Training in progress, step 4

adapter_config.json

@@ -23,22 +23,22 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "lm_heads.1",
-    "enc_to_dec_proj",
-    "lm_heads.2",
-    "embed_tokens.1",
-    "fc2",
+    "lm_heads.3",
     "out_proj",
+    "embed_tokens.1",
     "lm_heads.0",
-    "k_proj",
-    "fc1",
-    "embed_tokens.0",
     "v_proj",
+    "embed_tokens.0",
     "embed_tokens.3",
-    "audio_enc_to_dec_proj",
-    "embed_tokens.2",
     "q_proj",
-    "lm_heads.3"
+    "fc1",
+    "embed_tokens.2",
+    "enc_to_dec_proj",
+    "lm_heads.2",
+    "lm_heads.1",
+    "fc2",
+    "k_proj",
+    "audio_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:fa2099c38e60b46ed5258df42e9fd58f59dbc5b28e509f18ae556b419aee0d5a
+oid sha256:7b09d1b45d01532c25664b6a8d73ca24f45c1c840759ca69908c2c91b6009d7b
 size 87103456

trainer_state.json

@@ -10,110 +10,110 @@
   "log_history": [
     {
       "epoch": 0.26229508196721313,
-      "grad_norm": 1.36014723777771,
+      "grad_norm": 1.3779234886169434,
       "learning_rate": 0.00018571428571428572,
-      "loss": 9.4034,
+      "loss": 9.4061,
       "step": 2
     },
     {
       "epoch": 0.5245901639344263,
-      "grad_norm": 2.117264986038208,
+      "grad_norm": 2.1614365577697754,
       "learning_rate": 0.00017142857142857143,
-      "loss": 8.9051,
+      "loss": 8.9057,
       "step": 4
     },
     {
       "epoch": 0.7868852459016393,
-      "grad_norm": 2.277207851409912,
+      "grad_norm": 2.2431693077087402,
       "learning_rate": 0.00015714285714285716,
-      "loss": 8.3058,
+      "loss": 8.3094,
       "step": 6
     },
     {
       "epoch": 1.0491803278688525,
-      "grad_norm": 1.9988380670547485,
+      "grad_norm": 2.040867567062378,
       "learning_rate": 0.00014285714285714287,
-      "loss": 7.8175,
+      "loss": 7.8253,
       "step": 8
     },
     {
       "epoch": 1.3114754098360657,
-      "grad_norm": 1.7698421478271484,
+      "grad_norm": 1.7131154537200928,
       "learning_rate": 0.00012857142857142858,
-      "loss": 7.2821,
+      "loss": 7.2788,
       "step": 10
     },
     {
       "epoch": 1.5737704918032787,
-      "grad_norm": 2.32663893699646,
+      "grad_norm": 2.2424774169921875,
       "learning_rate": 0.00011428571428571428,
-      "loss": 7.4096,
+      "loss": 7.4106,
       "step": 12
     },
     {
       "epoch": 1.8360655737704918,
-      "grad_norm": 1.4435824155807495,
+      "grad_norm": 1.3827060461044312,
       "learning_rate": 0.0001,
-      "loss": 7.1488,
+      "loss": 7.1381,
       "step": 14
     },
     {
       "epoch": 2.098360655737705,
-      "grad_norm": 1.5567710399627686,
+      "grad_norm": 1.5854527950286865,
       "learning_rate": 8.571428571428571e-05,
-      "loss": 6.7253,
+      "loss": 6.73,
       "step": 16
     },
     {
       "epoch": 2.360655737704918,
-      "grad_norm": 1.3461309671401978,
+      "grad_norm": 1.3298927545547485,
       "learning_rate": 7.142857142857143e-05,
-      "loss": 6.9232,
+      "loss": 6.9203,
       "step": 18
     },
     {
       "epoch": 2.6229508196721314,
-      "grad_norm": 1.2633932828903198,
+      "grad_norm": 1.2383928298950195,
       "learning_rate": 5.714285714285714e-05,
-      "loss": 6.7861,
+      "loss": 6.7813,
       "step": 20
     },
     {
       "epoch": 2.8852459016393444,
-      "grad_norm": 0.7925029993057251,
+      "grad_norm": 0.7927147746086121,
       "learning_rate": 4.2857142857142856e-05,
-      "loss": 6.8389,
+      "loss": 6.8375,
       "step": 22
     },
     {
       "epoch": 3.1475409836065573,
-      "grad_norm": 1.3408855199813843,
+      "grad_norm": 1.323878288269043,
       "learning_rate": 2.857142857142857e-05,
-      "loss": 6.5778,
+      "loss": 6.5755,
       "step": 24
     },
     {
       "epoch": 3.4098360655737707,
-      "grad_norm": 1.250908613204956,
+      "grad_norm": 1.2399470806121826,
       "learning_rate": 1.4285714285714285e-05,
-      "loss": 6.8636,
+      "loss": 6.858,
       "step": 26
     },
     {
       "epoch": 3.6721311475409837,
-      "grad_norm": 1.3394016027450562,
+      "grad_norm": 1.3425202369689941,
       "learning_rate": 0.0,
-      "loss": 6.9516,
+      "loss": 6.9506,
       "step": 28
     },
     {
       "epoch": 3.6721311475409837,
       "step": 28,
-      "total_flos": 134754941373624.0,
-      "train_loss": 7.424190691539219,
-      "train_runtime": 121.6682,
-      "train_samples_per_second": 4.011,
-      "train_steps_per_second": 0.23
+      "total_flos": 132611574693336.0,
+      "train_loss": 7.423375640596662,
+      "train_runtime": 122.2841,
+      "train_samples_per_second": 3.991,
+      "train_steps_per_second": 0.229
     }
   ],
   "logging_steps": 2,
@@ -133,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 134754941373624.0,
+  "total_flos": 132611574693336.0,
   "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:b21cfb00c3b3ba05ddd27e4bb1c062195ee924a7227604116ce415796e5c359a
+oid sha256:d590ff2db245cff603ee4729814aa644ed00ba9a334de616c539cbfd9da92f25
 size 5304