End of training

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 15.7087 GB
+- VRAM Use: 15.7092 GB
 
 # Distillation (Teacher -> Student) Architecture Difference:
 
@@ -75,7 +75,7 @@ More information needed
 <br/>
 
 # Train Dataset
-Trained on 521,366,153 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
+Trained on 521,394,320 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
 
 - Num Samples: `990,000`
 - Subset: `20231101.en`
@@ -85,7 +85,7 @@ Trained on 521,366,153 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=layernorm_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=layernorm_teacher_only_affine, projector=mlp))
 ```
 
 # Hyperparameters
@@ -101,8 +101,8 @@ The following hyperparameters were used during training:
 - 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=layernorm_teacher_only, projector=mlp))`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f6d9cec8700>`
+- 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=layernorm_teacher_only_affine, projector=mlp))`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f9227c352a0>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`

logs/attn_norm=layernorm_teacher_only_affine, attn_projector=mlp, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=16, warmup_ratio=0/events.out.tfevents.1725435353.e3f806ea38c9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db90b083af9509b4ea492b530c588953c257fafbddb1f49fa9b546da7e7cbf96
+size 529