EXP_134_davidnet-e2e_s7: checkpoint step 1500

experiments/EXP_134_davidnet-e2e_s7/best_model/meta.json

@@ -1,10 +1,10 @@
 {
   "config_hash": "cec49e46a7c8",
-  "epoch": 1,
+  "epoch": 2,
   "exp_id": "EXP_134",
-  "metric": 0.9793904761904761,
+  "metric": 0.9821714285714286,
   "metric_name": "val/mean_auc",
-  "saved_at": "2026-10-05T20:47:07Z",
-  "sha256": "1ec6e6970f4166dcf901815648b9fc942fc9c83f591c8b89b507848496c222d3",
-  "step": 543
+  "saved_at": "2026-10-05T21:02:54Z",
+  "sha256": "b593b2cc0c5b30c786b9c3727d12c44068b1f3e2761f152207f6c7493ceeb15a",
+  "step": 1086
 }

experiments/EXP_134_davidnet-e2e_s7/best_model/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec6e6970f4166dcf901815648b9fc942fc9c83f591c8b89b507848496c222d3
+oid sha256:b593b2cc0c5b30c786b9c3727d12c44068b1f3e2761f152207f6c7493ceeb15a
 size 1064018476

experiments/EXP_134_davidnet-e2e_s7/checkpoints/LATEST.json

@@ -1,10 +1,10 @@
 {
-  "step": 1000,
-  "dir": "checkpoints/step-0001000",
-  "updated_at": "2026-10-05T20:59:20Z",
+  "step": 1500,
+  "dir": "checkpoints/step-0001500",
+  "updated_at": "2026-10-05T21:13:58Z",
   "config_hash": "cec49e46a7c8",
   "history": [
-    "checkpoints/step-0000500",
-    "checkpoints/step-0001000"
+    "checkpoints/step-0001000",
+    "checkpoints/step-0001500"
   ]
 }

experiments/EXP_134_davidnet-e2e_s7/checkpoints/{step-0000500 → step-0001500}/meta.json

@@ -1,13 +1,13 @@
 {
   "config_hash": "cec49e46a7c8",
-  "created_at": "2026-10-05T20:44:37Z",
-  "epoch": 0,
+  "created_at": "2026-10-05T21:13:53Z",
+  "epoch": 2,
   "files": {
     "training_state.pt": {
-      "bytes": 1952953431,
-      "sha256": "ab68c90e20447e21db9be16392fce8f8bd560ab1da7a93b26ad72800b8832d94"
+      "bytes": 1952954839,
+      "sha256": "f5926aedf1dc3ab3a0812e97c745b56a7caa9049afa53b4dd8dbaf4b39e039c4"
     }
   },
   "reason": "interval",
-  "step": 500
+  "step": 1500
 }

experiments/EXP_134_davidnet-e2e_s7/checkpoints/{step-0000500 → step-0001500}/training_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab68c90e20447e21db9be16392fce8f8bd560ab1da7a93b26ad72800b8832d94
-size 1952953431
+oid sha256:f5926aedf1dc3ab3a0812e97c745b56a7caa9049afa53b4dd8dbaf4b39e039c4
+size 1952954839

