Upload folder using huggingface_hub

adapter_config.json

@@ -23,7 +23,7 @@
   "r": 8,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "(?!^(multi_modal_projector))^(language_model|vision_model).*\\.(gate_proj|k_proj|v_proj|q_proj|down_proj|o_proj|up_proj|k_proj|q_proj|v_proj|fc1|o_proj|fc2)$",
+  "target_modules": "^(language_model).*\\.(k_proj|q_proj|gate_proj|v_proj|o_proj|down_proj|up_proj)$",
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29da1679493dc132ba519d28993e9bbb6b8ab3a1d78e9ce4dde127c7297e4f85
-size 67330312
+oid sha256:f4fad12160d36d5d83e42ef1c395ceedd61fb9f6086f97954c644477e3d0dd3f
+size 52511776

args.json

@@ -12,9 +12,9 @@
   "max_memory": {},
   "local_repo_path": null,
   "template": "llama3_2_vision",
-  "system": null,
-  "max_length": 8092,
-  "truncation_strategy": "left",
+  "system": "You are a helpful assistant that truthfully answers user questions about the provided image. Keep your response concise and to the point. Don't explain your answer. If you don't guarantee that the answer is completely correct, output 'I don't know.'",
+  "max_length": 2048,
+  "truncation_strategy": "delete",
   "max_pixels": null,
   "agent_template": null,
   "norm_bbox": null,
@@ -25,12 +25,12 @@
   "use_chat_template": true,
   "template_backend": "swift",
   "dataset": [
-    "new_task1_nothink_respone_full.json"
+    "task1_dpo_phase2_0528.json"
   ],
   "val_dataset": [],
   "split_dataset_ratio": 0.01,
-  "data_seed": 123,
-  "dataset_num_proc": 1,
+  "data_seed": 42,
+  "dataset_num_proc": 4,
   "dataset_shuffle": true,
   "val_dataset_shuffle": false,
   "streaming": false,
@@ -41,7 +41,7 @@
   "download_mode": "reuse_dataset_if_exists",
   "columns": {},
   "strict": false,
-  "remove_unused_columns": false,
+  "remove_unused_columns": true,
   "model_name": [
     null,
     null
@@ -59,10 +59,10 @@
   "bnb_4bit_use_double_quant": true,
   "bnb_4bit_quant_storage": null,
   "max_new_tokens": 64,
-  "temperature": 1.0,
+  "temperature": 0.9,
   "top_k": 50,
   "top_p": 0.9,
-  "repetition_penalty": 1.1,
+  "repetition_penalty": 1.0,
   "num_beams": 1,
   "stream": false,
   "stop_words": [],
@@ -74,10 +74,8 @@
   "tuner_backend": "peft",
   "train_type": "lora",
   "adapters": [],
-  "external_plugins": [
-    "/data/kdd/crag/cjz/ms-swift/examples/train/grpo/plugin/plugin.py"
-  ],
-  "seed": 123,
+  "external_plugins": [],
+  "seed": 42,
   "model_kwargs": {},
   "load_args": false,
   "load_data_args": false,
@@ -86,18 +84,18 @@
   "custom_register_path": [],
   "ignore_args_error": false,
   "use_swift_lora": false,
-  "output_dir": "/data2/kdd/crag/cjz/agents/output/response/v67-20250515-170509",
+  "output_dir": "/data2/kdd/crag/cjz/output/dpo_phase2/v1-20250528-012105",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
   "do_predict": false,
   "eval_strategy": "steps",
   "prediction_loss_only": false,
-  "per_device_train_batch_size": 8,
-  "per_device_eval_batch_size": 8,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 2,
   "per_gpu_train_batch_size": null,
   "per_gpu_eval_batch_size": null,
-  "gradient_accumulation_steps": 16,
+  "gradient_accumulation_steps": 8,
   "eval_accumulation_steps": null,
   "eval_delay": 0,
   "torch_empty_cache_steps": null,
@@ -106,8 +104,8 @@
   "adam_beta1": 0.9,
   "adam_beta2": 0.95,
   "adam_epsilon": 1e-08,
-  "max_grad_norm": 0.5,
-  "num_train_epochs": 4.0,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 2.0,
   "max_steps": -1,
   "lr_scheduler_type": "cosine",
   "lr_scheduler_kwargs": null,
@@ -116,13 +114,13 @@
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/data2/kdd/crag/cjz/agents/output/response/v67-20250515-170509/runs",
