Skip to content

docs(misc): point GB200 fine-tunes at the card's own import #6366

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cuichenx merged 1 commit into from
Oct 9, 2026
Merged

docs(misc): point GB200 fine-tunes at the card's own import #6366

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions docs/_static/model-verification/catalog-v1.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -912,7 +912,7 @@
}
],
"commands": [
"./scripts/training/train.sh --nodes 8 --gpus-per-node 4 --recipe deepseek_v4_flash_sft_openmath_thinking_packed_gb200_config --mode sft --step-func dsv4_step --pretrained_checkpoint work/models/deepseek-v4-flash-megatron --save_dir work/model-verification/dsv4-flash/sft-ref --save_interval 100 --max_steps 100 --seq_length 1024 --pipeline_model_parallel_size 4 --context_parallel_size 1 --expert_model_parallel_size 8 'model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL' scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null checkpoint.load_optim=false checkpoint.load_rng=false checkpoint.save_optim=false ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180"
"./scripts/training/train.sh --nodes 8 --gpus-per-node 4 --recipe deepseek_v4_flash_sft_openmath_thinking_packed_gb200_config --mode sft --step-func dsv4_step --pretrained_checkpoint work/model-verification/dsv4-flash/import-gpu/iter_0000000 --save_dir work/model-verification/dsv4-flash/sft-ref --save_interval 100 --max_steps 100 --seq_length 1024 --pipeline_model_parallel_size 4 --context_parallel_size 1 --expert_model_parallel_size 8 'model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL' scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null checkpoint.load_optim=false checkpoint.load_rng=false checkpoint.save_optim=false ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180"
],
"dimensions": {},
"enabled_features": {
Expand Down Expand Up @@ -984,7 +984,7 @@
}
],
"commands": [
"./scripts/training/train.sh --nodes 16 --gpus-per-node 4 --recipe deepseek_v4_flash_sft_openmath_thinking_packed_config --step-func dsv4_step --pretrained_checkpoint work/models/deepseek-v4-flash-megatron --save_dir work/model-verification/dsv4-flash/sft-long-context-ref --save_interval 100 --max_steps 100 model.pipeline_model_parallel_size=4 'model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL' model.context_parallel_size=2 model.cp_partition_mode=contiguous model.expert_model_parallel_size=8 model.moe_grouped_gemm=false model.recompute_granularity=full model.recompute_method=uniform model.recompute_num_layers=1 dataset.seq_length=1024 scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180"
"./scripts/training/train.sh --nodes 16 --gpus-per-node 4 --recipe deepseek_v4_flash_sft_openmath_thinking_packed_config --step-func dsv4_step --pretrained_checkpoint work/model-verification/dsv4-flash/import-gpu/iter_0000000 --save_dir work/model-verification/dsv4-flash/sft-long-context-ref --save_interval 100 --max_steps 100 model.pipeline_model_parallel_size=4 'model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL' model.context_parallel_size=2 model.cp_partition_mode=contiguous model.expert_model_parallel_size=8 model.moe_grouped_gemm=false model.recompute_granularity=full model.recompute_method=uniform model.recompute_num_layers=1 dataset.seq_length=1024 scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180"
],
"dimensions": {},
"enabled_features": {
Expand Down Expand Up @@ -1023,7 +1023,7 @@
}
],
"commands": [
"./scripts/training/train.sh --nodes 8 --gpus-per-node 4 --recipe deepseek_v4_flash_peft_openmath_thinking_packed_gb200_config --mode lora --step-func dsv4_step --pretrained_checkpoint work/models/deepseek-v4-flash-megatron --save_dir work/model-verification/dsv4-flash/peft-ref --save_interval 100 --max_steps 100 --seq_length 1024 --pipeline_model_parallel_size 4 --context_parallel_size 1 --expert_model_parallel_size 8 'model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL' scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null checkpoint.load_optim=false checkpoint.load_rng=false checkpoint.save_optim=false ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180"
"./scripts/training/train.sh --nodes 8 --gpus-per-node 4 --recipe deepseek_v4_flash_peft_openmath_thinking_packed_gb200_config --mode lora --step-func dsv4_step --pretrained_checkpoint work/model-verification/dsv4-flash/import-gpu/iter_0000000 --save_dir work/model-verification/dsv4-flash/peft-ref --save_interval 100 --max_steps 100 --seq_length 1024 --pipeline_model_parallel_size 4 --context_parallel_size 1 --expert_model_parallel_size 8 'model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL' scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null checkpoint.load_optim=false checkpoint.load_rng=false checkpoint.save_optim=false ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180"
