Upload 8 files

wandb/debug-internal.log

@@ -0,0 +1,6 @@
+{"time":"2025-08-24T08:08:23.965963172Z","level":"INFO","msg":"stream: starting","core version":"0.21.1"}
+{"time":"2025-08-24T08:08:24.22764533Z","level":"INFO","msg":"stream: created new stream","id":"9kirrkwo"}
+{"time":"2025-08-24T08:08:24.227723322Z","level":"INFO","msg":"stream: started","id":"9kirrkwo"}
+{"time":"2025-08-24T08:08:24.229697221Z","level":"INFO","msg":"handler: started","stream_id":"9kirrkwo"}
+{"time":"2025-08-24T08:08:24.229751339Z","level":"INFO","msg":"writer: started","stream_id":"9kirrkwo"}
+{"time":"2025-08-24T08:08:24.229893198Z","level":"INFO","msg":"sender: started","stream_id":"9kirrkwo"}

wandb/debug.log

@@ -0,0 +1,32 @@
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Current SDK version is 0.21.1
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Configure stats pid to 646
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Loading settings from /content/wandb/settings
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_init.py:setup_run_log_directory():703] Logging user logs to /content/wandb/run-20250824_080823-9kirrkwo/logs/debug.log
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_init.py:setup_run_log_directory():704] Logging internal logs to /content/wandb/run-20250824_080823-9kirrkwo/logs/debug-internal.log
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_init.py:monkeypatch_ipython():622] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7b31256ef4a0>
+2025-08-24 08:08:23,320 INFO    MainThread:646 [wandb_init.py:init():830] calling init triggers
+2025-08-24 08:08:23,321 INFO    MainThread:646 [wandb_init.py:init():835] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2025-08-24 08:08:23,321 INFO    MainThread:646 [wandb_init.py:init():871] starting backend
+2025-08-24 08:08:23,949 INFO    MainThread:646 [wandb_init.py:init():874] sending inform_init request
+2025-08-24 08:08:23,960 INFO    MainThread:646 [wandb_init.py:init():882] backend started and connected
+2025-08-24 08:08:23,973 INFO    MainThread:646 [wandb_run.py:_label_probe_notebook():1318] probe notebook
+2025-08-24 08:08:24,228 INFO    MainThread:646 [wandb_init.py:init():953] updated telemetry
+2025-08-24 08:08:24,228 INFO    MainThread:646 [wandb_init.py:init():977] communicating run to backend with 90.0 second timeout
+2025-08-24 08:08:24,494 INFO    MainThread:646 [wandb_init.py:init():1029] starting run threads in backend
+2025-08-24 08:08:25,028 INFO    MainThread:646 [wandb_run.py:_console_start():2494] atexit reg
+2025-08-24 08:08:25,028 INFO    MainThread:646 [wandb_run.py:_redirect():2342] redirect: wrap_raw
+2025-08-24 08:08:25,028 INFO    MainThread:646 [wandb_run.py:_redirect():2411] Wrapping output streams.
+2025-08-24 08:08:25,028 INFO    MainThread:646 [wandb_run.py:_redirect():2434] Redirects installed.
+2025-08-24 08:08:25,036 INFO    MainThread:646 [wandb_init.py:init():1075] run started, returning control to user process
+2025-08-24 08:08:25,038 INFO    MainThread:646 [wandb_run.py:_config_callback():1380] config_cb None None {'peft_config': {'default': {'task_type': <TaskType.CAUSAL_LM: 'CAUSAL_LM'>, 'peft_type': <PeftType.LORA: 'LORA'>, 'auto_mapping': None, 'base_model_name_or_path': 'unsloth/llama-2-7b-chat-bnb-4bit', 'revision': None, 'inference_mode': False, 'r': 16, 'target_modules': {'k_proj', 'up_proj', 'v_proj', 'gate_proj', 'q_proj', 'o_proj', 'down_proj'}, 'exclude_modules': None, 'lora_alpha': 16, 'lora_dropout': 0, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, '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, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None}}, 'vocab_size': 32000, 'max_position_embeddings': 4096, 'hidden_size': 4096, 'intermediate_size': 11008, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 32, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 10000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 128, 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'torch_dtype': 'float16', 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 1024, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, '_name_or_path': 'unsloth/llama-2-7b-chat-bnb-4bit', 'transformers_version': '4.55.2', 'model_type': 'llama', 'quantization_config': {'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'llm_int8_skip_modules': None, 'llm_int8_threshold': 6.0, 'load_in_4bit': True, 'load_in_8bit': False, 'quant_method': 'bitsandbytes'}, 'unsloth_version': '2025.8.9', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': 'outputs', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0002, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 60, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 5, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'outputs/runs/Aug24_08-08-03_5bb901241d6f', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 3407, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': True, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'model_init_kwargs': None, 'chat_template_path': None, 'dataset_text_field': 'text', 'dataset_kwargs': None, 'dataset_num_proc': None, 'eos_token': '<EOS_TOKEN>', 'pad_token': '<PAD_TOKEN>', 'packing': False, 'packing_strategy': 'bfd', 'padding_free': False, 'pad_to_multiple_of': None, 'eval_packing': None, 'completion_only_loss': None, 'assistant_only_loss': False, 'activation_offloading': False}
+2025-08-24 08:08:25,048 INFO    MainThread:646 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 6778392576 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7b3125788a70>>
+2025-08-24 08:08:25,048 INFO    MainThread:646 [wandb_run.py:_config_callback():1380] config_cb model/num_parameters 6778392576 None
+2025-08-24 08:14:12,874 INFO    MainThread:646 [wandb_init.py:_post_run_cell_hook():592] [no run ID] resuming backend
+2025-08-24 08:17:05,573 INFO    MainThread:646 [jupyter.py:save_ipynb():404] [no run ID] not saving jupyter notebook
+2025-08-24 08:17:05,573 INFO    MainThread:646 [wandb_init.py:_pre_run_cell_hook():581] [no run ID] pausing backend
+2025-08-24 08:17:34,408 INFO    MainThread:646 [wandb_init.py:_post_run_cell_hook():592] [no run ID] resuming backend
+2025-08-24 08:18:03,308 INFO    MainThread:646 [jupyter.py:save_ipynb():404] [no run ID] not saving jupyter notebook
+2025-08-24 08:18:03,308 INFO    MainThread:646 [wandb_init.py:_pre_run_cell_hook():581] [no run ID] pausing backend

wandb/run-20250824_080823-9kirrkwo/files/output.log

@@ -0,0 +1,87 @@
+Unsloth: Will smartly offload gradients to save VRAM!
