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/19gci1n4/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/ofa47ov0/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/1je8v3eb) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/11x8tlht) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1je8v3eb/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/11x8tlht/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.3754318356513977, "eval_runtime": 8.7776, "eval_samples_per_second": 75.989, "eval_steps_per_second": 9.57, "epoch": 2.0}
+{"eval_loss": 0.31595703959465027, "eval_runtime": 694.9722, "eval_samples_per_second": 0.892, "eval_steps_per_second": 0.112, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8772f90ce04a5e850ff75ef5b602d4536ede75be0d83e670f7afd86b395b8be
+oid sha256:051a2aa5612a00aefd0743508426504ceff0614f418bc3ffd2fae00bc7e2e01a
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7b9dddb75ac5e672146795acb35761f28f2d68a6d466ffa6fbe24010202e41
-size 995604017
+oid sha256:593f24adf357165ae7c067bfdec9e2e06abf005b482f2df7913d65b234eb4c23
+size 995599857

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e02f4d6ce2f227c58ed2904a072b80525c2072f5f7059f121957fe78ea4da6ff
-size 510403817
+oid sha256:d4f3731cebd57313c0396ec7ec7278cbf2f4370924b703a6aa6ddad82d193a89
+size 510401385

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4672dcf145f0b3d344693db21f586bc42e32415a69a154df09e50a321a49e325
-size 14503
+oid sha256:9a26923031d40478a72fa6bcd5409ab432e85028c059b7b08da05ecaa1c93850
+size 13547

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9dc76c688deef1eb9e98c1444375032667a38879fb6756f454c9b01f7d1a93d
+oid sha256:2587493ffef7a83ac744fa257014e43dd335fe886fa10856cabfbe630d057f3b
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.3754318356513977,
-  "best_model_checkpoint": "output/eminem/checkpoint-904",
+  "best_metric": 0.31595703959465027,
+  "best_model_checkpoint": "output/eminem/checkpoint-916",
   "epoch": 2.0,
-  "global_step": 904,
+  "global_step": 916,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1102,11 +1102,37 @@
       "eval_samples_per_second": 76.147,
       "eval_steps_per_second": 9.59,
       "step": 904
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.956064306819408e-05,
+      "loss": 0.7479,
+      "step": 905
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 4.7311949670299134e-05,
+      "loss": 0.7304,
+      "step": 910
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.508829441538651e-05,
+      "loss": 0.666,
+      "step": 915
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.31595703959465027,
+      "eval_runtime": 690.3622,
+      "eval_samples_per_second": 0.898,
+      "eval_steps_per_second": 0.113,
+      "step": 916
     }
   ],
-  "max_steps": 904,
-  "num_train_epochs": 2,
-  "total_flos": 943264235520000.0,
+  "max_steps": 1374,
+  "num_train_epochs": 3,
+  "total_flos": 955022376960000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5f3fe6c4b31e270bb58aea5ef8c2bf476b58d1810de27a6c9bec70157c8923
+oid sha256:98ff7520005bd1b7cd3b14407c7fae7975d1a94564c7ae5c3bb82fb25346e68c
 size 3055