初始化项目，由ModelHub XC社区提供模型

Model: mnoukhov/pythia410m-sft-tldr
Source: Original Platform

code/wandb/run-20240509_173156-a805570edd5eddcfb7deb3a583d7b4c2/files/conda-environment.yaml

@@ -0,0 +1,78 @@
+name: base
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - archspec=0.2.1=pyhd3eb1b0_0
+  - boltons=23.0.0=py312h06a4308_0
+  - brotli-python=1.0.9=py312h6a678d5_7
+  - bzip2=1.0.8=h7b6447c_0
+  - c-ares=1.19.1=h5eee18b_0
+  - ca-certificates=2023.12.12=h06a4308_0
+  - certifi=2024.2.2=py312h06a4308_0
+  - cffi=1.16.0=py312h5eee18b_0
+  - charset-normalizer=2.0.4=pyhd3eb1b0_0
+  - conda=24.1.2=py312h06a4308_0
+  - conda-content-trust=0.2.0=py312h06a4308_0
+  - conda-libmamba-solver=23.12.0=pyhd3eb1b0_1
+  - conda-package-handling=2.2.0=py312h06a4308_0
+  - conda-package-streaming=0.9.0=py312h06a4308_0
+  - cryptography=41.0.7=py312hdda0065_0
+  - distro=1.8.0=py312h06a4308_0
+  - expat=2.5.0=h6a678d5_0
+  - fmt=9.1.0=hdb19cb5_0
+  - icu=73.1=h6a678d5_0
+  - idna=3.4=py312h06a4308_0
+  - jsonpatch=1.32=pyhd3eb1b0_0
+  - jsonpointer=2.1=pyhd3eb1b0_0
+  - krb5=1.20.1=h143b758_1
+  - ld_impl_linux-64=2.38=h1181459_1
+  - libarchive=3.6.2=h6ac8c49_2
+  - libcurl=8.5.0=h251f7ec_0
+  - libedit=3.1.20230828=h5eee18b_0
+  - libev=4.33=h7f8727e_1
+  - libffi=3.4.4=h6a678d5_0
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libmamba=1.5.3=haf1ee3a_0
+  - libmambapy=1.5.3=py312h2dafd23_0
+  - libnghttp2=1.57.0=h2d74bed_0
+  - libsolv=0.7.24=he621ea3_0
+  - libssh2=1.10.0=hdbd6064_2
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libuuid=1.41.5=h5eee18b_0
+  - libxml2=2.10.4=hf1b16e4_1
+  - lz4-c=1.9.4=h6a678d5_0
+  - menuinst=2.0.2=py312h06a4308_0
+  - ncurses=6.4=h6a678d5_0
+  - openssl=3.0.13=h7f8727e_0
+  - packaging=23.1=py312h06a4308_0
+  - pcre2=10.42=hebb0a14_0
+  - pip=23.3.1=py312h06a4308_0
+  - platformdirs=3.10.0=py312h06a4308_0
+  - pluggy=1.0.0=py312h06a4308_1
+  - pybind11-abi=4=hd3eb1b0_1
+  - pycosat=0.6.6=py312h5eee18b_0
+  - pycparser=2.21=pyhd3eb1b0_0
+  - pysocks=1.7.1=py312h06a4308_0
+  - python=3.12.1=h996f2a0_0
+  - readline=8.2=h5eee18b_0
+  - reproc=14.2.4=h295c915_1
+  - reproc-cpp=14.2.4=h295c915_1
+  - requests=2.31.0=py312h06a4308_1
+  - ruamel.yaml=0.17.21=py312h5eee18b_0
+  - setuptools=68.2.2=py312h06a4308_0
+  - sqlite=3.41.2=h5eee18b_0
+  - tk=8.6.12=h1ccaba5_0
+  - tqdm=4.65.0=py312he106c6f_0
+  - truststore=0.8.0=py312h06a4308_0
+  - tzdata=2023d=h04d1e81_0
+  - urllib3=2.1.0=py312h06a4308_1
+  - wheel=0.41.2=py312h06a4308_0
+  - xz=5.4.5=h5eee18b_0
+  - yaml-cpp=0.8.0=h6a678d5_0
+  - zlib=1.2.13=h5eee18b_0
+  - zstandard=0.19.0=py312h5eee18b_0
+  - zstd=1.5.5=hc292b87_0
+prefix: /opt/conda

code/wandb/run-20240509_173156-a805570edd5eddcfb7deb3a583d7b4c2/files/config.yaml

