huggingartists

README.md

@@ -14,7 +14,7 @@ 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/c674178296f3d65792a66f851fbc62fc.900x900x1.png&#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/0ead4ce72e3e97a4ce025dcbf9ef366f.1000x1000x1.jpg&#39;)">
         </div>
     </div>
     <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/eminem")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/wqeebjm6/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/19gci1n4/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 Eminem's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1r91z1u3) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1je8v3eb) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1r91z1u3/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1je8v3eb/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.41102197766304016, "eval_runtime": 14.7285, "eval_samples_per_second": 43.182, "eval_steps_per_second": 5.432, "epoch": 3.0}
+{"eval_loss": 0.3754318356513977, "eval_runtime": 8.7776, "eval_samples_per_second": 75.989, "eval_steps_per_second": 9.57, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:179861d06f26a39a625bade68ca595e81d6de04012686551d418e512f108a547
+oid sha256:e8772f90ce04a5e850ff75ef5b602d4536ede75be0d83e670f7afd86b395b8be
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af45af4262862dc6b6a14037e759fcea974defe54215dbe6268cb309d499e5b
+oid sha256:fc7b9dddb75ac5e672146795acb35761f28f2d68a6d466ffa6fbe24010202e41
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcdd242b4ca2943da34998f3437f3d233bc20424c948fe5cd014c826a37894d1
+oid sha256:e02f4d6ce2f227c58ed2904a072b80525c2072f5f7059f121957fe78ea4da6ff
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dae1d462e506ffceccce9f9c31d892f0fe4bd0d84bb7d72de19955d2ea5bfc2
+oid sha256:4672dcf145f0b3d344693db21f586bc42e32415a69a154df09e50a321a49e325
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed0916d61de33d62f521fe37251dde481dd7b032866021fa20b2813604e4e361
+oid sha256:f9dc76c688deef1eb9e98c1444375032667a38879fb6756f454c9b01f7d1a93d
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.41102197766304016,
-  "best_model_checkpoint": "output/eminem/checkpoint-456",
-  "epoch": 1.0,
-  "global_step": 456,
+  "best_metric": 0.3754318356513977,
+  "best_model_checkpoint": "output/eminem/checkpoint-904",
+  "epoch": 2.0,
+  "global_step": 904,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -560,11 +560,553 @@
       "eval_samples_per_second": 41.742,
       "eval_steps_per_second": 5.251,
       "step": 456
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00011710752518939759,
+      "loss": 0.6694,
+      "step": 460
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00011539283602861273,
+      "loss": 0.6712,
+      "step": 465
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00011362164035023001,
+      "loss": 0.7083,
+      "step": 470
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00011179607703080105,
+      "loss": 0.6899,
+      "step": 475
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.000109918350600647,
+      "loss": 0.7508,
+      "step": 480
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001079907285816916,
+      "loss": 0.6351,
+      "step": 485
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00010601553874922655,
+      "loss": 0.7873,
+      "step": 490
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001039951663209155,
+      "loss": 0.7405,
+      "step": 495
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00010193205107643125,
+      "loss": 0.8115,
+      "step": 500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 9.982868441120446e-05,
+      "loss": 0.8309,
+      "step": 505
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 9.768760632784171e-05,
+      "loss": 0.7548,
+      "step": 510
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 9.551140236884618e-05,
+      "loss": 0.7107,
+      "step": 515
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 9.330270049434476e-05,
+      "loss": 0.6035,
+      "step": 520
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 9.1064167908592e-05,
+      "loss": 0.724,
+      "step": 525
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 8.879850783908354e-05,
+      "loss": 0.6642,
+      "step": 530
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 8.650845627216803e-05,
+      "loss": 0.6811,
+      "step": 535
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 8.41967786490999e-05,
+      "loss": 0.6505,
+      "step": 540
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 8.186626652652275e-05,
+      "loss": 0.7759,
+      "step": 545
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.951973420541605e-05,
+      "loss": 0.6233,
+      "step": 550
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.716001533257597e-05,
+      "loss": 0.7224,
+      "step": 555
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 7.478995947873449e-05,
+      "loss": 0.7252,
+      "step": 560
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 7.241242869744897e-05,
+      "loss": 0.6465,
+      "step": 565
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 7.003029406891743e-05,
+      "loss": 0.7505,
+      "step": 570
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.764643223289357e-05,
+      "loss": 0.7117,
+      "step": 575
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.526372191488798e-05,
+      "loss": 0.7289,
+      "step": 580
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.288504044985065e-05,
+      "loss": 0.7069,
+      "step": 585
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 6.05132603075328e-05,
+      "loss": 0.7925,
+      "step": 590
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.8151245623725575e-05,
+      "loss": 0.7614,
+      "step": 595
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.5801848741551456e-05,
+      "loss": 0.6241,
+      "step": 600
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.3467906767025034e-05,
+      "loss": 0.6841,
+      "step": 605
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.115223814297748e-05,
+      "loss": 0.7002,
+      "step": 610
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.885763924553591e-05,
+      "loss": 0.7048,
+      "step": 615
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.65868810072671e-05,
+      "loss": 0.6762,
+      "step": 620
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.434270557101253e-05,
+      "loss": 0.6848,
+      "step": 625
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.2127822978506955e-05,
+      "loss": 0.7911,
+      "step": 630
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.9944907897778e-05,
+      "loss": 0.767,
+      "step": 635
