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/2g2pefri/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/14l0irt0/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/1cgpsnr9) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1buv5m9i) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1cgpsnr9/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1buv5m9i/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.16.1",
+  "transformers_version": "4.16.2",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.39583703875541687, "eval_runtime": 15.6845, "eval_samples_per_second": 40.996, "eval_steps_per_second": 5.164, "epoch": 3.0}
+{"eval_loss": 0.37163448333740234, "eval_runtime": 28.704, "eval_samples_per_second": 20.45, "eval_steps_per_second": 2.578, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd580cdd6ae182fb6891fb3ab9c245878150973faa325cd10a031212867a481
+oid sha256:bb44bd892620724348b1f8bd98aff6e03e38fe1376bcd754f4b89769c6ed210a
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a56d81e45519802258d85034e9d148ff2c2b39b2cdab1bf361d45db8afd0826
+oid sha256:bfa216e29dab868efb9674298799ceecd462e1b341fde7e584fcff00171c7b33
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84e26d6c93df97456fef9936ec00c747b477c398b1ba8e7fd2e39abb2d9d5485
+oid sha256:ce13b2714bbf717a6d07d2e7d112009b4ee85fc468a7056e1df4e22a76c4b967
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1ca01a858269cc17577c848b7dfeb3a25a3f97086ed6a27be4b05c3cb771b1
+oid sha256:7753baebd09fb9ef19a9cbd379c34b2acd8cbc7bd213ace8e1d0bf591bb2bcfc
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2184305b4be28c3d577fb5099adb7f1233c0a22282f0740498d93642171b606
+oid sha256:63fe74d287e7e5851bce8bf478b5c5444779821627837777ac4e6b2d39e75580
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.39583703875541687,
-  "best_model_checkpoint": "output/eminem/checkpoint-910",
+  "best_metric": 0.37163448333740234,
+  "best_model_checkpoint": "output/eminem/checkpoint-924",
   "epoch": 2.0,
-  "global_step": 910,
+  "global_step": 924,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1122,11 +1122,31 @@
       "eval_samples_per_second": 47.047,
       "eval_steps_per_second": 5.927,
       "step": 910
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.7062254198703994e-05,
+      "loss": 0.8052,
+      "step": 915
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.8631088017841603e-05,
+      "loss": 0.7911,
+      "step": 920
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.37163448333740234,
+      "eval_runtime": 28.6365,
+      "eval_samples_per_second": 20.498,
+      "eval_steps_per_second": 2.584,
+      "step": 924
     }
   ],
-  "max_steps": 1365,
+  "max_steps": 1386,
   "num_train_epochs": 3,
-  "total_flos": 949404598272000.0,
+  "total_flos": 963383721984000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:772e3af6dfbf093ace803be6f7a82ae09aba1a764d9501254be31303aa54425c
+oid sha256:805b5eda2fc68bf70f2494e9471c8381559074bf1249ef0daf4c166fcf463efc
 size 3055