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/0ead4ce72e3e97a4ce025dcbf9ef366f.1000x1000x1.jpg&#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/357dbca4b44758c4b734ecb5c6dd19bc.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/2bthi2l5/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/3id5emxt/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/3uhe3l4p) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/39q5c3g1) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3uhe3l4p/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/39q5c3g1/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.3138461709022522, "eval_runtime": 8.6668, "eval_samples_per_second": 75.807, "eval_steps_per_second": 9.577, "epoch": 3.0}
+{"eval_loss": 0.289399653673172, "eval_runtime": 9.1714, "eval_samples_per_second": 75.888, "eval_steps_per_second": 9.486, "epoch": 4.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba2c0bb0c3662b61d1856691077cc0d163acb0938b223223d7c572850acac13
+oid sha256:f2f70e6d24e4d1ab815fe65bf51eae9fe93259a8a8a5bd20827f6f63b72d3cb5
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a55d17f06b4ab806d9383635f0ea345b6c6b980efee1e356aa139b263acedb
+oid sha256:ef05eac2e340bed3befe621b5b6755a3256f006542797eb76a9e2c1b580f0383
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf77abb0b419d0393b5e919f584b77b776cafea3e38f56bd317c366e1ca56ae
+oid sha256:bdb9b38526ad7fe28ee08f68c01b41e9f1fcc62c9a636cf6f22a8e312c4a333c
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84e11f89bd0e9088ead15625532c1b43e0a1cd35766796070671df9c7727ef78
+oid sha256:751843372ff16452c5a382bcca779a2ff0cd9510bd89e3c4af9f63092e540657
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a107dfc2c0a514694de57c3e884ece4223234fff3b17fb14fe84e93ad0ed41a7
+oid sha256:fc4ece6c3cec4b19efed292f7ef2310750d80298186925496928d2235a909340
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.3138461709022522,
-  "best_model_checkpoint": "output/eminem/checkpoint-1359",
-  "epoch": 3.0,
-  "global_step": 1359,
+  "best_metric": 0.289399653673172,
+  "best_model_checkpoint": "output/eminem/checkpoint-1792",
+  "epoch": 4.0,
+  "global_step": 1792,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1656,11 +1656,541 @@
       "eval_samples_per_second": 76.072,
       "eval_steps_per_second": 9.61,
       "step": 1359
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.4667747726642993e-05,
+      "loss": 0.6323,
+      "step": 1360
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 1.3214755505568174e-05,
+      "loss": 0.5288,
+      "step": 1365
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 1.1829845442054389e-05,
+      "loss": 0.4822,
+      "step": 1370
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.0514719932940577e-05,
+      "loss": 0.5699,
+      "step": 1375
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 9.270995592595549e-06,
+      "loss": 0.5351,
+      "step": 1380
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 8.100201265703248e-06,
+      "loss": 0.6382,
+      "step": 1385
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 7.0037761479277354e-06,
+      "loss": 0.5365,
+      "step": 1390
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 5.983068016793553e-06,
+      "loss": 0.5665,
+      "step": 1395
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 5.039331574927566e-06,
+      "loss": 0.5169,
+      "step": 1400
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 4.173726907722877e-06,
+      "loss": 0.5302,
+      "step": 1405
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 3.387318057306161e-06,
+      "loss": 0.5061,
+      "step": 1410
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 2.6810717145662967e-06,
+      "loss": 0.5636,
+      "step": 1415
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 2.0558560308545347e-06,
+      "loss": 0.5727,
+      "step": 1420
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 1.5124395508079945e-06,
+      "loss": 0.5178,
+      "step": 1425
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.0514902676223786e-06,
+      "loss": 0.5668,
+      "step": 1430
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 6.735748019196765e-07,
+      "loss": 0.5409,
+      "step": 1435
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.791577052345188e-07,
+      "loss": 0.5488,
+      "step": 1440
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 1.6860088896217012e-07,
+      "loss": 0.5891,
+      "step": 1445
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 4.216317948330257e-08,
+      "loss": 0.6293,
+      "step": 1450
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.0,
+      "loss": 0.5776,
+      "step": 1455
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 4.216317948328734e-08,
+      "loss": 0.6373,
+      "step": 1460
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.6860088896213203e-07,
+      "loss": 0.6081,
+      "step": 1465
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.791577052344655e-07,
+      "loss": 0.5801,
+      "step": 1470
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 6.73574801919608e-07,
+      "loss": 0.5491,
+      "step": 1475
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 1.051490267622295e-06,
+      "loss": 0.5859,
+      "step": 1480
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 1.5124395508078954e-06,
+      "loss": 0.5745,
+      "step": 1485
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 2.055856030853948e-06,
+      "loss": 0.4955,
+      "step": 1490
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 2.6810717145661676e-06,
+      "loss": 0.5646,
+      "step": 1495
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.387318057305407e-06,
+      "loss": 0.6039,
+      "step": 1500
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 4.173726907722717e-06,
+      "loss": 0.5249,
+      "step": 1505
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 5.039331574926652e-06,
+      "loss": 0.5415,
+      "step": 1510
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 5.983068016793356e-06,
+      "loss": 0.5852,
+      "step": 1515
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 7.003776147927523e-06,
+      "loss": 0.5236,
+      "step": 1520
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 8.100201265703026e-06,
+      "loss": 0.5849,
+      "step": 1525
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 9.270995592595313e-06,
+      "loss": 0.5388,
+      "step": 1530
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 1.051471993293929e-05,
+      "loss": 0.5372,
+      "step": 1535
