Training in progress, step 61875

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 15.7092 GB
+- VRAM Use: 15.7177 GB
 
 # Distillation (Teacher -> Student) Architecture Difference:
 
@@ -75,7 +75,7 @@ More information needed
 <br/>
 
 # Train Dataset
-Trained on 521,394,320 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
+Trained on 521,375,364 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
 
 - Num Samples: `990,000`
 - Subset: `20231101.en`
@@ -85,7 +85,7 @@ Trained on 521,394,320 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_affine, 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=layernorm_teacher_only, projector=orthogonal))
 ```
 
 # Hyperparameters
@@ -101,8 +101,8 @@ 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=layernorm_teacher_only_affine, projector=mlp))`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f9227c352a0>`
+- 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=orthogonal))`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f407f7e64a0>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`
@@ -131,6 +131,6 @@ The following hyperparameters were used during training:
 
 # Framework Versions
 - Distily 0.5.0
-- Transformers 4.44.1
+- Transformers 4.44.2
 - Pytorch 2.4.0+cu121
-- Datasets 2.21.0
+- Datasets 2.18.0

config.json

@@ -40,7 +40,7 @@
     }
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.1",
+  "transformers_version": "4.44.2",
   "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": "4.44.1"
+  "transformers_version": "4.44.2"
 }

logs/attn_norm=layernorm_teacher_only_affine, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=16, warmup_ratio=0/events.out.tfevents.1725420503.a7e428977e35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c03bdbfca39eb7f14d0c914cc2ac78685f7d73ab7c36895ad44217bf1434498
+size 3521137

logs/attn_norm=layernorm_teacher_only_affine, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=16, warmup_ratio=0/events.out.tfevents.1725422902.a7e428977e35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f3784e73c03d99d460bb9d7f22b4238513a673d65acf2bd4b37cc4fa3057f6
+size 31109646

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbeefd226b436e4591c03da38081b8a737c739d471a6c27f640a1c275a57aa9a
+oid sha256:818b1fdc5b41924cd37b2eabdb2ca010801407177916b8e4a7fcdc7e470cd44c
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44c08f1839b95c2e50f13d12d74873601728ffcbe2662209a30cbf75542b5c4
+oid sha256:ca1eccfecd5e1b25f6dfed9fb3649ebc001abd5900d33fa02be2fd2947b395b4
 size 5624