huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/queen")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1odfy5f2/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/1jdprwq2/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 Queen's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/n5mutjgn) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2lvkoamo) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/n5mutjgn/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2lvkoamo/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.20.0",
+  "transformers_version": "4.20.1",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.7435600757598877, "eval_runtime": 1.9524, "eval_samples_per_second": 44.56, "eval_steps_per_second": 5.634, "epoch": 2.0}
+{"eval_loss": 0.6673863530158997, "eval_runtime": 2.2201, "eval_samples_per_second": 42.79, "eval_steps_per_second": 5.405, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59d4092b6fbaa70e9f950aa8fcb06e8531e931e125851c1d4493cca00a1d6d3
+oid sha256:5426a408b5d5b84e1ae5b6c6ef13577cc7459d4be7cb4670fbc861bdd8c9832b
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c66880bc32b68f34b3eb7af0a61b4e00e160a67a148722eca25b7babef5c4229
+oid sha256:43b7bf14e6413ae5388a8e9590483437185ac7a86bbcfbf97feb2cba965b25a9
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3308c600cab57fc29528fed25a3b6bbe8e7e16d4e20d2e4b9967b339a59a76b
+oid sha256:36a48e1744a8050fe41aa9965ca2432011f5f6dadcaaf7da0753f18e0b167b32
 size 510396521

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad122a9ca484f0a33b6603349e6dcbd96996d2bf9f426d0ada5eb32987c4387e
+oid sha256:2106753fad7f12850372556f05b325a609d5d1918d505246dc95a8ad23713d7d
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:243af1ebed26a3a8d0b96be16a026fc3571686ab7c16190d8dea7c3ff4208aee
+oid sha256:b9400f744e6736bc4247e7cf5592a2fdcb5788998b7af1403eec6453074e2be8
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.7435600757598877,
-  "best_model_checkpoint": "output/queen/checkpoint-69",
-  "epoch": 1.0,
-  "global_step": 69,
+  "best_metric": 0.6673863530158997,
+  "best_model_checkpoint": "output/queen/checkpoint-136",
+  "epoch": 2.0,
+  "global_step": 136,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -100,11 +100,103 @@
       "eval_samples_per_second": 48.039,
       "eval_steps_per_second": 6.074,
       "step": 69
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.926355061606355e-07,
+      "loss": 1.3103,
+      "step": 70
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.5561795752596966e-06,
+      "loss": 0.9826,
+      "step": 75
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.027510448894829e-05,
+      "loss": 0.9993,
+      "step": 80
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.0092474810602806e-05,
+      "loss": 0.8551,
+      "step": 85
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.2486753626613595e-05,
+      "loss": 1.0815,
+      "step": 90
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.6799508616681124e-05,
+      "loss": 0.8781,
+      "step": 95
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 6.227039054081734e-05,
+      "loss": 0.9205,
+      "step": 100
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.807752594969924e-05,
+      "loss": 0.7833,
+      "step": 105
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.338117830043863e-05,
+      "loss": 1.083,
+      "step": 110
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00010736835802938959,
+      "loss": 1.0006,
+      "step": 115
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011929601172133724,
+      "loss": 1.0609,
+      "step": 120
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00012853049599834086,
+      "loss": 0.9702,
+      "step": 125
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00013458123912165544,
+      "loss": 1.0468,
+      "step": 130
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00013712680207144277,
+      "loss": 1.0231,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6673863530158997,
+      "eval_runtime": 2.2427,
+      "eval_samples_per_second": 42.36,
+      "eval_steps_per_second": 5.351,
+      "step": 136
     }
   ],
-  "max_steps": 138,
+  "max_steps": 136,
   "num_train_epochs": 2,
-  "total_flos": 70418202624000.0,
+  "total_flos": 139660591104000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3276c6263f8b9603729e374cfea7b7138a847c1c3c8a37df36295a1f7cfc5e34
+oid sha256:e7e996fa4db6846e691ba9e83e3330ddc142ed2dbd6e677589b0a43edc5c70fa
 size 3311