Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+language:
+- en
+tags:
+- fusion-bench
+base_model: meta-llama/Llama-3.2-1B-Instruct
+pipeline_tag: text-generation
+library_name: transformers
+datasets:
+- hendrydong/preference_700K
+---
+
+# Model Overview
+
+This model has been fine-tuned on the hendrydong/preference_700K dataset for 2 epochs, using the Llama-3.2-1B-Instruct model as the base.
+See [config](./hydra_output_2024-12-01_00-02-51/.hydra/config.yaml) for more details about the training hyperparameters.
+
+![alt text](tb_logs.png)
+
+Fine-tuning was done using the [fusion-bench](https://github.com/tanganke/fusion_bench):
+
+```bash
+fusion_bench --config-name llama_full_finetune \
+  fabric.loggers.name=llama_full_bradley_terry_rm \
+  method=lm_finetune/bradley_terry_rm \
+  method.dataloader_kwargs.batch_size=8 \
+  method.accumulate_grad_batches=16 \
+  method.lr_scheduler.min_lr=1e-7 \
+  method.lr_scheduler.max_lr=5e-6 \
+  method.lr_scheduler.warmup_steps=100 \
+  method.optimizer.lr=0 \
+  method.optimizer.weight_decay=0.001 \
+  method.gradient_clip_val=1 \
+  method.max_epochs=2 \
+  method.checkpoint_save_interval=epoch \
+  method.checkpoint_save_frequency=1 \
+  modelpool=SeqenceClassificationModelPool/llama_preference700k
+```
+
+8 GPUs, per-GPU batch size is 8, with gradient accumulation of 16 steps, so the effective batch size is 1024.

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "architectures": [
+    "LlamaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

events.out.tfevents.1732982699.amax.254571.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd840f74b9d9951672d58e54a0f9a8aa3ddc9a21d144bd62abbb7fc81fe615c
+size 424134

hydra_output_2024-12-01_00-02-51/.hydra/config.yaml

@@ -0,0 +1,87 @@
+fabric:
+  loggers:
+    _target_: lightning.fabric.loggers.TensorBoardLogger
+    root_dir: outputs/logs
+    name: llama_full_bradly_terry_rm
+    version: null
+    sub_dir: null
+    default_hp_metric: false
+  strategy:
+    _target_: lightning.fabric.strategies.FSDPStrategy
+    sharding_strategy: FULL_SHARD
+    cpu_offload: false
+    auto_wrap_policy:
+      _target_: fusion_bench.mixins.lightning_fabric.get_policy
+      _args_:
+      - transformers.models.llama.modeling_llama.LlamaDecoderLayer
+    activation_checkpointing_policy: ${.auto_wrap_policy}
+  _target_: lightning.Fabric
+  _recursive_: true
+  devices: auto
+  accelerator: auto
+  precision: bf16-true
+method:
+  _target_: fusion_bench.method.BradlyTerryRewardModeling
+  _recursive_: false
+  optimizer:
+    _target_: torch.optim.AdamW
+    lr: 0
+    weight_decay: 0.001
+    fused: null
+  lr_scheduler:
+    _target_: fusion_bench.optim.lr_scheduler.CosineDecayWithWarmup
+    T_max: _T_max_
+    init_lr: 0
+    warmup_steps: 100
+    max_lr: 5.0e-06
+    min_lr: 1.0e-07
+  dataloader_kwargs:
+    batch_size: 8
+    num_workers: 0
+    pin_memory: true
+  max_epochs: 2
+  max_steps: -1
+  max_steps_per_epoch: -1
+  accumulate_grad_batches: 16
+  lr_scheduler_interval: step
+  lr_scheduler_frequency: 1
+  checkpoint_save_interval: epoch
+  checkpoint_save_frequency: 1
+  gradient_clip_val: 1
+  gradient_clip_algorithm: norm
+  save_optimizer_state: false
+  save_full_model: true
+  save_ckpt_type: lightning
+  ckpt_path: null
+  max_length: 4096
+  fix_token_embedding: true
+modelpool:
+  _target_: fusion_bench.modelpool.CausalLMPool
+  pretrained_model_name_or_path: meta-llama/Llama-3.2-1B-Instruct
+  models:
+    _pretrained_:
+      _target_: fusion_bench.modelpool.seq_classification_lm.create_reward_model_from_pretrained
+      pretrained_model_name_or_path: ${...pretrained_model_name_or_path}
+      torch_dtype: bfloat16
+      use_flash_attention_2: true
+  tokenizer:
+    _target_: transformers.AutoTokenizer.from_pretrained
+    pretrained_model_name_or_path: ${..pretrained_model_name_or_path}
+    pad_token: <|end_of_text|>
+  train_datasets:
+    preference_700k:
+      _target_: fusion_bench.dataset.llama.preference_700k.load_tokenized_preference_700k_for_bradley_terry_rm
+      tokenizer: ${...tokenizer}
+      path: hendrydong/preference_700K
+      split: train
+      cache_path: null
+taskpool:
+  _target_: fusion_bench.taskpool.DummyTaskPool
+  model_save_path: null
+_target_: fusion_bench.programs.FabricModelFusionProgram
+_recursive_: false
+fast_dev_run: false
+dry_run: false
+print_config: true
+report_save_path: null
+print_function_call: true

hydra_output_2024-12-01_00-02-51/.hydra/hydra.yaml

@@ -0,0 +1,206 @@
+hydra:
+  run:
+    dir: outputs/${hydra.job.name}/${now:%Y-%m-%d_%H-%M-%S}
+  sweep:
+    dir: outputs/${hydra.job.name}/${now:%Y-%m-%d_%H-%M-%S}
+    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: fusion_bench
+    header: == ${hydra.help.app_name} ==
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help'
+    template: '${hydra.help.header}
+
+
+      fusion_bench is the command line interface for running model fusion benchmarks
+      in the FusionBench project.
+
+      It provides a flexible way to configure and execute various fusion algorithms
+      on different model pools and evaluate them across multiple tasks.
+
+
+      == Configuration groups ==
+
+      Compose your configuration from these groups (method, modelpool, taskpool are
+      the most important):
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      You can override options, for example:
+
+      fusion_bench method=task_arithmetic modelpool=clip-vit-base-patch32_svhn_and_mnist
+      taskpool=clip-vit-base-patch32_svhn_and_mnist
+
+
+      == Basic usage ==
+
+      fusion_bench [--config-path CONFIG_PATH] [--config-name CONFIG_NAME] OPTION_1=VALUE_1
+      OPTION_2=VALUE_2 ...
+
+
+      == Key options ==
+
+      --help, -h            : Print this help message and exit
+
+      --hydra-help          : Hydra''s help
+
+      --cfg, -c             : Show config instead of running [job|hydra|all]
+
+      --config-path, -cp    : Overrides the config_path
+
+      --config-name, -cn    : Overrides the config_name
+
+      --shell-completion, -sc : Install or Uninstall shell completion
+
+
+      For more detailed information on options and usage, please refer to the online
+      documentation:
+
+      https://tanganke.github.io/fusion_bench/cli/fusion_bench/
+
+
+      ${hydra.help.footer}'
+  hydra_help:
+    template: 'Hydra (${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'
+      rich_handler:
+        format: '%(message)s'
+    handlers:
+      console:
+        class: rich.logging.RichHandler
+        formatter: rich_handler
+      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:
+    - fabric.loggers.name=llama_full_bradly_terry_rm
+    - method=lm_finetune/bradly_terry_rm
+    - method.dataloader_kwargs.batch_size=8
+    - method.accumulate_grad_batches=16
+    - method.lr_scheduler.min_lr=1e-7
+    - method.lr_scheduler.max_lr=5e-6
+    - method.lr_scheduler.warmup_steps=100
+    - method.optimizer.lr=0
+    - method.optimizer.weight_decay=0.001
+    - method.gradient_clip_val=1
+    - method.max_epochs=2
+    - method.checkpoint_save_interval=epoch
+    - method.checkpoint_save_frequency=1
+    - modelpool=SeqenceClassificationModelPool/llama_preference700k
+  job:
+    name: cli
+    chdir: null
+    override_dirname: fabric.loggers.name=llama_full_bradly_terry_rm,method.accumulate_grad_batches=16,method.checkpoint_save_frequency=1,method.checkpoint_save_interval=epoch,method.dataloader_kwargs.batch_size=8,method.gradient_clip_val=1,method.lr_scheduler.max_lr=5e-6,method.lr_scheduler.min_lr=1e-7,method.lr_scheduler.warmup_steps=100,method.max_epochs=2,method.optimizer.lr=0,method.optimizer.weight_decay=0.001,method=lm_finetune/bradly_terry_rm,modelpool=SeqenceClassificationModelPool/llama_preference700k
+    id: ???
+    num: ???
+    config_name: llama_full_finetune
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.3'
+    cwd: /data0/users/tanganke/projects/fusion_bench
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /data0/users/tanganke/projects/fusion_bench/fusion_bench_config
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /data0/users/tanganke/projects/fusion_bench/outputs/cli/2024-12-01_00-02-51
+    choices:
+      taskpool: dummy
+      modelpool: SeqenceClassificationModelPool/llama_preference700k
+      method: lm_finetune/bradly_terry_rm
+      fabric: llama_fsdp
+      fabric/strategy: llama_fsdp
+      fabric/loggers: tensorboard_logger
+      hydra: default
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: rich_logging
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: fusion_bench_help
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

hydra_output_2024-12-01_00-02-51/.hydra/overrides.yaml

@@ -0,0 +1,14 @@
+- fabric.loggers.name=llama_full_bradly_terry_rm
+- method=lm_finetune/bradly_terry_rm
+- method.dataloader_kwargs.batch_size=8
+- method.accumulate_grad_batches=16
+- method.lr_scheduler.min_lr=1e-7
+- method.lr_scheduler.max_lr=5e-6
+- method.lr_scheduler.warmup_steps=100
+- method.optimizer.lr=0
+- method.optimizer.weight_decay=0.001
+- method.gradient_clip_val=1
+- method.max_epochs=2
+- method.checkpoint_save_interval=epoch
+- method.checkpoint_save_frequency=1
+- modelpool=SeqenceClassificationModelPool/llama_preference700k

