Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,36 @@ 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
+model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__8_1.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__14_6.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__15_8.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__15_3.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__9_9.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__14_14.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__11_5.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__8_6.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__13_1.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__9_14.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__13_14.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__9_3.distcp filter=lfs diff=lfs merge=lfs -text
+model_and_optim/__9_1.distcp filter=lfs diff=lfs merge=lfs -text

config.yaml

@@ -0,0 +1,629 @@
+run_name: multitask_train
+model:
+  model_name: molmo
+  llm:
+    d_model: 2560
+    n_heads: 32
+    n_kv_heads: 8
+    head_dim: 128
+    qkv_bias: false
+    clip_qkv: null
+    n_layers: 36
+    mlp_ratio: 4
+    mlp_hidden_size: 19456
+    activation_type: swiglu
+    block_type: sequential
+    rope: true
+    rope_full_precision: true
+    rope_theta: 1000000.0
+    rope_type: default
+    rope_factor: null
+    rope_high_freq_factor: null
+    rope_low_freq_factor: null
+    rope_original_max_position_embeddings: null
+    attention_type: sdpa
+    float32_attention: true
+    attention_dropout: 0.0
+    attention_layer_norm: true
+    attention_layer_norm_type: qwen3
+    residual_dropout: 0.1
+    response_residual_dropout: 0.0
+    layer_norm_type: rms
+    layer_norm_with_affine: true
+    layer_norm_eps: 1.0e-06
+    attention_layer_norm_with_affine: true
+    max_sequence_length: 4096
+    max_position_embeddings: null
+    include_bias: false
+    bias_for_layer_norm: null
+    norm_after: false
+    moe_num_experts: 8
+    moe_top_k: 2
+    moe_mlp_impl: sparse
+    moe_log_expert_assignment: false
+    moe_shared_expert: false
+    moe_lbl_in_fp32: false
+    moe_interleave: false
+    moe_loss_weight: 0.1
+    moe_zloss_weight: null
+    moe_dropless: true
+    moe_capacity_factor: 1.25
+    embedding_dropout: 0.0
+    scale_logits: false
+    vocab_size: 151936
+    additional_vocab_size: 128
+    weight_tying: true
+    embedding_size: 151936
+    use_position_ids: true
+    tokenizer:
+      identifier: Qwen/Qwen3-4B
+      tokenizer_dir: null
+    init_path: /weka/oe-training-default/mm-olmo/pretrained_llms/qwen3-4b.pt
+    init_incremental: null
+    new_embedding_init_range: 0.02
+    initializer_range: 0.02
+    normalize_input_embeds: false
+    activation_checkpoint: whole_layer
+    compile: blocks
+    fix_pad_tokenizer: false
+    init_std: 0.02
+    init_fn: normal
+    init_cutoff_factor: null
+  vision_backbone:
+    vit:
+      image_model_type: siglip
+      image_default_input_size:
+      - 378
+      - 378
+      image_patch_size: 14
+      image_pos_patch_size: 14
+      image_emb_dim: 1152
+      image_num_heads: 16
+      image_num_key_value_heads: 16
+      image_num_layers: 27
+      image_head_dim: 72
+      image_mlp_dim: 4304
+      image_mlp_activations: gelu_pytorch_tanh
+      image_dropout_rate: 0.0
+      image_num_pos: 729
+      image_norm_eps: 1.0e-06
+      attention_dropout: 0.0
+      residual_dropout: 0.0
+      initializer_range: 0.02