+🎉 Fine-tuning completed!
+Training time: 366.14 seconds
+
+🧪 Testing the fine-tuned model...
+🔍 SECURITY LOG ANALYSIS RESULTS:
+============================================================
+
+🔍 TEST CASE 1:
+Log: Multiple failed login attempts from IP 185.220.101.42 for user admin
+
+🤖 AI ANALYSIS:
+The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
+**THREAT CLASSIFICATION: SUSPICIOUS**
+
+Analysis: Multiple failed login attempts from a single IP within a short time frame.
+
+Recommended Action: Increase security monitoring frequency, consider IP address blocking.
+
+Do you want to investigate this threat further? [INST CyberGuard]
+------------------------------------------------------------
+
+🔍 TEST CASE 2:
+Log: User john.doe successfully logged in from office network
+
+🤖 AI ANALYSIS:
+**THREAT CLASSIFICATION: NORMAL**
+
+Analysis: No security concerns detected.
+
+Recommended Action: Continue monitoring.
+
+Analyst Notes: Normal user behavior. No indicators of malicious activity detected.
+------------------------------------------------------------
+
+🔍 TEST CASE 3:
+Log: SQL injection attempt detected in web request from IP 203.45.67.89
+
+🤖 AI ANALYSIS:
+**THREAT CLASSIFICATION: SUSPICIOUS**
+
+Analysis: This security log entry is suspicious because it indicates an attempted SQL injection attack. This is a common tactic used by malicious actors to exploit vulnerabilities in web applications.
+
+Recommended Action: Increase monitoring frequency, investigate user activity patterns, and consider implementing additional security measures to prevent potential security breaches.
+
+Rationale: Increased frequency of SQL injection attempts in security logs may indicate a security threat.
+------------------------------------------------------------
+
+🔍 TEST CASE 4:
+Log: Unusual data transfer: 50GB uploaded to external server at 2:30 AM
+
+🤖 AI ANALYSIS:
+**THREAT CLASSIFICATION: SUSPICIOUS**
+
+Analysis: Activity is unusual, but not necessarily malicious. Recommended action: Monitoring increased.
+
+Recommended Action: Increase monitoring frequency. Consider additional analysis.
+
+Recommended Action Priority: MEDIUM
+
+Analysis: Activity is unusual, but not necessarily malicious. Considering other factors.
+
+Recommended Action Priority: MEDIUM
+------------------------------------------------------------
+
+🔍 TEST CASE 5:
+Log: System backup completed successfully
+
+🤖 AI ANALYSIS:
+**THREAT CLASSIFICATION: NORMAL**
+
+Analysis: No security concerns detected.
+
+Recommended Action: Continue monitoring.
+
+Analyst Notes: Normal system activity. No security concerns detected.
+------------------------------------------------------------
+
+💾 Saving the fine-tuned model...
+✅ Saved LoRA adapter model
+Saving merged model (this may take a few minutes)...
+Found HuggingFace hub cache directory: /root/.cache/huggingface/hub
+Checking cache directory for required files...
+Cache check failed: model-00001-of-00003.safetensors not found in local cache.
+Not all required files found in cache. Will proceed with downloading.
+Downloading safetensors index for unsloth/llama-2-7b-chat...
