huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/eminem")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/rzzk4mti/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/i4fhzbrj/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 Eminem's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3goym9q5) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1poi2h7i) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3goym9q5/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1poi2h7i/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.16.2",
+  "transformers_version": "4.17.0",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.2587912380695343, "eval_runtime": 28.9992, "eval_samples_per_second": 21.207, "eval_steps_per_second": 2.655, "epoch": 5.0}
+{"eval_loss": 0.21638885140419006, "eval_runtime": 7.4926, "eval_samples_per_second": 75.808, "eval_steps_per_second": 9.476, "epoch": 16.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6502370464fa8cd462a1120ff3ee1dec9d5cb90a566bf81d4ec4ec2871aee3ee
+oid sha256:9b53cf55c5742dfd44f30083b86ae36459beabcbd11195bdaac41d1187bf6903
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea78d837462bd33d0b6f54deeb72fa1e3764e83693c5898b20be034af45e293d
+oid sha256:6dbdcbfbbed9454138a13e687af3e4629daf4c9011020de0b8620c5336aaafe5
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb985697bef42b35a4af505c6b0feac38014cf1700a081b2fee7115c3ec54778
-size 510403817
+oid sha256:aca2cc621206c043e63592cae95f51494033a0b1b40cab5e23ba5095d51fbf90
+size 510404393

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7de0ea18d422a4a904e0e321d0648ef7e938ccc8b5f8f3cda6bbcafb21a6903
+oid sha256:6e8aeaafb3f4610c17ece97e4f8b321dfc495ac314a95aa40c9bfe6baff30177
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da390c8a01b24385c79a732c429de5ff0108495a6ebece5eee2c39f888d039ff
+oid sha256:cf464022adc7eb0c26cafda89e5bc206138120150f9a55ed481cde8b86e0da26
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.2587912380695343,
-  "best_model_checkpoint": "output/eminem/checkpoint-458",
+  "best_metric": 0.21638885140419006,
+  "best_model_checkpoint": "output/eminem/checkpoint-464",
   "epoch": 1.0,
-  "global_step": 458,
+  "global_step": 464,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -560,11 +560,25 @@
       "eval_samples_per_second": 21.243,
       "eval_steps_per_second": 2.66,
       "step": 458
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.656213912947592e-06,
+      "loss": 0.6179,
+      "step": 460
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.21638885140419006,
+      "eval_runtime": 7.4743,
+      "eval_samples_per_second": 75.994,
+      "eval_steps_per_second": 9.499,
+      "step": 464
     }
   ],
-  "max_steps": 2290,
-  "num_train_epochs": 5,
-  "total_flos": 478425710592000.0,
+  "max_steps": 7424,
+  "num_train_epochs": 16,
+  "total_flos": 484304781312000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7a77ffb86041404ae25e05b2064145909205e5d64035e10a124f7b561b78a7
+oid sha256:f57a3894986a975d80afe4e8230dbc97b7c7cf3a77bfec1e24d21961b8e53884
 size 3055