huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/skillet")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3dfttz1c/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/1wmbkzn8/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 Skillet's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3j4hok8c) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3jke6b6i) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3j4hok8c/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3jke6b6i/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.3767073154449463, "eval_runtime": 1.8608, "eval_samples_per_second": 20.421, "eval_steps_per_second": 2.687, "epoch": 1.0}
+{"eval_loss": 2.182462215423584, "eval_runtime": 1.8241, "eval_samples_per_second": 20.832, "eval_steps_per_second": 2.741, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9e4df6148aa13358b5fc0d1d7732ebcd76c703202383ab402bbfbde4f40cde
+oid sha256:494a261cf329c21f2d5a20fd1bf77b6cfdc9e0eecaf3e3e2d5bd414d242c9214
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632a74218c8c93865446ae287401c967c6edac289d04a2e1fde9b9d4ae55f633
+oid sha256:6818a328c91aa8ee84d14bcca87646876943f9475d1bdea2558b2e344f1c0d70
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024c63bfd1728ea1606e9f49b45693548baf611c1bd3a441894dc76ee40d2877
+oid sha256:419ae6d97900e1cf2c292ef2ac616408e51bde90741b105c130919afb01354dc
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5d4ce71149472c91ed8113acdfa27f14f794e25946ca3416a5a2bf011d07a2d
-size 14567
+oid sha256:ce33455ae2ddcb7e4c137d33b3eb3d2db5d53e470ac3f0db274f1725db8326c8
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b187631ec6033019fb457e7347eb2d1876fbc061592b2f57081baca0156b529a
+oid sha256:8d5f77e4998f6148c66889b4624d4dea2feb622ab4d3aec5f547ee5d95d99502
 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/skillet", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.3767073154449463,
-  "best_model_checkpoint": "output/skillet/checkpoint-28",
-  "epoch": 1.0,
-  "global_step": 28,
+  "best_metric": 2.182462215423584,
+  "best_model_checkpoint": "output/skillet/checkpoint-56",
+  "epoch": 2.0,
+  "global_step": 56,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,11 +44,55 @@
       "eval_samples_per_second": 22.256,
       "eval_steps_per_second": 2.928,
       "step": 28
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.7199452243268996e-06,
+      "loss": 2.2694,
+      "step": 30
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.009247481060283e-05,
+      "loss": 2.3714,
+      "step": 35
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.333506393059682e-05,
+      "loss": 2.3801,
+      "step": 40
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.125714365012444e-05,
+      "loss": 2.3492,
+      "step": 45
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00012223363969730684,
+      "loss": 2.3538,
+      "step": 50
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00013676865759867644,
+      "loss": 2.1417,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.182462215423584,
+      "eval_runtime": 1.7149,
+      "eval_samples_per_second": 22.159,
+      "eval_steps_per_second": 2.916,
+      "step": 56
     }
   ],
-  "max_steps": 28,
-  "num_train_epochs": 1,
-  "total_flos": 29264707584000.0,
+  "max_steps": 56,
+  "num_train_epochs": 2,
+  "total_flos": 58398769152000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482e59b3a88c369d967bb53579ab0fd7ddcbb147e0c764e2dae093c8d67fc4a8
+oid sha256:26460a0f39fd310edfb607ce3aaecafe8e443c5d2dae6b1db65bfc5f8444ab1c
 size 2671