tnnanh1005 commited on Mar 7

Commit

c35ad83

verified ·

1 Parent(s): 04c8d77

Upload folder using huggingface_hub

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

.gitattributes +18 -0
data/thinking_dataset_merged.jsonl +3 -0
data/thinking_dataset_v2_swift.jsonl +3 -0
data/wandb/debug-internal.log +12 -0
data/wandb/debug.log +22 -0
data/wandb/run-20260304_035219-bzc9z48s/files/config.yaml +632 -0
data/wandb/run-20260304_035219-bzc9z48s/files/output.log +0 -0
data/wandb/run-20260304_035219-bzc9z48s/files/requirements.txt +159 -0
data/wandb/run-20260304_035219-bzc9z48s/files/wandb-metadata.json +110 -0
data/wandb/run-20260304_035219-bzc9z48s/files/wandb-summary.json +1 -0
data/wandb/run-20260304_035219-bzc9z48s/logs/debug-core.log +15 -0
data/wandb/run-20260304_035219-bzc9z48s/logs/debug-internal.log +14 -0
data/wandb/run-20260304_035219-bzc9z48s/logs/debug.log +24 -0
data/wandb/run-20260304_035219-bzc9z48s/run-bzc9z48s.wandb +3 -0
data/wandb/run-20260306_073928-dpxzw953/files/output.log +32 -0
data/wandb/run-20260306_073928-dpxzw953/files/requirements.txt +241 -0
data/wandb/run-20260306_073928-dpxzw953/files/wandb-metadata.json +97 -0
data/wandb/run-20260306_073928-dpxzw953/logs/debug-core.log +8 -0
data/wandb/run-20260306_073928-dpxzw953/logs/debug-internal.log +6 -0
data/wandb/run-20260306_073928-dpxzw953/logs/debug.log +22 -0
data/wandb/run-20260306_073928-dpxzw953/run-dpxzw953.wandb +3 -0
data/wandb/run-20260306_105746-8846dbl6/files/output.log +0 -0
data/wandb/run-20260306_105746-8846dbl6/files/requirements.txt +243 -0
data/wandb/run-20260306_105746-8846dbl6/files/wandb-metadata.json +97 -0
data/wandb/run-20260306_105746-8846dbl6/logs/debug-core.log +8 -0
data/wandb/run-20260306_105746-8846dbl6/logs/debug-internal.log +12 -0
data/wandb/run-20260306_105746-8846dbl6/logs/debug.log +22 -0
data/wandb/run-20260306_105746-8846dbl6/run-8846dbl6.wandb +3 -0
output/Qwen3-1.7B/v0-20260304-031440/args.json +346 -0
output/Qwen3-1.7B/v0-20260304-031440/images/train_epoch.png +0 -0
output/Qwen3-1.7B/v0-20260304-031440/images/train_grad_norm.png +0 -0
output/Qwen3-1.7B/v0-20260304-031440/images/train_learning_rate.png +0 -0
output/Qwen3-1.7B/v0-20260304-031440/images/train_loss.png +0 -0
output/Qwen3-1.7B/v0-20260304-031440/images/train_token_acc.png +0 -0
output/Qwen3-1.7B/v0-20260304-031440/logging.jsonl +17 -0
output/Qwen3-1.7B/v0-20260304-031440/runs/Mar04_03-19-12_ubuntu/events.out.tfevents.1772594352.ubuntu.2490446.0 +3 -0
output/proposals_RM_gpt_oss_120b_ensemble/polaris/polaris-adme-fang-hclint-1_scored_16.json +0 -0
output/proposals_RM_gpt_oss_120b_ensemble/polaris/polaris-adme-fang-hppb-1_scored_16.json +0 -0
output/proposals_RM_gpt_oss_120b_ensemble/polaris/polaris-adme-fang-solu-1_scored_16.json +0 -0
output/proposals_RM_gpt_oss_120b_ensemble/polaris/tdcommons-bbb-martins_scored_16.json +0 -0
output/proposals_RM_gpt_oss_120b_ensemble/polaris/tdcommons-cyp2d6-substrate-carbonmangels_scored_16.json +0 -0
output/proposals_RM_gpt_oss_120b_ensemble/polaris/tdcommons-herg_scored_16.json +0 -0
output/proposals_RM_gpt_oss_120b_ensemble/polaris/tdcommons-lipophilicity-astrazeneca_scored_16.json +0 -0
output/proposals_RM_gpt_oss_20b_ensemble/polaris/polaris-adme-fang-hclint-1_scored_16.json +0 -0
output/proposals_RM_gpt_oss_20b_ensemble/polaris/polaris-adme-fang-hppb-1_scored_16.json +0 -0
output/proposals_RM_gpt_oss_20b_ensemble/polaris/polaris-adme-fang-solu-1_scored_16.json +0 -0
output/proposals_RM_gpt_oss_20b_ensemble/polaris/tdcommons-bbb-martins_scored_16.json +0 -0
output/proposals_RM_gpt_oss_20b_ensemble/polaris/tdcommons-cyp2d6-substrate-carbonmangels_scored_16.json +0 -0
output/proposals_RM_gpt_oss_20b_ensemble/polaris/tdcommons-herg_scored_16.json +0 -0
output/proposals_RM_gpt_oss_20b_ensemble/polaris/tdcommons-lipophilicity-astrazeneca_scored_16.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,21 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/thinking_dataset_merged.jsonl filter=lfs diff=lfs merge=lfs -text
+data/thinking_dataset_v2_swift.jsonl filter=lfs diff=lfs merge=lfs -text
+data/wandb/run-20260304_035219-bzc9z48s/run-bzc9z48s.wandb filter=lfs diff=lfs merge=lfs -text
+data/wandb/run-20260306_073928-dpxzw953/run-dpxzw953.wandb filter=lfs diff=lfs merge=lfs -text
+data/wandb/run-20260306_105746-8846dbl6/run-8846dbl6.wandb filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_comparison_gpt_oss_120b_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_comparison_gpt_oss_20b_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_comparison_qwen3_1,7b_OG_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_comparison_qwen3_1,7b_sft_thinking_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_convergence_gpt_oss_120b_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_convergence_gpt_oss_20b_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_convergence_qwen3_1,7b_OG_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_convergence_qwen3_1,7b_sft_thinking_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_separate_gpt_oss_120b_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_separate_gpt_oss_20b_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_separate_qwen3_1,7b_OG_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+output/reward/ensemble_separate_qwen3_1,7b_sft_thinking_ensemble_temp0,8.png filter=lfs diff=lfs merge=lfs -text
+train/output/v0-20260304-035120/checkpoint-4374-merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text

data/thinking_dataset_merged.jsonl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3de53a26565bfce6ea455e6dd280984c40f68e79e1a0acefeefd1f2259897e
+size 337772135

data/thinking_dataset_v2_swift.jsonl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc9cf7992b7f889abba2bf9ac64e1ff44d1dc2b5f498c2208e231c7d7cba59a
+size 185136875

data/wandb/debug-internal.log ADDED Viewed

	@@ -0,0 +1,12 @@

+{"time":"2026-03-06T10:57:46.486394548Z","level":"INFO","msg":"stream: starting","core version":"0.25.0"}
+{"time":"2026-03-06T10:57:46.705840771Z","level":"INFO","msg":"stream: created new stream","id":"8846dbl6"}
+{"time":"2026-03-06T10:57:46.706184448Z","level":"INFO","msg":"handler: started","stream_id":"8846dbl6"}
+{"time":"2026-03-06T10:57:46.706376796Z","level":"INFO","msg":"stream: started","id":"8846dbl6"}
+{"time":"2026-03-06T10:57:46.70647031Z","level":"INFO","msg":"writer: started","stream_id":"8846dbl6"}
+{"time":"2026-03-06T10:57:46.706495415Z","level":"INFO","msg":"sender: started","stream_id":"8846dbl6"}
+{"time":"2026-03-06T19:23:17.154701842Z","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/nhatanh10102005-vinuniversity/ms-swift/8846dbl6/file_stream","body":"\n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>502 Server Error</title>\n</head>\n<body text=#000000 bgcolor=#ffffff>\n<h1>Error: Server Error</h1>\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\n<h2></h2>\n</body></html>\n"}
+{"time":"2026-03-07T01:23:02.15976294Z","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/nhatanh10102005-vinuniversity/ms-swift/8846dbl6/file_stream","body":"\n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>502 Server Error</title>\n</head>\n<body text=#000000 bgcolor=#ffffff>\n<h1>Error: Server Error</h1>\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\n<h2></h2>\n</body></html>\n"}
+{"time":"2026-03-07T02:55:05.824285344Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":15580}
+{"time":"2026-03-07T02:55:05.824494952Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":1}
+{"time":"2026-03-07T02:55:05.825190016Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":15613}
+{"time":"2026-03-07T02:55:05.840550203Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":904}

data/wandb/debug.log ADDED Viewed

	@@ -0,0 +1,22 @@

+2026-03-06 10:57:46,235 INFO    MainThread:1654770 [wandb_setup.py:_flush():81] Current SDK version is 0.25.0
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_setup.py:_flush():81] Configure stats pid to 1654770
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_init.py:setup_run_log_directory():717] Logging user logs to /root/code/na/Idea-filtering-training/data/wandb/run-20260306_105746-8846dbl6/logs/debug.log
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_init.py:setup_run_log_directory():718] Logging internal logs to /root/code/na/Idea-filtering-training/data/wandb/run-20260306_105746-8846dbl6/logs/debug-internal.log
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_init.py:init():844] calling init triggers
+2026-03-06 10:57:46,237 INFO    MainThread:1654770 [wandb_init.py:init():849] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-03-06 10:57:46,237 INFO    MainThread:1654770 [wandb_init.py:init():892] starting backend
+2026-03-06 10:57:46,468 INFO    MainThread:1654770 [wandb_init.py:init():895] sending inform_init request
+2026-03-06 10:57:46,475 INFO    MainThread:1654770 [wandb_init.py:init():903] backend started and connected
+2026-03-06 10:57:46,480 INFO    MainThread:1654770 [wandb_init.py:init():973] updated telemetry
+2026-03-06 10:57:46,491 INFO    MainThread:1654770 [wandb_init.py:init():997] communicating run to backend with 90.0 second timeout
+2026-03-06 10:57:47,094 INFO    MainThread:1654770 [wandb_init.py:init():1042] starting run threads in backend
+2026-03-06 10:57:47,290 INFO    MainThread:1654770 [wandb_run.py:_console_start():2524] atexit reg
+2026-03-06 10:57:47,290 INFO    MainThread:1654770 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-03-06 10:57:47,290 INFO    MainThread:1654770 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-03-06 10:57:47,290 INFO    MainThread:1654770 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-03-06 10:57:47,295 INFO    MainThread:1654770 [wandb_init.py:init():1082] run started, returning control to user process
+2026-03-06 10:57:47,296 INFO    MainThread:1654770 [wandb_run.py:_config_callback():1403] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': '/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', 'revision': None, 'inference_mode': False, 'r': 32, 'target_modules': ['gate_proj', 'up_proj', 'v_proj,o_proj', 'down_proj', 'k_proj', 'q_proj'], 'exclude_modules': None, 'lora_alpha': 64, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': [], 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False, 'lora_dtype': None, 'lorap_lr_ratio': None, 'lorap_emb_lr': 1e-06}}, 'vocab_size': 151936, 'max_position_embeddings': 40960, 'hidden_size': 2048, 'intermediate_size': 6144, 'num_hidden_layers': 28, 'num_attention_heads': 16, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_bias': False, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'pad_token_id': 151643, 'bos_token_id': None, 'eos_token_id': 151645, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 1000000, 'rope_type': 'default'}, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': ['Qwen3ForCausalLM'], 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', 'transformers_version': '5.3.0', 'model_type': 'qwen3', 'output_attentions': False, 'output_dir': '/root/code/na/Idea-filtering-training/train/output/v5-20260306-105729', 'per_device_train_batch_size': 1, 'num_train_epochs': 3.0, 'max_steps': -1, 'learning_rate': 0.0002, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_steps': 0.05, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 16, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 5, 'logging_first_step': True, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': '/root/code/na/Idea-filtering-training/train/output/v5-20260306-105729', 'project': 'huggingface', 'trackio_space_id': 'trackio', 'eval_strategy': 'no', 'eval_steps': 500.0, 'eval_delay': 0, 'per_device_eval_batch_size': 1, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': False, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 1, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': 2, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_backend': None, 'ddp_timeout': 18000000, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'resume_from_checkpoint': None, 'warmup_ratio': 0.05, 'logging_dir': '/root/code/na/Idea-filtering-training/train/output/v5-20260306-105729/runs', 'local_rank': -1, 'sortish_sampler': False, 'predict_with_generate': False, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None, 'tuner_backend': 'peft', 'vit_gradient_checkpointing': True, 'router_aux_loss_coef': 0.0, 'enable_dft_loss': False, 'enable_channel_loss': False, 'check_model': True, 'acc_strategy': 'token', 'train_dataloader_shuffle': True, 'group_by_length': False, 'max_epochs': 3, 'aligner_lr': None, 'vit_lr': None, 'use_logits_to_keep': None, 'ds3_gather_for_generation': True, 'resume_only_model': False, 'optimizer': None, 'loss_type': None, 'eval_metric': None, 'callbacks': [], 'early_stop_interval': None, 'eval_use_evalscope': False, 'eval_dataset': [], 'eval_dataset_args': None, 'eval_limit': None, 'eval_generation_config': None, 'extra_eval_args': None, 'tuner_type': 'lora', 'use_galore': False, 'galore_target_modules': None, 'galore_rank': 128, 'galore_update_proj_gap': 50, 'galore_scale': 1.0, 'galore_proj_type': 'std', 'galore_optim_per_parameter': False, 'galore_with_embedding': False, 'galore_quantization': False, 'galore_proj_quant': False, 'galore_proj_bits': 4, 'galore_proj_group_size': 256, 'galore_cos_threshold': 0.4, 'galore_gamma_proj': 2, 'galore_queue_size': 5, 'lisa_activated_layers': 0, 'lisa_step_interval': 20, 'use_flash_ckpt': False}
+2026-03-06 10:57:47,308 INFO    MainThread:1654770 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2060182528 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7ffc51dc5100>>
+2026-03-06 10:57:47,308 INFO    MainThread:1654770 [wandb_run.py:_config_callback():1403] config_cb model/num_parameters 2060182528 None