+      float32_attention: true
+      attention_type: sdpa
+      activation_checkpointing: true
+      init_path: /weka/oe-training-default/mm-olmo/pretrained_image_encoders/siglip2-so400m-14-384.pt
+      resize_mode: siglip
+      pad_value: 0.0
+      normalize: siglip
+    image_pooling_2d: attention_meanq
+    pooling_attention_mask: false
+    image_projector: mlp
+    image_padding_embed: null
+    vit_layers:
+    - -3
+    - -9
+    skip_unused_layers: true
+    image_feature_dropout: 0.0
+    connector_activation_checkpointing: true
+    compile_vit: blocks
+    compile_connector: dynamic
+    normalize_on_gpu: false
+  data_formatter:
+    prompt_templates: uber_model
+    message_format: role
+    system_prompt: demo_or_style
+    always_start_with_space: false
+    default_inference_len: 65
+    select_answer: best
+    debug: false
+    image_last: false
+    format_message_list: null
+    p_one_message: 0.0
+    eval_system_prompt_mapping: null
+    timestamp_mode: 50-percent-seconds
+    p_choice_content_in_mc: 1.0
+  mm_preprocessor:
+    crop_mode: overlap-and-resize-c2
+    use_col_tokens: true
+    max_crops: 8
+    pooling_w: 2
+    pooling_h: 2
+    overlap_margins:
+    - 4
+    - 4
+    max_images: null
+    max_multi_image_crops: 4
+    max_answer_len: null
+    last_message_loss_only: false
+    loss_token_weighting: root_subsegments
+    max_text_tokens: null
+    image_padding_mask: false
+    legacy_image_mask: false
+  bi_directional_attn: null
+seed: 6198
+epoch: null
+dry_run: false
+ft_llm: true
+ft_vit: true
+ft_connector: true
+ft_embedding: lm_head
+optimizer:
+  name: adamw
+  learning_rate: 0.0001
+  weight_decay: 0.01
+  betas:
+  - 0.9
+  - 0.95
+  eps: 1.0e-05
+  connector_learning_rate: 5.0e-06
+  vit_learning_rate: 5.0e-06
+  llm_learning_rate: 1.0e-05
+  frame_selector_learning_rate: 0.0001
+  temporal_token_scorer_learning_rate: 0.0001
+  connector_weight_decay: 0.0
+  vit_weight_decay: 0.0
+  llm_weight_decay: 0.0
+  frame_selector_weight_decay: 0.01
+  temporal_token_scorer_weight_decay: 0.01
+  connector_betas:
+  - 0.9
+  - 0.95
+  vit_betas:
+  - 0.9
+  - 0.95
+  llm_betas:
+  - 0.9
+  - 0.95
+  frame_selector_betas:
+  - 0.9
+  - 0.95
+  temporal_token_scorer_betas:
+  - 0.9
+  - 0.95
+  connector_eps: 1.0e-06
+  vit_eps: 1.0e-06
+  llm_eps: 1.0e-06
+  frame_selector_eps: 1.0e-06
+  temporal_token_scorer_eps: 1.0e-06
+  metrics_log_interval: -1
+scheduler:
+  name: multimodal
+  units: steps
+  t_warmup: 100
+  t_max: null
+  alpha_f: 0.1
+  connector_t_warmup: 200
+  vit_t_warmup: 200
+  llm_t_warmup: 200
+  frame_selector_t_warmup: 200
+  temporal_token_scorer_t_warmup: 200
+  grad_clip_warmup_steps: null
+  grad_clip_warmup_factor: null
+  warmup_min_lr: 0.0
+data:
+  dataset: null
+  mixture: null
+  root_size_mixture:
+  - rate: 0.15
+    mixture:
+      pixmo_ask_model_anything: null
+      pixmo_cap: 50000.0
+      pixmo_cap_qa_as_user_qa: null
+      pixmo_pointing_explanations: null
+  - rate: 0.5
+    mixture:
+      coco_2014_vqa_multi: null
+      text_vqa: null
+      okvqa: null
+      chart_qa_weighted: null
+      doc_qa: null
+      info_qa: null
+      ai2_diagram_v2_mix_transparent: null
+      a_okvqa_mc: null
+      a_okvqa_da: null
+      android_control: null
+      science_qa_img: null
+      tabwmp_da: null
+      st_qa: null
+      tally_qa: null
+      pixmo_clocks: 250000.0
+      dv_qa: 10000.0
+      figure_qa: 10000.0
+      plot_qa: 20000.0