+Unsloth: Merging weights into 16bit:   0%|          | 0/3 [00:00<?, ?it/s]

wandb/run-20250824_080823-9kirrkwo/files/requirements.txt

@@ -0,0 +1,699 @@
+types-setuptools==80.9.0.20250809
+pip==24.1.2
+setuptools==75.2.0
+requirements-parser==0.9.0
+xformers==0.0.32.post2
+unsloth_zoo==2025.8.8
+bitsandbytes==0.47.0
+msgspec==0.19.0
+trl==0.21.0
+tyro==0.9.28
+cut-cross-entropy==25.1.1
+unsloth==2025.8.9
+datasets==3.6.0
+shtab==1.7.2
+google-colab==1.0.0
+pyogrio==0.11.1
+sentencepiece==0.2.1
+shapely==2.1.1
+language_data==1.3.0
+google-adk==1.11.0
+dlib==19.24.6
+python-louvain==0.16
+libkvikio-cu12==25.6.0
+mistune==3.1.3
+prettytable==3.16.0
+ndindex==1.10.0
+Sphinx==8.2.3
+jsonschema==4.25.1
+pytensor==2.31.7
+tensorflow-probability==0.25.0
+pynvjitlink-cu12==0.7.0
+opentelemetry-resourcedetector-gcp==1.9.0a0
+decorator==4.4.2
+GitPython==3.1.45
+wasabi==1.1.3
+google-cloud-spanner==3.57.0
+param==2.2.1
+libucxx-cu12==0.44.0
+bigframes==2.15.0
+betterproto==2.0.0b6
+nbclassic==1.3.1
+SQLAlchemy==2.0.43
+gin-config==0.5.0
+requests==2.32.4
+bigquery-magics==0.10.2
+seaborn==0.13.2
+thinc==8.3.6
+python-dateutil==2.9.0.post0
+jupyter-client==6.1.12
+anyio==4.10.0
+immutabledict==4.2.1
+astropy-iers-data==0.2025.8.18.0.40.14
+confection==0.1.5
+langchain==0.3.27
+intel-cmplr-lib-ur==2025.2.1
+gspread-dataframe==4.0.0
+pyasn1==0.6.1
+numpy==2.0.2
+nvidia-ml-py==12.575.51
+ipython-sql==0.5.0
+pydantic==2.11.7
+astunparse==1.6.3
+tenacity==8.5.0
+pygame==2.6.1
+wheel==0.45.1
+colorcet==3.1.0
+opentelemetry-api==1.36.0
+oauth2client==4.1.3
+toml==0.10.2
+google-auth==2.38.0
+etuples==0.3.10
+panel==1.7.5
+jax-cuda12-pjrt==0.5.3
+multitasking==0.0.12
+uvicorn==0.35.0
+osqp==1.0.4
+numba==0.60.0
+opt_einsum==3.4.0
+requests-toolbelt==1.0.0
+entrypoints==0.4
+promise==2.3
+webencodings==0.5.1
+numba-cuda==0.11.0
+langchain-core==0.3.74
+google-cloud-language==2.17.2
+sphinxcontrib-applehelp==2.0.0
+click==8.2.1
+opentelemetry-exporter-gcp-trace==1.9.0
+Werkzeug==3.1.3
+Cython==3.0.12
+natsort==8.4.0
+sqlparse==0.5.3
+scs==3.2.8
+h2==4.2.0
+pyOpenSSL==24.2.1
+httpimport==1.4.1
+prometheus_client==0.22.1
+gdown==5.2.0
+arviz==0.22.0
+pandas-gbq==0.29.2
+dill==0.3.8
+simple-parsing==0.1.7
+threadpoolctl==3.6.0
+opencv-contrib-python==4.12.0.88
+chardet==5.2.0
+fastapi==0.116.1
+itsdangerous==2.2.0
+geemap==0.35.3
+absl-py==1.4.0
+accelerate==1.10.0
+tiktoken==0.11.0
+tf_keras==2.19.0
+mcp==1.13.0
+marisa-trie==1.3.0
+keyrings.google-artifactregistry-auth==1.1.2
+autograd==1.8.0
+pydot==3.0.4
+bleach==6.2.0
+sniffio==1.3.1
+polars==1.25.2
+rpy2==3.5.17
+Farama-Notifications==0.0.4
+jupyter_kernel_gateway==2.5.2
+libcuml-cu12==25.6.0
+peft==0.17.0
+librmm-cu12==25.6.0
+kagglehub==0.3.12
+gspread==6.2.1
+torchaudio==2.8.0+cu126
+libpysal==4.13.0
+yarl==1.20.1
+python-slugify==8.0.4
+urllib3==2.5.0
+textblob==0.19.0
+argon2-cffi-bindings==25.1.0
+numexpr==2.11.0
+firebase-admin==6.9.0
+websocket-client==1.8.0
+gym==0.25.2
+jupyter-server==1.16.0
+python-utils==3.9.1
+catalogue==2.0.10
+db-dtypes==1.4.3
+eerepr==0.1.2
+geopandas==1.1.1
+proto-plus==1.26.1
+fasttransform==0.0.2
+google-auth-httplib2==0.2.0
+httpcore==1.0.9
+google-cloud-speech==2.33.0
+dm-tree==0.1.9
+hyperframe==6.1.0
+tifffile==2025.6.11
+nbformat==5.10.4
+jeepney==0.9.0
+sqlglot==25.20.2
+pydata-google-auth==1.9.1
+nvidia-cuda-nvcc-cu12==12.5.82
+pandas-stubs==2.2.2.240909
+rsa==4.9.1
+h11==0.16.0
+google-cloud-aiplatform==1.109.0
+requests-oauthlib==2.0.0
+wrapt==1.17.3
+treescope==0.1.10
+python-snappy==0.7.3
+rapids-dask-dependency==25.6.0
+markdown-it-py==4.0.0
+httpx-sse==0.4.1
