Delete wandb

wandb/debug.log

@@ -1,27 +0,0 @@
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Current SDK version is 0.16.3
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Configure stats pid to 116027
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Loading settings from /home/rnd/.config/wandb/settings
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Loading settings from /home/rnd/Documents/Ameer/gemma/wandb/settings
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'new.py', 'program_abspath': '/home/rnd/Documents/Ameer/gemma/new.py', 'program': '/home/rnd/Documents/Ameer/gemma/new.py'}
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_init.py:_log_setup():526] Logging user logs to /home/rnd/Documents/Ameer/gemma/wandb/run-20240223_032422-b657btrg/logs/debug.log
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_init.py:_log_setup():527] Logging internal logs to /home/rnd/Documents/Ameer/gemma/wandb/run-20240223_032422-b657btrg/logs/debug-internal.log
-2024-02-23 03:24:22,981 INFO    MainThread:116027 [wandb_init.py:init():566] calling init triggers
-2024-02-23 03:24:22,981 INFO    MainThread:116027 [wandb_init.py:init():573] wandb.init called with sweep_config: {}
-config: {}
-2024-02-23 03:24:22,981 INFO    MainThread:116027 [wandb_init.py:init():616] starting backend
-2024-02-23 03:24:22,981 INFO    MainThread:116027 [wandb_init.py:init():620] setting up manager
-2024-02-23 03:24:22,982 INFO    MainThread:116027 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2024-02-23 03:24:22,984 INFO    MainThread:116027 [wandb_init.py:init():628] backend started and connected
-2024-02-23 03:24:22,986 INFO    MainThread:116027 [wandb_init.py:init():720] updated telemetry
-2024-02-23 03:24:22,986 INFO    MainThread:116027 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout
-2024-02-23 03:24:23,690 INFO    MainThread:116027 [wandb_run.py:_on_init():2262] communicating current version
-2024-02-23 03:24:23,800 INFO    MainThread:116027 [wandb_run.py:_on_init():2271] got version response 
-2024-02-23 03:24:23,800 INFO    MainThread:116027 [wandb_init.py:init():804] starting run threads in backend
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_run.py:_console_start():2241] atexit reg
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_run.py:_redirect():2096] redirect: wrap_raw
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_run.py:_redirect():2161] Wrapping output streams.
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_run.py:_redirect():2186] Redirects installed.
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_init.py:init():847] run started, returning control to user process
-2024-02-23 03:24:24,872 INFO    MainThread:116027 [wandb_run.py:_config_callback():1343] config_cb None None {'vocab_size': 256000, 'max_position_embeddings': 8192, 'hidden_size': 2048, 'intermediate_size': 16384, 'num_hidden_layers': 18, 'num_attention_heads': 8, 'head_dim': 256, 'num_key_value_heads': 1, 'hidden_act': 'gelu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 10000.0, 'attention_bias': False, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, '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, 'max_length': 20, '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, 'architectures': ['GemmaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 2, 'pad_token_id': 0, 'eos_token_id': 1, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'google/gemma-2b', 'transformers_version': '4.39.0.dev0', 'model_type': 'gemma', 'rope_scaling': None, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': './gemma-jokes-gemma', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', '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': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 2.5e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './logs', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 25, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 25, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'gemma-jokes-gemma-2024-02-23-03-24', '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}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['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': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, '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, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}