+      cosyn_chart_exp: null
+      cosyn_chemical_exp: null
+      cosyn_diagram_exp: null
+      cosyn_document: null
+      cosyn_math_exp: null
+      cosyn_music_exp: null
+      cosyn_table_exp: null
+  - rate: 0.35
+    mixture:
+      pixmo_points_train: null
+      pixmo_count_train: null
+      pixmo_points_high_freq_train: null
+      cosyn_point: null
+  kwargs_mixture: null
+  split: train
+  seed: 50189
+  pad: to_max
+  sequence_length: 2304
+  max_text_seq_len: null
+  shuffle: true
+  start_index: 0
+  packing: null
+  num_workers: 2
+  drop_last: true
+  pin_memory: true
+  prefetch_factor: null
+  persistent_workers: false
+  timeout: 0
+restore_dataloader: true
+fast_forward_batches: null
+evaluators: []
+eval_interval: 2000
+inf_evaluators:
+- label: chart_qa_exp
+  data:
+    dataset: chart_qa_exp
+    mixture: null
+    root_size_mixture: null
+    kwargs_mixture: null
+    split: validation
+    seed: 691203
+    pad: to_max
+    sequence_length: 1792
+    max_text_seq_len: null
+    shuffle: true
+    start_index: 0
+    packing: null
+    num_workers: 2
+    drop_last: true
+    pin_memory: true
+    prefetch_factor: null
+    persistent_workers: true
+    timeout: 0
+  evaluator:
+    n_to_log: 0
+    num_wandb_examples: 32
+    save_predictions: null
+    save_tokens: false
+    vqa_eval: relaxed_correctness,scifi_relaxed_correctness,em
+    pointing_eval: false
+    count_eval: false
+    point_count_eval: false
+    android_eval: false
+    clock_eval: false
+    clock_bench_eval: false
+    math_vista_eval: false
+    temp_compass_eval: ''
+    temp_compass_disable_api: false
+    video_mme_eval: ''
+    mme_videoocr_mc_eval: false
+    mlvu_gen_eval: false
+    long_video_bench_eval: false
+    plm_fgqa_eval: false
+    long_video_bench_caption_eval: false
+    vinoground_eval: false
+    vixmo_caption_eval: false
+    dream1k_caption_eval: false
+    refexp_eval: false
+    coco_caption_eval: false
+    qv_highlights_eval: false
+    tomato: false
+    temporal_bench: false
+  max_new_tokens: 256
+  device_batch_size: 4
+  subset_num_batches: null
+  max_examples: 2048
+  console_log_interval: 20
+  include_image: false
+- label: info_qa
+  data:
+    dataset: info_qa
+    mixture: null
+    root_size_mixture: null
+    kwargs_mixture: null
+    split: validation
+    seed: 691203
+    pad: to_max
+    sequence_length: 1792
+    max_text_seq_len: null
+    shuffle: true
+    start_index: 0
+    packing: null
+    num_workers: 2
+    drop_last: true
+    pin_memory: true
+    prefetch_factor: null
+    persistent_workers: true
+    timeout: 0
+  evaluator:
+    n_to_log: 0
+    num_wandb_examples: 32
+    save_predictions: null
+    save_tokens: false
+    vqa_eval: ansl,em
+    pointing_eval: false
+    count_eval: false
+    point_count_eval: false
+    android_eval: false
+    clock_eval: false
+    clock_bench_eval: false
+    math_vista_eval: false
+    temp_compass_eval: ''
+    temp_compass_disable_api: false
+    video_mme_eval: ''
+    mme_videoocr_mc_eval: false
+    mlvu_gen_eval: false
+    long_video_bench_eval: false
+    plm_fgqa_eval: false
+    long_video_bench_caption_eval: false
+    vinoground_eval: false
+    vixmo_caption_eval: false
+    dream1k_caption_eval: false
+    refexp_eval: false
+    coco_caption_eval: false
+    qv_highlights_eval: false
+    tomato: false
+    temporal_bench: false
+  max_new_tokens: 12
+  device_batch_size: 4
+  subset_num_batches: null
+  max_examples: 2048
