huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/coldplay")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1gzc0ns4/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/399heq03/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 Coldplay's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/22vgjn8r) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3o6fr9bq) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/22vgjn8r/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3o6fr9bq/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.5336766242980957, "eval_runtime": 2.7958, "eval_samples_per_second": 21.461, "eval_steps_per_second": 2.861, "epoch": 9.0}
+{"eval_loss": 1.2095028162002563, "eval_runtime": 3.4191, "eval_samples_per_second": 21.643, "eval_steps_per_second": 2.925, "epoch": 19.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06678e316f0244aae1a5d5def2e8ab05ebd44699021c19e283ec3d9b3eb7019
+oid sha256:a8806c168019cbc1ae2ffed46c832caa9529a17675216fdd1c782cc1176e7331
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f2f3a899d9271926fe05e74d2e1e78a5a284bbd2a99b96fa49ccf0da030a8c8
+oid sha256:37ac05510aa6c132c3344e1ec9d0f1e37c7031d848f40767d745da3aa0e66a9b
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f16ce366fea146ff0b814bbb0ee1c52aa946330b16cade31e7d9eb5550b66a
+oid sha256:0a7158419658b030a3d8570b711350a55f73d17342aa9920b8e41aff9c03d4a1
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88fb4b11febc18ef05627a88f778f7e276b66959c10157ee7e09d9fd08d92c2e
-size 14567
+oid sha256:1096f6f012654cb7b05c9d15f0c8c81dff6f30d1dbde8cf0b9489e06f1331a53
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5e135d5638eeea038dbe56656468198b1ccb302b58ca9cca115146d8a6edf2
+oid sha256:b9430296501fbe754e360495552f3a391e4c1ba2be1a491d6867af0670e74711
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.5336766242980957,
-  "best_model_checkpoint": "output/coldplay/checkpoint-450",
-  "epoch": 9.0,
-  "global_step": 450,
+  "best_metric": 1.2095028162002563,
+  "best_model_checkpoint": "output/coldplay/checkpoint-528",
+  "epoch": 11.0,
+  "global_step": 528,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -626,11 +626,117 @@
       "eval_samples_per_second": 22.279,
       "eval_steps_per_second": 2.971,
       "step": 450
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 6.411334533481208e-05,
+      "loss": 1.183,
+      "step": 455
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 8.635498649403306e-05,
+      "loss": 1.514,
+      "step": 460
+    },
+    {
+      "epoch": 9.69,
+      "learning_rate": 0.00010671211798514463,
+      "loss": 1.3301,
+      "step": 465
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 0.0001230240391439787,
+      "loss": 1.5153,
+      "step": 470
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 0.0001335594068833643,
+      "loss": 1.3648,
+      "step": 475
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.3593,
+      "step": 480
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2220196723937988,
+      "eval_runtime": 3.1642,
+      "eval_samples_per_second": 23.386,
+      "eval_steps_per_second": 3.16,
+      "step": 480
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 0.00013355940688336435,
+      "loss": 1.2865,
+      "step": 485
+    },
+    {
+      "epoch": 10.21,
+      "learning_rate": 0.00012302403914397878,
+      "loss": 1.315,
+      "step": 490
+    },
+    {
+      "epoch": 10.31,
+      "learning_rate": 0.00010671211798514499,
+      "loss": 1.237,
+      "step": 495
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 8.635498649403298e-05,
+      "loss": 1.1549,
+      "step": 500
+    },
+    {
+      "epoch": 10.52,
+      "learning_rate": 6.4113345334812e-05,
+      "loss": 1.3219,
+      "step": 505
+    },
+    {
+      "epoch": 10.62,
+      "learning_rate": 4.23479165397549e-05,
+      "loss": 1.2553,
+      "step": 510
+    },
+    {
+      "epoch": 10.73,
+      "learning_rate": 2.3368877084135498e-05,
+      "loss": 1.1603,
+      "step": 515
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 9.190657300387535e-06,
+      "loss": 1.2085,
+      "step": 520
+    },
+    {
+      "epoch": 10.94,
+      "learning_rate": 1.3181297643384459e-06,
+      "loss": 1.2453,
+      "step": 525
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.2095028162002563,
+      "eval_runtime": 3.297,
+      "eval_samples_per_second": 22.445,
+      "eval_steps_per_second": 3.033,
+      "step": 528
     }
   ],
-  "max_steps": 450,
-  "num_train_epochs": 9,
-  "total_flos": 468235321344000.0,
+  "max_steps": 912,
+  "num_train_epochs": 19,
+  "total_flos": 549235851264000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b49270cf7d7730cd41580e35a9163dd952c0d60570cdecffcd61412186ef48
+oid sha256:8634fa1cc14205deda566a1ce3471c09a00adb32b1ca2deb15e6602eb34457d2
 size 2863