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
+- baoshidaoren_music_snippets
 - generated_from_trainer
 model-index:
 - name: musicgen-melody-lora-baishidaoren-epoch4-lr1
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # musicgen-melody-lora-baishidaoren-epoch4-lr1
 
-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 zuona/baoshidaoren_music_snippets dataset.
 
 ## Model description
 

trainer_state.json

@@ -1,97 +1,125 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.888888888888889,
+  "epoch": 3.888888888888889,
   "eval_steps": 500,
-  "global_step": 21,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.25396825396825395,
-      "grad_norm": 21.025897979736328,
-      "learning_rate": 9.047619047619048e-05,
-      "loss": 72.1283,
+      "grad_norm": NaN,
+      "learning_rate": 9.642857142857143e-05,
+      "loss": 72.1443,
       "step": 2
     },
     {
       "epoch": 0.5079365079365079,
-      "grad_norm": 23.057056427001953,
-      "learning_rate": 8.095238095238096e-05,
-      "loss": 70.4889,
+      "grad_norm": 19.469039916992188,
+      "learning_rate": 8.92857142857143e-05,
+      "loss": 72.0489,
       "step": 4
     },
     {
       "epoch": 0.7619047619047619,
-      "grad_norm": 26.4029598236084,
-      "learning_rate": 7.142857142857143e-05,
-      "loss": 67.1196,
+      "grad_norm": 20.524240493774414,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 69.7797,
       "step": 6
     },
     {
       "epoch": 1.126984126984127,
-      "grad_norm": 55.33572006225586,
-      "learning_rate": 6.19047619047619e-05,
-      "loss": 84.5853,
+      "grad_norm": 49.45151138305664,
+      "learning_rate": 7.857142857142858e-05,
+      "loss": 89.8185,
       "step": 8
     },
     {
       "epoch": 1.380952380952381,
-      "grad_norm": 36.54444122314453,
-      "learning_rate": 5.2380952380952384e-05,
-      "loss": 59.4698,
+      "grad_norm": 32.59318161010742,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 62.2748,
       "step": 10
     },
     {
       "epoch": 1.6349206349206349,
-      "grad_norm": 32.44065475463867,
-      "learning_rate": 4.2857142857142856e-05,
-      "loss": 55.2143,
+      "grad_norm": 32.76274871826172,
+      "learning_rate": 6.428571428571429e-05,
+      "loss": 57.2675,
       "step": 12
     },
     {
       "epoch": 1.8888888888888888,
-      "grad_norm": 34.522281646728516,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 55.74,
+      "grad_norm": 36.317630767822266,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 56.7585,
       "step": 14
     },
     {
       "epoch": 2.253968253968254,
-      "grad_norm": 34.46546936035156,
-      "learning_rate": 2.380952380952381e-05,
-      "loss": 73.8978,
+      "grad_norm": 35.975807189941406,
+      "learning_rate": 5e-05,
+      "loss": 74.1119,
       "step": 16
     },
     {
       "epoch": 2.507936507936508,
-      "grad_norm": 20.34326171875,
-      "learning_rate": 1.4285714285714285e-05,
-      "loss": 50.4007,
+      "grad_norm": 20.22718620300293,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 49.704,
       "step": 18
     },
     {
       "epoch": 2.761904761904762,
-      "grad_norm": 21.0695858001709,
-      "learning_rate": 9.523809523809523e-06,
-      "loss": 51.1436,
+      "grad_norm": 18.7318172454834,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 49.5238,
       "step": 20
     },
     {
-      "epoch": 2.888888888888889,
-      "step": 21,
-      "total_flos": 331427311589016.0,
-      "train_loss": 63.36745144072033,
-      "train_runtime": 786.6395,
-      "train_samples_per_second": 0.481,
-      "train_steps_per_second": 0.027
+      "epoch": 3.126984126984127,
+      "grad_norm": 34.112125396728516,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 66.7037,
+      "step": 22
+    },
+    {
+      "epoch": 3.380952380952381,
+      "grad_norm": 19.139488220214844,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 46.9201,
+      "step": 24
+    },
+    {
+      "epoch": 3.634920634920635,
+      "grad_norm": 18.72429656982422,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 47.8016,
+      "step": 26
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 17.140914916992188,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 46.4582,
+      "step": 28
+    },
+    {
+      "epoch": 3.888888888888889,
+      "step": 28,
+      "total_flos": 445653973809192.0,
+      "train_loss": 61.52253450666155,
+      "train_runtime": 1057.0707,
+      "train_samples_per_second": 0.477,
+      "train_steps_per_second": 0.026
     }
   ],
   "logging_steps": 2,
-  "max_steps": 21,
+  "max_steps": 28,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -105,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 331427311589016.0,
+  "total_flos": 445653973809192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null