Training in progress, step 4

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563d62367eff0d026d6f12977994466d78be8804c258adbaeac3d45eb5dfa14c
+oid sha256:bd9be4656a77bb5db3858cf9a56e37f919319f53a4e22a8519c21a119984bb3e
 size 87103456

all_results.json

@@ -6,10 +6,10 @@
     "eval_samples": 4,
     "eval_samples_per_second": 0.021,
     "eval_steps_per_second": 0.021,
-    "total_flos": 16296977689776.0,
-    "train_loss": 67.02359962463379,
-    "train_runtime": 75.0366,
+    "total_flos": 15373112741376.0,
+    "train_loss": 67.15349578857422,
+    "train_runtime": 193.0014,
     "train_samples": 42,
-    "train_samples_per_second": 1.119,
-    "train_steps_per_second": 0.053
+    "train_samples_per_second": 0.435,
+    "train_steps_per_second": 0.021
 }

runs/Oct24_20-22-59_945154a0a094/events.out.tfevents.1729801456.945154a0a094.27261.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8715ba0d05c95e9a2653f582ddb3d26a23c784b44c4f0a1d9ef12568c24e6538
+size 13750

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.6666666666666665,
-    "total_flos": 16296977689776.0,
-    "train_loss": 67.02359962463379,
-    "train_runtime": 75.0366,
+    "total_flos": 15373112741376.0,
+    "train_loss": 67.15349578857422,
+    "train_runtime": 193.0014,
     "train_samples": 42,
-    "train_samples_per_second": 1.119,
-    "train_steps_per_second": 0.053
+    "train_samples_per_second": 0.435,
+    "train_steps_per_second": 0.021
 }

trainer_state.json

@@ -10,40 +10,40 @@
   "log_history": [
     {
       "epoch": 0.38095238095238093,
-      "grad_norm": 20.528797149658203,
+      "grad_norm": 25.628726959228516,
       "learning_rate": 0.00015000000000000001,
-      "loss": 72.0964,
+      "loss": 70.8207,
       "step": 1
     },
     {
       "epoch": 0.7619047619047619,
-      "grad_norm": 35.755401611328125,
+      "grad_norm": 37.944496154785156,
       "learning_rate": 0.0001,
-      "loss": 66.6014,
+      "loss": 66.5958,
       "step": 2
     },
     {
       "epoch": 1.2857142857142856,
-      "grad_norm": 21.73655128479004,
+      "grad_norm": 24.337867736816406,
       "learning_rate": 5e-05,
-      "loss": 68.7338,
+      "loss": 69.4538,
       "step": 3
     },
     {
       "epoch": 1.6666666666666665,
-      "grad_norm": 38.31291198730469,
+      "grad_norm": 32.62247085571289,
       "learning_rate": 0.0,
-      "loss": 60.6627,
+      "loss": 61.7436,
       "step": 4
     },
     {
       "epoch": 1.6666666666666665,
       "step": 4,
-      "total_flos": 16296977689776.0,
-      "train_loss": 67.02359962463379,
-      "train_runtime": 75.0366,
-      "train_samples_per_second": 1.119,
-      "train_steps_per_second": 0.053
+      "total_flos": 15373112741376.0,
+      "train_loss": 67.15349578857422,
+      "train_runtime": 193.0014,
+      "train_samples_per_second": 0.435,
+      "train_steps_per_second": 0.021
     }
   ],
   "logging_steps": 1.0,
@@ -63,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 16296977689776.0,
+  "total_flos": 15373112741376.0,
   "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:bf77e95cffc3a182313086f685e8bb85b38ddfecce9c93f6e7f7cd7cef681ea8
+oid sha256:698a3f013ad287a54ad827f8d0123dedfeae90e5f16059c944789346e604dcac
 size 5432