End of training

adapter_config.json

@@ -23,21 +23,21 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
-    "enc_to_dec_proj",
     "embed_tokens.1",
-    "lm_heads.3",
-    "lm_heads.2",
-    "k_proj",
-    "fc1",
-    "v_proj",
     "lm_heads.0",
+    "fc2",
     "embed_tokens.2",
-    "embed_tokens.0",
+    "q_proj",
     "lm_heads.1",
+    "enc_to_dec_proj",
     "audio_enc_to_dec_proj",
-    "q_proj",
-    "fc2",
+    "lm_heads.2",
+    "v_proj",
+    "lm_heads.3",
+    "embed_tokens.0",
+    "out_proj",
+    "k_proj",
+    "fc1",
     "embed_tokens.3"
   ],
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146581660f1540179e78bf468ebc9f4736d866e0bb585b6fcadfb67b77e00bfc
+oid sha256:c1e6dc68c41fbd045d9ac247c49496cf7724a6cf77cbcb2b67a92367bfe54a41
 size 87103456

trainer_state.json

@@ -10,96 +10,96 @@
   "log_history": [
     {
       "epoch": 0.32,
-      "grad_norm": 1.1198184490203857,
+      "grad_norm": 1.0203443765640259,
       "learning_rate": 0.00018333333333333334,
-      "loss": 9.5048,
+      "loss": 9.4828,
       "step": 2
     },
     {
       "epoch": 0.64,
-      "grad_norm": 1.484774112701416,
+      "grad_norm": 1.6231805086135864,
       "learning_rate": 0.0001666666666666667,
-      "loss": 9.1561,
+      "loss": 9.1586,
       "step": 4
     },
     {
       "epoch": 0.96,
-      "grad_norm": 1.7884565591812134,
+      "grad_norm": 2.2771148681640625,
       "learning_rate": 0.00015000000000000001,
-      "loss": 8.7599,
+      "loss": 8.6907,
       "step": 6
     },
     {
       "epoch": 1.28,
-      "grad_norm": 2.068845748901367,
+      "grad_norm": 2.1158745288848877,
       "learning_rate": 0.00013333333333333334,
-      "loss": 8.3414,
+      "loss": 8.2535,
       "step": 8
     },
     {
       "epoch": 1.6,
-      "grad_norm": 1.795763373374939,
+      "grad_norm": 1.86466646194458,
       "learning_rate": 0.00011666666666666668,
-      "loss": 7.7836,
+      "loss": 7.8775,
       "step": 10
     },
     {
       "epoch": 1.92,
-      "grad_norm": 1.7066673040390015,
+      "grad_norm": 1.410565972328186,
       "learning_rate": 0.0001,
-      "loss": 7.6516,
+      "loss": 7.5684,
       "step": 12
     },
     {
       "epoch": 2.24,
-      "grad_norm": 1.1048855781555176,
+      "grad_norm": 0.9350765347480774,
       "learning_rate": 8.333333333333334e-05,
-      "loss": 7.46,
+      "loss": 7.4331,
       "step": 14
     },
     {
       "epoch": 2.56,
-      "grad_norm": 1.1122359037399292,
+      "grad_norm": 0.9051127433776855,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 7.3065,
+      "loss": 7.3164,
       "step": 16
     },
     {
       "epoch": 2.88,
-      "grad_norm": 0.861113429069519,
+      "grad_norm": 0.8144361972808838,
       "learning_rate": 5e-05,
-      "loss": 7.3444,
+      "loss": 7.2426,
       "step": 18
     },
     {
       "epoch": 3.2,
-      "grad_norm": 0.823173999786377,
+      "grad_norm": 1.0328956842422485,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 7.2627,
+      "loss": 7.2851,
       "step": 20
     },
     {
       "epoch": 3.52,
-      "grad_norm": 1.0423370599746704,
+      "grad_norm": 0.9490511417388916,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 7.2814,
+      "loss": 7.213,
       "step": 22
     },
     {
       "epoch": 3.84,
-      "grad_norm": 1.099845290184021,
+      "grad_norm": 0.826574981212616,
       "learning_rate": 0.0,
-      "loss": 7.1932,
+      "loss": 7.1788,
       "step": 24
     },
     {
       "epoch": 3.84,
       "step": 24,
-      "total_flos": 109884496962696.0,
-      "train_loss": 7.920459071795146,
-      "train_runtime": 655.7984,
-      "train_samples_per_second": 0.61,
-      "train_steps_per_second": 0.037
+      "total_flos": 107168334014400.0,
+      "train_loss": 7.891708850860596,
+      "train_runtime": 637.8922,
+      "train_samples_per_second": 0.627,
+      "train_steps_per_second": 0.038
     }
   ],
   "logging_steps": 2,
@@ -119,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 109884496962696.0,
+  "total_flos": 107168334014400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f941d7fce172d0b7e47f0cd2175944690b202b69474adbde057d4362d96c34cd
+oid sha256:4ed44bbba431b37c6462f34863ba816b3104e8ed88becd5a7f9bd9e0cfa09f55
 size 5368