hydra_output_2024-12-01_00-02-51/cli.log

@@ -0,0 +1,136 @@
+[2024-12-01 00:02:53,586][lightning.pytorch.utilities.rank_zero][INFO] - You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision
+[2024-12-01 00:02:53,612][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/8
+[2024-12-01 00:02:59,279][lightning.pytorch.utilities.rank_zero][INFO] - ----------------------------------------------------------------------------------------------------
+distributed_backend=nccl
+All distributed processes registered. Starting with 8 processes
+----------------------------------------------------------------------------------------------------
+
+[2024-12-01 00:02:59,286][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
+[2024-12-01 00:02:59,289][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
+[2024-12-01 00:02:59,345][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
+[2024-12-01 00:02:59,346][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
+[2024-12-01 00:02:59,356][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
+[2024-12-01 00:02:59,359][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
+[2024-12-01 00:03:01,364][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
+[2024-12-01 00:03:09,127][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
+[2024-12-01 00:03:09,131][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
+[2024-12-01 00:04:59,492][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4932 > 4096. Truncating input.
+[2024-12-01 00:34:06,978][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4965 > 4096. Truncating input.
+[2024-12-01 01:05:39,996][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 7055 > 4096. Truncating input.
+[2024-12-01 01:10:35,674][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4203 > 4096. Truncating input.
+[2024-12-01 02:06:02,105][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5677 > 4096. Truncating input.
+[2024-12-01 02:06:33,375][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4222 > 4096. Truncating input.
+[2024-12-01 02:10:10,701][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4976 > 4096. Truncating input.
+[2024-12-01 03:21:23,107][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4984 > 4096. Truncating input.
+[2024-12-01 04:33:05,519][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4144 > 4096. Truncating input.
+[2024-12-01 04:46:26,474][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4502 > 4096. Truncating input.
+[2024-12-01 04:49:50,274][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4255 > 4096. Truncating input.
+[2024-12-01 05:09:21,368][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4729 > 4096. Truncating input.
+[2024-12-01 05:18:27,501][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4269 > 4096. Truncating input.
+[2024-12-01 05:33:40,443][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5366 > 4096. Truncating input.
+[2024-12-01 06:10:41,920][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4270 > 4096. Truncating input.
+[2024-12-01 06:20:14,659][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4744 > 4096. Truncating input.
+[2024-12-01 06:46:07,270][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4773 > 4096. Truncating input.
+[2024-12-01 06:57:34,764][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4424 > 4096. Truncating input.
+[2024-12-01 07:15:03,811][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5770 > 4096. Truncating input.
+[2024-12-01 07:59:26,708][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5077 > 4096. Truncating input.
+[2024-12-01 08:22:55,217][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4595 > 4096. Truncating input.
+[2024-12-01 08:28:34,958][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4970 > 4096. Truncating input.
+[2024-12-01 09:11:55,748][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4849 > 4096. Truncating input.
+[2024-12-01 09:18:10,430][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4212 > 4096. Truncating input.
+[2024-12-01 09:36:02,488][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5094 > 4096. Truncating input.
+[2024-12-01 09:58:00,077][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4604 > 4096. Truncating input.
+[2024-12-01 10:04:45,159][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6428 > 4096. Truncating input.
+[2024-12-01 10:22:07,223][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4722 > 4096. Truncating input.
+[2024-12-01 10:22:33,498][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4273 > 4096. Truncating input.
+[2024-12-01 10:23:07,412][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5221 > 4096. Truncating input.
+[2024-12-01 10:46:06,370][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4113 > 4096. Truncating input.
+[2024-12-01 11:49:17,945][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4926 > 4096. Truncating input.
+[2024-12-01 11:59:34,976][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5552 > 4096. Truncating input.
+[2024-12-01 12:29:36,230][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4880 > 4096. Truncating input.
+[2024-12-01 12:47:52,484][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5242 > 4096. Truncating input.
+[2024-12-01 13:13:31,623][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4747 > 4096. Truncating input.
+[2024-12-01 13:35:18,687][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4518 > 4096. Truncating input.
+[2024-12-01 13:59:48,328][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4663 > 4096. Truncating input.
+[2024-12-01 14:09:47,241][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5493 > 4096. Truncating input.
+[2024-12-01 14:13:35,064][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5026 > 4096. Truncating input.
+[2024-12-01 14:56:38,580][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4992 > 4096. Truncating input.
+[2024-12-01 15:31:30,090][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5095 > 4096. Truncating input.
+[2024-12-01 15:38:03,841][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4366 > 4096. Truncating input.
+[2024-12-01 16:30:51,639][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6038 > 4096. Truncating input.
+[2024-12-01 16:46:57,788][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6141 > 4096. Truncating input.
+[2024-12-01 17:12:33,754][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4434 > 4096. Truncating input.
+[2024-12-01 17:48:58,800][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4700 > 4096. Truncating input.
+[2024-12-01 18:58:06,524][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4268 > 4096. Truncating input.
+[2024-12-01 19:47:30,189][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4162 > 4096. Truncating input.
+[2024-12-01 19:59:31,522][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4585 > 4096. Truncating input.
+[2024-12-01 20:11:46,992][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8593 > 4096. Truncating input.
+[2024-12-01 20:59:46,422][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4412 > 4096. Truncating input.
+[2024-12-01 21:18:15,197][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4932 > 4096. Truncating input.
+[2024-12-01 21:45:51,725][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4684 > 4096. Truncating input.
+[2024-12-01 22:15:49,251][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4865 > 4096. Truncating input.
+[2024-12-01 22:16:57,422][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5669 > 4096. Truncating input.
+[2024-12-01 22:32:59,955][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5091 > 4096. Truncating input.
+[2024-12-02 00:03:56,712][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4463 > 4096. Truncating input.
+[2024-12-02 00:09:34,514][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4598 > 4096. Truncating input.
+[2024-12-02 00:15:38,290][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4998 > 4096. Truncating input.
+[2024-12-02 00:25:45,182][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4501 > 4096. Truncating input.
+[2024-12-02 00:27:43,466][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4920 > 4096. Truncating input.
+[2024-12-02 00:48:23,808][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4653 > 4096. Truncating input.
+[2024-12-02 01:02:12,105][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6340 > 4096. Truncating input.
+[2024-12-02 01:25:53,873][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5699 > 4096. Truncating input.
+[2024-12-02 01:26:44,039][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4751 > 4096. Truncating input.
+[2024-12-02 01:37:34,547][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4280 > 4096. Truncating input.
+[2024-12-02 01:44:42,867][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6591 > 4096. Truncating input.
+[2024-12-02 02:11:20,106][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4661 > 4096. Truncating input.
+[2024-12-02 02:23:40,509][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4528 > 4096. Truncating input.
+[2024-12-02 02:31:50,609][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4595 > 4096. Truncating input.
+[2024-12-02 02:49:41,372][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4533 > 4096. Truncating input.
+[2024-12-02 02:50:49,863][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4502 > 4096. Truncating input.
+[2024-12-02 03:11:35,819][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4179 > 4096. Truncating input.
+[2024-12-02 03:58:20,677][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4591 > 4096. Truncating input.
+[2024-12-02 04:29:14,017][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4214 > 4096. Truncating input.
+[2024-12-02 04:30:43,718][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4405 > 4096. Truncating input.
+[2024-12-02 04:43:04,782][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4212 > 4096. Truncating input.
+[2024-12-02 04:51:09,416][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4274 > 4096. Truncating input.
+[2024-12-02 05:06:45,536][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4447 > 4096. Truncating input.
+[2024-12-02 05:38:36,951][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4644 > 4096. Truncating input.
+[2024-12-02 05:44:42,194][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4527 > 4096. Truncating input.
+[2024-12-02 05:51:13,061][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4994 > 4096. Truncating input.
+[2024-12-02 05:56:25,820][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4482 > 4096. Truncating input.
+[2024-12-02 06:11:08,169][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4644 > 4096. Truncating input.
+[2024-12-02 06:18:43,410][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4292 > 4096. Truncating input.
+[2024-12-02 06:18:55,560][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4615 > 4096. Truncating input.
+[2024-12-02 07:03:20,453][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4153 > 4096. Truncating input.
+[2024-12-02 07:26:38,563][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4788 > 4096. Truncating input.
+[2024-12-02 07:34:38,677][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4360 > 4096. Truncating input.
+[2024-12-02 08:50:50,744][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5937 > 4096. Truncating input.
+[2024-12-02 08:53:42,954][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4685 > 4096. Truncating input.
+[2024-12-02 09:03:27,543][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4674 > 4096. Truncating input.
+[2024-12-02 09:07:58,014][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4231 > 4096. Truncating input.
+[2024-12-02 09:40:11,681][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5602 > 4096. Truncating input.
+[2024-12-02 09:46:50,557][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4449 > 4096. Truncating input.
+[2024-12-02 11:23:29,753][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8047 > 4096. Truncating input.
+[2024-12-02 11:25:42,289][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4604 > 4096. Truncating input.
+[2024-12-02 12:11:10,219][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5185 > 4096. Truncating input.
+[2024-12-02 12:26:00,410][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4867 > 4096. Truncating input.
+[2024-12-02 12:47:18,302][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4733 > 4096. Truncating input.
+[2024-12-02 12:56:22,131][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4571 > 4096. Truncating input.
+[2024-12-02 12:56:39,795][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4241 > 4096. Truncating input.
+[2024-12-02 13:23:30,059][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4273 > 4096. Truncating input.
+[2024-12-02 13:40:29,409][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4396 > 4096. Truncating input.
+[2024-12-02 13:50:04,924][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
+[2024-12-02 14:00:14,778][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
+[2024-12-02 15:04:05,386][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4493 > 4096. Truncating input.
+[2024-12-02 15:06:59,966][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5221 > 4096. Truncating input.
+[2024-12-02 15:24:08,497][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4656 > 4096. Truncating input.
+[2024-12-02 15:34:54,901][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4297 > 4096. Truncating input.
+[2024-12-02 16:12:50,950][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4741 > 4096. Truncating input.
+[2024-12-02 16:15:06,389][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4206 > 4096. Truncating input.
+[2024-12-02 16:24:17,204][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4620 > 4096. Truncating input.
+[2024-12-02 16:29:23,950][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4948 > 4096. Truncating input.
+[2024-12-02 17:25:42,866][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4808 > 4096. Truncating input.
+[2024-12-02 17:26:41,180][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4435 > 4096. Truncating input.
+[2024-12-02 17:39:04,165][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4812 > 4096. Truncating input.
+[2024-12-02 18:21:45,214][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4103 > 4096. Truncating input.
+[2024-12-02 18:24:20,723][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4773 > 4096. Truncating input.

