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

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.2"
+}

logs/rank_0000.log

@@ -0,0 +1,340 @@
+[2025-01-31 02:24:32,670][oumi][rank0][pid:10758][MainThread][INFO]][train.py:144] Resolved 'training.dataloader_num_workers=auto' to 'training.dataloader_num_workers=8'
+[2025-01-31 02:24:32,672][oumi][rank0][pid:10758][MainThread][INFO]][train.py:174] TrainingConfig:
+TrainingConfig(data=DataParams(train=DatasetSplitParams(datasets=[DatasetParams(dataset_name='HuggingFaceH4/ultrachat_200k',
+                                                                                dataset_path=None,
+                                                                                subset=None,
+                                                                                split='train_sft',
+                                                                                dataset_kwargs={},
+                                                                                sample_count=None,
+                                                                                mixture_proportion=None,
+                                                                                shuffle=False,
+                                                                                seed=None,
+                                                                                shuffle_buffer_size=1000,
+                                                                                trust_remote_code=True,
+                                                                                transform_num_workers=None)],
+                                                        collator_name=None,
+                                                        pack=False,
+                                                        stream=False,
+                                                        target_col=None,
+                                                        mixture_strategy='first_exhausted',
+                                                        seed=None,
+                                                        use_async_dataset=False,
+                                                        use_torchdata=None),
+                               test=DatasetSplitParams(datasets=[],
+                                                       collator_name=None,
+                                                       pack=False,
+                                                       stream=False,
+                                                       target_col=None,
+                                                       mixture_strategy='first_exhausted',
+                                                       seed=None,
+                                                       use_async_dataset=False,
+                                                       use_torchdata=None),
+                               validation=DatasetSplitParams(datasets=[],
+                                                             collator_name=None,
+                                                             pack=False,
+                                                             stream=False,
+                                                             target_col=None,
+                                                             mixture_strategy='first_exhausted',
+                                                             seed=None,
+                                                             use_async_dataset=False,
+                                                             use_torchdata=None)),
+               model=ModelParams(model_name='meta-llama/Meta-Llama-3.1-8B',
+                                 adapter_model=None,
+                                 tokenizer_name=None,
+                                 tokenizer_pad_token=None,
+                                 tokenizer_kwargs={},
+                                 model_max_length=8192,
+                                 load_pretrained_weights=True,
+                                 trust_remote_code=True,
+                                 torch_dtype_str='bfloat16',
+                                 compile=False,
+                                 chat_template='llama3-instruct',
+                                 attn_implementation='flash_attention_2',
+                                 device_map='auto',
+                                 model_kwargs={},
+                                 enable_liger_kernel=True,
+                                 shard_for_eval=False,
+                                 freeze_layers=[]),
+               training=TrainingParams(use_peft=False,
+                                       trainer_type=<TrainerType.TRL_SFT: 'trl_sft'>,
+                                       enable_gradient_checkpointing=True,
+                                       gradient_checkpointing_kwargs={'use_reentrant': False},
+                                       output_dir='output/llama8b-ultrachat',
+                                       per_device_train_batch_size=1,
+                                       per_device_eval_batch_size=8,
+                                       gradient_accumulation_steps=8,
+                                       max_steps=-1,
+                                       num_train_epochs=1,
+                                       save_epoch=False,
+                                       save_steps=800,
+                                       save_final_model=True,
+                                       seed=42,
+                                       run_name='llama8b-ultrachat.sky-2025-01-30-21-19-10-053582_sky-e018-bf996_1',
+                                       metrics_function=None,
+                                       log_level='info',
+                                       dep_log_level='warning',
+                                       enable_wandb=True,
+                                       enable_tensorboard=True,
+                                       logging_strategy='steps',
+                                       logging_dir=None,
+                                       logging_steps=100,
+                                       logging_first_step=False,
+                                       eval_strategy='no',
+                                       eval_steps=500,
+                                       learning_rate=2e-05,
+                                       lr_scheduler_type='linear',
+                                       lr_scheduler_kwargs={},
+                                       warmup_ratio=None,
+                                       warmup_steps=None,
+                                       optimizer='paged_adamw_8bit',
+                                       weight_decay=0.0,
+                                       adam_beta1=0.9,
+                                       adam_beta2=0.999,
+                                       adam_epsilon=1e-08,
+                                       sgd_momentum=0.0,
+                                       mixed_precision_dtype=<MixedPrecisionDtype.NONE: 'none'>,
+                                       compile=False,
+                                       include_performance_metrics=True,
+                                       include_alternative_mfu_metrics=False,
+                                       log_model_summary=False,
+                                       resume_from_checkpoint=None,
+                                       try_resume_from_last_checkpoint=False,
+                                       dataloader_num_workers=8,
+                                       dataloader_prefetch_factor=32,
+                                       dataloader_main_process_only=None,
+                                       ddp_find_unused_parameters=False,
+                                       max_grad_norm=1.0,
+                                       trainer_kwargs={'max_seq_length': 8192},
+                                       profiler=ProfilerParams(save_dir=None,
+                                                               enable_cpu_profiling=False,
+                                                               enable_cuda_profiling=False,
+                                                               record_shapes=False,
+                                                               profile_memory=False,
+                                                               with_stack=False,
+                                                               with_flops=False,
+                                                               with_modules=False,
+                                                               row_limit=50,
+                                                               schedule=ProfilerScheduleParams(enable_schedule=False,
+                                                                                               wait=0,
+                                                                                               warmup=1,
+                                                                                               active=3,
+                                                                                               repeat=1,
+                                                                                               skip_first=1)),
+                                       telemetry=TelemetryParams(telemetry_dir='telemetry',
+                                                                 collect_telemetry_for_all_ranks=False,
+                                                                 track_gpu_temperature=False),
+                                       empty_device_cache_steps=50,
+                                       nccl_default_timeout_minutes=None),
+               peft=PeftParams(lora_r=8,
+                               lora_alpha=8,
+                               lora_dropout=0.0,
+                               lora_target_modules=None,
+                               lora_modules_to_save=None,
+                               lora_bias='none',
+                               lora_init_weights=<LoraWeightInitialization.DEFAULT: 'default'>,
+                               lora_task_type=<TaskType.CAUSAL_LM: 'CAUSAL_LM'>,
+                               q_lora=False,
+                               q_lora_bits=4,
+                               bnb_4bit_quant_type='fp4',
+                               use_bnb_nested_quant=False,
+                               bnb_4bit_quant_storage='uint8',
+                               bnb_4bit_compute_dtype='float32',
+                               peft_save_mode=<PeftSaveMode.ADAPTER_ONLY: 'adapter_only'>),
+               fsdp=FSDPParams(enable_fsdp=False,
+                               sharding_strategy=<ShardingStrategy.FULL_SHARD: 'FULL_SHARD'>,
+                               cpu_offload=False,
