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/df75ede64ffcf049727bfbb01d323081.400x400x1.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/c771d3ee1c0969503cdaf34edf76f38a.400x400x1.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/the-beatles")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/h0p5r5wf/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/1twc71z8/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 The Beatles's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3j3numex) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3vbolrfq) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3j3numex/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3vbolrfq/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/the-beatles",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
+  "transformers_version": "4.10.2",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 2.5396728515625, "eval_runtime": 7.0101, "eval_samples_per_second": 22.111, "eval_steps_per_second": 2.853, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db2d69e71da261c15f87771242760b5d665f3cd57929b4e55ae317c32b104c5
+oid sha256:f3f36c2f7c7ddcb5a0ba27a0a735f4eeea2faf652a081d5446fcfd3063a5e91d
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46255a18333cf38e21887ef4b8da598321d99f39e25b9411ac313092cbd9901e
+oid sha256:01d0c006bc4779d8568c0522e5b4dffe3f82a222541b07e498cafa70e35560b2
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a8b57969a024e20e190b1f1ebf8da11b0ee5b5d48503133ab68ffc96d0fb4a
+oid sha256:24cb962a13630d160fb8f252859dfc4a16bbf489188271190908493e98b8bd48
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce591269ee5842453fd2dfb941b08afa9dcb7fca36bb49b0a4b1fe61941c6e86
-size 14503
+oid sha256:bf4704f411f7c64c230e3a475c23d3112f179d24c4827bb93cc3c981ff7942d5
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6bca18872f98ea1f3067aeed2ea8466e4f17513f6b052e942280bbb7b375238
+oid sha256:f1403a00d87496c96b524036f4c8c82be5fad3d7a1c0f59e9835444c0e5d9468
 size 623

tokenizer_config.json

@@ -1 +1 @@
-{"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": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
+{"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/the-beatles", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "global_step": 145,
+  "best_metric": 2.5396728515625,
+  "best_model_checkpoint": "output/the-beatles/checkpoint-250",
+  "epoch": 2.0,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -180,11 +180,145 @@
       "learning_rate": 0.0,
       "loss": 2.8741,
       "step": 145
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3101434185878598e-05,
+      "loss": 2.452,
+      "step": 150
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.8592752158891168e-05,
+      "loss": 2.5133,
+      "step": 155
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.4872714303239897e-05,
+      "loss": 2.3717,
+      "step": 160
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.184228186444085e-05,
+      "loss": 2.5966,
+      "step": 165
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.939154059863605e-05,
+      "loss": 2.5,
+      "step": 170
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.74014341858786e-05,
+      "loss": 2.4988,
+      "step": 175
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5.574564181941929e-05,
+      "loss": 2.6535,
+      "step": 180
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 6.429257036028911e-05,
+      "loss": 2.5217,
+      "step": 185
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.290742963971086e-05,
+      "loss": 2.5988,
+      "step": 190
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.145435818058069e-05,
+      "loss": 2.3431,
+      "step": 195
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.979856581412138e-05,
+      "loss": 2.5257,
+      "step": 200
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.780845940136392e-05,
+      "loss": 2.5586,
+      "step": 205
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00010535771813555913,
+      "loss": 2.4987,
+      "step": 210
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00011232728569676008,
+      "loss": 2.1873,
+      "step": 215
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011860724784110881,
+      "loss": 2.4757,
+      "step": 220
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.0001240985658141214,
+      "loss": 2.2676,
+      "step": 225
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00012871463825100903,
+      "loss": 2.5652,
+      "step": 230
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013238266693193403,
+      "loss": 2.3751,
+      "step": 235
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0001350448048534241,
+      "loss": 2.5399,
+      "step": 240
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00013665906851017317,
+      "loss": 2.0634,
+      "step": 245
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001372,
+      "loss": 2.3758,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.5396728515625,
+      "eval_runtime": 6.8424,
+      "eval_samples_per_second": 22.653,
+      "eval_steps_per_second": 2.923,
+      "step": 250
     }
   ],
-  "max_steps": 145,
-  "num_train_epochs": 1,
-  "total_flos": 150765502464000.0,
+  "max_steps": 250,
+  "num_train_epochs": 2,
+  "total_flos": 260246863872000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31bc268644de6146180d3e698e67bd8d1d36627678947674421707172860117
+oid sha256:ce42f54e5d08f9c1684b110fb05bbd513348d13b90f70989ccfab6b0fc97e2f0
 size 2671