hydra_output_2024-12-01_00-02-51/train_ddp_process_1.log

@@ -0,0 +1,122 @@
+[2024-12-01 00:02:59,178][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 1, MEMBER: 2/8
+[2024-12-01 00:02:59,183][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
+[2024-12-01 00:02:59,184][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
+[2024-12-01 00:02:59,236][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
+[2024-12-01 00:02:59,237][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
+[2024-12-01 00:02:59,243][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
+[2024-12-01 00:02:59,245][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
+[2024-12-01 00:03:00,170][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
+[2024-12-01 00:03:08,340][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
+[2024-12-01 00:03:08,344][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
+[2024-12-01 00:13:54,904][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4705 > 4096. Truncating input.
+[2024-12-01 00:18:32,680][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4296 > 4096. Truncating input.
+[2024-12-01 00:51:55,489][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4926 > 4096. Truncating input.
+[2024-12-01 01:02:14,833][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4360 > 4096. Truncating input.
+[2024-12-01 01:29:08,474][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4399 > 4096. Truncating input.
+[2024-12-01 01:32:02,731][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4547 > 4096. Truncating input.
+[2024-12-01 02:18:09,730][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4291 > 4096. Truncating input.
+[2024-12-01 02:24:35,692][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4601 > 4096. Truncating input.
+[2024-12-01 02:38:24,510][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4228 > 4096. Truncating input.
+[2024-12-01 02:49:27,652][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4257 > 4096. Truncating input.
+[2024-12-01 03:49:27,820][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4570 > 4096. Truncating input.
+[2024-12-01 04:11:57,917][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5525 > 4096. Truncating input.
+[2024-12-01 04:12:32,372][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4642 > 4096. Truncating input.
+[2024-12-01 04:16:37,798][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4525 > 4096. Truncating input.
+[2024-12-01 04:17:35,384][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4274 > 4096. Truncating input.
+[2024-12-01 04:19:11,675][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5526 > 4096. Truncating input.
+[2024-12-01 04:52:37,768][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4646 > 4096. Truncating input.
+[2024-12-01 04:53:53,309][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5315 > 4096. Truncating input.
+[2024-12-01 06:03:32,001][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4221 > 4096. Truncating input.
+[2024-12-01 06:22:05,739][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4292 > 4096. Truncating input.
+[2024-12-01 07:00:23,297][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4555 > 4096. Truncating input.
+[2024-12-01 07:19:10,907][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4479 > 4096. Truncating input.
+[2024-12-01 07:33:50,729][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4826 > 4096. Truncating input.
+[2024-12-01 07:34:53,468][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4582 > 4096. Truncating input.
+[2024-12-01 08:10:50,613][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4297 > 4096. Truncating input.
+[2024-12-01 08:24:53,508][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4646 > 4096. Truncating input.
+[2024-12-01 08:30:08,276][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4250 > 4096. Truncating input.
+[2024-12-01 08:42:45,451][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4312 > 4096. Truncating input.
+[2024-12-01 08:53:44,394][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
+[2024-12-01 09:23:04,435][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5602 > 4096. Truncating input.
+[2024-12-01 09:28:58,176][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4699 > 4096. Truncating input.
+[2024-12-01 09:36:45,893][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6295 > 4096. Truncating input.
+[2024-12-01 09:48:14,500][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4514 > 4096. Truncating input.
+[2024-12-01 10:49:52,885][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4849 > 4096. Truncating input.
+[2024-12-01 10:56:25,966][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4117 > 4096. Truncating input.
+[2024-12-01 11:45:16,117][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4785 > 4096. Truncating input.
+[2024-12-01 12:02:40,995][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4393 > 4096. Truncating input.
+[2024-12-01 12:04:28,428][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4153 > 4096. Truncating input.
+[2024-12-01 13:33:33,082][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4558 > 4096. Truncating input.
+[2024-12-01 13:48:57,757][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4587 > 4096. Truncating input.
+[2024-12-01 13:51:30,230][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4875 > 4096. Truncating input.
+[2024-12-01 14:05:15,857][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4241 > 4096. Truncating input.
+[2024-12-01 14:43:29,359][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4103 > 4096. Truncating input.
+[2024-12-01 14:55:05,214][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6179 > 4096. Truncating input.
+[2024-12-01 14:59:29,757][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4571 > 4096. Truncating input.
+[2024-12-01 15:01:46,670][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4800 > 4096. Truncating input.
+[2024-12-01 15:09:30,440][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4998 > 4096. Truncating input.
+[2024-12-01 15:23:27,067][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4948 > 4096. Truncating input.
+[2024-12-01 16:30:16,533][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4545 > 4096. Truncating input.
+[2024-12-01 16:52:44,415][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4140 > 4096. Truncating input.
+[2024-12-01 17:50:56,985][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4434 > 4096. Truncating input.
+[2024-12-01 18:35:47,988][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5025 > 4096. Truncating input.
+[2024-12-01 18:41:51,220][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4557 > 4096. Truncating input.
+[2024-12-01 18:48:31,601][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
+[2024-12-01 19:13:09,334][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4177 > 4096. Truncating input.
+[2024-12-01 19:20:27,822][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4733 > 4096. Truncating input.
+[2024-12-01 20:03:19,362][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4505 > 4096. Truncating input.
+[2024-12-01 20:48:52,846][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4369 > 4096. Truncating input.
+[2024-12-01 20:55:23,249][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4119 > 4096. Truncating input.
+[2024-12-01 22:32:18,376][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4963 > 4096. Truncating input.
+[2024-12-01 22:33:44,379][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4341 > 4096. Truncating input.
+[2024-12-01 22:46:03,520][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5770 > 4096. Truncating input.
+[2024-12-01 23:01:48,003][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8099 > 4096. Truncating input.
+[2024-12-01 23:11:30,341][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4585 > 4096. Truncating input.
+[2024-12-01 23:24:16,836][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4224 > 4096. Truncating input.
+[2024-12-01 23:42:32,402][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4790 > 4096. Truncating input.
+[2024-12-01 23:54:36,880][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4828 > 4096. Truncating input.
+[2024-12-02 00:00:43,016][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4598 > 4096. Truncating input.
+[2024-12-02 00:47:58,909][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4985 > 4096. Truncating input.
+[2024-12-02 00:59:32,922][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4663 > 4096. Truncating input.
+[2024-12-02 01:05:15,428][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4811 > 4096. Truncating input.
+[2024-12-02 01:11:54,229][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4291 > 4096. Truncating input.
+[2024-12-02 01:42:01,942][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4926 > 4096. Truncating input.
+[2024-12-02 01:44:43,177][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4142 > 4096. Truncating input.
+[2024-12-02 03:48:28,140][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4140 > 4096. Truncating input.
+[2024-12-02 04:02:00,107][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5839 > 4096. Truncating input.
+[2024-12-02 04:15:23,453][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4362 > 4096. Truncating input.
+[2024-12-02 04:17:47,445][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6295 > 4096. Truncating input.
+[2024-12-02 04:39:12,111][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4752 > 4096. Truncating input.
+[2024-12-02 04:47:16,553][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4164 > 4096. Truncating input.
+[2024-12-02 06:07:56,326][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4665 > 4096. Truncating input.
+[2024-12-02 06:27:16,794][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4239 > 4096. Truncating input.
+[2024-12-02 06:30:32,196][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4102 > 4096. Truncating input.
+[2024-12-02 06:54:11,922][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4722 > 4096. Truncating input.
+[2024-12-02 07:12:25,268][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5603 > 4096. Truncating input.
+[2024-12-02 07:57:00,936][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4699 > 4096. Truncating input.
+[2024-12-02 08:05:24,091][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5032 > 4096. Truncating input.
+[2024-12-02 08:46:30,033][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5082 > 4096. Truncating input.
+[2024-12-02 09:09:02,594][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4302 > 4096. Truncating input.
+[2024-12-02 09:20:05,038][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4917 > 4096. Truncating input.
+[2024-12-02 09:42:50,646][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4414 > 4096. Truncating input.
+[2024-12-02 11:36:16,670][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4926 > 4096. Truncating input.
+[2024-12-02 11:38:03,763][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4162 > 4096. Truncating input.
+[2024-12-02 11:47:25,860][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4537 > 4096. Truncating input.
+[2024-12-02 12:19:29,169][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4846 > 4096. Truncating input.
+[2024-12-02 12:25:16,281][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5195 > 4096. Truncating input.
+[2024-12-02 14:25:30,297][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4310 > 4096. Truncating input.
+[2024-12-02 14:56:36,867][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4705 > 4096. Truncating input.
+[2024-12-02 15:09:47,465][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4380 > 4096. Truncating input.
+[2024-12-02 15:22:15,867][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6428 > 4096. Truncating input.
+[2024-12-02 15:24:55,716][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4710 > 4096. Truncating input.
+[2024-12-02 15:36:18,579][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
+[2024-12-02 15:43:18,015][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4203 > 4096. Truncating input.
+[2024-12-02 15:44:31,177][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5525 > 4096. Truncating input.
+[2024-12-02 16:21:47,561][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4492 > 4096. Truncating input.
+[2024-12-02 16:27:50,367][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4177 > 4096. Truncating input.
+[2024-12-02 16:34:12,479][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4130 > 4096. Truncating input.
+[2024-12-02 16:59:17,693][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4984 > 4096. Truncating input.
+[2024-12-02 17:02:57,992][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4292 > 4096. Truncating input.
+[2024-12-02 17:30:41,525][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4718 > 4096. Truncating input.
+[2024-12-02 17:45:13,002][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4569 > 4096. Truncating input.
+[2024-12-02 18:19:00,014][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 9431 > 4096. Truncating input.

