huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/eminem")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3nw4yihh/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/2g2pefri/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/d2518d5z) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1cgpsnr9) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/d2518d5z/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1cgpsnr9/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.5308113694190979, "eval_runtime": 33.6836, "eval_samples_per_second": 20.544, "eval_steps_per_second": 2.583, "epoch": 2.0}
+{"eval_loss": 0.39583703875541687, "eval_runtime": 15.6845, "eval_samples_per_second": 40.996, "eval_steps_per_second": 5.164, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a848a5f09ac15240e3985770765e24f91d15132b1d91e4e6609d31cfa9381998
+oid sha256:7cd580cdd6ae182fb6891fb3ab9c245878150973faa325cd10a031212867a481
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93aacf90961d37a1a7828ff46e2dc62c33c91fee3a84fdc5ef4c64587efa913
+oid sha256:7a56d81e45519802258d85034e9d148ff2c2b39b2cdab1bf361d45db8afd0826
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a17213360ebd42855ba94ae341f8e0785b2c350210bb514a32c45f28a0a9946
+oid sha256:84e26d6c93df97456fef9936ec00c747b477c398b1ba8e7fd2e39abb2d9d5485
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a41f6ecc4cb672b89916065240d6da95437b3116ab28fa8f83b9d0f50b7335
+oid sha256:de1ca01a858269cc17577c848b7dfeb3a25a3f97086ed6a27be4b05c3cb771b1
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e839905521debf4509c82b96247599aa8aabe5b0cbac84cd46b26dbe8819f271
+oid sha256:f2184305b4be28c3d577fb5099adb7f1233c0a22282f0740498d93642171b606
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.5308113694190979,
-  "best_model_checkpoint": "output/eminem/checkpoint-898",
+  "best_metric": 0.39583703875541687,
+  "best_model_checkpoint": "output/eminem/checkpoint-910",
   "epoch": 2.0,
-  "global_step": 898,
+  "global_step": 910,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1096,11 +1096,37 @@
       "eval_samples_per_second": 20.587,
       "eval_steps_per_second": 2.588,
       "step": 898
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00013331119038948074,
+      "loss": 0.7724,
+      "step": 900
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0001340585253974795,
+      "loss": 0.7496,
+      "step": 905
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001347278522437355,
+      "loss": 0.8119,
+      "step": 910
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.39583703875541687,
+      "eval_runtime": 13.6672,
+      "eval_samples_per_second": 47.047,
+      "eval_steps_per_second": 5.927,
+      "step": 910
     }
   ],
-  "max_steps": 898,
-  "num_train_epochs": 2,
-  "total_flos": 937515810816000.0,
+  "max_steps": 1365,
+  "num_train_epochs": 3,
+  "total_flos": 949404598272000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e1bade9dac46ba2611ae8c7e18e7545beeeb1e60ed8853a281799cdfbbfd97
+oid sha256:772e3af6dfbf093ace803be6f7a82ae09aba1a764d9501254be31303aa54425c
 size 3055