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/3mcytn62/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/3c2104js/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/3rxlo957) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1dlzpggl) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3rxlo957/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1dlzpggl/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.0775227546691895, "eval_runtime": 29.9794, "eval_samples_per_second": 22.315, "eval_steps_per_second": 2.802, "epoch": 4.0}
+{"eval_loss": 1.9903991222381592, "eval_runtime": 28.0407, "eval_samples_per_second": 22.574, "eval_steps_per_second": 2.853, "epoch": 5.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068ab5abee507d02e0ceddd81264e97625f1b2536ccddc34bf29b3c8b3ddf237
+oid sha256:c88e5d7415fd662276affbd9369f18c777c3a2b92d5b2c02702e91f9c2553166
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed02c35a40feea9337942fb2d0af6e045d9ae959c5043e7a949880e6920ec465
+oid sha256:3d3997d2d71496da254deaa8339ab30383266088fadbeb77296cdbc17e681083
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c794e8f1590769642f891be807aaea565ce2ef03feb2f6701d1072683993b5ca
+oid sha256:da0a5926dee98cd799738081ef6596a563cc698aed17000c708c7d665a571d4b
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4a65a6312bd30b99e17460a422429487e35f933075a640659a7e061f47d2ca
+oid sha256:d9c96009cc830916fc0cdef903d45b797a110750d4443bb2ef8ac79515cff705
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d75ff6bd24c5b9f2bcd92e3bca8ca05f4520330d9b4bbbc3cf07c312fdc8ba2
+oid sha256:8b64415b7de70bf69249ffc51fd333c142109d716acc18810cac507645b6345d
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.0775227546691895,
-  "best_model_checkpoint": "output/eminem/checkpoint-1808",
+  "best_metric": 1.9903991222381592,
+  "best_model_checkpoint": "output/eminem/checkpoint-1824",
   "epoch": 4.0,
-  "global_step": 1808,
+  "global_step": 1824,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2212,11 +2212,37 @@
       "eval_samples_per_second": 22.386,
       "eval_steps_per_second": 2.811,
       "step": 1808
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.9689817301781333e-07,
+      "loss": 2.3835,
+      "step": 1810
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 5.860097463115006e-08,
+      "loss": 2.2235,
+      "step": 1815
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.628030220611354e-09,
+      "loss": 2.1558,
+      "step": 1820
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9903991222381592,
+      "eval_runtime": 27.7097,
+      "eval_samples_per_second": 22.844,
+      "eval_steps_per_second": 2.887,
+      "step": 1824
     }
   ],
-  "max_steps": 1808,
-  "num_train_epochs": 4,
-  "total_flos": 1886005886976000.0,
+  "max_steps": 2280,
+  "num_train_epochs": 5,
+  "total_flos": 1902336638976000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2740716c0b718fe72809d1fd0e35d4a082f6a5fd5928fa62e0b59f56579d0256
+oid sha256:9dba50a7dba0f035481d76d60993c89107c299d140e0bb150bc43e690b6c0a16
 size 2671