hydra_output_2024-12-01_00-02-51/train_ddp_process_2.log

@@ -0,0 +1,134 @@
+[2024-12-01 00:02:59,172][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 2, MEMBER: 3/8
+[2024-12-01 00:02:59,181][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
+[2024-12-01 00:02:59,184][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
+[2024-12-01 00:02:59,239][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
+[2024-12-01 00:02:59,240][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
+[2024-12-01 00:02:59,246][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
+[2024-12-01 00:02:59,248][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
+[2024-12-01 00:03:00,187][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
+[2024-12-01 00:03:08,585][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
+[2024-12-01 00:03:08,589][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
+[2024-12-01 00:29:38,209][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4405 > 4096. Truncating input.
+[2024-12-01 00:31:01,839][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4725 > 4096. Truncating input.
+[2024-12-01 00:52:50,172][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5242 > 4096. Truncating input.
+[2024-12-01 01:00:53,754][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4696 > 4096. Truncating input.
+[2024-12-01 01:19:47,401][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4316 > 4096. Truncating input.
+[2024-12-01 01:59:01,749][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4739 > 4096. Truncating input.
+[2024-12-01 02:02:47,194][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4824 > 4096. Truncating input.
+[2024-12-01 02:20:25,220][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4099 > 4096. Truncating input.
+[2024-12-01 02:32:14,763][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4344 > 4096. Truncating input.
+[2024-12-01 02:33:44,355][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6129 > 4096. Truncating input.
+[2024-12-01 02:51:53,436][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4157 > 4096. Truncating input.
+[2024-12-01 03:26:45,198][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4169 > 4096. Truncating input.
+[2024-12-01 03:42:48,188][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4142 > 4096. Truncating input.
+[2024-12-01 03:44:26,058][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5161 > 4096. Truncating input.
+[2024-12-01 03:46:33,087][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4496 > 4096. Truncating input.
+[2024-12-01 03:58:06,970][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4728 > 4096. Truncating input.
+[2024-12-01 04:01:32,668][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5032 > 4096. Truncating input.
+[2024-12-01 04:13:27,171][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4474 > 4096. Truncating input.
+[2024-12-01 04:28:53,605][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6157 > 4096. Truncating input.
+[2024-12-01 04:36:34,182][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4501 > 4096. Truncating input.
+[2024-12-01 04:46:15,754][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5669 > 4096. Truncating input.
+[2024-12-01 05:20:57,515][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4804 > 4096. Truncating input.
+[2024-12-01 06:03:42,862][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4292 > 4096. Truncating input.
+[2024-12-01 06:12:30,972][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4820 > 4096. Truncating input.
+[2024-12-01 07:01:58,912][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4960 > 4096. Truncating input.
+[2024-12-01 07:12:09,334][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4272 > 4096. Truncating input.
+[2024-12-01 07:18:45,866][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4799 > 4096. Truncating input.
+[2024-12-01 07:41:17,720][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5613 > 4096. Truncating input.
+[2024-12-01 07:57:37,832][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4865 > 4096. Truncating input.
+[2024-12-01 08:11:33,294][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4574 > 4096. Truncating input.
+[2024-12-01 08:42:26,816][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5327 > 4096. Truncating input.
+[2024-12-01 08:52:04,371][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4492 > 4096. Truncating input.
+[2024-12-01 08:53:33,586][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4653 > 4096. Truncating input.
+[2024-12-01 09:06:11,658][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6168 > 4096. Truncating input.
+[2024-12-01 09:25:08,512][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4396 > 4096. Truncating input.
+[2024-12-01 09:44:21,609][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5245 > 4096. Truncating input.
+[2024-12-01 09:51:38,604][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4656 > 4096. Truncating input.
+[2024-12-01 10:33:43,140][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4715 > 4096. Truncating input.
+[2024-12-01 10:39:19,144][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4224 > 4096. Truncating input.
+[2024-12-01 10:58:13,086][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4620 > 4096. Truncating input.
+[2024-12-01 11:02:36,098][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4233 > 4096. Truncating input.
+[2024-12-01 12:00:00,633][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4382 > 4096. Truncating input.
+[2024-12-01 13:09:45,758][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4811 > 4096. Truncating input.
+[2024-12-01 13:17:24,749][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4233 > 4096. Truncating input.
+[2024-12-01 13:48:35,171][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4734 > 4096. Truncating input.
+[2024-12-01 14:04:17,151][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4920 > 4096. Truncating input.
+[2024-12-01 15:10:23,309][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4738 > 4096. Truncating input.
+[2024-12-01 15:30:12,400][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4632 > 4096. Truncating input.
+[2024-12-01 16:19:19,022][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4945 > 4096. Truncating input.
+[2024-12-01 16:24:08,816][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5718 > 4096. Truncating input.
+[2024-12-01 16:31:20,129][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4176 > 4096. Truncating input.
+[2024-12-01 17:08:11,656][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4788 > 4096. Truncating input.
+[2024-12-01 17:56:18,313][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5699 > 4096. Truncating input.
+[2024-12-01 18:29:33,777][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4517 > 4096. Truncating input.
+[2024-12-01 18:45:48,764][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5700 > 4096. Truncating input.
+[2024-12-01 18:57:55,463][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4167 > 4096. Truncating input.
+[2024-12-01 19:19:02,294][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4394 > 4096. Truncating input.
+[2024-12-01 19:46:11,154][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4520 > 4096. Truncating input.
+[2024-12-01 19:50:59,247][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4463 > 4096. Truncating input.
+[2024-12-01 20:04:27,755][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4633 > 4096. Truncating input.
+[2024-12-01 20:14:23,788][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4142 > 4096. Truncating input.
+[2024-12-01 20:40:48,345][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4533 > 4096. Truncating input.
+[2024-12-01 20:50:51,330][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5354 > 4096. Truncating input.
+[2024-12-01 20:51:28,742][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5765 > 4096. Truncating input.
+[2024-12-01 20:54:24,091][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4280 > 4096. Truncating input.
+[2024-12-01 21:30:51,509][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4272 > 4096. Truncating input.
+[2024-12-01 21:51:58,420][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4339 > 4096. Truncating input.
+[2024-12-01 22:28:13,515][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5470 > 4096. Truncating input.
+[2024-12-01 22:28:24,593][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4957 > 4096. Truncating input.
+[2024-12-01 22:49:07,794][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4507 > 4096. Truncating input.
+[2024-12-01 22:50:05,853][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6720 > 4096. Truncating input.
+[2024-12-01 23:10:40,058][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4611 > 4096. Truncating input.
+[2024-12-01 23:35:44,964][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4255 > 4096. Truncating input.
+[2024-12-01 23:40:48,517][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4344 > 4096. Truncating input.
+[2024-12-01 23:59:07,822][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4599 > 4096. Truncating input.
+[2024-12-02 00:00:03,804][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4729 > 4096. Truncating input.
+[2024-12-02 00:09:56,476][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4969 > 4096. Truncating input.
+[2024-12-02 00:50:08,069][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5100 > 4096. Truncating input.
+[2024-12-02 00:55:15,702][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4225 > 4096. Truncating input.
+[2024-12-02 01:52:38,629][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4394 > 4096. Truncating input.
+[2024-12-02 02:18:18,279][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4747 > 4096. Truncating input.
+[2024-12-02 02:24:33,614][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4344 > 4096. Truncating input.
+[2024-12-02 02:40:26,075][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4203 > 4096. Truncating input.
+[2024-12-02 02:48:13,621][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4434 > 4096. Truncating input.
+[2024-12-02 03:05:14,565][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4705 > 4096. Truncating input.
+[2024-12-02 03:22:37,470][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4214 > 4096. Truncating input.
+[2024-12-02 03:33:52,853][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4856 > 4096. Truncating input.
+[2024-12-02 04:53:03,310][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6079 > 4096. Truncating input.
+[2024-12-02 04:54:15,100][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4477 > 4096. Truncating input.
+[2024-12-02 05:30:16,763][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4142 > 4096. Truncating input.
+[2024-12-02 06:07:40,482][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4229 > 4096. Truncating input.
+[2024-12-02 07:02:09,147][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4434 > 4096. Truncating input.
+[2024-12-02 08:03:44,435][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4981 > 4096. Truncating input.
+[2024-12-02 08:06:31,100][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4744 > 4096. Truncating input.
+[2024-12-02 08:09:55,796][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
+[2024-12-02 08:23:47,449][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4457 > 4096. Truncating input.
+[2024-12-02 08:30:32,283][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5552 > 4096. Truncating input.
+[2024-12-02 08:43:11,621][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4563 > 4096. Truncating input.
+[2024-12-02 08:45:01,428][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4269 > 4096. Truncating input.
+[2024-12-02 09:40:00,589][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4633 > 4096. Truncating input.
+[2024-12-02 10:07:26,011][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5242 > 4096. Truncating input.
+[2024-12-02 10:28:19,684][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4369 > 4096. Truncating input.
+[2024-12-02 10:44:58,033][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4837 > 4096. Truncating input.
+[2024-12-02 11:00:45,313][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4624 > 4096. Truncating input.
+[2024-12-02 11:27:41,463][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5375 > 4096. Truncating input.
+[2024-12-02 11:31:46,678][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4270 > 4096. Truncating input.
+[2024-12-02 11:55:58,529][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4641 > 4096. Truncating input.
+[2024-12-02 12:03:53,347][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4354 > 4096. Truncating input.
+[2024-12-02 12:34:07,576][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4563 > 4096. Truncating input.
+[2024-12-02 12:39:53,902][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4387 > 4096. Truncating input.
+[2024-12-02 13:12:32,952][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4875 > 4096. Truncating input.
+[2024-12-02 13:43:46,522][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6722 > 4096. Truncating input.
+[2024-12-02 13:51:04,754][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4971 > 4096. Truncating input.
+[2024-12-02 15:06:41,852][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6605 > 4096. Truncating input.
+[2024-12-02 15:12:58,271][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4503 > 4096. Truncating input.
+[2024-12-02 15:26:49,271][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4785 > 4096. Truncating input.
+[2024-12-02 15:50:28,837][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4646 > 4096. Truncating input.
+[2024-12-02 16:09:48,009][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4413 > 4096. Truncating input.
+[2024-12-02 16:27:39,292][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4945 > 4096. Truncating input.
+[2024-12-02 16:31:19,647][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4582 > 4096. Truncating input.
+[2024-12-02 16:57:13,493][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4695 > 4096. Truncating input.
+[2024-12-02 17:15:52,485][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4208 > 4096. Truncating input.
+[2024-12-02 17:16:20,797][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4236 > 4096. Truncating input.
+[2024-12-02 17:47:03,376][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4570 > 4096. Truncating input.

