Training in progress, step 99000

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 7.4148 GB
+- VRAM Use: 7.4164 GB
 
 # Distillation (Teacher -> Student) Architecture Difference:
 
@@ -85,7 +85,7 @@ Trained on 226,096,614 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=25, loss_fn=raw_mse, layer_mapper=layer-2, norm=layernorm, projector=mlp))
+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, projector=orthogonal))
 ```
 
 # Hyperparameters
@@ -102,9 +102,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: `polynomial`
 - lr_scheduler_warmup_ratio: `0.2`
 - 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))`
+- 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, projector=orthogonal))`
 - train_embeddings: `True`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7fcf24346980>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7fe60c136110>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`
@@ -136,4 +136,4 @@ The following hyperparameters were used during training:
 - Distily 0.4.1
 - Transformers 4.44.2
 - Pytorch 2.4.0+cu121
-- Datasets 2.18.0
+- Datasets 2.21.0

logs/attn_norm=None, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0.2/events.out.tfevents.1725111510.23668649e3db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4003eddf0c63bd02515b4a101bacfe68a15ec44a909e4481b4008ab4271221d8
+size 47486052

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce86b32ce7013508c4f37e2aa3087bac0a2b30faeb8080f63dfdc1da27d1c84e
+oid sha256:093dc85d7aa7ea16b441e7ac8ebdb50e781b78d01a3090dfa8465e7d65b3fdb4
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdbfabe14e1fee095c931cfc8983452f98e29f0aae284e39f3a04b8a36368215
+oid sha256:b04c8be3b9c81ff91b22fb6ea84369bf65907b954e1705878806919caa5e72d1
 size 5560