data/wandb/run-20260304_035219-bzc9z48s/files/config.yaml ADDED Viewed

	@@ -0,0 +1,632 @@

+_name_or_path:
+    value: /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
+_wandb:
+    value:
+        cli_version: 0.25.0
+        e:
+            cu7bd4tvbr27kn8zb6sicf7uvdvg0f2r:
+                args:
+                    - --model
+                    - Qwen/Qwen3-1.7B
+                    - --use_hf
+                    - "true"
+                    - --dataset
+                    - /root/code/na/Idea-filtering-training/data/thinking_dataset_v2_swift.jsonl
+                    - --train_type
+                    - lora
+                    - --lora_rank
+                    - "32"
+                    - --lora_alpha
+                    - "64"
+                    - --lora_dropout
+                    - "0.05"
+                    - --target_modules
+                    - q_proj
+                    - k_proj
+                    - v_proj
+                    - o_proj
+                    - gate_proj
+                    - up_proj
+                    - down_proj
+                    - --lora_ga_batch_size
+                    - "1"
+                    - --lora_ga_iters
+                    - "2"
+                    - --lora_ga_max_length
+                    - "1024"
+                    - --lora_ga_direction
+                    - ArB2r
+                    - --lora_ga_scale
+                    - stable
+                    - --lora_ga_stable_gamma
+                    - "16"
+                    - --per_device_train_batch_size
+                    - "1"
+                    - --gradient_accumulation_steps
+                    - "16"
+                    - --max_length
+                    - "2600"
+                    - --learning_rate
+                    - "2e-4"
+                    - --warmup_ratio
+                    - "0.05"
+                    - --max_epochs
+                    - "3"
+                    - --attn_impl
+                    - eager
+                    - --output_dir
+                    - /root/code/na/Idea-filtering-training/train/output
+                    - --save_strategy
+                    - steps
+                    - --save_steps
+                    - "1000"
+                    - --eval_steps
+                    - "500"
+                    - --dataloader_num_workers
+                    - "1"
+                    - --dataset_num_proc
+                    - "16"
+                    - --load_from_cache_file
+                    - "true"
+                    - --model_author
+                    - swift
+                    - --model_name
+                    - swift-robot
+                    - --loss_scale
+                    - ignore_empty_think
+                    - --report_to
+                    - wandb
+                cpu_count: 49
+                cpu_count_logical: 49
+                cudaVersion: "13.0"
+                disk:
+                    /:
+                        total: "960312868864"
+                        used: "865124937728"
+                email: nhatanh10102005@gmail.com
+                executable: /root/miniconda3/envs/RM/bin/python3
+                git:
+                    commit: 0dbe0bbbe696b2e49ffefa83123579a73fab61c6
+                    remote: https://tnnanh1010:@github.com/Drylab-AI/Idea-filtering-training.git
+                gpu: NVIDIA GeForce RTX 3060
+                gpu_count: 1
+                gpu_nvidia:
+                    - architecture: Ampere
+                      cudaCores: 3584
+                      memoryTotal: "12884901888"
+                      name: NVIDIA GeForce RTX 3060
+                      uuid: GPU-f370a18a-d749-7bf1-c827-82726afbb6cf
+                host: ubuntu
+                memory:
+                    total: "628090474496"
+                os: Linux-6.8.0-87-generic-x86_64-with-glibc2.35
+                program: /root/miniconda3/envs/RM/lib/python3.12/site-packages/swift/cli/sft.py
+                python: CPython 3.12.12
+                root: /root/code/na/Idea-filtering-training/data
+                startedAt: "2026-03-04T03:52:19.561578Z"
+                writerId: cu7bd4tvbr27kn8zb6sicf7uvdvg0f2r
+        m:
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "2": '*'
+              "5": 1
+              "6":
+                - 1
+              "7": []
+        python_version: 3.12.12
+        t:
+            "1":
+                - 1
+                - 11
+                - 49
+                - 51
+                - 71
+                - 84
+                - 98
+                - 105
+            "2":
+                - 1
+                - 11
+                - 49
+                - 51
+                - 71
+                - 84
+                - 98
+                - 105
+            "3":
+                - 7
+                - 13
+                - 19
+                - 62
+                - 66
+            "4": 3.12.12
+            "5": 0.25.0
+            "6": 5.2.0
+            "9":
+                "1": transformers_trainer
+            "12": 0.25.0
+            "13": linux-x86_64
+acc_strategy:
+    value: token
+accelerator_config:
+    value:
+        dispatch_batches: false
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.95
+adam_epsilon:
+    value: 1e-08
+aligner_lr:
+    value: null
+architectures:
+    value:
+        - Qwen3ForCausalLM
+attention_bias:
+    value: false
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: true
+batch_eval_metrics:
+    value: false
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: null
+callbacks:
+    value: []
+check_model:
+    value: true
+chunk_size_feed_forward:
+    value: 0
+data_seed:
+    value: 42
+dataloader_drop_last:
+    value: false
+dataloader_num_workers:
+    value: 1
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: 2
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_timeout:
+    value: 18000000
+debug:
+    value: []
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+do_eval:
+    value: false
+do_predict:
+    value: false
+do_train:
+    value: false
+ds3_gather_for_generation:
+    value: true
+dtype:
+    value: bfloat16
+early_stop_interval:
+    value: null
+enable_channel_loss:
+    value: false
+enable_dft_loss:
+    value: false
+enable_jit_checkpoint:
+    value: false
+eos_token_id:
+    value: 151645
+eval_accumulation_steps:
+    value: null
+eval_dataset:
+    value: []
+eval_dataset_args:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_generation_config:
+    value: null
+eval_limit:
+    value: null
+eval_metric:
+    value: null
+eval_on_start:
+    value: false
+eval_steps:
+    value: 500
+eval_strategy:
+    value: "no"
+eval_use_evalscope:
+    value: false
+eval_use_gather_object:
+    value: false
+extra_eval_args:
+    value: null
+fp16:
+    value: false
+fp16_full_eval:
+    value: false
+fsdp:
+    value: []
+fsdp_config:
+    value:
+        min_num_params: 0
+        xla: false
+        xla_fsdp_grad_ckpt: false
+        xla_fsdp_v2: false
+full_determinism:
+    value: false
+galore_cos_threshold:
+    value: 0.4
+galore_gamma_proj:
+    value: 2
+galore_optim_per_parameter:
+    value: false
+galore_proj_bits:
+    value: 4
+galore_proj_group_size:
+    value: 256
+galore_proj_quant:
+    value: false
+galore_proj_type:
+    value: std
+galore_quantization:
+    value: false
+galore_queue_size:
+    value: 5
+galore_rank:
+    value: 128
+galore_scale:
+    value: 1
+galore_target_modules:
+    value: null
+galore_update_proj_gap:
+    value: 50
+galore_with_embedding:
+    value: false
+generation_config:
+    value: null
+generation_max_length:
+    value: null
+generation_num_beams:
+    value: null
+gradient_accumulation_steps:
+    value: 16
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: false
+group_by_length:
+    value: false
+head_dim:
+    value: 128
+hidden_act:
+    value: silu
+hidden_size:
+    value: 2048
+hub_always_push:
+    value: false
+hub_model_id:
+    value: null
+hub_private_repo:
+    value: null
+hub_revision:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_num_input_tokens_seen:
+    value: "no"
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 6144
+is_encoder_decoder:
+    value: false
+label_names:
+    value: null
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+layer_types:
+    value:
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+learning_rate:
+    value: 0.0002
+length_column_name:
+    value: length
+liger_kernel_config:
+    value: null
+lisa_activated_layers:
+    value: 0
+lisa_step_interval:
+    value: 20
+load_best_model_at_end:
+    value: false
+local_rank:
+    value: -1
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging_dir:
+    value: /root/code/na/Idea-filtering-training/train/output/v0-20260304-035120/runs
+logging_first_step:
+    value: true
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 5
+logging_strategy:
+    value: steps
+loss_type:
+    value: null
+lr_scheduler_kwargs:
+    value: null
+lr_scheduler_type:
+    value: cosine
+max_epochs:
+    value: 3
+max_grad_norm:
+    value: 1
+max_position_embeddings:
+    value: 40960
+max_steps:
+    value: -1
+max_window_layers:
+    value: 28
+metric_for_best_model:
+    value: loss
+model/num_parameters:
+    value: 2066605056
+model_type:
+    value: qwen3
+neftune_noise_alpha:
+    value: null
+num_attention_heads:
+    value: 16
+num_hidden_layers:
+    value: 28
+num_key_value_heads:
+    value: 8
+num_train_epochs:
+    value: 3
+optim:
+    value: adamw_torch_fused
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+optimizer:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: /root/code/na/Idea-filtering-training/train/output/v0-20260304-035120
+output_hidden_states:
+    value: false
+pad_token_id:
+    value: 151643
+parallelism_config:
+    value: null
+peft_config:
+    value:
+        default:
+            alora_invocation_tokens: null
+            arrow_config: null
+            auto_mapping: null
+            base_model_name_or_path: /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
+            bias: none
+            corda_config: null
+            ensure_weight_tying: false
+            eva_config: null
+            exclude_modules: null
+            fan_in_fan_out: false
+            inference_mode: false
+            init_lora_weights: true
+            layer_replication: null
+            layers_pattern: null
+            layers_to_transform: null
+            lora_alpha: 64
+            lora_bias: false
+            lora_dropout: 0.05
+            lora_dtype: null
+            lorap_emb_lr: 1e-06
+            lorap_lr_ratio: null
+            megatron_config: null
+            megatron_core: megatron.core
+            modules_to_save: []
+            peft_type: LORA
+            peft_version: 0.18.1
+            qalora_group_size: 16
+            r: 32
+            revision: null
+            runtime_config:
+                ephemeral_gpu_offload: false
+            target_modules:
+                - o_proj
+                - q_proj
+                - down_proj
+                - v_proj
+                - gate_proj
+                - k_proj
+                - up_proj
+            target_parameters: null
+            task_type: CAUSAL_LM
+            trainable_token_indices: null
+            use_dora: false
+            use_qalora: false
+            use_rslora: false
+per_device_eval_batch_size:
+    value: 1
+per_device_train_batch_size:
+    value: 1
+predict_with_generate:
+    value: false
+prediction_loss_only:
+    value: false
+problem_type:
+    value: null
+project:
+    value: huggingface
+push_to_hub:
+    value: false
+remove_unused_columns:
+    value: false
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+resume_only_model:
+    value: false
+return_dict:
+    value: true
+rms_norm_eps:
+    value: 1e-06
+rope_parameters:
+    value:
+        rope_theta: 1000000
+        rope_type: default
+router_aux_loss_coef:
+    value: 0
+run_name:
+    value: /root/code/na/Idea-filtering-training/train/output/v0-20260304-035120
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_steps:
+    value: 1000
+save_strategy:
+    value: steps
+save_total_limit:
+    value: null
+seed:
+    value: 42
+skip_memory_metrics:
+    value: true
+sliding_window:
+    value: null
+sortish_sampler:
+    value: false
+tf32:
+    value: null
+tie_word_embeddings:
+    value: true
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_empty_cache_steps:
+    value: null
+trackio_space_id:
+    value: trackio
+train_dataloader_shuffle:
+    value: true
+train_sampling_strategy:
+    value: random
+transformers_version:
+    value: 5.2.0
+tuner_backend:
+    value: peft
+tuner_type:
+    value: lora
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_flash_ckpt:
+    value: false
+use_galore:
+    value: false
+use_liger_kernel:
+    value: false
+use_logits_to_keep:
+    value: null
+use_sliding_window:
+    value: false
+vit_gradient_checkpointing:
+    value: true
+vit_lr:
+    value: null
+vocab_size:
+    value: 151936
+warmup_ratio:
+    value: 0.05
+warmup_steps:
+    value: 0.05
+weight_decay:
+    value: 0.1

