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/cy7nthpy/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/m9zgb2vd/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/2hgvstnt) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/ys11x7xp) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2hgvstnt/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/ys11x7xp/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.3747466802597046, "eval_runtime": 7.026, "eval_samples_per_second": 21.207, "eval_steps_per_second": 2.704, "epoch": 13.0}
+{"eval_loss": 1.1428929567337036, "eval_runtime": 7.9754, "eval_samples_per_second": 21.441, "eval_steps_per_second": 2.758, "epoch": 12.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a0ed22dbf6a9bd7a962b4206529c5b815a5266affe74c8fbab8d7c67c678b8
+oid sha256:355b1113b602cec6460d0f66c7318d9309a2d51638c83d166b18454dad89bd5c
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae486a04cf9c310967320cdf13a21303624d9c5b8c37c7e267c7dde9079eb63b
+oid sha256:b59045dfc4ed4d02f26069b5cc05179d371e5fa764cb055d1a830e8c0382acd4
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d329a8e2a96548eb477ceb62baefe02d077414bc0c397d42965b651a2fa187
+oid sha256:3dc5e091ec6cb7f165ce89c1bc5ddd005d9d36c5598145f3b40df6a6b9c583cb
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f877e4bcb76e9ecc9bb481c6d8b7ee9505646a43bb655295a3a04f05d40ce503
-size 14503
+oid sha256:c63f55fe8fef4a486cd65797398129fb611c4447a861094695f459a188101b5d
+size 14631

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0aee656c44c094a4ce15e92ad37f3cff7d7b2a11b7b8ea601ce5c5f3e729f2
+oid sha256:e825854d4daee9b3baa1369de3bcfdc0baa5bcd259634286f62b5236f6992a0f
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.3747466802597046,
-  "best_model_checkpoint": "output/morgenshtern/checkpoint-1078",
-  "epoch": 11.0,
-  "global_step": 1078,
+  "best_metric": 1.1428929567337036,
+  "best_model_checkpoint": "output/morgenshtern/checkpoint-1140",
+  "epoch": 12.0,
+  "global_step": 1140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1408,11 +1408,97 @@
       "eval_samples_per_second": 21.247,
       "eval_steps_per_second": 2.709,
       "step": 1078
+    },
+    {
+      "epoch": 11.37,
+      "learning_rate": 4.1043693868806304e-05,
+      "loss": 1.1875,
+      "step": 1080
+    },
+    {
+      "epoch": 11.42,
+      "learning_rate": 5.17596955821411e-05,
+      "loss": 1.3125,
+      "step": 1085
+    },
+    {
+      "epoch": 11.47,
+      "learning_rate": 6.293505690059783e-05,
+      "loss": 1.2444,
+      "step": 1090
+    },
+    {
+      "epoch": 11.53,
+      "learning_rate": 7.426494309940222e-05,
+      "loss": 1.3268,
+      "step": 1095
+    },
+    {
+      "epoch": 11.58,
+      "learning_rate": 8.544030441785894e-05,
+      "loss": 1.3066,
+      "step": 1100
+    },
+    {
+      "epoch": 11.63,
+      "learning_rate": 9.615630613119375e-05,
+      "loss": 1.2542,
+      "step": 1105
+    },
+    {
+      "epoch": 11.68,
+      "learning_rate": 0.00010612064364719844,
+      "loss": 1.246,
+      "step": 1110
+    },
+    {
+      "epoch": 11.74,
+      "learning_rate": 0.00011506151581352574,
+      "loss": 1.2672,
+      "step": 1115
+    },
+    {
+      "epoch": 11.79,
+      "learning_rate": 0.00012273503894459246,
+      "loss": 1.2702,
+      "step": 1120
+    },
+    {
+      "epoch": 11.84,
+      "learning_rate": 0.00012893189933276523,
+      "loss": 1.3417,
+      "step": 1125
+    },
+    {
+      "epoch": 11.89,
+      "learning_rate": 0.00013348306278066356,
+      "loss": 1.2473,
+      "step": 1130
+    },
+    {
+      "epoch": 11.95,
+      "learning_rate": 0.00013626438541342674,
+      "loss": 1.1708,
+      "step": 1135
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.1564,
+      "step": 1140
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.1428929567337036,
+      "eval_runtime": 7.9608,
+      "eval_samples_per_second": 21.48,
+      "eval_steps_per_second": 2.764,
+      "step": 1140
     }
   ],
-  "max_steps": 1274,
-  "num_train_epochs": 13,
-  "total_flos": 1118199250944000.0,
+  "max_steps": 1140,
+  "num_train_epochs": 12,
+  "total_flos": 1182346444800000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f1578ed0263fa3cde0930e9e148d11708f37717f22b869ef9dc3fb789f5d60
+oid sha256:54fa34a299d69d7a3304670c0272e7c9b90a901c33b2a0c579d8b695f9d47857
 size 2671