huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/bring-me-the-horizon")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1yuqm1pv/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/1e9181i6/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 Bring Me The Horizon's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/z98a5j5r) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3p7pncir) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/z98a5j5r/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3p7pncir/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.761746883392334, "eval_runtime": 0.4813, "eval_samples_per_second": 74.8, "eval_steps_per_second": 10.389, "epoch": 52.0}
+{"eval_loss": 1.3656095266342163, "eval_runtime": 0.4403, "eval_samples_per_second": 74.943, "eval_steps_per_second": 11.355, "epoch": 108.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f60e50a7e388c49df33a2cac5abe57958ed061c6525713fbbaf0e72692b8751
+oid sha256:3ff98a92d7a8b2e431f9a5a76dd5a5df2cc58d7364acc5e1f5d951bcf0359ec4
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aec99ac123784c1df18282b656728c10ab998edaa76607406f49892e8c5d190
+oid sha256:4326008d729e27a10c347bbb6a46bd8799a6937e7c1eead85f7e90067bcb0243
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00a416d9b660bc7b7cd01571f1569a51e5c89dfe326c7ea762cb31673f6bdd8a
+oid sha256:b6cd18063e45fc379977b2bec642a11331a4fe8b17068ee3c6c7ceb85156ee9e
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9eb709ab35df7f70905c14ca74e38db768088a1b8d7f8fd0df5af8ff6128c9
+oid sha256:41c13ff59225bf75f6e3a42ec434ae273bb624cc97eb69019e900e7a38315153
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bbb036f11beb59109336ec9fefde1522b1dc6499163e8831bd87d849eba417d
+oid sha256:6113b0488c437ba8d289a92febabd7916f0db341f7e47637a541e44c487c9485
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.761746883392334,
-  "best_model_checkpoint": "output/bring-me-the-horizon/checkpoint-208",
+  "best_metric": 1.3656095266342163,
+  "best_model_checkpoint": "output/bring-me-the-horizon/checkpoint-216",
   "epoch": 8.0,
-  "global_step": 208,
+  "global_step": 216,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,11 +316,31 @@
       "eval_samples_per_second": 74.353,
       "eval_steps_per_second": 10.327,
       "step": 208
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 0.00012115064879796188,
+      "loss": 1.688,
+      "step": 210
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 0.00013673615134109727,
+      "loss": 1.5172,
+      "step": 215
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.3656095266342163,
+      "eval_runtime": 0.4451,
+      "eval_samples_per_second": 74.143,
+      "eval_steps_per_second": 11.234,
+      "step": 216
     }
   ],
-  "max_steps": 1352,
-  "num_train_epochs": 52,
-  "total_flos": 215043342336000.0,
+  "max_steps": 2916,
+  "num_train_epochs": 108,
+  "total_flos": 222490165248000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a61175f6b4282876536474ec422652e78dcd99a973713a9795eb16ce4347ccb
+oid sha256:77d7737b562948aaba74d132cdb2242f8cd3659133b02f42a93887fc2f475c32
 size 2863