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/2bz9yukx/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/2vaz5xpd/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/twadsp18) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/33jkyt37) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/twadsp18/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/33jkyt37/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.10.3",
+  "transformers_version": "4.11.0",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.0572774410247803, "eval_runtime": 8.579, "eval_samples_per_second": 76.815, "eval_steps_per_second": 9.675, "epoch": 3.0}
+{"eval_loss": 0.784148097038269, "eval_runtime": 30.5311, "eval_samples_per_second": 20.438, "eval_steps_per_second": 2.555, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20eb6424d7a6c8cbca837b1f6497ec1e75285bed5a2fbcf7318eb79224beead
+oid sha256:0f3a9b031e3200df1c61d184c70488f106b11715c82ff46195cdd2ddd04a79aa
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a737b5476b2b64d6ee60403a372008dffd1da427db9730971cae37a6071bc7e
+oid sha256:0349bd3cf8a316858fcf5dad74a6cd76573f7544486a0a1f4fdd1f058a75c504
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9672f687cdc7d48f473c264b25fb9caa69b604b37f2fe3e1ceca64523ce7db7
+oid sha256:1821b8a3e1e0709d148722fbf6e276d0ba0358335793aff16454c4ea733a845b
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a0b6074fa5ecbe34f49d042b57f08cb6d144845cca3e84961e9da0e1a483f0
-size 14503
+oid sha256:a49f5d20fc18c39901c23b9b6ba86d1006ef3fec5986d60cf00042600c5a1ac9
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f818a28238f6ef9ae2087458672f61e23380999bcccd67263d0f0878a46413
+oid sha256:0290e104fb13a007441de2a0eb7394a6eb15648f7c45d56eeaf2cbc6b73be3a8
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.0572774410247803,
-  "best_model_checkpoint": "output/eminem/checkpoint-906",
+  "best_metric": 0.784148097038269,
+  "best_model_checkpoint": "output/eminem/checkpoint-914",
   "epoch": 2.0,
-  "global_step": 906,
+  "global_step": 914,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1108,11 +1108,25 @@
       "eval_samples_per_second": 76.969,
       "eval_steps_per_second": 9.694,
       "step": 906
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.4404038393038775e-05,
+      "loss": 1.2124,
+      "step": 910
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.784148097038269,
+      "eval_runtime": 30.793,
+      "eval_samples_per_second": 20.264,
+      "eval_steps_per_second": 2.533,
+      "step": 914
     }
   ],
-  "max_steps": 1359,
+  "max_steps": 1371,
   "num_train_epochs": 3,
-  "total_flos": 945615863808000.0,
+  "total_flos": 953585270784000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df93b6b7a47ebb391916f854a4982a8eea12fd435c43c61e3d856e3ab44ccbd
-size 2671
+oid sha256:d257532c4b0d231f95f763cddd30c9aa94300b44464ea753808133329804a191
+size 2863