huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/grimes
+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/8dd2a89218346f6bdb326bf84cd9eb49.1000x1000x1.png&#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">Grimes</div>
+    <a href="https://genius.com/artists/grimes">
+    	<div style="text-align: center; font-size: 14px;">@grimes</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 Grimes.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/grimes).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/grimes")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3796ng30/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 Grimes's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/ourv0tjj) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/ourv0tjj/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/grimes')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/grimes")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/grimes")
+```
+
+## 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": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 2.3570337295532227, "eval_runtime": 1.5602, "eval_samples_per_second": 20.511, "eval_steps_per_second": 2.564, "epoch": 10.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa7a10b4616c6bb25095f5a6e6df472447309246c8137f5ba1d49f576f04c7b
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e2b33b0f4171ffd2deb0bc2a7a40fae42a0d7cba94c5ddf1fe05c722e79cdd
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e604579401dd96dece08c5a340e43a66ab68025cccbf2f52a44c445fb451aad1
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ac62fc33ec98b1c486420a3b8565fbb4779f350d60d80fcc0b1802972c47f9
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744fcc656fe1f449c2ea79ccccba224c3e3c1abb31179e9ce51f592461ac2c71
+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 +1,278 @@
+{
+  "best_metric": 2.3570337295532227,
+  "best_model_checkpoint": "output/grimes/checkpoint-168",
+  "epoch": 8.0,
+  "global_step": 168,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011888735840752609,
+      "loss": 2.8697,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.372648442002871e-05,
+      "loss": 2.7244,
+      "step": 10
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 2.5533,
+      "step": 15
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.662053209561833e-07,
+      "loss": 2.4558,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.552718162536621,
+      "eval_runtime": 1.4059,
+      "eval_samples_per_second": 22.762,
+      "eval_steps_per_second": 2.845,
+      "step": 21
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.1920020081922749e-05,
+      "loss": 2.436,
+      "step": 25
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.333506393059682e-05,
+      "loss": 2.4972,
+      "step": 30
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 2.1316,
+      "step": 35
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00013415229447692924,
+      "loss": 2.3666,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.45241641998291,
+      "eval_runtime": 1.4175,
+      "eval_samples_per_second": 22.575,
+      "eval_steps_per_second": 2.822,
+      "step": 42
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00013040646433810595,
+      "loss": 2.2004,
+      "step": 45
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 9.36623942715347e-05,
+      "loss": 2.2352,
+      "step": 50
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 4.3537605728465284e-05,
+      "loss": 1.9823,
+      "step": 55
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 6.793535661894062e-06,
+      "loss": 2.0814,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.412614583969116,
+      "eval_runtime": 1.4325,
+      "eval_samples_per_second": 22.338,
+      "eval_steps_per_second": 2.792,
+      "step": 63
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 3.047705523070765e-06,
+      "loss": 1.9043,
+      "step": 65
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.4300000000000014e-05,
+      "loss": 2.0794,
+      "step": 70
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 8.386493606940314e-05,
+      "loss": 1.767,
+      "step": 75
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.00012527997991807721,
+      "loss": 2.0631,
+      "step": 80
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.377373456954956,
+      "eval_runtime": 1.4484,
+      "eval_samples_per_second": 22.093,
+      "eval_steps_per_second": 2.762,
+      "step": 84
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 0.00013643379467904383,
+      "loss": 2.0061,
+      "step": 85
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.00011137140040750914,
+      "loss": 1.6506,
+      "step": 90
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 6.347351557997137e-05,
+      "loss": 1.9202,
+      "step": 95
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 1.8312641592473912e-05,
+      "loss": 1.9009,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 1.7547,
+      "step": 105
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.376068592071533,
+      "eval_runtime": 1.4234,
+      "eval_samples_per_second": 22.481,
+      "eval_steps_per_second": 2.81,
+      "step": 105
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 1.8312641592473936e-05,
+      "loss": 1.6331,
+      "step": 110
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 6.347351557997117e-05,
+      "loss": 1.7732,
+      "step": 115
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00011137140040750908,
+      "loss": 1.7347,
+      "step": 120
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 0.00013643379467904383,
+      "loss": 1.5963,
+      "step": 125
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.3798959255218506,
+      "eval_runtime": 1.4389,
+      "eval_samples_per_second": 22.239,
+      "eval_steps_per_second": 2.78,
+      "step": 126
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 0.0001252799799180772,
+      "loss": 1.5787,
+      "step": 130
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 8.386493606940322e-05,
+      "loss": 1.3787,
+      "step": 135
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 3.429999999999998e-05,
+      "loss": 1.4709,
+      "step": 140
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 3.0477055230707115e-06,
+      "loss": 1.7318,
+      "step": 145
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.3730082511901855,
+      "eval_runtime": 1.4477,
+      "eval_samples_per_second": 22.104,
+      "eval_steps_per_second": 2.763,
+      "step": 147
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 6.793535661894024e-06,
+      "loss": 1.4261,
+      "step": 150
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 4.353760572846532e-05,
+      "loss": 1.2714,
+      "step": 155
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 9.366239427153457e-05,
+      "loss": 1.3748,
+      "step": 160
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 0.00013040646433810593,
+      "loss": 1.5499,
+      "step": 165
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.3570337295532227,
+      "eval_runtime": 1.4478,
+      "eval_samples_per_second": 22.102,
+      "eval_steps_per_second": 2.763,
+      "step": 168
+    }
+  ],
+  "max_steps": 210,
+  "num_train_epochs": 10,
+  "total_flos": 175588245504000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa109cb8608765a0746aef97b10ee403703c8243a3711c142b84ef899083f2cc
+size 2671