Training in progress, step 61875

README.md

@@ -76,7 +76,7 @@ Trained on 145,744,973 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=25.0, loss_fn=raw_mse, layer_mapper=layer-2, projector=orthogonal))
+DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=25.0, loss_fn=cos, layer_mapper=layer-2, projector=orthogonal_layernorm))
 ```
 
 # Hyperparameters
@@ -93,9 +93,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: `cosine_with_min_lr`
 - lr_scheduler_warmup_ratio: `0.5`
 - 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=25.0, loss_fn=raw_mse, layer_mapper=layer-2, projector=orthogonal))`
+- distillation_objective: `DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=25.0, loss_fn=cos, layer_mapper=layer-2, projector=orthogonal_layernorm))`
 - train_embeddings: `True`
-- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f4fc8470190>`
+- lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x74d6cdb48550>`
 - student_model_name_or_path: `None`
 - student_config_name_or_path: `None`
 - student_model_config: `None`
@@ -114,7 +114,7 @@ The following hyperparameters were used during training:
 - dataset_test_size: `0.01`
 - gradient_accumulation_steps: `1`
 - weight_decay: `0.0`
-- max_grad_norm: `1.0`
+- max_grad_norm: `100`
 - warmup_ratio: `0.5`
 - warmup_steps: `0`
 - gradient_checkpointing: `True`
@@ -124,7 +124,7 @@ The following hyperparameters were used during training:
 
 
 # Framework Versions
-- Distily 0.4.1
-- Transformers 4.44.1
-- Pytorch 2.4.0+cu121
+- Distily 0.4.0
+- Transformers 4.44.2
+- Pytorch 2.3.0
 - Datasets 2.21.0

config.json

@@ -33,7 +33,7 @@
     }
   },
   "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_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm, max_grad_norm=100/events.out.tfevents.1724930717.d9703cfffc0c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd7c552177e5802941433d0f57124856f192ce8160f949ff8e2f84f4cb19a93
+size 29625389

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3492be38be60ffdc199b2730ab26e1fbb85587be7def2a396266a44684540b6
+oid sha256:2f45e140f24ab4ec8ec43779dc3e5642a64343b8b71aaae9f540a785da606968
 size 248894656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd9b97d544c6e4a7a7a5003714aa22d93e27ce4e3093e82f96023aba158f11ac
-size 5496
+oid sha256:1123657440e4634df04932c55b3109839fc67e1a52dfb99e7cf32cfee9d0f786
+size 5560