gpt2_bwgenerator

README.md

@@ -4,14 +4,14 @@ base_model: openai-community/gpt2
 tags:
 - generated_from_trainer
 model-index:
-- name: gpt2-finetuned
+- name: gpt2_bwgenerator
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# gpt2-finetuned
+# gpt2_bwgenerator
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
 
@@ -38,8 +38,7 @@ 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
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 

config.json

@@ -32,7 +32,7 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.42.0.dev0",
   "use_cache": true,
   "vocab_size": 50258

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d47720955693a8006f3fb4a614b6c5ac21894eab26b1618c2158d0d254e1ad0a
-size 497777280
+oid sha256:4d2951df980ef51ab7c9ac0765112871807d3538d40281c7f09333e753062d45
+size 248896048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864c6c7e732ee9623503b585739c99b2135bd7ed8b1bdb318e52386d3a292763
+oid sha256:50dddb2f085de66931e96026fa36c7b73a52550b4049970d16712afcdcda2a83
 size 5240