Training in progress, step 61875

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 15.6974 GB
+- VRAM Use: 15.6991 GB
 
 # Distillation (Teacher -> Student) Architecture Difference:
 
@@ -85,7 +85,7 @@ Trained on 521,413,804 tokens from the [wikimedia/wikipedia](https://huggingface
 # Training Objective
 
 ```
-DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=5, loss_fn=raw_mse, layer_mapper=layer-2, norm=instance_teacher_only, projector=mlp))
+DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=5, loss_fn=raw_mse, layer_mapper=layer-2, norm=instancenorm, projector=mlp))
 ```
 
 # Hyperparameters
@@ -94,16 +94,16 @@ The following hyperparameters were used during training:
 <details>
 <summary>Expand</summary>
 
-- learning_rate: `0.0001`
+- learning_rate: `0.0002`
 - train_batch_size: `16`
 - eval_batch_size: `8`
 - 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(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=5, loss_fn=raw_mse, layer_mapper=layer-2, norm=instance_teacher_only, projector=mlp))`
+- distillation_objective: `DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=5, loss_fn=raw_mse, layer_mapper=layer-2, norm=instancenorm, projector=mlp))`
 - train_embeddings: `True`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f460c9e5c00>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f9ba04f7130>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`

logs/attn_norm=instance_teacher_only, attn_projector=mlp, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=16, warmup_ratio=0/events.out.tfevents.1725245255.849724f928d2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21ee14b120d9fd0f175ebc72f111f30d45467edc097b3f80d22c868c4574c71
+size 29625546

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1061501f53ab6b5105d932085f2dc58d0dae360d4a0349432be53a9e2a96992
+oid sha256:e7942bccab3481741b096b5fc51e3e8dad9c6d1442245571e9aaa518cf77b2f9
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955f527f9e29e75391ecf1e3e4d718f71c1c005970fefe3f14962b04c2006b01
+oid sha256:5419e3ac9596a3487f62c2cfd4b59310ce7b70e1085a3de8ae72899aed6b85a6
 size 5624