+  "logging_dir": "/data2/kdd/crag/cjz/output/dpo_phase2/v1-20250528-012105/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 1,
   "logging_nan_inf_filter": true,
   "save_strategy": "steps",
-  "save_steps": 5.0,
+  "save_steps": 50.0,
   "save_total_limit": null,
   "save_safetensors": true,
   "save_on_each_node": false,
@@ -145,8 +143,8 @@
   "tpu_num_cores": null,
   "tpu_metrics_debug": false,
   "debug": null,
-  "dataloader_drop_last": true,
-  "eval_steps": 500.0,
+  "dataloader_drop_last": false,
+  "eval_steps": 300.0,
   "dataloader_num_workers": 4,
   "dataloader_prefetch_factor": null,
   "past_index": -1,
@@ -154,8 +152,8 @@
   "disable_tqdm": null,
   "label_names": null,
   "load_best_model_at_end": false,
-  "metric_for_best_model": "reward",
-  "greater_is_better": true,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
   "ignore_data_skip": false,
   "fsdp": "",
   "fsdp_min_num_params": 0,
@@ -178,26 +176,17 @@
       "enabled": "auto"
     },
     "zero_optimization": {
-      "stage": 3,
+      "stage": 2,
       "offload_optimizer": {
         "device": "none",
         "pin_memory": true
       },
-      "offload_param": {
-        "device": "none",
-        "pin_memory": true
-      },
+      "allgather_partitions": true,
+      "allgather_bucket_size": 200000000.0,
       "overlap_comm": false,
-      "contiguous_gradients": true,
-      "sub_group_size": 1000000000.0,
-      "reduce_bucket_size": "auto",
-      "zero_quantized_weights": false,
-      "zero_quantized_gradients": false,
-      "stage3_prefetch_bucket_size": "auto",
-      "stage3_param_persistence_threshold": "auto",
-      "stage3_max_live_parameters": 1000000000.0,
-      "stage3_max_reuse_distance": 1000000000.0,
-      "stage3_gather_16bit_weights_on_model_save": true
+      "reduce_scatter": true,
+      "reduce_bucket_size": 200000000.0,
+      "contiguous_gradients": true
     },
     "gradient_accumulation_steps": "auto",
     "gradient_clipping": "auto",
@@ -223,7 +212,7 @@
   "skip_memory_metrics": true,
   "use_legacy_prediction_loop": false,
   "push_to_hub": false,
-  "resume_from_checkpoint": "/data2/kdd/crag/cjz/agents/output/response/v64-20250515-000005/checkpoint-245",
+  "resume_from_checkpoint": null,
   "hub_model_id": null,
   "hub_strategy": "every_save",
   "hub_private_repo": null,
@@ -272,12 +261,13 @@
   "eval_datasets_args": null,
   "eval_generation_config": null,
   "freeze_parameters": [
+    "vision_model",
     "multi_modal_projector"
   ],
   "freeze_parameters_ratio": 0.0,
   "trainable_parameters": [],
   "freeze_llm": false,
-  "freeze_vit": false,
+  "freeze_vit": true,
   "freeze_aligner": true,
   "target_modules": [
     "all-linear"
@@ -353,7 +343,7 @@
   "create_checkpoint_symlink": false,
   "packing": false,
   "lazy_tokenize": true,
-  "loss_type": "grpo",
+  "loss_type": "sigmoid",
   "optimizer": null,
   "metric": null,
   "zero_hpz_partition_size": null,
@@ -375,14 +365,14 @@
   "response_length": 512,
   "missing_eos_penalty": null,
   "epsilon": 0.2,
-  "epsilon_high": 0.28,
+  "epsilon_high": null,
   "num_infer_workers": 1,
   "vllm_device": [
     "auto"
   ],
-  "vllm_gpu_memory_utilization": 0.8,
-  "vllm_max_model_len": 8192,
-  "vllm_max_num_seqs": 8,
+  "vllm_gpu_memory_utilization": 0.9,
+  "vllm_max_model_len": null,
+  "vllm_max_num_seqs": 256,
   "vllm_enforce_eager": false,
   "vllm_limit_mm_per_prompt": null,
   "vllm_enable_prefix_caching": true,
@@ -409,27 +399,25 @@
   "max_resample_times": 3,
   "overlong_filter": false,
   "soft_max_length": null,
-  "soft_cache_length": 20,
+  "soft_cache_length": null,
   "scale_rewards": true,
