huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/6ix9ine")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/23c4qor5/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/eqmcaj0r/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 6ix9ine's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/8askquwf) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/s5dpg3h2) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/8askquwf/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/s5dpg3h2/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.566208600997925, "eval_runtime": 2.6338, "eval_samples_per_second": 20.882, "eval_steps_per_second": 2.658, "epoch": 4.0}
+{"eval_loss": 2.4751908779144287, "eval_runtime": 3.052, "eval_samples_per_second": 20.97, "eval_steps_per_second": 2.621, "epoch": 5.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1828e0611eb3dd2b0e31ca17d4310d4d7489f09c72ac60fd8ea14bbf161796e
+oid sha256:b3f1fd139ad3512f861c6cd5592c2ace1fac98271efc42a42e36236dd6c48b59
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a41f3f5703dac31ae7a5401c632b68029d736e86bfffe760b46a0f472c96db60
+oid sha256:aceace990143d629f3db6198ece7069e41e3adcbd2ede64c0751815e4e703dab
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8d9d316dc2aba5868d7f29d4e845259d1702edafe69690c706ad4d698822e2
+oid sha256:dd7892196cf4da7ad9d98e0b4363158ba3daf1bd31982643189b086d83d48268
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21430a2736694d7f20ccf719d4c7704a6abda2499225d98352d67c327ad5baa9
+oid sha256:9a2571a29377ff85a1a70c33edf6c6403f4d3f4301398dc6bfae9afd8ec5e8db
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c6de287d0aeee2c682cd2a01e5e01657f181e757ee594a86aa0945f540d0b1
+oid sha256:851e454e65c7fab7dc2d566df885ced9c351f3fb626f4834f3f43f9a6d1bcacf
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.566208600997925,
-  "best_model_checkpoint": "output/6ix9ine/checkpoint-168",
-  "epoch": 4.0,
-  "global_step": 168,
+  "best_metric": 2.4751908779144287,
+  "best_model_checkpoint": "output/6ix9ine/checkpoint-205",
+  "epoch": 5.0,
+  "global_step": 205,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -236,11 +236,67 @@
       "eval_samples_per_second": 20.835,
       "eval_steps_per_second": 2.652,
       "step": 168
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 9.63352496067802e-06,
+      "loss": 2.2438,
+      "step": 170
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 2.7012936807688713e-05,
+      "loss": 2.4722,
+      "step": 175
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 5.042226894930893e-05,
+      "loss": 2.5159,
+      "step": 180
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 7.646728298233023e-05,
+      "loss": 2.2916,
+      "step": 185
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 0.00010137157954994105,
+      "loss": 2.3591,
+      "step": 190
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 0.00012152415773578518,
+      "loss": 2.7456,
+      "step": 195
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 0.0001340029924949682,
+      "loss": 2.4208,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0001369987139612046,
+      "loss": 2.3052,
+      "step": 205
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.4751908779144287,
+      "eval_runtime": 3.015,
+      "eval_samples_per_second": 21.227,
+      "eval_steps_per_second": 2.653,
+      "step": 205
     }
   ],
-  "max_steps": 168,
-  "num_train_epochs": 4,
-  "total_flos": 172714033152000.0,
+  "max_steps": 205,
+  "num_train_epochs": 5,
+  "total_flos": 210470731776000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecac0d19b2e1f0f637a36c6ba81af1b5f98eeb060b14910c27f5bc5242b68a0d
+oid sha256:60e6f694485954cbb3712355594581b180503eb9abe9206152317c41a5b1ee51
 size 2863