huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/morgenshtern")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/p956kstb/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/2mqz06ef/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 MORGENSHTERN's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1st5hxmj) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1u21f1zw) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1st5hxmj/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1u21f1zw/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.0746197700500488, "eval_runtime": 7.0746, "eval_samples_per_second": 22.051, "eval_steps_per_second": 2.827, "epoch": 13.0}
+{"eval_loss": 1.029100775718689, "eval_runtime": 7.2168, "eval_samples_per_second": 20.508, "eval_steps_per_second": 2.633, "epoch": 21.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c647ce86d1b1a86724518a6df72da43aedb998658e398e70f58daf9a2243c2d2
+oid sha256:22fb23883fc29f2e2299e376a3685d3899aa27180ebd009e6a276dd79c0f549a
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0215949aa5275f39e7df7af91225d000e2c9646cf575dd56a76789468682a08
+oid sha256:6cae6db0edbbd42bbc453b0149987a6ee3a6ba790c60e2925ab382f8c1f160ba
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b502aba936ef42281e40d36ce74875ad930f76b429614a069ad2a0cf5d62940e
+oid sha256:b0d244ecace2e78de24953f6135d7cc932ff6489b68a4c749677efd661e57029
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f7ad53ae8cbda635558cf1458df6c46c041d6541dd1606dd52a4492e1dfbd5
-size 14503
+oid sha256:76d31626c3bac6215c579c04c793834783bc9d247d3009c55526f8f7392b8d8e
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbd7e7d8b60f58c4a16b003557100be8552014654bb06fb1afc69d6829aafac8
+oid sha256:5d04e24471eba096654369d2172acef6ba07c54938134ee47e6aca1b621eca74
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.0746197700500488,
-  "best_model_checkpoint": "output/morgenshtern/checkpoint-1261",
+  "best_metric": 1.029100775718689,
+  "best_model_checkpoint": "output/morgenshtern/checkpoint-1274",
   "epoch": 13.0,
-  "global_step": 1261,
+  "global_step": 1274,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1654,11 +1654,31 @@
       "eval_samples_per_second": 22.241,
       "eval_steps_per_second": 2.851,
       "step": 1261
+    },
+    {
+      "epoch": 12.91,
+      "learning_rate": 2.835385281685176e-06,
+      "loss": 1.0594,
+      "step": 1265
+    },
+    {
+      "epoch": 12.96,
+      "learning_rate": 5.632050517253284e-07,
+      "loss": 1.1527,
+      "step": 1270
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.029100775718689,
+      "eval_runtime": 6.9675,
+      "eval_samples_per_second": 21.242,
+      "eval_steps_per_second": 2.727,
+      "step": 1274
     }
   ],
-  "max_steps": 1261,
-  "num_train_epochs": 13,
-  "total_flos": 1307244036096000.0,
+  "max_steps": 2058,
+  "num_train_epochs": 21,
+  "total_flos": 1320047345664000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869572ff71fc1f7eacca418acad1f3acfe2cf9117bc54dd7f9ecad9664ccf36f
+oid sha256:188b9cc77247d315e833007ec5b6ee4bead6e01dfa5781ac98b51d69684404d5
 size 2671