wandb/run-20240223_032422-b657btrg/files/conda-environment.yaml

@@ -1,123 +0,0 @@
-name: gemma
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - ca-certificates=2023.12.12=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.13=h7f8727e_0
-  - pip=23.3.1=py39h06a4308_0
-  - python=3.9.18=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.2.2=py39h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - wheel=0.41.2=py39h06a4308_0
-  - xz=5.4.5=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - accelerate==0.28.0.dev0
-      - aiohttp==3.9.3
-      - aiosignal==1.3.1
-      - appdirs==1.4.4
-      - asttokens==2.4.1
-      - async-timeout==4.0.3
-      - attrs==23.2.0
-      - bitsandbytes==0.42.0
-      - certifi==2024.2.2
-      - charset-normalizer==3.3.2
-      - click==8.1.7
-      - comm==0.2.1
-      - contourpy==1.2.0
-      - cycler==0.12.1
-      - datasets==2.17.1
-      - decorator==5.1.1
-      - dill==0.3.8
-      - docker-pycreds==0.4.0
-      - exceptiongroup==1.2.0
-      - executing==2.0.1
-      - filelock==3.13.1
-      - fonttools==4.49.0
-      - frozenlist==1.4.1
-      - fsspec==2023.10.0
-      - gitdb==4.0.11
-      - gitpython==3.1.42
-      - huggingface-hub==0.20.3
-      - idna==3.6
-      - importlib-resources==6.1.1
-      - ipython==8.18.1
-      - ipywidgets==8.1.2
-      - jedi==0.19.1
-      - jinja2==3.1.3
-      - jupyterlab-widgets==3.0.10
-      - kiwisolver==1.4.5
-      - markupsafe==2.1.5
-      - matplotlib==3.8.3
-      - matplotlib-inline==0.1.6
-      - mpmath==1.3.0
-      - multidict==6.0.5
-      - multiprocess==0.70.16
-      - networkx==3.2.1
-      - numpy==1.26.4
-      - nvidia-cublas-cu12==12.1.3.1
-      - nvidia-cuda-cupti-cu12==12.1.105
-      - nvidia-cuda-nvrtc-cu12==12.1.105
-      - nvidia-cuda-runtime-cu12==12.1.105
-      - nvidia-cudnn-cu12==8.9.2.26
-      - nvidia-cufft-cu12==11.0.2.54
-      - nvidia-curand-cu12==10.3.2.106
-      - nvidia-cusolver-cu12==11.4.5.107
-      - nvidia-cusparse-cu12==12.1.0.106
-      - nvidia-nccl-cu12==2.19.3
-      - nvidia-nvjitlink-cu12==12.3.101
-      - nvidia-nvtx-cu12==12.1.105
-      - packaging==23.2
-      - pandas==2.2.0
-      - parso==0.8.3
-      - peft==0.8.2
-      - pexpect==4.9.0
-      - pillow==10.2.0
-      - prompt-toolkit==3.0.43
-      - protobuf==4.25.3
-      - psutil==5.9.8
-      - ptyprocess==0.7.0
-      - pure-eval==0.2.2
-      - pyarrow==15.0.0
-      - pyarrow-hotfix==0.6
-      - pygments==2.17.2
-      - pyparsing==3.1.1
-      - python-dateutil==2.8.2
-      - pytz==2024.1
-      - pyyaml==6.0.1
-      - regex==2023.12.25
-      - requests==2.31.0
-      - safetensors==0.4.2
-      - scipy==1.12.0
-      - sentry-sdk==1.40.5
-      - setproctitle==1.3.3
-      - six==1.16.0
-      - smmap==5.0.1
-      - stack-data==0.6.3
-      - sympy==1.12
-      - tokenizers==0.15.2
-      - torch==2.2.1
-      - tqdm==4.66.2
-      - traitlets==5.14.1
-      - transformers==4.39.0.dev0
-      - triton==2.2.0
-      - typing-extensions==4.9.0
-      - tzdata==2024.1
-      - urllib3==2.2.1
-      - wandb==0.16.3
-      - wcwidth==0.2.13
-      - widgetsnbextension==4.0.10
-      - xxhash==3.4.1
-      - yarl==1.9.4
-      - zipp==3.17.0
-prefix: /home/rnd/miniconda3/envs/gemma