+  console_log_interval: 20
+  include_image: false
+- label: doc_qa
+  data:
+    dataset: doc_qa
+    mixture: null
+    root_size_mixture: null
+    kwargs_mixture: null
+    split: validation
+    seed: 691203
+    pad: to_max
+    sequence_length: 1792
+    max_text_seq_len: null
+    shuffle: true
+    start_index: 0
+    packing: null
+    num_workers: 2
+    drop_last: true
+    pin_memory: true
+    prefetch_factor: null
+    persistent_workers: true
+    timeout: 0
+  evaluator:
+    n_to_log: 0
+    num_wandb_examples: 32
+    save_predictions: null
+    save_tokens: false
+    vqa_eval: ansl,em
+    pointing_eval: false
+    count_eval: false
+    point_count_eval: false
+    android_eval: false
+    clock_eval: false
+    clock_bench_eval: false
+    math_vista_eval: false
+    temp_compass_eval: ''
+    temp_compass_disable_api: false
+    video_mme_eval: ''
+    mme_videoocr_mc_eval: false
+    mlvu_gen_eval: false
+    long_video_bench_eval: false
+    plm_fgqa_eval: false
+    long_video_bench_caption_eval: false
+    vinoground_eval: false
+    vixmo_caption_eval: false
+    dream1k_caption_eval: false
+    refexp_eval: false
+    coco_caption_eval: false
+    qv_highlights_eval: false
+    tomato: false
+    temporal_bench: false
+  max_new_tokens: 12
+  device_batch_size: 4
+  subset_num_batches: null
+  max_examples: 2048
+  console_log_interval: 20
+  include_image: false
+- label: ai2_diagram
+  data:
+    dataset: ai2_diagram_v2_mix_transparent
+    mixture: null
+    root_size_mixture: null
+    kwargs_mixture: null
+    split: validation
+    seed: 691203
+    pad: to_max
+    sequence_length: 1792
+    max_text_seq_len: null
+    shuffle: true
+    start_index: 0
+    packing: null
+    num_workers: 2
+    drop_last: true
+    pin_memory: true
+    prefetch_factor: null
+    persistent_workers: true
+    timeout: 0
+  evaluator:
+    n_to_log: 0
+    num_wandb_examples: 32
+    save_predictions: null
+    save_tokens: false
+    vqa_eval: mc_ai2d_opaque,mc_ai2d_transparent
+    pointing_eval: false
+    count_eval: false
+    point_count_eval: false
+    android_eval: false
+    clock_eval: false
+    clock_bench_eval: false
+    math_vista_eval: false
+    temp_compass_eval: ''
+    temp_compass_disable_api: false
+    video_mme_eval: ''
+    mme_videoocr_mc_eval: false
+    mlvu_gen_eval: false
+    long_video_bench_eval: false
+    plm_fgqa_eval: false
+    long_video_bench_caption_eval: false
+    vinoground_eval: false
+    vixmo_caption_eval: false
+    dream1k_caption_eval: false
+    refexp_eval: false
+    coco_caption_eval: false
+    qv_highlights_eval: false
+    tomato: false
+    temporal_bench: false
+  max_new_tokens: 32
+  device_batch_size: 4
+  subset_num_batches: null
+  max_examples: 2048
+  console_log_interval: 20
+  include_image: false
+- label: coco_2014_vqa
+  data:
+    dataset: coco_2014_vqa
+    mixture: null
+    root_size_mixture: null
+    kwargs_mixture: null
+    split: validation
+    seed: 691203
+    pad: to_max
+    sequence_length: 1792
+    max_text_seq_len: null
+    shuffle: true
+    start_index: 0
+    packing: null
+    num_workers: 2
+    drop_last: true
+    pin_memory: true
+    prefetch_factor: null
+    persistent_workers: true
+    timeout: 0
+  evaluator:
+    n_to_log: 0
+    num_wandb_examples: 32
+    save_predictions: null
+    save_tokens: false
+    vqa_eval: vqa_score
+    pointing_eval: false
+    count_eval: false
+    point_count_eval: false
+    android_eval: false