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.779659639322971e-05,
+      "loss": 0.6907,
+      "step": 640
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.568548274236045e-05,
+      "loss": 0.7518,
+      "step": 645
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.361411630295728e-05,
+      "loss": 0.6918,
+      "step": 650
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.158499843450359e-05,
+      "loss": 0.7341,
+      "step": 655
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2.9600579477565238e-05,
+      "loss": 0.6637,
+      "step": 660
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.7663255794802226e-05,
+      "loss": 0.7897,
+      "step": 665
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5775366877124698e-05,
+      "loss": 0.5947,
+      "step": 670
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.393919251856543e-05,
+      "loss": 0.6711,
+      "step": 675
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.21569500632249e-05,
+      "loss": 0.789,
+      "step": 680
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.043079172761756e-05,
+      "loss": 0.6784,
+      "step": 685
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.876280200169214e-05,
+      "loss": 0.648,
+      "step": 690
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.7154995131623676e-05,
+      "loss": 0.8539,
+      "step": 695
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.5609312687419874e-05,
+      "loss": 0.8157,
+      "step": 700
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.4127621218314657e-05,
+      "loss": 0.6428,
+      "step": 705
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.2711709998742864e-05,
+      "loss": 0.6836,
+      "step": 710
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.1363288867621515e-05,
+      "loss": 0.6848,
+      "step": 715
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.0083986163577838e-05,
+      "loss": 0.687,
+      "step": 720
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.875346758584498e-06,
+      "loss": 0.6913,
+      "step": 725
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.738830192380085e-06,
+      "loss": 0.7138,
+      "step": 730
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 6.675808909954194e-06,
+      "loss": 0.7293,
+      "step": 735
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 5.687566604196989e-06,
+      "loss": 0.7797,
+      "step": 740
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.7752966657182915e-06,
+      "loss": 0.6821,
+      "step": 745
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.940100741730516e-06,
+      "loss": 0.5752,
+      "step": 750
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.182987405707336e-06,
+      "loss": 0.7456,
+      "step": 755
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.5048709394422254e-06,
+      "loss": 0.694,
+      "step": 760
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.9065702289717339e-06,
+      "loss": 0.6621,
+      "step": 765
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.3888077756976535e-06,
+      "loss": 0.706,
+      "step": 770
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.522088239022507e-07,
+      "loss": 0.7326,
+      "step": 775
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.973006057100785e-07,
+      "loss": 0.6361,
+      "step": 780
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.245117044082019e-07,
+      "loss": 0.647,
+      "step": 785
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.3417153689374065e-07,
+      "loss": 0.7488,
+      "step": 790
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.6509955873614998e-08,
+      "loss": 0.7149,
+      "step": 795
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.6569722969137058e-09,
+      "loss": 0.6775,
+      "step": 800
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5.964259835508488e-08,
+      "loss": 0.7746,
+      "step": 805
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.003968112395687e-07,
+      "loss": 0.6598,
+      "step": 810
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.2374963770057325e-07,
+      "loss": 0.6891,
+      "step": 815
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.294313593051582e-07,
+      "loss": 0.6988,
+      "step": 820
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.1170728381449087e-06,
+      "loss": 0.6761,
+      "step": 825
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.5862059626056298e-06,
+      "loss": 0.7306,
+      "step": 830
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.1362642126509973e-06,
+      "loss": 0.6297,
+      "step": 835
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.766583343947401e-06,
+      "loss": 0.7385,
+      "step": 840
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.4764021899978206e-06,
+      "loss": 0.7045,
+      "step": 845
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.264863581318223e-06,
+      "loss": 0.6952,
+      "step": 850
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 5.131015380546021e-06,
+      "loss": 0.7021,
+      "step": 855
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.073811632230782e-06,
+      "loss": 0.6392,
+      "step": 860
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 7.09211382591858e-06,
+      "loss": 0.694,
+      "step": 865
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.18469227100481e-06,
+      "loss": 0.6864,
+      "step": 870
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 9.350227581695092e-06,
+      "loss": 0.7318,
+      "step": 875
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.0587312270281189e-05,
+      "loss": 0.6326,
+      "step": 880
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.1894452446807735e-05,
+      "loss": 0.7141,
+      "step": 885
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.3270069623077462e-05,
+      "loss": 0.713,
+      "step": 890
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.47125026188163e-05,
+      "loss": 0.7505,
+      "step": 895
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.6220009567696506e-05,
+      "loss": 0.7118,
+      "step": 900
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3754318356513977,
+      "eval_runtime": 8.7593,
+      "eval_samples_per_second": 76.147,
+      "eval_steps_per_second": 9.59,
+      "step": 904
     }
   ],
-  "max_steps": 1368,
-  "num_train_epochs": 3,
-  "total_flos": 475812790272000.0,
+  "max_steps": 904,
+  "num_train_epochs": 2,
+  "total_flos": 943264235520000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9d4e84835a869c4c9d855147718c055221c1c706451dc866b663d99f0469f6
+oid sha256:8f5f3fe6c4b31e270bb58aea5ef8c2bf476b58d1810de27a6c9bec70157c8923
 size 3055