wandb/run-20240223_032422-b657btrg/files/config.yaml

@@ -1,682 +0,0 @@
-wandb_version: 1
-
-_wandb:
-  desc: null
-  value:
-    python_version: 3.9.18
-    cli_version: 0.16.3
-    framework: huggingface
-    huggingface_version: 4.39.0.dev0
-    is_jupyter_run: false
-    is_kaggle_kernel: false
-    start_time: 1708638862.984978
-    t:
-      1:
-      - 1
-      - 11
-      - 49
-      - 51
-      - 55
-      - 71
-      - 98
-      2:
-      - 1
-      - 11
-      - 49
-      - 51
-      - 55
-      - 71
-      - 98
-      3:
-      - 7
-      - 13
-      - 23
-      4: 3.9.18
-      5: 0.16.3
-      6: 4.39.0.dev0
-      8:
-      - 5
-      9:
-        1: transformers_trainer
-      13: linux-x86_64
-    m:
-    - 1: train/global_step
-      6:
-      - 3
-    - 1: train/loss
-      5: 1
-      6:
-      - 1
-    - 1: train/grad_norm
-      5: 1
-      6:
-      - 1
-    - 1: train/learning_rate
-      5: 1
-      6:
-      - 1
-    - 1: train/epoch
-      5: 1
-      6:
-      - 1
-    - 1: eval/loss
-      5: 1
-      6:
-      - 1
-    - 1: eval/runtime
-      5: 1
-      6:
-      - 1
-    - 1: eval/samples_per_second
-      5: 1
-      6:
-      - 1
-    - 1: eval/steps_per_second
-      5: 1
-      6:
-      - 1
-vocab_size:
-  desc: null
-  value: 256000
-max_position_embeddings:
-  desc: null
-  value: 8192
-hidden_size:
-  desc: null
-  value: 2048
-intermediate_size:
-  desc: null
-  value: 16384
-num_hidden_layers:
-  desc: null
-  value: 18
-num_attention_heads:
-  desc: null
-  value: 8
-head_dim:
-  desc: null
-  value: 256
-num_key_value_heads:
-  desc: null
-  value: 1
-hidden_act:
-  desc: null
-  value: gelu
-initializer_range:
-  desc: null
-  value: 0.02
-rms_norm_eps:
-  desc: null
-  value: 1.0e-06
-use_cache:
-  desc: null
-  value: false
-rope_theta:
-  desc: null
-  value: 10000.0
-attention_bias:
-  desc: null
-  value: false
-attention_dropout:
-  desc: null
-  value: 0.0
-return_dict:
-  desc: null
-  value: true
-output_hidden_states:
-  desc: null
-  value: false
-output_attentions:
-  desc: null
-  value: false
-torchscript:
-  desc: null
-  value: false
-torch_dtype:
-  desc: null
-  value: bfloat16
-use_bfloat16:
-  desc: null
-  value: false
-tf_legacy_loss:
-  desc: null
-  value: false
-pruned_heads:
-  desc: null
-  value: {}
-tie_word_embeddings:
-  desc: null
-  value: true
-chunk_size_feed_forward:
-  desc: null
-  value: 0
-is_encoder_decoder:
-  desc: null
-  value: false
-is_decoder:
-  desc: null
-  value: false
-cross_attention_hidden_size:
-  desc: null
-  value: null
-add_cross_attention:
-  desc: null
-  value: false
-tie_encoder_decoder:
-  desc: null
-  value: false
-max_length:
-  desc: null
-  value: 20
-min_length:
-  desc: null
-  value: 0
-do_sample:
-  desc: null
-  value: false
-early_stopping:
-  desc: null
-  value: false
-num_beams:
-  desc: null
-  value: 1
-num_beam_groups:
-  desc: null
-  value: 1
-diversity_penalty:
-  desc: null
-  value: 0.0
-temperature:
-  desc: null
-  value: 1.0
-top_k:
-  desc: null
-  value: 50
-top_p:
-  desc: null
-  value: 1.0
-typical_p:
-  desc: null
-  value: 1.0
-repetition_penalty:
-  desc: null
-  value: 1.0
-length_penalty:
-  desc: null
-  value: 1.0
-no_repeat_ngram_size:
-  desc: null
-  value: 0
-encoder_no_repeat_ngram_size:
-  desc: null
-  value: 0
-bad_words_ids:
-  desc: null
-  value: null
-num_return_sequences:
-  desc: null
-  value: 1
-output_scores:
-  desc: null
-  value: false
-return_dict_in_generate:
-  desc: null
-  value: false
-forced_bos_token_id:
-  desc: null
-  value: null
-forced_eos_token_id:
-  desc: null
-  value: null
-remove_invalid_values:
-  desc: null
-  value: false
-exponential_decay_length_penalty:
