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/3id5emxt/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/jmcwl2kv/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/39q5c3g1) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1whzvxwj) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/39q5c3g1/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1whzvxwj/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.289399653673172, "eval_runtime": 9.1714, "eval_samples_per_second": 75.888, "eval_steps_per_second": 9.486, "epoch": 4.0}
+{"eval_loss": 0.21771365404129028, "eval_runtime": 30.0637, "eval_samples_per_second": 21.854, "eval_steps_per_second": 2.761, "epoch": 5.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f70e6d24e4d1ab815fe65bf51eae9fe93259a8a8a5bd20827f6f63b72d3cb5
+oid sha256:a3c84e167e98d6bd088c1429cee6bc62ba6d54ab7f3c66eab67e19d635ab2596
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef05eac2e340bed3befe621b5b6755a3256f006542797eb76a9e2c1b580f0383
+oid sha256:afee348b7efad6b1be2a8b10d85601fd94c046b69c8bba8337f0a5bec709098d
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb9b38526ad7fe28ee08f68c01b41e9f1fcc62c9a636cf6f22a8e312c4a333c
+oid sha256:f9b15d9ce61c2310babe315c1bd8cb94b184dbd5e5c313a021c60e754e525a80
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751843372ff16452c5a382bcca779a2ff0cd9510bd89e3c4af9f63092e540657
+oid sha256:0adf8de5d8959718687f938c23efe71b47657476c01a8cecd52658e6e0b44659
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4ece6c3cec4b19efed292f7ef2310750d80298186925496928d2235a909340
+oid sha256:965536734f76c5e6ed923fbf10a7658723a2c2e833c43f9c58cbbc65cf8ac992
 size 623

tokenizer.json

@@ -5,12 +5,12 @@
   "added_tokens": [
     {
       "id": 50256,
-      "special": true,
       "content": "<|endoftext|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.289399653673172,
-  "best_model_checkpoint": "output/eminem/checkpoint-1792",
+  "best_metric": 0.21771365404129028,
+  "best_model_checkpoint": "output/eminem/checkpoint-1812",
   "epoch": 4.0,
-  "global_step": 1792,
+  "global_step": 1812,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2186,11 +2186,43 @@
       "eval_samples_per_second": 75.973,
       "eval_steps_per_second": 9.497,
       "step": 1792
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 4.9300467408522294e-06,
+      "loss": 0.5907,
+      "step": 1795
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 5.853621386191686e-06,
+      "loss": 0.551,
+      "step": 1800
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 6.85263374207898e-06,
+      "loss": 0.6016,
+      "step": 1805
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.92588273195002e-06,
+      "loss": 0.5671,
+      "step": 1810
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.21771365404129028,
+      "eval_runtime": 29.2775,
+      "eval_samples_per_second": 22.44,
+      "eval_steps_per_second": 2.835,
+      "step": 1812
     }
   ],
-  "max_steps": 1792,
-  "num_train_epochs": 4,
-  "total_flos": 1871112241152000.0,
+  "max_steps": 2265,
+  "num_train_epochs": 5,
+  "total_flos": 1891623665664000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f0d5a99deab06022cafa0fcb19bad8061dc9fd864b2318bbf9b7f734d52f288
+oid sha256:a5e73081babceee84261a7b998dd78a63239c51b158835ceac32b4379ba9c29d
 size 3055