hydra_output_2024-12-01_00-02-51/train_ddp_process_3.log

@@ -0,0 +1,133 @@
+[2024-12-01 00:02:59,259][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 3, MEMBER: 4/8
+[2024-12-01 00:02:59,266][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
+[2024-12-01 00:02:59,267][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
+[2024-12-01 00:02:59,317][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
+[2024-12-01 00:02:59,318][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
+[2024-12-01 00:02:59,324][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
+[2024-12-01 00:02:59,325][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
+[2024-12-01 00:03:00,734][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
+[2024-12-01 00:03:10,245][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
+[2024-12-01 00:03:10,249][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
+[2024-12-01 00:18:11,515][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4239 > 4096. Truncating input.
+[2024-12-01 00:33:01,676][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4804 > 4096. Truncating input.
+[2024-12-01 00:49:38,319][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4425 > 4096. Truncating input.
+[2024-12-01 00:55:51,708][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4986 > 4096. Truncating input.
+[2024-12-01 01:00:08,387][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4429 > 4096. Truncating input.
+[2024-12-01 01:09:10,953][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4860 > 4096. Truncating input.
+[2024-12-01 01:27:54,291][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4372 > 4096. Truncating input.
+[2024-12-01 02:33:33,547][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4542 > 4096. Truncating input.
+[2024-12-01 03:01:07,179][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4183 > 4096. Truncating input.
+[2024-12-01 03:14:07,232][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4665 > 4096. Truncating input.
+[2024-12-01 03:39:09,252][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4635 > 4096. Truncating input.
+[2024-12-01 04:03:15,835][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5091 > 4096. Truncating input.
+[2024-12-01 04:19:11,714][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4482 > 4096. Truncating input.
+[2024-12-01 04:25:52,490][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4341 > 4096. Truncating input.
+[2024-12-01 05:13:17,570][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5600 > 4096. Truncating input.
+[2024-12-01 05:36:36,384][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4511 > 4096. Truncating input.
+[2024-12-01 05:50:19,911][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4674 > 4096. Truncating input.
+[2024-12-01 07:54:49,793][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5178 > 4096. Truncating input.
+[2024-12-01 08:37:03,252][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4738 > 4096. Truncating input.
+[2024-12-01 08:43:54,493][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4924 > 4096. Truncating input.
+[2024-12-01 08:59:31,927][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4687 > 4096. Truncating input.
+[2024-12-01 09:03:30,885][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4537 > 4096. Truncating input.
+[2024-12-01 09:10:14,640][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4716 > 4096. Truncating input.
+[2024-12-01 09:17:40,492][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4770 > 4096. Truncating input.
+[2024-12-01 10:01:45,044][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
+[2024-12-01 10:07:42,861][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6340 > 4096. Truncating input.
+[2024-12-01 10:13:27,108][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5721 > 4096. Truncating input.
+[2024-12-01 10:34:49,623][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4790 > 4096. Truncating input.
+[2024-12-01 10:53:03,737][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4368 > 4096. Truncating input.
+[2024-12-01 10:55:24,436][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4477 > 4096. Truncating input.
+[2024-12-01 10:56:15,352][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4944 > 4096. Truncating input.
+[2024-12-01 11:12:08,988][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5848 > 4096. Truncating input.
+[2024-12-01 11:34:58,966][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4806 > 4096. Truncating input.
+[2024-12-01 11:42:11,337][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4767 > 4096. Truncating input.
+[2024-12-01 11:53:26,800][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4332 > 4096. Truncating input.
+[2024-12-01 12:16:52,600][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6044 > 4096. Truncating input.
+[2024-12-01 12:22:41,578][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4704 > 4096. Truncating input.
+[2024-12-01 12:34:25,540][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4236 > 4096. Truncating input.
+[2024-12-01 12:42:06,870][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4370 > 4096. Truncating input.
+[2024-12-01 14:09:30,968][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4447 > 4096. Truncating input.
+[2024-12-01 14:12:20,117][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5100 > 4096. Truncating input.
+[2024-12-01 14:25:55,880][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4964 > 4096. Truncating input.
+[2024-12-01 14:30:49,047][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4808 > 4096. Truncating input.
+[2024-12-01 15:08:41,215][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4982 > 4096. Truncating input.
+[2024-12-01 15:36:29,085][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4479 > 4096. Truncating input.
+[2024-12-01 15:45:26,551][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4869 > 4096. Truncating input.
+[2024-12-01 15:47:45,320][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4210 > 4096. Truncating input.
+[2024-12-01 15:56:31,025][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6620 > 4096. Truncating input.
+[2024-12-01 16:42:24,207][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4475 > 4096. Truncating input.
+[2024-12-01 16:48:27,283][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4214 > 4096. Truncating input.
+[2024-12-01 17:17:17,841][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4661 > 4096. Truncating input.
+[2024-12-01 17:42:47,998][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4685 > 4096. Truncating input.
+[2024-12-01 18:21:09,137][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4507 > 4096. Truncating input.
+[2024-12-01 19:26:18,603][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4805 > 4096. Truncating input.
+[2024-12-01 20:40:59,044][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6809 > 4096. Truncating input.
+[2024-12-01 20:48:00,976][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4353 > 4096. Truncating input.
+[2024-12-01 20:58:26,088][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4405 > 4096. Truncating input.
+[2024-12-01 21:09:24,082][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4409 > 4096. Truncating input.
+[2024-12-01 21:27:49,106][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4264 > 4096. Truncating input.
+[2024-12-01 21:46:52,293][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4604 > 4096. Truncating input.
+[2024-12-01 22:06:57,510][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4696 > 4096. Truncating input.
+[2024-12-01 22:22:33,661][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4559 > 4096. Truncating input.
+[2024-12-01 22:39:38,360][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4545 > 4096. Truncating input.
+[2024-12-01 22:57:11,385][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4409 > 4096. Truncating input.
+[2024-12-01 23:16:33,933][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4735 > 4096. Truncating input.
+[2024-12-01 23:30:14,438][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4442 > 4096. Truncating input.
+[2024-12-02 00:37:33,807][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4296 > 4096. Truncating input.
+[2024-12-02 00:39:34,246][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4393 > 4096. Truncating input.
+[2024-12-02 00:55:47,988][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4505 > 4096. Truncating input.
+[2024-12-02 01:07:19,801][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4558 > 4096. Truncating input.
+[2024-12-02 01:22:41,777][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4820 > 4096. Truncating input.
+[2024-12-02 01:52:17,773][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4520 > 4096. Truncating input.
+[2024-12-02 02:30:10,926][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4167 > 4096. Truncating input.
+[2024-12-02 02:34:30,372][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4157 > 4096. Truncating input.
+[2024-12-02 03:23:23,367][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
+[2024-12-02 03:48:45,890][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5775 > 4096. Truncating input.
+[2024-12-02 04:00:13,519][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4656 > 4096. Truncating input.
+[2024-12-02 04:26:00,342][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4804 > 4096. Truncating input.
+[2024-12-02 04:39:12,208][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4479 > 4096. Truncating input.
+[2024-12-02 05:15:22,202][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4225 > 4096. Truncating input.
+[2024-12-02 05:17:22,404][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4511 > 4096. Truncating input.
+[2024-12-02 05:56:49,848][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4156 > 4096. Truncating input.
+[2024-12-02 06:01:31,837][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4922 > 4096. Truncating input.
+[2024-12-02 06:04:56,252][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4768 > 4096. Truncating input.
+[2024-12-02 06:08:13,362][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5718 > 4096. Truncating input.
+[2024-12-02 06:13:08,904][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4587 > 4096. Truncating input.
+[2024-12-02 06:57:50,777][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4258 > 4096. Truncating input.
+[2024-12-02 07:07:10,685][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4443 > 4096. Truncating input.
+[2024-12-02 07:18:38,364][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4224 > 4096. Truncating input.
+[2024-12-02 07:28:54,074][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4542 > 4096. Truncating input.
+[2024-12-02 07:53:32,167][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5353 > 4096. Truncating input.
+[2024-12-02 08:40:25,935][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4425 > 4096. Truncating input.
+[2024-12-02 09:05:51,950][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4806 > 4096. Truncating input.
+[2024-12-02 09:19:12,835][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4642 > 4096. Truncating input.
+[2024-12-02 10:12:37,258][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4982 > 4096. Truncating input.
+[2024-12-02 10:28:37,960][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4805 > 4096. Truncating input.
+[2024-12-02 10:30:43,544][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4465 > 4096. Truncating input.
+[2024-12-02 10:31:25,526][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4212 > 4096. Truncating input.
+[2024-12-02 10:35:04,139][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4268 > 4096. Truncating input.
+[2024-12-02 10:41:22,171][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4519 > 4096. Truncating input.
+[2024-12-02 10:48:31,055][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5277 > 4096. Truncating input.
+[2024-12-02 10:54:42,104][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8593 > 4096. Truncating input.
+[2024-12-02 11:01:11,465][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4122 > 4096. Truncating input.
+[2024-12-02 11:20:20,555][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4103 > 4096. Truncating input.
+[2024-12-02 11:40:15,181][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4172 > 4096. Truncating input.
+[2024-12-02 12:28:21,868][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4274 > 4096. Truncating input.
+[2024-12-02 12:32:16,649][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4144 > 4096. Truncating input.
+[2024-12-02 13:30:38,439][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4366 > 4096. Truncating input.
+[2024-12-02 13:49:46,741][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4635 > 4096. Truncating input.
+[2024-12-02 14:05:37,771][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4496 > 4096. Truncating input.
+[2024-12-02 14:47:43,535][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4683 > 4096. Truncating input.
+[2024-12-02 14:49:18,691][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4986 > 4096. Truncating input.
+[2024-12-02 14:59:25,093][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4243 > 4096. Truncating input.
+[2024-12-02 15:34:19,729][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5366 > 4096. Truncating input.
+[2024-12-02 15:55:01,950][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4685 > 4096. Truncating input.
+[2024-12-02 16:17:26,721][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4264 > 4096. Truncating input.
+[2024-12-02 16:41:39,937][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4423 > 4096. Truncating input.
+[2024-12-02 16:45:25,803][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5077 > 4096. Truncating input.
+[2024-12-02 17:41:31,173][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4301 > 4096. Truncating input.
+[2024-12-02 17:59:52,925][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5765 > 4096. Truncating input.
+[2024-12-02 18:06:33,845][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4304 > 4096. Truncating input.
+[2024-12-02 18:15:10,809][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4553 > 4096. Truncating input.
+[2024-12-02 18:15:36,078][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4140 > 4096. Truncating input.