+                               mixed_precision=None,
+                               backward_prefetch=<BackwardPrefetch.BACKWARD_PRE: 'BACKWARD_PRE'>,
+                               forward_prefetch=False,
+                               use_orig_params=None,
+                               state_dict_type=<StateDictType.FULL_STATE_DICT: 'FULL_STATE_DICT'>,
+                               auto_wrap_policy=<AutoWrapPolicy.NO_WRAP: 'NO_WRAP'>,
+                               min_num_params=100000,
+                               transformer_layer_cls=None,
+                               sync_module_states=True))
+[2025-01-31 02:24:33,489][oumi][rank0][pid:10758][MainThread][WARNING]][models.py:412] Undefined pad token. Setting it to `<|finetune_right_pad_id|>`.
+[2025-01-31 02:24:33,490][oumi][rank0][pid:10758][MainThread][INFO]][models.py:428] Using the chat template 'llama3-instruct' specified in model config!
+[2025-01-31 02:24:33,490][oumi][rank0][pid:10758][MainThread][INFO]][models.py:180] Building model for distributed training (world_size: 4)...
+[2025-01-31 02:24:33,490][oumi][rank0][pid:10758][MainThread][INFO]][models.py:185] Building model using device_map: cuda:0 (DeviceRankInfo(world_size=4, rank=0, local_world_size=4, local_rank=0))...
+[2025-01-31 02:24:33,490][oumi][rank0][pid:10758][MainThread][INFO]][models.py:255] Using model class: <class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'> to instantiate model.
+[2025-01-31 02:24:39,738][oumi][rank0][pid:10758][MainThread][INFO]][base_map_dataset.py:68] Creating map dataset (type: UltrachatH4Dataset) dataset_name: 'HuggingFaceH4/ultrachat_200k', dataset_path: 'None'...
+[2025-01-31 02:25:29,865][oumi][rank0][pid:10758][MainThread][INFO]][base_map_dataset.py:472] Dataset Info:
+	Split: train_sft
+	Version: 0.0.0
+	Dataset size: 3047427114
+	Download size: 1624049723
+	Size: 4671476837 bytes
+	Rows: 207865
+	Columns: ['prompt', 'prompt_id', 'messages']
+[2025-01-31 02:25:33,367][oumi][rank0][pid:10758][MainThread][INFO]][base_map_dataset.py:411] Loaded DataFrame with shape: (207865, 3). Columns:
+prompt       object
+prompt_id    object
+messages     object
+dtype: object
+[2025-01-31 02:25:33,466][oumi][rank0][pid:10758][MainThread][INFO]][base_map_dataset.py:297] UltrachatH4Dataset: features=dict_keys(['input_ids', 'attention_mask'])
+[2025-01-31 02:39:30,852][oumi][rank0][pid:10758][MainThread][INFO]][base_map_dataset.py:361] Finished transforming dataset (UltrachatH4Dataset)! Speed: 248.23 examples/sec. Examples: 207865. Duration: 837.4 sec. Transform workers: 1.
+[2025-01-31 02:39:31,449][oumi][rank0][pid:10758][MainThread][INFO]][torch_profiler_utils.py:150] PROF: Torch Profiler disabled!
+[2025-01-31 02:39:31,449][oumi][rank0][pid:10758][MainThread][WARNING]][callbacks.py:54] MFU logging requires packed datasets. Skipping MFU callbacks.
+[2025-01-31 02:39:31,499][oumi][rank0][pid:10758][MainThread][INFO]][training.py:49] SFTConfig(output_dir='output/llama8b-ultrachat',
+          overwrite_output_dir=False,
+          do_train=False,
+          do_eval=False,
+          do_predict=False,
+          eval_strategy=<IntervalStrategy.NO: 'no'>,
+          prediction_loss_only=False,
+          per_device_train_batch_size=1,
+          per_device_eval_batch_size=8,
+          per_gpu_train_batch_size=None,
+          per_gpu_eval_batch_size=None,
+          gradient_accumulation_steps=8,
+          eval_accumulation_steps=None,
+          eval_delay=0,
+          torch_empty_cache_steps=50,
+          learning_rate=2e-05,
+          weight_decay=0.0,
+          adam_beta1=0.9,
+          adam_beta2=0.999,
+          adam_epsilon=1e-08,
+          max_grad_norm=1.0,
+          num_train_epochs=1,
+          max_steps=-1,
+          lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>,
+          lr_scheduler_kwargs={},
+          warmup_ratio=0.0,
+          warmup_steps=0,
+          log_level='warning',
+          log_level_replica='warning',
+          log_on_each_node=True,
+          logging_dir='output/llama8b-ultrachat/runs/Jan31_02-39-31_sky-e018-bf996-370b-head-9t91s4aj-compute',
+          logging_strategy=<IntervalStrategy.STEPS: 'steps'>,
+          logging_first_step=False,
+          logging_steps=100,
+          logging_nan_inf_filter=True,
+          save_strategy=<IntervalStrategy.STEPS: 'steps'>,
+          save_steps=800,
+          save_total_limit=None,
+          save_safetensors=True,
+          save_on_each_node=False,
+          save_only_model=False,
+          restore_callback_states_from_checkpoint=False,
+          no_cuda=False,
+          use_cpu=False,
+          use_mps_device=False,
+          seed=42,
+          data_seed=None,
+          jit_mode_eval=False,
+          use_ipex=False,
+          bf16=False,
+          fp16=False,
+          fp16_opt_level='O1',
+          half_precision_backend='auto',
+          bf16_full_eval=False,
+          fp16_full_eval=False,
+          tf32=None,
+          local_rank=0,
+          ddp_backend=None,
+          tpu_num_cores=None,
+          tpu_metrics_debug=False,
+          debug=[],
+          dataloader_drop_last=False,
+          eval_steps=500,
+          dataloader_num_workers=8,
+          dataloader_prefetch_factor=32,
+          past_index=-1,
+          run_name='llama8b-ultrachat.sky-2025-01-30-21-19-10-053582_sky-e018-bf996_1',
+          disable_tqdm=False,
+          remove_unused_columns=True,
+          label_names=None,
+          load_best_model_at_end=False,
+          metric_for_best_model=None,
+          greater_is_better=None,
+          ignore_data_skip=False,
+          fsdp=[],
+          fsdp_min_num_params=0,
+          fsdp_config={'min_num_params': 0,
+                       'xla': False,
+                       'xla_fsdp_grad_ckpt': False,
+                       'xla_fsdp_v2': False},
+          fsdp_transformer_layer_cls_to_wrap=None,
+          accelerator_config=AcceleratorConfig(split_batches=False,
+                                               dispatch_batches=None,
+                                               even_batches=True,
+                                               use_seedable_sampler=True,
+                                               non_blocking=False,
+                                               gradient_accumulation_kwargs=None,
+                                               use_configured_state=False),
+          deepspeed=None,
+          label_smoothing_factor=0.0,
+          optim=<OptimizerNames.PAGED_ADAMW_8BIT: 'paged_adamw_8bit'>,
+          optim_args=None,
+          adafactor=False,
+          group_by_length=False,
+          length_column_name='length',
+          report_to=['wandb', 'tensorboard'],
+          ddp_find_unused_parameters=False,
+          ddp_bucket_cap_mb=None,
+          ddp_broadcast_buffers=None,
+          dataloader_pin_memory=True,
+          dataloader_persistent_workers=False,
+          skip_memory_metrics=True,
+          use_legacy_prediction_loop=False,
+          push_to_hub=False,
+          resume_from_checkpoint=None,
+          hub_model_id=None,
+          hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>,
+          hub_token=None,
+          hub_private_repo=False,
+          hub_always_push=False,
+          gradient_checkpointing=True,
+          gradient_checkpointing_kwargs={'use_reentrant': False},
+          include_inputs_for_metrics=False,
+          eval_do_concat_batches=True,
+          fp16_backend='auto',
+          evaluation_strategy=None,
+          push_to_hub_model_id=None,
+          push_to_hub_organization=None,
+          push_to_hub_token=None,
+          mp_parameters='',
+          auto_find_batch_size=False,
+          full_determinism=False,
+          torchdynamo=None,
+          ray_scope='last',
+          ddp_timeout=1800,
+          torch_compile=False,
+          torch_compile_backend=None,
+          torch_compile_mode=None,
+          dispatch_batches=None,
+          split_batches=None,
+          include_tokens_per_second=True,
+          include_num_input_tokens_seen=True,
+          neftune_noise_alpha=None,
+          optim_target_modules=None,
+          batch_eval_metrics=False,
+          eval_on_start=False,
+          use_liger_kernel=False,
+          eval_use_gather_object=False,
+          dataset_text_field=None,
+          packing=False,
+          max_seq_length=8192,
+          dataset_num_proc=None,
+          dataset_batch_size=1000,
+          model_init_kwargs=None,
+          dataset_kwargs=None,
+          eval_packing=None,
+          num_of_sequences=1024,
+          chars_per_token=3.6,
+          use_liger=False)
+[2025-01-31 02:39:31,564][oumi][rank0][pid:10758][MainThread][INFO]][device_utils.py:283] GPU Metrics Before Training: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=19007.0, temperature=35, fan_speed=None, fan_speeds=None, power_usage_watts=78.83800000000001, power_limit_watts=400.0, gpu_utilization=0, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 02:39:31,568][oumi][rank0][pid:10758][MainThread][INFO]][train.py:312] Training init time: 901.293s
+[2025-01-31 02:39:31,568][oumi][rank0][pid:10758][MainThread][INFO]][train.py:313] Starting training... (TrainerType.TRL_SFT, transformers: 4.45.2)
+[2025-01-31 13:18:45,137][oumi][rank0][pid:10758][MainThread][INFO]][device_utils.py:283] On epoch end: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=69213.0, temperature=42, fan_speed=None, fan_speeds=None, power_usage_watts=78.479, power_limit_watts=400.0, gpu_utilization=2, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 13:18:45,419][oumi][rank0][pid:10758][MainThread][INFO]][telemetry_callback.py:228] Saving telemetry callback summary to output/llama8b-ultrachat/telemetry/telemetry_callback_rank0000.json...
+[2025-01-31 13:18:45,420][oumi][rank0][pid:10758][MainThread][INFO]][train.py:320] Training is Complete.
+[2025-01-31 13:18:45,428][oumi][rank0][pid:10758][MainThread][INFO]][device_utils.py:283] GPU Metrics After Training: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=69213.0, temperature=42, fan_speed=None, fan_speeds=None, power_usage_watts=79.107, power_limit_watts=400.0, gpu_utilization=0, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 13:18:45,428][oumi][rank0][pid:10758][MainThread][INFO]][torch_utils.py:117] Peak GPU memory usage: 47.39 GB
+[2025-01-31 13:18:45,429][oumi][rank0][pid:10758][MainThread][INFO]][train.py:327] Saving final state...
+[2025-01-31 13:18:45,431][oumi][rank0][pid:10758][MainThread][INFO]][train.py:332] Saving final model...
+[2025-01-31 13:19:20,486][oumi][rank0][pid:10758][MainThread][INFO]][hf_trainer.py:102] Model has been saved at output/llama8b-ultrachat
+[2025-01-31 13:19:21,037][oumi][rank0][pid:10758][MainThread][INFO]][train.py:339] 
+
+» We're always looking for feedback. What's one thing we can improve? https://oumi.ai/feedback

