diff --git a/.gitattributes b/.gitattributes index f2d4ed2d718cf9ba91fbab4f3bfeade1305ba5af..2cbfb08f4f984c9d76aa9d926a5fab8c4be2a2a1 100644 --- a/.gitattributes +++ b/.gitattributes @@ -451,3 +451,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text 2026.04.11/08.20.17_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260411_082153-ecuxlp0j/run-ecuxlp0j.wandb filter=lfs diff=lfs merge=lfs -text 2026.04.11/08.20.51_train_llmbc_lowdim_maze2d-medium-v0/logs.json.txt filter=lfs diff=lfs merge=lfs -text 2026.04.11/08.20.51_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260411_082155-p2755cs0/run-p2755cs0.wandb filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/logs.json.txt filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260414_061220-6okd5etw/run-6okd5etw.wandb filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/run-981b5iwy.wandb filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/run-yrc5uqpn.wandb filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/run-40wpvpiq.wandb filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063146-ar8xzudz/run-ar8xzudz.wandb filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.30.11_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.30.11_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063229-tqhbov1v/run-tqhbov1v.wandb filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.30.13_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text +2026.04.14/06.30.13_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063231-pm30rgpl/run-pm30rgpl.wandb filter=lfs diff=lfs merge=lfs -text diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/config.yaml b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..12bd6f8c9d08fbc54e898f9ae3bf0e0e656c732a --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/config.yaml @@ -0,0 +1,165 @@ +name: train_llmbc_lowdim +_target_: llmbc.workspace.train_llmbc_lowdim_workspace.TrainLLMBCLowdimWorkspace +obs_dim: ${task.obs_dim} +action_dim: ${task.action_dim} +task_name: ${task.name} +exp_name: default +model_name: ${llm.name} +horizon: 1 +n_obs_steps: 1 +n_action_steps: 1 +n_latency_steps: 0 +past_action_visible: false +llm_orig_expert_feedback: true +llm_do_sample: false +policy: + _target_: llmbc.policy.llmbc_lowdim_policy.LLMBCLowdimPolicy + model: + _target_: llmbc.model.policy.policy_mlp.PolicyMLP + input_size: ${eval:'${n_obs_steps}*${obs_dim}'} + hidden_size: + - 256 + - 256 + - 256 + - 256 + output_size: ${eval:'${n_action_steps}*${action_dim}'} + activation: tanh + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + obs_dim: ${obs_dim} + action_dim: ${action_dim} + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + task_id: ${task_name} + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + cfg: ${llm} + obs_dim: ${task.obs_dim} + action_dim: ${task.action_dim} + horizon: ${horizon} + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + loss_bc_weight: 1.0 + loss_llm_weight: 0.01 + horizon: ${horizon} + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + normalize_llm_loss: true +dataloader: + batch_size: 16 + num_workers: 0 + shuffle: true + pin_memory: false + persistent_workers: false +val_dataloader: + batch_size: 16 + num_workers: 0 + shuffle: true + pin_memory: false + persistent_workers: false +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + betas: + - 0.95 + - 0.999 + eps: 1.0e-08 + weight_decay: 1.0e-06 +training: + device: cuda:0 + seed: 44 + debug: false + resume: false + lr_scheduler: cosine + lr_warmup_steps: 10 + num_epochs: 801 + gradient_accumulate_every: 8 + grad_norm_clip: 0.5 + rollout_every: 4 + checkpoint_every: 4 + val_every: 1 + sample_every: 4 + sample_max_batch: 128 + max_train_steps: null + max_val_steps: null + tqdm_interval_sec: 1.0 +logging: + project: ${task.name}-training-mix + resume: true + mode: online + name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} + tags: + - ${name} + - ${task_name} + - ${exp_name} + id: null + group: null +checkpoint: + topk: + monitor_key: test_success_rate + mode: max + k: 5 + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + save_last_ckpt: true + save_last_snapshot: false +multi_run: + run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} +task: + name: maze2d-medium-v0 + obs_dim: 6 + action_dim: 2 + env_runner: + _target_: llmbc.env_runner.pointmaze_lowdim_runner.PointmazeLowdimRunner + env_name: llf-pointmaze-maze2d-medium-v0 + n_train: 10 + n_test: 50 + n_envs: 10 + max_steps: 250 + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + instruction_type: b + feedback_type: + - hp + - hn + - fp + visual: false + discount: 0.99 + dataset: + _target_: llmbc.dataset.pointmaze_lowdim_dataset.PointmazeLowdimDataset + data_path: datasets/maze2d-medium-v0-mix(csp5).pt + data_path2: datasets/maze2d-medium-v0.pt + horizon: ${horizon} + pad_before: ${eval:'${n_obs_steps}-1'} + pad_after: ${eval:'${n_action_steps}-1'} + obs_eef_target: true + use_manual_normalizer: false + val_ratio: 0.02 + dummy_normalizer: true + instructor: + _target_: llmbc.translator.instructor.pointmaze_instructor.maze2d_medium_v0_instructor.Maze2dMediumV0Instructor +llm: + name: HuggingFaceTB/SmolLM2-135M-Instruct + model_name: SmolLM2-135M-Instruct + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + use_quantization: false + use_joint_mlp_projector: true + llm_mode: ete-finetuned + finetune_mode: orig + checkpoint: data/outputs/2025.10.16/11.53.22_train_llm_lowdim_maze2d-medium-v0/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-maze2d-medium-v0/checkpoint-11850 + max_length: 100 + lora_config: + r: 32 + lora_alpha: 64 + lora_dropout: 0.05 + bias: none + task_type: CAUSAL_LM + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + hydra: + job: + override_dirname: ${model_name} + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${model_name} diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/hydra.yaml b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4c2474c921f7eeb2a8c503988ddcfde0d50ec37e --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/hydra.yaml @@ -0,0 +1,155 @@ +hydra: + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + sweep: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - training.seed=44 + job: + name: train + chdir: null + override_dirname: training.seed=44 + id: ??? + num: ??? + config_name: llmbc_maze2d-medium-v0_mix(csp5).yaml + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.2.0 + version_base: '1.2' + cwd: /workspace/LLM-BC + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /workspace/LLM-BC/config/mix_data + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /workspace/LLM-BC/data/outputs/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/overrides.yaml b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7999937f0cd30e4f07ea732ca020a2c1c4587a69 --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/.hydra/overrides.yaml @@ -0,0 +1 @@ +- training.seed=44 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0264-test_success_rate=0.600.ckpt b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0264-test_success_rate=0.600.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..fbaf638d0be901851f22f8bcf66db8617a37934a --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0264-test_success_rate=0.600.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9569fc1d21c7f33064b324744e05625ad831ed80b5ec0bacbb398c7ce6756a3c +size 2432984 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0360-test_success_rate=0.580.ckpt b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0360-test_success_rate=0.580.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..4bc58ad947735382a0178a6ad5abcaa0fe0a8073 --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0360-test_success_rate=0.580.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f659d8b720b1bd263c79e37a73077fbadb02d4d487ab5faf6eb8e9322e6ff02 +size 2432984 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0420-test_success_rate=0.580.ckpt b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0420-test_success_rate=0.580.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..328fc867622ab0a1536d4f94257bfc6e984fbcd2 --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0420-test_success_rate=0.580.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91bc240b8870982b0650f238bbe7bed8dfd40ff54a4795e493c5c3a28bb2233 +size 2432984 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0440-test_success_rate=0.600.ckpt b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0440-test_success_rate=0.600.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..2a3a459c50560e61b194060efbdb4bcbc09e5118 --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0440-test_success_rate=0.600.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d24f2c8cca5303c5d03d7b6cfca5341b36985253ff3f705e952c518c3c798d18 +size 2432984 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0580-test_success_rate=0.600.ckpt b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0580-test_success_rate=0.600.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..1d25a5f0fc1ad09325931e97e0339253fb637eea --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/epoch=0580-test_success_rate=0.600.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1c41022079150e20786f934ec85d6bcfcebae53c0a1f00bfac0283ff3cf78c +size 2432984 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/latest.ckpt b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/latest.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..05c463902425c42f8aabe6d8a1b4e0cbbcf4df4c --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/checkpoints/latest.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfdcc92a992e8155fc1a8d2218c91b31bf8643fd8aa00149b22e73eb994d463b +size 2432984 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/logs.json.txt b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/logs.json.txt new file mode 100644 index 0000000000000000000000000000000000000000..dd86f2956cb06affe74916b44b48556166c0a7eb --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/logs.json.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57b8e33c8176eceb59054374e02d710213e4b99dc285b86b421aa7cd4f2b924a +size 354344598 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/train.log b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..87b987a50774bb8ec49c975992d850c55ba226a4 --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/train.log @@ -0,0 +1,13 @@ +[2026-04-14 06:11:27,692][numexpr.utils][INFO] - Note: detected 144 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable. +[2026-04-14 06:11:27,692][numexpr.utils][INFO] - Note: NumExpr detected 144 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16. +[2026-04-14 06:11:27,692][numexpr.utils][INFO] - NumExpr defaulting to 16 threads. +[2026-04-14 06:11:31,100][datasets][INFO] - PyTorch version 2.2.2 available. +[2026-04-14 06:11:31,100][datasets][INFO] - TensorFlow version 2.15.1 available. +[2026-04-14 06:11:31,101][datasets][INFO] - JAX version 0.4.30 available. +[2026-04-14 06:11:35,022][root][INFO] - running build_ext +[2026-04-14 06:11:35,024][root][INFO] - building 'mujoco_py.cymj' extension +[2026-04-14 06:11:35,024][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /venv/llm-bc/include -I/venv/llm-bc/include -fPIC -O2 -isystem /venv/llm-bc/include -fPIC -I/venv/llm-bc/lib/python3.9/site-packages/mujoco_py -I/root/.mujoco/mujoco210/include -I/venv/llm-bc/lib/python3.9/site-packages/numpy/core/include -I/venv/llm-bc/include/python3.9 -c /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.c -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.o -fopenmp -w +[2026-04-14 06:12:16,476][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /venv/llm-bc/include -I/venv/llm-bc/include -fPIC -O2 -isystem /venv/llm-bc/include -fPIC -I/venv/llm-bc/lib/python3.9/site-packages/mujoco_py -I/root/.mujoco/mujoco210/include -I/venv/llm-bc/lib/python3.9/site-packages/numpy/core/include -I/venv/llm-bc/include/python3.9 -c /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.c -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.o -fopenmp -w +[2026-04-14 06:12:16,608][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -shared -Wl,-rpath,/venv/llm-bc/lib -Wl,-rpath-link,/venv/llm-bc/lib -L/venv/llm-bc/lib -L/venv/llm-bc/lib -Wl,-rpath,/venv/llm-bc/lib -Wl,-rpath-link,/venv/llm-bc/lib -L/venv/llm-bc/lib /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.o -L/root/.mujoco/mujoco210/bin -Wl,--enable-new-dtags,-rpath,/root/.mujoco/mujoco210/bin -lmujoco210 -lglewosmesa -lOSMesa -lGL -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/lib.linux-x86_64-cpython-39/mujoco_py/cymj.cpython-39-x86_64-linux-gnu.so -fopenmp +[2026-04-14 06:12:19,274][absl][INFO] - MUJOCO_GL=osmesa, attempting to import specified OpenGL backend. +[2026-04-14 06:12:19,279][absl][INFO] - MuJoCo library version is: 2.3.7 diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260414_061220-6okd5etw/files/config.yaml b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260414_061220-6okd5etw/files/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c319383acba96f0b6583849ec1840a785ea66dde --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260414_061220-6okd5etw/files/config.yaml @@ -0,0 +1,273 @@ +_target_: + value: llmbc.workspace.train_llmbc_lowdim_workspace.TrainLLMBCLowdimWorkspace +_wandb: + value: + cli_version: 0.18.6 + m: [] + python_version: 3.9.25 + t: + "1": + - 1 + - 2 + - 3 + - 5 + - 11 + - 12 + - 41 + - 49 + - 50 + - 51 + - 53 + - 55 + - 71 + - 83 + - 95 + - 98 + - 100 + - 105 + "2": + - 1 + - 2 + - 3 + - 5 + - 11 + - 12 + - 41 + - 49 + - 50 + - 51 + - 53 + - 55 + - 71 + - 83 + - 95 + - 98 + - 100 + - 105 + "3": + - 13 + - 15 + - 16 + - 23 + - 55 + - 61 + "4": 3.9.25 + "5": 0.18.6 + "6": 4.47.1 + "8": + - 5 + "12": 0.18.6 + "13": linux-x86_64 +action_dim: + value: 2 +checkpoint: + value: + save_last_ckpt: true + save_last_snapshot: false + topk: + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + k: 5 + mode: max + monitor_key: test_success_rate +dataloader: + value: + batch_size: 16 + num_workers: 0 + persistent_workers: false + pin_memory: false + shuffle: true +exp_name: + value: default +horizon: + value: 1 +llm: + value: + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + checkpoint: data/outputs/2025.10.16/11.53.22_train_llm_lowdim_maze2d-medium-v0/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-maze2d-medium-v0/checkpoint-11850 + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + finetune_mode: orig + hydra: + job: + override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct + run: + dir: data/outputs/2026.04.14/06.11.26_HuggingFaceTB/SmolLM2-135M-Instruct + llm_mode: ete-finetuned + lora_config: + bias: none + lora_alpha: 64 + lora_dropout: 0.05 + r: 32 + task_type: CAUSAL_LM + max_length: 100 + model_name: SmolLM2-135M-Instruct + name: HuggingFaceTB/SmolLM2-135M-Instruct + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + use_joint_mlp_projector: true + use_quantization: false +llm_do_sample: + value: false +llm_orig_expert_feedback: + value: true +logging: + value: + group: null + id: null + mode: online + name: 2026.04.14-06.11.26_train_llmbc_lowdim_maze2d-medium-v0 + project: maze2d-medium-v0-training-mix + resume: true + tags: + - train_llmbc_lowdim + - maze2d-medium-v0 + - default +model_name: + value: HuggingFaceTB/SmolLM2-135M-Instruct +multi_run: + value: + run_dir: data/outputs/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0 + wandb_name_base: 2026.04.14-06.11.26_train_llmbc_lowdim_maze2d-medium-v0 +n_action_steps: + value: 1 +n_latency_steps: + value: 0 +n_obs_steps: + value: 1 +name: + value: train_llmbc_lowdim +obs_dim: + value: 6 +optimizer: + value: + _target_: torch.optim.AdamW + betas: + - 0.95 + - 0.999 + eps: 1e-08 + lr: 0.0001 + weight_decay: 1e-06 +output_dir: + value: /workspace/LLM-BC/data/outputs/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0 +past_action_visible: + value: false +policy: + value: + _target_: llmbc.policy.llmbc_lowdim_policy.LLMBCLowdimPolicy + action_dim: 2 + horizon: 1 + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + action_dim: 2 + cfg: + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + checkpoint: data/outputs/2025.10.16/11.53.22_train_llm_lowdim_maze2d-medium-v0/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-maze2d-medium-v0/checkpoint-11850 + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + finetune_mode: orig + hydra: + job: + override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct + run: + dir: data/outputs/2026.04.14/06.11.26_HuggingFaceTB/SmolLM2-135M-Instruct + llm_mode: ete-finetuned + lora_config: + bias: none + lora_alpha: 64 + lora_dropout: 0.05 + r: 32 + task_type: CAUSAL_LM + max_length: 100 + model_name: SmolLM2-135M-Instruct + name: HuggingFaceTB/SmolLM2-135M-Instruct + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + use_joint_mlp_projector: true + use_quantization: false + horizon: 1 + n_action_steps: 1 + n_obs_steps: 1 + obs_dim: 6 + task_id: maze2d-medium-v0 + loss_bc_weight: 1 + loss_llm_weight: 0.01 + model: + _target_: llmbc.model.policy.policy_mlp.PolicyMLP + activation: tanh + hidden_size: + - 256 + - 256 + - 256 + - 256 + input_size: 6 + n_action_steps: 1 + n_obs_steps: 1 + output_size: 2 + n_action_steps: 1 + n_obs_steps: 1 + normalize_llm_loss: true + obs_dim: 6 +task: + value: + action_dim: 2 + dataset: + _target_: llmbc.dataset.pointmaze_lowdim_dataset.PointmazeLowdimDataset + data_path: datasets/maze2d-medium-v0-mix(csp5).pt + data_path2: datasets/maze2d-medium-v0.pt + dummy_normalizer: true + horizon: 1 + obs_eef_target: true + pad_after: 0 + pad_before: 0 + use_manual_normalizer: false + val_ratio: 0.02 + env_runner: + _target_: llmbc.env_runner.pointmaze_lowdim_runner.PointmazeLowdimRunner + discount: 0.99 + env_name: llf-pointmaze-maze2d-medium-v0 + feedback_type: + - hp + - hn + - fp + instruction_type: b + max_steps: 250 + n_action_steps: 1 + n_envs: 10 + n_obs_steps: 1 + n_test: 50 + n_train: 10 + visual: false + instructor: + _target_: llmbc.translator.instructor.pointmaze_instructor.maze2d_medium_v0_instructor.Maze2dMediumV0Instructor + name: maze2d-medium-v0 + obs_dim: 6 +task_name: + value: maze2d-medium-v0 +training: + value: + checkpoint_every: 4 + debug: false + device: cuda:0 + grad_norm_clip: 0.5 + gradient_accumulate_every: 8 + lr_scheduler: cosine + lr_warmup_steps: 10 + max_train_steps: null + max_val_steps: null + num_epochs: 801 + resume: false + rollout_every: 4 + sample_every: 4 + sample_max_batch: 128 + seed: 44 + tqdm_interval_sec: 1 + val_every: 1 +val_dataloader: + value: + batch_size: 16 + num_workers: 0 + persistent_workers: false + pin_memory: false + shuffle: true diff --git a/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260414_061220-6okd5etw/files/output.log b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260414_061220-6okd5etw/files/output.log new file mode 100644 index 0000000000000000000000000000000000000000..c63c79f72d6868c0c58923b567ffb917ea012388 --- /dev/null +++ b/2026.04.14/06.11.26_train_llmbc_lowdim_maze2d-medium-v0/wandb/run-20260414_061220-6okd5etw/files/output.log @@ -0,0 +1,5 @@ +/venv/llm-bc/lib/python3.9/site-packages/gym/envs/registration.py:505: UserWarning: WARN: The environment maze2d-medium-v0 is out of date. You should consider upgrading to version `v1` with the environment ID `maze2d-medium-v1`. + logger.warn( +Eval PointmazeLowdimRunner 1/6: 0%| | 0/250 [00:00 + main() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/main.py", line 90, in decorated_main + _run_hydra( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 389, in _run_hydra + _run_app( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 452, in _run_app + run_and_report( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 213, in run_and_report + return func() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 453, in + lambda: hydra.run( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/hydra.py", line 119, in run + ret = run_job( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/workspace/LLM-BC/./train.py", line 32, in main + workspace.run() + File "/workspace/LLM-BC/llmbc/workspace/train_llm_diffusion_unet_lowdim_workspace.py", line 252, in run + runner_log = env_runner.run(policy) + File "/workspace/LLM-BC/llmbc/env_runner/metaworld_lowdim_runner.py", line 113, in run + self.env = AsyncVectorEnv(self.env_fns) + File "/workspace/LLM-BC/llmbc/gym_util/async_vector_env.py", line 168, in __init__ + self._check_observation_spaces() + File "/workspace/LLM-BC/llmbc/gym_util/async_vector_env.py", line 374, in _check_observation_spaces + same_spaces, successes = zip(*[pipe.recv() for pipe in self.parent_pipes]) + File "/workspace/LLM-BC/llmbc/gym_util/async_vector_env.py", line 374, in + same_spaces, successes = zip(*[pipe.recv() for pipe in self.parent_pipes]) + File "/venv/llm-bc/lib/python3.9/multiprocessing/connection.py", line 250, in recv + buf = self._recv_bytes() + File "/venv/llm-bc/lib/python3.9/multiprocessing/connection.py", line 414, in _recv_bytes + buf = self._recv(4) + File "/venv/llm-bc/lib/python3.9/multiprocessing/connection.py", line 379, in _recv + chunk = read(handle, remaining) +KeyboardInterrupt +Traceback (most recent call last): + File "/workspace/LLM-BC/./train.py", line 35, in + main() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/main.py", line 90, in decorated_main + _run_hydra( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 389, in _run_hydra + _run_app( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 452, in _run_app + run_and_report( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 213, in run_and_report + return func() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 453, in + lambda: hydra.run( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/hydra.py", line 119, in run + ret = run_job( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/workspace/LLM-BC/./train.py", line 32, in main + workspace.run() + File "/workspace/LLM-BC/llmbc/workspace/train_llm_diffusion_unet_lowdim_workspace.py", line 252, in run + runner_log = env_runner.run(policy) + File "/workspace/LLM-BC/llmbc/env_runner/metaworld_lowdim_runner.py", line 113, in run + self.env = AsyncVectorEnv(self.env_fns) + File "/workspace/LLM-BC/llmbc/gym_util/async_vector_env.py", line 168, in __init__ + self._check_observation_spaces() + File "/workspace/LLM-BC/llmbc/gym_util/async_vector_env.py", line 374, in _check_observation_spaces + same_spaces, successes = zip(*[pipe.recv() for pipe in self.parent_pipes]) + File "/workspace/LLM-BC/llmbc/gym_util/async_vector_env.py", line 374, in + same_spaces, successes = zip(*[pipe.recv() for pipe in self.parent_pipes]) + File "/venv/llm-bc/lib/python3.9/multiprocessing/connection.py", line 250, in recv + buf = self._recv_bytes() + File "/venv/llm-bc/lib/python3.9/multiprocessing/connection.py", line 414, in _recv_bytes + buf = self._recv(4) + File "/venv/llm-bc/lib/python3.9/multiprocessing/connection.py", line 379, in _recv + chunk = read(handle, remaining) +KeyboardInterrupt diff --git a/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/requirements.txt b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..f18b63306b50dded477ccac6858260d859b2a206 --- /dev/null +++ b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/requirements.txt @@ -0,0 +1,864 @@ +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +llmbc==0.0.0 +llmbc==0.0.0 +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +autocommand==2.2.2 +backports.tarfile==1.2.0 +importlib_metadata==8.0.0 +inflect==7.3.1 +jaraco.collections==5.1.0 +jaraco.context==5.3.0 +jaraco.functools==4.0.1 +jaraco.text==3.12.1 +more-itertools==10.3.0 +packaging==24.2 +platformdirs==4.2.2 +tomli==2.0.1 +typeguard==4.3.0 +typing_extensions==4.12.2 +wheel==0.45.1 +zipp==3.19.2 diff --git a/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/wandb-metadata.json b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/wandb-metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..1079ec21f9f42512e582b5d51155181e71d48610 --- /dev/null +++ b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/wandb-metadata.json @@ -0,0 +1,56 @@ +{ + "os": "Linux-5.15.0-168-generic-x86_64-with-glibc2.39", + "python": "3.9.25", + "startedAt": "2026-04-14T06:26:28.532096Z", + "args": [ + "--config-path", + "config/mix_data", + "--config-name", + "llmdp_sweep-v2_mix(csp5).yaml", + "policy.loss_llm_weight=1.0e-1" + ], + "program": "/workspace/LLM-BC/./train.py", + "codePath": "train.py", + "git": { + "remote": "https://github.com/CHYang25/LLM-BC.git", + "commit": "16b534f5ac2111b9cbfa638ab62d7944bff711d2" + }, + "email": "chris920325@gmail.com", + "root": "/workspace/LLM-BC/data/outputs/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2", + "host": "c8ef52649900", + "username": "root", + "executable": "/venv/llm-bc/bin/python3", + "codePathLocal": "train.py", + "cpu_count": 72, + "cpu_count_logical": 144, + "gpu": "NVIDIA GeForce RTX 4090", + "gpu_count": 2, + "disk": { + "/": { + "total": "545460846592", + "used": "352992382976" + } + }, + "memory": { + "total": "810942898176" + }, + "cpu": { + "count": 72, + "countLogical": 144 + }, + "gpu_nvidia": [ + { + "name": "NVIDIA GeForce RTX 4090", + "memoryTotal": "25757220864", + "cudaCores": 16384, + "architecture": "Ada" + }, + { + "name": "NVIDIA GeForce RTX 4090", + "memoryTotal": "25757220864", + "cudaCores": 16384, + "architecture": "Ada" + } + ], + "cudaVersion": "12.8" +} \ No newline at end of file diff --git a/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/wandb-summary.json b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/wandb-summary.json new file mode 100644 index 0000000000000000000000000000000000000000..2e5c82a206c8725a2ae248dec1578d661376dc69 --- /dev/null +++ b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/files/wandb-summary.json @@ -0,0 +1 @@ +{"_wandb":{"runtime":213},"lr":7.000000000000001e-06,"_runtime":213.817319835,"_step":550,"train_loss_dp":0.7344393730163574,"global_step":550,"epoch":0,"_timestamp":1.7761481617795644e+09,"train_loss":0.8508371114730835,"train_loss_llm":1.1639776229858398} \ No newline at end of file diff --git a/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/run-981b5iwy.wandb b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/run-981b5iwy.wandb new file mode 100644 index 0000000000000000000000000000000000000000..99f509412d5589607fbd5b04e7d603cb12f04072 --- /dev/null +++ b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062628-981b5iwy/run-981b5iwy.wandb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e61bd891da7f59f0cae5d086053a23d4eea0080b8d39b73c79790f25250279 +size 491520 diff --git a/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json new file mode 100644 index 0000000000000000000000000000000000000000..1a27ca8cdf85f754468c9bf05747fac09ce5d9c7 --- /dev/null +++ b/2026.04.14/06.25.31_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json @@ -0,0 +1 @@ +{"run_id": "981b5iwy"} \ No newline at end of file diff --git a/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/config.yaml b/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..237191d4e5026ae785779cbe8816d252740e6313 --- /dev/null +++ b/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/config.yaml @@ -0,0 +1,165 @@ +name: train_llmbc_lowdim +_target_: llmbc.workspace.train_llmbc_lowdim_workspace.TrainLLMBCLowdimWorkspace +obs_dim: ${task.obs_dim} +action_dim: ${task.action_dim} +task_name: ${task.name} +exp_name: default +model_name: ${llm.name} +horizon: 1 +n_obs_steps: 1 +n_action_steps: 1 +n_latency_steps: 0 +past_action_visible: false +llm_orig_expert_feedback: true +llm_do_sample: false +policy: + _target_: llmbc.policy.llmbc_lowdim_policy.LLMBCLowdimPolicy + model: + _target_: llmbc.model.policy.policy_mlp.PolicyMLP + input_size: ${eval:'${n_obs_steps}*${obs_dim}'} + hidden_size: + - 256 + - 256 + - 256 + - 256 + output_size: ${eval:'${n_action_steps}*${action_dim}'} + activation: tanh + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + obs_dim: ${obs_dim} + action_dim: ${action_dim} + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + task_id: ${task_name} + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + cfg: ${llm} + obs_dim: ${task.obs_dim} + action_dim: ${task.action_dim} + horizon: ${horizon} + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + loss_bc_weight: 1.0 + loss_llm_weight: 0.01 + horizon: ${horizon} + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + normalize_llm_loss: true +dataloader: + batch_size: 16 + num_workers: 0 + shuffle: true + pin_memory: false + persistent_workers: false +val_dataloader: + batch_size: 16 + num_workers: 0 + shuffle: true + pin_memory: false + persistent_workers: false +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + betas: + - 0.95 + - 0.999 + eps: 1.0e-08 + weight_decay: 1.0e-06 +training: + device: cuda:0 + seed: 43 + debug: false + resume: false + lr_scheduler: cosine + lr_warmup_steps: 10 + num_epochs: 801 + gradient_accumulate_every: 8 + grad_norm_clip: 0.5 + rollout_every: 4 + checkpoint_every: 4 + val_every: 1 + sample_every: 4 + sample_max_batch: 128 + max_train_steps: null + max_val_steps: null + tqdm_interval_sec: 1.0 +logging: + project: ${task.name}-training-mix + resume: true + mode: online + name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} + tags: + - ${name} + - ${task_name} + - ${exp_name} + id: null + group: null +checkpoint: + topk: + monitor_key: test_success_rate + mode: max + k: 5 + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + save_last_ckpt: true + save_last_snapshot: false +multi_run: + run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} +task: + name: maze2d-medium-v0 + obs_dim: 6 + action_dim: 2 + env_runner: + _target_: llmbc.env_runner.pointmaze_lowdim_runner.PointmazeLowdimRunner + env_name: llf-pointmaze-maze2d-medium-v0 + n_train: 10 + n_test: 50 + n_envs: 10 + max_steps: 250 + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + instruction_type: b + feedback_type: + - hp + - hn + - fp + visual: false + discount: 0.99 + dataset: + _target_: llmbc.dataset.pointmaze_lowdim_dataset.PointmazeLowdimDataset + data_path: datasets/maze2d-medium-v0-mix(csp5).pt + data_path2: datasets/maze2d-medium-v0.pt + horizon: ${horizon} + pad_before: ${eval:'${n_obs_steps}-1'} + pad_after: ${eval:'${n_action_steps}-1'} + obs_eef_target: true + use_manual_normalizer: false + val_ratio: 0.02 + dummy_normalizer: true + instructor: + _target_: llmbc.translator.instructor.pointmaze_instructor.maze2d_medium_v0_instructor.Maze2dMediumV0Instructor +llm: + name: HuggingFaceTB/SmolLM2-135M-Instruct + model_name: SmolLM2-135M-Instruct + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + use_quantization: false + use_joint_mlp_projector: true + llm_mode: ete-finetuned + finetune_mode: orig + checkpoint: data/outputs/2025.10.16/11.53.22_train_llm_lowdim_maze2d-medium-v0/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-maze2d-medium-v0/checkpoint-11850 + max_length: 100 + lora_config: + r: 32 + lora_alpha: 64 + lora_dropout: 0.05 + bias: none + task_type: CAUSAL_LM + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + hydra: + job: + override_dirname: ${model_name} + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${model_name} diff --git a/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/hydra.yaml b/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9652199764d5f14390e695e8ecb4aefc06d22b84 --- /dev/null +++ b/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/hydra.yaml @@ -0,0 +1,155 @@ +hydra: + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + sweep: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - training.seed=43 + job: + name: train + chdir: null + override_dirname: training.seed=43 + id: ??? + num: ??? + config_name: llmbc_maze2d-medium-v0_mix(csp5).yaml + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.2.0 + version_base: '1.2' + cwd: /workspace/LLM-BC + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /workspace/LLM-BC/config/mix_data + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /workspace/LLM-BC/data/outputs/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/overrides.yaml b/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ebf61aeca24956094799b4a1cab9370df040027f --- /dev/null +++ b/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/.hydra/overrides.yaml @@ -0,0 +1 @@ +- training.seed=43 diff --git a/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/train.log b/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/train.log new file mode 100644 index 0000000000000000000000000000000000000000..01f2659ed0605358717795853c2a896efbed9ed4 --- /dev/null +++ b/2026.04.14/06.25.35_train_llmbc_lowdim_maze2d-medium-v0/train.log @@ -0,0 +1,6 @@ +[2026-04-14 06:25:36,871][numexpr.utils][INFO] - Note: detected 144 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable. +[2026-04-14 06:25:36,871][numexpr.utils][INFO] - Note: NumExpr detected 144 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16. +[2026-04-14 06:25:36,871][numexpr.utils][INFO] - NumExpr defaulting to 16 threads. +[2026-04-14 06:25:40,671][datasets][INFO] - PyTorch version 2.2.2 available. +[2026-04-14 06:25:40,672][datasets][INFO] - TensorFlow version 2.15.1 available. +[2026-04-14 06:25:40,673][datasets][INFO] - JAX version 0.4.30 available. diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..58c223b28d457a7e7a31ea61719577073447c98e --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml @@ -0,0 +1,193 @@ +name: train_llm_diffusion_unet_lowdim +_target_: llmbc.workspace.train_llm_diffusion_unet_lowdim_workspace.TrainLLMDiffusionUnetLowdimWorkspace +obs_dim: ${task.obs_dim} +action_dim: ${task.action_dim} +task_name: ${task.name} +exp_name: default +model_name: ${llm.name} +horizon: 1 +n_obs_steps: 1 +n_action_steps: 1 +n_latency_steps: 0 +past_action_visible: false +keypoint_visible_rate: 1.0 +obs_as_local_cond: false +obs_as_global_cond: true +pred_action_steps_only: false +llm_orig_expert_feedback: true +llm_do_sample: false +policy: + _target_: llmbc.policy.llm_diffusion_unet_lowdim_policy.LLMDiffusionUnetLowdimPolicy + model: + _target_: llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D + input_dim: '${eval: ${task.action_dim} if ${obs_as_local_cond} or ${obs_as_global_cond} + else ${task.obs_dim} + ${task.action_dim}}' + local_cond_dim: '${eval: ${task.obs_dim} if ${obs_as_local_cond} else None}' + global_cond_dim: '${eval: ${task.obs_dim}*${n_obs_steps} if ${obs_as_global_cond} + else None}' + diffusion_step_embed_dim: 256 + down_dims: + - 256 + - 512 + - 1024 + kernel_size: 5 + n_groups: 8 + cond_predict_scale: true + noise_scheduler: + _target_: diffusers.schedulers.scheduling_ddpm.DDPMScheduler + num_train_timesteps: 100 + beta_start: 0.0001 + beta_end: 0.02 + beta_schedule: squaredcos_cap_v2 + variance_type: fixed_small + clip_sample: true + prediction_type: epsilon + horizon: ${horizon} + obs_dim: ${obs_dim} + action_dim: ${action_dim} + n_action_steps: ${eval:'${n_action_steps}+${n_latency_steps}'} + n_obs_steps: ${n_obs_steps} + num_inference_steps: 100 + obs_as_local_cond: ${obs_as_local_cond} + obs_as_global_cond: ${obs_as_global_cond} + pred_action_steps_only: ${pred_action_steps_only} + oa_step_convention: true + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + task_id: ${task_name} + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + cfg: ${llm} + obs_dim: ${obs_dim} + action_dim: ${action_dim} + horizon: ${horizon} + n_obs_steps: ${n_obs_steps} + n_action_steps: ${eval:'${n_action_steps}+${n_latency_steps}'} + loss_dp_weight: 1.0 + loss_llm_weight: 0.01 + normalize_llm_loss: true + reweight_llm_loss: true +ema: + _target_: llmbc.model.diffusion.ema_model.EMAModel + update_after_step: 0 + inv_gamma: 1.0 + power: 0.75 + min_value: 0.0 + max_value: 0.9999 +dataloader: + batch_size: 16 + num_workers: 0 + shuffle: true + pin_memory: false + persistent_workers: false +val_dataloader: + batch_size: 16 + num_workers: 0 + shuffle: false + pin_memory: false + persistent_workers: false +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + betas: + - 0.95 + - 0.999 + eps: 1.0e-08 + weight_decay: 1.0e-06 +training: + device: cuda:0 + seed: 42 + debug: false + resume: true + lr_scheduler: cosine + lr_warmup_steps: 500 + num_epochs: 1001 + gradient_accumulate_every: 16 + use_ema: true + rollout_every: 5 + checkpoint_every: 5 + val_every: 1 + sample_every: 5 + max_train_steps: null + max_val_steps: null + tqdm_interval_sec: 1.0 +logging: + project: ${task.name}-training + resume: true + mode: online + name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} + tags: + - ${name} + - ${task_name} + - ${exp_name} + id: null + group: null +checkpoint: + topk: + monitor_key: test_success_rate + mode: max + k: 5 + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + save_last_ckpt: true + save_last_snapshot: false +multi_run: + run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} +task: + name: sweep-v2 + obs_dim: 9 + action_dim: 4 + env_runner: + _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner + env_name: llf-metaworld-sweep-v2 + n_train: 10 + n_test: 50 + n_envs: 10 + max_steps: 30 + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + instruction_type: b + feedback_type: + - hp + - hn + - fp + visual: false + discount: 0.9 + dataset: + _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset + data_path: datasets/sweep-v2-mix(csp5).pt + data_path2: datasets/sweep-v2.pt + horizon: ${horizon} + pad_before: ${eval:'${n_obs_steps}-1'} + pad_after: ${eval:'${n_action_steps}-1'} + obs_eef_target: true + use_manual_normalizer: false + val_ratio: 0.1 + dummy_normalizer: false + instructor: + _target_: llmbc.translator.instructor.metaworld_instructor.sweep_v2_instructor.SweepV2Instructor +llm: + name: HuggingFaceTB/SmolLM2-135M-Instruct + model_name: SmolLM2-135M-Instruct + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + use_quantization: false + use_joint_mlp_projector: true + llm_mode: ete-finetuned + finetune_mode: orig + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + max_length: 100 + lora_config: + r: 32 + lora_alpha: 64 + lora_dropout: 0.05 + bias: none + task_type: CAUSAL_LM + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + hydra: + job: + override_dirname: ${model_name} + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${model_name} diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8c0f413b6e58dbf9a71cf3eda55313707ae3a92f --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml @@ -0,0 +1,155 @@ +hydra: + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + sweep: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - policy.loss_llm_weight=1.0e-2 + job: + name: train + chdir: null + override_dirname: policy.loss_llm_weight=1.0e-2 + id: ??? + num: ??? + config_name: llmdp_sweep-v2_mix(csp5).yaml + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.2.0 + version_base: '1.2' + cwd: /workspace/LLM-BC + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /workspace/LLM-BC/config/mix_data + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /workspace/LLM-BC/data/outputs/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7343b6263cb3c7b74167b25f5e33f1ef666ae6df --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml @@ -0,0 +1 @@ +- policy.loss_llm_weight=1.0e-2 diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt new file mode 100644 index 0000000000000000000000000000000000000000..d65d26a153e77ee152b36c0963271d7cd936fcd1 --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt @@ -0,0 +1,350 @@ +{"train_loss": 1.2142260074615479, "train_loss_dp": 1.2109837532043457, "train_loss_llm": 0.32422637939453125, "global_step": 0, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.5894043445587158, "train_loss_dp": 1.5555988550186157, "train_loss_llm": 3.3805484771728516, "global_step": 1, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 0.8592647910118103, "train_loss_dp": 0.8444761037826538, "train_loss_llm": 1.4788703918457031, "global_step": 2, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.5737547874450684, "train_loss_dp": 1.567467212677002, "train_loss_llm": 0.6287602186203003, "global_step": 3, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.2232937812805176, "train_loss_dp": 1.2161624431610107, "train_loss_llm": 0.7131385803222656, "global_step": 4, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.611609935760498, "train_loss_dp": 1.6041865348815918, "train_loss_llm": 0.7423383593559265, "global_step": 5, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.3413699865341187, "train_loss_dp": 1.3234602212905884, "train_loss_llm": 1.7909822463989258, "global_step": 6, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.193677544593811, "train_loss_dp": 1.1930253505706787, "train_loss_llm": 0.06521368026733398, "global_step": 7, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.0304384231567383, "train_loss_dp": 1.006334900856018, "train_loss_llm": 2.410350799560547, "global_step": 8, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.3652852773666382, "train_loss_dp": 1.3523192405700684, "train_loss_llm": 1.2966029644012451, "global_step": 9, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.381680965423584, "train_loss_dp": 1.3722383975982666, "train_loss_llm": 0.9442574977874756, "global_step": 10, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.2500667572021484, "train_loss_dp": 1.2402263879776, "train_loss_llm": 0.9840337038040161, "global_step": 11, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.2191638946533203, "train_loss_dp": 1.2112371921539307, "train_loss_llm": 0.792670726776123, "global_step": 12, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.1264299154281616, "train_loss_dp": 1.1232653856277466, "train_loss_llm": 0.3164515495300293, "global_step": 13, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.114905834197998, "train_loss_dp": 1.1038504838943481, "train_loss_llm": 1.1055290699005127, "global_step": 14, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.5273246765136719, "train_loss_dp": 1.5052738189697266, "train_loss_llm": 2.205087661743164, "global_step": 15, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 0.8774579167366028, "train_loss_dp": 0.8685603141784668, "train_loss_llm": 0.8897576332092285, "global_step": 16, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.242292881011963, "train_loss_dp": 1.2375354766845703, "train_loss_llm": 0.4757366180419922, "global_step": 17, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 0.9952828288078308, "train_loss_dp": 0.9838780164718628, "train_loss_llm": 1.1404805183410645, "global_step": 18, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.2600748538970947, "train_loss_dp": 1.2529277801513672, "train_loss_llm": 0.7147130966186523, "global_step": 19, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.1880123615264893, "train_loss_dp": 1.1880123615264893, "train_loss_llm": 0.0, "global_step": 20, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.3708230257034302, "train_loss_dp": 1.3630808591842651, "train_loss_llm": 0.774214506149292, "global_step": 21, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.1187998056411743, "train_loss_dp": 1.108497977256775, "train_loss_llm": 1.0301799774169922, "global_step": 22, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.1816767454147339, "train_loss_dp": 1.1755201816558838, "train_loss_llm": 0.6156516075134277, "global_step": 23, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.3325159549713135, "train_loss_dp": 1.3082664012908936, "train_loss_llm": 2.424954414367676, "global_step": 24, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.4005565643310547, "train_loss_dp": 1.3876872062683105, "train_loss_llm": 1.2869410514831543, "global_step": 25, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.2212674617767334, "train_loss_dp": 1.2060461044311523, "train_loss_llm": 1.5221405029296875, "global_step": 26, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 0.8301150798797607, "train_loss_dp": 0.8227673768997192, "train_loss_llm": 0.7347679138183594, "global_step": 27, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 0.9149899482727051, "train_loss_dp": 0.9067434072494507, "train_loss_llm": 0.8246545791625977, "global_step": 28, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.3611483573913574, "train_loss_dp": 1.2447832822799683, "train_loss_llm": 11.636505126953125, "global_step": 29, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.1991043090820312, "train_loss_dp": 1.1810945272445679, "train_loss_llm": 1.8009734153747559, "global_step": 30, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.39414644241333, "train_loss_dp": 1.3838207721710205, "train_loss_llm": 1.0325665473937988, "global_step": 31, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.232168436050415, "train_loss_dp": 0.9743912220001221, "train_loss_llm": 25.777721405029297, "global_step": 32, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.0207141637802124, "train_loss_dp": 1.0061120986938477, "train_loss_llm": 1.4602069854736328, "global_step": 33, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.224158763885498, "train_loss_dp": 1.1038836240768433, "train_loss_llm": 12.02751350402832, "global_step": 34, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 0.7783562541007996, "train_loss_dp": 0.7511874437332153, "train_loss_llm": 2.716879367828369, "global_step": 35, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.30172598361969, "train_loss_dp": 1.2940138578414917, "train_loss_llm": 0.7712092399597168, "global_step": 36, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.0512481927871704, "train_loss_dp": 1.0373506546020508, "train_loss_llm": 1.389752984046936, "global_step": 37, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.3016198873519897, "train_loss_dp": 1.2951383590698242, "train_loss_llm": 0.648158073425293, "global_step": 38, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.477652907371521, "train_loss_dp": 1.4623231887817383, "train_loss_llm": 1.5329742431640625, "global_step": 39, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.0078511238098145, "train_loss_dp": 1.0005815029144287, "train_loss_llm": 0.7269659042358398, "global_step": 40, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.1381250619888306, "train_loss_dp": 1.1300842761993408, "train_loss_llm": 0.8040800094604492, "global_step": 41, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.0345423221588135, "train_loss_dp": 1.02858567237854, "train_loss_llm": 0.5956590175628662, "global_step": 42, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.1918821334838867, "train_loss_dp": 1.182042121887207, "train_loss_llm": 0.9839978218078613, "global_step": 43, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.1983389854431152, "train_loss_dp": 1.1782596111297607, "train_loss_llm": 2.007936477661133, "global_step": 44, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.13905668258667, "train_loss_dp": 1.1314916610717773, "train_loss_llm": 0.7565021514892578, "global_step": 45, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.3465195894241333, "train_loss_dp": 1.3093535900115967, "train_loss_llm": 3.7166032791137695, "global_step": 46, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.300544261932373, "train_loss_dp": 1.2961735725402832, "train_loss_llm": 0.43706512451171875, "global_step": 47, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.7413785457611084, "train_loss_dp": 1.714151382446289, "train_loss_llm": 2.722715377807617, "global_step": 48, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.559943437576294, "train_loss_dp": 1.5114814043045044, "train_loss_llm": 4.8462066650390625, "global_step": 49, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.3392784595489502, "train_loss_dp": 1.2820918560028076, "train_loss_llm": 5.718661308288574, "global_step": 50, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.091318130493164, "train_loss_dp": 1.0823571681976318, "train_loss_llm": 0.896092414855957, "global_step": 51, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.3553695678710938, "train_loss_dp": 1.3473711013793945, "train_loss_llm": 0.7998428344726562, "global_step": 52, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.400208592414856, "train_loss_dp": 1.3946783542633057, "train_loss_llm": 0.553019642829895, "global_step": 53, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.024678111076355, "train_loss_dp": 1.0102272033691406, "train_loss_llm": 1.4450857639312744, "global_step": 54, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.2564771175384521, "train_loss_dp": 1.2389534711837769, "train_loss_llm": 1.7523598670959473, "global_step": 55, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.229862928390503, "train_loss_dp": 1.229862928390503, "train_loss_llm": 0.0, "global_step": 56, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.4351203441619873, "train_loss_dp": 1.4280118942260742, "train_loss_llm": 0.7108421325683594, "global_step": 57, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.7568683624267578, "train_loss_dp": 1.7568683624267578, "train_loss_llm": 0.0, "global_step": 58, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 0.9146701693534851, "train_loss_dp": 0.9106614589691162, "train_loss_llm": 0.4008716344833374, "global_step": 59, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.0629714727401733, "train_loss_dp": 1.0582225322723389, "train_loss_llm": 0.47489166259765625, "global_step": 60, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.3070189952850342, "train_loss_dp": 1.2989965677261353, "train_loss_llm": 0.8022446632385254, "global_step": 61, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.1110565662384033, "train_loss_dp": 1.1095645427703857, "train_loss_llm": 0.14920806884765625, "global_step": 62, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.1010279655456543, "train_loss_dp": 1.095658302307129, "train_loss_llm": 0.536961555480957, "global_step": 63, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.040368676185608, "train_loss_dp": 1.0287753343582153, "train_loss_llm": 1.159337043762207, "global_step": 64, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.283882975578308, "train_loss_dp": 1.2667810916900635, "train_loss_llm": 1.7101936340332031, "global_step": 65, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.2713927030563354, "train_loss_dp": 1.2617037296295166, "train_loss_llm": 0.9688944816589355, "global_step": 66, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 0.9697917699813843, "train_loss_dp": 0.9413739442825317, "train_loss_llm": 2.8417840003967285, "global_step": 67, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.2020347118377686, "train_loss_dp": 1.1800479888916016, "train_loss_llm": 2.198676824569702, "global_step": 68, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.3157751560211182, "train_loss_dp": 1.2875651121139526, "train_loss_llm": 2.8210039138793945, "global_step": 69, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.202554702758789, "train_loss_dp": 1.1841760873794556, "train_loss_llm": 1.8378667831420898, "global_step": 70, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.3491004705429077, "train_loss_dp": 1.3438347578048706, "train_loss_llm": 0.5265769958496094, "global_step": 71, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 0.936764121055603, "train_loss_dp": 0.9179775714874268, "train_loss_llm": 1.8786544799804688, "global_step": 72, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.1598823070526123, "train_loss_dp": 1.135289192199707, "train_loss_llm": 2.4593095779418945, "global_step": 73, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.3598875999450684, "train_loss_dp": 1.3555123805999756, "train_loss_llm": 0.4375239610671997, "global_step": 74, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.860397458076477, "train_loss_dp": 1.8556218147277832, "train_loss_llm": 0.47756195068359375, "global_step": 75, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.4227266311645508, "train_loss_dp": 1.414045810699463, "train_loss_llm": 0.8680804967880249, "global_step": 76, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.267741322517395, "train_loss_dp": 1.25203275680542, "train_loss_llm": 1.5708551406860352, "global_step": 77, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 0.9328470230102539, "train_loss_dp": 0.9169472455978394, "train_loss_llm": 1.5899808406829834, "global_step": 78, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 0.8221402168273926, "train_loss_dp": 0.7923790216445923, "train_loss_llm": 2.9761199951171875, "global_step": 79, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.015797734260559, "train_loss_dp": 1.0092968940734863, "train_loss_llm": 0.6500859260559082, "global_step": 80, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.287087082862854, "train_loss_dp": 1.279496669769287, "train_loss_llm": 0.759040355682373, "global_step": 81, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.4711720943450928, "train_loss_dp": 1.4356005191802979, "train_loss_llm": 3.5571517944335938, "global_step": 82, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.7746796607971191, "train_loss_dp": 1.5105911493301392, "train_loss_llm": 26.408855438232422, "global_step": 83, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 0.937280535697937, "train_loss_dp": 0.9340149760246277, "train_loss_llm": 0.32655787467956543, "global_step": 84, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.119026780128479, "train_loss_dp": 1.1136049032211304, "train_loss_llm": 0.5421831607818604, "global_step": 85, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.1145763397216797, "train_loss_dp": 1.1065962314605713, "train_loss_llm": 0.7980070114135742, "global_step": 86, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.3616853952407837, "train_loss_dp": 1.353653907775879, "train_loss_llm": 0.803144633769989, "global_step": 87, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.248418927192688, "train_loss_dp": 1.2383646965026855, "train_loss_llm": 1.005427360534668, "global_step": 88, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.0686962604522705, "train_loss_dp": 1.0592976808547974, "train_loss_llm": 0.9398558139801025, "global_step": 89, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 0.9523566961288452, "train_loss_dp": 0.9393671751022339, "train_loss_llm": 1.2989501953125, "global_step": 90, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 0.9704211354255676, "train_loss_dp": 0.9571309089660645, "train_loss_llm": 1.3290214538574219, "global_step": 91, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.2581830024719238, "train_loss_dp": 1.2500872611999512, "train_loss_llm": 0.8095684051513672, "global_step": 92, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.091536521911621, "train_loss_dp": 1.0850541591644287, "train_loss_llm": 0.6482415199279785, "global_step": 93, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.018674373626709, "train_loss_dp": 1.0096831321716309, "train_loss_llm": 0.8991279602050781, "global_step": 94, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.0770442485809326, "train_loss_dp": 1.067256212234497, "train_loss_llm": 0.9788017272949219, "global_step": 95, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.0118895769119263, "train_loss_dp": 0.9556567668914795, "train_loss_llm": 5.6232805252075195, "global_step": 96, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.0088353157043457, "train_loss_dp": 0.9946292638778687, "train_loss_llm": 1.4206085205078125, "global_step": 97, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.0618704557418823, "train_loss_dp": 1.0533971786499023, "train_loss_llm": 0.8473281860351562, "global_step": 98, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 0.9173486232757568, "train_loss_dp": 0.8348127603530884, "train_loss_llm": 8.253589630126953, "global_step": 99, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.2309874296188354, "train_loss_dp": 1.2110412120819092, "train_loss_llm": 1.9946260452270508, "global_step": 100, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.530369520187378, "train_loss_dp": 1.5212764739990234, "train_loss_llm": 0.9093027114868164, "global_step": 101, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.2080981731414795, "train_loss_dp": 1.183016061782837, "train_loss_llm": 2.508209228515625, "global_step": 102, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.28593111038208, "train_loss_dp": 1.2735224962234497, "train_loss_llm": 1.240865707397461, "global_step": 103, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.374464511871338, "train_loss_dp": 1.3602583408355713, "train_loss_llm": 1.4206228256225586, "global_step": 104, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 0.9377275109291077, "train_loss_dp": 0.9263818860054016, "train_loss_llm": 1.1345635652542114, "global_step": 105, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.3163727521896362, "train_loss_dp": 1.311410903930664, "train_loss_llm": 0.4961848258972168, "global_step": 106, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 0.9401397109031677, "train_loss_dp": 0.9401397109031677, "train_loss_llm": 0.0, "global_step": 107, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.3074995279312134, "train_loss_dp": 1.2755658626556396, "train_loss_llm": 3.193366050720215, "global_step": 108, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.3464398384094238, "train_loss_dp": 1.3270540237426758, "train_loss_llm": 1.938586711883545, "global_step": 109, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.1693884134292603, "train_loss_dp": 1.1397781372070312, "train_loss_llm": 2.961027145385742, "global_step": 110, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.522181510925293, "train_loss_dp": 1.5133485794067383, "train_loss_llm": 0.8832952976226807, "global_step": 111, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.3709678649902344, "train_loss_dp": 1.3595249652862549, "train_loss_llm": 1.144289255142212, "global_step": 112, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.987101137638092, "train_loss_dp": 0.9671929478645325, "train_loss_llm": 1.9908201694488525, "global_step": 113, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.2418595552444458, "train_loss_dp": 1.2201751470565796, "train_loss_llm": 2.1684465408325195, "global_step": 114, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.8841862082481384, "train_loss_dp": 0.8708856105804443, "train_loss_llm": 1.3300609588623047, "global_step": 115, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.22050142288208, "train_loss_dp": 1.2014448642730713, "train_loss_llm": 1.905655860900879, "global_step": 116, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.1527434587478638, "train_loss_dp": 1.1332242488861084, "train_loss_llm": 1.951920509338379, "global_step": 117, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.8063086867332458, "train_loss_dp": 0.7741774320602417, "train_loss_llm": 3.2131271362304688, "global_step": 118, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.9218640923500061, "train_loss_dp": 0.913447916507721, "train_loss_llm": 0.8416156768798828, "global_step": 119, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.399662733078003, "train_loss_dp": 1.3826619386672974, "train_loss_llm": 1.7000749111175537, "global_step": 120, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.5391050577163696, "train_loss_dp": 1.53459632396698, "train_loss_llm": 0.45086777210235596, "global_step": 121, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.4053776264190674, "train_loss_dp": 1.3952162265777588, "train_loss_llm": 1.016134262084961, "global_step": 122, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.246399998664856, "train_loss_dp": 1.2373460531234741, "train_loss_llm": 0.9053974151611328, "global_step": 123, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.199317455291748, "train_loss_dp": 1.186524510383606, "train_loss_llm": 1.2792892456054688, "global_step": 124, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.202831506729126, "train_loss_dp": 1.1726295948028564, "train_loss_llm": 3.020185708999634, "global_step": 125, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.3294272422790527, "train_loss_dp": 1.3156859874725342, "train_loss_llm": 1.3741207122802734, "global_step": 126, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.8595767617225647, "train_loss_dp": 0.8500500917434692, "train_loss_llm": 0.9526662826538086, "global_step": 127, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.0012800693511963, "train_loss_dp": 0.9812033176422119, "train_loss_llm": 2.0076799392700195, "global_step": 128, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.0801386833190918, "train_loss_dp": 1.0447351932525635, "train_loss_llm": 3.540346622467041, "global_step": 129, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.2674883604049683, "train_loss_dp": 1.2562992572784424, "train_loss_llm": 1.1189069747924805, "global_step": 130, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.2178473472595215, "train_loss_dp": 1.21113920211792, "train_loss_llm": 0.6708115339279175, "global_step": 131, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.9338388442993164, "train_loss_dp": 0.9120755195617676, "train_loss_llm": 2.176330804824829, "global_step": 132, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.495168685913086, "train_loss_dp": 1.4798719882965088, "train_loss_llm": 1.5296683311462402, "global_step": 133, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1203300952911377, "train_loss_dp": 1.109201431274414, "train_loss_llm": 1.112870693206787, "global_step": 134, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.7030981183052063, "train_loss_dp": 0.7003169059753418, "train_loss_llm": 0.2781219482421875, "global_step": 135, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.7989674806594849, "train_loss_dp": 0.7763664126396179, "train_loss_llm": 2.2601051330566406, "global_step": 136, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.2034188508987427, "train_loss_dp": 1.1995105743408203, "train_loss_llm": 0.39082586765289307, "global_step": 137, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.5198830366134644, "train_loss_dp": 1.5114814043045044, "train_loss_llm": 0.8401651382446289, "global_step": 138, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1898471117019653, "train_loss_dp": 1.1625717878341675, "train_loss_llm": 2.7275333404541016, "global_step": 139, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.9431044459342957, "train_loss_dp": 0.9387279748916626, "train_loss_llm": 0.4376487731933594, "global_step": 140, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1791592836380005, "train_loss_dp": 1.1608953475952148, "train_loss_llm": 1.8263983726501465, "global_step": 141, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1842983961105347, "train_loss_dp": 1.1788935661315918, "train_loss_llm": 0.5404876470565796, "global_step": 142, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1830167770385742, "train_loss_dp": 1.177420973777771, "train_loss_llm": 0.5595860481262207, "global_step": 143, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.7706676721572876, "train_loss_dp": 0.7500808835029602, "train_loss_llm": 2.0586776733398438, "global_step": 144, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0568273067474365, "train_loss_dp": 1.0306296348571777, "train_loss_llm": 2.6197643280029297, "global_step": 145, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.8390830159187317, "train_loss_dp": 0.8200579881668091, "train_loss_llm": 1.9025001525878906, "global_step": 146, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.1467828750610352, "train_loss_dp": 1.1427737474441528, "train_loss_llm": 0.40091609954833984, "global_step": 147, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.9128871560096741, "train_loss_dp": 0.9029089212417603, "train_loss_llm": 0.9978246688842773, "global_step": 148, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.1126600503921509, "train_loss_dp": 1.0998445749282837, "train_loss_llm": 1.2815475463867188, "global_step": 149, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.9934484362602234, "train_loss_dp": 0.983627200126648, "train_loss_llm": 0.9821264743804932, "global_step": 150, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.8006670475006104, "train_loss_dp": 0.7753530740737915, "train_loss_llm": 2.5313987731933594, "global_step": 151, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0276238918304443, "train_loss_dp": 1.0108177661895752, "train_loss_llm": 1.6806116104125977, "global_step": 152, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.4698054790496826, "train_loss_dp": 1.4573051929473877, "train_loss_llm": 1.2500245571136475, "global_step": 153, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.1208338737487793, "train_loss_dp": 1.1033995151519775, "train_loss_llm": 1.7434301376342773, "global_step": 154, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0510036945343018, "train_loss_dp": 1.000337839126587, "train_loss_llm": 5.066581726074219, "global_step": 155, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.7954217195510864, "train_loss_dp": 0.7764338254928589, "train_loss_llm": 1.898789882659912, "global_step": 156, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0372687578201294, "train_loss_dp": 1.0325254201889038, "train_loss_llm": 0.4743328094482422, "global_step": 157, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.092544436454773, "train_loss_dp": 1.0861330032348633, "train_loss_llm": 0.6411471366882324, "global_step": 158, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.2194020748138428, "train_loss_dp": 1.1884307861328125, "train_loss_llm": 3.0971336364746094, "global_step": 159, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.107576608657837, "train_loss_dp": 1.0977963209152222, "train_loss_llm": 0.9780311584472656, "global_step": 160, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.0311685800552368, "train_loss_dp": 1.0239753723144531, "train_loss_llm": 0.7193160057067871, "global_step": 161, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.8929820656776428, "train_loss_dp": 0.8832759857177734, "train_loss_llm": 0.9706106185913086, "global_step": 162, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.0656144618988037, "train_loss_dp": 1.052584171295166, "train_loss_llm": 1.3030333518981934, "global_step": 163, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.196394920349121, "train_loss_dp": 1.188420295715332, "train_loss_llm": 0.7974569797515869, "global_step": 164, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.0412317514419556, "train_loss_dp": 1.028942584991455, "train_loss_llm": 1.228917121887207, "global_step": 165, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.2923147678375244, "train_loss_dp": 1.275970697402954, "train_loss_llm": 1.634401559829712, "global_step": 166, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.457854986190796, "train_loss_dp": 1.4523682594299316, "train_loss_llm": 0.5486674308776855, "global_step": 167, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.8358233571052551, "train_loss_dp": 0.8237012624740601, "train_loss_llm": 1.2122089862823486, "global_step": 168, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.2824134826660156, "train_loss_dp": 1.2447845935821533, "train_loss_llm": 3.762887954711914, "global_step": 169, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.8838927149772644, "train_loss_dp": 0.7977854013442993, "train_loss_llm": 8.610729217529297, "global_step": 170, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.159955620765686, "train_loss_dp": 1.1208444833755493, "train_loss_llm": 3.9111108779907227, "global_step": 171, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.9689618349075317, "train_loss_dp": 0.9650105237960815, "train_loss_llm": 0.39513182640075684, "global_step": 172, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.1551589965820312, "train_loss_dp": 1.1478490829467773, "train_loss_llm": 0.7309961318969727, "global_step": 173, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.9433655738830566, "train_loss_dp": 0.9433655738830566, "train_loss_llm": 0.0, "global_step": 174, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.115327000617981, "train_loss_dp": 1.1106475591659546, "train_loss_llm": 0.46794044971466064, "global_step": 175, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.100792646408081, "train_loss_dp": 1.082282543182373, "train_loss_llm": 1.8510119915008545, "global_step": 176, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.0397549867630005, "train_loss_dp": 1.0299686193466187, "train_loss_llm": 0.9786415100097656, "global_step": 177, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.2450857162475586, "train_loss_dp": 1.2004895210266113, "train_loss_llm": 4.459615707397461, "global_step": 178, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9495880007743835, "train_loss_dp": 0.9388677477836609, "train_loss_llm": 1.0720233917236328, "global_step": 179, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.7823573350906372, "train_loss_dp": 0.7736498117446899, "train_loss_llm": 0.8707506656646729, "global_step": 180, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9191964268684387, "train_loss_dp": 0.9063225984573364, "train_loss_llm": 1.2873849868774414, "global_step": 181, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.1402461528778076, "train_loss_dp": 1.1191234588623047, "train_loss_llm": 2.1122732162475586, "global_step": 182, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.8272892832756042, "train_loss_dp": 0.8228100538253784, "train_loss_llm": 0.44792068004608154, "global_step": 183, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.0445338487625122, "train_loss_dp": 1.0336251258850098, "train_loss_llm": 1.0908684730529785, "global_step": 184, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.0622131824493408, "train_loss_dp": 0.991152286529541, "train_loss_llm": 7.106090545654297, "global_step": 185, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.8597482442855835, "train_loss_dp": 0.8495693206787109, "train_loss_llm": 1.0178899765014648, "global_step": 186, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9844797253608704, "train_loss_dp": 0.9774206280708313, "train_loss_llm": 0.7059082984924316, "global_step": 187, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.3411743640899658, "train_loss_dp": 1.33035409450531, "train_loss_llm": 1.0820218324661255, "global_step": 188, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.963067352771759, "train_loss_dp": 0.9588446021080017, "train_loss_llm": 0.4222745895385742, "global_step": 189, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.047143816947937, "train_loss_dp": 1.0167937278747559, "train_loss_llm": 3.0350112915039062, "global_step": 190, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.2898896932601929, "train_loss_dp": 1.2857036590576172, "train_loss_llm": 0.418597936630249, "global_step": 191, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9388867020606995, "train_loss_dp": 0.9324394464492798, "train_loss_llm": 0.6447279453277588, "global_step": 192, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.2793828248977661, "train_loss_dp": 1.231186866760254, "train_loss_llm": 4.819598197937012, "global_step": 193, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.1666911840438843, "train_loss_dp": 1.1645325422286987, "train_loss_llm": 0.2158680558204651, "global_step": 194, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.303589105606079, "train_loss_dp": 1.2741291522979736, "train_loss_llm": 2.9459991455078125, "global_step": 195, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.1922321319580078, "train_loss_dp": 1.1801778078079224, "train_loss_llm": 1.2054328918457031, "global_step": 196, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 0.9651893973350525, "train_loss_dp": 0.9529061317443848, "train_loss_llm": 1.2283272743225098, "global_step": 197, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.1780668497085571, "train_loss_dp": 1.1543831825256348, "train_loss_llm": 2.3683700561523438, "global_step": 198, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 0.7351898550987244, "train_loss_dp": 0.7292382717132568, "train_loss_llm": 0.5951566696166992, "global_step": 199, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.2100989818572998, "train_loss_dp": 0.9783383011817932, "train_loss_llm": 23.176063537597656, "global_step": 200, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.0502445697784424, "train_loss_dp": 1.0106562376022339, "train_loss_llm": 3.9588356018066406, "global_step": 201, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 0.6521593332290649, "train_loss_dp": 0.6481107473373413, "train_loss_llm": 0.40485620498657227, "global_step": 202, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.4098745584487915, "train_loss_dp": 1.303734540939331, "train_loss_llm": 10.614002227783203, "global_step": 203, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.3819440603256226, "train_loss_dp": 1.3341147899627686, "train_loss_llm": 4.782923698425293, "global_step": 204, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.103819489479065, "train_loss_dp": 1.1017730236053467, "train_loss_llm": 0.2046513557434082, "global_step": 205, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 0.940501868724823, "train_loss_dp": 0.9306132197380066, "train_loss_llm": 0.9888644218444824, "global_step": 206, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.1322269439697266, "train_loss_dp": 1.1281698942184448, "train_loss_llm": 0.40570664405822754, "global_step": 207, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.0362513065338135, "train_loss_dp": 1.026556134223938, "train_loss_llm": 0.9695119857788086, "global_step": 208, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8448707461357117, "train_loss_dp": 0.8448707461357117, "train_loss_llm": 0.0, "global_step": 209, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8706929087638855, "train_loss_dp": 0.8668233752250671, "train_loss_llm": 0.3869504928588867, "global_step": 210, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.2980793714523315, "train_loss_dp": 1.2917020320892334, "train_loss_llm": 0.6377372741699219, "global_step": 211, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.2147033214569092, "train_loss_dp": 1.20652174949646, "train_loss_llm": 0.8181605339050293, "global_step": 212, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.9953945279121399, "train_loss_dp": 0.9913030862808228, "train_loss_llm": 0.4091458320617676, "global_step": 213, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.2621140480041504, "train_loss_dp": 1.2506753206253052, "train_loss_llm": 1.1438686847686768, "global_step": 214, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8768635988235474, "train_loss_dp": 0.8692286014556885, "train_loss_llm": 0.7634992599487305, "global_step": 215, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.1312974691390991, "train_loss_dp": 1.1301722526550293, "train_loss_llm": 0.11252593994140625, "global_step": 216, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8877076506614685, "train_loss_dp": 0.8807100057601929, "train_loss_llm": 0.6997666358947754, "global_step": 217, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.7655230164527893, "train_loss_dp": 0.752112627029419, "train_loss_llm": 1.3410396575927734, "global_step": 218, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8268309235572815, "train_loss_dp": 0.8216547966003418, "train_loss_llm": 0.5176153182983398, "global_step": 219, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.9836443066596985, "train_loss_dp": 0.9762389659881592, "train_loss_llm": 0.740534782409668, "global_step": 220, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.3871673345565796, "train_loss_dp": 1.3758190870285034, "train_loss_llm": 1.1348257064819336, "global_step": 221, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.9618462920188904, "train_loss_dp": 0.9548556804656982, "train_loss_llm": 0.6990604400634766, "global_step": 222, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.121734380722046, "train_loss_dp": 1.1161866188049316, "train_loss_llm": 0.5547780990600586, "global_step": 223, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.2717845439910889, "train_loss_dp": 1.2252352237701416, "train_loss_llm": 4.654937744140625, "global_step": 224, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.133670449256897, "train_loss_dp": 1.1292202472686768, "train_loss_llm": 0.445019006729126, "global_step": 225, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.1635395288467407, "train_loss_dp": 1.1458921432495117, "train_loss_llm": 1.764742374420166, "global_step": 226, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.790412425994873, "train_loss_dp": 0.7768189907073975, "train_loss_llm": 1.359344482421875, "global_step": 227, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.2196625471115112, "train_loss_dp": 1.2109549045562744, "train_loss_llm": 0.8707695007324219, "global_step": 228, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.0803388357162476, "train_loss_dp": 1.0543369054794312, "train_loss_llm": 2.600187301635742, "global_step": 229, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.9198564291000366, "train_loss_dp": 0.9066956043243408, "train_loss_llm": 1.3160839080810547, "global_step": 230, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.8806276321411133, "train_loss_dp": 0.8740400671958923, "train_loss_llm": 0.6587562561035156, "global_step": 231, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.7853339910507202, "train_loss_dp": 0.7752537727355957, "train_loss_llm": 1.0080232620239258, "global_step": 232, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.9136844873428345, "train_loss_dp": 0.829277753829956, "train_loss_llm": 8.440671920776367, "global_step": 233, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.8012468814849854, "train_loss_dp": 0.7941519021987915, "train_loss_llm": 0.7094950675964355, "global_step": 234, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.5320197343826294, "train_loss_dp": 1.488776445388794, "train_loss_llm": 4.324326515197754, "global_step": 235, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.2080738544464111, "train_loss_dp": 1.1741201877593994, "train_loss_llm": 3.395369529724121, "global_step": 236, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.4821357727050781, "train_loss_dp": 1.4457201957702637, "train_loss_llm": 3.6415634155273438, "global_step": 237, "epoch": 0, "lr": 3e-06} +{"train_loss": 2.016885280609131, "train_loss_dp": 1.2957777976989746, "train_loss_llm": 72.11074829101562, "global_step": 238, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.9761942028999329, "train_loss_dp": 0.9635788202285767, "train_loss_llm": 1.2615375518798828, "global_step": 239, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.3200069665908813, "train_loss_dp": 1.125038743019104, "train_loss_llm": 19.4968204498291, "global_step": 240, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.2333816289901733, "train_loss_dp": 1.2297680377960205, "train_loss_llm": 0.3613567352294922, "global_step": 241, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.0169427394866943, "train_loss_dp": 0.951324462890625, "train_loss_llm": 6.561830520629883, "global_step": 242, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.8573359847068787, "train_loss_dp": 0.8521511554718018, "train_loss_llm": 0.5184810161590576, "global_step": 243, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.0643607378005981, "train_loss_dp": 1.0499974489212036, "train_loss_llm": 1.4363293647766113, "global_step": 244, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.251783847808838, "train_loss_dp": 1.220577359199524, "train_loss_llm": 3.120647430419922, "global_step": 245, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9586256742477417, "train_loss_dp": 0.952906608581543, "train_loss_llm": 0.5719079971313477, "global_step": 246, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9674288034439087, "train_loss_dp": 0.9626787900924683, "train_loss_llm": 0.4749996066093445, "global_step": 247, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.1254202127456665, "train_loss_dp": 1.115891456604004, "train_loss_llm": 0.9528732299804688, "global_step": 248, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.1593478918075562, "train_loss_dp": 1.145406723022461, "train_loss_llm": 1.3941142559051514, "global_step": 249, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9617233276367188, "train_loss_dp": 0.9384018778800964, "train_loss_llm": 2.3321447372436523, "global_step": 250, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.0569924116134644, "train_loss_dp": 1.0468077659606934, "train_loss_llm": 1.0184690952301025, "global_step": 251, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9256843328475952, "train_loss_dp": 0.9084959030151367, "train_loss_llm": 1.7188434600830078, "global_step": 252, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9216443300247192, "train_loss_dp": 0.893805742263794, "train_loss_llm": 2.78385591506958, "global_step": 253, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.6723043322563171, "train_loss_dp": 0.6642416715621948, "train_loss_llm": 0.8062641620635986, "global_step": 254, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.908981442451477, "train_loss_dp": 0.8921409249305725, "train_loss_llm": 1.6840534210205078, "global_step": 255, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.204549789428711, "train_loss_dp": 1.198688268661499, "train_loss_llm": 0.5861563682556152, "global_step": 256, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.2233939170837402, "train_loss_dp": 1.2152185440063477, "train_loss_llm": 0.817535400390625, "global_step": 257, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.104799747467041, "train_loss_dp": 1.0953290462493896, "train_loss_llm": 0.9470711946487427, "global_step": 258, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.3139615058898926, "train_loss_dp": 1.3055317401885986, "train_loss_llm": 