New model from https://wandb.ai/wandb/huggingtweets/runs/2kpz1912

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/commentiquette/1627081499240/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -42,20 +42,20 @@ The model was trained on tweets from Comment Etiquette.
 
 | Data | Comment Etiquette |
 | --- | --- |
-| Tweets downloaded | 3235 |
-| Retweets | 229 |
-| Short tweets | 362 |
-| Tweets kept | 2644 |
+| Tweets downloaded | 3203 |
+| Retweets | 232 |
+| Short tweets | 359 |
+| Tweets kept | 2612 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1n6onjv4/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2oqoo5dz/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 
 ## Training procedure
 
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @commentiquette's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/8k1wh00e) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2kpz1912) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/8k1wh00e/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2kpz1912/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -36,7 +36,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.0",
+  "transformers_version": "4.9.2",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359e9b19477292eba401af5afc1193b19531580368b468aedd487f3ec883812a
+oid sha256:0a2465f1ef62669fc5cbe8724d630ac9720d40b7ad8ba2b623fa4fa01538c962
 size 510403817

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466c295e408af9062ef2e37de441436afa5bf6ae05f855bab20051d816124625
+oid sha256:73c2a0fae436f57addfaf1de313f9664d635f6c81c59cc50db78f43e6c31ffee
 size 2671