huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/rihanna")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3c5muzh8/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/ee6eogks/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 Rihanna's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/uywap06b) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1mvns7x8) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/uywap06b/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1mvns7x8/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.752521276473999, "eval_runtime": 4.2607, "eval_samples_per_second": 45.532, "eval_steps_per_second": 5.868, "epoch": 7.0}
+{"eval_loss": 1.2033756971359253, "eval_runtime": 4.6245, "eval_samples_per_second": 39.572, "eval_steps_per_second": 4.974, "epoch": 7.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41a408893cb0ef0914b7c69fe63100edbcfd9827c5b8d83eff838506cbe6e73
+oid sha256:91223b3a97f4c33bf4beb5f6f9bc0bdba4a1266033f550d62ad0677eacb6527e
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3006a0c685ddebea1136f939b292ab67e24da1f0edd23faadf7a85985f46b34
+oid sha256:eb346aee3195e920755952ca3f6d08dbae55ea133ff03b948e5e75f31a13e735
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5b73d16cb2c0edc96673fe23be7a5214f61a1c9d00aaf44aacd9f96d1ea618
+oid sha256:227d1a1eff8e256ae4ff6404aab3e581a87996e190fb70a13aee77a4b37e346f
 size 510396521

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e82f1222285d031b8e21d934b74558389b98a783bb42db1010d0f55af3bc16
+oid sha256:ba49a0e1fbf48c63a7ae2a286d185ed913f3a9d7c46fb958fa2659acf47e391d
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc3e0c06b55e5f6cc34f1c4c7ab6e7fc251827bfa5f1b3ed68bfe476fa6cc0c
+oid sha256:880e20d26c7d0a4b78d5bba31d4851bd1223c0668a0dee28ba1cc31f27011705
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.752521276473999,
-  "best_model_checkpoint": "output/rihanna/checkpoint-780",
-  "epoch": 6.0,
-  "global_step": 780,
+  "best_metric": 1.2033756971359253,
+  "best_model_checkpoint": "output/rihanna/checkpoint-917",
+  "epoch": 7.0,
+  "global_step": 917,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -990,11 +990,189 @@
       "eval_samples_per_second": 45.684,
       "eval_steps_per_second": 5.887,
       "step": 780
+    },
+    {
+      "epoch": 5.99,
+      "learning_rate": 0.00013718027438920657,
+      "loss": 1.3027,
+      "step": 785
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.2558701038360596,
+      "eval_runtime": 3.8315,
+      "eval_samples_per_second": 47.762,
+      "eval_steps_per_second": 6.003,
+      "step": 786
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.0001368846170554219,
+      "loss": 1.0307,
+      "step": 790
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00013560834225858045,
+      "loss": 1.3396,
+      "step": 795
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 0.0001333697782460593,
+      "loss": 1.3763,
+      "step": 800
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 0.0001302010724480925,
+      "loss": 1.3968,
+      "step": 805
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 0.00012614772981696314,
+      "loss": 1.2598,
+      "step": 810
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 0.00012126795934232731,
+      "loss": 1.6357,
+      "step": 815
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 0.00011563183812719099,
+      "loss": 1.5069,
+      "step": 820
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 0.00010932030502902761,
+      "loss": 1.3309,
+      "step": 825
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 0.00010242399831808912,
+      "loss": 1.2963,
+      "step": 830
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 9.504195404499683e-05,
+      "loss": 1.5269,
+      "step": 835
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 8.728018381001126e-05,
+      "loss": 1.1606,
+      "step": 840
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 7.925015235826672e-05,
+      "loss": 1.4031,
+      "step": 845
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 7.10671768638214e-05,
+      "loss": 1.1422,
+      "step": 850
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 6.284877088998812e-05,
+      "loss": 1.2245,
+      "step": 855
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 5.4712956807894146e-05,
+      "loss": 1.5305,
+      "step": 860
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 4.677657090818787e-05,
+      "loss": 1.4329,
+      "step": 865
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 3.915358554573355e-05,
+      "loss": 1.0966,
+      "step": 870
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 3.1953472412537526e-05,
+      "loss": 1.1648,
+      "step": 875
+    },
+    {
+      "epoch": 6.72,
+      "learning_rate": 2.5279630443511272e-05,
+      "loss": 1.5295,
+      "step": 880
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 1.9227900931507197e-05,
+      "loss": 1.1119,
+      "step": 885
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 1.388519117566634e-05,
+      "loss": 1.0333,
+      "step": 890
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 9.328226428505963e-06,
+      "loss": 1.3515,
+      "step": 895
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 5.622448064706006e-06,
+      "loss": 1.2529,
+      "step": 900
+    },
+    {
+      "epoch": 6.91,
+      "learning_rate": 2.8210737947035045e-06,
+      "loss": 1.0788,
+      "step": 905
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 9.643334191210031e-07,
+      "loss": 1.4072,
+      "step": 910
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 7.88910991585708e-08,
+      "loss": 0.9972,
+      "step": 915
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.2033756971359253,
+      "eval_runtime": 4.6484,
+      "eval_samples_per_second": 39.368,
+      "eval_steps_per_second": 4.948,
+      "step": 917
     }
   ],
-  "max_steps": 910,
+  "max_steps": 917,
   "num_train_epochs": 7,
-  "total_flos": 811181113344000.0,
+  "total_flos": 953846562816000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf17e5c0319daac4eb8decc923d42c574d61cb10c1cc3267a038b27c7c37d44
+oid sha256:81b335aaeaa4f7d2d36b33d05514125a74b0cc817463fa2fde25b4ec3e8b0a75
 size 3311