huggingartists

README.md

@@ -14,7 +14,7 @@ widget:
 <div class="inline-flex flex-col" style="line-height: 1.5;">
     <div class="flex">
         <div
-			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/30a049d2de687550227ba815650eb196.585x585x1.png&#39;)">
+			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/97bcb5755cb9780d76b37726a0ce4bef.1000x1000x1.jpg&#39;)">
         </div>
     </div>
     <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/queen")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1v5o4ijc/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/1ddcmutf/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 Queen's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2apdiv6y) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1dhu8z5q) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2apdiv6y/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1dhu8z5q/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "huggingartists/queen",
+  "_name_or_path": "queen",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -18,7 +18,9 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -35,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.11.3",
+  "transformers_version": "4.16.2",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.775342345237732, "eval_runtime": 3.9684, "eval_samples_per_second": 21.923, "eval_steps_per_second": 2.772, "epoch": 12.0}
+{"eval_loss": 1.0593422651290894, "eval_runtime": 1.2351, "eval_samples_per_second": 74.489, "eval_steps_per_second": 9.716, "epoch": 10.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78164ec45551b127583fec5e4a0f6928dd1f4f77a75658bc2052260c3e93c6dc
+oid sha256:f71c5d51cdf52a930cd7e68b3903da1eb422d09bd06f91080d5d80355a54ba3c
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05aaab90d8caa0c02fb32e76686034b0a99f484a4537df99993a9ff56a1cd41
+oid sha256:0b8a2f7accefebd6dee4b8dea20bafd47f1f9acf8efc62324b4a2287db757050
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eecd5d268e5f975f932bf34dff98dd7e71a2e51f68b094f2ebc1800a6bd5a0f4
+oid sha256:8d37c527c1768f42033ebf3f95e514029cb59df6fe857c02fe5b6c2968b0e7dd
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fe9cc5f8604aa97b538fc3054764ff7cb9b030361ac3a1e8a39c4ddce759080
+oid sha256:f49bf0f2acadddffcdc0a4e3487fd525abbe1771468cbd89c3052c1ed8d61d77
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066420211cafaee663c00dce05f0eac5d610fd3a9b179d73be449c25b47fdfdc
+oid sha256:90d90db3c01e5ca255a7e75446ed55bd62e0e6b8c2052a1a18ccb2f8838ed976
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.775342345237732,
-  "best_model_checkpoint": "output/queen/checkpoint-621",
-  "epoch": 9.0,
-  "global_step": 621,
+  "best_metric": 1.0593422651290894,
+  "best_model_checkpoint": "output/queen/checkpoint-680",
+  "epoch": 10.0,
+  "global_step": 680,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -830,11 +830,91 @@
       "eval_samples_per_second": 22.699,
       "eval_steps_per_second": 2.87,
       "step": 621
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 1.2005173242556402e-05,
+      "loss": 1.3691,
+      "step": 625
+    },
+    {
+      "epoch": 9.26,
+      "learning_rate": 2.2384478845846314e-05,
+      "loss": 1.5005,
+      "step": 630
+    },
+    {
+      "epoch": 9.34,
+      "learning_rate": 3.5218932770313436e-05,
+      "loss": 1.4065,
+      "step": 635
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 4.982671888105515e-05,
+      "loss": 1.3225,
+      "step": 640
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 6.543181473690211e-05,
+      "loss": 1.0367,
+      "step": 645
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 8.120521692221662e-05,
+      "loss": 1.1784,
+      "step": 650
+    },
+    {
+      "epoch": 9.63,
+      "learning_rate": 9.630898093421192e-05,
+      "loss": 1.2778,
+      "step": 655
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 0.00010994073605561679,
+      "loss": 1.3754,
+      "step": 660
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 0.00012137631040942535,
+      "loss": 1.1983,
+      "step": 665
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 0.00013000820178695732,
+      "loss": 1.3077,
+      "step": 670
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 0.0001353778505291435,
+      "loss": 1.4969,
+      "step": 675
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.3263,
+      "step": 680
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.0593422651290894,
+      "eval_runtime": 1.2161,
+      "eval_samples_per_second": 75.649,
+      "eval_steps_per_second": 9.867,
+      "step": 680
     }
   ],
-  "max_steps": 828,
-  "num_train_epochs": 12,
-  "total_flos": 642778398720000.0,
+  "max_steps": 680,
+  "num_train_epochs": 10,
+  "total_flos": 704182026240000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f7066b415f01cd40fe79d9609a25d25e2e5ba0f11a92fd67adab5753419b6f
-size 2863
+oid sha256:9bfe077b70ca57958721fcbf6c5a404f931dd10af1a32aa26767d45cbe093bfa
+size 3055