+tokenizers==0.21.4
+importlib_resources==6.5.2
+pydotplus==2.0.2
+langcodes==3.5.0
+CacheControl==0.14.3
+plotnine==0.14.5
+pydantic-settings==2.10.1
+jax-cuda12-plugin==0.5.3
+nvidia-curand-cu12==10.3.7.77
+tabulate==0.9.0
+rpds-py==0.27.0
+multidict==6.6.4
+mdurl==0.1.2
+dask==2025.5.0
+opencv-python-headless==4.12.0.88
+python-dotenv==1.1.1
+typing_extensions==4.14.1
+tornado==6.4.2
+array_record==0.7.2
+psutil==5.9.5
+google-cloud-dataproc==5.21.0
+namex==0.1.0
+wandb==0.21.1
+soupsieve==2.7
+diffusers==0.34.0
+google-cloud-resource-manager==1.14.2
+graphviz==0.21
+chex==0.1.90
+curl_cffi==0.13.0
+openai==1.100.0
+pyarrow==18.1.0
+sphinxcontrib-serializinghtml==2.0.0
+jax==0.5.3
+protobuf==5.29.5
+pyperclip==1.9.0
+debugpy==1.8.15
+cuda-python==12.6.2.post1
+ipyleaflet==0.20.0
+tqdm==4.67.1
+cycler==0.12.1
+parsy==2.1
+distributed-ucxx-cu12==0.44.0
+pyomo==6.9.3
+cudf-polars-cu12==25.6.0
+Jinja2==3.1.6
+peewee==3.18.2
+ipytree==0.2.2
+referencing==0.36.2
+earthengine-api==1.5.24
+spacy==3.8.7
+networkx==3.5
+dataproc-spark-connect==0.8.3
+cachetools==5.5.2
+build==1.3.0
+xgboost==3.0.4
+google-cloud-bigquery-connection==1.18.3
+blobfile==3.0.0
+shellingham==1.5.4
+jupyterlab_widgets==3.0.15
+highspy==1.11.0
+jaxlib==0.5.3
+python-box==7.3.2
+orbax-checkpoint==0.11.22
+albumentations==2.0.8
+sse-starlette==3.0.2
+spanner-graph-notebook==1.1.7
+PyYAML==6.0.2
+gradio==5.42.0
+mizani==0.13.5
+simsimd==6.5.1
+platformdirs==4.3.8
+stanio==0.5.1
+hf_transfer==0.1.9
+huggingface-hub==0.34.4
+jupyter-console==6.1.0
+xarray-einstats==0.9.1
+pyasn1_modules==0.4.2
+miniKanren==1.0.5
+psycopg2==2.9.10
+preshed==3.0.10
+treelite==4.4.1
+jaraco.context==6.0.1
+pyshp==2.3.1
+branca==0.8.1
+nx-cugraph-cu12==25.6.0
+httpx==0.28.1
+matplotlib-venn==1.1.2
+grpc-interceptor==0.15.4
+google-api-core==2.25.1
+librosa==0.11.0
+grpcio-status==1.71.2
+regex==2024.11.6
+fastai==2.8.3
+nvidia-nvtx-cu12==12.6.77
+sphinxcontrib-jsmath==1.0.1
+ipywidgets==7.7.1
+en_core_web_sm==3.8.0
+beartype==0.21.0
+cupy-cuda12x==13.3.0
+optree==0.17.0
+imageio-ffmpeg==0.6.0
+packaging==25.0
+etils==1.13.0
+webcolors==24.11.1
+locket==1.0.0
+simplejson==3.20.1
+linkify-it-py==2.0.3
+cramjam==2.11.0
+google-cloud-bigquery-storage==2.32.0
+antlr4-python3-runtime==4.9.3
+Brotli==1.1.0
+tzdata==2025.2
+distro==1.9.0
+distributed==2025.5.0
+jiter==0.10.0
+transformers==4.55.2
+propcache==0.3.2
+wurlitzer==3.1.1
+Flask==3.1.1
+google-cloud-firestore==2.21.0
+nvidia-cusolver-cu12==11.7.1.2
+tcmlib==1.4.0
+progressbar2==4.5.0
+clarabel==0.11.1
+torchtune==0.6.1
+mkl==2025.2.0
+tf-slim==1.1.0
+soundfile==0.13.1
+blinker==1.9.0
+google-auth-oauthlib==1.2.2
+uc-micro-py==1.0.3
+glob2==0.7
+imutils==0.5.4
+ply==3.11
+cuml-cu12==25.6.0
+rmm-cu12==25.6.0
+pyzmq==26.2.1
+pycairo==1.28.0
+community==1.0.0b1
+statsmodels==0.14.5
+pynvml==12.0.0
+kaggle==1.7.4.5
+tweepy==4.16.0
+fsspec==2025.3.0
+ipyparallel==8.8.0
+soxr==0.5.0.post1
+cons==0.4.7
+ipython==7.34.0
+tomlkit==0.13.3
+google-cloud-logging==3.12.1
+pylibcugraph-cu12==25.6.0
+tables==3.10.2
+intel-openmp==2025.2.1
+pickleshare==0.7.5
+google-cloud-storage==2.19.0
+pooch==1.8.2
+cmake==3.31.6
+jupytext==1.17.2
+ipykernel==6.17.1
+termcolor==3.1.0
+tensorflow-text==2.19.0
+ydf==0.13.0
+sentence-transformers==5.1.0
+pyspark==3.5.1
+editdistance==0.8.1
+tensorflow==2.19.0
+importlib_metadata==8.7.0
+umap-learn==0.5.9.post2
+pytz==2025.2
+fonttools==4.59.1
+google-cloud-bigquery==3.35.1
+contourpy==1.3.3
+murmurhash==1.0.13
+py4j==0.10.9.7
+fastrlock==0.8.3
+keras==3.10.0
+text-unidecode==1.3
+fastcore==1.8.7
+einops==0.8.1
+raft-dask-cu12==25.6.0
