End of training

README.md

@@ -2,6 +2,8 @@
 license: cc-by-nc-4.0
 library_name: peft
 tags:
+- text-to-audio
+- ylacombe/tiny-punk
 - generated_from_trainer
 base_model: facebook/musicgen-melody
 model-index:
@@ -15,7 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/229461195/huggingface/runs/ncw7n610)
 # musicgen-melody-lora-punk2
 
-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 YLACOMBE/TINY-PUNK - DEFAULT dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.7288
+- Clap: -0.0424
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 3.764705882352941,
-    "eval_clap": -0.036870189011096954,
-    "eval_loss": 4.728781700134277,
-    "eval_runtime": 94.9338,
+    "eval_clap": -0.042357902973890305,
+    "eval_loss": 4.728766441345215,
+    "eval_runtime": 95.5459,
     "eval_samples": 5,
-    "eval_samples_per_second": 0.053,
-    "eval_steps_per_second": 0.053,
+    "eval_samples_per_second": 0.052,
+    "eval_steps_per_second": 0.052,
     "total_flos": 3464493556500.0,
-    "train_loss": 8.955368757247925,
-    "train_runtime": 43.5906,
+    "train_loss": 8.955286264419556,
+    "train_runtime": 43.6635,
     "train_samples": 33,
-    "train_samples_per_second": 3.028,
-    "train_steps_per_second": 0.184
+    "train_samples_per_second": 3.023,
+    "train_steps_per_second": 0.183
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.764705882352941,
-    "eval_clap": -0.036870189011096954,
-    "eval_loss": 4.728781700134277,
-    "eval_runtime": 94.9338,
+    "eval_clap": -0.042357902973890305,
+    "eval_loss": 4.728766441345215,
+    "eval_runtime": 95.5459,
     "eval_samples": 5,
-    "eval_samples_per_second": 0.053,
-    "eval_steps_per_second": 0.053
+    "eval_samples_per_second": 0.052,
+    "eval_steps_per_second": 0.052
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.764705882352941,
     "total_flos": 3464493556500.0,
-    "train_loss": 8.955368757247925,
-    "train_runtime": 43.5906,
+    "train_loss": 8.955286264419556,
+    "train_runtime": 43.6635,
     "train_samples": 33,
-    "train_samples_per_second": 3.028,
-    "train_steps_per_second": 0.184
+    "train_samples_per_second": 3.023,
+    "train_steps_per_second": 0.183
 }

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.47058823529411764,
-      "grad_norm": 1.1788331270217896,
+      "grad_norm": 1.1788603067398071,
       "learning_rate": 0.000175,
       "loss": 9.5575,
       "step": 1
     },
     {
       "epoch": 0.9411764705882353,
-      "grad_norm": 1.1702982187271118,
+      "grad_norm": 1.169764518737793,
       "learning_rate": 0.00015000000000000001,
       "loss": 9.4221,
       "step": 2
     },
     {
       "epoch": 1.4117647058823528,
-      "grad_norm": 1.1544806957244873,
+      "grad_norm": 1.1544612646102905,
       "learning_rate": 0.000125,
       "loss": 9.2271,
       "step": 3
     },
     {
       "epoch": 1.8823529411764706,
-      "grad_norm": 1.318764090538025,
+      "grad_norm": 1.3188167810440063,
       "learning_rate": 0.0001,
-      "loss": 8.9961,
+      "loss": 8.996,
       "step": 4
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 1.6400805711746216,
+      "grad_norm": 1.6397812366485596,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 8.8138,
+      "loss": 8.8136,
       "step": 5
     },
     {
       "epoch": 2.8235294117647056,
-      "grad_norm": 1.7725613117218018,
+      "grad_norm": 1.7697429656982422,
       "learning_rate": 5e-05,
-      "loss": 8.6992,
+      "loss": 8.699,
       "step": 6
     },
     {
       "epoch": 3.2941176470588234,
-      "grad_norm": 2.1556906700134277,
+      "grad_norm": 2.157055616378784,
       "learning_rate": 2.5e-05,
-      "loss": 8.4984,
+      "loss": 8.4982,
       "step": 7
     },
     {
       "epoch": 3.764705882352941,
-      "grad_norm": 2.2284181118011475,
+      "grad_norm": 2.2286105155944824,
       "learning_rate": 0.0,
-      "loss": 8.4288,
+      "loss": 8.4287,
       "step": 8
     },
     {
       "epoch": 3.764705882352941,
       "step": 8,
       "total_flos": 3464493556500.0,
-      "train_loss": 8.955368757247925,
-      "train_runtime": 43.5906,
-      "train_samples_per_second": 3.028,
-      "train_steps_per_second": 0.184
+      "train_loss": 8.955286264419556,
+      "train_runtime": 43.6635,
+      "train_samples_per_second": 3.023,
+      "train_steps_per_second": 0.183
     }
   ],
   "logging_steps": 1.0,