data/wandb/run-20260304_035219-bzc9z48s/files/output.log ADDED Viewed

The diff for this file is too large to render. See raw diff

data/wandb/run-20260304_035219-bzc9z48s/files/requirements.txt ADDED Viewed

	@@ -0,0 +1,159 @@

+trl==0.28.0
+pyarrow==23.0.1
+cffi==2.0.0
+aiosignal==1.4.0
+ms_swift==4.0.0
+aliyun-python-sdk-kms==2.16.5
+nvidia-cublas-cu12==12.8.4.1
+markdown-it-py==4.0.0
+nltk==3.9.3
+cuda-pathfinder==1.4.0
+sentencepiece==0.2.1
+pycryptodome==3.23.0
+hf-xet==1.3.2
+multiprocess==0.70.16
+wandb==0.25.0
+uv==0.10.8
+rich==14.3.3
+modelscope==1.34.0
+websockets==15.0.1
+binpacking==2.0.1
+mpmath==1.3.0
+certifi==2026.2.25
+triton==3.6.0
+nvidia-nvshmem-cu12==3.4.5
+python-multipart==0.0.22
+peft==0.18.1
+httpx==0.28.1
+numpy==2.4.2
+pillow==11.3.0
+wheel==0.46.3
+MarkupSafe==3.0.3
+ruff==0.15.4
+frozenlist==1.8.0
+xxhash==3.6.0
+psutil==7.2.2
+pytz==2026.1.post1
+platformdirs==4.9.2
+joblib==1.5.3
+nvidia-cuda-nvrtc-cu12==12.8.93
+safehttpx==0.1.7
+datasets==3.6.0
+tqdm==4.67.3
+openai==2.24.0
+nvidia-nccl-cu12==2.27.5
+sympy==1.14.0
+Werkzeug==3.1.6
+sentry-sdk==2.54.0
+attrdict==2.0.1
+nvidia-nvtx-cu12==12.8.90
+PyYAML==6.0.3
+requests==2.32.5
+importlib_metadata==8.7.1
+h11==0.16.0
+json_repair==0.58.3
+typer-slim==0.24.0
+pandas==2.3.3
+absl-py==2.4.0
+tomlkit==0.13.3
+nvidia-cuda-cupti-cu12==12.8.90
+gitdb==4.0.12
+tiktoken==0.12.0
+cpm-kernels==1.0.11
+tensorboard-data-server==0.7.2
+sniffio==1.3.1
+sortedcontainers==2.4.0
+nvidia-curand-cu12==10.3.9.90
+aiohttp==3.13.3
+transformers-stream-generator==0.0.5
+gradio==5.50.0
+pycparser==3.0
+yarl==1.23.0
+Pygments==2.19.2
+ffmpy==1.0.0
+brotli==1.2.0
+idna==3.11
+Jinja2==3.1.6
+pip==26.0.1
+jieba==0.42.1
+typing_extensions==4.15.0
+torch==2.10.0
+attrs==25.4.0
+cuda-bindings==12.9.4
+filelock==3.25.0
+fonttools==4.61.1
+accelerate==1.12.0
+httpcore==1.0.9
+charset-normalizer==3.4.4
+regex==2026.2.28
+simplejson==3.20.2
+tensorboard==2.20.0
+python-dateutil==2.9.0.post0
+tzdata==2025.3
+typer==0.24.1
+pydantic==2.12.3
+jiter==0.13.0
+annotated-doc==0.0.4
+aliyun-python-sdk-core==2.16.0
+oss2==2.19.1
+fastapi==0.135.1
+shellingham==1.5.4
+addict==2.4.0
+omegaconf==2.3.0
+distro==1.9.0
+fsspec==2025.3.0
+cycler==0.12.1
+rouge==1.0.1
+grpcio==1.78.0
+kiwisolver==1.4.9
+Markdown==3.10.2
+pydub==0.25.1
+protobuf==6.33.5
+crcmod==1.7
+typing-inspection==0.4.2
+zstandard==0.25.0
+gradio_client==1.14.0
+tokenizers==0.22.2
+packaging==25.0
+zipp==3.23.0
+mdurl==0.1.2
+contourpy==1.3.3
+aiohappyeyeballs==2.6.1
+transformers==5.2.0
+nvidia-cuda-runtime-cu12==12.8.90
+semantic-version==2.10.0
+dacite==1.9.2
+antlr4-python3-runtime==4.9.3
+anyio==4.12.1
+aiofiles==24.1.0
+nvidia-cusparse-cu12==12.5.8.93
+networkx==3.6.1
+cryptography==46.0.5
+uvicorn==0.41.0
+nvidia-cusolver-cu12==11.7.3.90
+pydantic_core==2.41.4
+nvidia-cufile-cu12==1.13.1.3
+pyparsing==3.3.2
+nvidia-cusparselt-cu12==0.7.1
+annotated-types==0.7.0
+propcache==0.4.1
+click==8.3.1
+starlette==0.52.1
+orjson==3.11.7
+dill==0.3.8
+groovy==0.1.2
+safetensors==0.7.0
+GitPython==3.1.46
+smmap==5.0.2
+nvidia-nvjitlink-cu12==12.8.93
+einops==0.8.2
+nvidia-cufft-cu12==11.3.3.83
+multidict==6.7.1
+matplotlib==3.10.8
+six==1.17.0
+jmespath==0.10.0
+nvidia-cudnn-cu12==9.10.2.21
+urllib3==2.6.3
+setuptools==80.10.2
+scipy==1.17.1
+huggingface_hub==1.5.0

data/wandb/run-20260304_035219-bzc9z48s/files/wandb-metadata.json ADDED Viewed

	@@ -0,0 +1,110 @@

+{
+  "os":  "Linux-6.8.0-87-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.12.12",
+  "startedAt":  "2026-03-04T03:52:19.561578Z",
+  "args":  [
+    "--model",
+    "Qwen/Qwen3-1.7B",
+    "--use_hf",
+    "true",
+    "--dataset",
+    "/root/code/na/Idea-filtering-training/data/thinking_dataset_v2_swift.jsonl",
+    "--train_type",
+    "lora",
+    "--lora_rank",
+    "32",
+    "--lora_alpha",
+    "64",
+    "--lora_dropout",
+    "0.05",
+    "--target_modules",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "--lora_ga_batch_size",
+    "1",
+    "--lora_ga_iters",
+    "2",
+    "--lora_ga_max_length",
+    "1024",
+    "--lora_ga_direction",
+    "ArB2r",
+    "--lora_ga_scale",
+    "stable",
+    "--lora_ga_stable_gamma",
+    "16",
+    "--per_device_train_batch_size",
+    "1",
+    "--gradient_accumulation_steps",
+    "16",
+    "--max_length",
+    "2600",
+    "--learning_rate",
+    "2e-4",
+    "--warmup_ratio",
+    "0.05",
+    "--max_epochs",
+    "3",
+    "--attn_impl",
+    "eager",
+    "--output_dir",
+    "/root/code/na/Idea-filtering-training/train/output",
+    "--save_strategy",
+    "steps",
+    "--save_steps",
+    "1000",
+    "--eval_steps",
+    "500",
+    "--dataloader_num_workers",
+    "1",
+    "--dataset_num_proc",
+    "16",
+    "--load_from_cache_file",
+    "true",
+    "--model_author",
+    "swift",
+    "--model_name",
+    "swift-robot",
+    "--loss_scale",
+    "ignore_empty_think",
+    "--report_to",
+    "wandb"
+  ],
+  "program":  "/root/miniconda3/envs/RM/lib/python3.12/site-packages/swift/cli/sft.py",
+  "git":  {
+    "remote":  "https://tnnanh1010:@github.com/Drylab-AI/Idea-filtering-training.git",
+    "commit":  "0dbe0bbbe696b2e49ffefa83123579a73fab61c6"
+  },
+  "email":  "nhatanh10102005@gmail.com",
+  "root":  "/root/code/na/Idea-filtering-training/data",
+  "host":  "ubuntu",
+  "executable":  "/root/miniconda3/envs/RM/bin/python3",
+  "cpu_count":  49,
+  "cpu_count_logical":  49,
+  "gpu":  "NVIDIA GeForce RTX 3060",
+  "gpu_count":  1,
+  "disk":  {
+    "/":  {
+      "total":  "960312868864",
+      "used":  "865124937728"
+    }
+  },
+  "memory":  {
+    "total":  "628090474496"
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA GeForce RTX 3060",
+      "memoryTotal":  "12884901888",
+      "cudaCores":  3584,
+      "architecture":  "Ampere",
+      "uuid":  "GPU-f370a18a-d749-7bf1-c827-82726afbb6cf"
+    }
+  ],
+  "cudaVersion":  "13.0",
+  "writerId":  "cu7bd4tvbr27kn8zb6sicf7uvdvg0f2r"
+}

data/wandb/run-20260304_035219-bzc9z48s/files/wandb-summary.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"train/token_acc":0.713329659081962,"train/grad_norm":0.028987018391489983,"_step":875,"train_samples_per_second":0.588,"train/epoch":3,"train_loss":1.1254750251988053,"_wandb":{"runtime":118958},"total_flos":1.168560397849688e+18,"_runtime":118958,"train_steps_per_second":0.037,"train_runtime":118959.0608,"train/learning_rate":4.573485906322894e-10,"_timestamp":1.772715298382969e+09,"train/loss":0.9691848754882812,"train/global_step":4374}

data/wandb/run-20260304_035219-bzc9z48s/logs/debug-core.log ADDED Viewed

	@@ -0,0 +1,15 @@

+{"time":"2026-03-04T03:52:19.636010859Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpizzvshbt/port-2895203.txt","pid":2895203,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-03-04T03:52:19.640913014Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":2895203}
+{"time":"2026-03-04T03:52:19.64082463Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-2895203-2907053-1415758021/socket","Net":"unix"}}
+{"time":"2026-03-04T03:52:19.788521881Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-03-04T03:52:19.800324062Z","level":"INFO","msg":"handleInformInit: received","streamId":"bzc9z48s","id":"1(@)"}
+{"time":"2026-03-04T03:52:20.001980096Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"bzc9z48s","id":"1(@)"}
+{"time":"2026-03-04T03:52:25.452788253Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"rpf9en822nne"}
+{"time":"2026-03-05T12:54:58.719926201Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
+{"time":"2026-03-05T12:54:58.720391834Z","level":"INFO","msg":"server is shutting down"}
+{"time":"2026-03-05T12:54:58.720342858Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
+{"time":"2026-03-05T12:54:58.720715555Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
+{"time":"2026-03-05T12:54:58.720699881Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-2895203-2907053-1415758021/socket","Net":"unix"}}
+{"time":"2026-03-05T12:54:59.799535118Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
+{"time":"2026-03-05T12:54:59.79964598Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
+{"time":"2026-03-05T12:54:59.799674575Z","level":"INFO","msg":"server is closed"}

data/wandb/run-20260304_035219-bzc9z48s/logs/debug-internal.log ADDED Viewed

	@@ -0,0 +1,14 @@

+{"time":"2026-03-04T03:52:19.801424661Z","level":"INFO","msg":"stream: starting","core version":"0.25.0"}
+{"time":"2026-03-04T03:52:20.001672605Z","level":"INFO","msg":"stream: created new stream","id":"bzc9z48s"}
+{"time":"2026-03-04T03:52:20.001883943Z","level":"INFO","msg":"handler: started","stream_id":"bzc9z48s"}
+{"time":"2026-03-04T03:52:20.001944483Z","level":"INFO","msg":"stream: started","id":"bzc9z48s"}
+{"time":"2026-03-04T03:52:20.001991456Z","level":"INFO","msg":"sender: started","stream_id":"bzc9z48s"}
+{"time":"2026-03-04T03:52:20.001995704Z","level":"INFO","msg":"writer: started","stream_id":"bzc9z48s"}
+{"time":"2026-03-04T22:00:05.351127978Z","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/nhatanh10102005-vinuniversity/ms-swift/bzc9z48s/file_stream","body":"\n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>502 Server Error</title>\n</head>\n<body text=#000000 bgcolor=#ffffff>\n<h1>Error: Server Error</h1>\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\n<h2></h2>\n</body></html>\n"}
+{"time":"2026-03-04T22:06:05.347371295Z","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/nhatanh10102005-vinuniversity/ms-swift/bzc9z48s/file_stream","body":"\n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>502 Server Error</title>\n</head>\n<body text=#000000 bgcolor=#ffffff>\n<h1>Error: Server Error</h1>\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\n<h2></h2>\n</body></html>\n"}
+{"time":"2026-03-05T02:39:18.098277092Z","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/nhatanh10102005-vinuniversity/ms-swift/bzc9z48s/file_stream","body":"\n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>502 Server Error</title>\n</head>\n<body text=#000000 bgcolor=#ffffff>\n<h1>Error: Server Error</h1>\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\n<h2></h2>\n</body></html>\n"}
+{"time":"2026-03-05T12:54:58.720317991Z","level":"INFO","msg":"stream: closing","id":"bzc9z48s"}
+{"time":"2026-03-05T12:54:59.333556397Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-03-05T12:54:59.784047742Z","level":"INFO","msg":"handler: closed","stream_id":"bzc9z48s"}
+{"time":"2026-03-05T12:54:59.784388437Z","level":"INFO","msg":"sender: closed","stream_id":"bzc9z48s"}
+{"time":"2026-03-05T12:54:59.784422878Z","level":"INFO","msg":"stream: closed","id":"bzc9z48s"}

