huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/metallica
+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/b04166fa115f4e8aae2c30f301ae52ba.480x480x1.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">Metallica</div>
+    <a href="https://genius.com/artists/metallica">
+    	<div style="text-align: center; font-size: 14px;">@metallica</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 Metallica.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/metallica).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/metallica")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/30glu695/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 Metallica's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2m1o5q6p) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2m1o5q6p/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/metallica')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/metallica")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/metallica")
+```
+
+## 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 +1,42 @@
+{
+  "_name_or_path": "metallica",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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": "4.19.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 3.0450499057769775, "eval_runtime": 3.7515, "eval_samples_per_second": 43.449, "eval_steps_per_second": 5.598, "epoch": 5.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738b0430eb900f7d2414b5e7bdba27aab418b7f70b324c956d9590716a208951
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfade080baa0bc9333bfb79db98aea4397f748c93c9458dffb6104379f4fa6c
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112d9c3ad682a23938f204ee05b28bf337cf8bce10886626825ed989c2a34cc6
+size 510396521

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4780b3c82eb6d52fa4678c301c114b864f4f33add27357847e1a28ec3a1f62
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799431c9df9be86fdf166619b508adb0bf4df878284cae689fc0164411e1f32b
+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 +1,434 @@
+{
+  "best_metric": 3.0450499057769775,
+  "best_model_checkpoint": "output/metallica/checkpoint-315",
+  "epoch": 5.0,
+  "global_step": 315,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013507870183531476,
+      "loss": 3.3881,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012884599993319768,
+      "loss": 3.3444,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011888735840752609,
+      "loss": 3.3036,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001058186737011911,
+      "loss": 3.3353,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.044818420726556e-05,
+      "loss": 3.2497,
+      "step": 25
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.372648442002871e-05,
+      "loss": 3.2277,
+      "step": 30
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.668773501204858e-05,
+      "loss": 3.0355,
+      "step": 35
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.0385704725240065e-05,
+      "loss": 2.898,
+      "step": 40
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 2.9592,
+      "step": 45
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3916710004507539e-05,
+      "loss": 2.9574,
+      "step": 50
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.38673186569003e-06,
+      "loss": 2.9963,
+      "step": 55
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.662053209561833e-07,
+      "loss": 2.9366,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.13543438911438,
+      "eval_runtime": 3.4469,
+      "eval_samples_per_second": 47.289,
+      "eval_steps_per_second": 6.092,
+      "step": 63
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.408888099334633e-07,
+      "loss": 2.948,
+      "step": 65
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.137086214086682e-06,
+      "loss": 2.811,
+      "step": 70
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.1920020081922749e-05,
+      "loss": 2.9051,
+      "step": 75
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.320835154085542e-05,
+      "loss": 2.813,
+      "step": 80
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 3.7303948905573005e-05,
+      "loss": 2.6726,
+      "step": 85
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.333506393059682e-05,
+      "loss": 2.817,
+      "step": 90
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.031024545323179e-05,
+      "loss": 2.8553,
+      "step": 95
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.71796561146101e-05,
+      "loss": 2.7581,
+      "step": 100
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 2.8057,
+      "step": 105
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0001164990457207046,
+      "loss": 2.7321,
+      "step": 110
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00012713575447996587,
+      "loss": 2.67,
+      "step": 115
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00013415229447692924,
+      "loss": 2.7242,
+      "step": 120
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00013711472479561806,
+      "loss": 2.7872,
+      "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.1001694202423096,
+      "eval_runtime": 3.559,
+      "eval_samples_per_second": 45.8,
+      "eval_steps_per_second": 5.901,
+      "step": 126
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00013583983266641012,
+      "loss": 2.5963,
+      "step": 130
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00013040646433810595,
+      "loss": 2.4975,
+      "step": 135
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0001211506487979619,
+      "loss": 2.5517,
+      "step": 140
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.00010864481591530664,
+      "loss": 2.454,
+      "step": 145
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 9.36623942715347e-05,
+      "loss": 2.4655,
+      "step": 150
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.712997813881747e-05,
+      "loss": 2.5144,
+      "step": 155
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 6.007002186118257e-05,
+      "loss": 2.4411,
+      "step": 160
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 4.3537605728465284e-05,
+      "loss": 2.49,
+      "step": 165
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.8555184084693446e-05,
+      "loss": 2.2522,
+      "step": 170
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.6049351202038163e-05,
+      "loss": 2.4637,
+      "step": 175
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 6.793535661894062e-06,
+      "loss": 2.4223,
+      "step": 180
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.3601673335899086e-06,
+      "loss": 2.255,
+      "step": 185
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.0634868144989014,
+      "eval_runtime": 3.6817,
+      "eval_samples_per_second": 44.273,
+      "eval_steps_per_second": 5.704,
+      "step": 189
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 8.527520438192717e-08,
+      "loss": 2.3823,
+      "step": 190
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 3.047705523070765e-06,
+      "loss": 2.3682,
+      "step": 195
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 1.0064245520034058e-05,
+      "loss": 2.3272,
+      "step": 200
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 2.0700954279295363e-05,
+      "loss": 2.2495,
+      "step": 205
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.4300000000000014e-05,
+      "loss": 2.0865,
+      "step": 210
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 5.0020343885389815e-05,
+      "loss": 2.279,
+      "step": 215
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 6.688975454676822e-05,
+      "loss": 2.1852,
+      "step": 220
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 8.386493606940314e-05,
+      "loss": 2.2131,
+      "step": 225
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 9.989605109442691e-05,
+      "loss": 2.2336,
+      "step": 230
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.00011399164845914455,
+      "loss": 2.2808,
+      "step": 235
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.00012527997991807721,
+      "loss": 2.4415,
+      "step": 240
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.00013306291378591332,
+      "loss": 2.1738,
+      "step": 245
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.00013685911119006654,
+      "loss": 2.3683,
+      "step": 250
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.110128879547119,
+      "eval_runtime": 3.7075,
+      "eval_samples_per_second": 43.965,
+      "eval_steps_per_second": 5.664,
+      "step": 252
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 0.00013643379467904383,
+      "loss": 2.0957,
+      "step": 255
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 0.00013181326813430994,
+      "loss": 2.1122,
+      "step": 260
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.00012328328999549248,
+      "loss": 2.0913,
+      "step": 265
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.00011137140040750914,
+      "loss": 2.0899,
+      "step": 270
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 9.681429527476003e-05,
+      "loss": 2.0885,
+      "step": 275
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 8.051226498795145e-05,
+      "loss": 2.054,
+      "step": 280
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 6.347351557997137e-05,
+      "loss": 2.0165,
+      "step": 285
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 4.675181579273458e-05,
+      "loss": 1.945,
+      "step": 290
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 3.138132629880886e-05,
+      "loss": 1.9216,
+      "step": 295
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 1.8312641592473912e-05,
+      "loss": 1.9411,
+      "step": 300
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 8.354000066802353e-06,
+      "loss": 1.7585,
+      "step": 305
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 2.121298164685252e-06,
+      "loss": 1.947,
+      "step": 310
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 1.9567,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.0450499057769775,
+      "eval_runtime": 3.7841,
+      "eval_samples_per_second": 43.076,
+      "eval_steps_per_second": 5.55,
+      "step": 315
+    }
+  ],
+  "max_steps": 315,
+  "num_train_epochs": 5,
+  "total_flos": 327268270080000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3cc83e29c6b53c606cb39e86a99d2063024b67ce2514b8bc35a52f6dc4980f
+size 3247