huggingartists

README.md

@@ -14,11 +14,11 @@ widget:
 <div class="inline-flex flex-col" style="line-height: 1.5;">
     <div class="flex">
         <div
-			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/df75ede64ffcf049727bfbb01d323081.400x400x1.jpg&#39;)">
+			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/1edcea93261e2e266c532ce204ba92da.1000x1000x1.jpg&#39;)">
         </div>
     </div>
     <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
-    <div style="text-align: center; font-size: 16px; font-weight: 800">The Beatles</div>
+    <div style="text-align: center; font-size: 16px; font-weight: 800">MORGENSHTERN</div>
     <a href="https://genius.com/artists/morgenshtern">
     	<div style="text-align: center; font-size: 14px;">@morgenshtern</div>
     </a>
@@ -34,7 +34,7 @@ To understand how the model was developed, check the [W&B report](https://wandb.
 
 ## Training data
 
-The model was trained on lyrics from The Beatles.
+The model was trained on lyrics from MORGENSHTERN.
 
 Dataset is available [here](https://huggingface.co/datasets/huggingartists/morgenshtern).
 And can be used with:
@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/morgenshtern")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/36ru50a4/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/huggingartists/huggingartists/runs/3of8bax2/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 The Beatles's lyrics.
+The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on MORGENSHTERN's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1k6lslqs) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/29va0sby) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1k6lslqs/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/29va0sby/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
+  "transformers_version": "4.10.0",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.546966552734375, "eval_runtime": 6.4283, "eval_samples_per_second": 22.556, "eval_steps_per_second": 2.956, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d11136176323aafb2ef75f5525ef66852770716f4ced58db73503e0a7484137
+oid sha256:a828940fd9988b72532dc4a17c18b562f948e61d3a0c8b6be9e117dee381362e
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df0396891551f1f573ada519077a8bf740ef79c72b09df5bc47b336bcfae1a01
-size 995603825
+oid sha256:aa430dc03f846a18abdb51d16edff75c0f3552a1f8035dae856393612fde1f9a
+size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14245ab76b0bcb59d2619dfecebb00c58ba368ba92e4979db4a5e50454a3f65d
+oid sha256:c2264a9b234d1b11adb7339ea59e58dad473cf0dc99c0f1d311469e6ce8e50fe
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec18bd090ee79f7be43632d1d02335edd519ec6f49a3a61a5f244bf515bf8da
+oid sha256:5dbad4e46f0b23a7fbe31e6a10224311e7ec288f4ef415ae360dec29f4e7661a
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cae94fe29647f1ab9ebfc3069e27ada487df598ed599d7fbb4182e85d06b41b1
+oid sha256:340c51ed8fb1370066103a87c329a9f9d39d9f589b8a9a525ff69c489da5b8e5
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "global_step": 232,
+  "best_metric": 1.546966552734375,
+  "best_model_checkpoint": "output/morgenshtern/checkpoint-294",
+  "epoch": 3.0,
+  "global_step": 294,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,11 +322,91 @@
       "learning_rate": 0.0001370993921901871,
       "loss": 1.7228,
       "step": 230
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 9.021642375642038e-05,
+      "loss": 1.6079,
+      "step": 235
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.954855279928984e-05,
+      "loss": 1.6691,
+      "step": 240
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.860000000000001e-05,
+      "loss": 1.7047,
+      "step": 245
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 5.765144720071019e-05,
+      "loss": 1.6921,
+      "step": 250
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.698357624357961e-05,
+      "loss": 1.5894,
+      "step": 255
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.686987328947878e-05,
+      "loss": 1.6388,
+      "step": 260
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.7569617608302645e-05,
+      "loss": 1.6748,
+      "step": 265
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.932123458329584e-05,
+      "loss": 1.6765,
+      "step": 270
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.233618333464885e-05,
+      "loss": 1.6658,
+      "step": 275
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 6.793535661894062e-06,
+      "loss": 1.5677,
+      "step": 280
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.8353852816850843e-06,
+      "loss": 1.6118,
+      "step": 285
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.632050517253132e-07,
+      "loss": 1.552,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.546966552734375,
+      "eval_runtime": 6.307,
+      "eval_samples_per_second": 22.99,
+      "eval_steps_per_second": 3.013,
+      "step": 294
     }
   ],
-  "max_steps": 232,
-  "num_train_epochs": 2,
-  "total_flos": 241695129600000.0,
+  "max_steps": 294,
+  "num_train_epochs": 3,
+  "total_flos": 306103615488000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f7789495a48c9ed1372c3a20ff68e3fd471ceffc8c79810dc223ac2f95c6ed
+oid sha256:eda2c3fc1a169357c5ab29108c2671d35b5d8c42cbde93e4b348dab2cf8667ff
 size 2671