data/wandb/run-20260304_035219-bzc9z48s/logs/debug.log ADDED Viewed

	@@ -0,0 +1,24 @@

+2026-03-04 03:52:19,563 INFO    MainThread:2895203 [wandb_setup.py:_flush():81] Current SDK version is 0.25.0
+2026-03-04 03:52:19,563 INFO    MainThread:2895203 [wandb_setup.py:_flush():81] Configure stats pid to 2895203
+2026-03-04 03:52:19,563 INFO    MainThread:2895203 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-03-04 03:52:19,563 INFO    MainThread:2895203 [wandb_init.py:setup_run_log_directory():717] Logging user logs to /root/code/na/Idea-filtering-training/data/wandb/run-20260304_035219-bzc9z48s/logs/debug.log
+2026-03-04 03:52:19,563 INFO    MainThread:2895203 [wandb_init.py:setup_run_log_directory():718] Logging internal logs to /root/code/na/Idea-filtering-training/data/wandb/run-20260304_035219-bzc9z48s/logs/debug-internal.log
+2026-03-04 03:52:19,563 INFO    MainThread:2895203 [wandb_init.py:init():844] calling init triggers
+2026-03-04 03:52:19,563 INFO    MainThread:2895203 [wandb_init.py:init():849] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-03-04 03:52:19,563 INFO    MainThread:2895203 [wandb_init.py:init():892] starting backend
+2026-03-04 03:52:19,788 INFO    MainThread:2895203 [wandb_init.py:init():895] sending inform_init request
+2026-03-04 03:52:19,791 INFO    MainThread:2895203 [wandb_init.py:init():903] backend started and connected
+2026-03-04 03:52:19,793 INFO    MainThread:2895203 [wandb_init.py:init():973] updated telemetry
+2026-03-04 03:52:19,802 INFO    MainThread:2895203 [wandb_init.py:init():997] communicating run to backend with 90.0 second timeout
+2026-03-04 03:52:20,304 INFO    MainThread:2895203 [wandb_init.py:init():1042] starting run threads in backend
+2026-03-04 03:52:20,444 INFO    MainThread:2895203 [wandb_run.py:_console_start():2524] atexit reg
+2026-03-04 03:52:20,444 INFO    MainThread:2895203 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-03-04 03:52:20,444 INFO    MainThread:2895203 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-03-04 03:52:20,444 INFO    MainThread:2895203 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-03-04 03:52:20,457 INFO    MainThread:2895203 [wandb_init.py:init():1082] run started, returning control to user process
+2026-03-04 03:52:20,464 INFO    MainThread:2895203 [wandb_run.py:_config_callback():1403] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': '/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', 'revision': None, 'inference_mode': False, 'r': 32, 'target_modules': ['o_proj', 'q_proj', 'down_proj', 'v_proj', 'gate_proj', 'k_proj', 'up_proj'], 'exclude_modules': None, 'lora_alpha': 64, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': [], 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False, 'lora_dtype': None, 'lorap_lr_ratio': None, 'lorap_emb_lr': 1e-06}}, 'vocab_size': 151936, 'max_position_embeddings': 40960, 'hidden_size': 2048, 'intermediate_size': 6144, 'num_hidden_layers': 28, 'num_attention_heads': 16, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_bias': False, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'pad_token_id': 151643, 'bos_token_id': None, 'eos_token_id': 151645, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 1000000, 'rope_type': 'default'}, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': ['Qwen3ForCausalLM'], 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', 'transformers_version': '5.2.0', 'model_type': 'qwen3', 'output_attentions': False, 'output_dir': '/root/code/na/Idea-filtering-training/train/output/v0-20260304-035120', 'per_device_train_batch_size': 1, 'num_train_epochs': 3.0, 'max_steps': -1, 'learning_rate': 0.0002, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_steps': 0.05, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 16, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 5, 'logging_first_step': True, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': '/root/code/na/Idea-filtering-training/train/output/v0-20260304-035120', 'project': 'huggingface', 'trackio_space_id': 'trackio', 'eval_strategy': 'no', 'eval_steps': 500.0, 'eval_delay': 0, 'per_device_eval_batch_size': 1, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': False, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 1, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': 2, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_backend': None, 'ddp_timeout': 18000000, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'resume_from_checkpoint': None, 'warmup_ratio': 0.05, 'logging_dir': '/root/code/na/Idea-filtering-training/train/output/v0-20260304-035120/runs', 'local_rank': -1, 'sortish_sampler': False, 'predict_with_generate': False, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None, 'tuner_backend': 'peft', 'vit_gradient_checkpointing': True, 'router_aux_loss_coef': 0.0, 'enable_dft_loss': False, 'enable_channel_loss': False, 'check_model': True, 'acc_strategy': 'token', 'train_dataloader_shuffle': True, 'group_by_length': False, 'max_epochs': 3, 'aligner_lr': None, 'vit_lr': None, 'use_logits_to_keep': None, 'ds3_gather_for_generation': True, 'resume_only_model': False, 'optimizer': None, 'loss_type': None, 'eval_metric': None, 'callbacks': [], 'early_stop_interval': None, 'eval_use_evalscope': False, 'eval_dataset': [], 'eval_dataset_args': None, 'eval_limit': None, 'eval_generation_config': None, 'extra_eval_args': None, 'tuner_type': 'lora', 'use_galore': False, 'galore_target_modules': None, 'galore_rank': 128, 'galore_update_proj_gap': 50, 'galore_scale': 1.0, 'galore_proj_type': 'std', 'galore_optim_per_parameter': False, 'galore_with_embedding': False, 'galore_quantization': False, 'galore_proj_quant': False, 'galore_proj_bits': 4, 'galore_proj_group_size': 256, 'galore_cos_threshold': 0.4, 'galore_gamma_proj': 2, 'galore_queue_size': 5, 'lisa_activated_layers': 0, 'lisa_step_interval': 20, 'use_flash_ckpt': False}
+2026-03-04 03:52:20,476 INFO    MainThread:2895203 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2066605056 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7ffdd71ffd40>>
+2026-03-04 03:52:20,476 INFO    MainThread:2895203 [wandb_run.py:_config_callback():1403] config_cb model/num_parameters 2066605056 None
+2026-03-05 12:54:58,719 INFO    wandb-AsyncioManager-main:2895203 [service_client.py:_forward_responses():134] Reached EOF.
+2026-03-05 12:54:58,720 INFO    wandb-AsyncioManager-main:2895203 [mailbox.py:close():155] Closing mailbox, abandoning 1 handles.

data/wandb/run-20260304_035219-bzc9z48s/run-bzc9z48s.wandb ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbdbb63608a901207189fc07dd128b30e789efd6d2ad661822b553b1d5bb4e0
+size 9286321

data/wandb/run-20260306_073928-dpxzw953/files/output.log ADDED Viewed

	@@ -0,0 +1,32 @@

+Train:   0%|                                                                                                                                                                            | 0/4374 [00:00<?, ?it/s][INFO:swift] use_logits_to_keep: True
+Train:   3%|██▍                                                                    | 150/4374 [1:05:30<30:16:07, 25.80s/it]
+{'loss': '2.883', 'grad_norm': '0.759', 'learning_rate': '9.1e-07', 'token_acc': '0.5381', 'epoch': '0.0006863', 'global_step/max_steps': '1/4374', 'elapsed_time': '27s', 'remaining_time': '1d 8h 53m 59s', 'memory(GiB)': '8.7', 'train_speed(s/it)': '27.08'}
+{'loss': '2.962', 'grad_norm': '0.7302', 'learning_rate': '4.57e-06', 'token_acc': '0.534', 'epoch': '0.003431', 'global_step/max_steps': '5/4374', 'elapsed_time': '2m 13s', 'remaining_time': '1d 8h 16m 8s', 'memory(GiB)': '9.95', 'train_speed(s/it)': '26.59'}
+{'loss': '2.918', 'grad_norm': '0.6915', 'learning_rate': '9.13e-06', 'token_acc': '0.5313', 'epoch': '0.006863', 'global_step/max_steps': '10/4374', 'elapsed_time': '4m 25s', 'remaining_time': '1d 8h 4m 23s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.46'}
+{'loss': '2.736', 'grad_norm': '0.4563', 'learning_rate': '1.37e-05', 'token_acc': '0.5312', 'epoch': '0.01029', 'global_step/max_steps': '15/4374', 'elapsed_time': '6m 35s', 'remaining_time': '1d 7h 54m 24s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.35'}
+{'loss': '2.398', 'grad_norm': '0.2684', 'learning_rate': '1.826e-05', 'token_acc': '0.5442', 'epoch': '0.01373', 'global_step/max_steps': '20/4374', 'elapsed_time': '8m 46s', 'remaining_time': '1d 7h 50m 4s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.32'}
+{'loss': '2.196', 'grad_norm': '0.149', 'learning_rate': '2.283e-05', 'token_acc': '0.5421', 'epoch': '0.01716', 'global_step/max_steps': '25/4374', 'elapsed_time': '10m 59s', 'remaining_time': '1d 7h 50m 15s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.35'}
+{'loss': '2.046', 'grad_norm': '0.07151', 'learning_rate': '2.74e-05', 'token_acc': '0.5469', 'epoch': '0.02059', 'global_step/max_steps': '30/4374', 'elapsed_time': '13m 9s', 'remaining_time': '1d 7h 44m 51s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.31'}
+{'loss': '1.945', 'grad_norm': '0.05515', 'learning_rate': '3.196e-05', 'token_acc': '0.545', 'epoch': '0.02402', 'global_step/max_steps': '35/4374', 'elapsed_time': '15m 22s', 'remaining_time': '1d 7h 44m 34s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.34'}
+{'loss': '1.924', 'grad_norm': '0.05004', 'learning_rate': '3.653e-05', 'token_acc': '0.5445', 'epoch': '0.02745', 'global_step/max_steps': '40/4374', 'elapsed_time': '17m 33s', 'remaining_time': '1d 7h 41m 42s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.33'}
+{'loss': '1.857', 'grad_norm': '0.05194', 'learning_rate': '4.11e-05', 'token_acc': '0.5542', 'epoch': '0.03088', 'global_step/max_steps': '45/4374', 'elapsed_time': '19m 44s', 'remaining_time': '1d 7h 37m 36s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.3'}
+{'loss': '1.752', 'grad_norm': '0.04649', 'learning_rate': '4.566e-05', 'token_acc': '0.5766', 'epoch': '0.03431', 'global_step/max_steps': '50/4374', 'elapsed_time': '21m 56s', 'remaining_time': '1d 7h 36m 37s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.32'}
+{'loss': '1.753', 'grad_norm': '0.0284', 'learning_rate': '5.023e-05', 'token_acc': '0.5762', 'epoch': '0.03774', 'global_step/max_steps': '55/4374', 'elapsed_time': '24m 8s', 'remaining_time': '1d 7h 35m 17s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.33'}
+{'loss': '1.729', 'grad_norm': '0.03265', 'learning_rate': '5.479e-05', 'token_acc': '0.5771', 'epoch': '0.04118', 'global_step/max_steps': '60/4374', 'elapsed_time': '26m 20s', 'remaining_time': '1d 7h 33m 20s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.33'}
+{'loss': '1.723', 'grad_norm': '0.02901', 'learning_rate': '5.936e-05', 'token_acc': '0.583', 'epoch': '0.04461', 'global_step/max_steps': '65/4374', 'elapsed_time': '28m 34s', 'remaining_time': '1d 7h 33m 53s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.37'}
+{'loss': '1.613', 'grad_norm': '0.02471', 'learning_rate': '6.393e-05', 'token_acc': '0.5987', 'epoch': '0.04804', 'global_step/max_steps': '70/4374', 'elapsed_time': '30m 43s', 'remaining_time': '1d 7h 28m 57s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.33'}
+{'loss': '1.641', 'grad_norm': '0.02978', 'learning_rate': '6.849e-05', 'token_acc': '0.5909', 'epoch': '0.05147', 'global_step/max_steps': '75/4374', 'elapsed_time': '32m 51s', 'remaining_time': '1d 7h 22m 57s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.28'}
+{'loss': '1.621', 'grad_norm': '0.02749', 'learning_rate': '7.306e-05', 'token_acc': '0.5946', 'epoch': '0.0549', 'global_step/max_steps': '80/4374', 'elapsed_time': '35m 1s', 'remaining_time': '1d 7h 19m 11s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.26'}
+{'loss': '1.587', 'grad_norm': '0.03279', 'learning_rate': '7.763e-05', 'token_acc': '0.5998', 'epoch': '0.05833', 'global_step/max_steps': '85/4374', 'elapsed_time': '37m 9s', 'remaining_time': '1d 7h 14m 44s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.23'}
+{'loss': '1.565', 'grad_norm': '0.02734', 'learning_rate': '8.219e-05', 'token_acc': '0.6056', 'epoch': '0.06176', 'global_step/max_steps': '90/4374', 'elapsed_time': '39m 19s', 'remaining_time': '1d 7h 11m 14s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.21'}
+{'loss': '1.518', 'grad_norm': '0.02591', 'learning_rate': '8.676e-05', 'token_acc': '0.6154', 'epoch': '0.06519', 'global_step/max_steps': '95/4374', 'elapsed_time': '41m 30s', 'remaining_time': '1d 7h 8m 56s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.21'}
+{'loss': '1.506', 'grad_norm': '0.02655', 'learning_rate': '9.132e-05', 'token_acc': '0.6157', 'epoch': '0.06863', 'global_step/max_steps': '100/4374', 'elapsed_time': '43m 38s', 'remaining_time': '1d 7h 4m 58s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.18'}
+{'loss': '1.522', 'grad_norm': '0.02904', 'learning_rate': '9.589e-05', 'token_acc': '0.6135', 'epoch': '0.07206', 'global_step/max_steps': '105/4374', 'elapsed_time': '45m 47s', 'remaining_time': '1d 7h 1m 26s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.16'}
+{'loss': '1.469', 'grad_norm': '0.03006', 'learning_rate': '0.0001005', 'token_acc': '0.6211', 'epoch': '0.07549', 'global_step/max_steps': '110/4374', 'elapsed_time': '48m 3s', 'remaining_time': '1d 7h 2m 29s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.21'}
+{'loss': '1.459', 'grad_norm': '0.03309', 'learning_rate': '0.000105', 'token_acc': '0.6205', 'epoch': '0.07892', 'global_step/max_steps': '115/4374', 'elapsed_time': '50m 15s', 'remaining_time': '1d 7h 0m 58s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.22'}
+{'loss': '1.413', 'grad_norm': '0.02772', 'learning_rate': '0.0001096', 'token_acc': '0.6308', 'epoch': '0.08235', 'global_step/max_steps': '120/4374', 'elapsed_time': '52m 26s', 'remaining_time': '1d 6h 58m 30s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.21'}
+{'loss': '1.428', 'grad_norm': '0.03154', 'learning_rate': '0.0001142', 'token_acc': '0.6297', 'epoch': '0.08578', 'global_step/max_steps': '125/4374', 'elapsed_time': '54m 38s', 'remaining_time': '1d 6h 57m 19s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.23'}
+{'loss': '1.41', 'grad_norm': '0.03049', 'learning_rate': '0.0001187', 'token_acc': '0.6343', 'epoch': '0.08921', 'global_step/max_steps': '130/4374', 'elapsed_time': '56m 50s', 'remaining_time': '1d 6h 55m 20s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.23'}
+{'loss': '1.426', 'grad_norm': '0.03384', 'learning_rate': '0.0001233', 'token_acc': '0.631', 'epoch': '0.09264', 'global_step/max_steps': '135/4374', 'elapsed_time': '58m 60s', 'remaining_time': '1d 6h 52m 27s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.22'}
+{'loss': '1.328', 'grad_norm': '0.03483', 'learning_rate': '0.0001278', 'token_acc': '0.6469', 'epoch': '0.09608', 'global_step/max_steps': '140/4374', 'elapsed_time': '1h 1m 8s', 'remaining_time': '1d 6h 48m 55s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.2'}
+{'loss': '1.445', 'grad_norm': '0.03589', 'learning_rate': '0.0001324', 'token_acc': '0.6279', 'epoch': '0.09951', 'global_step/max_steps': '145/4374', 'elapsed_time': '1h 3m 20s', 'remaining_time': '1d 6h 47m 14s', 'memory(GiB)': '11.16', 'train_speed(s/it)': '26.21'}

