demo_eli5_clm_model

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.7474
+- Loss: 3.7346
 
 ## Model description
 
@@ -40,15 +40,13 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.8686        | 1.0   | 1150 | 3.7657          |
-| 3.7817        | 2.0   | 2300 | 3.7500          |
-| 3.7358        | 3.0   | 3450 | 3.7474          |
+| 3.6313        | 1.0   | 1142 | 3.7346          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7722e3327a343b560814fb8b7c67d1ccaf42123af7986ecc99fee4aa86aefd53
+oid sha256:60adc694d6b56ee001f91e55cd07b860421d33e06a06e8161019b4a61f5f44cc
 size 327657928

runs/Dec01_00-38-37_3cd6c9115310/events.out.tfevents.1701391120.3cd6c9115310.48.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c545bea163e1cc77400c300eda8075f747c5437b8fad8350b72dbe0eef2ee765
-size 4911
+oid sha256:dcafb0f8b6b6e027a4975c09fc97beeaf6debda2de458ebc84a5885b489be0bf
+size 5536

runs/Dec01_00-38-37_3cd6c9115310/events.out.tfevents.1701391275.3cd6c9115310.48.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0713019f4a2914546ebca427372434e2b402ba4ba06fc3619bf2ef4454a131
+size 359