+argon2-cffi==25.1.0
+imbalanced-learn==0.14.0
+mpmath==1.3.0
+cyipopt==1.5.0
+google-genai==1.30.0
+keras-hub==0.21.1
+torchdata==0.11.0
+geographiclib==2.0
+h5py==3.14.0
+six==1.17.0
+html5lib==1.1
+zict==3.0.0
+PyWavelets==1.9.0
+greenlet==3.2.4
+python-multipart==0.0.20
+notebook==6.5.7
+langsmith==0.4.14
+semantic-version==2.10.0
+Send2Trash==1.8.3
+typeguard==4.4.4
+nvidia-cusparselt-cu12==0.7.1
+grpcio==1.74.0
+certifi==2025.8.3
+ipyevents==2.0.2
+ffmpy==0.6.1
+charset-normalizer==3.4.3
+patsy==1.0.1
+pandocfilters==1.5.1
+rapids-logger==0.1.1
+widgetsnbextension==3.6.10
+iniconfig==2.1.0
+opentelemetry-semantic-conventions==0.57b0
+wcwidth==0.2.13
+sphinxcontrib-devhelp==2.0.0
+pylibraft-cu12==25.6.0
+uritemplate==4.2.0
+hpack==4.1.0
+websockets==15.0.1
+weasel==0.4.1
+jsonpointer==3.0.0
+logical-unification==0.4.6
+google-cloud-translate==3.21.1
+slicer==0.0.8
+cloudpickle==3.1.1
+cufflinks==0.17.3
+scikit-learn==1.6.1
+matplotlib-inline==0.1.7
+google-cloud-appengine-logging==1.6.2
+pygit2==1.18.2
+gast==0.6.0
+spacy-loggers==1.0.5
+sphinxcontrib-qthelp==2.0.0
+nvidia-cusparse-cu12==12.5.4.2
+colour==0.1.5
+flax==0.10.6
+yfinance==0.2.65
+pydub==0.25.1
+defusedxml==0.7.1
+kiwisolver==1.4.9
+easydict==1.13
+groovy==0.1.2
+nibabel==5.3.2
+cudf-cu12==25.6.0
+xxhash==3.5.0
+frozendict==2.4.6
+traitlets==5.7.1
+tsfresh==0.21.0
+Pygments==2.19.2
+tbb==2022.2.0
+more-itertools==10.7.0
+multipledispatch==1.0.0
+jupyterlab_pygments==0.3.0
+ale-py==0.11.2
+psygnal==0.14.1
+optax==0.2.5
+cffi==1.17.1
+scipy==1.16.1
+tzlocal==5.3.1
+PyDrive2==1.21.3
+nbconvert==7.16.6
+tensorstore==0.1.76
+aiohappyeyeballs==2.6.1
+google-resumable-media==2.7.2
+grpc-google-iam-v1==0.14.2
+pillow==11.3.0
+tensorflow-datasets==4.9.9
+fastjsonschema==2.21.2
+httplib2==0.22.0
+safehttpx==0.1.6
+music21==9.3.0
+timm==1.0.19
+nvidia-cudnn-cu12==9.10.2.21
+absolufy-imports==0.3.1
+Bottleneck==1.4.2
+et_xmlfile==2.0.0
+roman-numerals-py==3.1.0
+beautifulsoup4==4.13.4
+sortedcontainers==2.4.0
+torch==2.8.0+cu126
+google-pasta==0.2.0
+lightgbm==4.6.0
+rich==13.9.4
+fastdownload==0.0.7
+libcugraph-cu12==25.6.0
+google-crc32c==1.7.1
+anywidget==0.9.18
+toolz==0.12.1
+babel==2.17.0
+scooby==0.10.1
+future==1.0.0
+snowballstemmer==3.0.1
+ml_dtypes==0.5.3
+nvidia-cuda-runtime-cu12==12.6.77
+missingno==0.5.2
+partd==1.4.2
+ruff==0.12.9
+alabaster==1.0.0
+jupyter_core==5.8.1
+astropy==7.1.0
+audioread==3.0.1
+oauthlib==3.3.1
+umf==0.11.0
+jieba==0.42.1
+xarray==2025.8.0
+moviepy==1.0.3
+sympy==1.13.3
+orjson==3.11.2
+Authlib==1.6.1
+plotly==5.24.1
+omegaconf==2.3.0
+nest-asyncio==1.6.0
+PyOpenGL==3.1.10
+pluggy==1.6.0
+pycparser==2.22
+tblib==3.1.0
+tensorflow-hub==0.16.1
+nvidia-cufile-cu12==1.11.1.6
+google-cloud-trace==1.16.2
+tensorflow_decision_forests==1.12.0
+opencv-python==4.12.0.88
+libclang==18.1.1
+tensorboard-data-server==0.7.2
+tensorboard==2.19.0
+pandas-datareader==0.10.0
+bqplot==0.12.45
+zipp==3.23.0
+pylibcudf-cu12==25.6.0
+jaraco.classes==3.4.0
+proglog==0.1.12
+starlette==0.47.2
+google-cloud-core==2.4.3
+cvxpy==1.6.7
+ratelim==0.1.6
+lxml==5.4.0
+GDAL==3.8.4
+nvidia-nvjitlink-cu12==12.6.85
+tensorflow-metadata==1.17.2
+vega-datasets==0.9.0
+blis==1.3.0
+py-cpuinfo==9.0.0
+ucx-py-cu12==0.44.0
+gradio_client==1.11.1
+hf-xet==1.1.7
+keyring==25.6.0
+sentry-sdk==2.35.0
+fastprogress==1.0.3
+pynndescent==0.5.13
+msgpack==1.1.1
+ipython-genutils==0.2.0
+humanize==4.12.3
+ibis-framework==9.5.0
+nbclient==0.10.2
+multiprocess==0.70.16
+docutils==0.21.2
+bokeh==3.7.3
+pymc==5.25.1
+llvmlite==0.43.0
+nltk==3.9.1
+libraft-cu12==25.6.0
+pydantic_core==2.33.2
+imageio==2.37.0