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 1.1829845442054121e-05,
+      "loss": 0.5343,
+      "step": 1540
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 1.3214755505566749e-05,
+      "loss": 0.5689,
+      "step": 1545
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.4667747726642696e-05,
+      "loss": 0.5281,
+      "step": 1550
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 1.6187036018636972e-05,
+      "loss": 0.5893,
+      "step": 1555
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 1.7770752800649943e-05,
+      "loss": 0.538,
+      "step": 1560
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 1.941695129323498e-05,
+      "loss": 0.5953,
+      "step": 1565
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.1123607911480585e-05,
+      "loss": 0.5626,
+      "step": 1570
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 2.2888624752492827e-05,
+      "loss": 0.5227,
+      "step": 1575
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 2.4709832174232166e-05,
+      "loss": 0.4595,
+      "step": 1580
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 2.658499146254842e-05,
+      "loss": 0.4945,
+      "step": 1585
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 2.8511797583108267e-05,
+      "loss": 0.4842,
+      "step": 1590
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 3.0487882014855305e-05,
+      "loss": 0.5576,
+      "step": 1595
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 3.251081566150148e-05,
+      "loss": 0.5323,
+      "step": 1600
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 3.45781118374983e-05,
+      "loss": 0.551,
+      "step": 1605
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 3.668722932477494e-05,
+      "loss": 0.6077,
+      "step": 1610
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 3.883557549653519e-05,
+      "loss": 0.5575,
+      "step": 1615
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 4.102050950423e-05,
+      "loss": 0.5375,
+      "step": 1620
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 4.3239345523814906e-05,
+      "loss": 0.5252,
+      "step": 1625
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 4.548935605729356e-05,
+      "loss": 0.5687,
+      "step": 1630
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 4.776777528547973e-05,
+      "loss": 0.5572,
+      "step": 1635
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 5.007180246788566e-05,
+      "loss": 0.4855,
+      "step": 1640
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 5.239860538550981e-05,
+      "loss": 0.5661,
+      "step": 1645
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 5.4745323822347075e-05,
+      "loss": 0.4792,
+      "step": 1650
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 5.710907308129398e-05,
+      "loss": 0.568,
+      "step": 1655
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 5.948694753015834e-05,
+      "loss": 0.5744,
+      "step": 1660
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 6.18760241733918e-05,
+      "loss": 0.5533,
+      "step": 1665
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 6.427336624518557e-05,
+      "loss": 0.5154,
+      "step": 1670
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 6.667602681947584e-05,
+      "loss": 0.5253,
+      "step": 1675
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 6.908105243243853e-05,
+      "loss": 0.511,
+      "step": 1680
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 7.148548671303826e-05,
+      "loss": 0.5867,
+      "step": 1685
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 7.388637401713134e-05,
+      "loss": 0.5813,
+      "step": 1690
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 7.628076306068698e-05,
+      "loss": 0.5911,
+      "step": 1695
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 7.866571054763731e-05,
+      "loss": 0.5641,
+      "step": 1700
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 8.103828478792738e-05,
+      "loss": 0.5811,
+      "step": 1705
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 8.339556930128123e-05,
+      "loss": 0.4312,
+      "step": 1710
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 8.573466640227146e-05,
+      "loss": 0.5149,
+      "step": 1715
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 8.805270076230236e-05,
+      "loss": 0.5371,
+      "step": 1720
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 9.0346822944092e-05,
+      "loss": 0.5879,
+      "step": 1725
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 9.261421290433879e-05,
+      "loss": 0.6111,
+      "step": 1730
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 9.485208346024451e-05,
+      "loss": 0.5744,
+      "step": 1735
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 9.705768371566385e-05,
+      "loss": 0.5572,
+      "step": 1740
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 9.922830244262129e-05,
+      "loss": 0.5072,
+      "step": 1745
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.00010136127141409314,
+      "loss": 0.6262,
+      "step": 1750
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 0.00010345396868391098,
+      "loss": 0.5653,
+      "step": 1755
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.00010550382180978354,
+      "loss": 0.629,
+      "step": 1760
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.00010750831101546573,
+      "loss": 0.501,
+      "step": 1765
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.00010946497228818022,
+      "loss": 0.6152,
+      "step": 1770
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 0.0001113714004075095,
+      "loss": 0.5848,
+      "step": 1775
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.00011322525190199372,
+      "loss": 0.6411,
+      "step": 1780
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 0.00011502424792984731,
+      "loss": 0.5627,
+      "step": 1785
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00011676617708021282,
+      "loss": 0.62,
+      "step": 1790
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.289399653673172,
+      "eval_runtime": 9.1611,
+      "eval_samples_per_second": 75.973,
+      "eval_steps_per_second": 9.497,
+      "step": 1792
     }
   ],
-  "max_steps": 1359,
-  "num_train_epochs": 3,
-  "total_flos": 1418815733760000.0,
+  "max_steps": 1792,
+  "num_train_epochs": 4,
+  "total_flos": 1871112241152000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b32292e517517120715d4e5ca63a376048fb88acff6625af239bf56bc4ec8d
+oid sha256:7f0d5a99deab06022cafa0fcb19bad8061dc9fd864b2318bbf9b7f734d52f288
 size 3055