auto-sync epoch_0_step_3499 2026-09-08 09:59

.gitattributes

@@ -95,3 +95,13 @@ ckpt/epoch_0_step_2999/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 ckpt/epoch_0_step_2999/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
 ckpt/epoch_0_step_2999/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 ckpt/epoch_0_step_2999/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/model/.hf_metadata/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/.metadata filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+ckpt/epoch_0_step_3499/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

ckpt/epoch_0_step_3499/config.yaml

@@ -0,0 +1,88 @@
+recipe: TrainFinetuneRecipeForNextTokenPrediction
+seed: 1234
+step_scheduler:
+  global_batch_size: 64
+  local_batch_size: 1
+  ckpt_every_steps: 500
+  gc_every_steps: 10
+  num_epochs: 1
+  max_steps: 4000
+dist_env:
+  backend: nccl
+  timeout_minutes: 30
+rng:
+  _target_: nemo_automodel.components.training.rng.StatefulRNG
+  seed: 1234
+  ranked: true
+model:
+  _target_: nemo_automodel.NeMoAutoModelForCausalLM.from_pretrained
+  pretrained_model_name_or_path: /llm-align/open_models/gemma4/gemma-4-E2B
+  torch_dtype: torch.bfloat16
+  use_liger_kernel: false
+  use_sdpa_patching: false
+  attn_implementation: sdpa
+  text_config:
+    use_cache: false
+    output_hidden_states: true
+checkpoint:
+  enabled: true
+  checkpoint_dir: /llm-align/liuchonghan/runs/gemma4_ngram/control/ckpt
+  model_save_format: safetensors
+  save_consolidated: false
+distributed:
+  strategy: fsdp2
+  dp_size: none
+  tp_size: 1
+  cp_size: 1
+  pp_size: 1
+  sequence_parallel: false
+  activation_checkpointing: false
+loss_fn:
+  _target_: nemo_automodel.components.loss.linear_ce.FusedLinearCrossEntropy
+  logit_softcapping: 30.0
+dataset:
+  _target_: nemo_automodel.components.datasets.llm.nanogpt_dataset.NanogptDataset
+  file_pattern: /llm-align/liuchonghan/datasets/fineweb_edu_gemma4/train_max_tokens_1200000000/dataset_*.bin
+  seq_len: 4096
+  shuffle_files: false
+  align_to_bos: false
+dataloader:
+  _target_: torchdata.stateful_dataloader.StatefulDataLoader
+  shuffle: false
+  collate_fn: nemo_automodel.components.datasets.utils.default_collater
+  num_workers: 2
+optimizer:
+  _target_: transformer_engine.pytorch.optimizers.fused_adam.FusedAdam
+  betas:
+  - 0.9
+  - 0.95
+  eps: 1.0e-08
+  lr: 1.0e-05
+  weight_decay: 0.1
+  adam_w_mode: true
+  bias_correction: true
+  master_weights: true
+  master_weight_dtype: torch.float32
+  store_param_remainders: true
+  exp_avg_dtype: torch.float32
+  exp_avg_sq_dtype: torch.float32
+lr_scheduler:
+  lr_decay_style: cosine
+  lr_warmup_steps: 400
+  min_lr: 1.0e-06
+clip_grad_norm:
+  max_norm: 1.0
+wandb:
+  enable: true
+  mode: offline
+  dir: /llm-align/liuchonghan/runs/gemma4_ngram/control/wandb
+  project: gemma4_e2b_ngram
+  name: e2b_base_control_fineweb_1.05Btok
+  entity: khazzz1c
+freeze_config:
+  freeze_modules:
+  - path: model.language_model.embed_tokens_per_layer
+  - path: model.language_model.embed_tokens
+  freeze_vision_tower: true
+  freeze_audio_tower: true
+  freeze_language_model: false

ckpt/epoch_0_step_3499/dataloader/dataloader_dp_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb793f081489f96f580463924fac4426ee07bb598caa12721d571c7c1173101b
+size 1915

ckpt/epoch_0_step_3499/dataloader/dataloader_dp_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c348848e2ad250e68b8cf3608afb4930c88aafae13a351cee8fe574604f9aa
+size 1915

ckpt/epoch_0_step_3499/dataloader/dataloader_dp_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f0858fbac2268b25265f98ecfed2fe0f961516276a9d32270c276a2f67d7d2d
+size 1915

ckpt/epoch_0_step_3499/dataloader/dataloader_dp_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63cb0fd67044e2c7469a5ec3be9bd07ac59fc6f522f2e7c4a1720d6b8cc08499
+size 1915

ckpt/epoch_0_step_3499/dataloader/dataloader_dp_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95ed75e24ed0200f8e6adcfb3927f1954957222169d0827a49241c1cd4ad9c1
+size 1915