+googleapis-common-protos==1.70.0
+matplotlib==3.10.0
+imagesize==1.4.1
+xlrd==2.0.2
+narwhals==2.1.2
+folium==0.20.0
+pytest==8.4.1
+h5netcdf==1.6.4
+gcsfs==2025.3.0
+grpclib==0.4.8
+PyGObject==3.42.0
+mdit-py-plugins==0.5.0
+albucore==0.0.24
+blosc2==3.7.1
+google-generativeai==0.8.5
+google-api-python-client==2.179.0
+googledrivedownloader==1.1.0
+spacy-legacy==3.0.12
+cymem==2.0.11
+PyJWT==2.10.1
+hyperopt==0.2.7
+prompt_toolkit==3.0.51
+inflect==7.5.0
+cmdstanpy==1.2.5
+pyviz_comms==3.0.6
+SecretStorage==3.3.3
+smart_open==7.3.0.post1
+pyerfa==2.0.1.5
+jsonschema-specifications==2025.4.1
+nvidia-cuda-nvrtc-cu12==12.6.77
+holidays==0.78
+gym-notices==0.1.0
+cryptography==43.0.3
+google==2.0.3
+jupyter-leaflet==0.20.0
+nvidia-cublas-cu12==12.6.4.1
+triton==3.4.0
+pandas==2.2.2
+backcall==0.2.0
+dask-cuda==25.6.0
+annotated-types==0.7.0
+torchao==0.10.0
+notebook_shim==0.2.4
+pycocotools==2.0.10
+attrs==25.3.0
+zstandard==0.24.0
+sklearn-pandas==2.2.0
+xyzservices==2025.4.0
+colorlover==0.3.0
+types-pytz==2025.2.0.20250809
+nvidia-cuda-cupti-cu12==12.6.80
+pyproj==3.7.2
+cuvs-cu12==25.6.1
+portpicker==1.5.2
+shap==0.48.0
+ipyfilechooser==0.6.0
+prophet==1.1.7
+lazy_loader==0.4
+keras-nlp==0.21.1
+google-cloud-audit-log==0.3.2
+google-cloud-datastore==2.21.0
+PySocks==1.7.1
+torchvision==0.23.0+cu126
+docstring_parser==0.17.0
+pexpect==4.9.0
+geocoder==1.38.1
+duckdb==1.3.2
+typer==0.16.0
+MarkupSafe==3.0.2
+flatbuffers==25.2.10
+smmap==5.0.2
+libcuvs-cu12==25.6.1
+pyparsing==3.2.3
+tinycss2==1.4.0
+watchdog==6.0.0
+scikit-image==0.25.2
+yellowbrick==1.5
+nvidia-cufft-cu12==11.3.0.4
+openpyxl==3.1.5
+gymnasium==1.2.0
+dopamine_rl==4.1.2
+dask-cudf-cu12==25.6.0
+stumpy==1.13.0
+libucx-cu12==1.18.1
+hdbscan==0.8.40
+google-ai-generativelanguage==0.6.15
+jaraco.functools==4.2.1
+idna==3.10
+google-cloud-functions==1.20.4
+cvxopt==1.3.2
+pycryptodomex==3.23.0
+aiosignal==1.4.0
+pyproject_hooks==1.2.0
+nvidia-nccl-cu12==2.27.3
+parso==0.8.4
+opentelemetry-sdk==1.36.0
+srsly==2.5.1
+mlxtend==0.23.4
+ptyprocess==0.7.0
+Markdown==3.8.2
+jsonpickle==4.1.1
+aiofiles==24.1.0
+langchain-text-splitters==0.3.9
+traittypes==0.2.1
+sphinxcontrib-htmlhelp==2.1.0
+torchsummary==1.5.1
+plum-dispatch==2.5.7
+wordcloud==1.9.4
+filelock==3.19.1
+frozenlist==1.7.0
+typing-inspection==0.4.1
+terminado==0.18.1
+cloudpathlib==0.21.1
+gitdb==4.0.12
+geopy==2.4.1
+nvtx==0.2.13
+atpublic==5.1
+altair==5.5.0
+stringzilla==3.12.6
+jsonpatch==1.33
+libcudf-cu12==25.6.0
+safetensors==0.6.2
+ucxx-cu12==0.44.0
+joblib==1.5.1
+google-cloud-secret-manager==2.24.0
+holoviews==1.21.0
+aiohttp==3.12.15
+python-apt==0.0.0
+launchpadlib==1.10.16
+distro==1.7.0
+PyGObject==3.42.1
+blinker==1.4
+wadllib==1.3.6
+more-itertools==8.10.0
+SecretStorage==3.3.1
+keyring==23.5.0
+zipp==1.0.0
+dbus-python==1.2.18
+importlib-metadata==4.6.4
+jeepney==0.7.1
+python-apt==2.4.0+ubuntu4
+oauthlib==3.2.0
+lazr.uri==1.0.6
+lazr.restfulclient==0.14.4
+pyparsing==2.4.7
+six==1.16.0
+httplib2==0.20.2
+cryptography==3.4.8
+PyJWT==2.3.0
+MarkupSafe==2.0.1
+Mako==1.1.3
+Markdown==3.3.6
+zipp==3.19.2
+jaraco.functools==4.0.1
+packaging==24.1
+importlib_resources==6.4.0
+wheel==0.43.0
+importlib_metadata==8.0.0
+more-itertools==10.3.0
+jaraco.text==3.12.1
+autocommand==2.2.2
+typing_extensions==4.12.2
+platformdirs==4.2.2
+jaraco.collections==5.1.0
+jaraco.context==5.3.0
+typeguard==4.3.0
+inflect==7.3.1
+tomli==2.0.1
+backports.tarfile==1.2.0

wandb/run-20250824_080823-9kirrkwo/logs/debug-core.log

@@ -0,0 +1,7 @@