logs/rank_0001.log

@@ -0,0 +1,35 @@
+[2025-01-31 02:24:32,070][oumi][rank1][pid:10759][MainThread][INFO]][train.py:144] Resolved 'training.dataloader_num_workers=auto' to 'training.dataloader_num_workers=8'
+[2025-01-31 02:24:33,144][oumi][rank1][pid:10759][MainThread][WARNING]][models.py:412] Undefined pad token. Setting it to `<|finetune_right_pad_id|>`.
+[2025-01-31 02:24:33,145][oumi][rank1][pid:10759][MainThread][INFO]][models.py:428] Using the chat template 'llama3-instruct' specified in model config!
+[2025-01-31 02:24:33,145][oumi][rank1][pid:10759][MainThread][INFO]][models.py:180] Building model for distributed training (world_size: 4)...
+[2025-01-31 02:24:33,145][oumi][rank1][pid:10759][MainThread][INFO]][models.py:185] Building model using device_map: cuda:1 (DeviceRankInfo(world_size=4, rank=1, local_world_size=4, local_rank=1))...
+[2025-01-31 02:24:33,145][oumi][rank1][pid:10759][MainThread][INFO]][models.py:255] Using model class: <class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'> to instantiate model.
+[2025-01-31 02:24:39,500][oumi][rank1][pid:10759][MainThread][INFO]][base_map_dataset.py:68] Creating map dataset (type: UltrachatH4Dataset) dataset_name: 'HuggingFaceH4/ultrachat_200k', dataset_path: 'None'...
+[2025-01-31 02:25:29,916][oumi][rank1][pid:10759][MainThread][INFO]][base_map_dataset.py:472] Dataset Info:
+	Split: train_sft
+	Version: 0.0.0
+	Dataset size: 3047427114
+	Download size: 1624049723
+	Size: 4671476837 bytes
+	Rows: 207865
+	Columns: ['prompt', 'prompt_id', 'messages']
+[2025-01-31 02:25:33,428][oumi][rank1][pid:10759][MainThread][INFO]][base_map_dataset.py:411] Loaded DataFrame with shape: (207865, 3). Columns:
+prompt       object
+prompt_id    object
+messages     object
+dtype: object
+[2025-01-31 02:25:33,526][oumi][rank1][pid:10759][MainThread][INFO]][base_map_dataset.py:297] UltrachatH4Dataset: features=dict_keys(['input_ids', 'attention_mask'])
+[2025-01-31 02:39:30,837][oumi][rank1][pid:10759][MainThread][INFO]][base_map_dataset.py:361] Finished transforming dataset (UltrachatH4Dataset)! Speed: 248.25 examples/sec. Examples: 207865. Duration: 837.3 sec. Transform workers: 1.
+[2025-01-31 02:39:31,439][oumi][rank1][pid:10759][MainThread][INFO]][torch_profiler_utils.py:150] PROF: Torch Profiler disabled!
+[2025-01-31 02:39:31,440][oumi][rank1][pid:10759][MainThread][WARNING]][callbacks.py:54] MFU logging requires packed datasets. Skipping MFU callbacks.
+[2025-01-31 02:39:31,567][oumi][rank1][pid:10759][MainThread][INFO]][device_utils.py:283] GPU Metrics Before Training: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=19007.0, temperature=35, fan_speed=None, fan_speeds=None, power_usage_watts=78.83800000000001, power_limit_watts=400.0, gpu_utilization=0, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 02:39:31,568][oumi][rank1][pid:10759][MainThread][INFO]][train.py:312] Training init time: 901.293s
+[2025-01-31 02:39:31,568][oumi][rank1][pid:10759][MainThread][INFO]][train.py:313] Starting training... (TrainerType.TRL_SFT, transformers: 4.45.2)
+[2025-01-31 13:18:45,140][oumi][rank1][pid:10759][MainThread][INFO]][train.py:320] Training is Complete.
+[2025-01-31 13:18:45,163][oumi][rank1][pid:10759][MainThread][INFO]][device_utils.py:283] GPU Metrics After Training: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=69213.0, temperature=42, fan_speed=None, fan_speeds=None, power_usage_watts=78.479, power_limit_watts=400.0, gpu_utilization=2, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 13:18:45,163][oumi][rank1][pid:10759][MainThread][INFO]][torch_utils.py:117] Peak GPU memory usage: 47.39 GB
+[2025-01-31 13:18:45,163][oumi][rank1][pid:10759][MainThread][INFO]][train.py:327] Saving final state...
+[2025-01-31 13:18:45,431][oumi][rank1][pid:10759][MainThread][INFO]][train.py:332] Saving final model...
+[2025-01-31 13:19:21,038][oumi][rank1][pid:10759][MainThread][INFO]][train.py:339] 
+
+» We're always looking for feedback. What's one thing we can improve? https://oumi.ai/feedback

