Training in progress, step 99000

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 7.4193 GB
+- VRAM Use: 7.4141 GB
 
 # Distillation (Teacher -> Student) Architecture Difference:
 
@@ -75,7 +75,7 @@ More information needed
 <br/>
 
 # Train Dataset
-Trained on 226,096,614 tokens from the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset.
+Trained on 226,131,064 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 226,096,614 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=orthogonal))
+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))
 ```
 
 # Hyperparameters
@@ -94,16 +94,16 @@ The following hyperparameters were used during training:
 <details>
 <summary>Expand</summary>
 
-- learning_rate: `0.0004`
+- learning_rate: `0.0001`
 - train_batch_size: `4`
 - 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=25, loss_fn=raw_mse, layer_mapper=layer-2, norm=layernorm, projector=orthogonal))`
+- 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))`
 - train_embeddings: `True`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f9c69ffd270>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f2c140a9e10>`
 - 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 4.44.1
-- Pytorch 2.4.0+cu121
+- Transformers 4.44.2
+- Pytorch 2.3.0
 - Datasets 2.21.0

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, attn_projector=mlp, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725001856.63bdd91cff03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1decad3c9933967acd396d7eb02f7dfd4d400a952220b7f5ce166a07bb0ac7c0
+size 47486040

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:986412a3927af65bc71fc15197058beb7a5489eb3563fddaaa69fee5b92d4542
+oid sha256:030e8e89144302e0b5288dbe6598d68477aea54810a66d214020f4db4feab995
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2c3c331b32cf9eee97259835d2683ea1573f05fbad01a3ee64694a5d98625d5
+oid sha256:ec8b22e20a5e8c40f7042842aa23f4e92bebbc0b3645c9e9f226b68374e33e78
 size 5560