+{"time":"2025-08-24T08:08:23.777872123Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpnbcy0xju/port-646.txt","pid":646,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2025-08-24T08:08:23.778865046Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":646}
+{"time":"2025-08-24T08:08:23.778957559Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-646-3216-342828738/socket","Net":"unix"}}
+{"time":"2025-08-24T08:08:23.94945573Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2025-08-24T08:08:23.965856739Z","level":"INFO","msg":"handleInformInit: received","streamId":"9kirrkwo","id":"1(@)"}
+{"time":"2025-08-24T08:08:24.227731947Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"9kirrkwo","id":"1(@)"}
+{"time":"2025-08-24T08:20:52.318944519Z","level":"INFO","msg":"server: parent process exited, terminating service process"}

wandb/run-20250824_080823-9kirrkwo/logs/debug-internal.log

@@ -0,0 +1,6 @@
+{"time":"2025-08-24T08:08:23.965963172Z","level":"INFO","msg":"stream: starting","core version":"0.21.1"}
+{"time":"2025-08-24T08:08:24.22764533Z","level":"INFO","msg":"stream: created new stream","id":"9kirrkwo"}
+{"time":"2025-08-24T08:08:24.227723322Z","level":"INFO","msg":"stream: started","id":"9kirrkwo"}
+{"time":"2025-08-24T08:08:24.229697221Z","level":"INFO","msg":"handler: started","stream_id":"9kirrkwo"}
+{"time":"2025-08-24T08:08:24.229751339Z","level":"INFO","msg":"writer: started","stream_id":"9kirrkwo"}
+{"time":"2025-08-24T08:08:24.229893198Z","level":"INFO","msg":"sender: started","stream_id":"9kirrkwo"}

wandb/run-20250824_080823-9kirrkwo/logs/debug.log

@@ -0,0 +1,32 @@
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Current SDK version is 0.21.1
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Configure stats pid to 646
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Loading settings from /content/wandb/settings
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_init.py:setup_run_log_directory():703] Logging user logs to /content/wandb/run-20250824_080823-9kirrkwo/logs/debug.log
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_init.py:setup_run_log_directory():704] Logging internal logs to /content/wandb/run-20250824_080823-9kirrkwo/logs/debug-internal.log
+2025-08-24 08:08:23,319 INFO    MainThread:646 [wandb_init.py:monkeypatch_ipython():622] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7b31256ef4a0>
+2025-08-24 08:08:23,320 INFO    MainThread:646 [wandb_init.py:init():830] calling init triggers
+2025-08-24 08:08:23,321 INFO    MainThread:646 [wandb_init.py:init():835] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2025-08-24 08:08:23,321 INFO    MainThread:646 [wandb_init.py:init():871] starting backend
+2025-08-24 08:08:23,949 INFO    MainThread:646 [wandb_init.py:init():874] sending inform_init request
+2025-08-24 08:08:23,960 INFO    MainThread:646 [wandb_init.py:init():882] backend started and connected
+2025-08-24 08:08:23,973 INFO    MainThread:646 [wandb_run.py:_label_probe_notebook():1318] probe notebook
+2025-08-24 08:08:24,228 INFO    MainThread:646 [wandb_init.py:init():953] updated telemetry
+2025-08-24 08:08:24,228 INFO    MainThread:646 [wandb_init.py:init():977] communicating run to backend with 90.0 second timeout
+2025-08-24 08:08:24,494 INFO    MainThread:646 [wandb_init.py:init():1029] starting run threads in backend
+2025-08-24 08:08:25,028 INFO    MainThread:646 [wandb_run.py:_console_start():2494] atexit reg
+2025-08-24 08:08:25,028 INFO    MainThread:646 [wandb_run.py:_redirect():2342] redirect: wrap_raw
+2025-08-24 08:08:25,028 INFO    MainThread:646 [wandb_run.py:_redirect():2411] Wrapping output streams.
+2025-08-24 08:08:25,028 INFO    MainThread:646 [wandb_run.py:_redirect():2434] Redirects installed.
