huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/xxxtentacion")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1fgk6duz/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/12xi0jh5/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 XXXTENTACION's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/7g46vrtf) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2l2qvy4j) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/7g46vrtf/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2l2qvy4j/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -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": 2.998302936553955, "eval_runtime": 7.549, "eval_samples_per_second": 21.062, "eval_steps_per_second": 2.649, "epoch": 2.0}
+{"eval_loss": 2.5633065700531006, "eval_runtime": 7.7985, "eval_samples_per_second": 21.158, "eval_steps_per_second": 2.693, "epoch": 3.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473c6ce96484afb22b5f44b9754253982be214dde5ccfc6e4636c65d85527beb
+oid sha256:c35bbdee0d6b253323c13ff1245f408049ab736cf0cf61eca89dcbaa56ef58e2
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42035e763018344e9c12b57960c5622bcb42c42ca8545f22d5745457bc43b7f0
+oid sha256:47629f5404c8831b180691275390a10b14f3fc2e28a274f45c15f37773ea51ce
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9bc902bf8c5fd91ac6140769cbcb1ed04fda15388d328a739a52c62d0e2b7c4
+oid sha256:47c54593d3c6ad8554535d25d1fdeea953eb6a2818bfc6ca16c02f606b0ee4f8
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3691a8950b6ce0a7fbcdee171960f1672959fb5e260f352ba982df89dd517c41
+oid sha256:bdea000658a9e494731762eaff1017b2c5e11bd26a0d5b297220d41bf58cb246
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0816ea5e3b1d810ba13a63e3db58b55d3131231050f4d5136f720f83ed0afbf
+oid sha256:e4159d6e3ebfb2c1ae6f63b34ad63e472c887ee5bdd3d6618f17a8021dbe67f5
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.998302936553955,
-  "best_model_checkpoint": "output/xxxtentacion/checkpoint-226",
-  "epoch": 2.0,
-  "global_step": 226,
+  "best_metric": 2.5633065700531006,
+  "best_model_checkpoint": "output/xxxtentacion/checkpoint-336",
+  "epoch": 3.0,
+  "global_step": 336,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -292,11 +292,151 @@
       "eval_samples_per_second": 21.089,
       "eval_steps_per_second": 2.653,
       "step": 226
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00013548005477567312,
+      "loss": 2.86,
+      "step": 230
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00013268947730420952,
+      "loss": 2.4836,
+      "step": 235
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00012864032674294055,
+      "loss": 2.4962,
+      "step": 240
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00012341211929557585,
+      "loss": 2.3394,
+      "step": 245
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00011710752518939714,
+      "loss": 2.3663,
+      "step": 250
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00010985035246307073,
+      "loss": 2.5085,
+      "step": 255
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.00010178311565541946,
+      "loss": 2.6029,
+      "step": 260
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 9.306423714063481e-05,
+      "loss": 2.589,
+      "step": 265
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 8.38649360694032e-05,
+      "loss": 2.6019,
+      "step": 270
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.436586601014643e-05,
+      "loss": 2.5593,
+      "step": 275
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.475356731952859e-05,
+      "loss": 2.38,
+      "step": 280
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 5.5216803909693685e-05,
+      "loss": 2.5886,
+      "step": 285
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.5942856349875636e-05,
+      "loss": 2.4662,
+      "step": 290
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 3.711384409752691e-05,
+      "loss": 2.6117,
+      "step": 295
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.8903149082065433e-05,
+      "loss": 2.3842,
+      "step": 300
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.1472010874005767e-05,
+      "loss": 2.4499,
+      "step": 305
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.4966360302693178e-05,
+      "loss": 2.3766,
+      "step": 310
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 9.513953703256716e-06,
+      "loss": 2.422,
+      "step": 315
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.221864069725753e-06,
+      "loss": 2.3515,
+      "step": 320
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.1743783824128875e-06,
+      "loss": 2.1874,
+      "step": 325
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 4.3134240132355735e-07,
+      "loss": 2.2719,
+      "step": 330
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 2.6985430122565824e-08,
+      "loss": 2.6279,
+      "step": 335
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.5633065700531006,
+      "eval_runtime": 7.7611,
+      "eval_samples_per_second": 21.26,
+      "eval_steps_per_second": 2.706,
+      "step": 336
     }
   ],
-  "max_steps": 226,
-  "num_train_epochs": 2,
-  "total_flos": 234378952704000.0,
+  "max_steps": 336,
+  "num_train_epochs": 3,
+  "total_flos": 348563570688000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f2723ca1e95981d792cb45af7783a851ea2dee4eed340a95ef82a8fb6a5a29
+oid sha256:8c4a4c88eed3db16ceebd513a7addcfd6e0e6d282b2db8b5e067fa1139964b5c
 size 2671