Model save

README.md

@@ -2,8 +2,6 @@
 license: cc-by-nc-4.0
 library_name: peft
 tags:
-- text-to-audio
-- sweet-dreambooths/black-eyed-peas-v1
 - generated_from_trainer
 base_model: facebook/musicgen-melody-large
 model-index:
@@ -14,14 +12,11 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 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/sanchit-gandhi/black-eyed-peas/runs/3nn9uham)
-[<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/sanchit-gandhi/black-eyed-peas/runs/3nn9uham)
+[<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/sanchit-gandhi/black-eyed-peas/runs/6y8tlzp8)
+[<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/sanchit-gandhi/black-eyed-peas/runs/6y8tlzp8)
 # black-eyed-peas-v1-unprompted
 
-This model is a fine-tuned version of [facebook/musicgen-melody-large](https://huggingface.co/facebook/musicgen-melody-large) on the SWEET-DREAMBOOTHS/BLACK-EYED-PEAS-V1 - DEFAULT dataset.
-It achieves the following results on the evaluation set:
-- Loss: 5.0311
-- Clap: -0.0634
+This model is a fine-tuned version of [facebook/musicgen-melody-large](https://huggingface.co/facebook/musicgen-melody-large) on an unknown dataset.
 
 ## Model description
 
@@ -44,23 +39,15 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 456
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2.0
+- num_epochs: 1.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Clap    |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 8.2807        | 0.3306 | 5    | 3.0158          | 0.0162  |
-| 6.536         | 0.6612 | 10   | 3.2537          | 0.0074  |
-| 6.1596        | 0.9917 | 15   | 4.2961          | -0.0395 |
-| 6.44          | 1.3223 | 20   | 4.8764          | -0.0380 |
-| 6.4944        | 1.6529 | 25   | 5.0227          | -0.0586 |
-| 6.3776        | 1.9835 | 30   | 5.0311          | -0.0541 |
 
 
 ### Framework versions

adapter_config.json

@@ -23,22 +23,22 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "audio_enc_to_dec_proj",
     "q_proj",
+    "audio_enc_to_dec_proj",
+    "embed_tokens.0",
+    "lm_heads.1",
+    "out_proj",
     "lm_heads.3",
-    "enc_to_dec_proj",
+    "embed_tokens.1",
+    "v_proj",
     "embed_tokens.2",
+    "enc_to_dec_proj",
+    "k_proj",
     "fc1",
-    "out_proj",
-    "embed_tokens.1",
-    "embed_tokens.3",
     "lm_heads.0",
-    "v_proj",
-    "embed_tokens.0",
     "lm_heads.2",
-    "fc2",
-    "lm_heads.1",
-    "k_proj"
+    "embed_tokens.3",
+    "fc2"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7855bac43ba87288c81fa5a565fb880f534471de3be65f15616700a30de9402
+oid sha256:d19243f574d00f49f4a272a7b0259ebfd46577b1c8e7b3ea931ed86fc426a519
 size 115742888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37acb3254b5135661d218a66809c6d514b70551f7e2548ae21db58b4af7c9808
+oid sha256:cbbc1e1ac2fd011f20c0fc90a3e0c4829fe10bbbc1b4c79172808000571a69f7
 size 5304