Model save

README.md

@@ -2,8 +2,6 @@
 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:
@@ -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/ylacombe/huggingface/runs/fibz5z40)
-[<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/ylacombe/huggingface/runs/fibz5z40)
+[<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/ylacombe/huggingface/runs/wk9bpko6)
+[<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/ylacombe/huggingface/runs/wk9bpko6)
 # musicgen-melody-lora-punk
 
-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: 0.2563
+This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on an unknown dataset.
 
 ## Model description
 
@@ -43,7 +38,7 @@ The following hyperparameters were used during training:
 - learning_rate: 0.0002
 - train_batch_size: 2
 - eval_batch_size: 1
-- seed: 456
+- seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27de65e63aa3e9805c34c5625f400c03e527dcd5d7702695b8dbe0cdb6695191
+oid sha256:ebddac262eb2c9ca14a4d09ecaa6a71b5cc2a406a005772b382aa5cc57a66f97
 size 87103456

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494294fe4c26ed33c87c68afd6fe7edca29e0c4e94f126655fc837e7ed49caf4
+oid sha256:71ba5d6fecc725a071b1a8758caab75ff2fe73631754c8228eab7c2cc602ffe2
 size 5176