End of training

README.md

@@ -94,7 +94,7 @@ The following hyperparameters were used during training:
 <details>
 <summary>Expand</summary>
 
-- learning_rate: `0.0001`
+- learning_rate: `0.0002`
 - train_batch_size: `4`
 - eval_batch_size: `8`
 - seed: `42`
@@ -103,7 +103,7 @@ The following hyperparameters were used during training:
 - 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=25, loss_fn=raw_mse, layer_mapper=layer-2, norm=layernorm, projector=mlp))`
 - train_embeddings: `True`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f29b07bc430>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f29b03e3a30>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`

logs/attn_norm=layernorm, attn_projector=mlp, attn_weight=25, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725032620.63bdd91cff03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1462dcfbb99344bd523c283724ec94c2af922e4664d1436aa996fc50f9ee28b
+size 529