logs/rank_0002.log

@@ -0,0 +1,35 @@
+[2025-01-31 02:24:32,067][oumi][rank2][pid:10760][MainThread][INFO]][train.py:144] Resolved 'training.dataloader_num_workers=auto' to 'training.dataloader_num_workers=8'
+[2025-01-31 02:24:33,575][oumi][rank2][pid:10760][MainThread][WARNING]][models.py:412] Undefined pad token. Setting it to `<|finetune_right_pad_id|>`.
+[2025-01-31 02:24:33,576][oumi][rank2][pid:10760][MainThread][INFO]][models.py:428] Using the chat template 'llama3-instruct' specified in model config!
+[2025-01-31 02:24:33,577][oumi][rank2][pid:10760][MainThread][INFO]][models.py:180] Building model for distributed training (world_size: 4)...
+[2025-01-31 02:24:33,577][oumi][rank2][pid:10760][MainThread][INFO]][models.py:185] Building model using device_map: cuda:2 (DeviceRankInfo(world_size=4, rank=2, local_world_size=4, local_rank=2))...
+[2025-01-31 02:24:33,577][oumi][rank2][pid:10760][MainThread][INFO]][models.py:255] Using model class: <class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'> to instantiate model.
+[2025-01-31 02:24:39,627][oumi][rank2][pid:10760][MainThread][INFO]][base_map_dataset.py:68] Creating map dataset (type: UltrachatH4Dataset) dataset_name: 'HuggingFaceH4/ultrachat_200k', dataset_path: 'None'...
+[2025-01-31 02:25:29,815][oumi][rank2][pid:10760][MainThread][INFO]][base_map_dataset.py:472] Dataset Info:
+	Split: train_sft
+	Version: 0.0.0
+	Dataset size: 3047427114
+	Download size: 1624049723
+	Size: 4671476837 bytes
+	Rows: 207865
+	Columns: ['prompt', 'prompt_id', 'messages']
+[2025-01-31 02:25:33,393][oumi][rank2][pid:10760][MainThread][INFO]][base_map_dataset.py:411] Loaded DataFrame with shape: (207865, 3). Columns:
+prompt       object
+prompt_id    object
+messages     object
+dtype: object
+[2025-01-31 02:25:33,490][oumi][rank2][pid:10760][MainThread][INFO]][base_map_dataset.py:297] UltrachatH4Dataset: features=dict_keys(['input_ids', 'attention_mask'])
+[2025-01-31 02:39:30,854][oumi][rank2][pid:10760][MainThread][INFO]][base_map_dataset.py:361] Finished transforming dataset (UltrachatH4Dataset)! Speed: 248.24 examples/sec. Examples: 207865. Duration: 837.4 sec. Transform workers: 1.
+[2025-01-31 02:39:31,470][oumi][rank2][pid:10760][MainThread][INFO]][torch_profiler_utils.py:150] PROF: Torch Profiler disabled!
+[2025-01-31 02:39:31,471][oumi][rank2][pid:10760][MainThread][WARNING]][callbacks.py:54] MFU logging requires packed datasets. Skipping MFU callbacks.
+[2025-01-31 02:39:31,566][oumi][rank2][pid:10760][MainThread][INFO]][device_utils.py:283] GPU Metrics Before Training: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=19007.0, temperature=35, fan_speed=None, fan_speeds=None, power_usage_watts=78.83800000000001, power_limit_watts=400.0, gpu_utilization=0, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 02:39:31,568][oumi][rank2][pid:10760][MainThread][INFO]][train.py:312] Training init time: 901.293s
+[2025-01-31 02:39:31,568][oumi][rank2][pid:10760][MainThread][INFO]][train.py:313] Starting training... (TrainerType.TRL_SFT, transformers: 4.45.2)
+[2025-01-31 13:18:45,140][oumi][rank2][pid:10760][MainThread][INFO]][train.py:320] Training is Complete.
+[2025-01-31 13:18:45,163][oumi][rank2][pid:10760][MainThread][INFO]][device_utils.py:283] GPU Metrics After Training: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=69213.0, temperature=42, fan_speed=None, fan_speeds=None, power_usage_watts=78.479, power_limit_watts=400.0, gpu_utilization=2, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 13:18:45,163][oumi][rank2][pid:10760][MainThread][INFO]][torch_utils.py:117] Peak GPU memory usage: 47.38 GB
+[2025-01-31 13:18:45,163][oumi][rank2][pid:10760][MainThread][INFO]][train.py:327] Saving final state...
+[2025-01-31 13:18:45,431][oumi][rank2][pid:10760][MainThread][INFO]][train.py:332] Saving final model...
+[2025-01-31 13:19:21,040][oumi][rank2][pid:10760][MainThread][INFO]][train.py:339] 
+
+» We're always looking for feedback. What's one thing we can improve? https://oumi.ai/feedback