+    clock_eval: false
+    clock_bench_eval: false
+    math_vista_eval: false
+    temp_compass_eval: ''
+    temp_compass_disable_api: false
+    video_mme_eval: ''
+    mme_videoocr_mc_eval: false
+    mlvu_gen_eval: false
+    long_video_bench_eval: false
+    plm_fgqa_eval: false
+    long_video_bench_caption_eval: false
+    vinoground_eval: false
+    vixmo_caption_eval: false
+    dream1k_caption_eval: false
+    refexp_eval: false
+    coco_caption_eval: false
+    qv_highlights_eval: false
+    tomato: false
+    temporal_bench: false
+  max_new_tokens: 12
+  device_batch_size: 4
+  subset_num_batches: null
+  max_examples: 2048
+  console_log_interval: 20
+  include_image: false
+inf_eval_interval: 2000
+eval_on_last_step: true
+eval_on_load: false
+save_folder: /weka/oe-training-default/sanghol/molmo/models/uber-v1/uber3.4-synthetic-siglip2-qwen3_4b
+checkpointer_config:
+  save_thread_count: null
+  load_thread_count: null
+  pre_download: false
+  work_dir: null
+  throttle_uploads: false
+canceled_check_interval: 50
+save_interval: 1000
+save_at: null
+save_final_optim: true
+save_num_checkpoints_to_keep: 1
+save_final_unsharded_checkpoint: false
+save_interval_ephemeral: null
+save_overwrite: true
+load_path: null
+reset_optimizer_state: false
+reset_trainer_state: false
+initial_model_checkpoint: /weka/oe-training-default/chrisk/molmo/models/dense-cap-v1/captioner-siglip2-qwen3_4b/step22347
+allow_resume: true
+max_duration: 30000
+global_train_batch_size: 256
+device_train_microbatch_size: 4
+max_grad_norm: 1.0
+multi_component_grad_norm: true
+batch_divisor: global_batch
+max_grad_norm_ratio: null
+precision: amp_bf16
+wandb:
+  project: molmo2-dev
+  entity: prior-ai2
+  group: uber-v1
+  name: uber3.4-synthetic-siglip2-qwen3_4b
+  tags:
+  - watching
+  log_artifacts: false
+  rank_zero_only: true
+  log_interval: 20
+  allow_resume: false
+beaker_log_interval: 50
+speed_monitor:
+  window_size: 20
+  gpu_flops_available: null
+console_log_interval: 20
+gen1_gc_interval: 1
+compile:
+  mode: default
+  fullgraph: false
+  dynamic: false
+  backend: inductor
+activation_checkpointing: true
+fsdp:
+  fsdp2: true
+  precision: float
+  use_orig_params: true
+  wrapping_strategy: by_block_and_size
+  sharding_strategy: FULL_SHARD
+  hybrid_sharding_num_model_replicas: null
+softmax_auxiliary_loss: true
+softmax_auxiliary_loss_scale: 0.0001
+saliency_score_loss_wt: null
+frame_score_loss_wt: null
+frame_score_loss_type: mse
+frame_score_loss_target: 0.7
+time_limit: null
+extra_steps_after_cancel: 10
+python_profiling: false
+torch_profiling: false
+stop_at: 30000
+stop_after: null
+fused_loss: false
+compile_loss: true
+runtime_data:
+  args: /gantry-runtime/launch_scripts/train_multitask_model.py 3.4-synthetic /weka/oe-training-default/chrisk/molmo/models/dense-cap-v1/captioner-siglip2-qwen3_4b
+    --save_overwrite --save_interval=1000 --wandb.group=uber-v1 --wandb.name=uber3.4-synthetic-siglip2-qwen3_4b
+    --save_folder=/weka/oe-training-default/sanghol/molmo/models/uber-v1/uber3.4-synthetic-siglip2-qwen3_4b
+  hostname: jupiter-cs-aus-112.reviz.ai2.in
+  date: 09/17/2025, 10:56
+  world_size: 16
+  resuming_from: /weka/oe-training-default/sanghol/molmo/models/uber-v1/uber3.4-synthetic-siglip2-qwen3_4b/step27000
+  beaker_experiment_id: 01K567APCW88M30XRRXSACWXPR
+  beaker_experiment_url: https://beaker.org/ex/01K567APCW88M30XRRXSACWXPR
+  wandb_id: 5307t37m
+  wandb_url: https://wandb.ai/prior-ai2/molmo2-dev/runs/5307t37m

