Training in progress, step 500

README.md

@@ -22,7 +22,7 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-This is an initial example of knowledge-distillation where the student loss is all cross-entropy loss \\(L_{CE}\\) of the ground-truth labels and none of the knowledge-distillation loss \\(L_{KD}\\).
+More information needed
 
 ## Intended uses & limitations
 
@@ -30,24 +30,20 @@ More information needed
 
 ## Training and evaluation data
 
-The training and evaluation data come straight from the `train` and `validation` splits in the clinc_oos dataset, respectively; and tokenized using the `distilbert-base-uncased` tokenization.
+More information needed
 
 ## Training procedure
 
-Please see page 224 in Chapter 8: Making Transformers Efficient in Production, Natural Language Processing with Transformers, May 2022.
-
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- num_epochs: 5
-- alpha: 1.0
-- temperature: 2.0
 - learning_rate: 2e-05
 - train_batch_size: 48
 - eval_batch_size: 48
 - seed: 8675309
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 5
 
 ### Training results
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:540cb48d6d62dda4135d99db3551cd60c2824b946892a637963f17de79b49ec3
+oid sha256:208843035a3b09138fb71fc845ece8a1a84870cb2a502ebcab325b8a9907edc6
 size 268290900

runs/Feb02_10-53-18_t4-us-west4-b-n1-standard-16/events.out.tfevents.1706871652.t4-us-west4-b-n1-standard-16.61276.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1659849339e1b8dd89f339072d5f0d5816b6f0efbfacef2cf05305d9171d5f4d
+size 12392

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d5c73c5b2b063d57a3a6212851ee24bce4ce3f312e4de923d67a3f3a6d3827
+oid sha256:7bcd0fc1b80966e4b4ea6d9978efc0e8af8797b7806c4de48be52cb7109b5ef0
 size 4792