huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/lil-nas-x")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/13ndcpsd/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/n5s2tj7p/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 Lil Nas X's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3p5781qk) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/334lnf7p) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3p5781qk/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/334lnf7p/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
+  "transformers_version": "4.10.0",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.6141936779022217, "eval_runtime": 1.3974, "eval_samples_per_second": 20.037, "eval_steps_per_second": 2.862, "epoch": 106.0}
+{"eval_loss": 1.9625495672225952, "eval_runtime": 1.0164, "eval_samples_per_second": 21.645, "eval_steps_per_second": 2.952, "epoch": 8.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e012de5ccfc4b4c18d70aee94f8defbfc1e50f57718ed71910a48c0e2e996780
+oid sha256:3b80cf54e3903aaa086ff55a5ae3584dda39458cc6c3bf59739d8cc7d68790b0
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31152ec3e7ee51f760ec20935ab2868246b309095fe64db579f8d857dc60e25f
+oid sha256:554ae32686dff8e0d3a563c810f5c9af42fa2a9bcdd37f183fa967124a0904f6
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90a5d88426cc944b9b9757165686316e8e8367bafb4aa8f561c8b87fddde8c4a
+oid sha256:b4a7a115b338a3868ea2fe887e0d69462ba75a749533bc9b843aac1df5f8df4e
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4752c512c2a88beb880fae152e08c8dd448d4cc3f5a72c4d66926f865266b7a
+oid sha256:eeb5802e7c97dc239cbd9f140547b94a41551dc6504f88f1c1435547ad81869d
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1491e00f77c720090b01b79de27682170c480dbbeee4b54bb59d93e9dda8447
+oid sha256:2c3fb618ee6e9aa59b1a47fa3c6a9f15a1e92380c65669fceabea70c078e74fd
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.6141936779022217,
-  "best_model_checkpoint": "output/lil-nas-x/checkpoint-133",
-  "epoch": 7.0,
-  "global_step": 133,
+  "best_metric": 1.9625495672225952,
+  "best_model_checkpoint": "output/lil-nas-x/checkpoint-152",
+  "epoch": 8.0,
+  "global_step": 152,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,11 +218,43 @@
       "eval_samples_per_second": 22.091,
       "eval_steps_per_second": 3.156,
       "step": 133
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 3.716937219336464e-06,
+      "loss": 1.9804,
+      "step": 135
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 4.1043693868806114e-05,
+      "loss": 2.296,
+      "step": 140
+    },
+    {
+      "epoch": 7.63,
+      "learning_rate": 9.615630613119378e-05,
+      "loss": 2.1816,
+      "step": 145
+    },
+    {
+      "epoch": 7.89,
+      "learning_rate": 0.0001334830627806635,
+      "loss": 2.0152,
+      "step": 150
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.9625495672225952,
+      "eval_runtime": 0.9643,
+      "eval_samples_per_second": 22.814,
+      "eval_steps_per_second": 3.111,
+      "step": 152
     }
   ],
-  "max_steps": 2014,
-  "num_train_epochs": 106,
-  "total_flos": 134957334528000.0,
+  "max_steps": 152,
+  "num_train_epochs": 8,
+  "total_flos": 154684882944000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe08a4b46827a3aa1d0e4730d532a662db372dd2e4a6888c5273969cfba12e5a
+oid sha256:430a51fdae1a88133b33525b9a58e2fa148b17cab07fc90ee92153a604f99585
 size 2671