-  desc: null
-  value: null
-suppress_tokens:
-  desc: null
-  value: null
-begin_suppress_tokens:
-  desc: null
-  value: null
-architectures:
-  desc: null
-  value:
-  - GemmaForCausalLM
-finetuning_task:
-  desc: null
-  value: null
-id2label:
-  desc: null
-  value:
-    '0': LABEL_0
-    '1': LABEL_1
-label2id:
-  desc: null
-  value:
-    LABEL_0: 0
-    LABEL_1: 1
-tokenizer_class:
-  desc: null
-  value: null
-prefix:
-  desc: null
-  value: null
-bos_token_id:
-  desc: null
-  value: 2
-pad_token_id:
-  desc: null
-  value: 0
-eos_token_id:
-  desc: null
-  value: 1
-sep_token_id:
-  desc: null
-  value: null
-decoder_start_token_id:
-  desc: null
-  value: null
-task_specific_params:
-  desc: null
-  value: null
-problem_type:
-  desc: null
-  value: null
-_name_or_path:
-  desc: null
-  value: google/gemma-2b
-transformers_version:
-  desc: null
-  value: 4.39.0.dev0
-model_type:
-  desc: null
-  value: gemma
-rope_scaling:
-  desc: null
-  value: null
-quantization_config:
-  desc: null
-  value:
-    quant_method: QuantizationMethod.BITS_AND_BYTES
-    _load_in_8bit: false
-    _load_in_4bit: true
-    llm_int8_threshold: 6.0
-    llm_int8_skip_modules: null
-    llm_int8_enable_fp32_cpu_offload: false
-    llm_int8_has_fp16_weight: false
-    bnb_4bit_quant_type: nf4
-    bnb_4bit_use_double_quant: true
-    bnb_4bit_compute_dtype: bfloat16
-    load_in_4bit: true
-    load_in_8bit: false
-output_dir:
-  desc: null
-  value: ./gemma-jokes-gemma
-overwrite_output_dir:
-  desc: null
-  value: false
-do_train:
-  desc: null
-  value: false
-do_eval:
-  desc: null
-  value: true
-do_predict:
-  desc: null
-  value: false
-evaluation_strategy:
-  desc: null
-  value: steps
-prediction_loss_only:
-  desc: null
-  value: false
-per_device_train_batch_size:
-  desc: null
-  value: 2
-per_device_eval_batch_size:
-  desc: null
-  value: 8
-per_gpu_train_batch_size:
-  desc: null
-  value: null
-per_gpu_eval_batch_size:
-  desc: null
-  value: null
-gradient_accumulation_steps:
-  desc: null
-  value: 1
-eval_accumulation_steps:
-  desc: null
-  value: null
-eval_delay:
-  desc: null
-  value: 0
-learning_rate:
-  desc: null
-  value: 2.5e-05
-weight_decay:
-  desc: null
-  value: 0.0
-adam_beta1:
-  desc: null
-  value: 0.9
-adam_beta2:
-  desc: null
-  value: 0.999
-adam_epsilon:
-  desc: null
-  value: 1.0e-08
-max_grad_norm:
-  desc: null
-  value: 1.0
-num_train_epochs:
-  desc: null
-  value: 3.0
-max_steps:
-  desc: null
-  value: 500
-lr_scheduler_type:
-  desc: null
-  value: linear
-lr_scheduler_kwargs:
-  desc: null
-  value: {}
-warmup_ratio:
-  desc: null
-  value: 0.0
-warmup_steps:
-  desc: null
-  value: 1
-log_level:
-  desc: null
-  value: passive
-log_level_replica:
-  desc: null
-  value: warning
-log_on_each_node:
-  desc: null
-  value: true
-logging_dir:
-  desc: null
-  value: ./logs
-logging_strategy:
-  desc: null
-  value: steps
-logging_first_step:
-  desc: null
-  value: false
-logging_steps:
-  desc: null
-  value: 25
-logging_nan_inf_filter:
-  desc: null
-  value: true
-save_strategy:
-  desc: null
-  value: steps
-save_steps:
-  desc: null
-  value: 25
-save_total_limit:
-  desc: null
-  value: null
-save_safetensors:
-  desc: null
-  value: true
-save_on_each_node:
-  desc: null
-  value: false
-save_only_model:
-  desc: null
-  value: false
-no_cuda:
-  desc: null
-  value: false
-use_cpu:
-  desc: null
-  value: false
-use_mps_device:
-  desc: null
-  value: false
-seed:
-  desc: null
-  value: 42
-data_seed:
-  desc: null
-  value: null
-jit_mode_eval:
-  desc: null
-  value: false
-use_ipex:
-  desc: null
-  value: false
-bf16:
-  desc: null
-  value: true
-fp16:
-  desc: null
-  value: false
