End of training

README.md

@@ -3,6 +3,8 @@ library_name: peft
 license: cc-by-nc-4.0
 base_model: facebook/musicgen-melody
 tags:
+- text-to-audio
+- dnb
 - generated_from_trainer
 model-index:
 - name: musicgen-melody-lora-dnb-colab-gs-8-lr-1e-05
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # musicgen-melody-lora-dnb-colab-gs-8-lr-1e-05
 
-This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on an unknown dataset.
+This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the istvanj/ncs-dnb dataset.
 
 ## Model description
 

trainer_state.json

@@ -1,97 +1,223 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6666666666666665,
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 21,
+  "global_step": 56,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.26666666666666666,
-      "grad_norm": 7.614686012268066,
-      "learning_rate": 9.047619047619048e-05,
-      "loss": 9.6721,
+      "grad_norm": 8.04544448852539,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 9.7008,
       "step": 2
     },
     {
       "epoch": 0.5333333333333333,
-      "grad_norm": 10.107391357421875,
-      "learning_rate": 8.095238095238096e-05,
-      "loss": 9.4969,
+      "grad_norm": 8.58763599395752,
+      "learning_rate": 9.285714285714288e-06,
+      "loss": 9.6856,
       "step": 4
     },
     {
       "epoch": 0.8,
-      "grad_norm": 11.758378028869629,
-      "learning_rate": 7.142857142857143e-05,
-      "loss": 9.3036,
+      "grad_norm": 8.556867599487305,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 9.6861,
       "step": 6
     },
     {
       "epoch": 1.0,
-      "grad_norm": 8.324995994567871,
-      "learning_rate": 6.19047619047619e-05,
-      "loss": 6.8191,
+      "grad_norm": 4.745382308959961,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 7.2233,
       "step": 8
     },
     {
       "epoch": 1.2666666666666666,
-      "grad_norm": 15.543440818786621,
-      "learning_rate": 5.2380952380952384e-05,
-      "loss": 8.8411,
+      "grad_norm": 8.518149375915527,
+      "learning_rate": 8.214285714285714e-06,
+      "loss": 9.6471,
       "step": 10
     },
     {
       "epoch": 1.5333333333333332,
-      "grad_norm": 16.783220291137695,
-      "learning_rate": 4.2857142857142856e-05,
-      "loss": 8.5329,
+      "grad_norm": 8.65839958190918,
+      "learning_rate": 8.035714285714286e-06,
+      "loss": 9.628,
       "step": 12
     },
     {
       "epoch": 1.8,
-      "grad_norm": 19.108684539794922,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 8.2567,
+      "grad_norm": 9.335356712341309,
+      "learning_rate": 7.67857142857143e-06,
+      "loss": 9.5758,
       "step": 14
     },
     {
       "epoch": 2.0,
-      "grad_norm": 8.789897918701172,
-      "learning_rate": 2.380952380952381e-05,
-      "loss": 6.1492,
+      "grad_norm": 4.886675834655762,
+      "learning_rate": 7.321428571428572e-06,
+      "loss": 7.2155,
       "step": 16
     },
     {
       "epoch": 2.2666666666666666,
-      "grad_norm": 17.98725128173828,
-      "learning_rate": 1.4285714285714285e-05,
-      "loss": 8.0423,
+      "grad_norm": 8.749220848083496,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 9.598,
       "step": 18
     },
     {
       "epoch": 2.533333333333333,
-      "grad_norm": 14.338889122009277,
-      "learning_rate": 4.7619047619047615e-06,
-      "loss": 7.9496,
+      "grad_norm": 9.361573219299316,
+      "learning_rate": 6.785714285714287e-06,
+      "loss": 9.5492,
       "step": 20
     },
     {
-      "epoch": 2.6666666666666665,
-      "step": 21,
-      "total_flos": 82187025809664.0,
-      "train_loss": 8.28742908296131,
-      "train_runtime": 577.7205,
-      "train_samples_per_second": 0.623,
-      "train_steps_per_second": 0.036
+      "epoch": 2.8,
+      "grad_norm": 9.688807487487793,
+      "learning_rate": 6.4285714285714295e-06,
+      "loss": 9.5681,
+      "step": 22
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.595108509063721,
+      "learning_rate": 6.071428571428571e-06,
+      "loss": 7.1347,
+      "step": 24
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 10.533788681030273,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 9.5282,
+      "step": 26
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 10.169437408447266,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 9.5187,
+      "step": 28
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 10.997018814086914,
+      "learning_rate": 5e-06,
+      "loss": 9.5172,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.385960578918457,
+      "learning_rate": 4.642857142857144e-06,
+      "loss": 7.0662,
+      "step": 32
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 10.675312042236328,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 9.4752,
+      "step": 34
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 10.457250595092773,
+      "learning_rate": 3.928571428571429e-06,
+      "loss": 9.4481,
+      "step": 36
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 10.809959411621094,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 9.4466,
+      "step": 38
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 6.051748752593994,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 7.0524,
+      "step": 40
+    },
+    {
+      "epoch": 5.266666666666667,
+      "grad_norm": 13.849763870239258,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 9.4191,
+      "step": 42
+    },
+    {
+      "epoch": 5.533333333333333,
+      "grad_norm": 11.320974349975586,
+      "learning_rate": 2.5e-06,
+      "loss": 9.4206,
+      "step": 44
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 13.425915718078613,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 9.3768,
+      "step": 46
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.168519020080566,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 7.044,
+      "step": 48
+    },
+    {
+      "epoch": 6.266666666666667,
+      "grad_norm": 13.479830741882324,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 9.3804,
+      "step": 50
+    },
+    {
+      "epoch": 6.533333333333333,
+      "grad_norm": 11.913396835327148,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 9.3622,
+      "step": 52
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 12.051567077636719,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 9.37,
+      "step": 54
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.3397536277771,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 7.0465,
+      "step": 56
+    },
+    {
+      "epoch": 7.0,
+      "step": 56,
+      "total_flos": 216424602812184.0,
+      "train_loss": 8.917289240019661,
+      "train_runtime": 1514.4023,
+      "train_samples_per_second": 0.634,
+      "train_steps_per_second": 0.037
     }
   ],
   "logging_steps": 2,
-  "max_steps": 21,
+  "max_steps": 56,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 8,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -105,7 +231,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 82187025809664.0,
+  "total_flos": 216424602812184.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null