data/wandb/run-20260306_073928-dpxzw953/files/requirements.txt ADDED Viewed

	@@ -0,0 +1,241 @@

+psutil==7.2.2
+colorama==0.4.6
+trl==0.28.0
+pyarrow==23.0.1
+msgpack==1.1.2
+astor==0.8.1
+cffi==2.0.0
+aiosignal==1.4.0
+sse-starlette==3.3.2
+setproctitle==1.3.7
+ms_swift==4.0.0
+mistral_common==1.9.1
+aliyun-python-sdk-kms==2.16.5
+nvidia-cublas-cu12==12.8.4.1
+markdown-it-py==4.0.0
+cachetools==7.0.3
+nltk==3.9.3
+cuda-pathfinder==1.4.0
+sentencepiece==0.2.1
+pycryptodome==3.23.0
+hf-xet==1.3.2
+multiprocess==0.70.16
+wandb==0.25.0
+fastar==0.8.0
+uv==0.10.8
+interegular==0.3.3
+rich==14.3.3
+modelscope==1.34.0
+websockets==15.0.1
+binpacking==2.0.1
+seaborn==0.13.2
+uvloop==0.22.1
+mpmath==1.3.0
+certifi==2026.2.25
+vllm==0.16.0
+supervisor==4.3.0
+flashinfer-python==0.6.3
+cbor2==5.8.0
+msgspec==0.20.0
+threadpoolctl==3.6.0
+watchfiles==1.1.1
+python-multipart==0.0.22
+peft==0.18.1
+httpx==0.28.1
+pillow==11.3.0
+wheel==0.46.3
+MarkupSafe==3.0.3
+ruff==0.15.4
+frozenlist==1.8.0
+xxhash==3.6.0
+psutil==7.2.2
+pytz==2026.1.post1
+platformdirs==4.9.2
+joblib==1.5.3
+transformers==5.3.0
+scikit-learn==1.8.0
+nvidia-cuda-nvrtc-cu12==12.8.93
+nvidia-cutlass-dsl-libs-base==4.4.1
+openai-harmony==0.0.8
+safehttpx==0.1.7
+gdown==5.2.1
+diskcache==5.6.3
+datasets==3.6.0
+tqdm==4.67.3
+openai==2.24.0
+nvidia-nccl-cu12==2.27.5
+sympy==1.14.0
+tabulate==0.10.0
+Werkzeug==3.1.6
+sentry-sdk==2.54.0
+numba==0.61.2
+attrdict==2.0.1
+referencing==0.37.0
+cuda-python==13.1.1
+jsonschema-specifications==2025.9.1
+nvidia-nvtx-cu12==12.8.90
+email-validator==2.3.0
+PyYAML==6.0.3
+requests==2.32.5
+cloudpickle==3.1.2
+xgrammar==0.1.29
+importlib_metadata==8.7.1
+prometheus_client==0.24.1
+h11==0.16.0
+json_repair==0.58.3
+typer-slim==0.24.0
+pandas==2.3.3
+absl-py==2.4.0
+tomlkit==0.13.3
+nvidia-cuda-cupti-cu12==12.8.90
+gitdb==4.0.12
+tiktoken==0.12.0
+soupsieve==2.8.3
+cpm-kernels==1.0.11
+tensorboard-data-server==0.7.2
+sniffio==1.3.1
+sortedcontainers==2.4.0
+pycountry==26.2.16
+triton==3.5.1
+nvidia-curand-cu12==10.3.9.90
+beautifulsoup4==4.14.3
+aiohttp==3.13.3
+nvidia-cutlass-dsl==4.4.1
+transformers-stream-generator==0.0.5
+gradio==5.50.0
+lark==1.2.2
+pycparser==3.0
+yarl==1.23.0
+outlines_core==0.2.11
+anthropic==0.84.0
+jsonschema==4.26.0
+Pygments==2.19.2
+nvidia-nvshmem-cu12==3.3.20
+ffmpy==1.0.0
+brotli==1.2.0
+idna==3.11
+Jinja2==3.1.6
+pip==26.0.1
+docstring_parser==0.17.0
+jieba==0.42.1
+typing_extensions==4.15.0
+torch==2.9.1
+attrs==25.4.0
+filelock==3.25.0
+fonttools==4.61.1
+accelerate==1.12.0
+httpcore==1.0.9
+ijson==3.5.0
+model-hosting-container-standards==0.1.13
+PyJWT==2.11.0
+charset-normalizer==3.4.4
+regex==2026.2.28
+simplejson==3.20.2
+tensorboard==2.20.0
+python-json-logger==4.0.0
+python-dateutil==2.9.0.post0
+nvidia-cudnn-frontend==1.18.0
+tzdata==2025.3
+typer==0.24.1
+pydantic==2.12.3
+jiter==0.13.0
+annotated-doc==0.0.4
+aliyun-python-sdk-core==2.16.0
+oss2==2.19.1
+fastapi==0.135.1
+shellingham==1.5.4
+addict==2.4.0
+omegaconf==2.3.0
+distro==1.9.0
+depyf==0.20.0
+numpy==2.2.6
+rignore==0.7.6
+torchaudio==2.9.1
+ray==2.54.0
+blake3==1.0.8
+fsspec==2025.3.0
+cycler==0.12.1
+rouge==1.0.1
+pydantic-settings==2.13.1
+grpcio==1.78.0
+kiwisolver==1.4.9
+partial-json-parser==0.2.1.1.post7
+Markdown==3.10.2
+httptools==0.7.1
+pydantic-extra-types==2.11.0
+rich-toolkit==0.19.7
+mcp==1.26.0
+pydub==0.25.1
+protobuf==6.33.5
+crcmod==1.7
+typing-inspection==0.4.2
+zstandard==0.25.0
+gradio_client==1.14.0
+tokenizers==0.22.2
+packaging==25.0
+zipp==3.23.0
+py-cpuinfo==9.0.0
+mdurl==0.1.2
+contourpy==1.3.3
+pyzmq==27.1.0
+aiohappyeyeballs==2.6.1
+ninja==1.13.0
+nvidia-cuda-runtime-cu12==12.8.90
+semantic-version==2.10.0
+dacite==1.9.2
+antlr4-python3-runtime==4.9.3
+python-dotenv==1.2.2
+compressed-tensors==0.13.0
+gguf==0.18.0
+anyio==4.12.1
+aiofiles==24.1.0
+nvidia-cusparse-cu12==12.5.8.93
+networkx==3.6.1
+cryptography==46.0.5
+uvicorn==0.41.0
+nvidia-cusolver-cu12==11.7.3.90
+fastapi-cloud-cli==0.14.0
+fastapi-cli==0.0.24
+pydantic_core==2.41.4
+llvmlite==0.44.0
+nvidia-cufile-cu12==1.13.1.3
+rpds-py==0.30.0
+pyparsing==3.3.2
+nvidia-cusparselt-cu12==0.7.1
+annotated-types==0.7.0
+pybase64==1.4.3
+propcache==0.4.1
+prometheus-fastapi-instrumentator==7.1.0
+click==8.3.1
+starlette==0.52.1
+PySocks==1.7.1
+orjson==3.11.7
+dill==0.3.8
+httpx-sse==0.4.3
+nvidia-ml-py==13.590.48
+loguru==0.7.3
+groovy==0.1.2
+cupy-cuda12x==14.0.1
+safetensors==0.7.0
+GitPython==3.1.46
+lm-format-enforcer==0.11.3
+grpcio-reflection==1.78.0
+smmap==5.0.2
+opencv-python-headless==4.13.0.92
+nvidia-nvjitlink-cu12==12.8.93
+einops==0.8.2
+nvidia-cufft-cu12==11.3.3.83
+multidict==6.7.1
+dnspython==2.8.0
+matplotlib==3.10.8
+six==1.17.0
+jmespath==0.10.0
+apache-tvm-ffi==0.1.9
+llguidance==1.3.0
+nvidia-cudnn-cu12==9.10.2.21
+urllib3==2.6.3
+setuptools==80.10.2
+cuda-bindings==13.1.1
+scipy==1.17.1
+huggingface_hub==1.5.0
+torchvision==0.24.1

data/wandb/run-20260306_073928-dpxzw953/files/wandb-metadata.json ADDED Viewed

	@@ -0,0 +1,97 @@

+{
+  "os":  "Linux-6.8.0-87-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.12.12",
+  "startedAt":  "2026-03-06T07:39:28.778950Z",
+  "args":  [
+    "--model",
+    "Qwen/Qwen3-1.7B",
+    "--use_hf",
+    "true",
+    "--dataset",
+    "/root/code/na/Idea-filtering-training/data/thinking_dataset_v2_swift.jsonl",
+    "--train_type",
+    "lora",
+    "--lora_rank",
+    "32",
+    "--lora_alpha",
+    "64",
+    "--lora_dropout",
+    "0.05",
+    "--target_modules",
+    "q_proj",
+    "k_proj",
+    "v_proj,o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "--per_device_train_batch_size",
+    "1",
+    "--gradient_accumulation_steps",
+    "16",
+    "--max_length",
+    "2600",
+    "--learning_rate",
+    "2e-4",
+    "--warmup_ratio",
+    "0.05",
+    "--max_epochs",
+    "3",
+    "--attn_impl",
+    "eager",
+    "--output_dir",
+    "/root/code/na/Idea-filtering-training/train/output",
+    "--save_strategy",
+    "steps",
+    "--save_steps",
+    "1000",
+    "--eval_steps",
+    "500",
+    "--dataloader_num_workers",
+    "1",
+    "--dataset_num_proc",
+    "16",
+    "--load_from_cache_file",
+    "true",
+    "--model_author",
+    "swift",
+    "--model_name",
+    "swift-robot",
+    "--loss_scale",
+    "ignore_empty_think",
+    "--report_to",
+    "wandb"
+  ],
+  "program":  "/root/miniconda3/envs/RM/lib/python3.12/site-packages/swift/cli/sft.py",
+  "git":  {
+    "remote":  "https://tnnanh1010:@github.com/Drylab-AI/Idea-filtering-training.git",
+    "commit":  "0dbe0bbbe696b2e49ffefa83123579a73fab61c6"
+  },
+  "email":  "nhatanh10102005@gmail.com",
+  "root":  "/root/code/na/Idea-filtering-training/data",
+  "host":  "ubuntu",
+  "executable":  "/root/miniconda3/envs/RM/bin/python3",
+  "cpu_count":  49,
+  "cpu_count_logical":  49,
+  "gpu":  "NVIDIA GeForce RTX 3060",
+  "gpu_count":  1,
+  "disk":  {
+    "/":  {
+      "total":  "960312868864",
+      "used":  "872757264384"
+    }
+  },
+  "memory":  {
+    "total":  "628090474496"
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA GeForce RTX 3060",
+      "memoryTotal":  "12884901888",
+      "cudaCores":  3584,
+      "architecture":  "Ampere",
+      "uuid":  "GPU-f370a18a-d749-7bf1-c827-82726afbb6cf"
+    }
+  ],
+  "cudaVersion":  "13.0",
+  "writerId":  "tjqljpihi24rr4l4o8xbv3328g1gs1n3"
+}

data/wandb/run-20260306_073928-dpxzw953/logs/debug-core.log ADDED Viewed

	@@ -0,0 +1,8 @@

+{"time":"2026-03-06T07:39:28.88021523Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpg_k4o6rr/port-3272902.txt","pid":3272902,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-03-06T07:39:28.882449709Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":3272902}
+{"time":"2026-03-06T07:39:28.882308612Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-3272902-3286179-1404695856/socket","Net":"unix"}}
+{"time":"2026-03-06T07:39:29.020770654Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-03-06T07:39:29.036363468Z","level":"INFO","msg":"handleInformInit: received","streamId":"dpxzw953","id":"1(@)"}
+{"time":"2026-03-06T07:39:29.255684067Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"dpxzw953","id":"1(@)"}
+{"time":"2026-03-06T07:39:35.284387334Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"cetk0o1tw0pu"}
+{"time":"2026-03-06T08:45:03.956181644Z","level":"INFO","msg":"server: parent process exited, terminating service process"}

data/wandb/run-20260306_073928-dpxzw953/logs/debug-internal.log ADDED Viewed

	@@ -0,0 +1,6 @@

+{"time":"2026-03-06T07:39:29.036940297Z","level":"INFO","msg":"stream: starting","core version":"0.25.0"}
+{"time":"2026-03-06T07:39:29.254845747Z","level":"INFO","msg":"stream: created new stream","id":"dpxzw953"}
+{"time":"2026-03-06T07:39:29.255262411Z","level":"INFO","msg":"handler: started","stream_id":"dpxzw953"}
+{"time":"2026-03-06T07:39:29.255639332Z","level":"INFO","msg":"stream: started","id":"dpxzw953"}
+{"time":"2026-03-06T07:39:29.255751228Z","level":"INFO","msg":"writer: started","stream_id":"dpxzw953"}
+{"time":"2026-03-06T07:39:29.255761468Z","level":"INFO","msg":"sender: started","stream_id":"dpxzw953"}