-fp16_opt_level:
-  desc: null
-  value: O1
-half_precision_backend:
-  desc: null
-  value: auto
-bf16_full_eval:
-  desc: null
-  value: false
-fp16_full_eval:
-  desc: null
-  value: false
-tf32:
-  desc: null
-  value: null
-local_rank:
-  desc: null
-  value: 0
-ddp_backend:
-  desc: null
-  value: null
-tpu_num_cores:
-  desc: null
-  value: null
-tpu_metrics_debug:
-  desc: null
-  value: false
-debug:
-  desc: null
-  value: []
-dataloader_drop_last:
-  desc: null
-  value: false
-eval_steps:
-  desc: null
-  value: 25
-dataloader_num_workers:
-  desc: null
-  value: 0
-dataloader_prefetch_factor:
-  desc: null
-  value: null
-past_index:
-  desc: null
-  value: -1
-run_name:
-  desc: null
-  value: gemma-jokes-gemma-2024-02-23-03-24
-disable_tqdm:
-  desc: null
-  value: false
-remove_unused_columns:
-  desc: null
-  value: true
-label_names:
-  desc: null
-  value: null
-load_best_model_at_end:
-  desc: null
-  value: false
-metric_for_best_model:
-  desc: null
-  value: null
-greater_is_better:
-  desc: null
-  value: null
-ignore_data_skip:
-  desc: null
-  value: false
-fsdp:
-  desc: null
-  value: []
-fsdp_min_num_params:
-  desc: null
-  value: 0
-fsdp_config:
-  desc: null
-  value:
-    min_num_params: 0
-    xla: false
-    xla_fsdp_v2: false
-    xla_fsdp_grad_ckpt: false
-fsdp_transformer_layer_cls_to_wrap:
-  desc: null
-  value: null
-accelerator_config:
-  desc: null
-  value:
-    split_batches: false
-    dispatch_batches: null
-    even_batches: true
-    use_seedable_sampler: true
-deepspeed:
-  desc: null
-  value: null
-label_smoothing_factor:
-  desc: null
-  value: 0.0
-optim:
-  desc: null
-  value: paged_adamw_8bit
-optim_args:
-  desc: null
-  value: null
-adafactor:
-  desc: null
-  value: false
-group_by_length:
-  desc: null
-  value: false
-length_column_name:
-  desc: null
-  value: length
-report_to:
-  desc: null
-  value:
-  - wandb
-ddp_find_unused_parameters:
-  desc: null
-  value: null
-ddp_bucket_cap_mb:
-  desc: null
-  value: null
-ddp_broadcast_buffers:
-  desc: null
-  value: null
-dataloader_pin_memory:
-  desc: null
-  value: true
-dataloader_persistent_workers:
-  desc: null
-  value: false
-skip_memory_metrics:
-  desc: null
-  value: true
-use_legacy_prediction_loop:
-  desc: null
-  value: false
-push_to_hub:
-  desc: null
-  value: false
-resume_from_checkpoint:
-  desc: null
-  value: null
-hub_model_id:
-  desc: null
-  value: null
-hub_strategy:
-  desc: null
-  value: every_save
-hub_token:
-  desc: null
-  value: <HUB_TOKEN>
-hub_private_repo:
-  desc: null
-  value: false
-hub_always_push:
-  desc: null
-  value: false
-gradient_checkpointing:
-  desc: null
-  value: true
-gradient_checkpointing_kwargs:
-  desc: null
-  value: null
-include_inputs_for_metrics:
-  desc: null
-  value: false
-fp16_backend:
-  desc: null
-  value: auto
-push_to_hub_model_id:
-  desc: null
-  value: null
-push_to_hub_organization:
-  desc: null
-  value: null
-push_to_hub_token:
-  desc: null
-  value: <PUSH_TO_HUB_TOKEN>
-mp_parameters:
-  desc: null
-  value: ''
-auto_find_batch_size:
-  desc: null
-  value: false
-full_determinism:
-  desc: null
-  value: false
-torchdynamo:
-  desc: null
-  value: null
-ray_scope:
-  desc: null
-  value: last
-ddp_timeout:
-  desc: null
-  value: 1800
-torch_compile:
-  desc: null
-  value: false
-torch_compile_backend:
-  desc: null
-  value: null
-torch_compile_mode:
-  desc: null
-  value: null
-dispatch_batches:
-  desc: null
-  value: null
-split_batches:
-  desc: null
-  value: null
-include_tokens_per_second:
-  desc: null
-  value: false
-include_num_input_tokens_seen:
-  desc: null
-  value: false
-neftune_noise_alpha:
-  desc: null
-  value: null

