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/2aa85f8fdffe5d0552ff319221fc63e4.959x959x1.jpg&#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/10f98dca7bcd1a31222e36374544cad5.1000x1000x1.png&#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/50-cent")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2iekmvbo/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/1291qx5n/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 50 Cent's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1zrybuom) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1igwpphq) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1zrybuom/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1igwpphq/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.15.0",
+  "transformers_version": "4.21.1",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 3.1829922199249268, "eval_runtime": 18.7316, "eval_samples_per_second": 20.82, "eval_steps_per_second": 2.616, "epoch": 3.0}
+{"eval_loss": 3.0555238723754883, "eval_runtime": 7.5342, "eval_samples_per_second": 44.464, "eval_steps_per_second": 5.575, "epoch": 4.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc7b1e66dd4804ccfb9dc1714f49153dd394cb37828b4d409f91f1c2b62adc8
+oid sha256:c31b862d45de3ccaef441f9fa1ef7b2f6652e2fc2f234e0f41fc2603aaf1b945
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9948f38cc1a6abe44b5a4dee4a5cf93797f4b56eee3fb384dcc06fc944da98f9
+oid sha256:61bd3affdd5f277c7a5fa396f629321f2ec69771dc1627813439141a226ef52a
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a35c4f858facf554a582294b1f58c98b5633f4416d25525aad47c8b1d043cf4
-size 510403817
+oid sha256:b0945e2dd7a9b1ceebc48b1ea934a8cae156a24935412485e958f7553a07f3a1
+size 510396521

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c270da9fce7276d12ff26b0a4bcaa95748084c5a24bfdf380b2b8c8b5bdff2
+oid sha256:6c320020a0ace51c3f4a7cf3c6f56a3d1dd0674fae61f1db1544dbd74bfc37ce
 size 14439

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1916ec374b6c0a9df0adb0631f08e8ad04238433d3a103302e9d6c65c1db806
+oid sha256:4418ab9fab32411bcd81f230a37050effcf0af203d9975e195bd2410cbd3f658
 size 623

special_tokens_map.json

@@ -1 +1,5 @@
-{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -1 +1,10 @@
-{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/50-cent", "tokenizer_class": "GPT2Tokenizer"}
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "huggingartists/50-cent",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 3.1829922199249268,
-  "best_model_checkpoint": "output/50-cent/checkpoint-765",
+  "best_metric": 3.0555238723754883,
+  "best_model_checkpoint": "output/50-cent/checkpoint-786",
   "epoch": 3.0,
-  "global_step": 765,
+  "global_step": 786,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -956,11 +956,43 @@
       "eval_samples_per_second": 20.875,
       "eval_steps_per_second": 2.623,
       "step": 765
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.2586318832182472e-06,
+      "loss": 3.1497,
+      "step": 770
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.958637034415764e-07,
+      "loss": 3.0369,
+      "step": 775
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.7746243957364735e-07,
+      "loss": 3.0894,
+      "step": 780
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.93157996134388e-09,
+      "loss": 3.108,
+      "step": 785
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.0555238723754883,
+      "eval_runtime": 7.2147,
+      "eval_samples_per_second": 46.433,
+      "eval_steps_per_second": 5.821,
+      "step": 786
     }
   ],
-  "max_steps": 765,
-  "num_train_epochs": 3,
-  "total_flos": 797985865728000.0,
+  "max_steps": 1048,
+  "num_train_epochs": 4,
+  "total_flos": 819411812352000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0953bfb72e20182c57ba68197da351f78842856132e9f560521cdd9c2df2cb65
-size 2991
+oid sha256:db91ef57c5d38de6898fc617729ddf27eb84a3d3f4675fcb9c0094e4e90223ff
+size 3375