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
+- Razavipour/persian-traditional-instruments-tiny
 - generated_from_trainer
 model-index:
 - name: musicgen-persian-traditional-instruments-tiny_3
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # musicgen-persian-traditional-instruments-tiny_3
 
-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 RAZAVIPOUR/PERSIAN-TRADITIONAL-INSTRUMENTS-TINY - DEFAULT dataset.
 
 ## Model description
 

all_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 2.0,
-    "total_flos": 29853631825608.0,
-    "train_loss": 30.133461475372314,
-    "train_runtime": 397.1796,
+    "epoch": 3.0,
+    "total_flos": 44771227963296.0,
+    "train_loss": 27.90105402469635,
+    "train_runtime": 632.9329,
     "train_samples": 119,
-    "train_samples_per_second": 0.599,
-    "train_steps_per_second": 0.04
+    "train_samples_per_second": 0.564,
+    "train_steps_per_second": 0.038
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 2.0,
-    "total_flos": 29853631825608.0,
-    "train_loss": 30.133461475372314,
-    "train_runtime": 397.1796,
+    "epoch": 3.0,
+    "total_flos": 44771227963296.0,
+    "train_loss": 27.90105402469635,
+    "train_runtime": 632.9329,
     "train_samples": 119,
-    "train_samples_per_second": 0.599,
-    "train_steps_per_second": 0.04
+    "train_samples_per_second": 0.564,
+    "train_steps_per_second": 0.038
 }

trainer_state.json

@@ -2,139 +2,195 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.13333333333333333,
-      "grad_norm": 5.564905166625977,
+      "grad_norm": 5.56486701965332,
       "learning_rate": 0.0002,
       "loss": 38.3533,
       "step": 1
     },
     {
       "epoch": 0.26666666666666666,
-      "grad_norm": 6.65146541595459,
-      "learning_rate": 0.0001875,
-      "loss": 36.8913,
+      "grad_norm": 6.651921272277832,
+      "learning_rate": 0.00019166666666666667,
+      "loss": 36.8912,
       "step": 2
     },
     {
       "epoch": 0.4,
-      "grad_norm": 8.893917083740234,
-      "learning_rate": 0.000175,
-      "loss": 35.9052,
+      "grad_norm": 8.944223403930664,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 35.8779,
       "step": 3
     },
     {
       "epoch": 0.5333333333333333,
-      "grad_norm": 8.743362426757812,
-      "learning_rate": 0.00016250000000000002,
-      "loss": 35.0392,
+      "grad_norm": 8.79480266571045,
+      "learning_rate": 0.000175,
+      "loss": 34.9511,
       "step": 4
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": NaN,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 33.1986,
+      "grad_norm": 10.800246238708496,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 32.9909,
       "step": 5
     },
     {
       "epoch": 0.8,
-      "grad_norm": 8.269606590270996,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 33.7741,
+      "grad_norm": 8.01695442199707,
+      "learning_rate": 0.00015833333333333332,
+      "loss": 32.5083,
       "step": 6
     },
     {
       "epoch": 0.9333333333333333,
-      "grad_norm": 8.749699592590332,
-      "learning_rate": 0.0001375,
-      "loss": 32.6172,
+      "grad_norm": 8.307640075683594,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 31.4153,
       "step": 7
     },
     {
       "epoch": 1.0,
-      "grad_norm": 5.006312847137451,
-      "learning_rate": 0.000125,
-      "loss": 16.351,
+      "grad_norm": 7.08075475692749,
+      "learning_rate": 0.00014166666666666668,
+      "loss": 15.999,
       "step": 8
     },
     {
       "epoch": 1.1333333333333333,
-      "grad_norm": 10.173412322998047,
-      "learning_rate": 0.00011250000000000001,
-      "loss": 30.0547,
+      "grad_norm": 9.917808532714844,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 28.7986,
       "step": 9
     },
     {
       "epoch": 1.2666666666666666,
-      "grad_norm": 8.951446533203125,
-      "learning_rate": 0.0001,
-      "loss": 30.6191,
+      "grad_norm": 10.226347923278809,
+      "learning_rate": 0.000125,
+      "loss": 29.6019,
       "step": 10
     },
     {
       "epoch": 1.4,
-      "grad_norm": 9.113348960876465,
-      "learning_rate": 8.75e-05,
-      "loss": 29.3415,
+      "grad_norm": 9.522478103637695,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 28.3856,
       "step": 11
     },
     {
       "epoch": 1.5333333333333332,
-      "grad_norm": 8.937090873718262,
-      "learning_rate": 7.500000000000001e-05,
-      "loss": 29.2385,
+      "grad_norm": 9.76523208618164,
+      "learning_rate": 0.00010833333333333333,
+      "loss": 28.2537,
       "step": 12
     },
     {
       "epoch": 1.6666666666666665,
-      "grad_norm": 8.111980438232422,
-      "learning_rate": 6.25e-05,
-      "loss": 28.6866,
+      "grad_norm": 6.195432186126709,
+      "learning_rate": 0.0001,
+      "loss": 27.6475,
       "step": 13
     },
     {
       "epoch": 1.8,
-      "grad_norm": 8.194887161254883,
-      "learning_rate": 5e-05,
-      "loss": 28.2205,
+      "grad_norm": 7.892975807189941,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 27.1004,
       "step": 14
     },
     {
       "epoch": 1.9333333333333333,
-      "grad_norm": 10.803622245788574,
-      "learning_rate": 3.7500000000000003e-05,
-      "loss": 29.6655,
+      "grad_norm": 9.260358810424805,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 28.3018,
       "step": 15
     },
     {
       "epoch": 2.0,
-      "grad_norm": 4.887396335601807,
-      "learning_rate": 2.5e-05,
-      "loss": 14.1792,
+      "grad_norm": 3.782254695892334,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 13.5816,
       "step": 16
     },
     {
-      "epoch": 2.0,
-      "step": 16,
-      "total_flos": 29853631825608.0,
-      "train_loss": 30.133461475372314,
-      "train_runtime": 397.1796,
-      "train_samples_per_second": 0.599,
-      "train_steps_per_second": 0.04
+      "epoch": 2.1333333333333333,
+      "grad_norm": 6.108007907867432,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 26.4921,
+      "step": 17
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 11.83798885345459,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 25.9269,
+      "step": 18
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 7.73467493057251,
+      "learning_rate": 5e-05,
+      "loss": 27.8886,
+      "step": 19
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 4.977690696716309,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 27.2834,
+      "step": 20
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 9.394918441772461,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 25.2599,
+      "step": 21
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 6.224085807800293,
+      "learning_rate": 2.5e-05,
+      "loss": 25.6994,
+      "step": 22
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 4.654765605926514,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 26.9324,
+      "step": 23
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.106358051300049,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 13.4846,
+      "step": 24
+    },
+    {
+      "epoch": 3.0,
+      "step": 24,
+      "total_flos": 44771227963296.0,
+      "train_loss": 27.90105402469635,
+      "train_runtime": 632.9329,
+      "train_samples_per_second": 0.564,
+      "train_steps_per_second": 0.038
     }
   ],
   "logging_steps": 1.0,
-  "max_steps": 16,
+  "max_steps": 24,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -148,7 +204,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 29853631825608.0,
+  "total_flos": 44771227963296.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null