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/34iy5awi/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/1gzc0ns4/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/p1oxwu42) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/22vgjn8r) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/p1oxwu42/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/22vgjn8r/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.3194692134857178, "eval_runtime": 1.0619, "eval_samples_per_second": 76.28, "eval_steps_per_second": 10.359, "epoch": 61.0}
+{"eval_loss": 1.5336766242980957, "eval_runtime": 2.7958, "eval_samples_per_second": 21.461, "eval_steps_per_second": 2.861, "epoch": 9.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b47c6d38b14cb8948342f6984a6c1085465ea6d66dc0b0e263b9efdcf12dd4d
+oid sha256:d06678e316f0244aae1a5d5def2e8ab05ebd44699021c19e283ec3d9b3eb7019
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8b48aba8a2ac3780274dff233d2f46b80384823383f633919cb3fff88e3a1a
+oid sha256:1f2f3a899d9271926fe05e74d2e1e78a5a284bbd2a99b96fa49ccf0da030a8c8
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d268187c04aaef8b37af7894fd8c042ea497315e5c23e7d7d5f5175e3c43fc91
+oid sha256:74f16ce366fea146ff0b814bbb0ee1c52aa946330b16cade31e7d9eb5550b66a
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8173196c210c0874e6edb77639fe67968b8a0f875123e25b7002bd9aa763efc
-size 14503
+oid sha256:88fb4b11febc18ef05627a88f778f7e276b66959c10157ee7e09d9fd08d92c2e
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea923f2e0b275d809c555b520c2a11f0ea9d5d9892df660f643bda82951dfca7
+oid sha256:8b5e135d5638eeea038dbe56656468198b1ccb302b58ca9cca115146d8a6edf2
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.3194692134857178,
-  "best_model_checkpoint": "output/coldplay/checkpoint-376",
-  "epoch": 8.0,
-  "global_step": 376,
+  "best_metric": 1.5336766242980957,
+  "best_model_checkpoint": "output/coldplay/checkpoint-450",
+  "epoch": 9.0,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -520,11 +520,117 @@
       "eval_samples_per_second": 75.98,
       "eval_steps_per_second": 10.318,
       "step": 376
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 8.979856581412133e-05,
+      "loss": 1.3418,
+      "step": 380
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 0.0001089220683072637,
+      "loss": 1.3258,
+      "step": 385
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 0.00012409856581412136,
+      "loss": 1.67,
+      "step": 390
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 0.00013384247701784757,
+      "loss": 1.6416,
+      "step": 395
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.5041,
+      "step": 400
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.550144910812378,
+      "eval_runtime": 2.6997,
+      "eval_samples_per_second": 22.225,
+      "eval_steps_per_second": 2.963,
+      "step": 400
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 0.0001338424770178476,
+      "loss": 1.3775,
+      "step": 405
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 0.00012409856581412158,
+      "loss": 1.3052,
+      "step": 410
+    },
+    {
+      "epoch": 8.3,
+      "learning_rate": 0.00010892206830726361,
+      "loss": 1.4469,
+      "step": 415
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 8.979856581412145e-05,
+      "loss": 1.5571,
+      "step": 420
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 6.859999999999995e-05,
+      "loss": 1.3572,
+      "step": 425
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 4.740143418587868e-05,
+      "loss": 1.5739,
+      "step": 430
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 2.8277931692736505e-05,
+      "loss": 1.4984,
+      "step": 435
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 1.3101434185878506e-05,
+      "loss": 1.4842,
+      "step": 440
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 3.3575229821524526e-06,
+      "loss": 1.3847,
+      "step": 445
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.0,
+      "loss": 1.3742,
+      "step": 450
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.5336766242980957,
+      "eval_runtime": 2.6931,
+      "eval_samples_per_second": 22.279,
+      "eval_steps_per_second": 2.971,
+      "step": 450
     }
   ],
-  "max_steps": 2867,
-  "num_train_epochs": 61,
-  "total_flos": 391938048000000.0,
+  "max_steps": 450,
+  "num_train_epochs": 9,
+  "total_flos": 468235321344000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7042b00f38d89f1720e38aa30d3c0f04599b070773bf507b3a660f4d7684fea2
+oid sha256:b8b49270cf7d7730cd41580e35a9163dd952c0d60570cdecffcd61412186ef48
 size 2863