New model from https://wandb.ai/wandb/huggingtweets/runs/3laoj52a

README.md

@@ -43,19 +43,19 @@ The model was trained on tweets from Anglio.S🟠L (33.3%).
 | Data | Anglio.S🟠L (33.3%) |
 | --- | --- |
 | Tweets downloaded | 3213 |
-| Retweets | 636 |
-| Short tweets | 558 |
-| Tweets kept | 2019 |
+| Retweets | 634 |
+| Short tweets | 562 |
+| Tweets kept | 2017 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2mp6lvkf/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/2g8dyjwv/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 @cryptoanglio's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1rr7jwwv) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3laoj52a) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1rr7jwwv/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3laoj52a/artifacts) is logged and versioned.
 
 ## How to use
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc261a03ef41c7e3d21d7d98d5acca524787a4d6213336fdd08a2f344e6ace77
+oid sha256:9b5c5c4646e77a6b45b56b9f1ffe67237001c63e3002f2780c2872d39ffe5bc0
 size 510396521

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30758ad8ade973ef547578ffa912d30d8bd4c81591b7ed1a809580605beada37
+oid sha256:c46a1e1ddcfb5ad64306b5bb94b295bc7beb0967d517d1d000f3b8a8a1c60a98
 size 3375