huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/face")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1dmct9sw/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/xtozoqtm/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 FACE's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3otnah8o) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/knkqp5iy) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3otnah8o/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/knkqp5iy/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/face",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.7059965133666992, "eval_runtime": 8.746, "eval_samples_per_second": 22.296, "eval_steps_per_second": 2.858, "epoch": 2.0}
+{"eval_loss": 1.536595344543457, "eval_runtime": 8.7966, "eval_samples_per_second": 22.281, "eval_steps_per_second": 2.842, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f694909ce939b2187156705b4fd647b0b2a00ad2041941dfde0b0712d3f44637
+oid sha256:a352dc2cb017f7537f484bbbd8674249ff6c9a5d0b9731ae3ead2468a57e2ed9
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0da00690b0b7fc97b4a072f81e5b4b37ad550b9ade55e57f69b85532cd94a81b
+oid sha256:22b89f9cd6657751dd2e461644ea376c8ac45cdaa75772ffdfea8283df3c3796
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59bad929cfa9ab4b603c5eafc65f453980979aef78d90b079446a704b2fa1c96
+oid sha256:83af0ad5904348f48de9db72cfdbe286540f30f4acb0c0e959c897788b30f4fa
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a2448bee8c48598a482e8f0244dbeea82e24f9583900c96093b61edc578387
-size 14503
+oid sha256:34c56094291dd7460e0ba6cf9174a82a82f05fa0dfbe9f60c1626e93605a150c
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4c9151b782acfc3e2cb37cc47d07656048381fd905bdb28d282ab7d8f1a8a1
+oid sha256:956abbf6e3c8b654d3a4e4b974a1c0bdb11f8a34b79cc43dfbd9f599fb3a3905
 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/face", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.7059965133666992,
-  "best_model_checkpoint": "output/face/checkpoint-268",
-  "epoch": 2.0,
-  "global_step": 268,
+  "best_metric": 1.536595344543457,
+  "best_model_checkpoint": "output/face/checkpoint-402",
+  "epoch": 3.0,
+  "global_step": 402,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -340,11 +340,181 @@
       "eval_samples_per_second": 22.706,
       "eval_steps_per_second": 2.911,
       "step": 268
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.0001371246011559198,
+      "loss": 1.731,
+      "step": 270
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.0001362782664645371,
+      "loss": 1.6293,
+      "step": 275
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00013450300386777127,
+      "loss": 1.5935,
+      "step": 280
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.00013182317999100535,
+      "loss": 1.5613,
+      "step": 285
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00012827557714724304,
+      "loss": 1.8451,
+      "step": 290
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.000123908888476113,
+      "loss": 1.7444,
+      "step": 295
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.00011878304959908774,
+      "loss": 1.6749,
+      "step": 300
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00011296841596437982,
+      "loss": 1.5253,
+      "step": 305
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00010654479717298873,
+      "loss": 1.6357,
+      "step": 310
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 9.96003615403955e-05,
+      "loss": 1.6636,
+      "step": 315
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 9.223042592950526e-05,
+      "loss": 1.646,
+      "step": 320
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 8.453614746515988e-05,
+      "loss": 1.7026,
+      "step": 325
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.662313508728495e-05,
+      "loss": 1.6289,
+      "step": 330
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.860000000000001e-05,
+      "loss": 1.4981,
+      "step": 335
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 6.0576864912715095e-05,
+      "loss": 1.5564,
+      "step": 340
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 5.266385253484016e-05,
+      "loss": 1.6555,
+      "step": 345
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.496957407049471e-05,
+      "loss": 1.5796,
+      "step": 350
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.759963845960453e-05,
+      "loss": 1.7131,
+      "step": 355
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 3.065520282701126e-05,
+      "loss": 1.61,
+      "step": 360
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.423158403562016e-05,
+      "loss": 1.6306,
+      "step": 365
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.8416950400912332e-05,
+      "loss": 1.5807,
+      "step": 370
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.3291111523887019e-05,
+      "loss": 1.5766,
+      "step": 375
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.924422852757e-06,
+      "loss": 1.6478,
+      "step": 380
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.376820008994686e-06,
+      "loss": 1.6091,
+      "step": 385
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.6969961322287634e-06,
+      "loss": 1.512,
+      "step": 390
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 9.21733535462923e-07,
+      "loss": 1.57,
+      "step": 395
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 7.53988440801922e-08,
+      "loss": 1.5282,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.536595344543457,
+      "eval_runtime": 8.6245,
+      "eval_samples_per_second": 22.726,
+      "eval_steps_per_second": 2.899,
+      "step": 402
     }
   ],
-  "max_steps": 268,
-  "num_train_epochs": 2,
-  "total_flos": 278798598144000.0,
+  "max_steps": 402,
+  "num_train_epochs": 3,
+  "total_flos": 418067251200000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff20da1bf81cef2f82cade2d05f960ab574b870297377eb2bc6103395307a13
+oid sha256:ed2d4b33a781b12e1276cd897224ebf9c500b46f888821b120698cf8724651f6
 size 2671