huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/6ix9ine")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/33owzv4t/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/2myyormf/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 6ix9ine's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/22q1oxft) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/7knioj7l) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/22q1oxft/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/7knioj7l/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 3.0470073223114014, "eval_runtime": 2.6704, "eval_samples_per_second": 20.596, "eval_steps_per_second": 2.621, "epoch": 2.0}
+{"eval_loss": 2.900149345397949, "eval_runtime": 2.5222, "eval_samples_per_second": 21.013, "eval_steps_per_second": 2.775, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df15ff3bf9d8a1748a052761e63c3b2f0e766961f7279a8de10378dfaeaf585
+oid sha256:e9509193c5fd5514fa34c5b8e4deef5d7ef27e6f54a88541e72dc9bbdcf0a7cd
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7c973b07fc7925a7773a7a9b8e96db55101b49d6bf109cfa76b63b9f7b450e
+oid sha256:6ab2bc41a7353a377e1364b89258475aeb37844383ea22bc18242bc8ff867965
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1cf3ab818bb31d83b57f1db70e0d084389c521eecdf3cbb96f980dd4a48168
+oid sha256:30fde55c2cd1fd62cf61de771d05ea50c736a8b1286a06e577692582cfdeed20
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d7a8e82d5104f8855899362d2c29661c48c9cc84dceb8ac5bbc637db2337f5
+oid sha256:fc87f4591da50bc4de4f46a7c5f73ef224136f280b5366df533254560016512d
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00dd6b6c01d14ec8bb955c14a18bd11e818291c6d3cf3ac44048cedcc0186d76
+oid sha256:744fcc656fe1f449c2ea79ccccba224c3e3c1abb31179e9ce51f592461ac2c71
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 3.0470073223114014,
-  "best_model_checkpoint": "output/6ix9ine/checkpoint-84",
-  "epoch": 2.0,
-  "global_step": 84,
+  "best_metric": 2.900149345397949,
+  "best_model_checkpoint": "output/6ix9ine/checkpoint-126",
+  "epoch": 3.0,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -118,11 +118,73 @@
       "eval_samples_per_second": 20.952,
       "eval_steps_per_second": 2.667,
       "step": 84
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.9181951337103552e-07,
+      "loss": 2.7319,
+      "step": 85
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 6.793535661894039e-06,
+      "loss": 2.7967,
+      "step": 90
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.194015018891494e-05,
+      "loss": 2.9303,
+      "step": 95
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.3537605728465236e-05,
+      "loss": 2.6571,
+      "step": 100
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.859999999999997e-05,
+      "loss": 2.816,
+      "step": 105
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 9.36623942715347e-05,
+      "loss": 2.8496,
+      "step": 110
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.00011525984981108502,
+      "loss": 2.9189,
+      "step": 115
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.00013040646433810595,
+      "loss": 2.8699,
+      "step": 120
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.00013700818048662894,
+      "loss": 2.5821,
+      "step": 125
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.900149345397949,
+      "eval_runtime": 2.5511,
+      "eval_samples_per_second": 20.775,
+      "eval_steps_per_second": 2.744,
+      "step": 126
     }
   ],
-  "max_steps": 84,
-  "num_train_epochs": 2,
-  "total_flos": 86226370560000.0,
+  "max_steps": 126,
+  "num_train_epochs": 3,
+  "total_flos": 129600847872000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd271d0572a7a3468694d79a611ddcf794549420f744198cdf5961c723dc8d78
+oid sha256:7e93bb873917a9ff90818f9d9ee0e70a0a0c0493fe6d3d599f966dfc8cd40a4e
 size 2863