End of training

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 7.4259 GB
+- VRAM Use: 7.4246 GB
 
 # Distillation (Teacher -> Student) Architecture Difference:
 
@@ -75,7 +75,7 @@ More information needed
 <br/>
 
 # Train Dataset
-Trained on 6,814,337 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
+Trained on 6,813,915 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
 
 - Num Samples: `9,900`
 - Subset: `20231101.en`
@@ -94,7 +94,7 @@ The following hyperparameters were used during training:
 <details>
 <summary>Expand</summary>
 
-- learning_rate: `0.0002`
+- learning_rate: `0.0001`
 - train_batch_size: `4`
 - eval_batch_size: `8`
 - seed: `42`
@@ -102,7 +102,7 @@ The following hyperparameters were used during training:
 - 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, projector=orthogonal))`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7feeb393be50>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7fd81c98ccd0>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=True, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725295355.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebd0e2d06f50a6e77e136a45346f6d168fbffa0309bcc05bd02ad8bfd3120a4
+size 249