@@ -0,0 +1,699 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.11.2
+    cli_version: 0.15.9
+    framework: huggingface
+    huggingface_version: 4.38.2
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1715275916.76161
+    t:
+      1:
+      - 1
+      - 5
+      - 11
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 84
+      - 98
+      - 105
+      2:
+      - 1
+      - 5
+      - 11
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 84
+      - 98
+      - 105
+      3:
+      - 7
+      - 23
+      4: 3.11.2
+      5: 0.15.9
+      6: 4.38.2
+      8:
+      - 5
+      9:
+        1: transformers_trainer
+    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
+    - 1: train/train_runtime
+      5: 1
+      6:
+      - 1
+    - 1: train/train_samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/train_steps_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/total_flos
+      5: 1
+      6:
+      - 1
+    - 1: train/train_loss
+      5: 1
+      6:
+      - 1
+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: null
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: false
+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:
+  - GPTNeoXForCausalLM
+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: 0
+pad_token_id:
+  desc: null
+  value: null
+eos_token_id:
+  desc: null
+  value: 0
+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: EleutherAI/pythia-410m-deduped
+transformers_version:
+  desc: null
+  value: 4.38.2
+model_type:
+  desc: null
+  value: gpt_neox
+vocab_size:
+  desc: null
+  value: 50304
+max_position_embeddings:
+  desc: null
+  value: 2048
+hidden_size:
+  desc: null
+  value: 1024
+num_hidden_layers:
+  desc: null
+  value: 24
+num_attention_heads:
+  desc: null
+  value: 16
+intermediate_size:
+  desc: null
+  value: 4096
+hidden_act:
+  desc: null
+  value: gelu
+rotary_pct:
+  desc: null
+  value: 0.25
+rotary_emb_base:
+  desc: null
+  value: 10000
+attention_dropout:
+  desc: null
+  value: 0.0
+hidden_dropout:
+  desc: null
+  value: 0.0
+classifier_dropout:
+  desc: null
+  value: 0.1
+initializer_range:
+  desc: null
+  value: 0.02
+layer_norm_eps:
+  desc: null
+  value: 1.0e-05
+use_cache:
+  desc: null
+  value: true
+use_parallel_residual:
+  desc: null
+  value: true
+rope_scaling:
+  desc: null
+  value: null
+attention_bias:
+  desc: null
+  value: true
+output_dir:
+  desc: null
+  value: /home/toolkit/trl/results/a805570edd5eddcfb7deb3a583d7b4c2
+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: 32
+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: 4
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+learning_rate:
+  desc: null
+  value: 3.0e-06
+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: 1.0
+max_steps:
+  desc: null
+  value: -1
+lr_scheduler_type:
+  desc: null
+  value: cosine
+lr_scheduler_kwargs:
+  desc: null
+  value: {}
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 0
+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: /home/toolkit/trl/results/a805570edd5eddcfb7deb3a583d7b4c2/runs/May09_17-31-02_40084257-ebc6-4abd-94a1-8b674b58783e
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 100
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 500
+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: 0.2
+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: /home/toolkit/trl/results/a805570edd5eddcfb7deb3a583d7b4c2
+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: adamw_torch
+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: false
+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: true
+resume_from_checkpoint:
+  desc: null
+  value: null
+hub_model_id:
+  desc: null
+  value: mnoukhov/pythia410m-sft-tldr
+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: false
+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

code/wandb/run-20240509_173156-a805570edd5eddcfb7deb3a583d7b4c2/files/requirements.txt

