huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/enya")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2bm55xog/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/16cuy8yb/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 Enya's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2k7w3aqe) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/il8ldqo8) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2k7w3aqe/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/il8ldqo8/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/enya",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
+  "transformers_version": "4.11.3",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.8410420417785645, "eval_runtime": 0.674, "eval_samples_per_second": 19.287, "eval_steps_per_second": 2.967, "epoch": 1.0}
+{"eval_loss": 2.340635061264038, "eval_runtime": 1.0097, "eval_samples_per_second": 20.799, "eval_steps_per_second": 2.971, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a89ef059675768f8a6abf9b70d7478e133da093e91a525d77e24061a2cc011
+oid sha256:9ae12e33dc4459139dd5cb877f40e563170e76cf02cbf695bc43b702adab4533
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5834d9947ac9b4f50a4967359e7883997f97acf9a5edcfa7d70b99a4b7b40ab9
+oid sha256:edd2fc56baf03a9af9b326a5d797f7133ed613761a70a2b9616d42edd3765ddb
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd41de40e7ab8cda06d52deb06320405dbb7753c1f1d60d43a9c4b88ff126029
+oid sha256:8de39b7c94af97b7d4d823f5bfc290a04eb524dcf4eb2670dad17651e2775335
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b900586c3eb8e502ea5e29725fd152b98e58e8a5c6181d26820be05fa63224c
-size 14567
+oid sha256:f1e3ab4076bbe5dd31c42ee9fb0c980245f8a8ad45b0c6aad32b66a5b7a4ebff
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b29a33773e8cb264d94536fa7121292fc3e454f55f0c744d04636f08d41199
+oid sha256:43864fbfdb282912e10e509b42fed1e4f801db6ebc73cd818d8527ae0c95a8a9
 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/enya", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.8410420417785645,
-  "best_model_checkpoint": "output/enya/checkpoint-15",
-  "epoch": 1.0,
-  "global_step": 15,
+  "best_metric": 2.340635061264038,
+  "best_model_checkpoint": "output/enya/checkpoint-28",
+  "epoch": 2.0,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -32,11 +32,31 @@
       "eval_samples_per_second": 21.042,
       "eval_steps_per_second": 3.237,
       "step": 15
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.333506393059682e-05,
+      "loss": 3.3112,
+      "step": 20
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00012223363969730684,
+      "loss": 3.3235,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.340635061264038,
+      "eval_runtime": 0.9038,
+      "eval_samples_per_second": 23.236,
+      "eval_steps_per_second": 3.319,
+      "step": 28
     }
   ],
-  "max_steps": 15,
-  "num_train_epochs": 1,
-  "total_flos": 15024291840000.0,
+  "max_steps": 28,
+  "num_train_epochs": 2,
+  "total_flos": 27958247424000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f9afaa63f05114771745ef1419e3688f3284c9e8f3035ee25126d0b60779c2
-size 2671
+oid sha256:c109007687b9bfde84137f68d320994073e254c2392a02d65e04e85e66232c4c
+size 2863