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/df75ede64ffcf049727bfbb01d323081.400x400x1.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">The Beatles</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 MORGENSHTERN.
+The model was trained on lyrics from The Beatles.
 
 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/3q6pnb0j/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/36ru50a4/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 The Beatles's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2ury2mhk) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1k6lslqs) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2ury2mhk/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1k6lslqs/artifacts) is logged and versioned.
 
 ## How to use
 
@@ -90,6 +90,8 @@ In addition, the data present in the user's tweets further affects the text gene
 
 [![Follow](https://img.shields.io/twitter/follow/alekseykorshuk?style=social)](https://twitter.com/intent/follow?screen_name=alekseykorshuk)
 
+[![Follow](https://img.shields.io/badge/dynamic/json?color=blue&label=Telegram%20Channel&query=%24.result&url=https%3A%2F%2Fapi.telegram.org%2Fbot1929545866%3AAAFGhV-KKnegEcLiyYJxsc4zV6C-bdPEBtQ%2FgetChatMemberCount%3Fchat_id%3D-1001253621662&style=social&logo=telegram)](https://t.me/joinchat/_CQ04KjcJ-4yZTky)
+
 For more details, visit the project repository.
 
 [![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/morgenshtern",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.1",
+  "transformers_version": "4.9.2",
   "use_cache": true,
   "vocab_size": 50257
 }

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31606b5df45658b03ce97110b2fb5cd44b16f8c126a0aeca7a01cf0645b9696f
+oid sha256:3d11136176323aafb2ef75f5525ef66852770716f4ced58db73503e0a7484137
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e1d282a1d71170062ecdb062d5c638852f43c3cd839ff61cacc44240716c313
+oid sha256:df0396891551f1f573ada519077a8bf740ef79c72b09df5bc47b336bcfae1a01
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be973f06905cedc248ba31c9027bfb7bed7f5330cc8eea151a16663cb260a5f
+oid sha256:14245ab76b0bcb59d2619dfecebb00c58ba368ba92e4979db4a5e50454a3f65d
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1a77f16b5380cb9f8dfa41c789f6f7b0d5f10d7040476401f9a011e850af2a4
-size 14503
+oid sha256:aec18bd090ee79f7be43632d1d02335edd519ec6f49a3a61a5f244bf515bf8da
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc8c181f3eeffc22bed5df763ebe76f1c0ce2ad567f243d6703ceaa6e371773
+oid sha256:cae94fe29647f1ab9ebfc3069e27ada487df598ed599d7fbb4182e85d06b41b1
 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/morgenshtern", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "global_step": 102,
+  "epoch": 2.0,
+  "global_step": 232,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,11 +166,167 @@
       "eval_samples_per_second": 40.618,
       "eval_steps_per_second": 5.077,
       "step": 100
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.0216830127274476e-06,
+      "loss": 1.8376,
+      "step": 105
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.037005536513067e-07,
+      "loss": 1.7024,
+      "step": 110
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.515656508272057e-08,
+      "loss": 1.7911,
+      "step": 115
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.0213613921093164e-07,
+      "loss": 1.8512,
+      "step": 120
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.0277372298297e-06,
+      "loss": 1.7573,
+      "step": 125
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.8721970205680935e-06,
+      "loss": 1.7902,
+      "step": 130
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.88343684654658e-06,
+      "loss": 1.7602,
+      "step": 135
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3988015692592823e-05,
+      "loss": 1.8606,
+      "step": 140
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.009247481060283e-05,
+      "loss": 1.6102,
+      "step": 145
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.708504883770769e-05,
+      "loss": 1.8574,
+      "step": 150
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.483771208671411e-05,
+      "loss": 1.6927,
+      "step": 155
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.320852254368187e-05,
+      "loss": 1.7203,
+      "step": 160
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.204422065684016e-05,
+      "loss": 1.8592,
+      "step": 165
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 6.118303533611755e-05,
+      "loss": 1.7338,
+      "step": 170
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.045764578878282e-05,
+      "loss": 1.7386,
+      "step": 175
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 7.969824496351964e-05,
+      "loss": 1.6874,
+      "step": 180
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.873564851492995e-05,
+      "loss": 1.8691,
+      "step": 185
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.740439236703416e-05,
+      "loss": 1.7808,
+      "step": 190
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00010554576216307802,
+      "loss": 1.8296,
+      "step": 195
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00011301069913603334,
+      "loss": 1.737,
+      "step": 200
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0001196625291967717,
+      "loss": 1.8,
+      "step": 205
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00012537946527356269,
+      "loss": 1.6787,
+      "step": 210
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.000130056837088046,
+      "loss": 1.664,
+      "step": 215
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00013360900754314024,
+      "loss": 1.5839,
+      "step": 220
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.0001359709406361119,
+      "loss": 1.8525,
+      "step": 225
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.0001370993921901871,
+      "loss": 1.7228,
+      "step": 230
     }
   ],
-  "max_steps": 102,
-  "num_train_epochs": 1,
-  "total_flos": 106345857024000.0,
+  "max_steps": 232,
+  "num_train_epochs": 2,
+  "total_flos": 241695129600000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f915a601b161294d09f0795c26c67c9dddff75c8768bf2451d5a65f6c1dd3a2
+oid sha256:e3f7789495a48c9ed1372c3a20ff68e3fd471ceffc8c79810dc223ac2f95c6ed
 size 2671