ckpt/epoch_0_step_3499/dataloader/dataloader_dp_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68ba1cce41af6a838b98c2ec5e892d06e52af31d2a198e7f396968d4b490e05
+size 1915

ckpt/epoch_0_step_3499/dataloader/dataloader_dp_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c084390749fe61d3defff44697d3acbc21a4acfd3fee7fb5f8ac0c066c7f421
+size 1915

ckpt/epoch_0_step_3499/dataloader/dataloader_dp_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ca9245d1631d534e14d6952169389a88d4296083b7d919465ab26a2328b1cc
+size 1915

ckpt/epoch_0_step_3499/losses.json

@@ -0,0 +1 @@
+{"train_loss": 2.3248672485351562}

ckpt/epoch_0_step_3499/model/.hf_metadata/config.json

@@ -0,0 +1,218 @@
+{
+  "_name_or_path": "/llm-align/open_models/gemma4/gemma-4-E2B",
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "chunk_size_feed_forward": 0,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_type": "gemma4",
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "problem_type": null,
+  "return_dict": true,
+  "text_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "chunk_size_feed_forward": 0,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1536,
+    "hidden_size_per_layer_input": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 35,
+    "num_key_value_heads": 1,
+    "num_kv_shared_layers": 20,
+    "output_attentions": false,
+    "output_hidden_states": true,
+    "pad_token_id": 0,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": false,
+    "use_double_wide_mlp": true,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280
+}

ckpt/epoch_0_step_3499/model/.hf_metadata/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.13.0.dev0",
+  "use_cache": false
+}

ckpt/epoch_0_step_3499/model/.hf_metadata/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
+size 32170070

ckpt/epoch_0_step_3499/model/.hf_metadata/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

ckpt/epoch_0_step_3499/model/consolidate.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Offline HF safetensors consolidation helper.
+# Defaults are conservative for login nodes and small CPU machines. For large
+# checkpoints, run this on a CPU compute node and increase parallelism. Work is
+# split across NPROC_PER_NODE worker processes, and each process uses NUM_THREADS
+# writer threads; keep NPROC_PER_NODE * NUM_THREADS within your CPU allocation.
+# Example for an 80-core CPU node:
+#   NPROC_PER_NODE=16 NUM_THREADS=5 bash "$0"
+# Slurm example:
+#   sbatch --cpus-per-task=80 --wrap='NPROC_PER_NODE=16 NUM_THREADS=5 bash /path/to/consolidate.sh'
+# Optional: set CAST_DTYPE=bf16 to request a floating-point dtype cast during export.
+NPROC_PER_NODE="${NPROC_PER_NODE:-1}"
+NUM_THREADS="${NUM_THREADS:-5}"
+CAST_DTYPE="${CAST_DTYPE:-}"
+PYTHON="${PYTHON:-python3}"
+TORCHRUN="${TORCHRUN:-torchrun}"
+CONSOLIDATION_TOOL="${CONSOLIDATION_TOOL:-tools/offline_hf_consolidation.py}"
+CAST_DTYPE_ARGS=()
+if [[ -n "${CAST_DTYPE}" ]]; then
+  CAST_DTYPE_ARGS=(--cast-dtype "${CAST_DTYPE}")
+fi
+if [[ ! -f "${CONSOLIDATION_TOOL}" ]]; then
+  echo "Could not find offline consolidation tool at ${CONSOLIDATION_TOOL}." >&2
+  echo "Run from the AutoModel repo root or set CONSOLIDATION_TOOL=/path/to/tools/offline_hf_consolidation.py." >&2
+  exit 1
+fi
+
+if [[ "${NPROC_PER_NODE}" -gt 1 ]]; then
+  "${TORCHRUN}" --nproc-per-node="${NPROC_PER_NODE}" "${CONSOLIDATION_TOOL}" \
+    --backend gloo \
+    --num-threads "${NUM_THREADS}" \
+    --model-name "/llm-align/open_models/gemma4/gemma-4-E2B" \
+    --input-dir "/llm-align/liuchonghan/runs/gemma4_ngram/control/ckpt/epoch_0_step_3499/model" \
+    --output-dir "/llm-align/liuchonghan/runs/gemma4_ngram/control/ckpt/epoch_0_step_3499/model/consolidated" \
+    "${CAST_DTYPE_ARGS[@]}"
+else
+  "${PYTHON}" "${CONSOLIDATION_TOOL}" \
+    --backend gloo \
+    --num-threads "${NUM_THREADS}" \
+    --model-name "/llm-align/open_models/gemma4/gemma-4-E2B" \
+    --input-dir "/llm-align/liuchonghan/runs/gemma4_ngram/control/ckpt/epoch_0_step_3499/model" \
+    --output-dir "/llm-align/liuchonghan/runs/gemma4_ngram/control/ckpt/epoch_0_step_3499/model/consolidated" \
+    "${CAST_DTYPE_ARGS[@]}"
+fi