logs/rank_0003.log

@@ -0,0 +1,35 @@
+[2025-01-31 02:24:32,068][oumi][rank3][pid:10761][MainThread][INFO]][train.py:144] Resolved 'training.dataloader_num_workers=auto' to 'training.dataloader_num_workers=8'
+[2025-01-31 02:24:33,035][oumi][rank3][pid:10761][MainThread][WARNING]][models.py:412] Undefined pad token. Setting it to `<|finetune_right_pad_id|>`.
+[2025-01-31 02:24:33,036][oumi][rank3][pid:10761][MainThread][INFO]][models.py:428] Using the chat template 'llama3-instruct' specified in model config!
+[2025-01-31 02:24:33,036][oumi][rank3][pid:10761][MainThread][INFO]][models.py:180] Building model for distributed training (world_size: 4)...
+[2025-01-31 02:24:33,036][oumi][rank3][pid:10761][MainThread][INFO]][models.py:185] Building model using device_map: cuda:3 (DeviceRankInfo(world_size=4, rank=3, local_world_size=4, local_rank=3))...
+[2025-01-31 02:24:33,036][oumi][rank3][pid:10761][MainThread][INFO]][models.py:255] Using model class: <class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'> to instantiate model.
+[2025-01-31 02:24:39,641][oumi][rank3][pid:10761][MainThread][INFO]][base_map_dataset.py:68] Creating map dataset (type: UltrachatH4Dataset) dataset_name: 'HuggingFaceH4/ultrachat_200k', dataset_path: 'None'...
+[2025-01-31 02:25:29,800][oumi][rank3][pid:10761][MainThread][INFO]][base_map_dataset.py:472] Dataset Info:
+	Split: train_sft
+	Version: 0.0.0
+	Dataset size: 3047427114
+	Download size: 1624049723
+	Size: 4671476837 bytes
+	Rows: 207865
+	Columns: ['prompt', 'prompt_id', 'messages']
+[2025-01-31 02:25:33,301][oumi][rank3][pid:10761][MainThread][INFO]][base_map_dataset.py:411] Loaded DataFrame with shape: (207865, 3). Columns:
+prompt       object
+prompt_id    object
+messages     object
+dtype: object
+[2025-01-31 02:25:33,411][oumi][rank3][pid:10761][MainThread][INFO]][base_map_dataset.py:297] UltrachatH4Dataset: features=dict_keys(['input_ids', 'attention_mask'])
+[2025-01-31 02:39:30,856][oumi][rank3][pid:10761][MainThread][INFO]][base_map_dataset.py:361] Finished transforming dataset (UltrachatH4Dataset)! Speed: 248.21 examples/sec. Examples: 207865. Duration: 837.4 sec. Transform workers: 1.
+[2025-01-31 02:39:31,453][oumi][rank3][pid:10761][MainThread][INFO]][torch_profiler_utils.py:150] PROF: Torch Profiler disabled!
+[2025-01-31 02:39:31,454][oumi][rank3][pid:10761][MainThread][WARNING]][callbacks.py:54] MFU logging requires packed datasets. Skipping MFU callbacks.
+[2025-01-31 02:39:31,566][oumi][rank3][pid:10761][MainThread][INFO]][device_utils.py:283] GPU Metrics Before Training: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=19007.0, temperature=35, fan_speed=None, fan_speeds=None, power_usage_watts=78.83800000000001, power_limit_watts=400.0, gpu_utilization=0, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 02:39:31,568][oumi][rank3][pid:10761][MainThread][INFO]][train.py:312] Training init time: 901.293s
+[2025-01-31 02:39:31,568][oumi][rank3][pid:10761][MainThread][INFO]][train.py:313] Starting training... (TrainerType.TRL_SFT, transformers: 4.45.2)
+[2025-01-31 13:18:45,140][oumi][rank3][pid:10761][MainThread][INFO]][train.py:320] Training is Complete.
+[2025-01-31 13:18:45,163][oumi][rank3][pid:10761][MainThread][INFO]][device_utils.py:283] GPU Metrics After Training: GPU runtime info: NVidiaGpuRuntimeInfo(device_index=0, device_count=4, used_memory_mb=69213.0, temperature=42, fan_speed=None, fan_speeds=None, power_usage_watts=78.479, power_limit_watts=400.0, gpu_utilization=2, memory_utilization=0, performance_state=0, clock_speed_graphics=1155, clock_speed_sm=1155, clock_speed_memory=1593).
+[2025-01-31 13:18:45,163][oumi][rank3][pid:10761][MainThread][INFO]][torch_utils.py:117] Peak GPU memory usage: 47.51 GB
+[2025-01-31 13:18:45,163][oumi][rank3][pid:10761][MainThread][INFO]][train.py:327] Saving final state...
+[2025-01-31 13:18:45,431][oumi][rank3][pid:10761][MainThread][INFO]][train.py:332] Saving final model...
+[2025-01-31 13:19:21,035][oumi][rank3][pid:10761][MainThread][INFO]][train.py:339] 
+
+» We're always looking for feedback. What's one thing we can improve? https://oumi.ai/feedback

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e9ff0b46ca79610c1b0f07cc5f0c3ef0b828680f76f2d4bafd0f2d444b9c64
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298052ea98d37fcbf0ccfe103adcb0cf6e67d662a49cdaf3606c884be0bca191
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab065dfcc0dda387b3f2f25e03b11f24c0519e79842409044cfe4670df3c76a
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23406a7b8f1551afbbefc196dce51f414a9a263746197bd9ae517580972651c
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/Jan31_02-39-31_sky-e018-bf996-370b-head-9t91s4aj-compute/events.out.tfevents.1738291276.sky-e018-bf996-370b-head-9t91s4aj-compute.10758.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6935fa29f3e2c4bd7e269b14ee50fb1f1af96985f13c66fb0c25de16d89905
+size 23822

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

telemetry/devices_info.txt

@@ -0,0 +1,5 @@
+CPU cores: 48 CUDA devices: 4
+device(0)='NVIDIA A100-SXM4-80GB' Capability: (8, 0) Memory: [Total: 79.15GiB Free: 76.58GiB Allocated: 0.0GiB Cached: 0.0GiB]
+device(1)='NVIDIA A100-SXM4-80GB' Capability: (8, 0) Memory: [Total: 79.15GiB Free: 77.26GiB Allocated: 0.0GiB Cached: 0.0GiB]
+device(2)='NVIDIA A100-SXM4-80GB' Capability: (8, 0) Memory: [Total: 79.15GiB Free: 77.26GiB Allocated: 0.0GiB Cached: 0.0GiB]
+device(3)='NVIDIA A100-SXM4-80GB' Capability: (8, 0) Memory: [Total: 79.15GiB Free: 77.4GiB Allocated: 0.0GiB Cached: 0.0GiB]

telemetry/telemetry_callback_metrics_rank0000.json

@@ -0,0 +1,10 @@
+{
+  "train_runtime": 38249.836,
+  "train_samples_per_second": 5.434,
+  "train_steps_per_second": 0.17,
+  "train_tokens_per_second": 1606.468,
+  "total_flos": 1.1089328326722978e+19,
+  "train_loss": 1.0435700872478528,
+  "epoch": 0.9998652991321415,
+  "num_input_tokens_seen": 246267812
+}

telemetry/telemetry_callback_rank0000.json

@@ -0,0 +1,39 @@
+{
+  "hostname": "sky-e018-bf996-370b-head-9t91s4aj-compute",
+  "total_time": 38353.834880079,
+  "timers": {
+    "epochs": {
+      "count": 1.0,
+      "mean": 38248.866652175995,
+      "median": 38248.866652175995,
+      "std_dev": 0,
+      "min": 38248.866652175995,
+      "max": 38248.866652175995,
+      "total": 38248.866652175995,
+      "percentage": 99.72631621262592
+    },
+    "microsteps": {
+      "count": 51944.0,
+      "mean": 0.7252536668023732,
+      "median": 0.6581094984994706,
+      "std_dev": 0.3160163179471894,
+      "min": 0.2832598160002817,
+      "max": 3.096779071000128,
+      "total": 37672.576468382475,
+      "percentage": 98.22375412047684
+    },
+    "steps": {
+      "count": 6493.0,
+      "mean": 5.802115983516538,
+      "median": 5.775943727999902,
+      "std_dev": 0.45848518239014535,
+      "min": 4.497165704999134,
+      "max": 8.424397875999603,
+      "total": 37673.139080972884,
+      "percentage": 98.22522102096323
+    }
+  },
+  "cuda_timers": {},
+  "gpu_memory": [],
+  "gpu_temperature": {}
+}