],
"dimensions": {},
"enabled_features": {
Expand Down Expand Up @@ -9911,7 +9911,7 @@
}
],
"commands": [
"./scripts/training/train.sh --nodes 2 --gpus-per-node 4 --recipe qwen35_vl_35b_a3b_sft_8gpu_gb200_bf16_functional_config --dataset medpix --pretrained_checkpoint work/model-verification/qwen3.6-35b-a3b/gb200-imported/iter_0000000 --max_steps 100 --warmup_iters 10 'dataset.source.load_kwargs={revision:69eb219d477ab8699296da1fd6b89beb768042d3}' 'dataset.source.adapter_kwargs={resized_height:448,resized_width:448}' dataset.hf_processor_path=Qwen/Qwen3.6-35B-A3B 'dataset.hf_processor_kwargs={revision:995ad96eacd98c81ed38be0c5b274b04031597b0}' scheduler.lr_decay_iters=100 model.hf_model_id=Qwen/Qwen3.6-35B-A3B model.bos_token_id=248044 logger.save_config_filepath=work/model-verification/qwen3.6-35b-a3b/gb200-sft/resolved-config.yaml"
"./scripts/training/train.sh --nodes 2 --gpus-per-node 4 --recipe qwen35_vl_35b_a3b_sft_8gpu_gb200_bf16_functional_config --dataset medpix --pretrained_checkpoint work/model-verification/qwen3.6-35b-a3b/imported-megatron/iter_0000000 --max_steps 100 --warmup_iters 10 'dataset.source.load_kwargs={revision:69eb219d477ab8699296da1fd6b89beb768042d3}' 'dataset.source.adapter_kwargs={resized_height:448,resized_width:448}' dataset.hf_processor_path=Qwen/Qwen3.6-35B-A3B 'dataset.hf_processor_kwargs={revision:995ad96eacd98c81ed38be0c5b274b04031597b0}' scheduler.lr_decay_iters=100 model.hf_model_id=Qwen/Qwen3.6-35B-A3B model.bos_token_id=248044 logger.save_config_filepath=work/model-verification/qwen3.6-35b-a3b/gb200-sft/resolved-config.yaml"
],
"dimensions": {},
"enabled_features": {
Expand Down Expand Up @@ -10054,7 +10054,7 @@
}
],
"commands": [
"./scripts/training/train.sh --nodes 2 --gpus-per-node 4 --recipe qwen35_vl_35b_a3b_peft_8gpu_gb200_bf16_functional_config --dataset medpix --pretrained_checkpoint work/model-verification/qwen3.6-35b-a3b/gb200-imported/iter_0000000 --max_steps 100 --warmup_iters 10 'dataset.source.load_kwargs={revision:69eb219d477ab8699296da1fd6b89beb768042d3}' 'dataset.source.adapter_kwargs={resized_height:448,resized_width:448}' dataset.hf_processor_path=Qwen/Qwen3.6-35B-A3B 'dataset.hf_processor_kwargs={revision:995ad96eacd98c81ed38be0c5b274b04031597b0}' scheduler.lr_decay_iters=100 model.hf_model_id=Qwen/Qwen3.6-35B-A3B model.bos_token_id=248044 logger.save_config_filepath=work/model-verification/qwen3.6-35b-a3b/gb200-peft/resolved-config.yaml"
"./scripts/training/train.sh --nodes 2 --gpus-per-node 4 --recipe qwen35_vl_35b_a3b_peft_8gpu_gb200_bf16_functional_config --dataset medpix --pretrained_checkpoint work/model-verification/qwen3.6-35b-a3b/imported-megatron/iter_0000000 --max_steps 100 --warmup_iters 10 'dataset.source.load_kwargs={revision:69eb219d477ab8699296da1fd6b89beb768042d3}' 'dataset.source.adapter_kwargs={resized_height:448,resized_width:448}' dataset.hf_processor_path=Qwen/Qwen3.6-35B-A3B 'dataset.hf_processor_kwargs={revision:995ad96eacd98c81ed38be0c5b274b04031597b0}' scheduler.lr_decay_iters=100 model.hf_model_id=Qwen/Qwen3.6-35B-A3B model.bos_token_id=248044 logger.save_config_filepath=work/model-verification/qwen3.6-35b-a3b/gb200-peft/resolved-config.yaml"
],
"dimensions": {},
"enabled_features": {
Expand Down
6 changes: 3 additions & 3 deletions docs/fern/versions/nightly/pages/models/deepseek/deepseek-v4.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -315,7 +315,7 @@ Choose a workflow, precision, and exact recorded combination. The command and ex
<span>Command</span>
<button type="button" class="verification-copy-command">Copy</button>
</div>
<pre><code class="language-bash">./scripts/training/train.sh --nodes 8 --gpus-per-node 4 --recipe deepseek_v4_flash_sft_openmath_thinking_packed_gb200_config --mode sft --step-func dsv4_step --pretrained_checkpoint work/models/deepseek-v4-flash-megatron --save_dir work/model-verification/dsv4-flash/sft-ref --save_interval 100 --max_steps 100 --seq_length 1024 --pipeline_model_parallel_size 4 --context_parallel_size 1 --expert_model_parallel_size 8 &#x27;model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL&#x27; scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null checkpoint.load_optim=false checkpoint.load_rng=false checkpoint.save_optim=false ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180</code></pre>