data/wandb/run-20260306_073928-dpxzw953/logs/debug.log ADDED Viewed

	@@ -0,0 +1,22 @@

+2026-03-06 07:39:28,783 INFO    MainThread:3272902 [wandb_setup.py:_flush():81] Current SDK version is 0.25.0
+2026-03-06 07:39:28,783 INFO    MainThread:3272902 [wandb_setup.py:_flush():81] Configure stats pid to 3272902
+2026-03-06 07:39:28,784 INFO    MainThread:3272902 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-03-06 07:39:28,784 INFO    MainThread:3272902 [wandb_init.py:setup_run_log_directory():717] Logging user logs to /root/code/na/Idea-filtering-training/data/wandb/run-20260306_073928-dpxzw953/logs/debug.log
+2026-03-06 07:39:28,784 INFO    MainThread:3272902 [wandb_init.py:setup_run_log_directory():718] Logging internal logs to /root/code/na/Idea-filtering-training/data/wandb/run-20260306_073928-dpxzw953/logs/debug-internal.log
+2026-03-06 07:39:28,784 INFO    MainThread:3272902 [wandb_init.py:init():844] calling init triggers
+2026-03-06 07:39:28,784 INFO    MainThread:3272902 [wandb_init.py:init():849] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-03-06 07:39:28,785 INFO    MainThread:3272902 [wandb_init.py:init():892] starting backend
+2026-03-06 07:39:29,020 INFO    MainThread:3272902 [wandb_init.py:init():895] sending inform_init request
+2026-03-06 07:39:29,026 INFO    MainThread:3272902 [wandb_init.py:init():903] backend started and connected
+2026-03-06 07:39:29,030 INFO    MainThread:3272902 [wandb_init.py:init():973] updated telemetry
+2026-03-06 07:39:29,039 INFO    MainThread:3272902 [wandb_init.py:init():997] communicating run to backend with 90.0 second timeout
+2026-03-06 07:39:30,085 INFO    MainThread:3272902 [wandb_init.py:init():1042] starting run threads in backend
+2026-03-06 07:39:30,275 INFO    MainThread:3272902 [wandb_run.py:_console_start():2524] atexit reg
+2026-03-06 07:39:30,275 INFO    MainThread:3272902 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-03-06 07:39:30,275 INFO    MainThread:3272902 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-03-06 07:39:30,275 INFO    MainThread:3272902 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-03-06 07:39:30,280 INFO    MainThread:3272902 [wandb_init.py:init():1082] run started, returning control to user process
+2026-03-06 07:39:30,282 INFO    MainThread:3272902 [wandb_run.py:_config_callback():1403] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': '/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', 'revision': None, 'inference_mode': False, 'r': 32, 'target_modules': ['v_proj,o_proj', 'gate_proj', 'up_proj', 'q_proj', 'k_proj', 'down_proj'], 'exclude_modules': None, 'lora_alpha': 64, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': [], 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False, 'lora_dtype': None, 'lorap_lr_ratio': None, 'lorap_emb_lr': 1e-06}}, 'vocab_size': 151936, 'max_position_embeddings': 40960, 'hidden_size': 2048, 'intermediate_size': 6144, 'num_hidden_layers': 28, 'num_attention_heads': 16, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_bias': False, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'pad_token_id': 151643, 'bos_token_id': None, 'eos_token_id': 151645, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 1000000, 'rope_type': 'default'}, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': ['Qwen3ForCausalLM'], 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', 'transformers_version': '5.3.0', 'model_type': 'qwen3', 'output_attentions': False, 'output_dir': '/root/code/na/Idea-filtering-training/train/output/v1-20260306-073834', 'per_device_train_batch_size': 1, 'num_train_epochs': 3.0, 'max_steps': -1, 'learning_rate': 0.0002, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_steps': 0.05, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 16, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 5, 'logging_first_step': True, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': '/root/code/na/Idea-filtering-training/train/output/v1-20260306-073834', 'project': 'huggingface', 'trackio_space_id': 'trackio', 'eval_strategy': 'no', 'eval_steps': 500.0, 'eval_delay': 0, 'per_device_eval_batch_size': 1, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': False, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 1, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': 2, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_backend': None, 'ddp_timeout': 18000000, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'resume_from_checkpoint': None, 'warmup_ratio': 0.05, 'logging_dir': '/root/code/na/Idea-filtering-training/train/output/v1-20260306-073834/runs', 'local_rank': -1, 'sortish_sampler': False, 'predict_with_generate': False, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None, 'tuner_backend': 'peft', 'vit_gradient_checkpointing': True, 'router_aux_loss_coef': 0.0, 'enable_dft_loss': False, 'enable_channel_loss': False, 'check_model': True, 'acc_strategy': 'token', 'train_dataloader_shuffle': True, 'group_by_length': False, 'max_epochs': 3, 'aligner_lr': None, 'vit_lr': None, 'use_logits_to_keep': None, 'ds3_gather_for_generation': True, 'resume_only_model': False, 'optimizer': None, 'loss_type': None, 'eval_metric': None, 'callbacks': [], 'early_stop_interval': None, 'eval_use_evalscope': False, 'eval_dataset': [], 'eval_dataset_args': None, 'eval_limit': None, 'eval_generation_config': None, 'extra_eval_args': None, 'tuner_type': 'lora', 'use_galore': False, 'galore_target_modules': None, 'galore_rank': 128, 'galore_update_proj_gap': 50, 'galore_scale': 1.0, 'galore_proj_type': 'std', 'galore_optim_per_parameter': False, 'galore_with_embedding': False, 'galore_quantization': False, 'galore_proj_quant': False, 'galore_proj_bits': 4, 'galore_proj_group_size': 256, 'galore_cos_threshold': 0.4, 'galore_gamma_proj': 2, 'galore_queue_size': 5, 'lisa_activated_layers': 0, 'lisa_step_interval': 20, 'use_flash_ckpt': False}
+2026-03-06 07:39:30,290 INFO    MainThread:3272902 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2060182528 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7ffe8032fd10>>
+2026-03-06 07:39:30,290 INFO    MainThread:3272902 [wandb_run.py:_config_callback():1403] config_cb model/num_parameters 2060182528 None

data/wandb/run-20260306_073928-dpxzw953/run-dpxzw953.wandb ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2472aae39445ec308f7f20624eb857ffabd422e57c2005b739a860f3cf49d028
+size 327680

data/wandb/run-20260306_105746-8846dbl6/files/output.log ADDED Viewed

The diff for this file is too large to render. See raw diff

data/wandb/run-20260306_105746-8846dbl6/files/requirements.txt ADDED Viewed

	@@ -0,0 +1,243 @@

+psutil==7.2.2
+colorama==0.4.6
+trl==0.28.0
+pyarrow==23.0.1
+msgpack==1.1.2
+astor==0.8.1
+cffi==2.0.0
+qwen-vl-utils==0.0.14
+aiosignal==1.4.0
+sse-starlette==3.3.2
+setproctitle==1.3.7
+ms_swift==4.0.0
+mistral_common==1.9.1
+aliyun-python-sdk-kms==2.16.5
+nvidia-cublas-cu12==12.8.4.1
+markdown-it-py==4.0.0
+cachetools==7.0.3
+nltk==3.9.3
+cuda-pathfinder==1.4.0
+sentencepiece==0.2.1
+pycryptodome==3.23.0
+hf-xet==1.3.2
+multiprocess==0.70.16
+wandb==0.25.0
+fastar==0.8.0
+uv==0.10.8
+interegular==0.3.3
+rich==14.3.3
+modelscope==1.34.0
+websockets==15.0.1
+binpacking==2.0.1
+seaborn==0.13.2
+uvloop==0.22.1
+mpmath==1.3.0
+certifi==2026.2.25
+vllm==0.16.0
+supervisor==4.3.0
+flashinfer-python==0.6.3
+cbor2==5.8.0
+msgspec==0.20.0
+threadpoolctl==3.6.0
+watchfiles==1.1.1
+python-multipart==0.0.22
+peft==0.18.1
+httpx==0.28.1
+pillow==11.3.0
+wheel==0.46.3
+MarkupSafe==3.0.3
+ruff==0.15.4
+frozenlist==1.8.0
+xxhash==3.6.0
+psutil==7.2.2
+pytz==2026.1.post1
+platformdirs==4.9.2
+joblib==1.5.3
+transformers==5.3.0
+scikit-learn==1.8.0
+nvidia-cuda-nvrtc-cu12==12.8.93
+nvidia-cutlass-dsl-libs-base==4.4.1
+openai-harmony==0.0.8
+safehttpx==0.1.7
+gdown==5.2.1
+diskcache==5.6.3
+datasets==3.6.0
+tqdm==4.67.3
+openai==2.24.0
+nvidia-nccl-cu12==2.27.5
+sympy==1.14.0
+tabulate==0.10.0
+Werkzeug==3.1.6
+sentry-sdk==2.54.0
+numba==0.61.2
+attrdict==2.0.1
+referencing==0.37.0
+cuda-python==13.1.1
+jsonschema-specifications==2025.9.1
+nvidia-nvtx-cu12==12.8.90
+email-validator==2.3.0
+PyYAML==6.0.3
+requests==2.32.5
+cloudpickle==3.1.2
+xgrammar==0.1.29
+importlib_metadata==8.7.1
+prometheus_client==0.24.1
+h11==0.16.0
+json_repair==0.58.3
+typer-slim==0.24.0
+pandas==2.3.3
+absl-py==2.4.0
+tomlkit==0.13.3
+nvidia-cuda-cupti-cu12==12.8.90
+gitdb==4.0.12
+tiktoken==0.12.0
+soupsieve==2.8.3
+cpm-kernels==1.0.11
+tensorboard-data-server==0.7.2
+sniffio==1.3.1
+sortedcontainers==2.4.0
+pycountry==26.2.16
+triton==3.5.1
+nvidia-curand-cu12==10.3.9.90
+beautifulsoup4==4.14.3
+aiohttp==3.13.3
+nvidia-cutlass-dsl==4.4.1
+transformers-stream-generator==0.0.5
+gradio==5.50.0
+lark==1.2.2
+pycparser==3.0
+yarl==1.23.0
+outlines_core==0.2.11
+anthropic==0.84.0
+jsonschema==4.26.0
+Pygments==2.19.2
+nvidia-nvshmem-cu12==3.3.20
+ffmpy==1.0.0
+brotli==1.2.0
+idna==3.11
+Jinja2==3.1.6
+pip==26.0.1
+docstring_parser==0.17.0
+jieba==0.42.1
+typing_extensions==4.15.0
+torch==2.9.1
+attrs==25.4.0
+filelock==3.25.0
+fonttools==4.61.1
+accelerate==1.12.0
+httpcore==1.0.9
+ijson==3.5.0
+model-hosting-container-standards==0.1.13
+PyJWT==2.11.0
+charset-normalizer==3.4.4
+regex==2026.2.28
+simplejson==3.20.2
+tensorboard==2.20.0
+python-json-logger==4.0.0
+python-dateutil==2.9.0.post0
+nvidia-cudnn-frontend==1.18.0
+tzdata==2025.3
+typer==0.24.1
+pydantic==2.12.3
+jiter==0.13.0
+annotated-doc==0.0.4
+aliyun-python-sdk-core==2.16.0
+oss2==2.19.1
+fastapi==0.135.1
+shellingham==1.5.4
+addict==2.4.0
+omegaconf==2.3.0
+distro==1.9.0
+depyf==0.20.0
+numpy==2.2.6
+rignore==0.7.6
+torchaudio==2.9.1
+ray==2.54.0
+blake3==1.0.8
+fsspec==2025.3.0
+cycler==0.12.1
+rouge==1.0.1
+pydantic-settings==2.13.1
+grpcio==1.78.0
+kiwisolver==1.4.9
+partial-json-parser==0.2.1.1.post7
+Markdown==3.10.2
+httptools==0.7.1
+pydantic-extra-types==2.11.0
+rich-toolkit==0.19.7
+mcp==1.26.0
+pydub==0.25.1
+protobuf==6.33.5
+crcmod==1.7
+typing-inspection==0.4.2
+zstandard==0.25.0
+gradio_client==1.14.0
+tokenizers==0.22.2
+packaging==25.0
+zipp==3.23.0
+py-cpuinfo==9.0.0
+mdurl==0.1.2
+contourpy==1.3.3
+pyzmq==27.1.0
+aiohappyeyeballs==2.6.1
+ninja==1.13.0
+nvidia-cuda-runtime-cu12==12.8.90
+semantic-version==2.10.0
+dacite==1.9.2
+antlr4-python3-runtime==4.9.3
+python-dotenv==1.2.2
+compressed-tensors==0.13.0
+gguf==0.18.0
+anyio==4.12.1
+aiofiles==24.1.0
+nvidia-cusparse-cu12==12.5.8.93
+networkx==3.6.1
+cryptography==46.0.5
+uvicorn==0.41.0
+nvidia-cusolver-cu12==11.7.3.90
+fastapi-cloud-cli==0.14.0
+fastapi-cli==0.0.24
+pydantic_core==2.41.4
+llvmlite==0.44.0
+nvidia-cufile-cu12==1.13.1.3
+rpds-py==0.30.0
+pyparsing==3.3.2
+nvidia-cusparselt-cu12==0.7.1
+annotated-types==0.7.0
+pybase64==1.4.3
+propcache==0.4.1
+prometheus-fastapi-instrumentator==7.1.0
+click==8.3.1
+starlette==0.52.1
+PySocks==1.7.1
+orjson==3.11.7
+dill==0.3.8
+httpx-sse==0.4.3
+nvidia-ml-py==13.590.48
+loguru==0.7.3
+groovy==0.1.2
+cupy-cuda12x==14.0.1
+safetensors==0.7.0
+GitPython==3.1.46
+lm-format-enforcer==0.11.3
+grpcio-reflection==1.78.0
+smmap==5.0.2
+opencv-python-headless==4.13.0.92
+nvidia-nvjitlink-cu12==12.8.93
+einops==0.8.2
+nvidia-cufft-cu12==11.3.3.83
+multidict==6.7.1
+dnspython==2.8.0
+matplotlib==3.10.8
+six==1.17.0
+jmespath==0.10.0
+apache-tvm-ffi==0.1.9
+llguidance==1.3.0
+nvidia-cudnn-cu12==9.10.2.21
+urllib3==2.6.3
+setuptools==80.10.2
+cuda-bindings==13.1.1
+av==16.1.0
+scipy==1.17.1
+huggingface_hub==1.5.0
+torchvision==0.24.1