@@ -0,0 +1,336 @@
+-rotobuf==4.22.3
+absl-py==2.1.0
+accelerate==0.22.0
+addict==2.4.0
+aenum==3.1.15
+aiofiles==23.2.1
+aiohttp==3.9.3
+aioprometheus==23.12.0
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+antlr4-python3-runtime==4.9.3
+anyio==3.7.1
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+arrow==1.2.3
+asttokens==2.2.1
+async-lru==2.0.4
+async-timeout==4.0.3
+attrs==23.2.0
+babel==2.14.0
+backcall==0.2.0
+basicsr==1.4.2
+beautifulsoup4==4.12.3
+bitsandbytes==0.42.0
+black==24.1.0
+bleach==6.0.0
+blendmodes==2022
+certifi==2023.11.17
+cffi==1.15.1
+cfgv==3.4.0
+charset-normalizer==3.2.0
+clean-fid==0.1.35
+click==8.1.7
+clip==1.0
+cmake==3.28.1
+comm==0.1.3
+contourpy==1.2.0
+cupy-cuda12x==12.1.0
+cycler==0.12.1
+datasets==2.17.0
+debugpy==1.6.7
+decorator==5.1.1
+deepspeed==0.13.3
+defusedxml==0.7.1
+deprecation==2.1.0
+dill==0.3.7
+distlib==0.3.7
+docker-pycreds==0.4.0
+docopt==0.6.2
+docstring-parser==0.15
+docstring-to-markdown==0.13
+eai-toolkit-client==1.3.0
+einops==0.4.1
+evaluate==0.4.1.dev0
+execnet==2.0.2
+executing==1.2.0
+facexlib==0.3.0
+fancycompleter==0.9.1
+fastapi==0.109.2
+fastjsonschema==2.16.3
+fastrlock==0.8.2
+ffmpy==0.3.1
+filelock==3.13.1
+filterpy==1.4.5
+fire==0.5.0
+flake8==6.0.0
+flash-attn==2.5.3
+fonttools==4.47.2
+fqdn==1.5.1
+frozenlist==1.4.1
+fsspec==2023.10.0
+ftfy==6.1.3
+future==0.18.3
+gdown==5.1.0
+gfpgan==1.3.8
+gitdb==4.0.11
+gitpython==3.1.32
+gradio-client==0.5.0
+gradio==3.41.2
+greenlet==3.0.3
+grpcio==1.60.1
+h11==0.14.0
+haven-ai==0.7.3
+hjson==3.1.0
+httpcore==1.0.4
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.20.3
+human-eval==1.0
+identify==2.5.27
+idna==3.4
+imageio==2.33.1
+importlib-metadata==7.0.1
+importlib-resources==6.1.1
+inflection==0.5.1
+iniconfig==2.0.0
+ipykernel==6.22.0
+ipython-genutils==0.2.0
+ipython==8.13.1
+ipywidgets==8.0.6
+isoduration==20.11.0
+isort==5.13.2
+jedi==0.18.2
+jinja2==3.1.3
+joblib==1.2.0
+json5==0.9.17
+jsonmerge==1.8.0
+jsonpointer==2.3
+jsonschema-specifications==2023.12.1
+jsonschema==4.21.1
+jupyter-client==8.2.0
+jupyter-console==6.6.3
+jupyter-core==5.3.0
+jupyter-events==0.6.3
+jupyter-lsp==2.2.2
+jupyter-server-terminals==0.4.4
+jupyter-server==2.5.0
+jupyter==1.0.0
+jupyterlab-pygments==0.2.2
+jupyterlab-server==2.25.3
+jupyterlab-widgets==3.0.7
+jupyterlab==4.1.2
+kiwisolver==1.4.5
+kornia==0.6.7
+lark==1.1.2
+lazy-loader==0.3
+lightning-utilities==0.10.1
+lit==17.0.6
+llvmlite==0.42.0
+lmdb==1.4.1
+lpips==0.1.4
+markdown-it-py==3.0.0
+markdown==3.5.2
+markupsafe==2.1.5
+matplotlib-inline==0.1.6
+matplotlib==3.8.2
+mccabe==0.7.0
+mdurl==0.1.2
+mistune==2.0.5
+mosestokenizer==1.2.1
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.5
+multiprocess==0.70.15
+mypy-extensions==0.4.3
+nbclassic==0.5.6
+nbclient==0.7.4
+nbconvert==7.3.1
+nbformat==5.8.0
+neovim==0.3.1
+nest-asyncio==1.5.6
+networkx==3.2.1
+ngrok==1.0.0
+ninja==1.11.1
+nltk==3.8.1
+nodeenv==1.8.0
+notebook-shim==0.2.3
+notebook==6.5.4
+numba==0.59.0
+numpy==1.23.5
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu11==10.9.0.58
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu11==10.2.10.91
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu11==2.14.3
+nvidia-nccl-cu12==2.18.1
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu11==11.7.91
+nvidia-nvtx-cu12==12.1.105
+omegaconf==2.2.3
+open-clip-torch==2.20.0
+opencv-python-headless==4.7.0.72
+opencv-python==4.9.0.80
