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/2myyormf/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/23c4qor5/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/7knioj7l) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/8askquwf) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/7knioj7l/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/8askquwf/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.900149345397949, "eval_runtime": 2.5222, "eval_samples_per_second": 21.013, "eval_steps_per_second": 2.775, "epoch": 3.0}
+{"eval_loss": 2.566208600997925, "eval_runtime": 2.6338, "eval_samples_per_second": 20.882, "eval_steps_per_second": 2.658, "epoch": 4.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9509193c5fd5514fa34c5b8e4deef5d7ef27e6f54a88541e72dc9bbdcf0a7cd
+oid sha256:e1828e0611eb3dd2b0e31ca17d4310d4d7489f09c72ac60fd8ea14bbf161796e
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab2bc41a7353a377e1364b89258475aeb37844383ea22bc18242bc8ff867965
+oid sha256:a41f3f5703dac31ae7a5401c632b68029d736e86bfffe760b46a0f472c96db60
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30fde55c2cd1fd62cf61de771d05ea50c736a8b1286a06e577692582cfdeed20
+oid sha256:9b8d9d316dc2aba5868d7f29d4e845259d1702edafe69690c706ad4d698822e2
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc87f4591da50bc4de4f46a7c5f73ef224136f280b5366df533254560016512d
+oid sha256:21430a2736694d7f20ccf719d4c7704a6abda2499225d98352d67c327ad5baa9
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744fcc656fe1f449c2ea79ccccba224c3e3c1abb31179e9ce51f592461ac2c71
+oid sha256:81c6de287d0aeee2c682cd2a01e5e01657f181e757ee594a86aa0945f540d0b1
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.900149345397949,
-  "best_model_checkpoint": "output/6ix9ine/checkpoint-126",
-  "epoch": 3.0,
-  "global_step": 126,
+  "best_metric": 2.566208600997925,
+  "best_model_checkpoint": "output/6ix9ine/checkpoint-168",
+  "epoch": 4.0,
+  "global_step": 168,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -180,11 +180,67 @@
       "eval_samples_per_second": 20.775,
       "eval_steps_per_second": 2.744,
       "step": 126
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.00013415229447692926,
+      "loss": 2.6428,
+      "step": 130
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.00012223363969730686,
+      "loss": 2.6782,
+      "step": 135
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.00010290000000000009,
+      "loss": 2.6065,
+      "step": 140
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 7.882429945968553e-05,
+      "loss": 2.5807,
+      "step": 145
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 5.333506393059687e-05,
+      "loss": 2.5988,
+      "step": 150
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 2.9956244016835525e-05,
+      "loss": 2.5281,
+      "step": 155
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 1.1920020081922795e-05,
+      "loss": 2.6676,
+      "step": 160
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 1.7199452243269073e-06,
+      "loss": 2.6813,
+      "step": 165
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.566208600997925,
+      "eval_runtime": 2.6398,
+      "eval_samples_per_second": 20.835,
+      "eval_steps_per_second": 2.652,
+      "step": 168
     }
   ],
-  "max_steps": 126,
-  "num_train_epochs": 3,
-  "total_flos": 129600847872000.0,
+  "max_steps": 168,
+  "num_train_epochs": 4,
+  "total_flos": 172714033152000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e93bb873917a9ff90818f9d9ee0e70a0a0c0493fe6d3d599f966dfc8cd40a4e
+oid sha256:ecac0d19b2e1f0f637a36c6ba81af1b5f98eeb060b14910c27f5bc5242b68a0d
 size 2863