data/wandb/run-20260306_105746-8846dbl6/files/wandb-metadata.json ADDED Viewed

	@@ -0,0 +1,97 @@

+{
+  "os":  "Linux-6.8.0-87-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.12.12",
+  "startedAt":  "2026-03-06T10:57:46.231329Z",
+  "args":  [
+    "--model",
+    "Qwen/Qwen3-1.7B",
+    "--use_hf",
+    "true",
+    "--dataset",
+    "/root/code/na/Idea-filtering-training/data/thinking_dataset_v2_swift.jsonl",
+    "--train_type",
+    "lora",
+    "--lora_rank",
+    "32",
+    "--lora_alpha",
+    "64",
+    "--lora_dropout",
+    "0.05",
+    "--target_modules",
+    "q_proj",
+    "k_proj",
+    "v_proj,o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "--per_device_train_batch_size",
+    "1",
+    "--gradient_accumulation_steps",
+    "16",
+    "--max_length",
+    "2600",
+    "--learning_rate",
+    "2e-4",
+    "--warmup_ratio",
+    "0.05",
+    "--max_epochs",
+    "3",
+    "--attn_impl",
+    "eager",
+    "--output_dir",
+    "/root/code/na/Idea-filtering-training/train/output",
+    "--save_strategy",
+    "steps",
+    "--save_steps",
+    "1000",
+    "--eval_steps",
+    "500",
+    "--dataloader_num_workers",
+    "1",
+    "--dataset_num_proc",
+    "16",
+    "--load_from_cache_file",
+    "true",
+    "--model_author",
+    "swift",
+    "--model_name",
+    "swift-robot",
+    "--loss_scale",
+    "ignore_empty_think",
+    "--report_to",
+    "wandb"
+  ],
+  "program":  "/root/miniconda3/envs/RM/lib/python3.12/site-packages/swift/cli/sft.py",
+  "git":  {
+    "remote":  "https://tnnanh1010:@github.com/Drylab-AI/Idea-filtering-training.git",
+    "commit":  "0dbe0bbbe696b2e49ffefa83123579a73fab61c6"
+  },
+  "email":  "nhatanh10102005@gmail.com",
+  "root":  "/root/code/na/Idea-filtering-training/data",
+  "host":  "ubuntu",
+  "executable":  "/root/miniconda3/envs/RM/bin/python3",
+  "cpu_count":  49,
+  "cpu_count_logical":  49,
+  "gpu":  "NVIDIA GeForce RTX 3060",
+  "gpu_count":  1,
+  "disk":  {
+    "/":  {
+      "total":  "960312868864",
+      "used":  "892185260032"
+    }
+  },
+  "memory":  {
+    "total":  "628090474496"
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA GeForce RTX 3060",
+      "memoryTotal":  "12884901888",
+      "cudaCores":  3584,
+      "architecture":  "Ampere",
+      "uuid":  "GPU-f370a18a-d749-7bf1-c827-82726afbb6cf"
+    }
+  ],
+  "cudaVersion":  "13.0",
+  "writerId":  "pnelgqh2vvvgt4d15fvpxk9xawojic2y"
+}

data/wandb/run-20260306_105746-8846dbl6/logs/debug-core.log ADDED Viewed

	@@ -0,0 +1,8 @@

+{"time":"2026-03-06T10:57:46.314363437Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpg5b71rb2/port-1654770.txt","pid":1654770,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-03-06T10:57:46.316418659Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1654770}
+{"time":"2026-03-06T10:57:46.316317152Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1654770-1660166-284857756/socket","Net":"unix"}}
+{"time":"2026-03-06T10:57:46.467869627Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-03-06T10:57:46.485944099Z","level":"INFO","msg":"handleInformInit: received","streamId":"8846dbl6","id":"1(@)"}
+{"time":"2026-03-06T10:57:46.706399787Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8846dbl6","id":"1(@)"}
+{"time":"2026-03-06T10:57:52.301492638Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"sijs3l0vpag5"}
+{"time":"2026-03-07T02:55:05.849650733Z","level":"INFO","msg":"server: parent process exited, terminating service process"}

data/wandb/run-20260306_105746-8846dbl6/logs/debug-internal.log ADDED Viewed

	@@ -0,0 +1,12 @@

+{"time":"2026-03-06T10:57:46.486394548Z","level":"INFO","msg":"stream: starting","core version":"0.25.0"}
+{"time":"2026-03-06T10:57:46.705840771Z","level":"INFO","msg":"stream: created new stream","id":"8846dbl6"}
+{"time":"2026-03-06T10:57:46.706184448Z","level":"INFO","msg":"handler: started","stream_id":"8846dbl6"}
+{"time":"2026-03-06T10:57:46.706376796Z","level":"INFO","msg":"stream: started","id":"8846dbl6"}
+{"time":"2026-03-06T10:57:46.70647031Z","level":"INFO","msg":"writer: started","stream_id":"8846dbl6"}
+{"time":"2026-03-06T10:57:46.706495415Z","level":"INFO","msg":"sender: started","stream_id":"8846dbl6"}
+{"time":"2026-03-06T19:23:17.154701842Z","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/nhatanh10102005-vinuniversity/ms-swift/8846dbl6/file_stream","body":"\n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>502 Server Error</title>\n</head>\n<body text=#000000 bgcolor=#ffffff>\n<h1>Error: Server Error</h1>\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\n<h2></h2>\n</body></html>\n"}
+{"time":"2026-03-07T01:23:02.15976294Z","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/nhatanh10102005-vinuniversity/ms-swift/8846dbl6/file_stream","body":"\n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>502 Server Error</title>\n</head>\n<body text=#000000 bgcolor=#ffffff>\n<h1>Error: Server Error</h1>\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\n<h2></h2>\n</body></html>\n"}
+{"time":"2026-03-07T02:55:05.824285344Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":15580}
+{"time":"2026-03-07T02:55:05.824494952Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":1}
+{"time":"2026-03-07T02:55:05.825190016Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":15613}
+{"time":"2026-03-07T02:55:05.840550203Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":904}

data/wandb/run-20260306_105746-8846dbl6/logs/debug.log ADDED Viewed

	@@ -0,0 +1,22 @@

+2026-03-06 10:57:46,235 INFO    MainThread:1654770 [wandb_setup.py:_flush():81] Current SDK version is 0.25.0
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_setup.py:_flush():81] Configure stats pid to 1654770
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_init.py:setup_run_log_directory():717] Logging user logs to /root/code/na/Idea-filtering-training/data/wandb/run-20260306_105746-8846dbl6/logs/debug.log
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_init.py:setup_run_log_directory():718] Logging internal logs to /root/code/na/Idea-filtering-training/data/wandb/run-20260306_105746-8846dbl6/logs/debug-internal.log
+2026-03-06 10:57:46,236 INFO    MainThread:1654770 [wandb_init.py:init():844] calling init triggers
+2026-03-06 10:57:46,237 INFO    MainThread:1654770 [wandb_init.py:init():849] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-03-06 10:57:46,237 INFO    MainThread:1654770 [wandb_init.py:init():892] starting backend
+2026-03-06 10:57:46,468 INFO    MainThread:1654770 [wandb_init.py:init():895] sending inform_init request
+2026-03-06 10:57:46,475 INFO    MainThread:1654770 [wandb_init.py:init():903] backend started and connected
+2026-03-06 10:57:46,480 INFO    MainThread:1654770 [wandb_init.py:init():973] updated telemetry
+2026-03-06 10:57:46,491 INFO    MainThread:1654770 [wandb_init.py:init():997] communicating run to backend with 90.0 second timeout
+2026-03-06 10:57:47,094 INFO    MainThread:1654770 [wandb_init.py:init():1042] starting run threads in backend
+2026-03-06 10:57:47,290 INFO    MainThread:1654770 [wandb_run.py:_console_start():2524] atexit reg
+2026-03-06 10:57:47,290 INFO    MainThread:1654770 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-03-06 10:57:47,290 INFO    MainThread:1654770 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-03-06 10:57:47,290 INFO    MainThread:1654770 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-03-06 10:57:47,295 INFO    MainThread:1654770 [wandb_init.py:init():1082] run started, returning control to user process
+2026-03-06 10:57:47,296 INFO    MainThread:1654770 [wandb_run.py:_config_callback():1403] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': '/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', 'revision': None, 'inference_mode': False, 'r': 32, 'target_modules': ['gate_proj', 'up_proj', 'v_proj,o_proj', 'down_proj', 'k_proj', 'q_proj'], 'exclude_modules': None, 'lora_alpha': 64, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': [], 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False, 'lora_dtype': None, 'lorap_lr_ratio': None, 'lorap_emb_lr': 1e-06}}, 'vocab_size': 151936, 'max_position_embeddings': 40960, 'hidden_size': 2048, 'intermediate_size': 6144, 'num_hidden_layers': 28, 'num_attention_heads': 16, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_bias': False, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'pad_token_id': 151643, 'bos_token_id': None, 'eos_token_id': 151645, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 1000000, 'rope_type': 'default'}, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': ['Qwen3ForCausalLM'], 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', 'transformers_version': '5.3.0', 'model_type': 'qwen3', 'output_attentions': False, 'output_dir': '/root/code/na/Idea-filtering-training/train/output/v5-20260306-105729', 'per_device_train_batch_size': 1, 'num_train_epochs': 3.0, 'max_steps': -1, 'learning_rate': 0.0002, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_steps': 0.05, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 16, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 5, 'logging_first_step': True, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': '/root/code/na/Idea-filtering-training/train/output/v5-20260306-105729', 'project': 'huggingface', 'trackio_space_id': 'trackio', 'eval_strategy': 'no', 'eval_steps': 500.0, 'eval_delay': 0, 'per_device_eval_batch_size': 1, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': False, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 1, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': 2, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_backend': None, 'ddp_timeout': 18000000, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'resume_from_checkpoint': None, 'warmup_ratio': 0.05, 'logging_dir': '/root/code/na/Idea-filtering-training/train/output/v5-20260306-105729/runs', 'local_rank': -1, 'sortish_sampler': False, 'predict_with_generate': False, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None, 'tuner_backend': 'peft', 'vit_gradient_checkpointing': True, 'router_aux_loss_coef': 0.0, 'enable_dft_loss': False, 'enable_channel_loss': False, 'check_model': True, 'acc_strategy': 'token', 'train_dataloader_shuffle': True, 'group_by_length': False, 'max_epochs': 3, 'aligner_lr': None, 'vit_lr': None, 'use_logits_to_keep': None, 'ds3_gather_for_generation': True, 'resume_only_model': False, 'optimizer': None, 'loss_type': None, 'eval_metric': None, 'callbacks': [], 'early_stop_interval': None, 'eval_use_evalscope': False, 'eval_dataset': [], 'eval_dataset_args': None, 'eval_limit': None, 'eval_generation_config': None, 'extra_eval_args': None, 'tuner_type': 'lora', 'use_galore': False, 'galore_target_modules': None, 'galore_rank': 128, 'galore_update_proj_gap': 50, 'galore_scale': 1.0, 'galore_proj_type': 'std', 'galore_optim_per_parameter': False, 'galore_with_embedding': False, 'galore_quantization': False, 'galore_proj_quant': False, 'galore_proj_bits': 4, 'galore_proj_group_size': 256, 'galore_cos_threshold': 0.4, 'galore_gamma_proj': 2, 'galore_queue_size': 5, 'lisa_activated_layers': 0, 'lisa_step_interval': 20, 'use_flash_ckpt': False}
+2026-03-06 10:57:47,308 INFO    MainThread:1654770 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2060182528 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7ffc51dc5100>>
+2026-03-06 10:57:47,308 INFO    MainThread:1654770 [wandb_run.py:_config_callback():1403] config_cb model/num_parameters 2060182528 None

data/wandb/run-20260306_105746-8846dbl6/run-8846dbl6.wandb ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0d044c0d3dfab768ea82c3b508f38854050786dec53711998fe38a11b2fb26
+size 5136760