   "wandb_log_unique_prompts": null,
   "vllm_server_host": null,
   "vllm_server_port": 8000,
   "vllm_server_timeout": 240.0,
   "num_generations": 8,
-  "max_completion_length": 50,
+  "max_completion_length": 512,
   "ds3_gather_for_generation": true,
-  "reward_funcs": [
-    "Response_no_think_reward_1"
-  ],
+  "reward_funcs": [],
   "reward_weights": null,
-  "log_completions": true,
-  "use_vllm": true,
-  "num_iterations": 2,
-  "rlhf_type": "grpo",
+  "log_completions": false,
+  "use_vllm": false,
+  "num_iterations": 1,
+  "rlhf_type": "dpo",
   "ref_model": null,
   "ref_model_type": null,
   "ref_model_revision": null,
-  "beta": 0.01,
+  "beta": 0.1,
   "label_smoothing": 0,
   "rpo_alpha": 1.0,
   "cpo_alpha": 1.0,
@@ -442,9 +430,9 @@
   "local_world_size": 1,
   "model_suffix": "Llama-3.2-11B-Vision-Instruct",
   "model_info": "ModelInfo(model_type='llama3_2_vision', model_dir='/data1/chenjiazun/LLM/Llama-3.2-11B-Vision-Instruct', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling={'factor': 8.0, 'high_freq_factor': 4.0, 'low_freq_factor': 1.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}, config=None, task_type='causal_lm', num_labels=None)",
-  "model_meta": "ModelMeta(model_type='llama3_2_vision', model_groups=[ModelGroup(models=[Model(ms_model_id='LLM-Research/Llama-3.2-11B-Vision-Instruct', hf_model_id='meta-llama/Llama-3.2-11B-Vision-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-90B-Vision-Instruct', hf_model_id='meta-llama/Llama-3.2-90B-Vision-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-11B-Vision', hf_model_id='meta-llama/Llama-3.2-11B-Vision', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-90B-Vision', hf_model_id='meta-llama/Llama-3.2-90B-Vision', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='llama3_2_vision', get_function=<function get_model_tokenizer_llama3_2_vision at 0x763e328dbe20>, model_arch='llama3_2_vision', architectures=['MllamaForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.45'], tags=[])",
+  "model_meta": "ModelMeta(model_type='llama3_2_vision', model_groups=[ModelGroup(models=[Model(ms_model_id='LLM-Research/Llama-3.2-11B-Vision-Instruct', hf_model_id='meta-llama/Llama-3.2-11B-Vision-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-90B-Vision-Instruct', hf_model_id='meta-llama/Llama-3.2-90B-Vision-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-11B-Vision', hf_model_id='meta-llama/Llama-3.2-11B-Vision', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-90B-Vision', hf_model_id='meta-llama/Llama-3.2-90B-Vision', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='llama3_2_vision', get_function=<function get_model_tokenizer_llama3_2_vision at 0x776c83836c20>, model_arch='llama3_2_vision', architectures=['MllamaForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.45'], tags=[])",
   "model_dir": "/data1/chenjiazun/LLM/Llama-3.2-11B-Vision-Instruct",
   "hub": "<class 'swift.hub.hub.MSHub'>",
   "evaluation_strategy": "steps",
-  "training_args": "GRPOConfig(output_dir='/data2/kdd/crag/cjz/agents/output/response/v67-20250515-170509', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=8, per_device_eval_batch_size=8, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0002, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=4.