huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/pharaoh")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3kao1xf5/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/jefxst5w/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 PHARAOH's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/xsxegmjq) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1fqlqxjo) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/xsxegmjq/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1fqlqxjo/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.11.2",
+  "transformers_version": "4.11.3",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.7224986553192139, "eval_runtime": 22.1306, "eval_samples_per_second": 22.548, "eval_steps_per_second": 2.847, "epoch": 2.0}
+{"eval_loss": 1.6883338689804077, "eval_runtime": 19.6397, "eval_samples_per_second": 22.607, "eval_steps_per_second": 2.851, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2b4c5319db04b9872d2055b5b79d1b4807f1c3915b4626047165c4d8e7d4ec
+oid sha256:484cb86e3f52479a236c203dabe5e4e5f4963b14df3281ba549a73b1e7a9af01
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26bbacfce71425f128a87fdb7029463499be8bc995eb14eb839740e92b47317a
+oid sha256:63018a2ad54b6c6a33ce78abf8194353639485350842ab974fa3c1670b92825a
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff62d0348d173b28829e07fec717386e9eef99e506d12c023aa35c55239ae7d
+oid sha256:d21702f9a805941e1ce2a37d267084c86a60112567810eb89dcaeb07c9fc68a5
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da0f194b462662f09bef1ea47010e6352ae99c4cb094909f982d2deeb47ae8b
-size 14567
+oid sha256:30d4900f8326487fb775920085a48084a08ba78e6bcfb99648ba03dd0e37557f
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ed819f11a0f4645df58a01f50e8c26eb756310ea7f77b118bb1ec57797118f8
+oid sha256:da9ebf71c2208f03e5a6aa50f8cb521e72774afec2ec08cfe12ef435108ef2fb
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.7224986553192139,
-  "best_model_checkpoint": "output/pharaoh/checkpoint-167",
+  "best_metric": 1.6883338689804077,
+  "best_model_checkpoint": "output/pharaoh/checkpoint-174",
   "epoch": 1.0,
-  "global_step": 167,
+  "global_step": 174,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -212,11 +212,25 @@
       "eval_samples_per_second": 22.454,
       "eval_steps_per_second": 2.835,
       "step": 167
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.5909924568597513e-06,
+      "loss": 1.4675,
+      "step": 170
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6883338689804077,
+      "eval_runtime": 18.8954,
+      "eval_samples_per_second": 23.498,
+      "eval_steps_per_second": 2.964,
+      "step": 174
     }
   ],
-  "max_steps": 334,
+  "max_steps": 348,
   "num_train_epochs": 2,
-  "total_flos": 174412431360000.0,
+  "total_flos": 181597962240000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0544ae26ed18e0692923459bb51b32637aeec0f8caa1502a1b6bf0910ecd6d
+oid sha256:f5f224f4b34842037ca5146b3d9ac77172108df521b4d2b1e99dad44209ed521
 size 2863