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/22e752c5e4e7e4d2e8488babffb33bbf.1000x1000x1.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/e308b1bc9eeb159ecfa9d807d715f095.1000x1000x1.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">MORGENSHTERN</div>
+    <div style="text-align: center; font-size: 16px; font-weight: 800">SLAVA MARLOW</div>
     <a href="https://genius.com/artists/slava-marlow">
     	<div style="text-align: center; font-size: 14px;">@slava-marlow</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 MORGENSHTERN.
+The model was trained on lyrics from SLAVA MARLOW.
 
 Dataset is available [here](https://huggingface.co/datasets/huggingartists/slava-marlow).
 And can be used with:
@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/slava-marlow")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3sgmpuhy/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/dajo6l0v/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 MORGENSHTERN's lyrics.
+The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on SLAVA MARLOW's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/omn4wgyz) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1djy4mi8) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/omn4wgyz/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1djy4mi8/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
+  "transformers_version": "4.11.3",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.5765409469604492, "eval_runtime": 8.007, "eval_samples_per_second": 21.232, "eval_steps_per_second": 2.748, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1b2b8983b832ed22b122c66ed7bf7c9ff715a4eb640f438af09f67c85dcdb3
+oid sha256:0f31f81a0ff5da76be1d7744122ddaa1d4c33c954bdadcae9976300407273a91
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d52890222d19bf8524cb84e4a332cd839ef36dc1eac420a410a07722ca8431
+oid sha256:e61f1c361c857b02d5d0830f1edf1460b1f7dab9003211a02897fe30b5bd91d1
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbce2307bb9b496425c8f71076a4a1c33b5a768103d6507e3eacaf6b99edcf0
+oid sha256:1fc237e81048121824c38df56404ddd7899a39fab731a11c12988aa8ebd5164c
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c058b8fa70d384486107f733302e1b72d74991a369b69e1c49457273f7c177
+oid sha256:5960c90ad81f7699bd122a5bfa6732fd3b57d2883f4ba4ed0d4dd0a79b0596f4
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be7b21ee2235eef38a55c0348c96600344a2bc81677cfa58e757a83abbb30f2
+oid sha256:8267538b8f71047573a2bf4b20b591f7a175ff510694f359e666cbbd6a22e8c0
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "global_step": 260,
+  "best_metric": 1.5765409469604492,
+  "best_model_checkpoint": "output/slava-marlow/checkpoint-327",
+  "epoch": 3.0,
+  "global_step": 327,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -318,11 +318,97 @@
       "learning_rate": 0.0001372,
       "loss": 1.7608,
       "step": 260
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 8.331367795957333e-05,
+      "loss": 1.7155,
+      "step": 265
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.353868846414889e-05,
+      "loss": 1.6697,
+      "step": 270
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 6.366131153585115e-05,
+      "loss": 1.5567,
+      "step": 275
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 5.3886322040426775e-05,
+      "loss": 1.5568,
+      "step": 280
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.441637217755689e-05,
+      "loss": 1.678,
+      "step": 285
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 3.544779015521354e-05,
+      "loss": 1.5895,
+      "step": 290
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.716650997114681e-05,
+      "loss": 1.6833,
+      "step": 295
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.9744216684073583e-05,
+      "loss": 1.5874,
+      "step": 300
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.333478708966784e-05,
+      "loss": 1.5961,
+      "step": 305
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.071099592209943e-06,
+      "loss": 1.6268,
+      "step": 310
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 4.062279408693099e-06,
+      "loss": 1.5704,
+      "step": 315
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.3914362170045804e-06,
+      "loss": 1.5144,
+      "step": 320
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.139411505919223e-07,
+      "loss": 1.753,
+      "step": 325
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.5765409469604492,
+      "eval_runtime": 8.0085,
+      "eval_samples_per_second": 21.227,
+      "eval_steps_per_second": 2.747,
+      "step": 327
     }
   ],
-  "max_steps": 260,
-  "num_train_epochs": 2,
-  "total_flos": 271221129216000.0,
+  "max_steps": 327,
+  "num_train_epochs": 3,
+  "total_flos": 340594163712000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5906cf86decfa153fcf84533fd92086ce9d1eb8f6ff2a692ce1232bc92d20c5
-size 2671
+oid sha256:d77fa0328ab599e88846dcdcfe668efcd1424c4a8c70e39af87fe4768ee0b599
+size 2863