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data2/kdd/crag/cjz/agents/output/response/v67-20250515-170509/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=5, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=123, data_seed=123, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=True, eval_steps=500, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/data2/kdd/crag/cjz/agents/output/response/v67-20250515-170509', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, tp_size=0, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint='/data2/kdd/crag/cjz/agents/output/response/v64-20250515-000005/checkpoint-245', hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=8, max_completion_length=50, ds3_gather_for_generation=True, shuffle_dataset=True, temperature=1.0, top_p=0.9, top_k=50, min_p=None, repetition_penalty=1.1, cache_implementation=None, use_vllm=True, vllm_server_host=None, vllm_server_port=8000, vllm_server_timeout=240.0, vllm_guided_decoding_regex=None, beta=0.01, num_iterations=2, epsilon=0.2, epsilon_high=0.28, reward_weights=None, scale_rewards=True, loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, use_liger_loss=False, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, vllm_device=['auto'], vllm_gpu_memory_utilization=0.8, vllm_dtype=None, vllm_max_model_len=8192, vllm_enable_prefix_caching=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='lora', optimizer=None, local_repo_path=None, galore_config=None, num_infer_workers=1, vllm_max_num_seqs=8, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=50, repetition_n_grams=3, repetition_max_penalty=-1.0, use_lmdeploy=False, lmdeploy_device='auto', lmdeploy_session_len=None, lmdeploy_cache_max_entry_count=0.8, async_generate=False, tensor_parallel_size=1, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, gc_collect_after_offload=False, multi_turn_func=None, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=20, dataset_shuffle=True, stop_words=[])"
+  "training_args": "DPOConfig(output_dir='/data2/kdd/crag/cjz/output/dpo_phase2/v1-20250528-012105', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0002, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data2/kdd/crag/cjz/output/dpo_phase2/v1-20250528-012105/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=300, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/data2/kdd/crag/cjz/output/dpo_phase2/v1-20250528-012105', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, tp_size=0, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, ref_model_init_kwargs=None, model_adapter_name=None, ref_adapter_name=None, force_use_ref_model=False, disable_dropout=True, use_logits_to_keep=False, dataset_num_proc=4, padding_value=None, label_pad_token_id=None, max_prompt_length=512, max_completion_length=512, max_length=2048, truncation_mode='keep_end', padding_free=False, precompute_ref_log_probs=False, precompute_ref_batch_size=None, tools=None, loss_type='sigmoid', beta=0.1, f_divergence_type=<FDivergenceType.REVERSE_KL: 'reverse_kl'>, f_alpha_divergence_coef=1.0, reference_free=False, label_smoothing=0, use_weighting=False, rpo_alpha=1.0, discopop_tau=0.05, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, generate_during_eval=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='lora', optimizer=None, local_repo_path=None, galore_config=None)"
 }

latest

@@ -1 +1 @@
-global_step280
+global_step799

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02034183374b3378e32cb927af60ea7d3894665df94e961d4a00180b159e7087
-size 14498
+oid sha256:964771ea4d152605618c22273abbcef8154a9735e5ca07daff1650a42df501c8
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989cd45105b54e752d9e40372417e9cf25b8e10f3504638030af27d4f0e73897
+oid sha256:ab14d4c63ee0a9523bd9778d4168994a6d1557cfdd6f2268ed3eb4a755abd54d
 size 1064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:299721334abd93ccd8bac0f14076b8b992a0297f94b0fd973cb274ad848eb333
-size 10168
+oid sha256:ccd6adf03cbc28fcd10f8776e16882e610a76a0b5367ddbb5022d7e7f6de2b22
+size 8632