model_and_optim/__11_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036d3530bc0f84e4b39bb554e3f5366508408a07682acc89ce4c6b6c25ff25d8
+size 197127554

model_and_optim/__11_5.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d89b473d945cd8aa4afda5ac21e4c174ce99fb6dc2d28b5ed59d26f354fa2e
+size 197309771

model_and_optim/__12_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3867052c128477976fa5fce2163827afa499d476da8e75f5cad7ab330de1733d
+size 197127554

model_and_optim/__13_1.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6cfa136d98a316a592271f724b5e92cc85e791164f1972f0b65e89c15604fb
+size 197124856

model_and_optim/__13_14.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544981e85717915dccd2cd32953a82ba670de251c7e51ba1c905d36bd8f4d618
+size 197319955

model_and_optim/__14_14.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e0b83932a8388f8f75c991e177747007d8d22ee3f4721cc3bb1855befe8356
+size 197319955

model_and_optim/__14_6.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e3fdfb3854204248eeaaf824c438c02cd2940942e7196329598dbe982c7527
+size 197308194

model_and_optim/__15_3.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e1f8771208100081d129c3312f300125293afeb5555b9ea2530019f6b8ce00
+size 197124856

model_and_optim/__15_8.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d9a3f125531fabe7c86738b0109c19e2359935a5a22b14ac81268a0352ff4c
+size 197195331

model_and_optim/__1_12.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ce2d6636e08b88487346486793577ea5759c1fa02e5a2dc0238af77d447a7b
+size 197145891

model_and_optim/__1_14.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10db0f47254174128fabd4f06b9f325d0b76b95da216c16fbd9044f55419bd1f
+size 197319955

model_and_optim/__2_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1822b1376bd567b8a5eeebf12b54f4961ad33c20a5f61825a0c931cb0c44626
+size 197127554

model_and_optim/__2_2.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5c9561b5b294105cc426c204ba94aa969af192ea31541317dc0f522978fd03
+size 197124856

model_and_optim/__2_8.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511fe5311412e0c60695113c12fdb49de202320f988d281bd5b11abcb0eacb92
+size 197195331

model_and_optim/__3_13.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e8eea91aa896c0c0929dd40bd6af91d37364ffdc39d0b1153355dd012626dba
+size 197319955

model_and_optim/__3_14.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd757baf9d4dc3823fb5684477d6cc9c95d845086fd366e3d2b48a6439ef7f7
+size 197319955

model_and_optim/__3_6.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18bd08d0b52978d27846f8ba3c73ca54faa6ba35ac85b0105c3af4f47cde0dfa
+size 197308194

model_and_optim/__4_2.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa030e27ea0e133e2a904a68107813863ed72b8534f9dda9b30a2387f4fa8b4d
+size 197124856

model_and_optim/__4_9.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5039f31d76b1530e3db4ae1d283e297e592d75d869244647e07f05acb584fd4a
+size 197182971

model_and_optim/__5_1.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0714aaff801c1f87f68c2e865a8c92806864c716f59e3c2e387c66debb9bb020
+size 197124856

model_and_optim/__5_2.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0942f55880e603dfcfd2dde9eb9246bd19b03d977cb5799a530cd5a3f3880eaa
+size 197124856

