huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/platina")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/ugrse2us/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/2ih365j7/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 Платина (Platina)'s lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/174snup8) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1quasiz0) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/174snup8/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1quasiz0/artifacts) is logged and versioned.
 
 ## How to use
 

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.5137468576431274, "eval_runtime": 5.9741, "eval_samples_per_second": 21.928, "eval_steps_per_second": 2.846, "epoch": 4.0}
+{"eval_loss": 1.3523887395858765, "eval_runtime": 6.2976, "eval_samples_per_second": 21.119, "eval_steps_per_second": 2.699, "epoch": 5.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674bcbe4c3f0b74c808b2acddd4c29980ae0e900a2d265df4a57bdda5b5995cb
+oid sha256:1a6eabf9f9233b440eedfafd6710ddc3daeea0fffdfe8c2a281b4758902fa78c
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c84c8d034b21501bcaa1bb5445c0df2a821aa1846fc23438d5d5b489ae916db
+oid sha256:554836147560545c9373bbde2a72b0db4282ab87a5b7a113a7d10b992febc8fa
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfad19679cf041d3a6d0d3c84576e0a908395320dd1342c1eff0220a5cbf7829
+oid sha256:058b060e53ad2583dcda7b9ab91cc8ba684ee7591ea5fab893e07e5d17e956f3
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793f8e26475d3635b181b3b379f08c9cf76d34985095cf8466590d2e2b8b1156
+oid sha256:3ebfb9f7c5ef30fc6c5169e74f8cece8ea746e80139907978a5ace953a7c1b9a
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7960f9c01bdbbfc38037b14cc37d37af713a0aaaedd217788c1312c4a9e32c
+oid sha256:56a03ee9c4f7d46c39bb609d5652834cf98daba2d29c096120b392bb7cba62b1
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.5137468576431274,
-  "best_model_checkpoint": "output/platina/checkpoint-348",
-  "epoch": 4.0,
-  "global_step": 348,
+  "best_metric": 1.3523887395858765,
+  "best_model_checkpoint": "output/platina/checkpoint-435",
+  "epoch": 5.0,
+  "global_step": 435,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -452,11 +452,127 @@
       "eval_samples_per_second": 22.648,
       "eval_steps_per_second": 2.939,
       "step": 348
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 1.788243178686371e-07,
+      "loss": 1.5412,
+      "step": 350
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 2.1799062746641418e-06,
+      "loss": 1.4467,
+      "step": 355
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 6.340326210572388e-06,
+      "loss": 1.5015,
+      "step": 360
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 1.2524827574860016e-05,
+      "loss": 1.4381,
+      "step": 365
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 2.053235029776879e-05,
+      "loss": 1.4247,
+      "step": 370
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 3.0102567316140582e-05,
+      "loss": 1.414,
+      "step": 375
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 4.092434788749928e-05,
+      "loss": 1.3577,
+      "step": 380
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 5.264587254760211e-05,
+      "loss": 1.4768,
+      "step": 385
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 6.48860708710403e-05,
+      "loss": 1.4088,
+      "step": 390
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 7.724701018971169e-05,
+      "loss": 1.4472,
+      "step": 395
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 8.932683250807266e-05,
+      "loss": 1.415,
+      "step": 400
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 0.00010073281903200549,
+      "loss": 1.4059,
+      "step": 405
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 0.00011109415757939859,
+      "loss": 1.4512,
+      "step": 410
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 0.00012007399779992913,
+      "loss": 1.5409,
+      "step": 415
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 0.00012738040228509664,
+      "loss": 1.3528,
+      "step": 420
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 0.0001327758375444962,
+      "loss": 1.5104,
+      "step": 425
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 0.0001360848962937354,
+      "loss": 1.4315,
+      "step": 430
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.4081,
+      "step": 435
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.3523887395858765,
+      "eval_runtime": 6.0439,
+      "eval_samples_per_second": 22.006,
+      "eval_steps_per_second": 2.813,
+      "step": 435
     }
   ],
-  "max_steps": 348,
-  "num_train_epochs": 4,
-  "total_flos": 362150756352000.0,
+  "max_steps": 435,
+  "num_train_epochs": 5,
+  "total_flos": 452296507392000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29bc07a887bc66db2f72baab7071a8ed663e30bb50cd30619db8b1114d32a09
+oid sha256:2cf0d38b97ef8d76fefde84a017dca88b69ddcb5c6903588227fab13bcb9da45
 size 2863