ckpt/epoch_0_step_3499/model/shard-00001-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262fb724221aed01d88de460cd159fc4255a824340dda830e32de7ec9fafe47e
+size 1288086744

ckpt/epoch_0_step_3499/model/shard-00002-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b96dfff86c554b6164a7e1b29df46f2fc49e018aa6a66f6e5b105abf66159c3
+size 1288116916

ckpt/epoch_0_step_3499/model/shard-00003-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775b23824afa1e21f3dce824d4bb95dc5014b4e153d282b2ebee8f53c3a53b07
+size 1272388292

ckpt/epoch_0_step_3499/model/shard-00004-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eacb735ec4d4fb3ca290cf4831720807db45fba746afbcf6f0b95fb6d7c5986
+size 1272388220

ckpt/epoch_0_step_3499/model/shard-00005-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe94ed1afccacc48796118f6b77afa14366884771b958dce0970ebc863c2d22
+size 1272388428

ckpt/epoch_0_step_3499/model/shard-00006-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0354e8a877afb40daa14291e9fe80cc4ae52fd4395cda664b9d9ce6c39803043
+size 1272388450

ckpt/epoch_0_step_3499/model/shard-00007-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81717e28af25472e36acff2dd53042f51c34d432a62a870feee53e012d392bce
+size 1272388522

ckpt/epoch_0_step_3499/model/shard-00008-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ee142a7cee1aac26448d776cd5246bd072531ca7983376a8accf7892c995c0
+size 1272388522

ckpt/epoch_0_step_3499/optim/.metadata

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c30f0e0f383a0612f134105ff12ee0428bbf14ac74e537e147cd7cee8095238
+size 4120680

ckpt/epoch_0_step_3499/optim/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b6326eb3cbf4141b2533ae6095d5b4cc4632093860f44df4ba0cd097b82c7a
+size 2348762093

ckpt/epoch_0_step_3499/optim/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea21d2bcc982ed2437bfde6ddddf2d3b55636d353b01ed7cbea78558e53085c
+size 2349308106

ckpt/epoch_0_step_3499/optim/__2_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31522b1c00fbfea2a14c7b27bc820dcd85278c9eb1f49da691aaa826f524f792
+size 2349308106

ckpt/epoch_0_step_3499/optim/__3_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4a568d75e66c0a537ace45bfa69201adc3c965df1f6ccd9708b6b8ef903773
+size 2349308106

ckpt/epoch_0_step_3499/optim/__4_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec6bc5c24b86c5952c4f24d4ccc265dc41b513c06dd48394f072300f65d8285
+size 2349308106

ckpt/epoch_0_step_3499/optim/__5_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d61a702295622c336856dfbf58ed5d4a1e92bdcfd1d78fdfcd4b7336ba5314
+size 2349306845

ckpt/epoch_0_step_3499/optim/__6_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e025abde21706f5bc74a3f52d98c9f8308b11db19e58adf829d2f021191b74
+size 2349306845

ckpt/epoch_0_step_3499/optim/__7_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449d329111eb4b6a1d39fcb6b141c45b72a638656be1747782ecc07b42c6ef1d
+size 2349306845

ckpt/epoch_0_step_3499/rng/rng_global_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127b09eac361efbf704e21cf1bee26f3100b64e0cf8b66694ab3eeb27b539d16
+size 15461

ckpt/epoch_0_step_3499/rng/rng_global_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0a2ec856d02b763b9e0e3c2afffa721eeec648cbc0314079098707675124ef
+size 15461

ckpt/epoch_0_step_3499/rng/rng_global_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953f7e48cebd0fe7ca90ac7ca4ded21d9226081fee24e12a2e362613a6ab3d62
+size 15461

ckpt/epoch_0_step_3499/rng/rng_global_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833474b12f6e4ef051ccb0a07150a93f21f474804ada10df4255573bfd575176
+size 15461

ckpt/epoch_0_step_3499/rng/rng_global_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b60a138b1bdba4a6f08f6d34844db415a8a6eb01f336e813ec1206178818d8
+size 15461

ckpt/epoch_0_step_3499/rng/rng_global_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12478054a12f4574601fbcc93bb4c2b18436d4ab957f97206a637fcff0e7c39
+size 15461

ckpt/epoch_0_step_3499/rng/rng_global_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72e9cb72ea73bb6aa0eb17f870345ff4d13de92da878e00a08a5b0f8642b3f66
+size 15461

ckpt/epoch_0_step_3499/rng/rng_global_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e621f9ee1b9c83de09e0e417b240330d784eb81fb25b837cc69ea5999265b991
+size 15461

ckpt/epoch_0_step_3499/step_scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe7446b9947b6c83210ae9ed2adb79a86ca9d494222a97052f2bbb6c4033247
+size 1303