<pre><code class="language-bash">./scripts/training/train.sh --nodes 8 --gpus-per-node 4 --recipe deepseek_v4_flash_sft_openmath_thinking_packed_gb200_config --mode sft --step-func dsv4_step --pretrained_checkpoint work/model-verification/dsv4-flash/import-gpu/iter_0000000 --save_dir work/model-verification/dsv4-flash/sft-ref --save_interval 100 --max_steps 100 --seq_length 1024 --pipeline_model_parallel_size 4 --context_parallel_size 1 --expert_model_parallel_size 8 &#x27;model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL&#x27; scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null checkpoint.load_optim=false checkpoint.load_rng=false checkpoint.save_optim=false ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180</code></pre>
</div>
</section>
<section class="verification-expected-result">
Expand Down Expand Up @@ -365,7 +365,7 @@ Choose a workflow, precision, and exact recorded combination. The command and ex
<span>Command</span>
<button type="button" class="verification-copy-command">Copy</button>
</div>
<pre><code class="language-bash">./scripts/training/train.sh --nodes 16 --gpus-per-node 4 --recipe deepseek_v4_flash_sft_openmath_thinking_packed_config --step-func dsv4_step --pretrained_checkpoint work/models/deepseek-v4-flash-megatron --save_dir work/model-verification/dsv4-flash/sft-long-context-ref --save_interval 100 --max_steps 100 model.pipeline_model_parallel_size=4 &#x27;model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL&#x27; model.context_parallel_size=2 model.cp_partition_mode=contiguous model.expert_model_parallel_size=8 model.moe_grouped_gemm=false model.recompute_granularity=full model.recompute_method=uniform model.recompute_num_layers=1 dataset.seq_length=1024 scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180</code></pre>
<pre><code class="language-bash">./scripts/training/train.sh --nodes 16 --gpus-per-node 4 --recipe deepseek_v4_flash_sft_openmath_thinking_packed_config --step-func dsv4_step --pretrained_checkpoint work/model-verification/dsv4-flash/import-gpu/iter_0000000 --save_dir work/model-verification/dsv4-flash/sft-long-context-ref --save_interval 100 --max_steps 100 model.pipeline_model_parallel_size=4 &#x27;model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL&#x27; model.context_parallel_size=2 model.cp_partition_mode=contiguous model.expert_model_parallel_size=8 model.moe_grouped_gemm=false model.recompute_granularity=full model.recompute_method=uniform model.recompute_num_layers=1 dataset.seq_length=1024 scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180</code></pre>
</div>
</section>
<section class="verification-expected-result">
Expand Down Expand Up @@ -423,7 +423,7 @@ Choose a workflow, precision, and exact recorded combination. The command and ex
<span>Command</span>
<button type="button" class="verification-copy-command">Copy</button>
</div>
<pre><code class="language-bash">./scripts/training/train.sh --nodes 8 --gpus-per-node 4 --recipe deepseek_v4_flash_peft_openmath_thinking_packed_gb200_config --mode lora --step-func dsv4_step --pretrained_checkpoint work/models/deepseek-v4-flash-megatron --save_dir work/model-verification/dsv4-flash/peft-ref --save_interval 100 --max_steps 100 --seq_length 1024 --pipeline_model_parallel_size 4 --context_parallel_size 1 --expert_model_parallel_size 8 &#x27;model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL&#x27; scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null checkpoint.load_optim=false checkpoint.load_rng=false checkpoint.save_optim=false ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180</code></pre>
<pre><code class="language-bash">./scripts/training/train.sh --nodes 8 --gpus-per-node 4 --recipe deepseek_v4_flash_peft_openmath_thinking_packed_gb200_config --mode lora --step-func dsv4_step --pretrained_checkpoint work/model-verification/dsv4-flash/import-gpu/iter_0000000 --save_dir work/model-verification/dsv4-flash/peft-ref --save_interval 100 --max_steps 100 --seq_length 1024 --pipeline_model_parallel_size 4 --context_parallel_size 1 --expert_model_parallel_size 8 &#x27;model.pipeline_model_parallel_layout=Et*11|t*11|t*11|t*10mL&#x27; scheduler.lr_warmup_iters=10 scheduler.lr_decay_iters=100 validation.eval_interval=0 validation.eval_iters=0 rng.seed=5678 ddp.check_for_nan_in_grad=true ddp.check_for_large_grads=true rerun_state_machine.check_for_nan_in_loss=true checkpoint.exit_on_missing_checkpoint=false checkpoint.load=null checkpoint.load_optim=false checkpoint.load_rng=false checkpoint.save_optim=false ddp.overlap_grad_reduce=false logger.log_interval=1 logger.log_throughput=true logger.tensorboard_dir=null dist.distributed_timeout_minutes=180</code></pre>
</div>
</section>
<section class="verification-expected-result">
Expand Down
Loading
Loading