Training in progress, step 198000

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 7.4145 GB
+- VRAM Use: 7.4173 GB
 
 # Distillation (Teacher -> Student) Architecture Difference:
 
@@ -75,7 +75,7 @@ More information needed
 <br/>
 
 # Train Dataset
-Trained on 226,137,833 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
+Trained on 226,165,778 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
 
 - Num Samples: `396,000`
 - Subset: `20231101.en`
@@ -85,7 +85,7 @@ Trained on 226,137,833 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, 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, projector=orthogonal))
 ```
 
 # Hyperparameters
@@ -95,16 +95,15 @@ The following hyperparameters were used during training:
 <summary>Expand</summary>
 
 - learning_rate: `0.0001`
-- train_batch_size: `4`
+- train_batch_size: `2`
 - eval_batch_size: `8`
 - seed: `42`
 - optimizer: `Adam with betas=(0.9,0.999) and epsilon=1e-08`
 - 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=5, 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=5, loss_fn=raw_mse, layer_mapper=layer-2, norm=layernorm, projector=orthogonal))`
 - train_embeddings: `True`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7fd06c06f5e0>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f00d9654670>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `distilbert/distilgpt2`
 - student_model_config: `None`
@@ -124,7 +123,7 @@ The following hyperparameters were used during training:
 - gradient_accumulation_steps: `1`
 - weight_decay: `0.0`
 - max_grad_norm: `1.0`
-- warmup_ratio: `0.2`
+- warmup_ratio: `0`
 - warmup_steps: `0`
 - gradient_checkpointing: `True`
 
@@ -134,6 +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 2.18.0
+- 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=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=2, warmup_ratio=0/events.out.tfevents.1725087942.e3f806ea38c9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f47c2bd125f7b88f7934f74067c73e9cadc34a34ba942db3026944c6934686
-size 253
+oid sha256:e1c19d8bbe37626c7079f2262080a3949ec0c51b0f1f60bde20ce51c48772f6f
+size 529

logs/attn_norm=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=2, warmup_ratio=0/events.out.tfevents.1725088155.e3f806ea38c9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4136f1bc67a55f32d0d36383454e98fefa9bb6fbb98d15307940c74f87392f6b
+size 95114834

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc2a89d9b93a9c39e0bb7c3211860d6573064462f7394851f5550aad564fd7d
+oid sha256:7175adf590905ccea6b2233241d87bb4b83d5c77348e43b830358b6f6d220076
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7b9a733e8eddf676f77eff2f4387758e33482198ef07a3b029094fffc69e3b
+oid sha256:b380858034193bb564d29ce062331c1a266654fb6a6d7144376d7fb98e653fa7
 size 5560