| optimizer: | |
| allreduce_bucket_size: 500000000 | |
| beta1: 0.9 | |
| beta2: 0.95 | |
| debug_log: false | |
| eps: 1e-08 | |
| gradient_clipping: 0.0 | |
| zero: true | |
| zero_save_static: false | |
| topology: | |
| activation_checkpointing_type: disabled | |
| global_batch_size: 1024 | |
| gradient_accumulation_steps: 2 | |
| micro_batch_size: 2 | |
| model_parallel_size: 1 | |
| pipe_parallel_size: 1 | |
| pipe_partition_method: balanced | |
| pipe_partition_overwrite: null | |
| sequence_parallel: false | |
| trainer: | |
| seed: 42 | |
| train_iterations: 72000 | |
| training: | |
| allow_missing_params_in_optimizer: true | |
| training_groups: | |
| - group_name: param_group | |
| independent_weight_decay: true | |
| learning_rate_scheduler: | |
| learning_rate: 11.313708498984761 | |
| learning_rate_decay_iters: 72000 | |
| learning_rate_decay_style: cosine | |
| learning_rate_minimum: 1.131370849898476 | |
| learning_rate_warmup_steps: 500 | |
| parameters_exclude: | |
| - norm | |
| weight_decay: 0.0001221 | |
| transformer_architecture: | |
| attention_bias: false | |
| attention_num_kv_heads: null | |
| attention_qkv_in_one: true | |
| dropout_after_attention: 0.0 | |
| dropout_after_mlp: 0.0 | |
| dropout_attention_probs: 0.0 | |
| dropout_embedding: 0.0 | |
| dropout_image_encoder: 0.0 | |
| fp8_config_attention: | |
| dtypes_forward: | |
| left_dtype: e4m3 | |
| right_dtype: e4m3 | |
| dtypes_grad_input: | |
| left_dtype: e5m2 | |
| right_dtype: e4m3 | |
| dtypes_grad_weight: | |
| left_dtype: e4m3 | |
| right_dtype: e5m2 | |
| fp8_config_mlp: | |
| dtypes_forward: | |
| left_dtype: e4m3 | |
| right_dtype: e4m3 | |
| dtypes_grad_input: | |
| left_dtype: e5m2 | |
| right_dtype: e4m3 | |
| dtypes_grad_weight: | |
| left_dtype: e4m3 | |
| right_dtype: e5m2 | |
| hidden_size: 3072 | |
| image_encoder: false | |
| key_query_norm: false | |
| layernorm: | |
| layernorm_epsilon: 1e-05 | |
| optimization_type: torch | |
| local_attention_window_size: null | |
| masked_softmax: | |
| kernel: flash_attention | |
| scale: 1.0 | |
| softmax_in_fp32: false | |
| mlp_bias: false | |
| mlp_factor: 2.6666666666666665 | |
| mlp_type: swiglu | |
| norm_type: rms | |
| num_attention_heads: 24 | |
| num_layers: 24 | |
| num_local_attention_heads: 0 | |
| precision: bfloat16 | |
| relative_position_embedding_type: rotary_complex | |
| reset_attention_mask: false | |
| reset_position_ids: false | |
| rotary_embedding_base: 10000 | |
| rotary_percentage: 1.0 | |
| sequence_length: 4096 | |
| umup: | |
| act_mult: 1.0 | |
| attn_mult: 1.0 | |
| enable: true | |
| loss_mult: 1.0 | |
| normalize_depth_to_num_layers: true | |
| residual_attn_ratio: 0.25 | |
| residual_mult: 1.0 | |
| vocab_file: null | |
| vocab_size: 65536 | |
| weight_tying: false | |