End of training

README.md

@@ -1,7 +1,7 @@
 ---
+base_model: austindavis/gpt2-lichess-uci-2016-01_11
 tags:
 - generated_from_trainer
-base_model: austindavis/gpt2-lichess-uci-2016-01_11
 model-index:
 - name: gpt2-lichess-uci-201302b
   results: []
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [austindavis/gpt2-lichess-uci-2016-01_11](https://huggingface.co/austindavis/gpt2-lichess-uci-2016-01_11) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0589
+- Loss: 1.0454
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.002
-- train_batch_size: 32
+- train_batch_size: 20
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5d4fb396a7e86927010d628646c0739b49a8509b35b52441dc25ca94f062dc
+oid sha256:407554007c97352e45fd4bb5be0978d5ffebdcd57595dc842293b2d21b489e0a
 size 102086376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c020cfe11a5201d0589dd585e930504240a8ca6a443c04837f506d96f9c075d5
+oid sha256:f899e3f6a872496484caba85851d40a2e0fa957d5b4af9f3e189a0d67b0bb558
 size 4984