End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.8305
+- Loss: 5.4593
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0005
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
@@ -47,16 +47,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 6.4795        | 0.94  | 500  | 6.1043          |
-| 5.3968        | 1.87  | 1000 | 5.7712          |
-| 4.7369        | 2.81  | 1500 | 5.6812          |
-| 4.1696        | 3.75  | 2000 | 5.7365          |
-| 3.6165        | 4.68  | 2500 | 5.8735          |
-| 3.098         | 5.62  | 3000 | 6.0607          |
-| 2.595         | 6.55  | 3500 | 6.3035          |
-| 2.1458        | 7.49  | 4000 | 6.5112          |
-| 1.7782        | 8.43  | 4500 | 6.7049          |
-| 1.5026        | 9.36  | 5000 | 6.8305          |
+| 6.5045        | 1.17  | 500  | 6.1462          |
+| 5.5972        | 2.35  | 1000 | 5.7812          |
+| 5.1108        | 3.52  | 1500 | 5.6020          |
+| 4.7389        | 4.69  | 2000 | 5.4971          |
+| 4.4098        | 5.87  | 2500 | 5.4530          |
+| 4.1016        | 7.04  | 3000 | 5.4385          |
+| 3.8119        | 8.22  | 3500 | 5.4539          |
+| 3.5917        | 9.39  | 4000 | 5.4593          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333f300ba3b1ec0e899de7e7cff2719ba64cea68d9a31749c24d7fad6cc20d53
+oid sha256:fa01c4ab463c41ea0581d8efe8ad6fc49dc764694409fa3f4e328c9b10471728
 size 497783424

runs/Feb10_02-02-48_nlp-gpu-01.be.ucsc.edu/events.out.tfevents.1707559369.nlp-gpu-01.be.ucsc.edu.93660.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d113b27da60e709f27322aad82b1e47559495023cbe7f545151b62c4802a219
-size 7880
+oid sha256:20822a187079c1e30055316c4ff6556915920f4871d94e763f1306e0066ce9b0
+size 8234