huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/the-69-eyes")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/18m20vda/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/26sibipb/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 69 Eyes's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/pzviwm1c) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1mjcdm16) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/pzviwm1c/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1mjcdm16/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/the-69-eyes",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4347fa24f724f6af375c0c142ef50a04189a351b0756ef0d2d0f4ac953bc108a
+oid sha256:6d2fd5b1afaf116a39f755e26296380d3eec8406fd70e53654a002a8db8cbaae
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e514d69d00f69b68d61d0a8d88bb06402ddebef2d1871ce40f613a92660c88fc
+oid sha256:e2f16b0e107c7209482b6190ad42405b8c3463c0c12724c2ab00a8f456fe970a
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:002ecc0839dfba4944e9311daffde41b40a4fa1f233cb5e4e199ae2bbfa68d6c
+oid sha256:147141a198f50348eec12a8be8748e7bcac887ef3123868663aa533c954ffb66
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d81ac468f505cb376110a9f2607d5f0dc0e8ddbae28e3da62e1b998978a77b
+oid sha256:42f832651a0accfa4311d38c743dbc50c813115218404d96324bcfdb29ee00e8
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3759f0274d6462c99515ad4f587a39c595bfc6a862d6d53aec4d5f4c94343a76
+oid sha256:86d137ee262f4b00e272a51ae406d7a6210993de30d2e72955bafb1afdce9bf1
 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-69-eyes", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "global_step": 17,
+  "epoch": 2.0,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -24,11 +24,29 @@
       "learning_rate": 4.6324050628611986e-06,
       "loss": 2.9096,
       "step": 15
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.0275104488948473e-05,
+      "loss": 2.9067,
+      "step": 20
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 6.227039054081748e-05,
+      "loss": 2.6172,
+      "step": 25
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011929601172133719,
+      "loss": 2.7089,
+      "step": 30
     }
   ],
-  "max_steps": 17,
-  "num_train_epochs": 1,
-  "total_flos": 17637212160000.0,
+  "max_steps": 34,
+  "num_train_epochs": 2,
+  "total_flos": 35274424320000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0dac2582e3a9da517fa3023d708c08cf2db74791dc5160e2bc682d22ecc4d38
+oid sha256:e545d99cd3fbc4df90a4159c3c1fd0083fe9f8c064f6be6b842e2fa9c052d75c
 size 2671