Checkpoint at step 5209

best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6041a80e8d6b5dbea253b7b3eb42e770af91dc27f3f0e652b11a6aa67df96e
+size 5607926677

best_model_5209.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6041a80e8d6b5dbea253b7b3eb42e770af91dc27f3f0e652b11a6aa67df96e
+size 5607926677

config.json

@@ -26,11 +26,11 @@
     "mixed_precision": false,
     "precision": "fp16",
     "epochs": 6,
-    "batch_size": 8,
+    "batch_size": 4,
     "eval_batch_size": 4,
     "grad_clip": 0.0,
     "scheduler_after_epoch": true,
-    "lr": 2e-05,
+    "lr": 1e-05,
     "optimizer": "AdamW",
     "optimizer_params": {
         "betas": [
@@ -40,14 +40,9 @@
         "eps": 1e-08,
         "weight_decay": 0.01
     },
-    "lr_scheduler": "MultiStepLR",
+    "lr_scheduler": "ExponentialLR",
     "lr_scheduler_params": {
-        "milestones": [
-            5000,
-            15000,
-            30000
-        ],
-        "gamma": 0.5,
+        "gamma": 0.95,
         "last_epoch": -1
     },
     "use_grad_scaler": false,
@@ -75,7 +70,7 @@
     "phoneme_cache_path": null,
     "characters": null,
     "add_blank": false,
-    "batch_group_size": 8,
+    "batch_group_size": 4,
     "loss_masking": null,
     "min_audio_len": 1,
     "max_audio_len": Infinity,
@@ -102,7 +97,7 @@
         }
     ],
     "test_sentences": [],
-    "eval_split_max_size": 256,
+    "eval_split_max_size": 32,
     "eval_split_size": 0.01,
     "use_speaker_weighted_sampler": false,
     "speaker_weighted_sampler_alpha": 1.0,
@@ -186,6 +181,6 @@
     "optimizer_wd_only_on_weights": false,
     "weighted_loss_attrs": null,
     "weighted_loss_multipliers": null,
-    "restore_path": "/workspace/training_output/XTTS_Dahih_OmarSamir_Finetune-December-19-2025_04+09PM-0000000/best_model_6626.pth",
+    "restore_path": "/workspace/training_output/XTTS_Dahih_OmarSamir_Finetune-December-19-2025_10+29PM-0000000/best_model_5208.pth",
     "github_branch": "inside_docker"
 }

events.out.tfevents.1766186420.0d38972e308b.2948.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372a0ba650721a896101e2daa2e9c7699f10061e7e9d10fecb8d838c27c460e9
+size 6305

ipykernel_launcher.py

@@ -0,0 +1,18 @@
+"""Entry point for launching an IPython kernel.
+
+This is separate from the ipykernel package so we can avoid doing imports until
+after removing the cwd from sys.path.
+"""
+
+import sys
+from pathlib import Path
+
+if __name__ == "__main__":
+    # Remove the CWD from sys.path while we load stuff.
+    # This is added back by InteractiveShellApp.init_path()
+    if sys.path[0] == "" or Path(sys.path[0]) == Path.cwd():
+        del sys.path[0]
+
+    from ipykernel import kernelapp as app
+
+    app.launch_new_instance()

trainer_0_log.txt

@@ -0,0 +1,34 @@
+ > Training Environment:
+ | > Backend: Torch
+ | > Mixed precision: False
+ | > Precision: float32
+ | > Current device: 0
+ | > Num. of GPUs: 1
+ | > Num. of CPUs: 256
+ | > Num. of Torch Threads: 1
+ | > Torch seed: 1
+ | > Torch CUDNN: True
+ | > Torch CUDNN deterministic: False
+ | > Torch CUDNN benchmark: False
+ | > Torch TF32 MatMul: False
+ > Start Tensorboard: tensorboard --logdir=/workspace/training_output/XTTS_Dahih_OmarSamir_Finetune-December-19-2025_11+20PM-0000000
+ > Restoring from best_model_5208.pth ...
+ > Restoring Model...
+ > Restoring Optimizer...
+ > Model restored from step 5208
+
+ > Model has 514771807 parameters
+
+ > EPOCH: 0/6
+ --> /workspace/training_output/XTTS_Dahih_OmarSamir_Finetune-December-19-2025_11+20PM-0000000
+
+ > EVALUATION 
+
+
+  --> EVAL PERFORMANCE
+     | > avg_loader_time: 0.07972378827430109 (+0)
+     | > avg_loss_text_ce: 0.03184887157702769 (+0)
+     | > avg_loss_mel_ce: 4.041015415578272 (+0)
+     | > avg_loss: 4.072864298884932 (+0)
+
+ > BEST MODEL : /workspace/training_output/XTTS_Dahih_OmarSamir_Finetune-December-19-2025_11+20PM-0000000/best_model_5209.pth