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/ig4q4eqf/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/2gdiva6q/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/db57x0am) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/13beiwnf) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/db57x0am/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/13beiwnf/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/queen",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.10.0",
+  "transformers_version": "4.10.2",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.78603196144104, "eval_runtime": 4.4505, "eval_samples_per_second": 20.896, "eval_steps_per_second": 2.696, "epoch": 1.0}
+{"eval_loss": 2.3717236518859863, "eval_runtime": 4.3967, "eval_samples_per_second": 21.607, "eval_steps_per_second": 2.729, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b955ad1d98d60e4a56ea65cd7af69546400a28f421c2801d0ef8b6fd2d9ea437
+oid sha256:502d1eca67475172a0f7e73acfe65ee0982960cae78a2b5e5553c81196e5486f
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfeeba500d22510553a572de22a25ea0707e4a392bc1f3af82ca455b76331fd0
+oid sha256:50eefa38edcc45ea891b86bb4da4f52375500fba7bb5584d8cdb052e5223ca88
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ba360ecd74841426dc0cd5e0158e6e01aa6f85266b3ee694feaf2090dd4700
+oid sha256:a5e0293710fde0a4aceadc99d7a89a6f9829daedae2710b8bf9821bc4ca243d0
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d6b4e2addd40ee3dbf3862c476aa351cc6b5d909581f28b2888fbdee737084a
+oid sha256:1191b4ca1a5f132d0d48f14b4540315157d0debe4480006a34a7119f47c28f6a
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dec6c7b398d46bf0643dddb205917b4bc646cca40c919a70adace10f69e2863
+oid sha256:18209b36204372bc8bd57462514f70b2cc7d1fa3bea72f64e7301510fe0e371f
 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/queen", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.78603196144104,
-  "best_model_checkpoint": "output/queen/checkpoint-68",
-  "epoch": 1.0,
-  "global_step": 68,
+  "best_metric": 2.3717236518859863,
+  "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,
@@ -92,11 +92,103 @@
       "eval_samples_per_second": 21.192,
       "eval_steps_per_second": 2.734,
       "step": 68
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.926355061606279e-07,
+      "loss": 2.8201,
+      "step": 70
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.55617957525975e-06,
+      "loss": 2.7876,
+      "step": 75
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.0275104488948473e-05,
+      "loss": 2.8738,
+      "step": 80
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.009247481060283e-05,
+      "loss": 2.6439,
+      "step": 85
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.2486753626613365e-05,
+      "loss": 2.5993,
+      "step": 90
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.679950861668151e-05,
+      "loss": 2.7072,
+      "step": 95
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 6.227039054081748e-05,
+      "loss": 2.7465,
+      "step": 100
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.807752594969911e-05,
+      "loss": 2.5926,
+      "step": 105
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.338117830043867e-05,
+      "loss": 2.7178,
+      "step": 110
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00010736835802938978,
+      "loss": 2.7027,
+      "step": 115
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011929601172133719,
+      "loss": 2.4457,
+      "step": 120
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00012853049599834097,
+      "loss": 2.6806,
+      "step": 125
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00013458123912165538,
+      "loss": 2.4508,
+      "step": 130
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00013712680207144277,
+      "loss": 2.6492,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.3717236518859863,
+      "eval_runtime": 4.3106,
+      "eval_samples_per_second": 22.039,
+      "eval_steps_per_second": 2.784,
+      "step": 136
     }
   ],
-  "max_steps": 68,
-  "num_train_epochs": 1,
-  "total_flos": 70679494656000.0,
+  "max_steps": 136,
+  "num_train_epochs": 2,
+  "total_flos": 141097697280000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f64a8be8343c77766c582ca358c4ea6417470b4fe54e9cb6521375a994a4c0
+oid sha256:fe033cb76b844ba6d85ac8b88771923eea234dc7f7b0240e79578bf023ae7efa
 size 2671