End of training

README.md

@@ -3,6 +3,8 @@ base_model: facebook/musicgen-melody
 library_name: peft
 license: cc-by-nc-4.0
 tags:
+- text-to-audio
+- Punk
 - generated_from_trainer
 model-index:
 - name: Large-Data
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Large-Data
 
-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 PlutoG99001/Electronic-full dataset.
 
 ## Model description
 

trainer_state.json

@@ -1,67 +1,109 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5555555555555554,
+  "epoch": 3.84,
   "eval_steps": 500,
-  "global_step": 12,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.5925925925925926,
-      "grad_norm": 1.2005751132965088,
-      "learning_rate": 0.0001666666666666667,
-      "loss": 9.4962,
+      "epoch": 0.32,
+      "grad_norm": 1.2555780410766602,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 9.4154,
       "step": 2
     },
     {
-      "epoch": 1.1851851851851851,
-      "grad_norm": 1.47324538230896,
-      "learning_rate": 0.00013333333333333334,
-      "loss": 9.1456,
+      "epoch": 0.64,
+      "grad_norm": 1.53036367893219,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 9.0215,
       "step": 4
     },
     {
-      "epoch": 1.7777777777777777,
-      "grad_norm": 2.0616180896759033,
-      "learning_rate": 0.0001,
-      "loss": 8.731,
+      "epoch": 0.96,
+      "grad_norm": 1.8442403078079224,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.535,
       "step": 6
     },
     {
-      "epoch": 2.3703703703703702,
-      "grad_norm": 2.349423885345459,
-      "learning_rate": 6.666666666666667e-05,
-      "loss": 8.2574,
+      "epoch": 1.28,
+      "grad_norm": 2.2389612197875977,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 8.0172,
       "step": 8
     },
     {
-      "epoch": 2.962962962962963,
-      "grad_norm": 1.723225474357605,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 7.9055,
+      "epoch": 1.6,
+      "grad_norm": 2.622530698776245,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 7.8423,
       "step": 10
     },
     {
-      "epoch": 3.5555555555555554,
-      "grad_norm": 1.465832233428955,
-      "learning_rate": 0.0,
-      "loss": 7.7976,
+      "epoch": 1.92,
+      "grad_norm": 1.8883254528045654,
+      "learning_rate": 0.0001,
+      "loss": 7.6953,
       "step": 12
     },
     {
-      "epoch": 3.5555555555555554,
-      "step": 12,
-      "total_flos": 69844190099040.0,
-      "train_loss": 8.555556774139404,
-      "train_runtime": 79.8982,
-      "train_samples_per_second": 2.703,
-      "train_steps_per_second": 0.15
+      "epoch": 2.24,
+      "grad_norm": NaN,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 7.4797,
+      "step": 14
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.4147595167160034,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 7.4009,
+      "step": 16
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.086115598678589,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 7.2106,
+      "step": 18
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.3016234636306763,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 7.2342,
+      "step": 20
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 1.3679742813110352,
+      "learning_rate": 2.5e-05,
+      "loss": 7.1718,
+      "step": 22
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 2.1608622074127197,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 7.1113,
+      "step": 24
+    },
+    {
+      "epoch": 3.84,
+      "step": 24,
+      "total_flos": 124647858838128.0,
+      "train_loss": 7.844584743181865,
+      "train_runtime": 146.2747,
+      "train_samples_per_second": 2.735,
+      "train_steps_per_second": 0.164
     }
   ],
   "logging_steps": 2,
-  "max_steps": 12,
+  "max_steps": 24,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
@@ -77,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 69844190099040.0,
+  "total_flos": 124647858838128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null