hydra_output_2024-12-01_00-02-51/train_ddp_process_4.log

@@ -0,0 +1,119 @@
+[2024-12-01 00:02:59,152][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 4, MEMBER: 5/8
+[2024-12-01 00:02:59,161][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
+[2024-12-01 00:02:59,162][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
+[2024-12-01 00:02:59,214][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
+[2024-12-01 00:02:59,216][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
+[2024-12-01 00:02:59,222][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
+[2024-12-01 00:02:59,223][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
+[2024-12-01 00:03:00,857][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
+[2024-12-01 00:03:08,775][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
+[2024-12-01 00:03:08,779][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
+[2024-12-01 00:54:42,229][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4533 > 4096. Truncating input.
+[2024-12-01 01:13:56,533][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4306 > 4096. Truncating input.
+[2024-12-01 01:21:31,155][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4611 > 4096. Truncating input.
+[2024-12-01 01:35:28,346][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4722 > 4096. Truncating input.
+[2024-12-01 01:37:23,354][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5123 > 4096. Truncating input.
+[2024-12-01 01:43:01,233][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4859 > 4096. Truncating input.
+[2024-12-01 04:11:34,913][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5160 > 4096. Truncating input.
+[2024-12-01 05:08:12,263][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4624 > 4096. Truncating input.
+[2024-12-01 05:16:55,465][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4457 > 4096. Truncating input.
+[2024-12-01 05:19:02,563][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4768 > 4096. Truncating input.
+[2024-12-01 05:43:56,920][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4443 > 4096. Truncating input.
+[2024-12-01 06:54:15,129][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4303 > 4096. Truncating input.
+[2024-12-01 07:08:02,094][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
+[2024-12-01 07:13:37,491][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4812 > 4096. Truncating input.
+[2024-12-01 07:43:38,617][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4867 > 4096. Truncating input.
+[2024-12-01 07:55:22,909][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4144 > 4096. Truncating input.
+[2024-12-01 07:56:56,809][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5094 > 4096. Truncating input.
+[2024-12-01 08:26:46,447][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4160 > 4096. Truncating input.
+[2024-12-01 09:10:25,389][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4179 > 4096. Truncating input.
+[2024-12-01 09:19:53,549][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
+[2024-12-01 09:45:55,124][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4802 > 4096. Truncating input.
+[2024-12-01 09:59:13,332][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4598 > 4096. Truncating input.
+[2024-12-01 10:06:28,100][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4527 > 4096. Truncating input.
+[2024-12-01 10:23:43,620][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4478 > 4096. Truncating input.
+[2024-12-01 10:27:46,585][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4792 > 4096. Truncating input.
+[2024-12-01 10:33:55,225][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6658 > 4096. Truncating input.
+[2024-12-01 10:47:51,495][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5470 > 4096. Truncating input.
+[2024-12-01 10:52:53,113][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4521 > 4096. Truncating input.
+[2024-12-01 12:46:50,600][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4229 > 4096. Truncating input.
+[2024-12-01 13:12:14,395][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6769 > 4096. Truncating input.
+[2024-12-01 13:56:59,946][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4214 > 4096. Truncating input.
+[2024-12-01 14:25:01,416][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4683 > 4096. Truncating input.
+[2024-12-01 14:41:13,651][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
+[2024-12-01 14:53:02,872][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4912 > 4096. Truncating input.
+[2024-12-01 14:57:50,083][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4206 > 4096. Truncating input.
+[2024-12-01 15:47:23,022][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4711 > 4096. Truncating input.
+[2024-12-01 15:53:09,654][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4641 > 4096. Truncating input.
+[2024-12-01 16:03:13,871][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4725 > 4096. Truncating input.
+[2024-12-01 16:22:54,796][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4258 > 4096. Truncating input.
+[2024-12-01 16:55:59,421][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4661 > 4096. Truncating input.
+[2024-12-01 17:00:16,216][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5808 > 4096. Truncating input.
+[2024-12-01 17:09:53,476][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4387 > 4096. Truncating input.
+[2024-12-01 17:54:34,548][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4780 > 4096. Truncating input.
+[2024-12-01 17:55:27,865][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 9431 > 4096. Truncating input.
+[2024-12-01 18:12:56,365][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4921 > 4096. Truncating input.
+[2024-12-01 18:15:30,583][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4264 > 4096. Truncating input.
+[2024-12-01 18:33:13,442][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4414 > 4096. Truncating input.
+[2024-12-01 18:48:05,022][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4684 > 4096. Truncating input.
+[2024-12-01 19:02:59,305][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4752 > 4096. Truncating input.
+[2024-12-01 19:39:16,313][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4724 > 4096. Truncating input.
+[2024-12-01 19:58:15,306][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4237 > 4096. Truncating input.
+[2024-12-01 20:22:53,091][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4754 > 4096. Truncating input.
+[2024-12-01 20:45:19,055][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4923 > 4096. Truncating input.
+[2024-12-01 21:16:39,259][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4802 > 4096. Truncating input.
+[2024-12-01 21:56:33,396][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4716 > 4096. Truncating input.
+[2024-12-01 22:15:18,551][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4724 > 4096. Truncating input.
+[2024-12-01 22:35:16,456][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4312 > 4096. Truncating input.
+[2024-12-01 22:48:43,615][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6141 > 4096. Truncating input.
+[2024-12-01 23:59:44,559][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5009 > 4096. Truncating input.
+[2024-12-02 00:32:11,770][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4767 > 4096. Truncating input.
+[2024-12-02 00:50:18,765][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4738 > 4096. Truncating input.
+[2024-12-02 01:21:17,604][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4992 > 4096. Truncating input.
+[2024-12-02 02:17:08,361][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4754 > 4096. Truncating input.
+[2024-12-02 02:41:59,056][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4804 > 4096. Truncating input.
+[2024-12-02 02:57:16,208][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4223 > 4096. Truncating input.
+[2024-12-02 03:06:48,278][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5295 > 4096. Truncating input.
+[2024-12-02 03:09:23,166][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4405 > 4096. Truncating input.
+[2024-12-02 03:13:19,493][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4501 > 4096. Truncating input.
+[2024-12-02 03:46:52,243][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5446 > 4096. Truncating input.
+[2024-12-02 04:07:00,833][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4965 > 4096. Truncating input.
+[2024-12-02 04:11:58,321][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4715 > 4096. Truncating input.
+[2024-12-02 04:33:53,561][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4624 > 4096. Truncating input.
+[2024-12-02 04:40:21,710][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4233 > 4096. Truncating input.
+[2024-12-02 04:41:59,364][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4780 > 4096. Truncating input.
+[2024-12-02 04:48:12,022][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4380 > 4096. Truncating input.
+[2024-12-02 05:13:10,884][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4976 > 4096. Truncating input.
+[2024-12-02 05:51:48,187][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4165 > 4096. Truncating input.
+[2024-12-02 06:03:04,070][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4738 > 4096. Truncating input.
+[2024-12-02 06:03:21,399][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4517 > 4096. Truncating input.
+[2024-12-02 06:26:03,486][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4572 > 4096. Truncating input.
+[2024-12-02 06:38:06,548][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4130 > 4096. Truncating input.
+[2024-12-02 06:38:17,758][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4912 > 4096. Truncating input.
+[2024-12-02 06:47:54,646][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4382 > 4096. Truncating input.
+[2024-12-02 07:05:07,466][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6809 > 4096. Truncating input.
+[2024-12-02 08:27:50,800][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5700 > 4096. Truncating input.
+[2024-12-02 09:00:29,344][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5094 > 4096. Truncating input.
+[2024-12-02 09:03:38,639][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4144 > 4096. Truncating input.
+[2024-12-02 09:08:41,753][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4849 > 4096. Truncating input.
+[2024-12-02 09:15:35,116][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6620 > 4096. Truncating input.
+[2024-12-02 09:24:01,625][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4826 > 4096. Truncating input.
+[2024-12-02 09:30:04,111][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4725 > 4096. Truncating input.
+[2024-12-02 10:21:05,172][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4479 > 4096. Truncating input.
+[2024-12-02 10:22:11,790][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5010 > 4096. Truncating input.
+[2024-12-02 11:12:30,771][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4332 > 4096. Truncating input.
+[2024-12-02 12:17:59,283][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4792 > 4096. Truncating input.
+[2024-12-02 12:39:54,092][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4183 > 4096. Truncating input.
+[2024-12-02 13:57:39,771][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8354 > 4096. Truncating input.
+[2024-12-02 14:07:20,263][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4687 > 4096. Truncating input.
+[2024-12-02 14:28:10,511][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4316 > 4096. Truncating input.
+[2024-12-02 14:29:04,223][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4544 > 4096. Truncating input.
+[2024-12-02 14:35:14,342][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4728 > 4096. Truncating input.
+[2024-12-02 15:04:52,030][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5613 > 4096. Truncating input.
+[2024-12-02 15:49:38,503][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4424 > 4096. Truncating input.
+[2024-12-02 16:23:33,295][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4893 > 4096. Truncating input.
+[2024-12-02 16:34:29,070][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6044 > 4096. Truncating input.
+[2024-12-02 16:37:49,910][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4233 > 4096. Truncating input.
+[2024-12-02 17:07:51,808][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5721 > 4096. Truncating input.
+[2024-12-02 17:38:01,006][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5026 > 4096. Truncating input.
+[2024-12-02 17:53:41,323][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4802 > 4096. Truncating input.