0.8429725170135498, "global_step": 259, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.8189157247543335, "train_loss_dp": 0.7952377200126648, "train_loss_llm": 2.3677990436553955, "global_step": 260, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.7308699488639832, "train_loss_dp": 0.7195430994033813, "train_loss_llm": 1.1326828002929688, "global_step": 261, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.7054136395454407, "train_loss_dp": 0.6950370669364929, "train_loss_llm": 1.037658452987671, "global_step": 262, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.9875133633613586, "train_loss_dp": 0.9790518283843994, "train_loss_llm": 0.8461538553237915, "global_step": 263, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.1116515398025513, "train_loss_dp": 1.099230408668518, "train_loss_llm": 1.2421073913574219, "global_step": 264, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.26888108253479, "train_loss_dp": 1.2592241764068604, "train_loss_llm": 0.9656886458396912, "global_step": 265, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.076149344444275, "train_loss_dp": 1.0639097690582275, "train_loss_llm": 1.2239608764648438, "global_step": 266, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.063284993171692, "train_loss_dp": 1.0430526733398438, "train_loss_llm": 2.0232338905334473, "global_step": 267, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.9694548845291138, "train_loss_dp": 0.9406946897506714, "train_loss_llm": 2.8760199546813965, "global_step": 268, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.8402442336082458, "train_loss_dp": 0.8313390612602234, "train_loss_llm": 0.8905158042907715, "global_step": 269, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.0363178253173828, "train_loss_dp": 1.0363178253173828, "train_loss_llm": 0.0, "global_step": 270, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.2708722352981567, "train_loss_dp": 1.249863624572754, "train_loss_llm": 2.1008596420288086, "global_step": 271, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.8101922273635864, "train_loss_dp": 0.8029913306236267, "train_loss_llm": 0.7200882434844971, "global_step": 272, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.270508050918579, "train_loss_dp": 1.2500911951065063, "train_loss_llm": 2.041682243347168, "global_step": 273, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.8519293069839478, "train_loss_dp": 0.8470282554626465, "train_loss_llm": 0.4901081323623657, "global_step": 274, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.206408143043518, "train_loss_dp": 1.1970850229263306, "train_loss_llm": 0.9323081970214844, "global_step": 275, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.2787306308746338, "train_loss_dp": 1.1633915901184082, "train_loss_llm": 11.533899307250977, "global_step": 276, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.938746452331543, "train_loss_dp": 0.9267393350601196, "train_loss_llm": 1.2007102966308594, "global_step": 277, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.0588295459747314, "train_loss_dp": 1.0540907382965088, "train_loss_llm": 0.473876953125, "global_step": 278, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.1287081241607666, "train_loss_dp": 1.1169074773788452, "train_loss_llm": 1.1800613403320312, "global_step": 279, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.1671936511993408, "train_loss_dp": 1.1598732471466064, "train_loss_llm": 0.7320423126220703, "global_step": 280, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.9664711356163025, "train_loss_dp": 0.9661685824394226, "train_loss_llm": 0.0302581787109375, "global_step": 281, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.8956195712089539, "train_loss_dp": 0.8922961354255676, "train_loss_llm": 0.33234232664108276, "global_step": 282, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.0822522640228271, "train_loss_dp": 1.0808215141296387, "train_loss_llm": 0.14307308197021484, "global_step": 283, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.9898412823677063, "train_loss_dp": 0.9549367427825928, "train_loss_llm": 3.4904537200927734, "global_step": 284, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.8137789964675903, "train_loss_dp": 0.8008929491043091, "train_loss_llm": 1.288604736328125, "global_step": 285, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.1449403762817383, "train_loss_dp": 1.1220868825912476, "train_loss_llm": 2.285353660583496, "global_step": 286, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.9789936542510986, "train_loss_dp": 0.9397944808006287, "train_loss_llm": 3.919917583465576, "global_step": 287, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.7996547818183899, "train_loss_dp": 0.7951436042785645, "train_loss_llm": 0.45111608505249023, "global_step": 288, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.1863093376159668, "train_loss_dp": 1.1545655727386475, "train_loss_llm": 3.1743812561035156, "global_step": 289, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.094476580619812, "train_loss_dp": 1.0789673328399658, "train_loss_llm": 1.5509250164031982, "global_step": 290, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.7286985516548157, "train_loss_dp": 0.695349395275116, "train_loss_llm": 3.3349151611328125, "global_step": 291, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.8538903594017029, "train_loss_dp": 0.8476069569587708, "train_loss_llm": 0.6283421516418457, "global_step": 292, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.096050500869751, "train_loss_dp": 1.081933617591858, "train_loss_llm": 1.4116897583007812, "global_step": 293, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.8915770649909973, "train_loss_dp": 0.880878210067749, "train_loss_llm": 1.069886565208435, "global_step": 294, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.1769020557403564, "train_loss_dp": 1.1708498001098633, "train_loss_llm": 0.6052254438400269, "global_step": 295, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.1362321376800537, "train_loss_dp": 1.1254382133483887, "train_loss_llm": 1.079390048980713, "global_step": 296, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.0254043340682983, "train_loss_dp": 1.0254043340682983, "train_loss_llm": 0.0, "global_step": 297, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.9390648007392883, "train_loss_dp": 0.9337210655212402, "train_loss_llm": 0.534372091293335, "global_step": 298, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.0619200468063354, "train_loss_dp": 0.9854391813278198, "train_loss_llm": 7.648087501525879, "global_step": 299, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.9273417592048645, "train_loss_dp": 0.9239466786384583, "train_loss_llm": 0.339508056640625, "global_step": 300, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.8679295778274536, "train_loss_dp": 0.8602054119110107, "train_loss_llm": 0.7724189758300781, "global_step": 301, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.2388479709625244, "train_loss_dp": 1.1727399826049805, "train_loss_llm": 6.61080265045166, "global_step": 302, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.9015404582023621, "train_loss_dp": 0.8882120847702026, "train_loss_llm": 1.3328378200531006, "global_step": 303, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.0708075761795044, "train_loss_dp": 1.0668206214904785, "train_loss_llm": 0.39869219064712524, "global_step": 304, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.9203828573226929, "train_loss_dp": 0.8907637596130371, "train_loss_llm": 2.961907386779785, "global_step": 305, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.0209006071090698, "train_loss_dp": 1.0103039741516113, "train_loss_llm": 1.059661865234375, "global_step": 306, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.0560258626937866, "train_loss_dp": 1.0481963157653809, "train_loss_llm": 0.7829568386077881, "global_step": 307, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.8696987628936768, "train_loss_dp": 0.853388786315918, "train_loss_llm": 1.6309967041015625, "global_step": 308, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.2426722049713135, "train_loss_dp": 1.226274013519287, "train_loss_llm": 1.639822006225586, "global_step": 309, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.0811240673065186, "train_loss_dp": 1.0267776250839233, "train_loss_llm": 5.434648513793945, "global_step": 310, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.268541932106018, "train_loss_dp": 1.2665159702301025, "train_loss_llm": 0.2025909423828125, "global_step": 311, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.1095284223556519, "train_loss_dp": 1.1064952611923218, "train_loss_llm": 0.3033146858215332, "global_step": 312, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.9223203659057617, "train_loss_dp": 0.9167141914367676, "train_loss_llm": 0.5606203079223633, "global_step": 313, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.2852535247802734, "train_loss_dp": 1.269548773765564, "train_loss_llm": 1.5704741477966309, "global_step": 314, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.7039891481399536, "train_loss_dp": 0.697694718837738, "train_loss_llm": 0.6294441223144531, "global_step": 315, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.4207193851470947, "train_loss_dp": 1.4016109704971313, "train_loss_llm": 1.9108467102050781, "global_step": 316, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.0881227254867554, "train_loss_dp": 1.0802347660064697, "train_loss_llm": 0.7887916564941406, "global_step": 317, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.4858653545379639, "train_loss_dp": 1.4580174684524536, "train_loss_llm": 2.784789800643921, "global_step": 318, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.7847555875778198, "train_loss_dp": 0.7751880884170532, "train_loss_llm": 0.9567484855651855, "global_step": 319, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.9809284806251526, "train_loss_dp": 0.9737030267715454, "train_loss_llm": 0.7225475311279297, "global_step": 320, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1537349224090576, "train_loss_dp": 1.1510746479034424, "train_loss_llm": 0.266021728515625, "global_step": 321, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 0.835584819316864, "train_loss_dp": 0.8233403563499451, "train_loss_llm": 1.2244462966918945, "global_step": 322, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1909435987472534, "train_loss_dp": 1.170578956604004, "train_loss_llm": 2.036468505859375, "global_step": 323, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.04839289188385, "train_loss_dp": 1.0379482507705688, "train_loss_llm": 1.0444637537002563, "global_step": 324, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1169261932373047, "train_loss_dp": 1.113403558731079, "train_loss_llm": 0.35226768255233765, "global_step": 325, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 0.9538261890411377, "train_loss_dp": 0.900374174118042, "train_loss_llm": 5.3451995849609375, "global_step": 326, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.8533211946487427, "train_loss_dp": 1.1018012762069702, "train_loss_llm": 75.15199279785156, "global_step": 327, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.2160426378250122, "train_loss_dp": 1.1747119426727295, "train_loss_llm": 4.133065223693848, "global_step": 328, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.5272111892700195, "train_loss_dp": 1.4971003532409668, "train_loss_llm": 3.011080741882324, "global_step": 329, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.198259949684143, "train_loss_dp": 1.1762311458587646, "train_loss_llm": 2.2028770446777344, "global_step": 330, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 0.9671088457107544, "train_loss_dp": 0.9570469856262207, "train_loss_llm": 1.0061886310577393, "global_step": 331, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1578236818313599, "train_loss_dp": 1.090648889541626, "train_loss_llm": 6.717479705810547, "global_step": 332, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.2753055095672607, "train_loss_dp": 1.2596111297607422, "train_loss_llm": 1.569443702697754, "global_step": 333, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.244830846786499, "train_loss_dp": 1.2119802236557007, "train_loss_llm": 3.2850570678710938, "global_step": 334, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.2530181407928467, "train_loss_dp": 1.2431042194366455, "train_loss_llm": 0.9913945198059082, "global_step": 335, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.028684139251709, "train_loss_dp": 1.0209881067276, "train_loss_llm": 0.7696084976196289, "global_step": 336, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.2703415155410767, "train_loss_dp": 1.2386189699172974, "train_loss_llm": 3.172260284423828, "global_step": 337, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.9917907118797302, "train_loss_dp": 0.9633889198303223, "train_loss_llm": 2.840177536010742, "global_step": 338, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.2144412994384766, "train_loss_dp": 1.1925339698791504, "train_loss_llm": 2.19073486328125, "global_step": 339, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.1099491119384766, "train_loss_dp": 1.0976893901824951, "train_loss_llm": 1.225975513458252, "global_step": 340, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.9008839130401611, "train_loss_dp": 0.8591746687889099, "train_loss_llm": 4.170927047729492, "global_step": 341, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.1456151008605957, "train_loss_dp": 1.136354923248291, "train_loss_llm": 0.9260196685791016, "global_step": 342, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.3753620386123657, "train_loss_dp": 1.3299955129623413, "train_loss_llm": 4.536657333374023, "global_step": 343, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.505616307258606, "train_loss_dp": 1.4726543426513672, "train_loss_llm": 3.296200752258301, "global_step": 344, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.036675214767456, "train_loss_dp": 1.0265394449234009, "train_loss_llm": 1.0135817527770996, "global_step": 345, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.1253588199615479, "train_loss_dp": 1.1137542724609375, "train_loss_llm": 1.1604557037353516, "global_step": 346, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.9643039107322693, "train_loss_dp": 0.9567458629608154, "train_loss_llm": 0.7558053731918335, "global_step": 347, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.920651912689209, "train_loss_dp": 0.9127265214920044, "train_loss_llm": 0.7925376892089844, "global_step": 348, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.9552338719367981, "train_loss_dp": 0.9501639008522034, "train_loss_llm": 0.5069942474365234, "global_step": 349, "epoch": 0, "lr": 4.4e-06} diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/train.log b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/train.log new file mode 100644 index 0000000000000000000000000000000000000000..fc641c1b867303bc900d95ae9099aab6378e494a --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/train.log @@ -0,0 +1,14 @@ +[2026-04-14 06:26:22,319][numexpr.utils][INFO] - Note: detected 144 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable. +[2026-04-14 06:26:22,319][numexpr.utils][INFO] - Note: NumExpr detected 144 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16. +[2026-04-14 06:26:22,319][numexpr.utils][INFO] - NumExpr defaulting to 16 threads. +[2026-04-14 06:26:24,562][datasets][INFO] - PyTorch version 2.2.2 available. +[2026-04-14 06:26:24,562][datasets][INFO] - TensorFlow version 2.15.1 available. +[2026-04-14 06:26:24,563][datasets][INFO] - JAX version 0.4.30 available. +[2026-04-14 06:26:26,423][llmbc.model.diffusion.conditional_unet1d][INFO] - number of parameters: 6.501479e+07 +[2026-04-14 06:26:30,451][root][INFO] - running build_ext +[2026-04-14 06:26:30,453][root][INFO] - building 'mujoco_py.cymj' extension +[2026-04-14 06:26:30,453][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /venv/llm-bc/include -I/venv/llm-bc/include -fPIC -O2 -isystem /venv/llm-bc/include -fPIC -I/venv/llm-bc/lib/python3.9/site-packages/mujoco_py -I/root/.mujoco/mujoco210/include -I/venv/llm-bc/lib/python3.9/site-packages/numpy/core/include -I/venv/llm-bc/include/python3.9 -c /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.c -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.o -fopenmp -w +[2026-04-14 06:27:13,374][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /venv/llm-bc/include -I/venv/llm-bc/include -fPIC -O2 -isystem /venv/llm-bc/include -fPIC -I/venv/llm-bc/lib/python3.9/site-packages/mujoco_py -I/root/.mujoco/mujoco210/include -I/venv/llm-bc/lib/python3.9/site-packages/numpy/core/include -I/venv/llm-bc/include/python3.9 -c /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.c -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.o -fopenmp -w +[2026-04-14 06:27:13,505][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -shared -Wl,-rpath,/venv/llm-bc/lib -Wl,-rpath-link,/venv/llm-bc/lib -L/venv/llm-bc/lib -L/venv/llm-bc/lib -Wl,-rpath,/venv/llm-bc/lib -Wl,-rpath-link,/venv/llm-bc/lib -L/venv/llm-bc/lib /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.o -L/root/.mujoco/mujoco210/bin -Wl,--enable-new-dtags,-rpath,/root/.mujoco/mujoco210/bin -lmujoco210 -lglewosmesa -lOSMesa -lGL -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/lib.linux-x86_64-cpython-39/mujoco_py/cymj.cpython-39-x86_64-linux-gnu.so -fopenmp +[2026-04-14 06:27:57,107][absl][INFO] - MUJOCO_GL=osmesa, attempting to import specified OpenGL backend. +[2026-04-14 06:27:57,117][absl][INFO] - MuJoCo library version is: 2.3.7 diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/config.yaml b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..467080807b0dac904faead61d19f5d8126e2eda4 --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/config.yaml @@ -0,0 +1,304 @@ +_target_: + value: llmbc.workspace.train_llm_diffusion_unet_lowdim_workspace.TrainLLMDiffusionUnetLowdimWorkspace +_wandb: + value: + cli_version: 0.18.6 + m: [] + python_version: 3.9.25 + t: + "1": + - 1 + - 2 + - 3 + - 5 + - 11 + - 12 + - 41 + - 49 + - 50 + - 51 + - 53 + - 55 + - 71 + - 83 + - 95 + - 98 + - 100 + - 105 + "2": + - 1 + - 2 + - 3 + - 5 + - 11 + - 12 + - 41 + - 49 + - 50 + - 51 + - 53 + - 55 + - 71 + - 83 + - 95 + - 98 + - 100 + - 105 + "3": + - 13 + - 15 + - 16 + - 23 + - 55 + - 61 + "4": 3.9.25 + "5": 0.18.6 + "6": 4.47.1 + "8": + - 5 + "12": 0.18.6 + "13": linux-x86_64 +action_dim: + value: 4 +checkpoint: + value: + save_last_ckpt: true + save_last_snapshot: false + topk: + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + k: 5 + mode: max + monitor_key: test_success_rate +dataloader: + value: + batch_size: 16 + num_workers: 0 + persistent_workers: false + pin_memory: false + shuffle: true +ema: + value: + _target_: llmbc.model.diffusion.ema_model.EMAModel + inv_gamma: 1 + max_value: 0.9999 + min_value: 0 + power: 0.75 + update_after_step: 0 +exp_name: + value: default +horizon: + value: 1 +keypoint_visible_rate: + value: 1 +llm: + value: + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + finetune_mode: orig + hydra: + job: + override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct + run: + dir: data/outputs/2026.04.14/06.26.20_HuggingFaceTB/SmolLM2-135M-Instruct + llm_mode: ete-finetuned + lora_config: + bias: none + lora_alpha: 64 + lora_dropout: 0.05 + r: 32 + task_type: CAUSAL_LM + max_length: 100 + model_name: SmolLM2-135M-Instruct + name: HuggingFaceTB/SmolLM2-135M-Instruct + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + use_joint_mlp_projector: true + use_quantization: false +llm_do_sample: + value: false +llm_orig_expert_feedback: + value: true +logging: + value: + group: null + id: null + mode: online + name: 2026.04.14-06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2 + project: sweep-v2-training + resume: true + tags: + - train_llm_diffusion_unet_lowdim + - sweep-v2 + - default +model_name: + value: HuggingFaceTB/SmolLM2-135M-Instruct +multi_run: + value: + run_dir: data/outputs/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2 + wandb_name_base: 2026.04.14-06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2 +n_action_steps: + value: 1 +n_latency_steps: + value: 0 +n_obs_steps: + value: 1 +name: + value: train_llm_diffusion_unet_lowdim +obs_as_global_cond: + value: true +obs_as_local_cond: + value: false +obs_dim: + value: 9 +optimizer: + value: + _target_: torch.optim.AdamW + betas: + - 0.95 + - 0.999 + eps: 1e-08 + lr: 0.0001 + weight_decay: 1e-06 +output_dir: + value: /workspace/LLM-BC/data/outputs/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2 +past_action_visible: + value: false +policy: + value: + _target_: llmbc.policy.llm_diffusion_unet_lowdim_policy.LLMDiffusionUnetLowdimPolicy + action_dim: 4 + horizon: 1 + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + action_dim: 4 + cfg: + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + finetune_mode: orig + hydra: + job: + override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct + run: + dir: data/outputs/2026.04.14/06.26.20_HuggingFaceTB/SmolLM2-135M-Instruct + llm_mode: ete-finetuned + lora_config: + bias: none + lora_alpha: 64 + lora_dropout: 0.05 + r: 32 + task_type: CAUSAL_LM + max_length: 100 + model_name: SmolLM2-135M-Instruct + name: HuggingFaceTB/SmolLM2-135M-Instruct + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + use_joint_mlp_projector: true + use_quantization: false + horizon: 1 + n_action_steps: 1 + n_obs_steps: 1 + obs_dim: 9 + task_id: sweep-v2 + loss_dp_weight: 1 + loss_llm_weight: 0.01 + model: + _target_: llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D + cond_predict_scale: true + diffusion_step_embed_dim: 256 + down_dims: + - 256 + - 512 + - 1024 + global_cond_dim: 9 + input_dim: 4 + kernel_size: 5 + local_cond_dim: null + n_groups: 8 + n_action_steps: 1 + n_obs_steps: 1 + noise_scheduler: + _target_: diffusers.schedulers.scheduling_ddpm.DDPMScheduler + beta_end: 0.02 + beta_schedule: squaredcos_cap_v2 + beta_start: 0.0001 + clip_sample: true + num_train_timesteps: 100 + prediction_type: epsilon + variance_type: fixed_small + normalize_llm_loss: true + num_inference_steps: 100 + oa_step_convention: true + obs_as_global_cond: true + obs_as_local_cond: false + obs_dim: 9 + pred_action_steps_only: false + reweight_llm_loss: true +pred_action_steps_only: + value: false +task: + value: + action_dim: 4 + dataset: + _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset + data_path: datasets/sweep-v2-mix(csp5).pt + data_path2: datasets/sweep-v2.pt + dummy_normalizer: false + horizon: 1 + obs_eef_target: true + pad_after: 0 + pad_before: 0 + use_manual_normalizer: false + val_ratio: 0.1 + env_runner: + _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner + discount: 0.9 + env_name: llf-metaworld-sweep-v2 + feedback_type: + - hp + - hn + - fp + instruction_type: b + max_steps: 30 + n_action_steps: 1 + n_envs: 10 + n_obs_steps: 1 + n_test: 50 + n_train: 10 + visual: false + instructor: + _target_: llmbc.translator.instructor.metaworld_instructor.sweep_v2_instructor.SweepV2Instructor + name: sweep-v2 + obs_dim: 9 +task_name: + value: sweep-v2 +training: + value: + checkpoint_every: 5 + debug: false + device: cuda:0 + gradient_accumulate_every: 16 + lr_scheduler: cosine + lr_warmup_steps: 500 + max_train_steps: null + max_val_steps: null + num_epochs: 1001 + resume: true + rollout_every: 5 + sample_every: 5 + seed: 42 + tqdm_interval_sec: 1 + use_ema: true + val_every: 1 +val_dataloader: + value: + batch_size: 16 + num_workers: 0 + persistent_workers: false + pin_memory: false + shuffle: false diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/output.log b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/output.log new file mode 100644 index 0000000000000000000000000000000000000000..c142970b4fbc2909243cac0281ae330807f49f84 --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/output.log @@ -0,0 +1,56 @@ +Traceback (most recent call last): + File "/workspace/LLM-BC/./train.py", line 35, in + main() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/main.py", line 90, in decorated_main + _run_hydra( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 389, in _run_hydra + _run_app( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 452, in _run_app + run_and_report( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 213, in run_and_report + return func() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 453, in + lambda: hydra.run( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/hydra.py", line 119, in run + ret = run_job( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/workspace/LLM-BC/./train.py", line 32, in main + workspace.run() + File "/workspace/LLM-BC/llmbc/workspace/train_llm_diffusion_unet_lowdim_workspace.py", line 199, in run + raw_loss, raw_loss_dp, raw_loss_llm = self.model.compute_loss(batch) + File "/workspace/LLM-BC/llmbc/policy/llm_diffusion_unet_lowdim_policy.py", line 320, in compute_loss + loss_ce = self.llm_discriminator.compute_similarity_loss( + File "/workspace/LLM-BC/llmbc/discriminator/llm_ce_discriminator.py", line 56, in compute_similarity_loss + outputs, label_ids = self.llm_translator.forward( + File "/workspace/LLM-BC/llmbc/translator/llm_translator.py", line 315, in forward + label_padding = torch.ones(max_length - len(labels_ids[i]), dtype=labels_ids[i].dtype).to("cuda") * IGNORE_INDEX +KeyboardInterrupt +Traceback (most recent call last): + File "/workspace/LLM-BC/./train.py", line 35, in + main() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/main.py", line 90, in decorated_main + _run_hydra( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 389, in _run_hydra + _run_app( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 452, in _run_app + run_and_report( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 213, in run_and_report + return func() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 453, in + lambda: hydra.run( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/hydra.py", line 119, in run + ret = run_job( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/workspace/LLM-BC/./train.py", line 32, in main + workspace.run() + File "/workspace/LLM-BC/llmbc/workspace/train_llm_diffusion_unet_lowdim_workspace.py", line 199, in run + raw_loss, raw_loss_dp, raw_loss_llm = self.model.compute_loss(batch) + File "/workspace/LLM-BC/llmbc/policy/llm_diffusion_unet_lowdim_policy.py", line 320, in compute_loss + loss_ce = self.llm_discriminator.compute_similarity_loss( + File "/workspace/LLM-BC/llmbc/discriminator/llm_ce_discriminator.py", line 56, in compute_similarity_loss + outputs, label_ids = self.llm_translator.forward( + File "/workspace/LLM-BC/llmbc/translator/llm_translator.py", line 315, in forward + label_padding = torch.ones(max_length - len(labels_ids[i]), dtype=labels_ids[i].dtype).to("cuda") * IGNORE_INDEX +KeyboardInterrupt diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/requirements.txt b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..f18b63306b50dded477ccac6858260d859b2a206 --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/requirements.txt @@ -0,0 +1,864 @@ +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +llmbc==0.0.0 +llmbc==0.0.0 +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +autocommand==2.2.2 +backports.tarfile==1.2.0 +importlib_metadata==8.0.0 +inflect==7.3.1 +jaraco.collections==5.1.0 +jaraco.context==5.3.0 +jaraco.functools==4.0.1 +jaraco.text==3.12.1 +more-itertools==10.3.0 +packaging==24.2 +platformdirs==4.2.2 +tomli==2.0.1 +typeguard==4.3.0 +typing_extensions==4.12.2 +wheel==0.45.1 +zipp==3.19.2 diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/wandb-metadata.json b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/wandb-metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..3ba643f2adbbda0a521e803057ebbbc483ea6d2d --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/wandb-metadata.json @@ -0,0 +1,56 @@ +{ + "os": "Linux-5.15.0-168-generic-x86_64-with-glibc2.39", + "python": "3.9.25", + "startedAt": "2026-04-14T06:27:58.079904Z", + "args": [ + "--config-path", + "config/mix_data", + "--config-name", + "llmdp_sweep-v2_mix(csp5).yaml", + "policy.loss_llm_weight=1.0e-2" + ], + "program": "/workspace/LLM-BC/./train.py", + "codePath": "train.py", + "git": { + "remote": "https://github.com/CHYang25/LLM-BC.git", + "commit": "16b534f5ac2111b9cbfa638ab62d7944bff711d2" + }, + "email": "chris920325@gmail.com", + "root": "/workspace/LLM-BC/data/outputs/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2", + "host": "c8ef52649900", + "username": "root", + "executable": "/venv/llm-bc/bin/python3", + "codePathLocal": "train.py", + "cpu_count": 72, + "cpu_count_logical": 144, + "gpu": "NVIDIA GeForce RTX 4090", + "gpu_count": 2, + "disk": { + "/": { + "total": "545460846592", + "used": "352995897344" + } + }, + "memory": { + "total": "810942898176" + }, + "cpu": { + "count": 72, + "countLogical": 144 + }, + "gpu_nvidia": [ + { + "name": "NVIDIA GeForce RTX 4090", + "memoryTotal": "25757220864", + "cudaCores": 16384, + "architecture": "Ada" + }, + { + "name": "NVIDIA GeForce RTX 4090", + "memoryTotal": "25757220864", + "cudaCores": 16384, + "architecture": "Ada" + } + ], + "cudaVersion": "12.8" +} \ No newline at end of file diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/wandb-summary.json b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/wandb-summary.json new file mode 100644 index 0000000000000000000000000000000000000000..9d6b07d97e38772d94508ae24e1411b2755acc6e --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/files/wandb-summary.json @@ -0,0 +1 @@ +{"_runtime":122.944232842,"_step":349,"train_loss":0.9552338719367981,"_wandb":{"runtime":122},"lr":4.4e-06,"_timestamp":1.7761482008848052e+09,"train_loss_dp":0.9501639008522034,"epoch":0,"global_step":349,"train_loss_llm":0.5069942474365234} \ No newline at end of file diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/run-yrc5uqpn.wandb b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/run-yrc5uqpn.wandb new file mode 100644 index 0000000000000000000000000000000000000000..39134f394d4978eadeb1475bf5b5c81aff076740 --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062758-yrc5uqpn/run-yrc5uqpn.wandb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a12b8c2c9675c1de5d0b0c99f3f711dfbb88d0cfd9336fa2f24e859fe83d716 +size 327680 diff --git a/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json new file mode 100644 index 0000000000000000000000000000000000000000..625efb5f2bc77b531899fdefde3c73eb7d046315 --- /dev/null +++ b/2026.04.14/06.26.20_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json @@ -0,0 +1 @@ +{"run_id": "yrc5uqpn"} \ No newline at end of file diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b14b2d454108734c90d7c2448f6866a4b9a4e78d --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml @@ -0,0 +1,193 @@ +name: train_llm_diffusion_unet_lowdim +_target_: llmbc.workspace.train_llm_diffusion_unet_lowdim_workspace.TrainLLMDiffusionUnetLowdimWorkspace +obs_dim: ${task.obs_dim} +action_dim: ${task.action_dim} +task_name: ${task.name} +exp_name: default +model_name: ${llm.name} +horizon: 1 +n_obs_steps: 1 +n_action_steps: 1 +n_latency_steps: 0 +past_action_visible: false +keypoint_visible_rate: 1.0 +obs_as_local_cond: false +obs_as_global_cond: true +pred_action_steps_only: false +llm_orig_expert_feedback: true +llm_do_sample: false +policy: + _target_: llmbc.policy.llm_diffusion_unet_lowdim_policy.LLMDiffusionUnetLowdimPolicy + model: + _target_: llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D + input_dim: '${eval: ${task.action_dim} if ${obs_as_local_cond} or ${obs_as_global_cond} + else ${task.obs_dim} + ${task.action_dim}}' + local_cond_dim: '${eval: ${task.obs_dim} if ${obs_as_local_cond} else None}' + global_cond_dim: '${eval: ${task.obs_dim}*${n_obs_steps} if ${obs_as_global_cond} + else None}' + diffusion_step_embed_dim: 256 + down_dims: + - 256 + - 512 + - 1024 + kernel_size: 5 + n_groups: 8 + cond_predict_scale: true + noise_scheduler: + _target_: diffusers.schedulers.scheduling_ddpm.DDPMScheduler + num_train_timesteps: 100 + beta_start: 0.0001 + beta_end: 0.02 + beta_schedule: squaredcos_cap_v2 + variance_type: fixed_small + clip_sample: true + prediction_type: epsilon + horizon: ${horizon} + obs_dim: ${obs_dim} + action_dim: ${action_dim} + n_action_steps: ${eval:'${n_action_steps}+${n_latency_steps}'} + n_obs_steps: ${n_obs_steps} + num_inference_steps: 100 + obs_as_local_cond: ${obs_as_local_cond} + obs_as_global_cond: ${obs_as_global_cond} + pred_action_steps_only: ${pred_action_steps_only} + oa_step_convention: true + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + task_id: ${task_name} + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + cfg: ${llm} + obs_dim: ${obs_dim} + action_dim: ${action_dim} + horizon: ${horizon} + n_obs_steps: ${n_obs_steps} + n_action_steps: ${eval:'${n_action_steps}+${n_latency_steps}'} + loss_dp_weight: 1.0 + loss_llm_weight: 0.001 + normalize_llm_loss: true + reweight_llm_loss: true +ema: + _target_: llmbc.model.diffusion.ema_model.EMAModel + update_after_step: 0 + inv_gamma: 1.0 + power: 0.75 + min_value: 0.0 + max_value: 0.9999 +dataloader: + batch_size: 16 + num_workers: 0 + shuffle: true + pin_memory: false + persistent_workers: false +val_dataloader: + batch_size: 16 + num_workers: 0 + shuffle: false + pin_memory: false + persistent_workers: false +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + betas: + - 0.95 + - 0.999 + eps: 1.0e-08 + weight_decay: 1.0e-06 +training: + device: cuda:0 + seed: 42 + debug: false + resume: true + lr_scheduler: cosine + lr_warmup_steps: 500 + num_epochs: 1001 + gradient_accumulate_every: 16 + use_ema: true + rollout_every: 5 + checkpoint_every: 5 + val_every: 1 + sample_every: 5 + max_train_steps: null + max_val_steps: null + tqdm_interval_sec: 1.0 +logging: + project: ${task.name}-training + resume: true + mode: online + name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} + tags: + - ${name} + - ${task_name} + - ${exp_name} + id: null + group: null +checkpoint: + topk: + monitor_key: test_success_rate + mode: max + k: 5 + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + save_last_ckpt: true + save_last_snapshot: false +multi_run: + run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} +task: + name: sweep-v2 + obs_dim: 9 + action_dim: 4 + env_runner: + _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner + env_name: llf-metaworld-sweep-v2 + n_train: 10 + n_test: 50 + n_envs: 10 + max_steps: 30 + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + instruction_type: b + feedback_type: + - hp + - hn + - fp + visual: false + discount: 0.9 + dataset: + _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset + data_path: datasets/sweep-v2-mix(csp5).pt + data_path2: datasets/sweep-v2.pt + horizon: ${horizon} + pad_before: ${eval:'${n_obs_steps}-1'} + pad_after: ${eval:'${n_action_steps}-1'} + obs_eef_target: true + use_manual_normalizer: false + val_ratio: 0.1 + dummy_normalizer: false + instructor: + _target_: llmbc.translator.instructor.metaworld_instructor.sweep_v2_instructor.SweepV2Instructor +llm: + name: HuggingFaceTB/SmolLM2-135M-Instruct + model_name: SmolLM2-135M-Instruct + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + use_quantization: false + use_joint_mlp_projector: true + llm_mode: ete-finetuned + finetune_mode: orig + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + max_length: 100 + lora_config: + r: 32 + lora_alpha: 64 + lora_dropout: 0.05 + bias: none + task_type: CAUSAL_LM + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + hydra: + job: + override_dirname: ${model_name} + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${model_name} diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f57531e53bf1440ebf484c14fd76323781e48258 --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml @@ -0,0 +1,155 @@ +hydra: + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + sweep: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - policy.loss_llm_weight=1.0e-3 + job: + name: train + chdir: null + override_dirname: policy.loss_llm_weight=1.0e-3 + id: ??? + num: ??? + config_name: llmdp_sweep-v2_mix(csp5).yaml + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.2.0 + version_base: '1.2' + cwd: /workspace/LLM-BC + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /workspace/LLM-BC/config/mix_data + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /workspace/LLM-BC/data/outputs/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..dd7296ef5c15eabe738b29ec20bc7985c262ec84 --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml @@ -0,0 +1 @@ +- policy.loss_llm_weight=1.0e-3 diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt new file mode 100644 index 0000000000000000000000000000000000000000..5858a60f2b9b5cb450fd598c7bb65a4ee1d59ff1 --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt @@ -0,0 +1,351 @@ +{"train_loss": 1.2113080024719238, "train_loss_dp": 1.2109837532043457, "train_loss_llm": 0.32422637939453125, "global_step": 0, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.5589793920516968, "train_loss_dp": 1.5555988550186157, "train_loss_llm": 3.3805484771728516, "global_step": 1, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 0.845954954624176, "train_loss_dp": 0.8444761037826538, "train_loss_llm": 1.4788703918457031, "global_step": 2, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.5680959224700928, "train_loss_dp": 1.567467212677002, "train_loss_llm": 0.6287602186203003, "global_step": 3, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.2168755531311035, "train_loss_dp": 1.2161624431610107, "train_loss_llm": 0.7131385803222656, "global_step": 4, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.6049288511276245, "train_loss_dp": 1.6041865348815918, "train_loss_llm": 0.7423383593559265, "global_step": 5, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.3252512216567993, "train_loss_dp": 1.3234602212905884, "train_loss_llm": 1.7909822463989258, "global_step": 6, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.193090558052063, "train_loss_dp": 1.1930253505706787, "train_loss_llm": 0.06521368026733398, "global_step": 7, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.0087451934814453, "train_loss_dp": 1.006334900856018, "train_loss_llm": 2.410350799560547, "global_step": 8, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.3536158800125122, "train_loss_dp": 1.3523192405700684, "train_loss_llm": 1.2966029644012451, "global_step": 9, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.3731826543807983, "train_loss_dp": 1.3722383975982666, "train_loss_llm": 0.9442574977874756, "global_step": 10, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.2412104606628418, "train_loss_dp": 1.2402263879776, "train_loss_llm": 0.9840337038040161, "global_step": 11, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.2120298147201538, "train_loss_dp": 1.2112371921539307, "train_loss_llm": 0.792670726776123, "global_step": 12, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.123581886291504, "train_loss_dp": 1.1232653856277466, "train_loss_llm": 0.3164515495300293, "global_step": 13, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.104956030845642, "train_loss_dp": 1.1038504838943481, "train_loss_llm": 1.1055290699005127, "global_step": 14, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 1.507478952407837, "train_loss_dp": 1.5052738189697266, "train_loss_llm": 2.205087661743164, "global_step": 15, "epoch": 0, "lr": 2.0000000000000002e-07} +{"train_loss": 0.8694500923156738, "train_loss_dp": 0.8685603141784668, "train_loss_llm": 0.8897576332092285, "global_step": 16, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.2379846572875977, "train_loss_dp": 1.23750901222229, "train_loss_llm": 0.47563648223876953, "global_step": 17, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 0.9851002097129822, "train_loss_dp": 0.9839596748352051, "train_loss_llm": 1.1405296325683594, "global_step": 18, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.2536287307739258, "train_loss_dp": 1.2529140710830688, "train_loss_llm": 0.7146296501159668, "global_step": 19, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.1880640983581543, "train_loss_dp": 1.1880640983581543, "train_loss_llm": 0.0, "global_step": 20, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.3638073205947876, "train_loss_dp": 1.3630330562591553, "train_loss_llm": 0.7742547988891602, "global_step": 21, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.1094576120376587, "train_loss_dp": 1.1084274053573608, "train_loss_llm": 1.0301847457885742, "global_step": 22, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.1761385202407837, "train_loss_dp": 1.1755229234695435, "train_loss_llm": 0.6155905723571777, "global_step": 23, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.310711145401001, "train_loss_dp": 1.3082859516143799, "train_loss_llm": 2.4251956939697266, "global_step": 24, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.389030933380127, "train_loss_dp": 1.3877439498901367, "train_loss_llm": 1.286992073059082, "global_step": 25, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.2076236009597778, "train_loss_dp": 1.206101417541504, "train_loss_llm": 1.5222282409667969, "global_step": 26, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 0.8233837485313416, "train_loss_dp": 0.8226487636566162, "train_loss_llm": 0.7349624633789062, "global_step": 27, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 0.9075433611869812, "train_loss_dp": 0.9067178964614868, "train_loss_llm": 0.8254804611206055, "global_step": 28, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.2564138174057007, "train_loss_dp": 1.2447782754898071, "train_loss_llm": 11.635519027709961, "global_step": 29, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.182792067527771, "train_loss_dp": 1.1809906959533691, "train_loss_llm": 1.8013277053833008, "global_step": 30, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.384852647781372, "train_loss_dp": 1.3838200569152832, "train_loss_llm": 1.0326085090637207, "global_step": 31, "epoch": 0, "lr": 4.0000000000000003e-07} +{"train_loss": 1.0001124143600464, "train_loss_dp": 0.9743348956108093, "train_loss_llm": 25.777488708496094, "global_step": 32, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.0076208114624023, "train_loss_dp": 1.0061602592468262, "train_loss_llm": 1.460500717163086, "global_step": 33, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.1158424615859985, "train_loss_dp": 1.1038153171539307, "train_loss_llm": 12.027143478393555, "global_step": 34, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 0.7538604736328125, "train_loss_dp": 0.7511436343193054, "train_loss_llm": 2.716831684112549, "global_step": 35, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.2947951555252075, "train_loss_dp": 1.294024109840393, "train_loss_llm": 0.7710599899291992, "global_step": 36, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.038709282875061, "train_loss_dp": 1.0373194217681885, "train_loss_llm": 1.3898152112960815, "global_step": 37, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.2957764863967896, "train_loss_dp": 1.295128345489502, "train_loss_llm": 0.648097038269043, "global_step": 38, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.4637757539749146, "train_loss_dp": 1.462242841720581, "train_loss_llm": 1.5329017639160156, "global_step": 39, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.0012942552566528, "train_loss_dp": 1.0005671977996826, "train_loss_llm": 0.727025032043457, "global_step": 40, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.130832314491272, "train_loss_dp": 1.130028247833252, "train_loss_llm": 0.8040447235107422, "global_step": 41, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.0291799306869507, "train_loss_dp": 1.0285847187042236, "train_loss_llm": 0.5952534675598145, "global_step": 42, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.1830793619155884, "train_loss_dp": 1.1820952892303467, "train_loss_llm": 0.9840414524078369, "global_step": 43, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.180253028869629, "train_loss_dp": 1.1782448291778564, "train_loss_llm": 2.0081424713134766, "global_step": 44, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.1321213245391846, "train_loss_dp": 1.1313648223876953, "train_loss_llm": 0.7564888000488281, "global_step": 45, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.3130393028259277, "train_loss_dp": 1.3093225955963135, "train_loss_llm": 3.7166566848754883, "global_step": 46, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.2966513633728027, "train_loss_dp": 1.29621422290802, "train_loss_llm": 0.43712055683135986, "global_step": 47, "epoch": 0, "lr": 6.000000000000001e-07} +{"train_loss": 1.7168747186660767, "train_loss_dp": 1.7141518592834473, "train_loss_llm": 2.7229061126708984, "global_step": 48, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.5162822008132935, "train_loss_dp": 1.5114319324493408, "train_loss_llm": 4.850288391113281, "global_step": 49, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.2879774570465088, "train_loss_dp": 1.2822577953338623, "train_loss_llm": 5.719704627990723, "global_step": 50, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.0831292867660522, "train_loss_dp": 1.0822336673736572, "train_loss_llm": 0.8956203460693359, "global_step": 51, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.3481751680374146, "train_loss_dp": 1.3473753929138184, "train_loss_llm": 0.7997703552246094, "global_step": 52, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.3952451944351196, "train_loss_dp": 1.3946921825408936, "train_loss_llm": 0.55296790599823, "global_step": 53, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.0116087198257446, "train_loss_dp": 1.0101635456085205, "train_loss_llm": 1.4451277256011963, "global_step": 54, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.2406364679336548, "train_loss_dp": 1.2388842105865479, "train_loss_llm": 1.7522797584533691, "global_step": 55, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.2297825813293457, "train_loss_dp": 1.2297825813293457, "train_loss_llm": 0.0, "global_step": 56, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.4288654327392578, "train_loss_dp": 1.4281561374664307, "train_loss_llm": 0.7093353271484375, "global_step": 57, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.7569656372070312, "train_loss_dp": 1.7569656372070312, "train_loss_llm": 0.0, "global_step": 58, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 0.9110017418861389, "train_loss_dp": 0.9106008410453796, "train_loss_llm": 0.4008868932723999, "global_step": 59, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.0586212873458862, "train_loss_dp": 1.0581459999084473, "train_loss_llm": 0.47524261474609375, "global_step": 60, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.299753189086914, "train_loss_dp": 1.2989509105682373, "train_loss_llm": 0.8022832870483398, "global_step": 61, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.109700083732605, "train_loss_dp": 1.1095507144927979, "train_loss_llm": 0.14933395385742188, "global_step": 62, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.0962027311325073, "train_loss_dp": 1.0956658124923706, "train_loss_llm": 0.53692626953125, "global_step": 63, "epoch": 0, "lr": 8.000000000000001e-07} +{"train_loss": 1.0299979448318481, "train_loss_dp": 1.028838872909546, "train_loss_llm": 1.1591196060180664, "global_step": 64, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.268467664718628, "train_loss_dp": 1.266757845878601, "train_loss_llm": 1.7098541259765625, "global_step": 65, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.2627112865447998, "train_loss_dp": 1.2617413997650146, "train_loss_llm": 0.9699356555938721, "global_step": 66, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 0.9442915320396423, "train_loss_dp": 0.9414495825767517, "train_loss_llm": 2.841965675354004, "global_step": 67, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.182284951210022, "train_loss_dp": 1.1800861358642578, "train_loss_llm": 2.1988537311553955, "global_step": 68, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.2904601097106934, "train_loss_dp": 1.2876392602920532, "train_loss_llm": 2.8208560943603516, "global_step": 69, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.1859405040740967, "train_loss_dp": 1.1841027736663818, "train_loss_llm": 1.837789535522461, "global_step": 70, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.3444772958755493, "train_loss_dp": 1.3439511060714722, "train_loss_llm": 0.526209831237793, "global_step": 71, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 0.9198011159896851, "train_loss_dp": 0.9179220199584961, "train_loss_llm": 1.8790779113769531, "global_step": 72, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.1377739906311035, "train_loss_dp": 1.135314702987671, "train_loss_llm": 2.459256172180176, "global_step": 73, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.3559603691101074, "train_loss_dp": 1.355522871017456, "train_loss_llm": 0.4374455213546753, "global_step": 74, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.856017827987671, "train_loss_dp": 1.8555402755737305, "train_loss_llm": 0.4775686264038086, "global_step": 75, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.4149651527404785, "train_loss_dp": 1.4140968322753906, "train_loss_llm": 0.868317723274231, "global_step": 76, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.253494381904602, "train_loss_dp": 1.2519232034683228, "train_loss_llm": 1.5712180137634277, "global_step": 77, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 0.9185299873352051, "train_loss_dp": 0.9169398546218872, "train_loss_llm": 1.590118646621704, "global_step": 78, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 0.7954443693161011, "train_loss_dp": 0.792466402053833, "train_loss_llm": 2.9779510498046875, "global_step": 79, "epoch": 0, "lr": 1.0000000000000002e-06} +{"train_loss": 1.00989830493927, "train_loss_dp": 1.00924813747406, "train_loss_llm": 0.6501235961914062, "global_step": 80, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.2802278995513916, "train_loss_dp": 1.2794685363769531, "train_loss_llm": 0.7593181133270264, "global_step": 81, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.439178228378296, "train_loss_dp": 1.4356193542480469, "train_loss_llm": 3.558879852294922, "global_step": 82, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.5372323989868164, "train_loss_dp": 1.5108232498168945, "train_loss_llm": 26.409198760986328, "global_step": 83, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 0.934393584728241, "train_loss_dp": 0.9340671300888062, "train_loss_llm": 0.3264431953430176, "global_step": 84, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.1141325235366821, "train_loss_dp": 1.1135903596878052, "train_loss_llm": 0.5421745777130127, "global_step": 85, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.1073263883590698, "train_loss_dp": 1.1065282821655273, "train_loss_llm": 0.7980890274047852, "global_step": 86, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.3542910814285278, "train_loss_dp": 1.3534879684448242, "train_loss_llm": 0.8031370043754578, "global_step": 87, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.2393393516540527, "train_loss_dp": 1.2383337020874023, "train_loss_llm": 1.005661964416504, "global_step": 88, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.0601671934127808, "train_loss_dp": 1.0592271089553833, "train_loss_llm": 0.940072774887085, "global_step": 89, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 0.9407315850257874, "train_loss_dp": 0.9394307136535645, "train_loss_llm": 1.300872802734375, "global_step": 90, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 0.9584405422210693, "train_loss_dp": 0.9571114182472229, "train_loss_llm": 1.3291091918945312, "global_step": 91, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.2508066892623901, "train_loss_dp": 1.2499979734420776, "train_loss_llm": 0.8086690902709961, "global_step": 92, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.0856820344924927, "train_loss_dp": 1.085033893585205, "train_loss_llm": 0.6481223106384277, "global_step": 93, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.010387659072876, "train_loss_dp": 1.009488821029663, "train_loss_llm": 0.8988838195800781, "global_step": 94, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 1.0682752132415771, "train_loss_dp": 1.0672967433929443, "train_loss_llm": 0.9785041809082031, "global_step": 95, "epoch": 0, "lr": 1.2000000000000002e-06} +{"train_loss": 0.9612948894500732, "train_loss_dp": 0.9556695818901062, "train_loss_llm": 5.625323295593262, "global_step": 96, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 0.9959707260131836, "train_loss_dp": 0.9945476651191711, "train_loss_llm": 1.4230327606201172, "global_step": 97, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.0540872812271118, "train_loss_dp": 1.0532400608062744, "train_loss_llm": 0.8472709655761719, "global_step": 98, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 0.8430070877075195, "train_loss_dp": 0.8347525596618652, "train_loss_llm": 8.254554748535156, "global_step": 99, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.212937355041504, "train_loss_dp": 1.2109421491622925, "train_loss_llm": 1.9952383041381836, "global_step": 100, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.5220714807510376, "train_loss_dp": 1.5211623907089233, "train_loss_llm": 0.9090893268585205, "global_step": 101, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.185511827468872, "train_loss_dp": 1.1830048561096191, "train_loss_llm": 2.507007598876953, "global_step": 102, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.274741768836975, "train_loss_dp": 1.2734978199005127, "train_loss_llm": 1.2439632415771484, "global_step": 103, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.3616313934326172, "train_loss_dp": 1.3602102994918823, "train_loss_llm": 1.4210619926452637, "global_step": 104, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 0.927491307258606, "train_loss_dp": 0.9263561367988586, "train_loss_llm": 1.1351572275161743, "global_step": 105, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.3116765022277832, "train_loss_dp": 1.3111802339553833, "train_loss_llm": 0.4962620735168457, "global_step": 106, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 0.9401284456253052, "train_loss_dp": 0.9401284456253052, "train_loss_llm": 0.0, "global_step": 107, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.2789523601531982, "train_loss_dp": 1.2757561206817627, "train_loss_llm": 3.19625186920166, "global_step": 108, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.3289803266525269, "train_loss_dp": 1.3270416259765625, "train_loss_llm": 1.9387450218200684, "global_step": 109, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.142594575881958, "train_loss_dp": 1.139634370803833, "train_loss_llm": 2.960202217102051, "global_step": 110, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.514200210571289, "train_loss_dp": 1.5133166313171387, "train_loss_llm": 0.8835506439208984, "global_step": 111, "epoch": 0, "lr": 1.4000000000000001e-06} +{"train_loss": 1.360787034034729, "train_loss_dp": 1.3596423864364624, "train_loss_llm": 1.144688367843628, "global_step": 112, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.969142735004425, "train_loss_dp": 0.9671523571014404, "train_loss_llm": 1.990363359451294, "global_step": 113, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.2223730087280273, "train_loss_dp": 1.2202041149139404, "train_loss_llm": 2.168877124786377, "global_step": 114, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.872321605682373, "train_loss_dp": 0.8709912300109863, "train_loss_llm": 1.3303956985473633, "global_step": 115, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.2033883333206177, "train_loss_dp": 1.2014824151992798, "train_loss_llm": 1.905907154083252, "global_step": 116, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.1351537704467773, "train_loss_dp": 1.1332049369812012, "train_loss_llm": 1.9487953186035156, "global_step": 117, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.7772543430328369, "train_loss_dp": 0.7740431427955627, "train_loss_llm": 3.2112045288085938, "global_step": 118, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.9142816662788391, "train_loss_dp": 0.9134396314620972, "train_loss_llm": 0.8420600891113281, "global_step": 119, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.3841831684112549, "train_loss_dp": 1.3824827671051025, "train_loss_llm": 1.7003915309906006, "global_step": 120, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.535054087638855, "train_loss_dp": 1.5346031188964844, "train_loss_llm": 0.4509390592575073, "global_step": 121, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.396112084388733, "train_loss_dp": 1.395089030265808, "train_loss_llm": 1.0230941772460938, "global_step": 122, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.2383545637130737, "train_loss_dp": 1.2374491691589355, "train_loss_llm": 0.9054279327392578, "global_step": 123, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.1876963376998901, "train_loss_dp": 1.1864168643951416, "train_loss_llm": 1.279426097869873, "global_step": 124, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.1756627559661865, "train_loss_dp": 1.172638177871704, "train_loss_llm": 3.0246083736419678, "global_step": 125, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 1.3171985149383545, "train_loss_dp": 1.3158243894577026, "train_loss_llm": 1.3741283416748047, "global_step": 126, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.8509191274642944, "train_loss_dp": 0.8499661684036255, "train_loss_llm": 0.952977180480957, "global_step": 127, "epoch": 0, "lr": 1.6000000000000001e-06} +{"train_loss": 0.9834503531455994, "train_loss_dp": 0.9814432859420776, "train_loss_llm": 2.0070724487304688, "global_step": 128, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.0482537746429443, "train_loss_dp": 1.0447148084640503, "train_loss_llm": 3.5389113426208496, "global_step": 129, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.257519006729126, "train_loss_dp": 1.2564001083374023, "train_loss_llm": 1.1189355850219727, "global_step": 130, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.2116267681121826, "train_loss_dp": 1.2109559774398804, "train_loss_llm": 0.6708385944366455, "global_step": 131, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.9143540263175964, "train_loss_dp": 0.9121775031089783, "train_loss_llm": 2.1765458583831787, "global_step": 132, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.481313705444336, "train_loss_dp": 1.4797840118408203, "train_loss_llm": 1.5296707153320312, "global_step": 133, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1101750135421753, "train_loss_dp": 1.1090611219406128, "train_loss_llm": 1.1138830184936523, "global_step": 134, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.7004116773605347, "train_loss_dp": 0.7001343965530396, "train_loss_llm": 0.27727508544921875, "global_step": 135, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.7784458994865417, "train_loss_dp": 0.776190996170044, "train_loss_llm": 2.2548980712890625, "global_step": 136, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1998752355575562, "train_loss_dp": 1.1994842290878296, "train_loss_llm": 0.3909933567047119, "global_step": 137, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.5123146772384644, "train_loss_dp": 1.5114731788635254, "train_loss_llm": 0.8414807319641113, "global_step": 138, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.165122389793396, "train_loss_dp": 1.1623948812484741, "train_loss_llm": 2.7275238037109375, "global_step": 139, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.9391596913337708, "train_loss_dp": 0.9387196898460388, "train_loss_llm": 0.44000244140625, "global_step": 140, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1626678705215454, "train_loss_dp": 1.160836935043335, "train_loss_llm": 1.8309268951416016, "global_step": 141, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.179438591003418, "train_loss_dp": 1.1788986921310425, "train_loss_llm": 0.539953351020813, "global_step": 142, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 1.1778478622436523, "train_loss_dp": 1.1772880554199219, "train_loss_llm": 0.5597635507583618, "global_step": 143, "epoch": 0, "lr": 1.8e-06} +{"train_loss": 0.7519816160202026, "train_loss_dp": 0.7499206066131592, "train_loss_llm": 2.0610313415527344, "global_step": 144, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.033149242401123, "train_loss_dp": 1.030527114868164, "train_loss_llm": 2.6221847534179688, "global_step": 145, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.8218566179275513, "train_loss_dp": 0.8199536800384521, "train_loss_llm": 1.902939796447754, "global_step": 146, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.1430176496505737, "train_loss_dp": 1.1426165103912354, "train_loss_llm": 0.40108823776245117, "global_step": 147, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.9039509892463684, "train_loss_dp": 0.9029526710510254, "train_loss_llm": 0.9983015060424805, "global_step": 148, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.1010316610336304, "train_loss_dp": 1.0997487306594849, "train_loss_llm": 1.2829561233520508, "global_step": 149, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.9845446348190308, "train_loss_dp": 0.9835625886917114, "train_loss_llm": 0.9820713996887207, "global_step": 150, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.7779905200004578, "train_loss_dp": 0.7754586935043335, "train_loss_llm": 2.5318164825439453, "global_step": 151, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0124595165252686, "train_loss_dp": 1.0107777118682861, "train_loss_llm": 1.6817703247070312, "global_step": 152, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.4586260318756104, "train_loss_dp": 1.4573760032653809, "train_loss_llm": 1.2500834465026855, "global_step": 153, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.1048839092254639, "train_loss_dp": 1.1031421422958374, "train_loss_llm": 1.74176025390625, "global_step": 154, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0053070783615112, "train_loss_dp": 1.0002398490905762, "train_loss_llm": 5.06719970703125, "global_step": 155, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 0.7785001397132874, "train_loss_dp": 0.7765992879867554, "train_loss_llm": 1.9008564949035645, "global_step": 156, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0327329635620117, "train_loss_dp": 1.0322593450546265, "train_loss_llm": 0.47359180450439453, "global_step": 157, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0866814851760864, "train_loss_dp": 1.0860393047332764, "train_loss_llm": 0.6421303749084473, "global_step": 158, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.1910791397094727, "train_loss_dp": 1.187978982925415, "train_loss_llm": 3.1001720428466797, "global_step": 159, "epoch": 0, "lr": 2.0000000000000003e-06} +{"train_loss": 1.0988060235977173, "train_loss_dp": 1.0978245735168457, "train_loss_llm": 0.9814157485961914, "global_step": 160, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.0247409343719482, "train_loss_dp": 1.0240224599838257, "train_loss_llm": 0.7184739112854004, "global_step": 161, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.8840754628181458, "train_loss_dp": 0.8831058740615845, "train_loss_llm": 0.9695768356323242, "global_step": 162, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.0541455745697021, "train_loss_dp": 1.0528428554534912, "train_loss_llm": 1.3027024269104004, "global_step": 163, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.1891512870788574, "train_loss_dp": 1.1883537769317627, "train_loss_llm": 0.7975687980651855, "global_step": 164, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.0300145149230957, "train_loss_dp": 1.0287904739379883, "train_loss_llm": 1.2240309715270996, "global_step": 165, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.2772839069366455, "train_loss_dp": 1.2756500244140625, "train_loss_llm": 1.6338398456573486, "global_step": 166, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.4530216455459595, "train_loss_dp": 1.452472448348999, "train_loss_llm": 0.5492558479309082, "global_step": 167, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.8250415325164795, "train_loss_dp": 0.8238312005996704, "train_loss_llm": 1.2103333473205566, "global_step": 168, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.2482695579528809, "train_loss_dp": 1.2445018291473389, "train_loss_llm": 3.767702102661133, "global_step": 169, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.8066973090171814, "train_loss_dp": 0.7980784177780151, "train_loss_llm": 8.618911743164062, "global_step": 170, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.1247379779815674, "train_loss_dp": 1.1208258867263794, "train_loss_llm": 3.912109375, "global_step": 171, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.9651830196380615, "train_loss_dp": 0.9647877216339111, "train_loss_llm": 0.3952951431274414, "global_step": 172, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.148676872253418, "train_loss_dp": 1.1479425430297852, "train_loss_llm": 0.7343111038208008, "global_step": 173, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 0.9433470964431763, "train_loss_dp": 0.9433470964431763, "train_loss_llm": 0.0, "global_step": 174, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.1110782623291016, "train_loss_dp": 1.110610008239746, "train_loss_llm": 0.46828949451446533, "global_step": 175, "epoch": 0, "lr": 2.2e-06} +{"train_loss": 1.0836390256881714, "train_loss_dp": 1.0817854404449463, "train_loss_llm": 1.8535747528076172, "global_step": 176, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.0304619073867798, "train_loss_dp": 1.0294827222824097, "train_loss_llm": 0.9792404174804688, "global_step": 177, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.2052817344665527, "train_loss_dp": 1.2008137702941895, "train_loss_llm": 4.468011856079102, "global_step": 178, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9397463798522949, "train_loss_dp": 0.9386704564094543, "train_loss_llm": 1.0759334564208984, "global_step": 179, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.7744102478027344, "train_loss_dp": 0.7735385894775391, "train_loss_llm": 0.8716411590576172, "global_step": 180, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9073777198791504, "train_loss_dp": 0.9060908555984497, "train_loss_llm": 1.2868871688842773, "global_step": 181, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.1213650703430176, "train_loss_dp": 1.1192471981048584, "train_loss_llm": 2.117826461791992, "global_step": 182, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.8236191272735596, "train_loss_dp": 0.8231710195541382, "train_loss_llm": 0.4481140375137329, "global_step": 183, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.0349735021591187, "train_loss_dp": 1.0338809490203857, "train_loss_llm": 1.092587947845459, "global_step": 184, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9988579750061035, "train_loss_dp": 0.9917410612106323, "train_loss_llm": 7.116888046264648, "global_step": 185, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.8507592678070068, "train_loss_dp": 0.8497412800788879, "train_loss_llm": 1.0179882049560547, "global_step": 186, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9779895544052124, "train_loss_dp": 0.9772846102714539, "train_loss_llm": 0.7049155235290527, "global_step": 187, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.3312708139419556, "train_loss_dp": 1.330188512802124, "train_loss_llm": 1.0822707414627075, "global_step": 188, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9593352675437927, "train_loss_dp": 0.9589107036590576, "train_loss_llm": 0.42458438873291016, "global_step": 189, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.0197609663009644, "train_loss_dp": 1.0167262554168701, "train_loss_llm": 3.034749984741211, "global_step": 190, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 1.2858330011367798, "train_loss_dp": 1.285414457321167, "train_loss_llm": 0.4184989929199219, "global_step": 191, "epoch": 0, "lr": 2.4000000000000003e-06} +{"train_loss": 0.9332898259162903, "train_loss_dp": 0.9326448440551758, "train_loss_llm": 0.6449551582336426, "global_step": 192, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.2359142303466797, "train_loss_dp": 1.231081247329712, "train_loss_llm": 4.832974433898926, "global_step": 193, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.1643035411834717, "train_loss_dp": 1.1640876531600952, "train_loss_llm": 0.2158433198928833, "global_step": 194, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.276792049407959, "train_loss_dp": 1.2738449573516846, "train_loss_llm": 2.9471492767333984, "global_step": 195, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.1814332008361816, "train_loss_dp": 1.1802271604537964, "train_loss_llm": 1.2060976028442383, "global_step": 196, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 0.9542033672332764, "train_loss_dp": 0.9529739618301392, "train_loss_llm": 1.229403018951416, "global_step": 197, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.1571743488311768, "train_loss_dp": 1.1548030376434326, "train_loss_llm": 2.37127685546875, "global_step": 198, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 0.7295464277267456, "train_loss_dp": 0.728955864906311, "train_loss_llm": 0.5905838012695312, "global_step": 199, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.0015571117401123, "train_loss_dp": 0.9783788919448853, "train_loss_llm": 23.178180694580078, "global_step": 200, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.0145008563995361, "train_loss_dp": 1.0105431079864502, "train_loss_llm": 3.957691192626953, "global_step": 201, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 0.648456871509552, "train_loss_dp": 0.6480518579483032, "train_loss_llm": 0.40498554706573486, "global_step": 202, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.313805103302002, "train_loss_dp": 1.3031940460205078, "train_loss_llm": 10.611042022705078, "global_step": 203, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.3389441967010498, "train_loss_dp": 1.3341532945632935, "train_loss_llm": 4.790843963623047, "global_step": 204, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.102067470550537, "train_loss_dp": 1.1018626689910889, "train_loss_llm": 0.20481538772583008, "global_step": 205, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 0.9313886165618896, "train_loss_dp": 0.9303997755050659, "train_loss_llm": 0.9888467788696289, "global_step": 206, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.1283764839172363, "train_loss_dp": 1.1279702186584473, "train_loss_llm": 0.40624749660491943, "global_step": 207, "epoch": 0, "lr": 2.6e-06} +{"train_loss": 1.0273942947387695, "train_loss_dp": 1.0264244079589844, "train_loss_llm": 0.9699411392211914, "global_step": 208, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8452053666114807, "train_loss_dp": 0.8452053666114807, "train_loss_llm": 0.0, "global_step": 209, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8671678304672241, "train_loss_dp": 0.8667815923690796, "train_loss_llm": 0.3862495422363281, "global_step": 210, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.2919409275054932, "train_loss_dp": 1.2913035154342651, "train_loss_llm": 0.6373605728149414, "global_step": 211, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.2071784734725952, "train_loss_dp": 1.2063597440719604, "train_loss_llm": 0.8187451362609863, "global_step": 212, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.9915256500244141, "train_loss_dp": 0.9911161661148071, "train_loss_llm": 0.40947723388671875, "global_step": 213, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.2514506578445435, "train_loss_dp": 1.2503032684326172, "train_loss_llm": 1.1473705768585205, "global_step": 214, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8697264194488525, "train_loss_dp": 0.868963360786438, "train_loss_llm": 0.7630748748779297, "global_step": 215, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.1300768852233887, "train_loss_dp": 1.1299668550491333, "train_loss_llm": 0.11003875732421875, "global_step": 216, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.881068229675293, "train_loss_dp": 0.8803726434707642, "train_loss_llm": 0.6955909729003906, "global_step": 217, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.7535129189491272, "train_loss_dp": 0.7521725296974182, "train_loss_llm": 1.3404150009155273, "global_step": 218, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.8224195837974548, "train_loss_dp": 0.821901798248291, "train_loss_llm": 0.5177874565124512, "global_step": 219, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.9766490459442139, "train_loss_dp": 0.975908637046814, "train_loss_llm": 0.7404384613037109, "global_step": 220, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.377051591873169, "train_loss_dp": 1.3759162425994873, "train_loss_llm": 1.1353375911712646, "global_step": 221, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 0.9554775357246399, "train_loss_dp": 0.9547816514968872, "train_loss_llm": 0.6958713531494141, "global_step": 222, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.1168142557144165, "train_loss_dp": 1.1162590980529785, "train_loss_llm": 0.5551265478134155, "global_step": 223, "epoch": 0, "lr": 2.8000000000000003e-06} +{"train_loss": 1.2304797172546387, "train_loss_dp": 1.2258176803588867, "train_loss_llm": 4.662047386169434, "global_step": 224, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.1293238401412964, "train_loss_dp": 1.1288785934448242, "train_loss_llm": 0.44530439376831055, "global_step": 225, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.1476926803588867, "train_loss_dp": 1.1459271907806396, "train_loss_llm": 1.765434741973877, "global_step": 226, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.7780570983886719, "train_loss_dp": 0.7766939401626587, "train_loss_llm": 1.363138198852539, "global_step": 227, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.2119451761245728, "train_loss_dp": 1.2110717296600342, "train_loss_llm": 0.8734626770019531, "global_step": 228, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.057111144065857, "train_loss_dp": 1.0545047521591187, "train_loss_llm": 2.6064376831054688, "global_step": 229, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.9079468846321106, "train_loss_dp": 0.9066292643547058, "train_loss_llm": 1.3176403045654297, "global_step": 230, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.8751040697097778, "train_loss_dp": 0.8744442462921143, "train_loss_llm": 0.6598072052001953, "global_step": 231, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.7758923768997192, "train_loss_dp": 0.7748883366584778, "train_loss_llm": 1.0040168762207031, "global_step": 232, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.8375587463378906, "train_loss_dp": 0.8291288018226624, "train_loss_llm": 8.42996597290039, "global_step": 233, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.7949652075767517, "train_loss_dp": 0.7942540645599365, "train_loss_llm": 0.7111620903015137, "global_step": 234, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.4924968481063843, "train_loss_dp": 1.4881751537322998, "train_loss_llm": 4.321743011474609, "global_step": 235, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.1771422624588013, "train_loss_dp": 1.1737477779388428, "train_loss_llm": 3.394542694091797, "global_step": 236, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.4503920078277588, "train_loss_dp": 1.4467439651489258, "train_loss_llm": 3.648099899291992, "global_step": 237, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.3675427436828613, "train_loss_dp": 1.2954208850860596, "train_loss_llm": 72.121826171875, "global_step": 238, "epoch": 0, "lr": 3e-06} +{"train_loss": 0.9646413326263428, "train_loss_dp": 0.9633788466453552, "train_loss_llm": 1.2624778747558594, "global_step": 239, "epoch": 0, "lr": 3e-06} +{"train_loss": 1.1442116498947144, "train_loss_dp": 1.1247045993804932, "train_loss_llm": 19.50709342956543, "global_step": 240, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.229844331741333, "train_loss_dp": 1.2294831275939941, "train_loss_llm": 0.36118602752685547, "global_step": 241, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9572376012802124, "train_loss_dp": 0.9506734609603882, "train_loss_llm": 6.564121246337891, "global_step": 242, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.8527343273162842, "train_loss_dp": 0.8522154092788696, "train_loss_llm": 0.5188912153244019, "global_step": 243, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.0515928268432617, "train_loss_dp": 1.0501519441604614, "train_loss_llm": 1.4408516883850098, "global_step": 244, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.2232630252838135, "train_loss_dp": 1.2201411724090576, "train_loss_llm": 3.121842861175537, "global_step": 245, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9529631733894348, "train_loss_dp": 0.9523892402648926, "train_loss_llm": 0.5739237070083618, "global_step": 246, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9630469083786011, "train_loss_dp": 0.9625718593597412, "train_loss_llm": 0.47504037618637085, "global_step": 247, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.1164318323135376, "train_loss_dp": 1.1154800653457642, "train_loss_llm": 0.9518008232116699, "global_step": 248, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.1466361284255981, "train_loss_dp": 1.145241141319275, "train_loss_llm": 1.3949520587921143, "global_step": 249, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9411832094192505, "train_loss_dp": 0.9388471245765686, "train_loss_llm": 2.3360671997070312, "global_step": 250, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.0483355522155762, "train_loss_dp": 1.047311544418335, "train_loss_llm": 1.0240333080291748, "global_step": 251, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.9099900126457214, "train_loss_dp": 0.908272385597229, "train_loss_llm": 1.7176060676574707, "global_step": 252, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.8964932560920715, "train_loss_dp": 0.8937091827392578, "train_loss_llm": 2.784043788909912, "global_step": 253, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.6653807759284973, "train_loss_dp": 0.6645738482475281, "train_loss_llm": 0.8069276809692383, "global_step": 254, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 0.8939193487167358, "train_loss_dp": 0.8922350406646729, "train_loss_llm": 1.684330940246582, "global_step": 255, "epoch": 0, "lr": 3.2000000000000003e-06} +{"train_loss": 1.1988483667373657, "train_loss_dp": 1.1982628107070923, "train_loss_llm": 0.585566520690918, "global_step": 256, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.2160420417785645, "train_loss_dp": 1.2152230739593506, "train_loss_llm": 0.8189777135848999, "global_step": 257, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.0962705612182617, "train_loss_dp": 1.0953199863433838, "train_loss_llm": 0.9505208730697632, "global_step": 258, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.3069539070129395, "train_loss_dp": 1.3061105012893677, "train_loss_llm": 0.843407392501831, "global_step": 259, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.7975951433181763, "train_loss_dp": 0.7952274084091187, "train_loss_llm": 2.367708444595337, "global_step": 260, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.721216082572937, "train_loss_dp": 0.72008216381073, "train_loss_llm": 1.1339340209960938, "global_step": 261, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.69647216796875, "train_loss_dp": 0.6954328417778015, "train_loss_llm": 1.0393414497375488, "global_step": 262, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.9801919460296631, "train_loss_dp": 0.9793461561203003, "train_loss_llm": 0.8458011150360107, "global_step": 263, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.10097336769104, "train_loss_dp": 1.0997307300567627, "train_loss_llm": 1.2425899505615234, "global_step": 264, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.2597533464431763, "train_loss_dp": 1.258787751197815, "train_loss_llm": 0.9655556082725525, "global_step": 265, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.0647258758544922, "train_loss_dp": 1.063507318496704, "train_loss_llm": 1.2185382843017578, "global_step": 266, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.0454201698303223, "train_loss_dp": 1.0433969497680664, "train_loss_llm": 2.0232481956481934, "global_step": 267, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.9429545402526855, "train_loss_dp": 0.9400829076766968, "train_loss_llm": 2.871659755706787, "global_step": 268, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.8326311707496643, "train_loss_dp": 0.8317397832870483, "train_loss_llm": 0.891406774520874, "global_step": 269, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.036145567893982, "train_loss_dp": 1.036145567893982, "train_loss_llm": 0.0, "global_step": 270, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 1.2521494626998901, "train_loss_dp": 1.2500450611114502, "train_loss_llm": 2.1044344902038574, "global_step": 271, "epoch": 0, "lr": 3.4000000000000005e-06} +{"train_loss": 0.8038797974586487, "train_loss_dp": 0.8031554222106934, "train_loss_llm": 0.7243483066558838, "global_step": 272, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.2528009414672852, "train_loss_dp": 1.2507556676864624, "train_loss_llm": 2.0452141761779785, "global_step": 273, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.8474252820014954, "train_loss_dp": 