distily/distily_distsmollm_max_length

Summary

Distilled with Distily library using teacher model HuggingFaceTB/SmolLM-135M on dataset wikimedia/wikipedia.

Model Architecture:

• Architecture: LlamaForCausalLM
• Total Parameters: 81,413,568
• Data Type (dtype): torch.float32
• Model Size: 0.30 GB

Student Model Details

LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(49152, 576)
    (layers): ModuleList(
      (0-14): 15 x LlamaDecoderLayer(
        (self_attn): LlamaSdpaAttention(
          (q_proj): Linear(in_features=576, out_features=576, bias=False)
          (k_proj): Linear(in_features=576, out_features=192, bias=False)
          (v_proj): Linear(in_features=576, out_features=192, bias=False)
          (o_proj): Linear(in_features=576, out_features=576, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LigerSwiGLUMLP(
          (gate_proj): Linear(in_features=576, out_features=1536, bias=False)
          (up_proj): Linear(in_features=576, out_features=1536, bias=False)
          (down_proj): Linear(in_features=1536, out_features=576, bias=False)
        )
        (input_layernorm): LigerRMSNorm((576,), eps=1e-05, offset=0.0)
        (post_attention_layernorm): LigerRMSNorm((576,), eps=1e-05, offset=0.0)
      )
    )
    (norm): LigerRMSNorm((576,), eps=1e-05, offset=0.0)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=576, out_features=49152, bias=False)
)

Resource Usage

• Max Train VRAM Use: 3.7488 GB
• Available VRAM: 23.4329 GB
• GPUs:
  • 1x NVIDIA GeForce RTX 4090
• CPUs: 64
• CPU Memory: 251.7299 GB
• CPU Memory Bandwidth: 1600 GB/s

Distillation (Teacher -> Student) Architecture Difference:

• Architecture: LlamaForCausalLM -> LlamaForCausalLM
• Total Parameters: 134,515,008 -> 81,413,568
• Data Type (dtype): torch.float32 -> torch.float32
• Model Size: 0.25 GB -> 0.30 GB

Module Diff Details

--- teacher model modules
+++ student model modules
@@ -2,7 +2,7 @@
   (model): LlamaModel(
     (embed_tokens): Embedding(49152, 576)
     (layers): ModuleList(
-      (0-29): 30 x LlamaDecoderLayer(
+      (0-14): 15 x LlamaDecoderLayer(
         (self_attn): LlamaSdpaAttention(
           (q_proj): Linear(in_features=576, out_features=576, bias=False)
           (k_proj): Linear(in_features=576, out_features=192, bias=False)
@@ -10,17 +10,16 @@
           (o_proj): Linear(in_features=576, out_features=576, bias=False)
           (rotary_emb): LlamaRotaryEmbedding()
         )
-        (mlp): LlamaMLP(
+        (mlp): LigerSwiGLUMLP(
           (gate_proj): Linear(in_features=576, out_features=1536, bias=False)
           (up_proj): Linear(in_features=576, out_features=1536, bias=False)
           (down_proj): Linear(in_features=1536, out_features=576, bias=False)
-          (act_fn): SiLU()
         )
-        (input_layernorm): LlamaRMSNorm((576,), eps=1e-05)
-        (post_attention_layernorm): LlamaRMSNorm((576,), eps=1e-05)
+        (input_layernorm): LigerRMSNorm((576,), eps=1e-05, offset=0.0)
+        (post_attention_layernorm): LigerRMSNorm((576,), eps=1e-05, offset=0.0)
       )
     )
-    (norm): LlamaRMSNorm((576,), eps=1e-05)
+    (norm): LigerRMSNorm((576,), eps=1e-05, offset=0.0)
     (rotary_emb): LlamaRotaryEmbedding()
   )
   (lm_head): Linear(in_features=576, out_features=49152, bias=False)

Train Dataset

Trained on 374,508,910 tokens from the wikimedia/wikipedia dataset.

• Num Samples: 998,000
• Subset: 20231101.en
• Split: train

Training Objective

DistillationObjective(
    logits_loss_component=LossComponent(
        weight=1,
        loss_fn='kl'
    ),
    hs_loss_component=LossComponent(
        weight=0
    ),
    attn_loss_component=LossComponent(
        weight=0
    )
)

Hyperparameters

The following hyperparameters were used during training:

Expand

• learning_rate: 0.0002
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: polynomial
• num_epochs: 1.0
• distillation_objective: DistillationObjective( logits_loss_component=LossComponent( weight=1, loss_fn='kl' ), hs_loss_component=LossComponent( weight=0 ), attn_loss_component=LossComponent( weight=0 ) )
• lr_scheduler: <torch.optim.lr_scheduler.LambdaLR object at 0x72cfc8ab4af0>
• student_model_name_or_path: None
• student_config_name_or_path: None
• student_model_config: {'num_hidden_layers': 15}
• reinitialize_weights: None
• copy_teacher_modules: [('lm_head', False)]
• student_model_as_bitnet: False
• student_use_liger_kernel: True
• teacher_model_name_or_path: HuggingFaceTB/SmolLM-135M
• teacher_load_in_8bit: False
• teacher_load_in_4bit: False
• dataset_uri: wikimedia/wikipedia
• dataset_subset: 20231101.en
• dataset_split: train
• dataset_column_name: text
• dataset_sample_size: 1000000
• dataset_max_seq_length: 512
• dataset_test_size: 0.002
• dataset_shuffle: False
• dataset_shuffle_seed: 42
• dataset_trust_remote_code: False
• gradient_accumulation_steps: 1
• weight_decay: 0.0
• max_grad_norm: 1.0
• warmup_ratio: 0.0
• warmup_steps: 0
• gradient_checkpointing: True

Framework Versions

• Distily 0.5.0
• Transformers 4.45.0.dev0
• Pytorch 2.5.0.dev20240910+cu121
• Datasets 2.21.0