hydra_output_2024-12-01_00-02-51/train_ddp_process_5.log

@@ -0,0 +1,126 @@
+[2024-12-01 00:02:58,802][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 5, MEMBER: 6/8
+[2024-12-01 00:02:58,809][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
+[2024-12-01 00:02:58,809][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
+[2024-12-01 00:02:58,860][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
+[2024-12-01 00:02:58,861][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
+[2024-12-01 00:02:58,871][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
+[2024-12-01 00:02:58,873][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
+[2024-12-01 00:03:00,977][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
+[2024-12-01 00:03:09,011][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
+[2024-12-01 00:03:09,014][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
+[2024-12-01 00:25:50,984][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4139 > 4096. Truncating input.
+[2024-12-01 00:27:08,107][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4353 > 4096. Truncating input.
+[2024-12-01 00:56:56,460][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
+[2024-12-01 01:01:54,056][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4354 > 4096. Truncating input.
+[2024-12-01 01:03:51,242][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4971 > 4096. Truncating input.
+[2024-12-01 01:11:10,706][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5010 > 4096. Truncating input.
+[2024-12-01 01:56:36,869][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4225 > 4096. Truncating input.
+[2024-12-01 02:36:36,417][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4437 > 4096. Truncating input.
+[2024-12-01 02:38:56,046][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4365 > 4096. Truncating input.
+[2024-12-01 02:39:16,158][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4496 > 4096. Truncating input.
+[2024-12-01 02:53:09,918][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4501 > 4096. Truncating input.
+[2024-12-01 03:15:13,397][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4981 > 4096. Truncating input.
+[2024-12-01 03:27:25,833][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4140 > 4096. Truncating input.
+[2024-12-01 03:51:52,907][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4837 > 4096. Truncating input.
+[2024-12-01 04:07:51,453][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
+[2024-12-01 04:13:51,219][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4231 > 4096. Truncating input.
+[2024-12-01 05:31:40,951][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4470 > 4096. Truncating input.
+[2024-12-01 05:44:54,377][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4302 > 4096. Truncating input.
+[2024-12-01 06:09:15,205][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4172 > 4096. Truncating input.
+[2024-12-01 06:30:13,435][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4544 > 4096. Truncating input.
+[2024-12-01 07:29:10,829][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4598 > 4096. Truncating input.
+[2024-12-01 07:40:59,923][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4164 > 4096. Truncating input.
+[2024-12-01 07:42:13,899][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4103 > 4096. Truncating input.
+[2024-12-01 07:45:29,522][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4423 > 4096. Truncating input.
+[2024-12-01 08:43:38,441][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4130 > 4096. Truncating input.
+[2024-12-01 08:44:49,569][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4692 > 4096. Truncating input.
+[2024-12-01 09:16:07,523][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4823 > 4096. Truncating input.
+[2024-12-01 09:47:11,409][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4856 > 4096. Truncating input.
+[2024-12-01 10:20:18,874][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4311 > 4096. Truncating input.
+[2024-12-01 10:39:43,923][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4156 > 4096. Truncating input.
+[2024-12-01 11:19:17,171][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4344 > 4096. Truncating input.
+[2024-12-01 12:20:09,388][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4518 > 4096. Truncating input.
+[2024-12-01 12:38:05,642][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4531 > 4096. Truncating input.
+[2024-12-01 12:45:50,057][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4144 > 4096. Truncating input.
+[2024-12-01 12:51:19,115][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4310 > 4096. Truncating input.
+[2024-12-01 13:34:36,359][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4973 > 4096. Truncating input.
+[2024-12-01 13:39:35,635][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4969 > 4096. Truncating input.
+[2024-12-01 14:32:32,268][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4815 > 4096. Truncating input.
+[2024-12-01 14:40:47,289][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4475 > 4096. Truncating input.
+[2024-12-01 15:10:12,607][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4695 > 4096. Truncating input.
+[2024-12-01 15:15:08,675][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5839 > 4096. Truncating input.
+[2024-12-01 15:22:29,232][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4223 > 4096. Truncating input.
+[2024-12-01 15:30:23,138][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4122 > 4096. Truncating input.
+[2024-12-01 16:27:27,280][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5353 > 4096. Truncating input.
+[2024-12-01 16:46:47,219][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8354 > 4096. Truncating input.
+[2024-12-01 17:04:20,706][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4710 > 4096. Truncating input.
+[2024-12-01 17:17:17,893][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4266 > 4096. Truncating input.
+[2024-12-01 19:11:34,812][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4111 > 4096. Truncating input.
+[2024-12-01 19:12:10,303][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4225 > 4096. Truncating input.
+[2024-12-01 19:15:55,659][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4624 > 4096. Truncating input.
+[2024-12-01 19:27:31,904][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4572 > 4096. Truncating input.
+[2024-12-01 19:36:06,480][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5937 > 4096. Truncating input.
+[2024-12-01 20:12:28,074][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4751 > 4096. Truncating input.
+[2024-12-01 20:18:08,847][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4893 > 4096. Truncating input.
+[2024-12-01 21:11:20,813][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4165 > 4096. Truncating input.
+[2024-12-01 21:13:17,157][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4255 > 4096. Truncating input.
+[2024-12-01 21:51:26,240][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4399 > 4096. Truncating input.
+[2024-12-01 22:07:17,123][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4646 > 4096. Truncating input.
+[2024-12-01 23:20:22,143][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4111 > 4096. Truncating input.
+[2024-12-01 23:40:11,754][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4514 > 4096. Truncating input.
+[2024-12-01 23:47:04,498][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4302 > 4096. Truncating input.
+[2024-12-02 00:02:10,904][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4317 > 4096. Truncating input.
+[2024-12-02 00:04:54,655][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5160 > 4096. Truncating input.
+[2024-12-02 00:12:20,252][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4531 > 4096. Truncating input.
+[2024-12-02 00:37:51,084][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4880 > 4096. Truncating input.
+[2024-12-02 01:02:41,448][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4311 > 4096. Truncating input.
+[2024-12-02 01:16:29,792][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4799 > 4096. Truncating input.
+[2024-12-02 01:23:33,991][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4525 > 4096. Truncating input.
+[2024-12-02 01:42:01,845][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5808 > 4096. Truncating input.
+[2024-12-02 01:48:47,810][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4221 > 4096. Truncating input.
+[2024-12-02 02:00:20,951][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4505 > 4096. Truncating input.
+[2024-12-02 02:13:04,065][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6102 > 4096. Truncating input.
+[2024-12-02 02:32:45,233][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4555 > 4096. Truncating input.
+[2024-12-02 03:22:08,724][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4815 > 4096. Truncating input.
+[2024-12-02 03:55:15,110][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4711 > 4096. Truncating input.
+[2024-12-02 04:05:59,852][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4964 > 4096. Truncating input.
+[2024-12-02 04:06:22,323][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4437 > 4096. Truncating input.
+[2024-12-02 04:10:40,146][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5242 > 4096. Truncating input.
+[2024-12-02 04:38:08,950][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
+[2024-12-02 05:21:03,459][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4499 > 4096. Truncating input.
+[2024-12-02 05:26:14,727][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4306 > 4096. Truncating input.
+[2024-12-02 05:29:02,827][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4303 > 4096. Truncating input.
+[2024-12-02 05:58:13,992][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4547 > 4096. Truncating input.
+[2024-12-02 06:11:20,533][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4220 > 4096. Truncating input.
+[2024-12-02 06:11:37,194][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4470 > 4096. Truncating input.
+[2024-12-02 06:27:05,986][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5493 > 4096. Truncating input.
+[2024-12-02 06:28:41,495][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6179 > 4096. Truncating input.
+[2024-12-02 06:47:22,981][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5407 > 4096. Truncating input.
+[2024-12-02 07:10:08,853][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5526 > 4096. Truncating input.
+[2024-12-02 07:19:46,268][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4822 > 4096. Truncating input.
+[2024-12-02 07:40:53,053][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6038 > 4096. Truncating input.
+[2024-12-02 07:43:55,944][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4491 > 4096. Truncating input.
+[2024-12-02 08:14:30,948][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4960 > 4096. Truncating input.
+[2024-12-02 08:37:04,877][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4849 > 4096. Truncating input.
+[2024-12-02 09:02:23,302][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4353 > 4096. Truncating input.
+[2024-12-02 10:20:33,401][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4204 > 4096. Truncating input.
+[2024-12-02 11:16:40,587][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4518 > 4096. Truncating input.
+[2024-12-02 11:38:03,799][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4800 > 4096. Truncating input.
+[2024-12-02 11:38:55,211][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4700 > 4096. Truncating input.
+[2024-12-02 11:47:36,592][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4611 > 4096. Truncating input.
+[2024-12-02 11:58:23,008][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4859 > 4096. Truncating input.
+[2024-12-02 11:58:48,730][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4237 > 4096. Truncating input.
+[2024-12-02 12:04:39,279][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4521 > 4096. Truncating input.
+[2024-12-02 12:14:04,079][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4370 > 4096. Truncating input.
+[2024-12-02 12:17:28,272][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4581 > 4096. Truncating input.
+[2024-12-02 12:24:04,960][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4898 > 4096. Truncating input.
+[2024-12-02 12:38:07,511][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4255 > 4096. Truncating input.
+[2024-12-02 12:48:34,832][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4734 > 4096. Truncating input.
+[2024-12-02 13:09:53,630][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4924 > 4096. Truncating input.
+[2024-12-02 13:45:30,808][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4739 > 4096. Truncating input.
+[2024-12-02 15:20:02,074][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4522 > 4096. Truncating input.
+[2024-12-02 16:46:10,450][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5094 > 4096. Truncating input.
+[2024-12-02 17:14:41,665][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5327 > 4096. Truncating input.
+[2024-12-02 17:22:11,928][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5315 > 4096. Truncating input.
+[2024-12-02 17:51:37,183][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4144 > 4096. Truncating input.
+[2024-12-02 17:52:41,523][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5354 > 4096. Truncating input.

hydra_output_2024-12-01_00-02-51/train_ddp_process_6.log

@@ -0,0 +1,103 @@
+[2024-12-01 00:02:58,856][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 6, MEMBER: 7/8
+[2024-12-01 00:02:58,862][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
+[2024-12-01 00:02:58,863][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
+[2024-12-01 00:02:58,913][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
+[2024-12-01 00:02:58,915][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
+[2024-12-01 00:02:58,921][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
+[2024-12-01 00:02:58,922][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
+[2024-12-01 00:02:59,849][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
+[2024-12-01 00:03:09,095][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
+[2024-12-01 00:03:09,098][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
+[2024-12-01 00:06:20,852][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4727 > 4096. Truncating input.
+[2024-12-01 01:27:07,856][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4672 > 4096. Truncating input.
+[2024-12-01 01:59:30,104][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4302 > 4096. Truncating input.
+[2024-12-01 02:26:23,752][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4928 > 4096. Truncating input.
+[2024-12-01 02:54:25,551][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4822 > 4096. Truncating input.
+[2024-12-01 03:24:26,745][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5009 > 4096. Truncating input.
+[2024-12-01 03:58:17,719][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4279 > 4096. Truncating input.
+[2024-12-01 04:22:30,573][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6605 > 4096. Truncating input.
+[2024-12-01 05:23:06,026][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6722 > 4096. Truncating input.
+[2024-12-01 05:31:30,272][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5082 > 4096. Truncating input.
+[2024-12-01 05:34:57,569][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4220 > 4096. Truncating input.
+[2024-12-01 06:48:29,544][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4615 > 4096. Truncating input.
+[2024-12-01 07:18:13,461][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4528 > 4096. Truncating input.
+[2024-12-01 08:00:31,680][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5277 > 4096. Truncating input.
+[2024-12-01 08:02:52,070][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4339 > 4096. Truncating input.
+[2024-12-01 08:30:55,759][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4203 > 4096. Truncating input.
+[2024-12-01 08:33:02,864][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4208 > 4096. Truncating input.
+[2024-12-01 08:40:45,758][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4599 > 4096. Truncating input.
+[2024-12-01 09:28:00,571][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4449 > 4096. Truncating input.
+[2024-12-01 09:36:13,424][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4154 > 4096. Truncating input.
+[2024-12-01 09:38:21,960][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 7287 > 4096. Truncating input.
+[2024-12-01 09:48:25,236][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4224 > 4096. Truncating input.
+[2024-12-01 09:58:25,324][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4846 > 4096. Truncating input.
+[2024-12-01 10:15:03,869][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4591 > 4096. Truncating input.
+[2024-12-01 10:48:14,493][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4491 > 4096. Truncating input.
+[2024-12-01 11:22:38,713][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4505 > 4096. Truncating input.
+[2024-12-01 11:29:21,830][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4243 > 4096. Truncating input.
+[2024-12-01 11:46:16,285][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4302 > 4096. Truncating input.
+[2024-12-01 11:53:04,158][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5258 > 4096. Truncating input.
+[2024-12-01 12:14:38,689][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4102 > 4096. Truncating input.
+[2024-12-01 12:37:54,867][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4117 > 4096. Truncating input.
+[2024-12-01 13:00:41,811][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4563 > 4096. Truncating input.
+[2024-12-01 14:50:37,930][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5018 > 4096. Truncating input.
+[2024-12-01 15:11:34,736][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4493 > 4096. Truncating input.
+[2024-12-01 16:03:58,695][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5603 > 4096. Truncating input.
+[2024-12-01 16:05:51,754][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4581 > 4096. Truncating input.
+[2024-12-01 17:39:51,417][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5775 > 4096. Truncating input.
+[2024-12-01 18:13:15,816][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4553 > 4096. Truncating input.
+[2024-12-01 19:07:22,882][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4552 > 4096. Truncating input.
+[2024-12-01 20:14:47,029][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4138 > 4096. Truncating input.
+[2024-12-01 20:17:58,085][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4898 > 4096. Truncating input.
+[2024-12-01 20:20:47,178][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4604 > 4096. Truncating input.
+[2024-12-01 21:04:26,142][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4718 > 4096. Truncating input.
+[2024-12-01 22:01:51,325][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4661 > 4096. Truncating input.
+[2024-12-01 22:19:50,088][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4266 > 4096. Truncating input.
+[2024-12-01 22:37:18,200][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4257 > 4096. Truncating input.
+[2024-12-01 23:11:04,540][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4557 > 4096. Truncating input.
+[2024-12-02 00:26:23,381][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6769 > 4096. Truncating input.
+[2024-12-02 00:51:27,744][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4222 > 4096. Truncating input.
+[2024-12-02 00:51:59,526][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4429 > 4096. Truncating input.
+[2024-12-02 01:08:13,532][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4489 > 4096. Truncating input.
+[2024-12-02 02:11:09,227][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4282 > 4096. Truncating input.
+[2024-12-02 02:20:51,665][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4445 > 4096. Truncating input.
+[2024-12-02 02:30:43,344][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4154 > 4096. Truncating input.
+[2024-12-02 03:37:27,317][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4860 > 4096. Truncating input.
+[2024-12-02 04:31:29,196][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4865 > 4096. Truncating input.
+[2024-12-02 04:31:40,276][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4302 > 4096. Truncating input.
+[2024-12-02 05:02:46,830][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4856 > 4096. Truncating input.
+[2024-12-02 05:38:02,758][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6168 > 4096. Truncating input.
+[2024-12-02 07:10:38,230][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4365 > 4096. Truncating input.
+[2024-12-02 07:24:06,549][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4533 > 4096. Truncating input.
+[2024-12-02 07:36:29,871][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4632 > 4096. Truncating input.
+[2024-12-02 07:39:28,784][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4722 > 4096. Truncating input.
+[2024-12-02 08:20:56,709][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6129 > 4096. Truncating input.
+[2024-12-02 08:51:01,632][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4210 > 4096. Truncating input.
+[2024-12-02 08:59:17,913][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4169 > 4096. Truncating input.
+[2024-12-02 09:02:12,470][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6157 > 4096. Truncating input.
+[2024-12-02 09:14:56,916][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4869 > 4096. Truncating input.
+[2024-12-02 09:46:28,909][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4944 > 4096. Truncating input.
+[2024-12-02 09:50:16,358][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4674 > 4096. Truncating input.
+[2024-12-02 10:51:38,626][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4113 > 4096. Truncating input.
+[2024-12-02 10:59:49,906][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5123 > 4096. Truncating input.
+[2024-12-02 11:16:05,197][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4160 > 4096. Truncating input.
+[2024-12-02 11:35:21,289][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
+[2024-12-02 12:25:49,672][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4117 > 4096. Truncating input.
+[2024-12-02 12:47:01,236][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4770 > 4096. Truncating input.
+[2024-12-02 13:46:31,191][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4727 > 4096. Truncating input.
+[2024-12-02 14:02:37,628][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4119 > 4096. Truncating input.
+[2024-12-02 14:33:17,395][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4099 > 4096. Truncating input.
+[2024-12-02 14:33:58,512][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4176 > 4096. Truncating input.
+[2024-12-02 15:02:58,046][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4824 > 4096. Truncating input.
+[2024-12-02 15:11:10,797][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4412 > 4096. Truncating input.
+[2024-12-02 15:17:37,258][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4475 > 4096. Truncating input.
+[2024-12-02 16:23:02,419][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4368 > 4096. Truncating input.
+[2024-12-02 16:35:55,049][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4921 > 4096. Truncating input.
+[2024-12-02 16:40:02,141][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5600 > 4096. Truncating input.
+[2024-12-02 16:41:22,432][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4474 > 4096. Truncating input.
+[2024-12-02 17:07:07,894][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4161 > 4096. Truncating input.
+[2024-12-02 17:08:12,948][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4372 > 4096. Truncating input.
+[2024-12-02 17:42:15,388][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5632 > 4096. Truncating input.
+[2024-12-02 17:42:48,817][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6658 > 4096. Truncating input.
+[2024-12-02 18:12:47,063][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4475 > 4096. Truncating input.
+[2024-12-02 18:23:40,977][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4928 > 4096. Truncating input.

