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

@@ -1,363 +1,55 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.4,
+  "epoch": 2.32,
   "eval_steps": 500,
-  "global_step": 96,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.16,
-      "grad_norm": 24.299409866333008,
-      "learning_rate": 0.00019583333333333334,
-      "loss": 9.6308,
+      "epoch": 0.64,
+      "grad_norm": 19.88896369934082,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 9.6148,
       "step": 2
     },
     {
-      "epoch": 0.32,
-      "grad_norm": 21.645837783813477,
-      "learning_rate": 0.00019166666666666667,
-      "loss": 8.8304,
+      "epoch": 1.0,
+      "grad_norm": 3.0083649158477783,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 5.1146,
       "step": 4
     },
     {
-      "epoch": 0.48,
-      "grad_norm": 26.87311553955078,
-      "learning_rate": 0.0001875,
-      "loss": 8.2558,
+      "epoch": 1.6400000000000001,
+      "grad_norm": 17.57530975341797,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 8.3805,
       "step": 6
     },
-    {
-      "epoch": 0.64,
-      "grad_norm": 20.85015106201172,
-      "learning_rate": 0.00018333333333333334,
-      "loss": 7.6341,
-      "step": 8
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 11.373078346252441,
-      "learning_rate": 0.0001791666666666667,
-      "loss": 7.3657,
-      "step": 10
-    },
-    {
-      "epoch": 0.96,
-      "grad_norm": 8.73630428314209,
-      "learning_rate": 0.000175,
-      "loss": 7.3537,
-      "step": 12
-    },
-    {
-      "epoch": 1.08,
-      "grad_norm": 5.606980323791504,
-      "learning_rate": 0.00017083333333333333,
-      "loss": 5.4308,
-      "step": 14
-    },
-    {
-      "epoch": 1.24,
-      "grad_norm": 4.6125168800354,
-      "learning_rate": 0.0001666666666666667,
-      "loss": 7.1842,
-      "step": 16
-    },
-    {
-      "epoch": 1.4,
-      "grad_norm": 7.653925895690918,
-      "learning_rate": 0.00016250000000000002,
-      "loss": 7.0222,
-      "step": 18
-    },
-    {
-      "epoch": 1.56,
-      "grad_norm": 4.941583633422852,
-      "learning_rate": 0.00015833333333333332,
-      "loss": 6.962,
-      "step": 20
-    },
-    {
-      "epoch": 1.72,
-      "grad_norm": 6.187161922454834,
-      "learning_rate": 0.00015416666666666668,
-      "loss": 6.9915,
-      "step": 22
-    },
-    {
-      "epoch": 1.88,
-      "grad_norm": 3.677783489227295,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 6.7917,
-      "step": 24
-    },
     {
       "epoch": 2.0,
-      "grad_norm": 3.971726417541504,
-      "learning_rate": 0.00014583333333333335,
-      "loss": 5.0888,
-      "step": 26
-    },
-    {
-      "epoch": 2.16,
-      "grad_norm": 4.507529258728027,
-      "learning_rate": 0.00014166666666666668,
-      "loss": 6.969,
-      "step": 28
+      "grad_norm": 3.7451229095458984,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 4.5262,
+      "step": 8
     },
     {
       "epoch": 2.32,
-      "grad_norm": 5.118126392364502,
-      "learning_rate": 0.0001375,
-      "loss": 6.702,
-      "step": 30
-    },
-    {
-      "epoch": 2.48,
-      "grad_norm": 4.643431663513184,
-      "learning_rate": 0.00013333333333333334,
-      "loss": 6.9216,
-      "step": 32
-    },
-    {
-      "epoch": 2.64,
-      "grad_norm": 3.6992788314819336,
-      "learning_rate": 0.00012916666666666667,
-      "loss": 6.8128,
-      "step": 34
-    },
-    {
-      "epoch": 2.8,
-      "grad_norm": 4.0084614753723145,
-      "learning_rate": 0.000125,
-      "loss": 6.8316,
-      "step": 36
-    },
-    {
-      "epoch": 2.96,
-      "grad_norm": 3.2957804203033447,
-      "learning_rate": 0.00012083333333333333,
-      "loss": 6.7879,
-      "step": 38
-    },
-    {
-      "epoch": 3.08,
-      "grad_norm": 5.090462684631348,
-      "learning_rate": 0.00011666666666666668,
-      "loss": 5.0059,
-      "step": 40
-    },
-    {
-      "epoch": 3.24,
-      "grad_norm": 5.256293773651123,
-      "learning_rate": 0.00011250000000000001,
-      "loss": 6.8814,
-      "step": 42
-    },
-    {
-      "epoch": 3.4,
-      "grad_norm": 4.577947616577148,
-      "learning_rate": 0.00010833333333333333,
-      "loss": 6.7358,
-      "step": 44
-    },
-    {
-      "epoch": 3.56,
-      "grad_norm": 4.876791954040527,
-      "learning_rate": 0.00010416666666666667,
-      "loss": 6.8413,
-      "step": 46
-    },
-    {
-      "epoch": 3.7199999999999998,
-      "grad_norm": 3.020899534225464,
-      "learning_rate": 0.0001,
-      "loss": 6.8198,
-      "step": 48
-    },
-    {