+openfile==0.0.7
+orjson==3.9.13
+packaging==23.1
+pandas==2.2.0
+pandocfilters==1.5.0
+parameterized==0.9.0
+parso==0.8.3
+pathspec==0.10.3
+pathtools==0.1.2
+pdbpp==0.10.3
+peft==0.10.0
+pexpect==4.8.0
+pickleshare==0.7.5
+piexif==1.1.3
+pillow==9.5.0
+pip==23.0.1
+platformdirs==3.10.0
+pluggy==1.3.0
+pre-commit==3.4.0
+prometheus-client==0.16.0
+prompt-toolkit==3.0.38
+protobuf==3.20.0
+psutil==5.9.5
+ptyprocess==0.7.0
+pure-eval==0.2.2
+py-cpuinfo==9.0.0
+pyarrow-hotfix==0.6
+pyarrow==13.0.0
+pycparser==2.21
+pydantic-core==2.16.3
+pydantic==1.10.14
+pydub==0.25.1
+pyflakes==3.0.1
+pygments==2.15.1
+pynvim==0.5.0
+pynvml==11.5.0
+pyparsing==3.1.1
+pyre-extensions==0.0.23
+pyrepl==0.9.0
+pyrsistent==0.19.3
+pytest-metadata==3.0.0
+pytest-xdist==3.3.1
+pytest==7.4.1
+python-dateutil==2.8.2
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-lsp-black==2.0.0
+python-lsp-isort==0.1
+python-lsp-jsonrpc==1.1.2
+python-lsp-server==1.10.0
+python-multipart==0.0.7
+pytorch-lightning==1.9.4
+pytz==2024.1
+pywavelets==1.5.0
+pyyaml==6.0.1
+pyzmq==25.0.2
+qtconsole==5.4.2
+qtpy==2.3.1
+quantile-python==1.1
+ray==2.9.1
+realesrgan==0.3.0
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+resize-right==0.0.2
+responses==0.18.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.6.0
+rouge-score==0.1.2
+rpds-py==0.17.1
+safetensors==0.4.1
+scikit-image==0.21.0
+scikit-learn==1.2.2
+scipy==1.12.0
+seaborn==0.13.2
+semantic-version==2.10.0
+send2trash==1.8.2
+sentencepiece==0.1.99
+sentry-sdk==1.19.1
+setproctitle==1.3.2
+setuptools==68.1.2
+shtab==1.6.4
+six==1.16.0
+sklearn==0.0.post4
+smmap==5.0.1
+sniffio==1.3.0
+soupsieve==2.5
+stack-data==0.6.2
+starlette==0.36.3
+sympy==1.12
+tb-nightly==2.16.0a20240205
+tensorboard-data-server==0.7.2
+termcolor==2.3.0
+terminado==0.17.1
+tf-keras-nightly==2.16.0.dev2024020510
+threadpoolctl==3.1.0
+tifffile==2024.1.30
+timm==0.9.2
+tinycss2==1.2.1
+tokenize-rt==5.1.0
+tokenizers==0.15.0
+tomesd==0.1.3
+tomli==2.0.1
+toolwrapper==2.1.0
+toolz==0.12.1
+torch-ema==0.3
+torch==2.1.2
+torchdiffeq==0.2.3
+torchmetrics==1.3.0.post0
+torchsde==0.2.6
+torchvision==0.15.2+cu118
+tornado==6.3.1
+tqdm==4.66.1
+traitlets==5.9.0
+trampoline==0.1.2
+transformers==4.38.2
+triton==2.1.0
+trl==0.7.5.dev0
+typing-extensions==4.9.0
+typing-inspect==0.8.0
+tyro==0.5.12
+tzdata==2023.4
+uctools==1.3.0
+ujson==5.9.0
+uri-template==1.2.0
+urllib3==2.0.4
+uvicorn==0.27.0.post1
+uvloop==0.19.0
+virtualenv==20.24.4
+vllm==0.3.2
+wandb==0.15.9
+watchfiles==0.21.0
+wcwidth==0.2.13
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.5.1
+websockets==11.0.3
+werkzeug==3.0.1
+wheel==0.41.2
+widgetsnbextension==4.0.7
+wmctrl==0.4
+xformers==0.0.23.post1
+xxhash==3.3.0
+yapf==0.40.2
+yarl==1.9.4
+zipp==3.17.0

code/wandb/run-20240509_173156-a805570edd5eddcfb7deb3a583d7b4c2/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 2.5779, "train/grad_norm": 3.9158174991607666, "train/learning_rate": 1.2813624190484708e-09, "train/epoch": 1.0, "train/global_step": 912, "_timestamp": 1715278532.1392817, "_runtime": 2615.3776717185974, "_step": 13, "eval/loss": 2.5804877281188965, "eval/runtime": 58.1953, "eval/samples_per_second": 110.782, "eval/steps_per_second": 13.85, "train/train_runtime": 2617.6291, "train/train_samples_per_second": 44.591, "train/train_steps_per_second": 0.348, "train/total_flos": 1.3292726803182387e+17, "train/train_loss": 2.614081516600492}