telemetry/telemetry_callback_wandb_rank0000.json

@@ -0,0 +1,5 @@
+{
+  "id": "ygcwk1w6",
+  "name": "llama8b-ultrachat.sky-2025-01-30-21-19-10-053582_sky-e018-bf996_1",
+  "url": "https://wandb.ai/nyu-dice-lab/oumi-train/runs/ygcwk1w6"
+}

telemetry/training_config.yaml

@@ -0,0 +1,166 @@
+data:
+  train:
+    datasets:
+    - dataset_name: HuggingFaceH4/ultrachat_200k
+      dataset_path: null
+      subset: null
+      split: train_sft
+      dataset_kwargs: {}
+      sample_count: null
+      mixture_proportion: null
+      shuffle: false
+      seed: null
+      shuffle_buffer_size: 1000
+      trust_remote_code: true
+      transform_num_workers: null
+    collator_name: null
+    pack: false
+    stream: false
+    target_col: null
+    mixture_strategy: first_exhausted
+    seed: null
+    use_async_dataset: false
+    use_torchdata: null
+  test:
+    datasets: []
+    collator_name: null
+    pack: false
+    stream: false
+    target_col: null
+    mixture_strategy: first_exhausted
+    seed: null
+    use_async_dataset: false
+    use_torchdata: null
+  validation:
+    datasets: []
+    collator_name: null
+    pack: false
+    stream: false
+    target_col: null
+    mixture_strategy: first_exhausted
+    seed: null
+    use_async_dataset: false
+    use_torchdata: null
+model:
+  model_name: meta-llama/Meta-Llama-3.1-8B
+  adapter_model: null
+  tokenizer_name: null
+  tokenizer_pad_token: null
+  tokenizer_kwargs: {}
+  model_max_length: 8192
+  load_pretrained_weights: true
+  trust_remote_code: true
+  torch_dtype_str: bfloat16
+  compile: false
+  chat_template: llama3-instruct
+  attn_implementation: flash_attention_2
+  device_map: auto
+  model_kwargs: {}
+  enable_liger_kernel: true
+  shard_for_eval: false
+  freeze_layers: []
+training:
+  use_peft: false
+  trainer_type: TRL_SFT
+  enable_gradient_checkpointing: true
+  gradient_checkpointing_kwargs:
+    use_reentrant: false
+  output_dir: output/llama8b-ultrachat
+  per_device_train_batch_size: 1
+  per_device_eval_batch_size: 8
+  gradient_accumulation_steps: 8
+  max_steps: -1
+  num_train_epochs: 1
+  save_epoch: false
+  save_steps: 800
+  save_final_model: true
+  seed: 42
+  run_name: llama8b-ultrachat.sky-2025-01-30-21-19-10-053582_sky-e018-bf996_1
+  metrics_function: null
+  log_level: info
+  dep_log_level: warning
+  enable_wandb: true
+  enable_tensorboard: true
+  logging_strategy: steps
+  logging_dir: null
+  logging_steps: 100
+  logging_first_step: false
+  eval_strategy: 'no'
+  eval_steps: 500
+  learning_rate: 2.0e-05
+  lr_scheduler_type: linear
+  lr_scheduler_kwargs: {}
+  warmup_ratio: null
+  warmup_steps: null
+  optimizer: paged_adamw_8bit
+  weight_decay: 0.0
+  adam_beta1: 0.9
+  adam_beta2: 0.999
+  adam_epsilon: 1.0e-08
+  sgd_momentum: 0.0
+  mixed_precision_dtype: NONE
+  compile: false
+  include_performance_metrics: true
+  include_alternative_mfu_metrics: false
+  log_model_summary: false
+  resume_from_checkpoint: null
+  try_resume_from_last_checkpoint: false
+  dataloader_num_workers: 8
+  dataloader_prefetch_factor: 32
+  dataloader_main_process_only: null
+  ddp_find_unused_parameters: false
+  max_grad_norm: 1.0
+  trainer_kwargs:
+    max_seq_length: 8192
+  profiler:
+    save_dir: null
+    enable_cpu_profiling: false
+    enable_cuda_profiling: false
+    record_shapes: false
+    profile_memory: false
+    with_stack: false
+    with_flops: false
+    with_modules: false
+    row_limit: 50
+    schedule:
+      enable_schedule: false
+      wait: 0
+      warmup: 1
+      active: 3
+      repeat: 1
+      skip_first: 1
+  telemetry:
+    telemetry_dir: telemetry
+    collect_telemetry_for_all_ranks: false
+    track_gpu_temperature: false
+  empty_device_cache_steps: 50
+  nccl_default_timeout_minutes: null
+peft:
+  lora_r: 8
+  lora_alpha: 8
+  lora_dropout: 0.0
+  lora_target_modules: null
+  lora_modules_to_save: null
+  lora_bias: none
+  lora_init_weights: DEFAULT
+  lora_task_type: CAUSAL_LM
+  q_lora: false
+  q_lora_bits: 4
+  bnb_4bit_quant_type: fp4
+  use_bnb_nested_quant: false
+  bnb_4bit_quant_storage: uint8
+  bnb_4bit_compute_dtype: float32
+  peft_save_mode: ADAPTER_ONLY
+fsdp:
+  enable_fsdp: false
+  sharding_strategy: FULL_SHARD
+  cpu_offload: false
+  mixed_precision: null
+  backward_prefetch: BACKWARD_PRE
+  forward_prefetch: false
+  use_orig_params: null
+  state_dict_type: FULL_STATE_DICT
+  auto_wrap_policy: NO_WRAP
+  min_num_params: 100000
+  transformer_layer_cls: null
+  sync_module_states: true

telemetry/world_size.json

@@ -0,0 +1,4 @@
+{
+  "LOCAL_WORLD_SIZE": 4,
+  "WORLD_SIZE": 4
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb956fd3e742594d4410fdb86df5edf0c1b0f1f382117a2fbd877f2372ec158d
+size 17210019