wandb/run-20240223_032422-b657btrg/files/output.log

@@ -1,1198 +0,0 @@
-
-
-  5%|███▎                                                               | 25/500 [00:03<01:11,  6.69it/s]
-{'loss': 4.0257, 'grad_norm': 6.853318691253662, 'learning_rate': 2.3797595190380762e-05, 'epoch': 0.0}
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-100%|███████████████████████████████████████████████████████████████▊| 2888/2896 [05:34<00:00,  8.65it/s]
-
-
-
-  9%|██████▏                                                            | 46/500 [05:44<01:44,  4.35it/s]
- 10%|██████▋                                                            | 50/500 [05:44<01:16,  5.90it/s]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-100%|███████████████████████████████████████████████████████████████████████████████████▉| 2893/2896 [05:35<00:00,  8.65it/s]
-
-
-
- 15%|█████████████                                                                          | 75/500 [11:26<01:12,  5.88it/s]
-{'loss': 3.2615, 'grad_norm': 5.772947788238525, 'learning_rate': 2.1292585170340683e-05, 'epoch': 0.0}
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- 99%|███████████████████████████████████████████████████████████████████████████████████▌| 2880/2896 [06:00<00:01,  8.69it/s]
-
-
- 20%|█████████████████▏                                                                    | 100/500 [17:34<01:08,  5.83it/s]
-  0%|                                                                                       | 4/2896 [00:00<04:43, 10.21it/s]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- 99%|███████████████████████████████████████████████████████████████████████████████████▌| 2881/2896 [05:40<00:01,  8.69it/s]
-
-
- 23%|████████████████████                                                                  | 117/500 [23:21<03:08,  2.03it/s]
- 25%|█████████████████████▌                                                                | 125/500 [23:22<01:03,  5.91it/s]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-100%|███████████████████████████████████████████████████████████████████████████████████▉| 2894/2896 [05:39<00:00,  8.67it/s]
-
-
- 30%|█████████████████████████▊                                                            | 150/500 [29:07<00:59,  5.91it/s]
-  0%|                                                                                       | 2/2896 [00:00<02:46, 17.41it/s]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- 99%|███████████████████████████████████████████████████████████████████████████████████▌| 2880/2896 [05:38<00:01,  8.68it/s]
-
-
- 35%|██████████████████████████████                                                        | 175/500 [34:54<00:55,  5.88it/s]
-  0%|                                                                                       | 4/2896 [00:00<04:25, 10.91it/s]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-  File "/home/rnd/Documents/Ameer/gemma/new.py", line 184, in <module>                   | 1763/2896 [03:27<02:10,  8.69it/s]
-    trainer.train()
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/trainer.py", line 1624, in train
-    return inner_training_loop(
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/trainer.py", line 2029, in _inner_training_loop
-    self._maybe_log_save_evaluate(tr_loss, grad_norm, model, trial, epoch, ignore_keys_for_eval)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/trainer.py", line 2412, in _maybe_log_save_evaluate
-    metrics = self.evaluate(ignore_keys=ignore_keys_for_eval)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/trainer.py", line 3229, in evaluate
-    output = eval_loop(
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/trainer.py", line 3418, in evaluation_loop
-    loss, logits, labels = self.prediction_step(model, inputs, prediction_loss_only, ignore_keys=ignore_keys)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/trainer.py", line 3635, in prediction_step
-    loss, outputs = self.compute_loss(model, inputs, return_outputs=True)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/trainer.py", line 2925, in compute_loss
-    outputs = model(**inputs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
-    return self._call_impl(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
-    return forward_call(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/accelerate/utils/operations.py", line 829, in forward
-    return model_forward(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/accelerate/utils/operations.py", line 817, in __call__
-    return convert_to_fp32(self.model_forward(*args, **kwargs))
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/torch/amp/autocast_mode.py", line 16, in decorate_autocast
-    return func(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/peft/peft_model.py", line 1091, in forward
-    return self.base_model(
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
-    return self._call_impl(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
-    return forward_call(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/peft/tuners/tuners_utils.py", line 160, in forward
-    return self.model.forward(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/accelerate/hooks.py", line 166, in new_forward
-    output = module._old_forward(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/models/gemma/modeling_gemma.py", line 1070, in forward
-    outputs = self.model(
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
-    return self._call_impl(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
-    return forward_call(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/accelerate/hooks.py", line 166, in new_forward
-    output = module._old_forward(*args, **kwargs)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/models/gemma/modeling_gemma.py", line 875, in forward
-    causal_mask = self._update_causal_mask(attention_mask, inputs_embeds)
-  File "/home/rnd/miniconda3/envs/gemma/lib/python3.9/site-packages/transformers/models/gemma/modeling_gemma.py", line 979, in _update_causal_mask
-    if not is_tracing and torch.any(attention_mask != 1):
-KeyboardInterrupt

