huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/the-the-pigs
+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/2f1fd1b951237ad3387096f392d41fa5.720x720x1.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">The ‘’Вепри’’ (The Pigs)</div>
+    <a href="https://genius.com/artists/the-the-pigs">
+    	<div style="text-align: center; font-size: 14px;">@the-the-pigs</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 The ‘’Вепри’’ (The Pigs).
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/the-the-pigs).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/the-the-pigs")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/s5khturf/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 The ‘’Вепри’’ (The Pigs)'s lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2wm2oonn) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2wm2oonn/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/the-the-pigs')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/the-the-pigs")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/the-the-pigs")
+```
+
+## 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": 1.7347867488861084, "eval_runtime": 0.9361, "eval_samples_per_second": 20.297, "eval_steps_per_second": 3.205, "epoch": 20.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02c32ea8cbf7c2e61290b1d72ca0369e968b66bb1edd7b4464b23c5092af01b
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d794e2cf1e854660cf8c67241054d968e9933fc96e0ac960005808d8e19da9a
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13a43a42b8448df12dbb6b75830224c036b3bcb9c128c9833c197779081b8a6
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c1257d23e86fa50a3c449eb97c44e917eeff6eada6271ca3edb44fa461f708
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8eb138d3e74e4ee9a8cfdbf6948246533add92d0858995ee833af706c95c53c
+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 +1,226 @@
+{
+  "best_metric": 1.7347867488861084,
+  "best_model_checkpoint": "output/the-the-pigs/checkpoint-117",
+  "epoch": 9.0,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.292589525111794e-05,
+      "loss": 2.5049,
+      "step": 5
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.725216267546246e-05,
+      "loss": 2.2501,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.966219425201416,
+      "eval_runtime": 0.848,
+      "eval_samples_per_second": 22.405,
+      "eval_steps_per_second": 3.538,
+      "step": 13
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.857716640189785e-06,
+      "loss": 2.2537,
+      "step": 15
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.686881626551516e-05,
+      "loss": 2.1305,
+      "step": 20
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00013520660867542716,
+      "loss": 2.0792,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.9108868837356567,
+      "eval_runtime": 0.8428,
+      "eval_samples_per_second": 22.544,
+      "eval_steps_per_second": 3.56,
+      "step": 26
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00010756924162575734,
+      "loss": 2.1293,
+      "step": 30
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.9630758374242683e-05,
+      "loss": 2.0062,
+      "step": 35
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.830873966217041,
+      "eval_runtime": 0.8441,
+      "eval_samples_per_second": 22.51,
+      "eval_steps_per_second": 3.554,
+      "step": 39
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.9933913245728396e-06,
+      "loss": 1.9324,
+      "step": 40
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 6.033118373448485e-05,
+      "loss": 1.9227,
+      "step": 45
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.00012934228335981018,
+      "loss": 1.9492,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8247166872024536,
+      "eval_runtime": 0.8513,
+      "eval_samples_per_second": 22.319,
+      "eval_steps_per_second": 3.524,
+      "step": 52
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 0.00011994783732453755,
+      "loss": 1.8601,
+      "step": 55
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 4.42741047488822e-05,
+      "loss": 1.7486,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 1.8994,
+      "step": 65
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.7911409139633179,
+      "eval_runtime": 0.8376,
+      "eval_samples_per_second": 22.685,
+      "eval_steps_per_second": 3.582,
+      "step": 65
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 4.4274104748882125e-05,
+      "loss": 1.7558,
+      "step": 70
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 0.00011994783732453749,
+      "loss": 1.8425,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.780040979385376,
+      "eval_runtime": 0.8465,
+      "eval_samples_per_second": 22.444,
+      "eval_steps_per_second": 3.544,
+      "step": 78
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 0.00012934228335981018,
+      "loss": 1.72,
+      "step": 80
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 6.033118373448493e-05,
+      "loss": 1.7991,
+      "step": 85
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 1.9933913245728244e-06,
+      "loss": 1.7086,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.7639576196670532,
+      "eval_runtime": 0.8412,
+      "eval_samples_per_second": 22.587,
+      "eval_steps_per_second": 3.566,
+      "step": 91
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 2.963075837424261e-05,
+      "loss": 1.6218,
+      "step": 95
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 0.00010756924162575728,
+      "loss": 1.6723,
+      "step": 100
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.7437282800674438,
+      "eval_runtime": 0.8437,
+      "eval_samples_per_second": 22.521,
+      "eval_steps_per_second": 3.556,
+      "step": 104
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 0.0001352066086754272,
+      "loss": 1.7365,
+      "step": 105
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 7.68688162655152e-05,
+      "loss": 1.6506,
+      "step": 110
+    },
+    {
+      "epoch": 8.85,
+      "learning_rate": 7.85771664018977e-06,
+      "loss": 1.5713,
+      "step": 115
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.7347867488861084,
+      "eval_runtime": 0.851,
+      "eval_samples_per_second": 22.327,
+      "eval_steps_per_second": 3.525,
+      "step": 117
+    }
+  ],
+  "max_steps": 260,
+  "num_train_epochs": 20,
+  "total_flos": 115229786112000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:115de7483970d263e0616e850a6e0d52e43c047dc3d58f7fce41ea06d8252d5f
+size 2671