hydra_output_2024-12-01_00-02-51/train_ddp_process_7.log

@@ -0,0 +1,110 @@
+[2024-12-01 00:02:59,265][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 7, MEMBER: 8/8
+[2024-12-01 00:02:59,272][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
+[2024-12-01 00:02:59,273][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
+[2024-12-01 00:02:59,325][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
+[2024-12-01 00:02:59,326][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
+[2024-12-01 00:02:59,332][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
+[2024-12-01 00:02:59,333][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
+[2024-12-01 00:03:01,074][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
+[2024-12-01 00:03:09,213][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
+[2024-12-01 00:03:09,217][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
+[2024-12-01 00:29:10,202][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4304 > 4096. Truncating input.
+[2024-12-01 01:38:36,363][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4927 > 4096. Truncating input.
+[2024-12-01 02:00:30,185][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4563 > 4096. Truncating input.
+[2024-12-01 02:59:29,219][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4489 > 4096. Truncating input.
+[2024-12-01 04:01:09,819][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5446 > 4096. Truncating input.
+[2024-12-01 04:02:37,109][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4656 > 4096. Truncating input.
+[2024-12-01 04:14:48,934][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4559 > 4096. Truncating input.
+[2024-12-01 04:26:27,792][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4264 > 4096. Truncating input.
+[2024-12-01 04:33:16,726][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4435 > 4096. Truncating input.
+[2024-12-01 05:01:43,965][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4985 > 4096. Truncating input.
+[2024-12-01 05:27:47,667][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4517 > 4096. Truncating input.
+[2024-12-01 05:37:44,798][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4828 > 4096. Truncating input.
+[2024-12-01 05:44:31,044][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4963 > 4096. Truncating input.
+[2024-12-01 05:50:31,027][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4705 > 4096. Truncating input.
+[2024-12-01 06:13:34,991][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4362 > 4096. Truncating input.
+[2024-12-01 06:26:41,441][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4741 > 4096. Truncating input.
+[2024-12-01 06:27:31,916][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4674 > 4096. Truncating input.
+[2024-12-01 06:27:50,096][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4802 > 4096. Truncating input.
+[2024-12-01 06:46:45,160][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4499 > 4096. Truncating input.
+[2024-12-01 06:53:50,075][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4380 > 4096. Truncating input.
+[2024-12-01 07:00:04,358][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4317 > 4096. Truncating input.
+[2024-12-01 07:06:08,859][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5195 > 4096. Truncating input.
+[2024-12-01 07:24:49,998][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5632 > 4096. Truncating input.
+[2024-12-01 07:50:14,098][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4380 > 4096. Truncating input.
+[2024-12-01 07:52:20,931][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6079 > 4096. Truncating input.
+[2024-12-01 07:53:14,617][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8047 > 4096. Truncating input.
+[2024-12-01 08:12:23,380][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4522 > 4096. Truncating input.
+[2024-12-01 09:24:06,913][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5375 > 4096. Truncating input.
+[2024-12-01 09:46:49,958][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4644 > 4096. Truncating input.
+[2024-12-01 10:03:11,726][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4413 > 4096. Truncating input.
+[2024-12-01 10:06:17,350][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8099 > 4096. Truncating input.
+[2024-12-01 10:21:56,208][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4685 > 4096. Truncating input.
+[2024-12-01 11:04:32,779][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4274 > 4096. Truncating input.
+[2024-12-01 11:32:31,368][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4644 > 4096. Truncating input.
+[2024-12-01 11:40:37,131][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6102 > 4096. Truncating input.
+[2024-12-01 11:56:03,244][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4445 > 4096. Truncating input.
+[2024-12-01 12:19:15,011][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5185 > 4096. Truncating input.
+[2024-12-01 12:21:58,720][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4917 > 4096. Truncating input.
+[2024-12-01 13:01:23,440][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6591 > 4096. Truncating input.
+[2024-12-01 13:18:19,939][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4456 > 4096. Truncating input.
+[2024-12-01 13:23:32,175][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5407 > 4096. Truncating input.
+[2024-12-01 13:42:02,861][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5295 > 4096. Truncating input.
+[2024-12-01 13:44:56,121][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4503 > 4096. Truncating input.
+[2024-12-01 13:59:59,514][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5365 > 4096. Truncating input.
+[2024-12-01 14:37:53,795][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4130 > 4096. Truncating input.
+[2024-12-01 14:41:13,698][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4994 > 4096. Truncating input.
+[2024-12-01 15:08:08,991][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4865 > 4096. Truncating input.
+[2024-12-01 15:16:11,724][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4380 > 4096. Truncating input.
+[2024-12-01 15:51:09,740][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4569 > 4096. Truncating input.
+[2024-12-01 17:15:31,169][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4735 > 4096. Truncating input.
+[2024-12-01 17:15:50,705][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4957 > 4096. Truncating input.
+[2024-12-01 17:16:12,343][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4611 > 4096. Truncating input.
+[2024-12-01 18:32:25,187][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4609 > 4096. Truncating input.
+[2024-12-01 19:00:15,039][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4465 > 4096. Truncating input.
+[2024-12-01 19:25:39,910][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4856 > 4096. Truncating input.
+[2024-12-01 19:29:17,214][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4922 > 4096. Truncating input.
+[2024-12-01 19:37:39,547][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4204 > 4096. Truncating input.
+[2024-12-01 19:56:08,649][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4301 > 4096. Truncating input.
+[2024-12-01 19:59:48,851][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4442 > 4096. Truncating input.
+[2024-12-01 20:47:15,803][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4282 > 4096. Truncating input.
+[2024-12-01 21:04:07,815][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6720 > 4096. Truncating input.
+[2024-12-01 21:05:10,492][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4161 > 4096. Truncating input.
+[2024-12-01 21:27:38,311][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5848 > 4096. Truncating input.
+[2024-12-01 21:49:31,607][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 7287 > 4096. Truncating input.
+[2024-12-01 22:54:49,298][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4973 > 4096. Truncating input.
+[2024-12-02 00:19:43,160][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4250 > 4096. Truncating input.
+[2024-12-02 00:25:26,495][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5161 > 4096. Truncating input.
+[2024-12-02 00:47:58,870][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4353 > 4096. Truncating input.
+[2024-12-02 02:04:38,642][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4518 > 4096. Truncating input.
+[2024-12-02 02:14:07,905][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5018 > 4096. Truncating input.
+[2024-12-02 02:14:33,277][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4517 > 4096. Truncating input.
+[2024-12-02 02:36:15,506][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4609 > 4096. Truncating input.
+[2024-12-02 02:47:31,108][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4407 > 4096. Truncating input.
+[2024-12-02 03:02:00,604][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4380 > 4096. Truncating input.
+[2024-12-02 03:03:37,747][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4138 > 4096. Truncating input.
+[2024-12-02 04:11:05,327][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4228 > 4096. Truncating input.
+[2024-12-02 05:02:35,765][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4478 > 4096. Truncating input.
+[2024-12-02 05:29:02,798][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5677 > 4096. Truncating input.
+[2024-12-02 05:51:58,988][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5095 > 4096. Truncating input.
+[2024-12-02 06:14:45,215][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5025 > 4096. Truncating input.
+[2024-12-02 06:52:55,749][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4117 > 4096. Truncating input.
+[2024-12-02 08:27:40,017][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4692 > 4096. Truncating input.
+[2024-12-02 08:36:20,266][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5365 > 4096. Truncating input.
+[2024-12-02 08:41:13,132][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5258 > 4096. Truncating input.
+[2024-12-02 09:07:47,098][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4970 > 4096. Truncating input.
+[2024-12-02 09:43:34,687][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5245 > 4096. Truncating input.
+[2024-12-02 09:49:23,920][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4923 > 4096. Truncating input.
+[2024-12-02 10:07:41,774][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4139 > 4096. Truncating input.
+[2024-12-02 10:57:26,097][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4927 > 4096. Truncating input.
+[2024-12-02 11:01:46,333][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5178 > 4096. Truncating input.
+[2024-12-02 11:11:45,921][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4704 > 4096. Truncating input.
+[2024-12-02 12:03:29,505][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4672 > 4096. Truncating input.
+[2024-12-02 14:25:13,862][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4456 > 4096. Truncating input.
+[2024-12-02 15:19:02,576][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 7055 > 4096. Truncating input.
+[2024-12-02 15:40:12,347][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4823 > 4096. Truncating input.
+[2024-12-02 15:59:55,087][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4279 > 4096. Truncating input.
+[2024-12-02 16:22:12,874][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4601 > 4096. Truncating input.
+[2024-12-02 16:29:51,006][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4496 > 4096. Truncating input.
+[2024-12-02 17:12:46,832][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4574 > 4096. Truncating input.
+[2024-12-02 17:33:31,870][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4725 > 4096. Truncating input.

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42b01fc70de3b2c9403062b896552a6090569d42fbd537f4c529c29cb36440f
+size 2471653888

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2062 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}