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/e308b1bc9eeb159ecfa9d807d715f095.1000x1000x1.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/22e752c5e4e7e4d2e8488babffb33bbf.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">SLAVA MARLOW</div>
+    <div style="text-align: center; font-size: 16px; font-weight: 800">MORGENSHTERN</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 SLAVA MARLOW.
+The model was trained on lyrics from MORGENSHTERN.
 
 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/2poqm17q/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/3sgmpuhy/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 SLAVA MARLOW'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/2panzd8n) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/omn4wgyz) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2panzd8n/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/omn4wgyz/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/slava-marlow",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003784fb2a244bf7e21fdbbdc3a834eb3efaafb776212f5cf93ec828dbb17488
+oid sha256:df1b2b8983b832ed22b122c66ed7bf7c9ff715a4eb640f438af09f67c85dcdb3
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d66da2b88a6bf8081f372db1fa0c2cf5cd172181d51df70e580d5f4187cb31c9
-size 995603825
+oid sha256:96d52890222d19bf8524cb84e4a332cd839ef36dc1eac420a410a07722ca8431
+size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98afaa2f1ee5ccee595508e8f6e51413def19a720991b4505d84e97c9d97f5d7
+oid sha256:4dbce2307bb9b496425c8f71076a4a1c33b5a768103d6507e3eacaf6b99edcf0
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc586ea7da20fdcf00ff0887d22ffce1b92144c78c437772b896f540b1d1ffe
-size 14567
+oid sha256:13c058b8fa70d384486107f733302e1b72d74991a369b69e1c49457273f7c177
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544ea5472f84fc475d9eea4362936fe8523ee24e1f075c1fe1aa245108e95828
+oid sha256:3be7b21ee2235eef38a55c0348c96600344a2bc81677cfa58e757a83abbb30f2
 size 623

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/slava-marlow", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "global_step": 130,
+  "epoch": 2.0,
+  "global_step": 260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -162,11 +162,167 @@
       "learning_rate": 0.0,
       "loss": 1.8023,
       "step": 130
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 5.001712368734975e-07,
+      "loss": 1.7351,
+      "step": 135
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.9933913245728244e-06,
+      "loss": 1.7454,
+      "step": 140
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.457885751780542e-06,
+      "loss": 1.9051,
+      "step": 145
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.857716640189785e-06,
+      "loss": 1.818,
+      "step": 150
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.2143306799695167e-05,
+      "loss": 1.707,
+      "step": 155
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.7252162675462473e-05,
+      "loss": 1.7507,
+      "step": 160
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.3109785644681427e-05,
+      "loss": 1.8168,
+      "step": 165
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.9630758374242703e-05,
+      "loss": 1.7313,
+      "step": 170
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 3.671999039779749e-05,
+      "loss": 1.6952,
+      "step": 175
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.427410474888204e-05,
+      "loss": 1.7249,
+      "step": 180
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.218294542987354e-05,
+      "loss": 1.6855,
+      "step": 185
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 6.03311837344848e-05,
+      "loss": 1.5632,
+      "step": 190
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 6.859999999999999e-05,
+      "loss": 1.7108,
+      "step": 195
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.686881626551516e-05,
+      "loss": 1.816,
+      "step": 200
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.501705457012643e-05,
+      "loss": 1.8067,
+      "step": 205
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.292589525111794e-05,
+      "loss": 1.7471,
+      "step": 210
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00010048000960220248,
+      "loss": 1.8035,
+      "step": 215
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00010756924162575728,
+      "loss": 1.7207,
+      "step": 220
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00011409021435531856,
+      "loss": 1.7529,
+      "step": 225
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0001199478373245375,
+      "loss": 1.7625,
+      "step": 230
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00012505669320030482,
+      "loss": 1.7044,
+      "step": 235
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0001293422833598102,
+      "loss": 1.6402,
+      "step": 240
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013274211424821946,
+      "loss": 1.7453,
+      "step": 245
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00013520660867542716,
+      "loss": 1.7462,
+      "step": 250
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00013669982876312649,
+      "loss": 1.7852,
+      "step": 255
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.7608,
+      "step": 260
     }
   ],
-  "max_steps": 130,
-  "num_train_epochs": 1,
-  "total_flos": 135610564608000.0,
+  "max_steps": 260,
+  "num_train_epochs": 2,
+  "total_flos": 271221129216000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:663a0823886f0f29fbe2b3eb1a51d774e2a897437f6b1d5c0c410531a33384eb
+oid sha256:f5906cf86decfa153fcf84533fd92086ce9d1eb8f6ff2a692ce1232bc92d20c5
 size 2671