huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/scriptonite
+tags:
+- huggingartists
+- lyrics
+- lm-head
+- causal-lm
+widget:
+- text: "I am"
+---
+
+<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/411d50392aef867fe0e9dd55a074ecfb.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">Скриптонит (Scriptonite)</div>
+    <a href="https://genius.com/artists/scriptonite">
+    	<div style="text-align: center; font-size: 14px;">@scriptonite</div>
+    </a>
+</div>
+
+I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).
+
+Create your own bot based on your favorite artist with [the demo](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb)!
+
+## How does it work?
+
+To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).
+
+## Training data
+
+The model was trained on lyrics from Скриптонит (Scriptonite).
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/scriptonite).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/scriptonite")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3iyoxg0v/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 Скриптонит (Scriptonite)'s lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/di1clo79) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/di1clo79/artifacts) is logged and versioned.
+
+## How to use
+
+You can use this model directly with a pipeline for text generation:
+
+```python
+from transformers import pipeline
+generator = pipeline('text-generation',
+                     model='huggingartists/scriptonite')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/scriptonite")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/scriptonite")
+```
+
+## Limitations and bias
+
+The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
+
+In addition, the data present in the user's tweets further affects the text generated by the model.
+
+## About
+
+*Built by Aleksey Korshuk*
+
+[![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
+
+[![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

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "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",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 200,
+      "min_length": 100,
+      "temperature": 1.0,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.727362871170044, "eval_runtime": 20.7773, "eval_samples_per_second": 21.369, "eval_steps_per_second": 2.695, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5c46ac5fd3298d2a01f9b7915560bc450f3997bc18b7dada5a182b6fbdeffa
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8246c465fe86028eab455a564decb982d3c8b4cc33c5a236fa65250065f2dfa
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4642ea9beb4bc34749ebce90968edfe32be19e17efd0ba3eb969a39d1b3c9fd3
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361696374a33a1ba4cfa105bbdd0232fc91f20b020d2290b0ed59f96e83efc13
+size 14439

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5643af0d2d309ea9f8d4e15ffbc8ebd3faca59b9cbbd8bf85f08e202e280408b
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +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"}

trainer_state.json

@@ -0,0 +1,390 @@
+{
+  "best_metric": 1.727362871170044,
+  "best_model_checkpoint": "output/scriptonite/checkpoint-306",
+  "epoch": 1.0,
+  "global_step": 306,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013710963595739938,
+      "loss": 2.6067,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001368387818954924,
+      "loss": 2.3107,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00013638815138477438,
+      "loss": 2.1302,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013575893162042516,
+      "loss": 2.1562,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013495278029461931,
+      "loss": 2.0081,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013397182122930294,
+      "loss": 1.9735,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001328186387809415,
+      "loss": 2.0752,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001314962710319808,
+      "loss": 2.0235,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001300082017869573,
+      "loss": 2.0059,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001283583513943447,
+      "loss": 1.8462,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012655106641831695,
+      "loss": 1.8365,
+      "step": 55
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00012459110818763681,
+      "loss": 2.0625,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012248364025183937,
+      "loss": 1.9252,
+      "step": 65
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00012023421477775639,
+      "loss": 1.9528,
+      "step": 70
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011784875792222071,
+      "loss": 1.7558,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011533355421948647,
+      "loss": 1.8522,
+      "step": 80
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011269523002449659,
+      "loss": 1.7714,
+      "step": 85
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000109940736055617,
+      "loss": 1.8545,
+      "step": 90
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001070773290828286,
+      "loss": 1.856,
+      "step": 95
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00010411255280962044,
+      "loss": 1.7938,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001010542179989503,
+      "loss": 1.8907,
+      "step": 105
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.791038189563213e-05,
+      "loss": 1.8999,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.468932699936187e-05,
+      "loss": 1.8537,
+      "step": 115
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.139953924430466e-05,
+      "loss": 1.8283,
+      "step": 120
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.804968564273005e-05,
+      "loss": 1.6966,
+      "step": 125
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.46485914515931e-05,
+      "loss": 1.8649,
+      "step": 130
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.120521692221673e-05,
+      "loss": 1.8703,
+      "step": 135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.772863369432873e-05,
+      "loss": 1.7685,
+      "step": 140
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.422800089664365e-05,
+      "loss": 1.8474,
+      "step": 145
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.071254101695329e-05,
+      "loss": 1.7611,
+      "step": 150
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.719151560529643e-05,
+      "loss": 1.7199,
+      "step": 155
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.367420087421813e-05,
+      "loss": 1.7935,
+      "step": 160
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 6.016986326040062e-05,
+      "loss": 1.7749,
+      "step": 165
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.668773501204858e-05,
+      "loss": 1.8416,
+      "step": 170
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.323698986634498e-05,
+      "loss": 1.7939,
+      "step": 175
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.982671888105512e-05,
+      "loss": 1.6949,
+      "step": 180
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.646590648395145e-05,
+      "loss": 1.7562,
+      "step": 185
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.316340680315709e-05,
+      "loss": 1.6271,
+      "step": 190
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.992792034076668e-05,
+      "loss": 1.713,
+      "step": 195
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.6767971051197685e-05,
+      "loss": 1.7105,
+      "step": 200
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.369188388466058e-05,
+      "loss": 1.7335,
+      "step": 205
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.0707762854909304e-05,
+      "loss": 1.6748,
+      "step": 210
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.7823469689053436e-05,
+      "loss": 1.7346,
+      "step": 215
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.50466031156793e-05,
+      "loss": 1.8197,
+      "step": 220
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.2384478845846175e-05,
+      "loss": 1.6761,
+      "step": 225
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.9844110299697732e-05,
+      "loss": 1.7013,
+      "step": 230
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7432190129464996e-05,
+      "loss": 1.7646,
+      "step": 235
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.5155072587539005e-05,
+      "loss": 1.5319,
+      "step": 240
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3018756786064535e-05,
+      "loss": 1.79,
+      "step": 245
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.1028870892157994e-05,
+      "loss": 1.6705,
+      "step": 250
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.190657300387505e-06,
+      "loss": 1.6285,
+      "step": 255
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.508958821578629e-06,
+      "loss": 1.706,
+      "step": 260
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.988205924331354e-06,
+      "loss": 1.6291,
+      "step": 265
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.6324050628611986e-06,
+      "loss": 1.7411,
+      "step": 270
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.445128121914628e-06,
+      "loss": 1.7647,
+      "step": 275
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.4295030065665785e-06,
+      "loss": 1.7888,
+      "step": 280
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5882054016913933e-06,
+      "loss": 1.6871,
+      "step": 285
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.234517228169584e-07,
+      "loss": 1.7539,
+      "step": 290
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.3699327693326474e-07,
+      "loss": 1.6844,
+      "step": 295
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3011164863877445e-07,
+      "loss": 1.6774,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.6153237799239955e-09,
+      "loss": 1.7028,
+      "step": 305
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.727362871170044,
+      "eval_runtime": 20.8096,
+      "eval_samples_per_second": 21.336,
+      "eval_steps_per_second": 2.691,
+      "step": 306
+    }
+  ],
+  "max_steps": 306,
+  "num_train_epochs": 1,
+  "total_flos": 319560155136000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaaf6708f9300a70cac38b2d9556974db0fe2981edabe48909dbaf43501c3dca
+size 2671