End of training

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: gpt2-medium
 tags:
 - generated_from_trainer
-datasets:
-- piqa
 model-index:
 - name: platistil
   results: []
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # platistil
 
-This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the piqa dataset.
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset.
 
 ## Model description
 
@@ -34,13 +32,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.01
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.25
+- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 3.0
 
 ### Training results

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb9562ebb4eca660bc4028c9fca124a187c84c301e9bbb5bd16ccfef098325f8
+oid sha256:12f56f15a6c7c6db5bae3690e7d1d562aaecc01a49076cbbf21cdcfd2558fe9b
 size 3151856

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d2d6cdb35b79718ff6544b529b6090c2cadb53d585bed5e0c767865bfe4601e
+oid sha256:7aec30b908f8713803bd37cf76f06b0db58fd5199bc91d0e2a3973e0a745a8f0
 size 4091