End of training

README.md

@@ -3,6 +3,8 @@ library_name: peft
 license: cc-by-nc-4.0
 base_model: facebook/musicgen-small
 tags:
+- text-to-audio
+- indian
 - generated_from_trainer
 model-index:
 - name: musicgen-small-ft1
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # musicgen-small-ft1
 
-This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on an unknown dataset.
+This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the DevPanda004/indian-music-and-metadata-3 dataset.
 
 ## Model description
 

trainer_state.json

@@ -1,69 +1,111 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 1.88,
   "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": 0.64,
-      "grad_norm": 22.516803741455078,
-      "learning_rate": 0.0001666666666666667,
-      "loss": 9.6314,
+      "epoch": 0.16,
+      "grad_norm": 27.128768920898438,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 9.6266,
       "step": 2
     },
     {
-      "epoch": 1.0,
-      "grad_norm": 2.688298225402832,
-      "learning_rate": 0.00013333333333333334,
-      "loss": 5.1075,
+      "epoch": 0.32,
+      "grad_norm": 24.79010009765625,
+      "learning_rate": 0.000175,
+      "loss": 9.0447,
       "step": 4
     },
     {
-      "epoch": 1.6400000000000001,
-      "grad_norm": 19.711145401000977,
-      "learning_rate": 0.0001,
-      "loss": 8.2415,
+      "epoch": 0.48,
+      "grad_norm": 18.81116485595703,
+      "learning_rate": 0.00015833333333333332,
+      "loss": 8.5322,
       "step": 6
     },
     {
-      "epoch": 2.0,
-      "grad_norm": 6.4154276847839355,
-      "learning_rate": 6.666666666666667e-05,
-      "loss": 4.5098,
+      "epoch": 0.64,
+      "grad_norm": 26.39373779296875,
+      "learning_rate": 0.00014166666666666668,
+      "loss": 7.9093,
       "step": 8
     },
     {
-      "epoch": 2.64,
-      "grad_norm": 25.797412872314453,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 7.5803,
+      "epoch": 0.8,
+      "grad_norm": 23.423715591430664,
+      "learning_rate": 0.000125,
+      "loss": 7.6659,
       "step": 10
     },
     {
-      "epoch": 3.0,
-      "grad_norm": 5.132017135620117,
-      "learning_rate": 0.0,
-      "loss": 4.3452,
+      "epoch": 0.96,
+      "grad_norm": 12.479715347290039,
+      "learning_rate": 0.00010833333333333333,
+      "loss": 7.5728,
       "step": 12
     },
     {
-      "epoch": 3.0,
-      "step": 12,
-      "total_flos": 25094075608584.0,
-      "train_loss": 6.569292863210042,
-      "train_runtime": 89.1968,
-      "train_samples_per_second": 2.242,
-      "train_steps_per_second": 0.135
+      "epoch": 1.08,
+      "grad_norm": 8.727032661437988,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 5.5276,
+      "step": 14
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 6.857452869415283,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 7.3248,
+      "step": 16
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 12.307377815246582,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 7.1551,
+      "step": 18
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.698224067687988,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 7.0827,
+      "step": 20
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 7.9674906730651855,
+      "learning_rate": 2.5e-05,
+      "loss": 7.1063,
+      "step": 22
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 5.259669303894043,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 6.9544,
+      "step": 24
+    },
+    {
+      "epoch": 1.88,
+      "step": 24,
+      "total_flos": 60263854292736.0,
+      "train_loss": 7.62520436445872,
+      "train_runtime": 205.0269,
+      "train_samples_per_second": 1.951,
+      "train_steps_per_second": 0.117
     }
   ],
   "logging_steps": 2,
-  "max_steps": 12,
+  "max_steps": 24,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -77,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 25094075608584.0,
+  "total_flos": 60263854292736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null