Training in progress, step 99000

README.md

@@ -44,7 +44,7 @@ More information needed
 
 # Resource Usage Comparison
 
-- VRAM Use: 7.4167 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=5, loss_fn=raw_mse, layer_mapper=layer-2, 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, projector=orthogonal))
 ```
 
 # Hyperparameters
@@ -101,9 +101,9 @@ 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, 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, projector=orthogonal))`
 - train_embeddings: `True`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f350ddbc700>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f57c9a3ea10>`
 - 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 2.18.0
+- 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=None, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725152625.e3f806ea38c9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3af1340ecad1f29e55c81b7065db034d2dc61f8ca9f53f89a3a810d8e9c1f641
-size 253
+oid sha256:c32dc5926638a3ede5a171d8b6e6d98a5bfd89f9c2c644d67b4929da341392d1
+size 529

logs/attn_norm=rmsnorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725152766.e3f806ea38c9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6cd6cfef7c29c9721d7efa5cd60bf29298647ad20377278a7d3e7eb35ef0f7c
+size 47486050

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9737b6a94e355ba067f2db8bfada27d0f622c9af7dcc80055245a9c1a2ae7ac4
+oid sha256:363bb36cfeee39dc5404e2642d29bc23d9c67a635c0db6e9b7417e7cbec3b497
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45ff7ce8dcb76616ef8e8eb497a0df0162702fc45c878b595fd1474753012e15
+oid sha256:cae73e29762f617bdb9fa139016c8068dd595abe8212755c4225cd860c968669
 size 5560