output/Qwen3-1.7B/v0-20260304-031440/args.json ADDED Viewed

	@@ -0,0 +1,346 @@

+{
+  "output_dir": "/root/code/na/Idea-filtering-training/output/Qwen3-1.7B/v0-20260304-031440",
+  "per_device_train_batch_size": 1,
+  "num_train_epochs": 3.0,
+  "max_steps": -1,
+  "learning_rate": 0.0001,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_steps": 0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "optim_target_modules": null,
+  "gradient_accumulation_steps": null,
+  "average_tokens_across_devices": true,
+  "max_grad_norm": 1.0,
+  "label_smoothing_factor": 0.0,
+  "bf16": true,
+  "fp16": false,
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "use_cache": false,
+  "neftune_noise_alpha": null,
+  "torch_empty_cache_steps": null,
+  "auto_find_batch_size": false,
+  "logging_strategy": "steps",
+  "logging_steps": 5,
+  "logging_first_step": true,
+  "log_on_each_node": true,
+  "logging_nan_inf_filter": true,
+  "include_num_input_tokens_seen": false,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "disable_tqdm": null,
+  "report_to": [
+    "tensorboard"
+  ],
+  "run_name": "/root/code/na/Idea-filtering-training/output/Qwen3-1.7B/v0-20260304-031440",
+  "project": "huggingface",
+  "trackio_space_id": "trackio",
+  "eval_strategy": "no",
+  "eval_steps": 500,
+  "eval_delay": 0,
+  "per_device_eval_batch_size": 1,
+  "prediction_loss_only": false,
+  "eval_on_start": false,
+  "eval_do_concat_batches": true,
+  "eval_use_gather_object": false,
+  "eval_accumulation_steps": null,
+  "include_for_metrics": [],
+  "batch_eval_metrics": false,
+  "save_only_model": false,
+  "save_strategy": "steps",
+  "save_steps": 500,
+  "save_on_each_node": false,
+  "save_total_limit": null,
+  "enable_jit_checkpoint": false,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_always_push": false,
+  "hub_revision": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "restore_callback_states_from_checkpoint": false,
+  "full_determinism": false,
+  "seed": 42,
+  "data_seed": 42,
+  "use_cpu": false,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "dataloader_drop_last": false,
+  "dataloader_num_workers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "dataloader_prefetch_factor": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "train_sampling_strategy": "random",
+  "length_column_name": "length",
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_backend": null,
+  "ddp_timeout": 18000000,
+  "fsdp": [],
+  "fsdp_config": null,
+  "deepspeed": null,
+  "debug": null,
+  "skip_memory_metrics": true,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "resume_from_checkpoint": null,
+  "warmup_ratio": null,
+  "logging_dir": "/root/code/na/Idea-filtering-training/output/Qwen3-1.7B/v0-20260304-031440/runs",
+  "local_rank": -1,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "tuner_backend": "peft",
+  "vit_gradient_checkpointing": null,
+  "router_aux_loss_coef": 0.0,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "group_by_length": false,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "eval_metric": null,
+  "callbacks": [],
+  "early_stop_interval": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "tuner_type": "lora",
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "use_flash_ckpt": false,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "Qwen/Qwen3-1.7B",
+  "model_type": "qwen3",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "experts_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen3",
+  "system": null,
+  "max_length": 40960,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": false,
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "/root/code/na/Idea-filtering-training/data/thinking_dataset_merged.jsonl"
+  ],
+  "val_dataset": [],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 1,
+  "load_from_cache_file": false,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "structured_outputs_regex": null,
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "custom_register_path": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": false,
+  "use_hf": true,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_regex": null,
+  "target_parameters": null,
+  "modules_to_save": [],
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": "ms-swift",
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_notification_method": null,
+  "swanlab_webhook_url": null,
+  "swanlab_secret": null,
+  "swanlab_sender_email": null,
+  "swanlab_receiver_email": null,
+  "swanlab_smtp_server": null,
+  "swanlab_smtp_port": null,
+  "swanlab_email_language": "zh",
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "swift_version": "4.0.0",
+  "ckpt_dir": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "Qwen3-1.7B",
+  "model_info": "ModelInfo(model_type='qwen3', model_dir='/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e', torch_dtype=torch.bfloat16, max_model_len=40960, quant_method=None, quant_bits=None, rope_scaling={'rope_theta': 1000000, 'rope_type': 'default'}, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], template='qwen3', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', hf_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek_r1', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3Guard-Gen-0.6B', hf_model_id='Qwen/Qwen3Guard-Gen-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-4B', hf_model_id='Qwen/Qwen3Guard-Gen-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-8B', hf_model_id='Qwen/Qwen3Guard-Gen-8B', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_guard', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507', hf_model_id='Qwen/Qwen3-4B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_thinking', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_nothinking', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.register.ModelLoader'>, template='qwen3', model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
+  "model_dir": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e",
+  "template_meta": "Qwen3MixedTemplateMeta(template_type='qwen3', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.base.Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=True, thinking_prefix='', non_thinking_prefix='<think>\\n\\n</think>\\n\\n', history_thinking_prefix='')",
+  "_val_dataset_exists": false,
+  "hub": "<class 'swift.hub.hub.HFHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/code/na/Idea-filtering-training/output/Qwen3-1.7B/v0-20260304-031440', per_device_train_batch_size=1, num_train_epochs=3.0, max_steps=-1, learning_rate=0.0001, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=16, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=5, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['tensorboard'], run_name='/root/code/na/Idea-filtering-training/output/Qwen3-1.7B/v0-20260304-031440', project='huggingface', trackio_space_id='trackio', eval_strategy=<IntervalStrategy.NO: 'no'>, eval_steps=500, eval_delay=0, per_device_eval_batch_size=1, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_on_each_node=False, save_total_limit=None, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, 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), parallelism_config=None, dataloader_drop_last=False, dataloader_num_workers=1, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, deepspeed=None, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, warmup_ratio=None, logging_dir='/root/code/na/Idea-filtering-training/output/Qwen3-1.7B/v0-20260304-031440/runs', local_rank=-1, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='lora', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
+}

output/Qwen3-1.7B/v0-20260304-031440/images/train_epoch.png ADDED Viewed

output/Qwen3-1.7B/v0-20260304-031440/images/train_grad_norm.png ADDED Viewed

output/Qwen3-1.7B/v0-20260304-031440/images/train_learning_rate.png ADDED Viewed

output/Qwen3-1.7B/v0-20260304-031440/images/train_loss.png ADDED Viewed

output/Qwen3-1.7B/v0-20260304-031440/images/train_token_acc.png ADDED Viewed

output/Qwen3-1.7B/v0-20260304-031440/logging.jsonl ADDED Viewed

	@@ -0,0 +1,17 @@

+{"loss": 2.80828404, "grad_norm": 0.70461369, "learning_rate": 0.0001, "token_acc": 0.54860752, "epoch": 0.00039497, "global_step/max_steps": "1/7596", "elapsed_time": "22s", "remaining_time": "1d 22h 44m 52s", "memory(GiB)": 9.3, "train_speed(s/it)": 22.158197}
+{"loss": 2.10956383, "grad_norm": 0.06330702, "learning_rate": 0.0001, "token_acc": 0.54739539, "epoch": 0.00197487, "global_step/max_steps": "5/7596", "elapsed_time": "1m 45s", "remaining_time": "1d 20h 26m 11s", "memory(GiB)": 11.09, "train_speed(s/it)": 21.073719}
+{"loss": 1.88895645, "grad_norm": 0.06611262, "learning_rate": 0.0001, "token_acc": 0.54985593, "epoch": 0.00394974, "global_step/max_steps": "10/7596", "elapsed_time": "3m 30s", "remaining_time": "1d 20h 20m 37s", "memory(GiB)": 11.09, "train_speed(s/it)": 21.043592}
+{"loss": 1.81560631, "grad_norm": 0.03588019, "learning_rate": 0.0001, "token_acc": 0.55962598, "epoch": 0.00592461, "global_step/max_steps": "15/7596", "elapsed_time": "5m 17s", "remaining_time": "1d 20h 30m 47s", "memory(GiB)": 11.09, "train_speed(s/it)": 21.137915}
+{"loss": 1.68152924, "grad_norm": 0.03120046, "learning_rate": 0.0001, "token_acc": 0.58999685, "epoch": 0.00789948, "global_step/max_steps": "20/7596", "elapsed_time": "7m 5s", "remaining_time": "1d 20h 43m 44s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.254456}
+{"loss": 1.73896103, "grad_norm": 0.02689376, "learning_rate": 0.0001, "token_acc": 0.58061652, "epoch": 0.00987435, "global_step/max_steps": "25/7596", "elapsed_time": "8m 48s", "remaining_time": "1d 20h 26m 37s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.132875}
+{"loss": 1.63750725, "grad_norm": 0.02659717, "learning_rate": 0.0001, "token_acc": 0.59855935, "epoch": 0.01184922, "global_step/max_steps": "30/7596", "elapsed_time": "10m 35s", "remaining_time": "1d 20h 27m 52s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.156749}
+{"loss": 1.62336521, "grad_norm": 0.02456974, "learning_rate": 9.999e-05, "token_acc": 0.59320185, "epoch": 0.01382409, "global_step/max_steps": "35/7596", "elapsed_time": "12m 21s", "remaining_time": "1d 20h 27m 45s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.169781}
+{"loss": 1.56308775, "grad_norm": 0.02603255, "learning_rate": 9.999e-05, "token_acc": 0.60313748, "epoch": 0.01579896, "global_step/max_steps": "40/7596", "elapsed_time": "14m 8s", "remaining_time": "1d 20h 29m 47s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.200038}
+{"loss": 1.60969524, "grad_norm": 0.02644657, "learning_rate": 9.999e-05, "token_acc": 0.59429054, "epoch": 0.01777383, "global_step/max_steps": "45/7596", "elapsed_time": "15m 50s", "remaining_time": "1d 20h 16m 44s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.110333}
+{"loss": 1.54298725, "grad_norm": 0.02468126, "learning_rate": 9.999e-05, "token_acc": 0.61193504, "epoch": 0.0197487, "global_step/max_steps": "50/7596", "elapsed_time": "17m 37s", "remaining_time": "1d 20h 18m 46s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.140509}
+{"loss": 1.50155048, "grad_norm": 0.02367931, "learning_rate": 9.999e-05, "token_acc": 0.61832011, "epoch": 0.02172357, "global_step/max_steps": "55/7596", "elapsed_time": "19m 22s", "remaining_time": "1d 20h 15m 47s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.130747}
+{"loss": 1.52671709, "grad_norm": 0.02718145, "learning_rate": 9.998e-05, "token_acc": 0.60960499, "epoch": 0.02369844, "global_step/max_steps": "60/7596", "elapsed_time": "21m 8s", "remaining_time": "1d 20h 13m 59s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.130449}
+{"loss": 1.54125071, "grad_norm": 0.02729321, "learning_rate": 9.998e-05, "token_acc": 0.61034281, "epoch": 0.02567331, "global_step/max_steps": "65/7596", "elapsed_time": "22m 51s", "remaining_time": "1d 20h 7m 16s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.090954}
+{"loss": 1.500739, "grad_norm": 0.02714855, "learning_rate": 9.998e-05, "token_acc": 0.61303845, "epoch": 0.02764818, "global_step/max_steps": "70/7596", "elapsed_time": "24m 34s", "remaining_time": "1d 20h 2m 6s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.063844}
+{"loss": 1.51486931, "grad_norm": 0.02550467, "learning_rate": 9.998e-05, "token_acc": 0.61092864, "epoch": 0.02962305, "global_step/max_steps": "75/7596", "elapsed_time": "26m 19s", "remaining_time": "1d 19h 59m 50s", "memory(GiB)": 11.15, "train_speed(s/it)": 21.059681}
+{"train_dataset": "1665.517589±354.737407, min=757.000000, max=38083.000000, size=40509", "model_parameter_info": "PeftModelForCausalLM: 2066.6051M Params (34.8652M Trainable [1.6871%]), 0.0001M Buffers.", "last_model_checkpoint": null, "best_model_checkpoint": null, "best_metric": null, "global_step": 78, "log_history": [{"loss": 2.808284044265747, "grad_norm": 0.7046136856079102, "learning_rate": 9.999999572368355e-05, "token_acc": 0.5486075163060358, "epoch": 0.0003949739564047496, "step": 1}, {"loss": 2.1095638275146484, "grad_norm": 0.063307024538517, "learning_rate": 9.999989309212533e-05, "token_acc": 0.547395388556789, "epoch": 0.0019748697820237476, "step": 5}, {"loss": 1.8889564514160155, "grad_norm": 0.06611262261867523, "learning_rate": 9.999957236895852e-05, "token_acc": 0.5498559329433336, "epoch": 0.003949739564047495, "step": 10}, {"loss": 1.8156063079833984, "grad_norm": 0.0358801893889904, "learning_rate": 9.999903783187103e-05, "token_acc": 0.5596259794991111, "epoch": 0.005924609346071244, "step": 15}, {"loss": 1.6815292358398437, "grad_norm": 0.031200457364320755, "learning_rate": 9.999828948314876e-05, "token_acc": 0.5899968477461385, "epoch": 0.00789947912809499, "step": 20}, {"loss": 1.7389610290527344, "grad_norm": 0.02689375728368759, "learning_rate": 9.999732732599186e-05, "token_acc": 0.5806165194426737, "epoch": 0.009874348910118739, "step": 25}, {"loss": 1.6375072479248047, "grad_norm": 0.026597166433930397, "learning_rate": 9.999615136451483e-05, "token_acc": 0.5985593512767425, "epoch": 0.011849218692142487, "step": 30}, {"loss": 1.6233652114868165, "grad_norm": 0.024569744244217873, "learning_rate": 9.999476160374644e-05, "token_acc": 0.5932018540398073, "epoch": 0.013824088474166234, "step": 35}, {"loss": 1.5630877494812012, "grad_norm": 0.026032552123069763, "learning_rate": 9.999315804962974e-05, "token_acc": 0.603137482149879, "epoch": 0.01579895825618998, "step": 40}, {"loss": 1.6096952438354493, "grad_norm": 0.026446569710969925, "learning_rate": 9.999134070902207e-05, "token_acc": 0.5942905357896218, "epoch": 0.01777382803821373, "step": 45}, {"loss": 1.5429872512817382, "grad_norm": 0.02468126453459263, "learning_rate": 9.99893095896949e-05, "token_acc": 0.6119350428766726, "epoch": 0.019748697820237478, "step": 50}, {"loss": 1.5015504837036133, "grad_norm": 0.023679306730628014, "learning_rate": 9.998706470033396e-05, "token_acc": 0.6183201072739662, "epoch": 0.021723567602261226, "step": 55}, {"loss": 1.5267170906066894, "grad_norm": 0.02718144841492176, "learning_rate": 9.998460605053911e-05, "token_acc": 0.6096049924254415, "epoch": 0.023698437384284975, "step": 60}, {"loss": 1.5412507057189941, "grad_norm": 0.027293212711811066, "learning_rate": 9.99819336508243e-05, "token_acc": 0.6103428082346052, "epoch": 0.025673307166308723, "step": 65}, {"loss": 1.5007390022277831, "grad_norm": 0.027148548513650894, "learning_rate": 9.997904751261756e-05, "token_acc": 0.6130384536946818, "epoch": 0.027648176948332468, "step": 70}, {"loss": 1.5148693084716798, "grad_norm": 0.025504665449261665, "learning_rate": 9.997594764826092e-05, "token_acc": 0.6109286421308378, "epoch": 0.029623046730356217, "step": 75}], "memory": 11.15234375}

output/Qwen3-1.7B/v0-20260304-031440/runs/Mar04_03-19-12_ubuntu/events.out.tfevents.1772594352.ubuntu.2490446.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:04588eed7d3811342a53b44cd39e2a3c6c1789117591fe16de77bed141c4d4b0
+size 10843

output/proposals_RM_gpt_oss_120b_ensemble/polaris/polaris-adme-fang-hclint-1_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_120b_ensemble/polaris/polaris-adme-fang-hppb-1_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_120b_ensemble/polaris/polaris-adme-fang-solu-1_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_120b_ensemble/polaris/tdcommons-bbb-martins_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_120b_ensemble/polaris/tdcommons-cyp2d6-substrate-carbonmangels_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_120b_ensemble/polaris/tdcommons-herg_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_120b_ensemble/polaris/tdcommons-lipophilicity-astrazeneca_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_20b_ensemble/polaris/polaris-adme-fang-hclint-1_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_20b_ensemble/polaris/polaris-adme-fang-hppb-1_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_20b_ensemble/polaris/polaris-adme-fang-solu-1_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_20b_ensemble/polaris/tdcommons-bbb-martins_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_20b_ensemble/polaris/tdcommons-cyp2d6-substrate-carbonmangels_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_20b_ensemble/polaris/tdcommons-herg_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff

output/proposals_RM_gpt_oss_20b_ensemble/polaris/tdcommons-lipophilicity-astrazeneca_scored_16.json ADDED Viewed

The diff for this file is too large to render. See raw diff