss_only=False,
+push_to_hub=True,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_revision=False,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=True,
+report_to=['wandb'],
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+run_name=data/Qwen2.5-1.5B-Open-R1-Distill,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=100,
+save_strategy=SaveStrategy.STEPS,
+save_total_limit=1,
+seed=42,
+skip_memory_metrics=True,
+split_batches=None,
+system_prompt=None,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torch_empty_cache_steps=None,
+torchdynamo=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_liger=True,
+use_liger_kernel=False,
+use_mps_device=False,
+wandb_entity=None,
+wandb_project=None,
+warmup_ratio=0.05,
+warmup_steps=0,
+weight_decay=0.0,
+)
+2025-03-31 14:28:09 - INFO - __main__ - *** Initializing model kwargs ***
+2025-03-31 14:28:57 - INFO - __main__ - *** Train ***

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a434a6258d5e80496c2ac23201ae84ae70b1ccdaa749a90c4c6aaf9d8b345e
+oid sha256:101ddd1fac8b4eb1e7df57a3b3ff60cea6d1f3f8835be34ee66e7c4983e0c0d9
 size 7544