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
+- taufiqsyed/salami_cleaned_sampled
 - generated_from_trainer
 model-index:
 - name: salami_truncsplit_model_trial2
@@ -14,7 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # salami_truncsplit_model_trial2
 
-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 TAUFIQSYED/SALAMI_CLEANED_SAMPLED - DEFAULT dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.6239
+- Clap: 0.0428
 
 ## Model description
 

all_results.json

@@ -1,9 +1,15 @@
 {
-    "epoch": 0.8,
-    "total_flos": 3295460764752.0,
-    "train_loss": 10.123604774475098,
-    "train_runtime": 9.2915,
-    "train_samples": 20,
-    "train_samples_per_second": 2.153,
-    "train_steps_per_second": 0.108
+    "epoch": 0.96,
+    "eval_clap": 0.04283957555890083,
+    "eval_loss": 5.623888969421387,
+    "eval_runtime": 202.5479,
+    "eval_samples": 32,
+    "eval_samples_per_second": 0.158,
+    "eval_steps_per_second": 0.158,
+    "total_flos": 39958787199960.0,
+    "train_loss": 7.737621545791626,
+    "train_runtime": 78.8623,
+    "train_samples": 200,
+    "train_samples_per_second": 2.536,
+    "train_steps_per_second": 0.152
 }

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.96,
+    "eval_clap": 0.04283957555890083,
+    "eval_loss": 5.623888969421387,
+    "eval_runtime": 202.5479,
+    "eval_samples": 32,
+    "eval_samples_per_second": 0.158,
+    "eval_steps_per_second": 0.158
+}

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 0.8,
-    "total_flos": 3295460764752.0,
-    "train_loss": 10.123604774475098,
-    "train_runtime": 9.2915,
-    "train_samples": 20,
-    "train_samples_per_second": 2.153,
-    "train_steps_per_second": 0.108
+    "epoch": 0.96,
+    "total_flos": 39958787199960.0,
+    "train_loss": 7.737621545791626,
+    "train_runtime": 78.8623,
+    "train_samples": 200,
+    "train_samples_per_second": 2.536,
+    "train_steps_per_second": 0.152
 }

trainer_state.json

@@ -1,32 +1,109 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 0.96,
   "eval_steps": 25,
-  "global_step": 1,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.8,
-      "grad_norm": Infinity,
+      "epoch": 0.08,
+      "grad_norm": 65.75566101074219,
       "learning_rate": 0.0002,
-      "loss": 10.1236,
+      "loss": 9.9453,
       "step": 1
     },
+    {
+      "epoch": 0.16,
+      "grad_norm": 49.121734619140625,
+      "learning_rate": 0.0002,
+      "loss": 9.5694,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 63.262027740478516,
+      "learning_rate": 0.0002,
+      "loss": 8.9499,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 54.31144332885742,
+      "learning_rate": 0.0002,
+      "loss": 8.2463,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 35.41240310668945,
+      "learning_rate": 0.0002,
+      "loss": 7.7117,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 47.44524383544922,
+      "learning_rate": 0.0002,
+      "loss": 7.3188,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 63.63182067871094,
+      "learning_rate": 0.0002,
+      "loss": 7.3082,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 63.364933013916016,
+      "learning_rate": 0.0002,
+      "loss": 7.2847,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 47.89399337768555,
+      "learning_rate": 0.0002,
+      "loss": 7.0953,
+      "step": 9
+    },
     {
       "epoch": 0.8,
-      "step": 1,
-      "total_flos": 3295460764752.0,
-      "train_loss": 10.123604774475098,
-      "train_runtime": 9.2915,
-      "train_samples_per_second": 2.153,
-      "train_steps_per_second": 0.108
+      "grad_norm": 22.77845573425293,
+      "learning_rate": 0.0002,
+      "loss": 6.6363,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 22.07503318786621,
+      "learning_rate": 0.0002,
+      "loss": 6.2242,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 14.495305061340332,
+      "learning_rate": 0.0002,
+      "loss": 6.5613,
+      "step": 12
+    },
+    {
+      "epoch": 0.96,
+      "step": 12,
+      "total_flos": 39958787199960.0,
+      "train_loss": 7.737621545791626,
+      "train_runtime": 78.8623,
+      "train_samples_per_second": 2.536,
+      "train_steps_per_second": 0.152
     }
   ],
   "logging_steps": 1.0,
-  "max_steps": 1,
+  "max_steps": 12,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -42,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3295460764752.0,
+  "total_flos": 39958787199960.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null