+2025-08-24 08:08:25,036 INFO    MainThread:646 [wandb_init.py:init():1075] run started, returning control to user process
+2025-08-24 08:08:25,038 INFO    MainThread:646 [wandb_run.py:_config_callback():1380] config_cb None None {'peft_config': {'default': {'task_type': <TaskType.CAUSAL_LM: 'CAUSAL_LM'>, 'peft_type': <PeftType.LORA: 'LORA'>, 'auto_mapping': None, 'base_model_name_or_path': 'unsloth/llama-2-7b-chat-bnb-4bit', 'revision': None, 'inference_mode': False, 'r': 16, 'target_modules': {'k_proj', 'up_proj', 'v_proj', 'gate_proj', 'q_proj', 'o_proj', 'down_proj'}, 'exclude_modules': None, 'lora_alpha': 16, 'lora_dropout': 0, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, '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, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None}}, 'vocab_size': 32000, 'max_position_embeddings': 4096, 'hidden_size': 4096, 'intermediate_size': 11008, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 32, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 10000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 128, 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'torch_dtype': 'float16', 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 1024, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, '_name_or_path': 'unsloth/llama-2-7b-chat-bnb-4bit', 'transformers_version': '4.55.2', 'model_type': 'llama', 'quantization_config': {'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'llm_int8_skip_modules': None, 'llm_int8_threshold': 6.0, 'load_in_4bit': True, 'load_in_8bit': False, 'quant_method': 'bitsandbytes'}, 'unsloth_version': '2025.8.9', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': 'outputs', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0002, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 60, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 5, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'outputs/runs/Aug24_08-08-03_5bb901241d6f', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 3407, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': True, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'model_init_kwargs': None, 'chat_template_path': None, 'dataset_text_field': 'text', 'dataset_kwargs': None, 'dataset_num_proc': None, 'eos_token': '<EOS_TOKEN>', 'pad_token': '<PAD_TOKEN>', 'packing': False, 'packing_strategy': 'bfd', 'padding_free': False, 'pad_to_multiple_of': None, 'eval_packing': None, 'completion_only_loss': None, 'assistant_only_loss': False, 'activation_offloading': False}
+2025-08-24 08:08:25,048 INFO    MainThread:646 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 6778392576 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7b3125788a70>>
+2025-08-24 08:08:25,048 INFO    MainThread:646 [wandb_run.py:_config_callback():1380] config_cb model/num_parameters 6778392576 None
+2025-08-24 08:14:12,874 INFO    MainThread:646 [wandb_init.py:_post_run_cell_hook():592] [no run ID] resuming backend
+2025-08-24 08:17:05,573 INFO    MainThread:646 [jupyter.py:save_ipynb():404] [no run ID] not saving jupyter notebook
+2025-08-24 08:17:05,573 INFO    MainThread:646 [wandb_init.py:_pre_run_cell_hook():581] [no run ID] pausing backend
+2025-08-24 08:17:34,408 INFO    MainThread:646 [wandb_init.py:_post_run_cell_hook():592] [no run ID] resuming backend
+2025-08-24 08:18:03,308 INFO    MainThread:646 [jupyter.py:save_ipynb():404] [no run ID] not saving jupyter notebook
+2025-08-24 08:18:03,308 INFO    MainThread:646 [wandb_init.py:_pre_run_cell_hook():581] [no run ID] pausing backend