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/2mol6j1a/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/1jvphstz/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/35sq6jaq) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/15ya0ypw) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/35sq6jaq/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/15ya0ypw/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.19.2",
+  "transformers_version": "4.20.0",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.200975701212883, "eval_runtime": 14.714, "eval_samples_per_second": 43.224, "eval_steps_per_second": 5.437, "epoch": 2.0}
+{"eval_loss": 0.16962459683418274, "eval_runtime": 13.6942, "eval_samples_per_second": 44.252, "eval_steps_per_second": 5.55, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69833549ccfd36fe66e772afe6f4a3d07369b965ae5d6a0ecb8bd1a0536b2df
+oid sha256:86c809434f7ba223e0f4932427aff4dd77ca926e41c1cf80cef1468940dc33f9
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d59312be6947afd2ba8011456d4e8908905235d6e1780c6feaddcce691dd0f
+oid sha256:d69eaa2fd8405bcba2bc9d6757374a18123acd399e298991b6dee092e5866cfc
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e59175cb5178adcc41b3c715192961b8befb8944063b8edbaff0c3fe9b07e8e
+oid sha256:ba08fd25ed18420dc4bfd849ebbeb91bed54e82af9e69832076c8c35126e8566
 size 510396521

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e43063477db1b2b70df331c88c4d6e034ea15f0e3e30c9c64fc77e81e122fc
+oid sha256:7d9a3990d4128b6374fa74f68431dc132ace2dfd765c1e8c95339672c1ebb33e
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa23e484404e2ec35aa04932ba167a546a0ca5eb25f20a84b410351d432dbc48
+oid sha256:bc741aec1f1a1d576673177552ef39f4ab62f9d8d11904393f5388f0931779fe
 size 623

special_tokens_map.json

@@ -1 +1,5 @@
-{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -1 +1,10 @@
-{"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/eminem", "tokenizer_class": "GPT2Tokenizer"}
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "huggingartists/eminem",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.200975701212883,
-  "best_model_checkpoint": "output/eminem/checkpoint-456",
+  "best_metric": 0.16962459683418274,
+  "best_model_checkpoint": "output/eminem/checkpoint-459",
   "epoch": 1.0,
-  "global_step": 456,
+  "global_step": 459,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -560,11 +560,19 @@
       "eval_samples_per_second": 42.993,
       "eval_steps_per_second": 5.408,
       "step": 456
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.16962459683418274,
+      "eval_runtime": 12.708,
+      "eval_samples_per_second": 47.687,
+      "eval_steps_per_second": 5.98,
+      "step": 459
     }
   ],
-  "max_steps": 912,
+  "max_steps": 918,
   "num_train_epochs": 2,
-  "total_flos": 475682144256000.0,
+  "total_flos": 478817648640000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b43ec02b3eaa28a980d2e5f3e7ecf8dc4639ef71a3a66137055cf261993e8b5
-size 3247
+oid sha256:101cd019ae7a87de818159c75aa149460e38611ef07323554d4ab03e40a38235
+size 3311