wandb/run-20240223_032422-b657btrg/files/requirements.txt

@@ -1,101 +0,0 @@
-accelerate==0.28.0.dev0
-aiohttp==3.9.3
-aiosignal==1.3.1
-appdirs==1.4.4
-asttokens==2.4.1
-async-timeout==4.0.3
-attrs==23.2.0
-bitsandbytes==0.42.0
-certifi==2024.2.2
-charset-normalizer==3.3.2
-click==8.1.7
-comm==0.2.1
-contourpy==1.2.0
-cycler==0.12.1
-datasets==2.17.1
-decorator==5.1.1
-dill==0.3.8
-docker-pycreds==0.4.0
-exceptiongroup==1.2.0
-executing==2.0.1
-filelock==3.13.1
-fonttools==4.49.0
-frozenlist==1.4.1
-fsspec==2023.10.0
-gitdb==4.0.11
-gitpython==3.1.42
-huggingface-hub==0.20.3
-idna==3.6
-importlib-resources==6.1.1
-ipython==8.18.1
-ipywidgets==8.1.2
-jedi==0.19.1
-jinja2==3.1.3
-jupyterlab-widgets==3.0.10
-kiwisolver==1.4.5
-markupsafe==2.1.5
-matplotlib-inline==0.1.6
-matplotlib==3.8.3
-mpmath==1.3.0
-multidict==6.0.5
-multiprocess==0.70.16
-networkx==3.2.1
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==8.9.2.26
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-nccl-cu12==2.19.3
-nvidia-nvjitlink-cu12==12.3.101
-nvidia-nvtx-cu12==12.1.105
-packaging==23.2
-pandas==2.2.0
-parso==0.8.3
-peft==0.8.2
-pexpect==4.9.0
-pillow==10.2.0
-pip==23.3.1
-prompt-toolkit==3.0.43
-protobuf==4.25.3
-psutil==5.9.8
-ptyprocess==0.7.0
-pure-eval==0.2.2
-pyarrow-hotfix==0.6
-pyarrow==15.0.0
-pygments==2.17.2
-pyparsing==3.1.1
-python-dateutil==2.8.2
-pytz==2024.1
-pyyaml==6.0.1
-regex==2023.12.25
-requests==2.31.0
-safetensors==0.4.2
-scipy==1.12.0
-sentry-sdk==1.40.5
-setproctitle==1.3.3
-setuptools==68.2.2
-six==1.16.0
-smmap==5.0.1
-stack-data==0.6.3
-sympy==1.12
-tokenizers==0.15.2
-torch==2.2.1
-tqdm==4.66.2
-traitlets==5.14.1
-transformers==4.39.0.dev0
-triton==2.2.0
-typing-extensions==4.9.0
-tzdata==2024.1
-urllib3==2.2.1
-wandb==0.16.3
-wcwidth==0.2.13
-wheel==0.41.2
-widgetsnbextension==4.0.10
-xxhash==3.4.1
-yarl==1.9.4
-zipp==3.17.0

wandb/run-20240223_032422-b657btrg/files/wandb-metadata.json

@@ -1,202 +0,0 @@
-{
-    "os": "Linux-5.4.0-172-generic-x86_64-with-glibc2.31",
-    "python": "3.9.18",
-    "heartbeatAt": "2024-02-22T21:54:23.837753",
-    "startedAt": "2024-02-22T21:54:22.976651",
-    "docker": null,
-    "cuda": null,
-    "args": [],
-    "state": "running",
-    "program": "/home/rnd/Documents/Ameer/gemma/new.py",
-    "codePathLocal": "new.py",
-    "codePath": "new.py",
-    "host": "rnd-System-Product-Name",
-    "username": "rnd",
-    "executable": "/home/rnd/miniconda3/envs/gemma/bin/python",
-    "cpu_count": 24,
-    "cpu_count_logical": 32,
-    "cpu_freq": {
-        "current": 4938.592250000001,
-        "min": 800.0,
-        "max": 5700.0
-    },
-    "cpu_freq_per_core": [
-        {
-            "current": 5500.0,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5500.0,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5500.0,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5504.691,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5500.0,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5526.894,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5500.0,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5516.923,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5800.0,
-            "min": 800.0,
-            "max": 7400.0
-        },
-        {
-            "current": 5819.727,
-            "min": 800.0,
-            "max": 7400.0
-        },
-        {
-            "current": 5684.191,
-            "min": 800.0,
-            "max": 7400.0
-        },
-        {
-            "current": 5815.223,
-            "min": 800.0,
-            "max": 7400.0
-        },
-        {
-            "current": 5500.0,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5500.0,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5500.0,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 5536.423,
-            "min": 800.0,
-            "max": 7000.0
-        },
-        {
-            "current": 4296.422,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4302.26,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4292.475,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4279.054,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4283.433,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4300.044,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4368.421,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4280.523,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4291.353,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4314.482,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4299.578,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4300.072,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4301.981,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4311.285,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4302.597,
-            "min": 800.0,
-            "max": 4300.0
-        },
-        {
-            "current": 4306.9,
-            "min": 800.0,
-            "max": 4300.0
-        }
-    ],
-    "disk": {
-        "/": {
-            "total": 1832.2072448730469,
-            "used": 1698.8227272033691
-        }
-    },
-    "gpu": "NVIDIA GeForce RTX 3090 Ti",
-    "gpu_count": 1,
-    "gpu_devices": [
-        {
-            "name": "NVIDIA GeForce RTX 3090 Ti",
-            "memory_total": 25757220864
-        }
-    ],
-    "memory": {
-        "total": 62.508731842041016
-    }
-}

