New model from https://wandb.ai/wandb/huggingtweets/runs/10czim3i

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/foxnews/1629574796027/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -10,7 +10,7 @@ widget:
 <div class="inline-flex flex-col" style="line-height: 1.5;">
     <div class="flex">
         <div
-			style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://pbs.twimg.com/profile_images/918480715158716419/4X8oCbge_400x400.jpg&#39;)">
+			style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://pbs.twimg.com/profile_images/1459143267673677853/xtIvtfZp_400x400.jpg&#39;)">
         </div>
         <div
             style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">
@@ -43,19 +43,19 @@ The model was trained on tweets from Fox News.
 | Data | Fox News |
 | --- | --- |
 | Tweets downloaded | 3250 |
-| Retweets | 17 |
-| Short tweets | 5 |
-| Tweets kept | 3228 |
+| Retweets | 84 |
+| Short tweets | 0 |
+| Tweets kept | 3166 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1vjlmqz6/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/3gz4o7tf/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 @foxnews's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2dipn7wd) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/10czim3i) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2dipn7wd/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/10czim3i/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -8,7 +8,6 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -18,7 +17,9 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -36,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
+  "transformers_version": "4.17.0",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb8126134b7720a139c40b6643d3159d9e8ba93d5f99e41f2969b090fb9f4b7
-size 510403817
+oid sha256:23946788830b63f55a5fbf715fbb112d89753f1237437b91bfd27eb198ac5c08
+size 510404393

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de0f0be497e35ee49b93e7afdeb99735e6bf5e80078fe385e44977457d7aad4
-size 2671
+oid sha256:2f0c24c386d2621b2f3d7dbc7ca70a5e0d7b959b83004e10e9e282f92e0dae0c
+size 2991