0.8469349145889282, "train_loss_llm": 0.49039697647094727, "global_step": 274, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.1974656581878662, "train_loss_dp": 1.1965305805206299, "train_loss_llm": 0.9350690841674805, "global_step": 275, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.1751670837402344, "train_loss_dp": 1.1636312007904053, "train_loss_llm": 11.535860061645508, "global_step": 276, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.9275045394897461, "train_loss_dp": 0.9263038039207458, "train_loss_llm": 1.2007064819335938, "global_step": 277, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.0550025701522827, "train_loss_dp": 1.0545289516448975, "train_loss_llm": 0.47359371185302734, "global_step": 278, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.118127703666687, "train_loss_dp": 1.116943120956421, "train_loss_llm": 1.1845817565917969, "global_step": 279, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.1602343320846558, "train_loss_dp": 1.1595017910003662, "train_loss_llm": 0.7325186729431152, "global_step": 280, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.9661479592323303, "train_loss_dp": 0.9661190509796143, "train_loss_llm": 0.028900146484375, "global_step": 281, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.8921505212783813, "train_loss_dp": 0.891818106174469, "train_loss_llm": 0.3324199914932251, "global_step": 282, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.079240322113037, "train_loss_dp": 1.0790988206863403, "train_loss_llm": 0.1414651870727539, "global_step": 283, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.9580252766609192, "train_loss_dp": 0.9545332193374634, "train_loss_llm": 3.4920387268066406, "global_step": 284, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.8020926117897034, "train_loss_dp": 0.8007901310920715, "train_loss_llm": 1.3024520874023438, "global_step": 285, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 1.123852252960205, "train_loss_dp": 1.1215667724609375, "train_loss_llm": 2.2854433059692383, "global_step": 286, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.943714439868927, "train_loss_dp": 0.9397944211959839, "train_loss_llm": 3.9200081825256348, "global_step": 287, "epoch": 0, "lr": 3.6e-06} +{"train_loss": 0.7960315346717834, "train_loss_dp": 0.7955789566040039, "train_loss_llm": 0.4525725841522217, "global_step": 288, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.1580305099487305, "train_loss_dp": 1.1548525094985962, "train_loss_llm": 3.1779422760009766, "global_step": 289, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.0809510946273804, "train_loss_dp": 1.0793955326080322, "train_loss_llm": 1.5555198192596436, "global_step": 290, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.6982622742652893, "train_loss_dp": 0.6949447393417358, "train_loss_llm": 3.3175277709960938, "global_step": 291, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.8484363555908203, "train_loss_dp": 0.8478072285652161, "train_loss_llm": 0.6291027069091797, "global_step": 292, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.0838271379470825, "train_loss_dp": 1.0824178457260132, "train_loss_llm": 1.409332275390625, "global_step": 293, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.8819434642791748, "train_loss_dp": 0.8808730840682983, "train_loss_llm": 1.0703829526901245, "global_step": 294, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.1714118719100952, "train_loss_dp": 1.1708070039749146, "train_loss_llm": 0.604843020439148, "global_step": 295, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.126109004020691, "train_loss_dp": 1.1250288486480713, "train_loss_llm": 1.0801409482955933, "global_step": 296, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.0248970985412598, "train_loss_dp": 1.0248970985412598, "train_loss_llm": 0.0, "global_step": 297, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.9338111877441406, "train_loss_dp": 0.9332759976387024, "train_loss_llm": 0.535181999206543, "global_step": 298, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.9935199022293091, "train_loss_dp": 0.9858657121658325, "train_loss_llm": 7.6541948318481445, "global_step": 299, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.9248150587081909, "train_loss_dp": 0.9244741201400757, "train_loss_llm": 0.34091949462890625, "global_step": 300, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.8608558773994446, "train_loss_dp": 0.8600831627845764, "train_loss_llm": 0.7727339267730713, "global_step": 301, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.1782559156417847, "train_loss_dp": 1.171644687652588, "train_loss_llm": 6.61122989654541, "global_step": 302, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 0.8898539543151855, "train_loss_dp": 0.8885205388069153, "train_loss_llm": 1.3334004878997803, "global_step": 303, "epoch": 0, "lr": 3.8e-06} +{"train_loss": 1.067720890045166, "train_loss_dp": 1.0673210620880127, "train_loss_llm": 0.3998118042945862, "global_step": 304, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.8939509987831116, "train_loss_dp": 0.890986442565918, "train_loss_llm": 2.964561939239502, "global_step": 305, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.0115349292755127, "train_loss_dp": 1.0104701519012451, "train_loss_llm": 1.0647544860839844, "global_step": 306, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.0481693744659424, "train_loss_dp": 1.0473825931549072, "train_loss_llm": 0.7867661714553833, "global_step": 307, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.8547577857971191, "train_loss_dp": 0.8531267642974854, "train_loss_llm": 1.6310176849365234, "global_step": 308, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.228912115097046, "train_loss_dp": 1.2272719144821167, "train_loss_llm": 1.6402053833007812, "global_step": 309, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.0326021909713745, "train_loss_dp": 1.0271694660186768, "train_loss_llm": 5.432718276977539, "global_step": 310, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.267053484916687, "train_loss_dp": 1.2668509483337402, "train_loss_llm": 0.20250320434570312, "global_step": 311, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.107075810432434, "train_loss_dp": 1.1067700386047363, "train_loss_llm": 0.30582571029663086, "global_step": 312, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.9171063303947449, "train_loss_dp": 0.9165456295013428, "train_loss_llm": 0.5606918334960938, "global_step": 313, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.2713171243667603, "train_loss_dp": 1.2697443962097168, "train_loss_llm": 1.5726909637451172, "global_step": 314, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.6992313265800476, "train_loss_dp": 0.6986074447631836, "train_loss_llm": 0.6238861083984375, "global_step": 315, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.403481125831604, "train_loss_dp": 1.401566982269287, "train_loss_llm": 1.914093017578125, "global_step": 316, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.0799481868743896, "train_loss_dp": 1.0791573524475098, "train_loss_llm": 0.7908363342285156, "global_step": 317, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 1.4620671272277832, "train_loss_dp": 1.4592591524124146, "train_loss_llm": 2.807957887649536, "global_step": 318, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.7750579118728638, "train_loss_dp": 0.7740998864173889, "train_loss_llm": 0.9580368995666504, "global_step": 319, "epoch": 0, "lr": 4.000000000000001e-06} +{"train_loss": 0.9734408855438232, "train_loss_dp": 0.9727185964584351, "train_loss_llm": 0.7222604751586914, "global_step": 320, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1509928703308105, "train_loss_dp": 1.1507270336151123, "train_loss_llm": 0.2658653259277344, "global_step": 321, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 0.8242414593696594, "train_loss_dp": 0.8230121731758118, "train_loss_llm": 1.2292871475219727, "global_step": 322, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1724762916564941, "train_loss_dp": 1.1704481840133667, "train_loss_llm": 2.0280914306640625, "global_step": 323, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.038427710533142, "train_loss_dp": 1.037381887435913, "train_loss_llm": 1.0457860231399536, "global_step": 324, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1120530366897583, "train_loss_dp": 1.1116998195648193, "train_loss_llm": 0.3532347083091736, "global_step": 325, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 0.904810905456543, "train_loss_dp": 0.899479866027832, "train_loss_llm": 5.331026077270508, "global_step": 326, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1774355173110962, "train_loss_dp": 1.1022679805755615, "train_loss_llm": 75.16754150390625, "global_step": 327, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1792408227920532, "train_loss_dp": 1.1751174926757812, "train_loss_llm": 4.123276710510254, "global_step": 328, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.4997353553771973, "train_loss_dp": 1.49672269821167, "train_loss_llm": 3.0126028060913086, "global_step": 329, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.1793338060379028, "train_loss_dp": 1.1770999431610107, "train_loss_llm": 2.2338204383850098, "global_step": 330, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 0.956778883934021, "train_loss_dp": 0.9557748436927795, "train_loss_llm": 1.0040538311004639, "global_step": 331, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.098751187324524, "train_loss_dp": 1.091995358467102, "train_loss_llm": 6.755779266357422, "global_step": 332, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.2604960203170776, "train_loss_dp": 1.2589225769042969, "train_loss_llm": 1.5734949111938477, "global_step": 333, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.2166566848754883, "train_loss_dp": 1.2133680582046509, "train_loss_llm": 3.2885799407958984, "global_step": 334, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.2427011728286743, "train_loss_dp": 1.241709589958191, "train_loss_llm": 0.9915516376495361, "global_step": 335, "epoch": 0, "lr": 4.2000000000000004e-06} +{"train_loss": 1.0223388671875, "train_loss_dp": 1.0215694904327393, "train_loss_llm": 0.7694258689880371, "global_step": 336, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.2411962747573853, "train_loss_dp": 1.2380201816558838, "train_loss_llm": 3.1760597229003906, "global_step": 337, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.966313898563385, "train_loss_dp": 0.9634715914726257, "train_loss_llm": 2.8423099517822266, "global_step": 338, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.1959434747695923, "train_loss_dp": 1.1937735080718994, "train_loss_llm": 2.1699752807617188, "global_step": 339, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.0998724699020386, "train_loss_dp": 1.0986469984054565, "train_loss_llm": 1.2255198955535889, "global_step": 340, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.8646638989448547, "train_loss_dp": 0.8604604005813599, "train_loss_llm": 4.203488349914551, "global_step": 341, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.1382033824920654, "train_loss_dp": 1.1372756958007812, "train_loss_llm": 0.9277114868164062, "global_step": 342, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.3346738815307617, "train_loss_dp": 1.330129861831665, "train_loss_llm": 4.544013977050781, "global_step": 343, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.4760773181915283, "train_loss_dp": 1.4727771282196045, "train_loss_llm": 3.300149917602539, "global_step": 344, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.028049111366272, "train_loss_dp": 1.0270345211029053, "train_loss_llm": 1.0145602226257324, "global_step": 345, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.1148306131362915, "train_loss_dp": 1.1136733293533325, "train_loss_llm": 1.1573162078857422, "global_step": 346, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.9583247900009155, "train_loss_dp": 0.9575679898262024, "train_loss_llm": 0.7568280696868896, "global_step": 347, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.9133409261703491, "train_loss_dp": 0.9125498533248901, "train_loss_llm": 0.7910995483398438, "global_step": 348, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 0.948867678642273, "train_loss_dp": 0.9483661651611328, "train_loss_llm": 0.5014915466308594, "global_step": 349, "epoch": 0, "lr": 4.4e-06} +{"train_loss": 1.038795828819275, "train_loss_dp": 1.0383384227752686, "train_loss_llm": 0.457424521446228, "global_step": 350, "epoch": 0, "lr": 4.4e-06} diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/train.log b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/train.log new file mode 100644 index 0000000000000000000000000000000000000000..031eefd8730f11f9b8c62a0b089a2fec067b186a --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/train.log @@ -0,0 +1,14 @@ +[2026-04-14 06:26:57,055][numexpr.utils][INFO] - Note: detected 144 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable. +[2026-04-14 06:26:57,055][numexpr.utils][INFO] - Note: NumExpr detected 144 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16. +[2026-04-14 06:26:57,055][numexpr.utils][INFO] - NumExpr defaulting to 16 threads. +[2026-04-14 06:26:59,292][datasets][INFO] - PyTorch version 2.2.2 available. +[2026-04-14 06:26:59,292][datasets][INFO] - TensorFlow version 2.15.1 available. +[2026-04-14 06:26:59,293][datasets][INFO] - JAX version 0.4.30 available. +[2026-04-14 06:27:00,910][llmbc.model.diffusion.conditional_unet1d][INFO] - number of parameters: 6.501479e+07 +[2026-04-14 06:27:14,121][root][INFO] - running build_ext +[2026-04-14 06:27:14,123][root][INFO] - building 'mujoco_py.cymj' extension +[2026-04-14 06:27:14,123][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /venv/llm-bc/include -I/venv/llm-bc/include -fPIC -O2 -isystem /venv/llm-bc/include -fPIC -I/venv/llm-bc/lib/python3.9/site-packages/mujoco_py -I/root/.mujoco/mujoco210/include -I/venv/llm-bc/lib/python3.9/site-packages/numpy/core/include -I/venv/llm-bc/include/python3.9 -c /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.c -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.o -fopenmp -w +[2026-04-14 06:27:56,140][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /venv/llm-bc/include -I/venv/llm-bc/include -fPIC -O2 -isystem /venv/llm-bc/include -fPIC -I/venv/llm-bc/lib/python3.9/site-packages/mujoco_py -I/root/.mujoco/mujoco210/include -I/venv/llm-bc/lib/python3.9/site-packages/numpy/core/include -I/venv/llm-bc/include/python3.9 -c /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.c -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.o -fopenmp -w +[2026-04-14 06:27:56,252][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -shared -Wl,-rpath,/venv/llm-bc/lib -Wl,-rpath-link,/venv/llm-bc/lib -L/venv/llm-bc/lib -L/venv/llm-bc/lib -Wl,-rpath,/venv/llm-bc/lib -Wl,-rpath-link,/venv/llm-bc/lib -L/venv/llm-bc/lib /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.o -L/root/.mujoco/mujoco210/bin -Wl,--enable-new-dtags,-rpath,/root/.mujoco/mujoco210/bin -lmujoco210 -lglewosmesa -lOSMesa -lGL -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/lib.linux-x86_64-cpython-39/mujoco_py/cymj.cpython-39-x86_64-linux-gnu.so -fopenmp +[2026-04-14 06:27:59,173][absl][INFO] - MUJOCO_GL=osmesa, attempting to import specified OpenGL backend. +[2026-04-14 06:27:59,179][absl][INFO] - MuJoCo library version is: 2.3.7 diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/config.yaml b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e597ffccbe7d1691e5b34ceea62fbb17aaddd47b --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/config.yaml @@ -0,0 +1,304 @@ +_target_: + value: llmbc.workspace.train_llm_diffusion_unet_lowdim_workspace.TrainLLMDiffusionUnetLowdimWorkspace +_wandb: + value: + cli_version: 0.18.6 + m: [] + python_version: 3.9.25 + t: + "1": + - 1 + - 2 + - 3 + - 5 + - 11 + - 12 + - 41 + - 49 + - 50 + - 51 + - 53 + - 55 + - 71 + - 83 + - 95 + - 98 + - 100 + - 105 + "2": + - 1 + - 2 + - 3 + - 5 + - 11 + - 12 + - 41 + - 49 + - 50 + - 51 + - 53 + - 55 + - 71 + - 83 + - 95 + - 98 + - 100 + - 105 + "3": + - 13 + - 15 + - 16 + - 23 + - 55 + - 61 + "4": 3.9.25 + "5": 0.18.6 + "6": 4.47.1 + "8": + - 5 + "12": 0.18.6 + "13": linux-x86_64 +action_dim: + value: 4 +checkpoint: + value: + save_last_ckpt: true + save_last_snapshot: false + topk: + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + k: 5 + mode: max + monitor_key: test_success_rate +dataloader: + value: + batch_size: 16 + num_workers: 0 + persistent_workers: false + pin_memory: false + shuffle: true +ema: + value: + _target_: llmbc.model.diffusion.ema_model.EMAModel + inv_gamma: 1 + max_value: 0.9999 + min_value: 0 + power: 0.75 + update_after_step: 0 +exp_name: + value: default +horizon: + value: 1 +keypoint_visible_rate: + value: 1 +llm: + value: + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + finetune_mode: orig + hydra: + job: + override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct + run: + dir: data/outputs/2026.04.14/06.26.55_HuggingFaceTB/SmolLM2-135M-Instruct + llm_mode: ete-finetuned + lora_config: + bias: none + lora_alpha: 64 + lora_dropout: 0.05 + r: 32 + task_type: CAUSAL_LM + max_length: 100 + model_name: SmolLM2-135M-Instruct + name: HuggingFaceTB/SmolLM2-135M-Instruct + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + use_joint_mlp_projector: true + use_quantization: false +llm_do_sample: + value: false +llm_orig_expert_feedback: + value: true +logging: + value: + group: null + id: null + mode: online + name: 2026.04.14-06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2 + project: sweep-v2-training + resume: true + tags: + - train_llm_diffusion_unet_lowdim + - sweep-v2 + - default +model_name: + value: HuggingFaceTB/SmolLM2-135M-Instruct +multi_run: + value: + run_dir: data/outputs/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2 + wandb_name_base: 2026.04.14-06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2 +n_action_steps: + value: 1 +n_latency_steps: + value: 0 +n_obs_steps: + value: 1 +name: + value: train_llm_diffusion_unet_lowdim +obs_as_global_cond: + value: true +obs_as_local_cond: + value: false +obs_dim: + value: 9 +optimizer: + value: + _target_: torch.optim.AdamW + betas: + - 0.95 + - 0.999 + eps: 1e-08 + lr: 0.0001 + weight_decay: 1e-06 +output_dir: + value: /workspace/LLM-BC/data/outputs/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2 +past_action_visible: + value: false +policy: + value: + _target_: llmbc.policy.llm_diffusion_unet_lowdim_policy.LLMDiffusionUnetLowdimPolicy + action_dim: 4 + horizon: 1 + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + action_dim: 4 + cfg: + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + finetune_mode: orig + hydra: + job: + override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct + run: + dir: data/outputs/2026.04.14/06.26.55_HuggingFaceTB/SmolLM2-135M-Instruct + llm_mode: ete-finetuned + lora_config: + bias: none + lora_alpha: 64 + lora_dropout: 0.05 + r: 32 + task_type: CAUSAL_LM + max_length: 100 + model_name: SmolLM2-135M-Instruct + name: HuggingFaceTB/SmolLM2-135M-Instruct + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + use_joint_mlp_projector: true + use_quantization: false + horizon: 1 + n_action_steps: 1 + n_obs_steps: 1 + obs_dim: 9 + task_id: sweep-v2 + loss_dp_weight: 1 + loss_llm_weight: 0.001 + model: + _target_: llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D + cond_predict_scale: true + diffusion_step_embed_dim: 256 + down_dims: + - 256 + - 512 + - 1024 + global_cond_dim: 9 + input_dim: 4 + kernel_size: 5 + local_cond_dim: null + n_groups: 8 + n_action_steps: 1 + n_obs_steps: 1 + noise_scheduler: + _target_: diffusers.schedulers.scheduling_ddpm.DDPMScheduler + beta_end: 0.02 + beta_schedule: squaredcos_cap_v2 + beta_start: 0.0001 + clip_sample: true + num_train_timesteps: 100 + prediction_type: epsilon + variance_type: fixed_small + normalize_llm_loss: true + num_inference_steps: 100 + oa_step_convention: true + obs_as_global_cond: true + obs_as_local_cond: false + obs_dim: 9 + pred_action_steps_only: false + reweight_llm_loss: true +pred_action_steps_only: + value: false +task: + value: + action_dim: 4 + dataset: + _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset + data_path: datasets/sweep-v2-mix(csp5).pt + data_path2: datasets/sweep-v2.pt + dummy_normalizer: false + horizon: 1 + obs_eef_target: true + pad_after: 0 + pad_before: 0 + use_manual_normalizer: false + val_ratio: 0.1 + env_runner: + _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner + discount: 0.9 + env_name: llf-metaworld-sweep-v2 + feedback_type: + - hp + - hn + - fp + instruction_type: b + max_steps: 30 + n_action_steps: 1 + n_envs: 10 + n_obs_steps: 1 + n_test: 50 + n_train: 10 + visual: false + instructor: + _target_: llmbc.translator.instructor.metaworld_instructor.sweep_v2_instructor.SweepV2Instructor + name: sweep-v2 + obs_dim: 9 +task_name: + value: sweep-v2 +training: + value: + checkpoint_every: 5 + debug: false + device: cuda:0 + gradient_accumulate_every: 16 + lr_scheduler: cosine + lr_warmup_steps: 500 + max_train_steps: null + max_val_steps: null + num_epochs: 1001 + resume: true + rollout_every: 5 + sample_every: 5 + seed: 42 + tqdm_interval_sec: 1 + use_ema: true + val_every: 1 +val_dataloader: + value: + batch_size: 16 + num_workers: 0 + persistent_workers: false + pin_memory: false + shuffle: false diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/output.log b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/output.log new file mode 100644 index 0000000000000000000000000000000000000000..ab9db5cf5adb96ff1b222233eb885c4d10db16b6 --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/output.log @@ -0,0 +1,120 @@ +Traceback (most recent call last): + File "/workspace/LLM-BC/./train.py", line 35, in + main() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/main.py", line 90, in decorated_main + _run_hydra( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 389, in _run_hydra + _run_app( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 452, in _run_app + run_and_report( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 213, in run_and_report + return func() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 453, in + lambda: hydra.run( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/hydra.py", line 119, in run + ret = run_job( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/workspace/LLM-BC/./train.py", line 32, in main + workspace.run() + File "/workspace/LLM-BC/llmbc/workspace/train_llm_diffusion_unet_lowdim_workspace.py", line 199, in run + raw_loss, raw_loss_dp, raw_loss_llm = self.model.compute_loss(batch) + File "/workspace/LLM-BC/llmbc/policy/llm_diffusion_unet_lowdim_policy.py", line 320, in compute_loss + loss_ce = self.llm_discriminator.compute_similarity_loss( + File "/workspace/LLM-BC/llmbc/discriminator/llm_ce_discriminator.py", line 56, in compute_similarity_loss + outputs, label_ids = self.llm_translator.forward( + File "/workspace/LLM-BC/llmbc/translator/llm_translator.py", line 321, in forward + outputs = self.model( + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/workspace/LLM-BC/llmbc/model/llm/llama_lowdim_model.py", line 122, in forward + return super().forward( + File "/venv/llm-bc/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 1163, in forward + outputs = self.model( + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 913, in forward + layer_outputs = decoder_layer( + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 640, in forward + hidden_states, self_attn_weights, present_key_value = self.self_attn( + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 523, in forward + key_states = self.k_proj(hidden_states) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/linear.py", line 116, in forward + return F.linear(input, self.weight, self.bias) +KeyboardInterrupt +Traceback (most recent call last): + File "/workspace/LLM-BC/./train.py", line 35, in + main() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/main.py", line 90, in decorated_main + _run_hydra( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 389, in _run_hydra + _run_app( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 452, in _run_app + run_and_report( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 213, in run_and_report + return func() + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/utils.py", line 453, in + lambda: hydra.run( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/_internal/hydra.py", line 119, in run + ret = run_job( + File "/venv/llm-bc/lib/python3.9/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/workspace/LLM-BC/./train.py", line 32, in main + workspace.run() + File "/workspace/LLM-BC/llmbc/workspace/train_llm_diffusion_unet_lowdim_workspace.py", line 199, in run + raw_loss, raw_loss_dp, raw_loss_llm = self.model.compute_loss(batch) + File "/workspace/LLM-BC/llmbc/policy/llm_diffusion_unet_lowdim_policy.py", line 320, in compute_loss + loss_ce = self.llm_discriminator.compute_similarity_loss( + File "/workspace/LLM-BC/llmbc/discriminator/llm_ce_discriminator.py", line 56, in compute_similarity_loss + outputs, label_ids = self.llm_translator.forward( + File "/workspace/LLM-BC/llmbc/translator/llm_translator.py", line 321, in forward + outputs = self.model( + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/workspace/LLM-BC/llmbc/model/llm/llama_lowdim_model.py", line 122, in forward + return super().forward( + File "/venv/llm-bc/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 1163, in forward + outputs = self.model( + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 913, in forward + layer_outputs = decoder_layer( + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 640, in forward + hidden_states, self_attn_weights, present_key_value = self.self_attn( + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 523, in forward + key_states = self.k_proj(hidden_states) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl + return forward_call(*args, **kwargs) + File "/venv/llm-bc/lib/python3.9/site-packages/torch/nn/modules/linear.py", line 116, in forward + return F.linear(input, self.weight, self.bias) +KeyboardInterrupt diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/requirements.txt b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..f18b63306b50dded477ccac6858260d859b2a206 --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/requirements.txt @@ -0,0 +1,864 @@ +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +llmbc==0.0.0 +llmbc==0.0.0 +aiohappyeyeballs==2.6.1 +antlr4-python3-runtime==4.9.3 +asciitree==0.3.3 +async-timeout==5.0.1 +attrs==25.4.0 +certifi==2025.10.5 +charset-normalizer==3.4.4 +colorama==0.4.6 +dill==0.3.8 +docstring-parser==0.16 +eval_type_backport==0.2.2 +fasteners==0.20 +filelock==3.17.0 +frozenlist==1.8.0 +fsspec==2024.3.1 +gmpy2==2.2.1 +hf-xet==1.1.8 +idna==3.11 +llvmlite==0.39.1 +MarkupSafe==3.0.2 +mdurl==0.1.2 +mkl-service==2.4.0 +mpmath==1.3.0 +msgpack==1.1.1 +networkx==3.2.1 +packaging==25.0 +propcache==0.3.1 +psutil==7.0.0 +pycparser==2.23 +Pygments==2.19.1 +PyOpenGL==3.1.10 +PySocks==1.7.1 +tzdata==2025.3 +xxhash==3.5.0 +pytz==2025.2 +PyYAML==6.0.2 +regex==2025.9.1 +safetensors==0.5.3 +setuptools==80.9.0 +shtab==1.7.2 +six==1.17.0 +tqdm==4.67.1 +tensorboard==2.15.2 +uvloop==0.22.1 +wheel==0.45.1 +zipp==3.21.0 +tensorflow-estimator==2.15.0 +tensorboard-data-server==0.7.2 +google-auth-oauthlib==1.3.1 +tensorflow==2.15.1 +Jinja2==3.1.6 +markdown-it-py==2.2.0 +multiprocess==0.70.15 +numpy==1.23.5 +pillow==11.3.0 +pip==23.3.2 +python-dateutil==2.9.0.post0 +aiosignal==1.4.0 +brotlicffi==1.0.9.2 +hydra-core==1.2.0 +multidict==6.7.0 +pycares==4.10.0 +rich==14.2.0 +sympy==1.14.0 +typeguard==4.4.4 +aiodns==3.5.0 +urllib3==2.5.0 +yarl==1.18.0 +aiohttp==3.12.15 +pyarrow==21.0.0 +pyarrow-hotfix==0.7 +tokenizers==0.21.0 +av==10.0.0 +einops==0.4.1 +Bottleneck==1.4.2 +mkl_fft==1.3.11 +mkl_random==1.2.8 +numba==0.56.4 +numcodecs==0.12.1 +numexpr==2.10.1 +pandas==2.3.3 +zarr==2.12.0 +datasets==2.19.0 +transformers==4.47.1 +accelerate==1.0.1 +peft==0.14.0 +trl==0.11.4 +torch==2.2.2 +tabulate==0.9.0 +sentencepiece==0.2.0 +pyperclip==1.11.0 +PyOpenGL-accelerate==3.1.10 +pydub==0.25.1 +py-cpuinfo==9.0.0 +pure_eval==0.2.3 +ptyprocess==0.7.0 +nvidia-ml-py==13.595.45 +hjson==3.1.0 +gym-notices==0.1.0 +glfw==2.0.0 +Farama-Notifications==0.0.4 +websockets==15.0.1 +wcwidth==0.6.0 +uc-micro-py==1.0.3 +typing-inspection==0.4.2 +triton==2.2.0 +trimesh==4.11.5 +transforms3d==0.4.2 +traitlets==5.14.3 +threadpoolctl==3.6.0 +tenacity==9.1.2 +sniffio==1.3.1 +smmap==5.0.3 +setproctitle==1.3.7 +sentry-sdk==2.57.0 +semantic-version==2.10.0 +scipy==1.13.1 +rpds-py==0.27.1 +python-multipart==0.0.20 +pyparsing==3.3.2 +pynvml==13.0.1 +pydantic_core==2.41.5 +pycryptodomex==3.23.0 +pyasn1==0.6.3 +grpcio==1.80.0 +platformdirs==4.4.0 +pexpect==4.9.0 +parso==0.8.6 +orjson==3.11.5 +opencv-python==4.11.0.86 +stack-data==0.6.3 +omegaconf==2.2.1 +nvidia-nvtx-cu12==12.1.105 +nvidia-nvjitlink-cu12==12.9.86 +nvidia-nccl-cu12==2.19.3 +nvidia-curand-cu12==10.3.2.106 +nvidia-cufft-cu12==11.0.2.54 +nvidia-cuda-runtime-cu12==12.1.105 +nvidia-cuda-nvrtc-cu12==12.1.105 +nvidia-cuda-cupti-cu12==12.1.105 +nvidia-cublas-cu12==12.1.3.1 +ninja==1.13.0 +narwhals==2.19.0 +lxml==6.0.3 +kiwisolver==1.4.7 +joblib==1.5.3 +jiter==0.13.0 +imageio-ffmpeg==0.6.0 +ImageIO==2.37.2 +h5py==3.14.0 +h11==0.16.0 +fonttools==4.60.2 +ffmpy==1.0.0 +fast_kinematics==0.2.2 +executing==2.2.1 +exceptiongroup==1.3.1 +docker-pycreds==0.4.0 +distro==1.9.0 +decorator==5.2.1 +dacite==1.9.2 +cycler==0.12.1 +contourpy==1.3.0 +cloudpickle==3.1.2 +click==8.1.8 +asttokens==3.0.1 +annotated-types==0.7.0 +annotated-doc==0.0.4 +aiofiles==25.1.0 +absl-py==2.3.1 +uvicorn==0.39.0 +tiktoken==0.8.0 +scikit-learn==1.6.1 +sapien==3.0.0b1 +referencing==0.36.2 +pydantic==2.12.5 +pyasn1_modules==0.4.2 +prompt_toolkit==3.0.52 +nvidia-cusparse-cu12==12.1.0.106 +nvidia-cudnn-cu12==8.9.2.26 +nltk==3.9.2 +mujoco==2.3.7 +mdit-py-plugins==0.3.3 +matplotlib-inline==0.2.1 +matplotlib==3.7.5 +linkify-it-py==2.0.3 +jedi==0.19.2 +huggingface-hub==0.26.2 +httpcore==1.0.9 +gymnasium==0.29.1 +google-pasta==0.2.0 +gitdb==4.0.12 +cryptography==46.0.7 +blobfile==3.0.0 +anyio==4.12.1 +tyro==0.9.1 +toppra==0.6.6 +starlette==0.49.3 +seaborn==0.13.2 +rouge_score==0.1.2 +pynndescent==0.6.0 +nvidia-cusolver-cu12==11.4.5.107 +jsonschema-specifications==2025.9.1 +ipython==8.18.1 +httpx==0.28.1 +gymnasium-robotics==1.2.0 +google-auth==2.49.2 +GitPython==3.1.46 +diffusers==0.31.0 +wandb==0.18.6 +umap-learn==0.5.9.post2 +requests-oauthlib==2.0.0 +openai==2.8.1 +mplib==0.1.1 +jsonschema==4.25.1 +gradio_client==0.2.9 +google-genai==1.47.0 +fastapi==0.128.8 +torchvision==0.17.2 +torchaudio==2.2.2 +sentence-transformers==3.2.1 +pytorch-seed==0.2.0 +deepspeed==0.16.1 +bitsandbytes==0.45.0 +altair==6.0.0 +timm==1.0.22 +gradio==3.36.1 +evaluate==0.4.3 +arm_pytorch_utilities==0.5.0 +tensorflow-io-gcs-filesystem==0.37.1 +Markdown==3.9 +pybullet==3.2.6 +wrapt==1.14.2 +tensorflow-probability==0.23.0 +parse==1.19.1 +dm-tree==0.1.8 +termcolor==3.1.0 +requests==2.32.0 +cffi==2.0.0 +opt_einsum==3.4.0 +labmaze==1.0.6 +typing_extensions==4.15.0 +importlib-resources==5.13.0 +importlib-metadata==5.2.0 +FLAML==2.3.6 +dm-env==1.6 +diskcache==5.6.3 +Cython==0.29.37 +mujoco-py==2.1.2.14 +jaxlib==0.4.30 +dm-control==1.0.14 +cmudict==1.0.13 +syllables==1.0.9 +metaworld==2.0.0 +jax==0.4.30 +highway-env==1.9.1 +gym_bandits==0.0.2 +d4rl==1.1 +pyautogen==0.1.0 +protobuf==4.25.9 +tf-agents==0.19.0 +oauthlib==3.3.1 +pytorch-kinematics==0.7.5 +pygame==2.6.1 +gin-config==0.5.0 +mani_skill==3.0.0b20 +tifffile==2024.8.30 +Shapely==1.8.4 +PyWavelets==1.6.0 +Werkzeug==3.1.8 +astunparse==1.6.3 +scikit-image==0.19.3 +pymunk==6.2.1 +ml-dtypes==0.3.2 +gast==0.7.0 +stable-baselines3==2.2.1 +keras==2.15.0 +libclang==18.1.1 +flatbuffers==25.12.19 +gym==0.23.1 +llmbc==0.0.0 +mjrl==1.0.0 +llfbench==0.1.0 +autocommand==2.2.2 +backports.tarfile==1.2.0 +importlib_metadata==8.0.0 +inflect==7.3.1 +jaraco.collections==5.1.0 +jaraco.context==5.3.0 +jaraco.functools==4.0.1 +jaraco.text==3.12.1 +more-itertools==10.3.0 +packaging==24.2 +platformdirs==4.2.2 +tomli==2.0.1 +typeguard==4.3.0 +typing_extensions==4.12.2 +wheel==0.45.1 +zipp==3.19.2 diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/wandb-metadata.json b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/wandb-metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..ada933a4e6a1a1878beba209836c09227b29afaf --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/wandb-metadata.json @@ -0,0 +1,56 @@ +{ + "os": "Linux-5.15.0-168-generic-x86_64-with-glibc2.39", + "python": "3.9.25", + "startedAt": "2026-04-14T06:28:00.115458Z", + "args": [ + "--config-path", + "config/mix_data", + "--config-name", + "llmdp_sweep-v2_mix(csp5).yaml", + "policy.loss_llm_weight=1.0e-3" + ], + "program": "/workspace/LLM-BC/./train.py", + "codePath": "train.py", + "git": { + "remote": "https://github.com/CHYang25/LLM-BC.git", + "commit": "16b534f5ac2111b9cbfa638ab62d7944bff711d2" + }, + "email": "chris920325@gmail.com", + "root": "/workspace/LLM-BC/data/outputs/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2", + "host": "c8ef52649900", + "username": "root", + "executable": "/venv/llm-bc/bin/python3", + "codePathLocal": "train.py", + "cpu_count": 72, + "cpu_count_logical": 144, + "gpu": "NVIDIA GeForce RTX 4090", + "gpu_count": 2, + "disk": { + "/": { + "total": "545460846592", + "used": "352995950592" + } + }, + "memory": { + "total": "810942898176" + }, + "cpu": { + "count": 72, + "countLogical": 144 + }, + "gpu_nvidia": [ + { + "name": "NVIDIA GeForce RTX 4090", + "memoryTotal": "25757220864", + "cudaCores": 16384, + "architecture": "Ada" + }, + { + "name": "NVIDIA GeForce RTX 4090", + "memoryTotal": "25757220864", + "cudaCores": 16384, + "architecture": "Ada" + } + ], + "cudaVersion": "12.8" +} \ No newline at end of file diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/wandb-summary.json b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/wandb-summary.json new file mode 100644 index 0000000000000000000000000000000000000000..4c64925abdd723a0a4e7cdf61914ddb1d351a316 --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/files/wandb-summary.json @@ -0,0 +1 @@ +{"train_loss_llm":0.457424521446228,"global_step":350,"lr":4.4e-06,"_step":350,"train_loss":1.038795828819275,"train_loss_dp":1.0383384227752686,"epoch":0,"_runtime":123.52932171,"_timestamp":1.7761482035517893e+09,"_wandb":{"runtime":123}} \ No newline at end of file diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/run-40wpvpiq.wandb b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/run-40wpvpiq.wandb new file mode 100644 index 0000000000000000000000000000000000000000..9db87ad7fa464d7563c85511aed50f80d9bf6d50 --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_062800-40wpvpiq/run-40wpvpiq.wandb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6937d6127c91e64cde28ba2cdd56468f83f6d918acbe58c345200a773fc4559 +size 327680 diff --git a/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json new file mode 100644 index 0000000000000000000000000000000000000000..229ca5afc4d98a8228f5f28e8ad8326fd7cd8e3b --- /dev/null +++ b/2026.04.14/06.26.55_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/wandb-resume.json @@ -0,0 +1 @@ +{"run_id": "40wpvpiq"} \ No newline at end of file diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..22552e7b0295040a5534599fe06331d5979c04e6 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/config.yaml @@ -0,0 +1,193 @@ +name: train_llm_diffusion_unet_lowdim +_target_: llmbc.workspace.train_llm_diffusion_unet_lowdim_workspace.TrainLLMDiffusionUnetLowdimWorkspace +obs_dim: ${task.obs_dim} +action_dim: ${task.action_dim} +task_name: ${task.name} +exp_name: default +model_name: ${llm.name} +horizon: 1 +n_obs_steps: 1 +n_action_steps: 1 +n_latency_steps: 0 +past_action_visible: false +keypoint_visible_rate: 1.0 +obs_as_local_cond: false +obs_as_global_cond: true +pred_action_steps_only: false +llm_orig_expert_feedback: true +llm_do_sample: false +policy: + _target_: llmbc.policy.llm_diffusion_unet_lowdim_policy.LLMDiffusionUnetLowdimPolicy + model: + _target_: llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D + input_dim: '${eval: ${task.action_dim} if ${obs_as_local_cond} or ${obs_as_global_cond} + else ${task.obs_dim} + ${task.action_dim}}' + local_cond_dim: '${eval: ${task.obs_dim} if ${obs_as_local_cond} else None}' + global_cond_dim: '${eval: ${task.obs_dim}*${n_obs_steps} if ${obs_as_global_cond} + else None}' + diffusion_step_embed_dim: 256 + down_dims: + - 256 + - 512 + - 1024 + kernel_size: 5 + n_groups: 8 + cond_predict_scale: true + noise_scheduler: + _target_: diffusers.schedulers.scheduling_ddpm.DDPMScheduler + num_train_timesteps: 100 + beta_start: 0.0001 + beta_end: 0.02 + beta_schedule: squaredcos_cap_v2 + variance_type: fixed_small + clip_sample: true + prediction_type: epsilon + horizon: ${horizon} + obs_dim: ${obs_dim} + action_dim: ${action_dim} + n_action_steps: ${eval:'${n_action_steps}+${n_latency_steps}'} + n_obs_steps: ${n_obs_steps} + num_inference_steps: 100 + obs_as_local_cond: ${obs_as_local_cond} + obs_as_global_cond: ${obs_as_global_cond} + pred_action_steps_only: ${pred_action_steps_only} + oa_step_convention: true + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + task_id: ${task_name} + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + cfg: ${llm} + obs_dim: ${obs_dim} + action_dim: ${action_dim} + horizon: ${horizon} + n_obs_steps: ${n_obs_steps} + n_action_steps: ${eval:'${n_action_steps}+${n_latency_steps}'} + loss_dp_weight: 1.0 + loss_llm_weight: 0.01 + normalize_llm_loss: true + reweight_llm_loss: true +ema: + _target_: llmbc.model.diffusion.ema_model.EMAModel + update_after_step: 0 + inv_gamma: 1.0 + power: 0.75 + min_value: 0.0 + max_value: 0.9999 +dataloader: + batch_size: 16 + num_workers: 0 + shuffle: true + pin_memory: false + persistent_workers: false +val_dataloader: + batch_size: 16 + num_workers: 0 + shuffle: false + pin_memory: false + persistent_workers: false +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + betas: + - 0.95 + - 0.999 + eps: 1.0e-08 + weight_decay: 1.0e-06 +training: + device: cuda:0 + seed: 42 + debug: false + resume: true + lr_scheduler: cosine + lr_warmup_steps: 500 + num_epochs: 1001 + gradient_accumulate_every: 16 + use_ema: true + rollout_every: 5 + checkpoint_every: 5 + val_every: 1 + sample_every: 5 + max_train_steps: null + max_val_steps: null + tqdm_interval_sec: 1.0 +logging: + project: ${task.name}-training-mix + resume: true + mode: online + name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} + tags: + - ${name} + - ${task_name} + - ${exp_name} + id: null + group: null +checkpoint: + topk: + monitor_key: test_success_rate + mode: max + k: 5 + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + save_last_ckpt: true + save_last_snapshot: false +multi_run: + run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name} +task: + name: sweep-v2 + obs_dim: 9 + action_dim: 4 + env_runner: + _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner + env_name: llf-metaworld-sweep-v2 + n_train: 10 + n_test: 50 + n_envs: 10 + max_steps: 30 + n_obs_steps: ${n_obs_steps} + n_action_steps: ${n_action_steps} + instruction_type: b + feedback_type: + - hp + - hn + - fp + visual: false + discount: 0.9 + dataset: + _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset + data_path: datasets/sweep-v2-mix(csp5).pt + data_path2: datasets/sweep-v2.pt + horizon: ${horizon} + pad_before: ${eval:'${n_obs_steps}-1'} + pad_after: ${eval:'${n_action_steps}-1'} + obs_eef_target: true + use_manual_normalizer: false + val_ratio: 0.1 + dummy_normalizer: false + instructor: + _target_: llmbc.translator.instructor.metaworld_instructor.sweep_v2_instructor.SweepV2Instructor +llm: + name: HuggingFaceTB/SmolLM2-135M-Instruct + model_name: SmolLM2-135M-Instruct + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + use_quantization: false + use_joint_mlp_projector: true + llm_mode: ete-finetuned + finetune_mode: orig + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + max_length: 100 + lora_config: + r: 32 + lora_alpha: 64 + lora_dropout: 0.05 + bias: none + task_type: CAUSAL_LM + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + hydra: + job: + override_dirname: ${model_name} + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${model_name} diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..69903f501f0f216a9d3f1579b308a47dc164220c --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/hydra.yaml @@ -0,0 +1,155 @@ +hydra: + run: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + sweep: + dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - policy.loss_llm_weight=1.0e-2 + job: + name: train + chdir: null + override_dirname: policy.loss_llm_weight=1.0e-2 + id: ??? + num: ??? + config_name: llmdp_sweep-v2_mix(csp5).yaml + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.2.0 + version_base: '1.2' + cwd: /workspace/LLM-BC + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /workspace/LLM-BC/config/mix_data + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /workspace/LLM-BC/data/outputs/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7343b6263cb3c7b74167b25f5e33f1ef666ae6df --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/.hydra/overrides.yaml @@ -0,0 +1 @@ +- policy.loss_llm_weight=1.0e-2 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0180-test_success_rate=0.800.ckpt b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0180-test_success_rate=0.800.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..3d099fb6bc8db090c30a8a2ae1cf248b568b3519 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0180-test_success_rate=0.800.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c33d4de138a11e92ed54df6269b25434292d0217348a9891a824683d927173 +size 1040498994 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0210-test_success_rate=0.820.ckpt b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0210-test_success_rate=0.820.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..e54993b927a0b1847df71cc25f488ff1388c72b4 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0210-test_success_rate=0.820.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2bc48c8a7d4ec783614bd156bc4754c0ea049c0996d6c506ea1123b212bf56 +size 1040498994 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0260-test_success_rate=0.800.ckpt b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0260-test_success_rate=0.800.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..e5e268f3593ecc025d86f6679d4e2f175a71a026 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0260-test_success_rate=0.800.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3b71690ef0ca39e842c2ed7b1deb7c428536d07aefce0e2a06c22def3a430c +size 1040498994 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0430-test_success_rate=0.800.ckpt b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0430-test_success_rate=0.800.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..cdc9426e7595a2733eb30539bfcf08362f1f5c90 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0430-test_success_rate=0.800.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a5a967d017f6b0137eb0bcffdac8181133e99170d6f926789fe557a3a9ea57 +size 1040498994 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0475-test_success_rate=0.820.ckpt b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0475-test_success_rate=0.820.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..a5944e663d343bd46df843e93f2d873f11534c88 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/epoch=0475-test_success_rate=0.820.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f49ec61c2f6bd4fc160d152edb7a1d3d287a1b6b4006747ebb3862dcf9b86b5a +size 1040498994 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/latest.ckpt b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/latest.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..2b6bfde888905991cd5faa0f32c7465f00e0fe4c --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/checkpoints/latest.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a1d2dbe03d086e94e2646a2034d85381b14ecafe07935f1a2aaedd70c6cf7e2 +size 1040498994 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt new file mode 100644 index 0000000000000000000000000000000000000000..9ed8aad833a8f96f6a0e6dea1a8d7f31c9f96c5b --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/logs.json.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52e3ab39b238c51912874c73da9e218f128c19a30218049ddd15f37148a79b98 +size 97964862 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/train.log b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/train.log new file mode 100644 index 0000000000000000000000000000000000000000..68a21160489e15a124abfdd15f61b45eed23fad5 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/train.log @@ -0,0 +1,14 @@ +[2026-04-14 06:30:10,702][numexpr.utils][INFO] - Note: detected 144 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable. +[2026-04-14 06:30:10,702][numexpr.utils][INFO] - Note: NumExpr detected 144 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16. +[2026-04-14 06:30:10,703][numexpr.utils][INFO] - NumExpr defaulting to 16 threads. +[2026-04-14 06:30:13,036][datasets][INFO] - PyTorch version 2.2.2 available. +[2026-04-14 06:30:13,037][datasets][INFO] - TensorFlow version 2.15.1 available. +[2026-04-14 06:30:13,037][datasets][INFO] - JAX version 0.4.30 available. +[2026-04-14 06:30:14,676][llmbc.model.diffusion.conditional_unet1d][INFO] - number of parameters: 6.501479e+07 +[2026-04-14 06:30:19,323][root][INFO] - running build_ext +[2026-04-14 06:30:19,325][root][INFO] - building 'mujoco_py.cymj' extension +[2026-04-14 06:30:19,325][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /venv/llm-bc/include -I/venv/llm-bc/include -fPIC -O2 -isystem /venv/llm-bc/include -fPIC -I/venv/llm-bc/lib/python3.9/site-packages/mujoco_py -I/root/.mujoco/mujoco210/include -I/venv/llm-bc/lib/python3.9/site-packages/numpy/core/include -I/venv/llm-bc/include/python3.9 -c /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.c -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.o -fopenmp -w +[2026-04-14 06:31:01,701][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /venv/llm-bc/include -I/venv/llm-bc/include -fPIC -O2 -isystem /venv/llm-bc/include -fPIC -I/venv/llm-bc/lib/python3.9/site-packages/mujoco_py -I/root/.mujoco/mujoco210/include -I/venv/llm-bc/lib/python3.9/site-packages/numpy/core/include -I/venv/llm-bc/include/python3.9 -c /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.c -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.o -fopenmp -w +[2026-04-14 06:31:01,840][root][INFO] - gcc -pthread -B /venv/llm-bc/compiler_compat -shared -Wl,-rpath,/venv/llm-bc/lib -Wl,-rpath-link,/venv/llm-bc/lib -L/venv/llm-bc/lib -L/venv/llm-bc/lib -Wl,-rpath,/venv/llm-bc/lib -Wl,-rpath-link,/venv/llm-bc/lib -L/venv/llm-bc/lib /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/cymj.o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/temp.linux-x86_64-cpython-39/venv/llm-bc/lib/python3.9/site-packages/mujoco_py/gl/osmesashim.o -L/root/.mujoco/mujoco210/bin -Wl,--enable-new-dtags,-rpath,/root/.mujoco/mujoco210/bin -lmujoco210 -lglewosmesa -lOSMesa -lGL -o /venv/llm-bc/lib/python3.9/site-packages/mujoco_py/generated/_pyxbld_2.1.2.14_39_linuxcpuextensionbuilder/lib.linux-x86_64-cpython-39/mujoco_py/cymj.cpython-39-x86_64-linux-gnu.so -fopenmp +[2026-04-14 06:31:45,415][absl][INFO] - MUJOCO_GL=osmesa, attempting to import specified OpenGL backend. +[2026-04-14 06:31:45,424][absl][INFO] - MuJoCo library version is: 2.3.7 diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063146-ar8xzudz/files/config.yaml b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063146-ar8xzudz/files/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..549c65367ae5ba87feb7d23f0a0c73dfa14f0181 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063146-ar8xzudz/files/config.yaml @@ -0,0 +1,304 @@ +_target_: + value: llmbc.workspace.train_llm_diffusion_unet_lowdim_workspace.TrainLLMDiffusionUnetLowdimWorkspace +_wandb: + value: + cli_version: 0.18.6 + m: [] + python_version: 3.9.25 + t: + "1": + - 1 + - 2 + - 3 + - 5 + - 11 + - 12 + - 41 + - 49 + - 50 + - 51 + - 53 + - 55 + - 71 + - 83 + - 95 + - 98 + - 100 + - 105 + "2": + - 1 + - 2 + - 3 + - 5 + - 11 + - 12 + - 41 + - 49 + - 50 + - 51 + - 53 + - 55 + - 71 + - 83 + - 95 + - 98 + - 100 + - 105 + "3": + - 13 + - 15 + - 16 + - 23 + - 55 + - 61 + "4": 3.9.25 + "5": 0.18.6 + "6": 4.47.1 + "8": + - 5 + "12": 0.18.6 + "13": linux-x86_64 +action_dim: + value: 4 +checkpoint: + value: + save_last_ckpt: true + save_last_snapshot: false + topk: + format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt + k: 5 + mode: max + monitor_key: test_success_rate +dataloader: + value: + batch_size: 16 + num_workers: 0 + persistent_workers: false + pin_memory: false + shuffle: true +ema: + value: + _target_: llmbc.model.diffusion.ema_model.EMAModel + inv_gamma: 1 + max_value: 0.9999 + min_value: 0 + power: 0.75 + update_after_step: 0 +exp_name: + value: default +horizon: + value: 1 +keypoint_visible_rate: + value: 1 +llm: + value: + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + finetune_mode: orig + hydra: + job: + override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct + run: + dir: data/outputs/2026.04.14/06.30.09_HuggingFaceTB/SmolLM2-135M-Instruct + llm_mode: ete-finetuned + lora_config: + bias: none + lora_alpha: 64 + lora_dropout: 0.05 + r: 32 + task_type: CAUSAL_LM + max_length: 100 + model_name: SmolLM2-135M-Instruct + name: HuggingFaceTB/SmolLM2-135M-Instruct + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + use_joint_mlp_projector: true + use_quantization: false +llm_do_sample: + value: false +llm_orig_expert_feedback: + value: true +logging: + value: + group: null + id: null + mode: online + name: 2026.04.14-06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2 + project: sweep-v2-training-mix + resume: true + tags: + - train_llm_diffusion_unet_lowdim + - sweep-v2 + - default +model_name: + value: HuggingFaceTB/SmolLM2-135M-Instruct +multi_run: + value: + run_dir: data/outputs/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2 + wandb_name_base: 2026.04.14-06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2 +n_action_steps: + value: 1 +n_latency_steps: + value: 0 +n_obs_steps: + value: 1 +name: + value: train_llm_diffusion_unet_lowdim +obs_as_global_cond: + value: true +obs_as_local_cond: + value: false +obs_dim: + value: 9 +optimizer: + value: + _target_: torch.optim.AdamW + betas: + - 0.95 + - 0.999 + eps: 1e-08 + lr: 0.0001 + weight_decay: 1e-06 +output_dir: + value: /workspace/LLM-BC/data/outputs/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2 +past_action_visible: + value: false +policy: + value: + _target_: llmbc.policy.llm_diffusion_unet_lowdim_policy.LLMDiffusionUnetLowdimPolicy + action_dim: 4 + horizon: 1 + llm_discriminator: + _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator + llm_translator: + _target_: llmbc.translator.llm_translator.LLMTranslator + action_dim: 4 + cfg: + causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM + checkpoint: data/outputs/2025.11.01/23.03.01_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-5690 + config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig + finetune_mode: orig + hydra: + job: + override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct + run: + dir: data/outputs/2026.04.14/06.30.09_HuggingFaceTB/SmolLM2-135M-Instruct + llm_mode: ete-finetuned + lora_config: + bias: none + lora_alpha: 64 + lora_dropout: 0.05 + r: 32 + task_type: CAUSAL_LM + max_length: 100 + model_name: SmolLM2-135M-Instruct + name: HuggingFaceTB/SmolLM2-135M-Instruct + prompter: + _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter + use_joint_mlp_projector: true + use_joint_mlp_projector: true + use_quantization: false + horizon: 1 + n_action_steps: 1 + n_obs_steps: 1 + obs_dim: 9 + task_id: sweep-v2 + loss_dp_weight: 1 + loss_llm_weight: 0.01 + model: + _target_: llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D + cond_predict_scale: true + diffusion_step_embed_dim: 256 + down_dims: + - 256 + - 512 + - 1024 + global_cond_dim: 9 + input_dim: 4 + kernel_size: 5 + local_cond_dim: null + n_groups: 8 + n_action_steps: 1 + n_obs_steps: 1 + noise_scheduler: + _target_: diffusers.schedulers.scheduling_ddpm.DDPMScheduler + beta_end: 0.02 + beta_schedule: squaredcos_cap_v2 + beta_start: 0.0001 + clip_sample: true + num_train_timesteps: 100 + prediction_type: epsilon + variance_type: fixed_small + normalize_llm_loss: true + num_inference_steps: 100 + oa_step_convention: true + obs_as_global_cond: true + obs_as_local_cond: false + obs_dim: 9 + pred_action_steps_only: false + reweight_llm_loss: true +pred_action_steps_only: + value: false +task: + value: + action_dim: 4 + dataset: + _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset + data_path: datasets/sweep-v2-mix(csp5).pt + data_path2: datasets/sweep-v2.pt + dummy_normalizer: false + horizon: 1 + obs_eef_target: true + pad_after: 0 + pad_before: 0 + use_manual_normalizer: false + val_ratio: 0.1 + env_runner: + _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner + discount: 0.9 + env_name: llf-metaworld-sweep-v2 + feedback_type: + - hp + - hn + - fp + instruction_type: b + max_steps: 30 + n_action_steps: 1 + n_envs: 10 + n_obs_steps: 1 + n_test: 50 + n_train: 10 + visual: false + instructor: + _target_: llmbc.translator.instructor.metaworld_instructor.sweep_v2_instructor.SweepV2Instructor + name: sweep-v2 + obs_dim: 9 +task_name: + value: sweep-v2 +training: + value: + checkpoint_every: 5 + debug: false + device: cuda:0 + gradient_accumulate_every: 16 + lr_scheduler: cosine + lr_warmup_steps: 500 + max_train_steps: null + max_val_steps: null + num_epochs: 1001 + resume: true + rollout_every: 5 + sample_every: 5 + seed: 42 + tqdm_interval_sec: 1 + use_ema: true + val_every: 1 +val_dataloader: + value: + batch_size: 16 + num_workers: 0 + persistent_workers: false + pin_memory: false + shuffle: false diff --git a/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063146-ar8xzudz/files/output.log b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063146-ar8xzudz/files/output.log new file mode 100644 index 0000000000000000000000000000000000000000..db44fe9ed3980844c9a925b05cf7e41bf4a4bf81 --- /dev/null +++ b/2026.04.14/06.30.09_train_llm_diffusion_unet_lowdim_sweep-v2/wandb/run-20260414_063146-ar8xzudz/files/output.log @@ -0,0 +1,3 @@ +Eval MetaworldLowdimRunner 1/6: 0%| | 0/30 [00:00