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "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": "{% set role_prefix = '<|start_header_id|>' %}{% set role_suffix = '<|end_header_id|>\\n\\n' %}{% set turn_suffix = '<|eot_id|>' %}{% set image_token = '<|image|>' %}{{ bos_token }}{%- for message in messages -%}{{ role_prefix + message['role'] + role_suffix }}{%- if message['content'] is string -%}{{ message['content'] | trim }}{%- elif message['content'] is iterable -%}{%- for content in message['content'] -%}{%- if content['type'] == 'text' -%}{{  content['content'] | trim }}{%- elif content['type'].startswith('image') -%}{{  image_token }}{%- endif -%}{%- endfor -%}{%- endif -%}{{  turn_suffix  + '\\n' }}{%- endfor -%}{%- if add_generation_prompt -%}{{ role_prefix + 'assistant' + role_suffix }}{%- endif -%}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,556 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998652991321415,
+  "eval_steps": 500,
+  "global_step": 6495,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015394384898108415,
+      "grad_norm": 1.9140625,
+      "learning_rate": 1.9692070823710548e-05,
+      "loss": 1.1459,
+      "num_input_tokens_seen": 3815960,
+      "step": 100
+    },
+    {
+      "epoch": 0.03078876979621683,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.9384141647421097e-05,
+      "loss": 1.0878,
+      "num_input_tokens_seen": 7588127,
+      "step": 200
+    },
+    {
+      "epoch": 0.04618315469432525,
+      "grad_norm": 1.625,
+      "learning_rate": 1.907621247113164e-05,
+      "loss": 1.0942,
+      "num_input_tokens_seen": 11373466,
+      "step": 300
+    },
+    {
+      "epoch": 0.06157753959243366,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.876828329484219e-05,
+      "loss": 1.0788,
+      "num_input_tokens_seen": 15148940,
+      "step": 400
+    },
+    {
+      "epoch": 0.07697192449054208,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.8460354118552735e-05,
+      "loss": 1.0807,
+      "num_input_tokens_seen": 18941722,
+      "step": 500
+    },
+    {
+      "epoch": 0.0923663093886505,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.815242494226328e-05,
+      "loss": 1.0628,
+      "num_input_tokens_seen": 22691439,
+      "step": 600
+    },
+    {
+      "epoch": 0.1077606942867589,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.7844495765973827e-05,
+      "loss": 1.057,
+      "num_input_tokens_seen": 26519584,
+      "step": 700
+    },
+    {
+      "epoch": 0.12315507918486732,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.7536566589684373e-05,
+      "loss": 1.0591,
+      "num_input_tokens_seen": 30335003,
+      "step": 800
+    },
+    {
+      "epoch": 0.13854946408297575,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.722863741339492e-05,
+      "loss": 1.0597,
+      "num_input_tokens_seen": 34122220,
+      "step": 900
+    },
+    {
+      "epoch": 0.15394384898108415,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.6920708237105468e-05,
+      "loss": 1.0784,
+      "num_input_tokens_seen": 37937918,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16933823387919256,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.6612779060816014e-05,
+      "loss": 1.0598,
+      "num_input_tokens_seen": 41762422,
+      "step": 1100
+    },
+    {
+      "epoch": 0.184732618777301,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.630484988452656e-05,
+      "loss": 1.0658,
+      "num_input_tokens_seen": 45541351,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2001270036754094,
+      "grad_norm": 1.9453125,
+      "learning_rate": 1.5996920708237106e-05,
+      "loss": 1.0557,
+      "num_input_tokens_seen": 49317373,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2155213885735178,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.5688991531947652e-05,
+      "loss": 1.0597,
+      "num_input_tokens_seen": 53117895,
+      "step": 1400
+    },
+    {
+      "epoch": 0.23091577347162623,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.53810623556582e-05,
+      "loss": 1.0616,
+      "num_input_tokens_seen": 56839161,
+      "step": 1500
+    },
+    {
+      "epoch": 0.24631015836973463,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.5073133179368746e-05,
+      "loss": 1.053,
+      "num_input_tokens_seen": 60623928,
+      "step": 1600
+    },
+    {
+      "epoch": 0.26170454326784304,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.4765204003079292e-05,
+      "loss": 1.0483,
+      "num_input_tokens_seen": 64408460,
+      "step": 1700
+    },
+    {
+      "epoch": 0.2770989281659515,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.445727482678984e-05,
+      "loss": 1.049,
+      "num_input_tokens_seen": 68223027,
+      "step": 1800
+    },
+    {
+      "epoch": 0.2924933130640599,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.4149345650500385e-05,
+      "loss": 1.0482,
+      "num_input_tokens_seen": 71994158,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3078876979621683,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.3841416474210933e-05,
+      "loss": 1.0497,
+      "num_input_tokens_seen": 75865760,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3232820828602767,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.3533487297921479e-05,
+      "loss": 1.0409,
+      "num_input_tokens_seen": 79623921,
+      "step": 2100
+    },
+    {
+      "epoch": 0.3386764677583851,
+      "grad_norm": 1.7890625,
+      "learning_rate": 1.3225558121632025e-05,
+      "loss": 1.0501,
+      "num_input_tokens_seen": 83411874,
+      "step": 2200
+    },
+    {
+      "epoch": 0.3540708526564935,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.2917628945342572e-05,
+      "loss": 1.0542,
+      "num_input_tokens_seen": 87182489,
+      "step": 2300
+    },
+    {
+      "epoch": 0.369465237554602,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.2609699769053118e-05,
+      "loss": 1.0482,
+      "num_input_tokens_seen": 90989837,
+      "step": 2400
+    },
+    {
+      "epoch": 0.3848596224527104,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.2301770592763664e-05,
+      "loss": 1.0404,
+      "num_input_tokens_seen": 94853551,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4002540073508188,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.1993841416474212e-05,
+      "loss": 1.0401,
+      "num_input_tokens_seen": 98649900,
+      "step": 2600
+    },
+    {
+      "epoch": 0.4156483922489272,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.1685912240184758e-05,
+      "loss": 1.0453,
+      "num_input_tokens_seen": 102455430,
+      "step": 2700
+    },
+    {
+      "epoch": 0.4310427771470356,
+      "grad_norm": 1.75,
+      "learning_rate": 1.1377983063895306e-05,
+      "loss": 1.0335,
+      "num_input_tokens_seen": 106279858,
+      "step": 2800
+    },
+    {
+      "epoch": 0.44643716204514405,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.1070053887605852e-05,
+      "loss": 1.0486,
+      "num_input_tokens_seen": 110042375,
+      "step": 2900
+    },
+    {
+      "epoch": 0.46183154694325246,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.0762124711316398e-05,
+      "loss": 1.0347,
+      "num_input_tokens_seen": 113836688,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47722593184136086,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.0454195535026945e-05,
+      "loss": 1.041,
+      "num_input_tokens_seen": 117581458,
+      "step": 3100
+    },
+    {
+      "epoch": 0.49262031673946927,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.0146266358737491e-05,
