Model save

README.md

@@ -12,8 +12,8 @@ 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/b8se0vmo)
-[<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/b8se0vmo)
+[<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/8ycxnynu)
+[<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/8ycxnynu)
 # black-eyed-peas-v1-crafted-prompt-3-epochs
 
 This model is a fine-tuned version of [facebook/musicgen-melody-large](https://huggingface.co/facebook/musicgen-melody-large) on an unknown dataset.

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a31e252da2fa281a7232cb2bc46a7c0fc4409debe64ffbb49f233b9907354b
+oid sha256:ca435ac5d88714516cc5070507273d647419f9efdd8bcb64d7b743b32d2c6f15
 size 115742888

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.6879999999999997,
+    "total_flos": 231798834079728.0,
+    "train_loss": 9.752382596333822,
+    "train_runtime": 1792.9741,
+    "train_samples": 125,
+    "train_samples_per_second": 0.209,
+    "train_steps_per_second": 0.012
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.6879999999999997,
+    "total_flos": 231798834079728.0,
+    "train_loss": 9.752382596333822,
+    "train_runtime": 1792.9741,
+    "train_samples": 125,
+    "train_samples_per_second": 0.209,
+    "train_steps_per_second": 0.012
+}

trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6879999999999997,
+  "eval_steps": 30,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.7382475137710571,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 10.1861,
+      "step": 1
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 1.5424667596817017,
+      "learning_rate": 2.7142857142857144e-05,
+      "loss": 10.0983,
+      "step": 2
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 1.8689937591552734,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 10.133,
+      "step": 3
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 1.9022722244262695,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 10.0471,
+      "step": 4
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.0458884239196777,
+      "learning_rate": 2.2857142857142858e-05,
+      "loss": 9.9922,
+      "step": 5
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 2.3358101844787598,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 10.0411,
+      "step": 6
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 2.354118585586548,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 10.0344,
+      "step": 7
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 2.3863983154296875,
+      "learning_rate": 1.8571428571428572e-05,
+      "loss": 9.9137,
+      "step": 8
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 2.524012804031372,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 9.8263,
+      "step": 9
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.6917295455932617,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 9.7679,
+      "step": 10
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 2.6992530822753906,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 9.6647,
+      "step": 11
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 2.9822065830230713,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 9.6447,
+      "step": 12
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 3.070004463195801,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 9.6797,
+      "step": 13
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 3.1922192573547363,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 9.5573,
+      "step": 14
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 3.1647372245788574,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 9.5216,
+      "step": 15
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 3.2566683292388916,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 9.5464,
+      "step": 16
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 3.1021530628204346,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 9.4385,
+      "step": 17
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 3.345439910888672,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 9.4269,
+      "step": 18
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 3.5849218368530273,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 9.4999,
+      "step": 19
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 3.8040404319763184,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 9.44,
+      "step": 20
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 3.2971229553222656,
+      "learning_rate": 0.0,
+      "loss": 9.3401,
+      "step": 21
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "step": 21,
+      "total_flos": 231798834079728.0,
+      "train_loss": 9.752382596333822,
+      "train_runtime": 1792.9741,
+      "train_samples_per_second": 0.209,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 21,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 231798834079728.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ce71f30a1d77dc920e747b594dbf3462090ccf044984d2de31fdba1edd5120
+oid sha256:9f6742ea29acfe8964c1d78aabaa63ecf56038b4206fa71f2d9cb1d5768f6ea8
 size 5368