End of training

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 15.6974 GB
+- VRAM Use: 15.7006 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=instance_teacher_only, projector=orthogonal))
 ```
 
 # Hyperparameters
@@ -101,9 +101,9 @@ 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=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=instance_teacher_only, projector=orthogonal))`
 - train_embeddings: `True`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f459c7204c0>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f3d6a80fa90>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`
@@ -135,4 +135,4 @@ The following hyperparameters were used during training:
 - Distily 0.4.1
 - Transformers 4.44.2
 - Pytorch 2.4.0+cu121
-- Datasets 2.21.0
+- Datasets 2.18.0

logs/attn_norm=instance_teacher_only, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=8, warmup_ratio=0/events.out.tfevents.1725340001.a7e428977e35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7fd30d4bfc4a725807f316f3730f09d59d7719bb69a9db8c89b70ff2cce1f7
+size 529

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4bc9a6cbde92637ccde86f757f84ee56fdd2bf9ba77499beb1f3a761f2e6d6
+oid sha256:a42e0363b74fe69eae4b567c4028f2b6ae9eb5c47147f78afd55d87f42093b76
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f79d4bf843c19da12b9ec40e8df71cd9241f34ee4effe4574f24f46b808b897
+oid sha256:4d7b2087ed8d80950ecd4c57013fd14f8c8c48b7a8dd54482b90b1b1124adde9
 size 5624