+      "loss": 1.0357,
+      "num_input_tokens_seen": 121341275,
+      "step": 3200
+    },
+    {
+      "epoch": 0.5080147016375777,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.838337182448037e-06,
+      "loss": 1.0374,
+      "num_input_tokens_seen": 125088162,
+      "step": 3300
+    },
+    {
+      "epoch": 0.5234090865356861,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.530408006158585e-06,
+      "loss": 1.0255,
+      "num_input_tokens_seen": 128901749,
+      "step": 3400
+    },
+    {
+      "epoch": 0.5388034714337945,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.22247882986913e-06,
+      "loss": 1.0282,
+      "num_input_tokens_seen": 132736866,
+      "step": 3500
+    },
+    {
+      "epoch": 0.554197856331903,
+      "grad_norm": 1.6953125,
+      "learning_rate": 8.914549653579677e-06,
+      "loss": 1.0398,
+      "num_input_tokens_seen": 136595429,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5695922412300114,
+      "grad_norm": 1.7578125,
+      "learning_rate": 8.606620477290224e-06,
+      "loss": 1.025,
+      "num_input_tokens_seen": 140426462,
+      "step": 3700
+    },
+    {
+      "epoch": 0.5849866261281198,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.29869130100077e-06,
+      "loss": 1.0291,
+      "num_input_tokens_seen": 144234914,
+      "step": 3800
+    },
+    {
+      "epoch": 0.6003810110262282,
+      "grad_norm": 2.453125,
+      "learning_rate": 7.990762124711316e-06,
+      "loss": 1.0233,
+      "num_input_tokens_seen": 148032058,
+      "step": 3900
+    },
+    {
+      "epoch": 0.6157753959243366,
+      "grad_norm": 1.734375,
+      "learning_rate": 7.682832948421864e-06,
+      "loss": 1.0347,
+      "num_input_tokens_seen": 151814536,
+      "step": 4000
+    },
+    {
+      "epoch": 0.631169780822445,
+      "grad_norm": 1.7578125,
+      "learning_rate": 7.37490377213241e-06,
+      "loss": 1.0457,
+      "num_input_tokens_seen": 155598931,
+      "step": 4100
+    },
+    {
+      "epoch": 0.6465641657205534,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.066974595842957e-06,
+      "loss": 1.0473,
+      "num_input_tokens_seen": 159326528,
+      "step": 4200
+    },
+    {
+      "epoch": 0.6619585506186618,
+      "grad_norm": 1.7109375,
+      "learning_rate": 6.7590454195535035e-06,
+      "loss": 1.0482,
+      "num_input_tokens_seen": 163084806,
+      "step": 4300
+    },
+    {
+      "epoch": 0.6773529355167702,
+      "grad_norm": 1.734375,
+      "learning_rate": 6.4511162432640495e-06,
+      "loss": 1.0267,
+      "num_input_tokens_seen": 166891971,
+      "step": 4400
+    },
+    {
+      "epoch": 0.6927473204148786,
+      "grad_norm": 1.703125,
+      "learning_rate": 6.143187066974596e-06,
+      "loss": 1.0165,
+      "num_input_tokens_seen": 170700927,
+      "step": 4500
+    },
+    {
+      "epoch": 0.708141705312987,
+      "grad_norm": 1.7421875,
+      "learning_rate": 5.835257890685143e-06,
+      "loss": 1.0386,
+      "num_input_tokens_seen": 174509215,
+      "step": 4600
+    },
+    {
+      "epoch": 0.7235360902110956,
+      "grad_norm": 1.859375,
+      "learning_rate": 5.52732871439569e-06,
+      "loss": 1.0286,
+      "num_input_tokens_seen": 178355672,
+      "step": 4700
+    },
+    {
+      "epoch": 0.738930475109204,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.219399538106236e-06,
+      "loss": 1.0199,
+      "num_input_tokens_seen": 182172598,
+      "step": 4800
+    },
+    {
+      "epoch": 0.7543248600073124,
+      "grad_norm": 1.7734375,
+      "learning_rate": 4.911470361816783e-06,
+      "loss": 1.023,
+      "num_input_tokens_seen": 185945174,
+      "step": 4900
+    },
+    {
+      "epoch": 0.7697192449054208,
+      "grad_norm": 1.4765625,
+      "learning_rate": 4.6035411855273295e-06,
+      "loss": 1.0317,
+      "num_input_tokens_seen": 189723364,
+      "step": 5000
+    },
+    {
+      "epoch": 0.7851136298035292,
+      "grad_norm": 1.53125,
+      "learning_rate": 4.2956120092378755e-06,
+      "loss": 1.0262,
+      "num_input_tokens_seen": 193515488,
+      "step": 5100
+    },
+    {
+      "epoch": 0.8005080147016376,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.987682832948422e-06,
+      "loss": 1.0276,
+      "num_input_tokens_seen": 197294619,
+      "step": 5200
+    },
+    {
+      "epoch": 0.815902399599746,
+      "grad_norm": 1.6640625,
+      "learning_rate": 3.6797536566589687e-06,
+      "loss": 1.0141,
+      "num_input_tokens_seen": 201079998,
+      "step": 5300
+    },
+    {
+      "epoch": 0.8312967844978544,
+      "grad_norm": 1.875,
+      "learning_rate": 3.3718244803695155e-06,
+      "loss": 1.0406,
+      "num_input_tokens_seen": 204892665,
+      "step": 5400
+    },
+    {
+      "epoch": 0.8466911693959628,
+      "grad_norm": 1.75,
+      "learning_rate": 3.063895304080062e-06,
+      "loss": 1.0144,
+      "num_input_tokens_seen": 208692509,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8620855542940712,
+      "grad_norm": 1.625,
+      "learning_rate": 2.7559661277906087e-06,
+      "loss": 1.0328,
+      "num_input_tokens_seen": 212482079,
+      "step": 5600
+    },
+    {
+      "epoch": 0.8774799391921797,
+      "grad_norm": 1.4453125,
+      "learning_rate": 2.4480369515011547e-06,
+      "loss": 1.0158,
+      "num_input_tokens_seen": 216265581,
+      "step": 5700
+    },
+    {
+      "epoch": 0.8928743240902881,
+      "grad_norm": 1.421875,
+      "learning_rate": 2.1401077752117015e-06,
+      "loss": 1.0376,
+      "num_input_tokens_seen": 220058453,
+      "step": 5800
+    },
+    {
+      "epoch": 0.9082687089883965,
+      "grad_norm": 1.875,
+      "learning_rate": 1.8321785989222479e-06,
+      "loss": 1.0116,
+      "num_input_tokens_seen": 223849666,
+      "step": 5900
+    },
+    {
+      "epoch": 0.9236630938865049,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.5242494226327945e-06,
+      "loss": 1.0319,
+      "num_input_tokens_seen": 227586204,
+      "step": 6000
+    },
+    {
+      "epoch": 0.9390574787846133,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.216320246343341e-06,
+      "loss": 1.0248,
+      "num_input_tokens_seen": 231383644,
+      "step": 6100
+    },
+    {
+      "epoch": 0.9544518636827217,
+      "grad_norm": 1.71875,
+      "learning_rate": 9.083910700538877e-07,
+      "loss": 1.0252,
+      "num_input_tokens_seen": 235171998,
+      "step": 6200
+    },
+    {
+      "epoch": 0.9698462485808301,
+      "grad_norm": 1.59375,
+      "learning_rate": 6.004618937644343e-07,
+      "loss": 1.033,
+      "num_input_tokens_seen": 238903492,
+      "step": 6300
+    },
+    {
+      "epoch": 0.9852406334789385,
+      "grad_norm": 1.671875,
+      "learning_rate": 2.9253271747498076e-07,
+      "loss": 1.0206,
+      "num_input_tokens_seen": 242682149,
+      "step": 6400
+    },
+    {
+      "epoch": 0.9998652991321415,
+      "num_input_tokens_seen": 246267812,
+      "step": 6495,
+      "total_flos": 1.1089328326722978e+19,
+      "train_loss": 1.0435700872478528,
+      "train_runtime": 38249.836,
+      "train_samples_per_second": 5.434,
+      "train_steps_per_second": 0.17,
+      "train_tokens_per_second": 1606.468
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 6495,
+  "num_input_tokens_seen": 246267812,
+  "num_train_epochs": 1,
+  "save_steps": 800,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1089328326722978e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eca322335a543b9701d348d90d97880464343d1798ed183ddce17b887fd34ae
+size 5624