Training in progress, step 123750

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=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=instance_teacher_only, projector=orthogonal))
 ```
 
 # Hyperparameters
@@ -94,16 +94,16 @@ The following hyperparameters were used during training:
 <details>
 <summary>Expand</summary>
 
-- learning_rate: `0.0001`
-- train_batch_size: `8`
+- learning_rate: `0.0002`
+- train_batch_size: `16`
 - eval_batch_size: `8`
 - seed: `42`
 - 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))`
+- 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 0x7f44e3dc38b0>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f273080d2d0>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`
@@ -133,6 +133,6 @@ The following hyperparameters were used during training:
 
 # Framework Versions
 - Distily 0.4.1
-- Transformers 4.44.2
+- Transformers 4.44.1
 - Pytorch 2.4.0+cu121
 - Datasets 2.21.0

config.json

@@ -40,7 +40,7 @@
     }
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.44.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.44.1"
 }

logs/attn_norm=instance_teacher_only, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=16, warmup_ratio=0/events.out.tfevents.1725243527.e3f806ea38c9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c042981d7ed1c75092c8550e4ce29d15889233d99c75c9f5f56871a7377d7b
+size 29625560

logs/attn_norm=instance_teacher_only, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=16, warmup_ratio=0/events.out.tfevents.1725260837.e3f806ea38c9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82cceadfc3045ad3acd3978bd8016d5418dc495e2c7ecb4af85527ea084dae13
+size 529

logs/attn_norm=layernorm_teacher_only, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=8, warmup_ratio=0/events.out.tfevents.1725262129.e3f806ea38c9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da27c98af11481ba5130300573a31ab852f2020a1bdac508976ee720d7552c3
+size 59393302

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0c7367062b9930c2af270d67ccf35573c5171c85157ac9fe730fc8a6658c8f
+oid sha256:a36d1aeeaf4ea60186f79ad4958e2974f72668820ca25a7e85951ca1e9dd0e73
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282c83cda9341b422f4189a5a7127f6cba3be665f892404c9302b13ccc5176bb
+oid sha256:95123fc10b651d49fc44298c330c78c0d98e418546aeb245bbe0ae5ab1048d11
 size 5624