wandb/run-20240223_032422-b657btrg/files/wandb-summary.json

@@ -1 +0,0 @@
-{"train/loss": 2.9901, "train/grad_norm": 5.66660213470459, "train/learning_rate": 1.628256513026052e-05, "train/epoch": 0.0, "train/global_step": 175, "_timestamp": 1708640958.932987, "_runtime": 2095.9480090141296, "_step": 12, "eval/loss": 3.162160873413086, "eval/runtime": 340.5303, "eval/samples_per_second": 68.029, "eval/steps_per_second": 8.504, "_wandb": {"runtime": 2302}}

wandb/run-20240223_032422-b657btrg/logs/debug.log

@@ -1,27 +0,0 @@
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Current SDK version is 0.16.3
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Configure stats pid to 116027
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Loading settings from /home/rnd/.config/wandb/settings
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Loading settings from /home/rnd/Documents/Ameer/gemma/wandb/settings
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'new.py', 'program_abspath': '/home/rnd/Documents/Ameer/gemma/new.py', 'program': '/home/rnd/Documents/Ameer/gemma/new.py'}
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_init.py:_log_setup():526] Logging user logs to /home/rnd/Documents/Ameer/gemma/wandb/run-20240223_032422-b657btrg/logs/debug.log
-2024-02-23 03:24:22,980 INFO    MainThread:116027 [wandb_init.py:_log_setup():527] Logging internal logs to /home/rnd/Documents/Ameer/gemma/wandb/run-20240223_032422-b657btrg/logs/debug-internal.log
-2024-02-23 03:24:22,981 INFO    MainThread:116027 [wandb_init.py:init():566] calling init triggers
-2024-02-23 03:24:22,981 INFO    MainThread:116027 [wandb_init.py:init():573] wandb.init called with sweep_config: {}
-config: {}
-2024-02-23 03:24:22,981 INFO    MainThread:116027 [wandb_init.py:init():616] starting backend
-2024-02-23 03:24:22,981 INFO    MainThread:116027 [wandb_init.py:init():620] setting up manager
-2024-02-23 03:24:22,982 INFO    MainThread:116027 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2024-02-23 03:24:22,984 INFO    MainThread:116027 [wandb_init.py:init():628] backend started and connected
-2024-02-23 03:24:22,986 INFO    MainThread:116027 [wandb_init.py:init():720] updated telemetry
-2024-02-23 03:24:22,986 INFO    MainThread:116027 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout
-2024-02-23 03:24:23,690 INFO    MainThread:116027 [wandb_run.py:_on_init():2262] communicating current version
-2024-02-23 03:24:23,800 INFO    MainThread:116027 [wandb_run.py:_on_init():2271] got version response 
-2024-02-23 03:24:23,800 INFO    MainThread:116027 [wandb_init.py:init():804] starting run threads in backend
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_run.py:_console_start():2241] atexit reg
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_run.py:_redirect():2096] redirect: wrap_raw
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_run.py:_redirect():2161] Wrapping output streams.
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_run.py:_redirect():2186] Redirects installed.
-2024-02-23 03:24:24,871 INFO    MainThread:116027 [wandb_init.py:init():847] run started, returning control to user process
-2024-02-23 03:24:24,872 INFO    MainThread:116027 [wandb_run.py:_config_callback():1343] config_cb None None {'vocab_size': 256000, 'max_position_embeddings': 8192, 'hidden_size': 2048, 'intermediate_size': 16384, 'num_hidden_layers': 18, 'num_attention_heads': 8, 'head_dim': 256, 'num_key_value_heads': 1, 'hidden_act': 'gelu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 10000.0, 'attention_bias': False, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, '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, 'max_length': 20, '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, 'architectures': ['GemmaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 2, 'pad_token_id': 0, 'eos_token_id': 1, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'google/gemma-2b', 'transformers_version': '4.39.0.dev0', 'model_type': 'gemma', 'rope_scaling': None, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': './gemma-jokes-gemma', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', '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': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 2.5e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 500, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './logs', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 25, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 25, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'gemma-jokes-gemma-2024-02-23-03-24', '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}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['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': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, '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, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}

wandb/run-20240223_032422-b657btrg/run-b657btrg.wandb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d50af94be5df0d2db6e804280eafdecb87c0ad05f6e33f9783c5396a91cc8b25
-size 8654393