huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/nirvana")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2so60o7u/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/plmwg217/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 Nirvana's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/l6zav1kr) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2aaxwzd4) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/l6zav1kr/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2aaxwzd4/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.128573179244995, "eval_runtime": 1.2287, "eval_samples_per_second": 43.137, "eval_steps_per_second": 5.697, "epoch": 2.0}
+{"eval_loss": 1.7358663082122803, "eval_runtime": 2.0349, "eval_samples_per_second": 20.64, "eval_steps_per_second": 2.949, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1740b9403c2980e1c12ea39ca34dd90e719cb426af2e560c4662fb685a4adc5c
+oid sha256:38b8911734a29e325912427efb96ad710eeebdec940f173c4c1cdf4bd6295893
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c7d18d91a68d3aac0f231a3453ae4f8448552fe1cceca43dfeddf734b115cf
+oid sha256:8ea53252af8c636e7d87ccfe4ffa643cb49756436eab6186e4214ea668b415a6
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:190fc0c852d0ebcb0d529ca1ef8faf27bb0e63a90b3312da7edff4f56cd84c70
+oid sha256:75c2f6598fea7212344467f26fdd0991f32656d8a34cf5910e5c27adb467fa3d
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8690557d45fc8d72f6eb673bd42b9a6c47364d62cbc2a5af224d1d6fa8d651
+oid sha256:379e3990b5cff526d3b72fba15374693b30ed8e1821d3514ef232ad47d9ec9f7
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95317d63b9a0922ed3de67fdcb9f6bbf4898f9cd35c41f60f3577d5b1e618ec0
+oid sha256:5704cdbfa3a8ad0fca4ee30e2feb20b3d392393975fb15db2691fbf243dcbce0
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.128573179244995,
-  "best_model_checkpoint": "output/nirvana/checkpoint-72",
-  "epoch": 2.0,
-  "global_step": 72,
+  "best_metric": 1.7358663082122803,
+  "best_model_checkpoint": "output/nirvana/checkpoint-111",
+  "epoch": 3.0,
+  "global_step": 111,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,11 +114,75 @@
       "eval_samples_per_second": 44.396,
       "eval_steps_per_second": 5.864,
       "step": 72
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8826501369476318,
+      "eval_runtime": 1.8444,
+      "eval_samples_per_second": 22.772,
+      "eval_steps_per_second": 3.253,
+      "step": 74
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.0001369528677140173,
+      "loss": 2.0939,
+      "step": 75
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00012848876816285752,
+      "loss": 2.1654,
+      "step": 80
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.00010939183589447406,
+      "loss": 2.0452,
+      "step": 85
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 8.305259792170682e-05,
+      "loss": 1.7357,
+      "step": 90
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 5.414740207829316e-05,
+      "loss": 2.0788,
+      "step": 95
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.7808164105525978e-05,
+      "loss": 1.928,
+      "step": 100
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.711231837142545e-06,
+      "loss": 1.9376,
+      "step": 105
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 2.4713228598268823e-07,
+      "loss": 1.9652,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.7358663082122803,
+      "eval_runtime": 1.8478,
+      "eval_samples_per_second": 22.729,
+      "eval_steps_per_second": 3.247,
+      "step": 111
     }
   ],
-  "max_steps": 72,
-  "num_train_epochs": 2,
-  "total_flos": 73161768960000.0,
+  "max_steps": 111,
+  "num_train_epochs": 3,
+  "total_flos": 112878157824000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ccf6b2194f29afd6fd696a5ff25947b9d920926b5a6ac01723ed2e5798c9d44
+oid sha256:d4d2cede8ad0eb56c1a914509bcb224f91e3e03e5504f88d252a2fa457cfb418
 size 3055