model_and_optim/__5_3.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235fa65eda6e32eee2534977603d237baf9726bd3555e3d228b3882c777e4a00
+size 197124856

model_and_optim/__6_7.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f2bfca1f88be1bfdbe97c9cc96cc8baed131fc024b578214f857a2da140fc5
+size 197182971

model_and_optim/__6_8.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f17b8747158fada7b747868de492d9698885baa2beedbefe2b0d21990013c1d
+size 197195331

model_and_optim/__7_1.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4eb9bf8637ea2bb7c39dc4720e39dbd3ef5109742c8c4a59f8e2c99271a861
+size 197124856

model_and_optim/__7_13.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a1d8c511e834e147bba36295cec622a4b76ec7ac8f893511ec03d66d46de61
+size 197319955

model_and_optim/__7_7.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26405a974e58bf62834ec8b429b584633892ff41f47f14d07c14b278b76a39e4
+size 197182971

model_and_optim/__8_1.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bb5740b18cf7c1574195df8f44a2aab2d5731eadb900a7a04e86fa37756eb5
+size 197124856

model_and_optim/__8_6.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ef9e41bd3eeff3b2856205661404f9c6aae7ec3bd53ad1cceffa6a1935d188
+size 197308194

model_and_optim/__9_1.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9984326b5354a57ca982982b56426d1046c24a2e68f02d3e7597587438383e8e
+size 197124856

model_and_optim/__9_14.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f766bc24548057646be5e3e26380b50ab67d5cc7f67c1ee03a869c80d5aa681f
+size 197319955

model_and_optim/__9_3.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23942e76b2fcc80ba1c6d7153c7cd5f14c481b4a109ba1983f2151576265b825
+size 197124856

model_and_optim/__9_9.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efa678dd4a9c00f71f39a9029b0bbf46743630e6c29a1c6c7bfa82d9beee0df
+size 197182971

train/rank0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790482fab49a0c3d2c64a9984b8fdc8b0115b669feac925eb8a2c2d51bdf85fc
+size 14997

train/rank1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:565ca8a17981b2bec78be27fbc6a592fabe408801a1b870c8b28ecda63e2ef99
+size 15061

train/rank10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26290f02251c772bfafa80337265b84771ace54a31ca80d81e4b043e7b3b6738
+size 15069

train/rank11.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ebdc2c5fb99cd077b786716c1ff9774704307c37d9e82eb8108976052b54e62
+size 15069

train/rank12.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53bd2bdf4e4829c6af91be63447a01eeb27b6e7909405f1de9e089cb9b88c240
+size 15069

train/rank13.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106b7bf9c85649c99541d2bd79eddee0109332b21094df28f18a0d62e69aa622
+size 15069

train/rank14.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14fb7452113d272c5674e2630da1e79ae9f8bc87ac85234f8024c17e1b287991
+size 15069

train/rank15.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d533fd5701673ab6de194178693854038b5f6b570c5fcc56555f68365103217b
+size 15069

train/rank2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7076eb17dffd55535f64c004c2cd1a0af952f1d92ece76edc645d41fe7fde9
+size 15061

train/rank3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6257eb07a70516fae3192d00df2c9b9a1b5515edab68e25bab7703446a8a2f78
+size 15061

train/rank4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dc3674cfa577eaa5d0e9968ab31069e33b3eca5f003cc41af41970880d8661
+size 15061

train/rank5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66aebfe1843cbdb2ec33d9db1d8ff39815fb59da3074fd26b2f4ad1fa8d36bc
+size 15061

train/rank6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220671d73c8066bb3775b27ca91e81897d22c081f7532875a7d7dd0463b39ddb
+size 15061

train/rank7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baaac80ef69d25c6e82f184cc612948bc4fac1ecbe31ddc187c594eea901be59
+size 15061

train/rank8.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28511be4e382e3117f3f6951da76b80c10fbe282321987c50251bfa14b7ef20
+size 15061