-      "epoch": 3.88,
-      "grad_norm": 3.4423134326934814,
-      "learning_rate": 9.583333333333334e-05,
-      "loss": 6.696,
-      "step": 50
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 1.9926425218582153,
-      "learning_rate": 9.166666666666667e-05,
-      "loss": 5.1219,
-      "step": 52
-    },
-    {
-      "epoch": 4.16,
-      "grad_norm": 3.435487985610962,
-      "learning_rate": 8.75e-05,
-      "loss": 6.7308,
-      "step": 54
-    },
-    {
-      "epoch": 4.32,
-      "grad_norm": 3.666560649871826,
-      "learning_rate": 8.333333333333334e-05,
-      "loss": 6.807,
-      "step": 56
-    },
-    {
-      "epoch": 4.48,
-      "grad_norm": 5.933062553405762,
-      "learning_rate": 7.916666666666666e-05,
-      "loss": 6.5088,
-      "step": 58
-    },
-    {
-      "epoch": 4.64,
-      "grad_norm": 7.5597944259643555,
-      "learning_rate": 7.500000000000001e-05,
-      "loss": 6.8242,
-      "step": 60
-    },
-    {
-      "epoch": 4.8,
-      "grad_norm": 4.08908224105835,
-      "learning_rate": 7.083333333333334e-05,
-      "loss": 6.7755,
-      "step": 62
-    },
-    {
-      "epoch": 4.96,
-      "grad_norm": 2.845886707305908,
-      "learning_rate": 6.666666666666667e-05,
-      "loss": 6.7024,
-      "step": 64
-    },
-    {
-      "epoch": 5.08,
-      "grad_norm": 4.930906295776367,
-      "learning_rate": 6.25e-05,
-      "loss": 5.0796,
-      "step": 66
-    },
-    {
-      "epoch": 5.24,
-      "grad_norm": 4.909699440002441,
-      "learning_rate": 5.833333333333334e-05,
-      "loss": 6.6225,
-      "step": 68
-    },
-    {
-      "epoch": 5.4,
-      "grad_norm": 5.248680591583252,
-      "learning_rate": 5.4166666666666664e-05,
-      "loss": 6.6255,
-      "step": 70
-    },
-    {
-      "epoch": 5.5600000000000005,
-      "grad_norm": 4.862923622131348,
-      "learning_rate": 5e-05,
-      "loss": 6.6052,
-      "step": 72
-    },
-    {
-      "epoch": 5.72,
-      "grad_norm": 4.014983177185059,
-      "learning_rate": 4.5833333333333334e-05,
-      "loss": 6.7604,
-      "step": 74
-    },
-    {
-      "epoch": 5.88,
-      "grad_norm": 5.7904887199401855,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 6.5661,
-      "step": 76
-    },
-    {
-      "epoch": 6.0,
-      "grad_norm": 2.4023070335388184,
-      "learning_rate": 3.7500000000000003e-05,
-      "loss": 4.9485,
-      "step": 78
-    },
-    {
-      "epoch": 6.16,
-      "grad_norm": 8.205228805541992,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 6.4406,
-      "step": 80
-    },
-    {
-      "epoch": 6.32,
-      "grad_norm": 4.756229400634766,
-      "learning_rate": 2.916666666666667e-05,
-      "loss": 6.701,
-      "step": 82
-    },
-    {
-      "epoch": 6.48,
-      "grad_norm": 3.8812973499298096,
-      "learning_rate": 2.5e-05,
-      "loss": 6.4635,
-      "step": 84
-    },
-    {
-      "epoch": 6.64,
-      "grad_norm": 4.376280784606934,
-      "learning_rate": 2.0833333333333336e-05,
-      "loss": 6.6409,
-      "step": 86
-    },
-    {
-      "epoch": 6.8,
-      "grad_norm": 3.6164727210998535,
-      "learning_rate": 1.6666666666666667e-05,
-      "loss": 6.5085,
-      "step": 88
-    },
-    {
-      "epoch": 6.96,
-      "grad_norm": 3.8249928951263428,
-      "learning_rate": 1.25e-05,
-      "loss": 6.6132,
-      "step": 90
-    },
-    {
-      "epoch": 7.08,
-      "grad_norm": 3.8151330947875977,
-      "learning_rate": 8.333333333333334e-06,
-      "loss": 5.0894,
-      "step": 92
-    },
-    {
-      "epoch": 7.24,
-      "grad_norm": 4.085716724395752,
-      "learning_rate": 4.166666666666667e-06,
-      "loss": 6.5454,
-      "step": 94
-    },
-    {
-      "epoch": 7.4,
-      "grad_norm": 5.319828987121582,
-      "learning_rate": 0.0,
-      "loss": 6.5279,
-      "step": 96
-    },
-    {
-      "epoch": 7.4,
-      "step": 96,
-      "total_flos": 238308734281248.0,
-      "train_loss": 6.6824056307474775,
-      "train_runtime": 800.3785,
-      "train_samples_per_second": 1.999,
-      "train_steps_per_second": 0.12
+      "step": 9,
+      "total_flos": 87485929268832.0,
+      "train_loss": 7.02129332224528,
+      "train_runtime": 224.2171,
+      "train_samples_per_second": 2.676,
+      "train_steps_per_second": 0.04
     }
   ],
   "logging_steps": 2,
-  "max_steps": 96,
+  "max_steps": 9,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -371,8 +63,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 238308734281248.0,
-  "train_batch_size": 2,
+  "total_flos": 87485929268832.0,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null
 }