experiments/EXP_134_davidnet-e2e_s7/logs/pipeline.jsonl

@@ -13,3 +13,7 @@
 {"t": "2026-10-05T20:47:10Z", "level": "INFO", "event": "epoch_completed", "msg": "[epoch_completed] EXP_134 epoch 1/6 (epoch=1, step=543, lr=2.962e-05, train/v=0.02504, train/a=0.006415, train/quad=0.1052, train/loc=0.1032, train/sync=1.744, train/dis=0.0115, train/total=0.3112, val/v_loss=0.2242, val/a_loss=1.942e-05, val/quad_loss=0.6452, val/loc_loss=0.6159, val/sync_loss=0.4604, val/dis_loss=0.01622, val/loss=0.9024, val/video_auc=0.9588, val/video_f1@0.5=0.9379, val/audio_auc=1, val/audio_f1@0.5=1, val/clip_auc=0.9661, val/clip_f1@0.5=0.9662, val/mean_auc=0.9794, val/quad_macro_f1=0.8839, epoch_seconds=934.6, val_seconds=70.9, best=0.9794, improved=True)", "epoch": 1, "step": 543, "lr": 2.961518973100432e-05, "train/v": 0.0250449418889137, "train/a": 0.006414689948824734, "train/quad": 0.10523473196678439, "train/loc": 0.10316326157981015, "train/sync": 1.7438979102761707, "train/dis": 0.011497428312434164, "train/total": 0.3111981663501433, "val/v_loss": 0.2242186783050294, "val/a_loss": 1.941705847526757e-05, "val/quad_loss": 0.6451838786324515, "val/loc_loss": 0.6158926675352492, "val/sync_loss": 0.4603520943568303, "val/dis_loss": 0.016218503750860692, "val/loss": 0.9024334369048189, "val/video_auc": 0.9587809523809524, "val/video_f1@0.5": 0.9379128137384413, "val/audio_auc": 1.0, "val/audio_f1@0.5": 1.0, "val/clip_auc": 0.966051364365971, "val/clip_f1@0.5": 0.9662162162162162, "val/mean_auc": 0.9793904761904761, "val/quad_macro_f1": 0.8839382392897173, "epoch_seconds": 934.6, "val_seconds": 70.9, "best": 0.9793904761904761, "improved": true}
 {"t": "2026-10-05T20:47:10Z", "level": "INFO", "event": "validation_completed", "msg": "[validation_completed] val/mean_auc=0.9793904761904761"}
 {"t": "2026-10-05T20:59:19Z", "level": "INFO", "event": "checkpoint_saved", "msg": "[checkpoint_saved] step 1000 (interval) (step=1000, epoch=1, mb=1953)", "step": 1000, "epoch": 1, "mb": 1953.0}
+{"t": "2026-10-05T20:59:57Z", "level": "INFO", "event": "checkpoint_uploaded", "msg": "[checkpoint_uploaded] step 1000 verified on HF (step=1000, seconds=37.3, with_best=True)", "step": 1000, "seconds": 37.3, "with_best": true}
+{"t": "2026-10-05T21:02:57Z", "level": "INFO", "event": "epoch_completed", "msg": "[epoch_completed] EXP_134 epoch 2/6 (epoch=2, step=1086, lr=2.539e-05, train/v=0.03011, train/a=0.007398, train/quad=0.1194, train/loc=0.121, train/sync=1.513, train/dis=0.01087, train/total=0.3101, val/v_loss=0.2323, val/a_loss=0.003271, val/quad_loss=0.8162, val/loc_loss=0.7934, val/sync_loss=0.4234, val/dis_loss=0.01145, val/loss=1.084, val/video_auc=0.9643, val/video_f1@0.5=0.8918, val/audio_auc=1, val/audio_f1@0.5=0.9905, val/clip_auc=0.9769, val/clip_f1@0.5=0.9435, val/mean_auc=0.9822, val/quad_macro_f1=0.8377, epoch_seconds=942.6, val_seconds=71, best=0.9822, improved=True)", "epoch": 2, "step": 1086, "lr": 2.5391566924870616e-05, "train/v": 0.03010753179524702, "train/a": 0.007398241517931824, "train/quad": 0.11942002415181373, "train/loc": 0.12104001648840226, "train/sync": 1.5129483630863563, "train/dis": 0.010871686670812564, "train/total": 0.3101178020447159, "val/v_loss": 0.23230381943089573, "val/a_loss": 0.0032711590443798197, "val/quad_loss": 0.8161946674269319, "val/loc_loss": 0.7933969634072408, "val/sync_loss": 0.4234119745401236, "val/dis_loss": 0.011451273526136691, "val/loss": 1.083857118549685, "val/video_auc": 0.9643428571428572, "val/video_f1@0.5": 0.8918128654970761, "val/audio_auc": 1.0, "val/audio_f1@0.5": 0.9904761904761905, "val/clip_auc": 0.9769181380417336, "val/clip_f1@0.5": 0.9435294117647058, "val/mean_auc": 0.9821714285714286, "val/quad_macro_f1": 0.8377312475256351, "epoch_seconds": 942.6, "val_seconds": 71.0, "best": 0.9821714285714286, "improved": true}
+{"t": "2026-10-05T21:02:57Z", "level": "INFO", "event": "validation_completed", "msg": "[validation_completed] val/mean_auc=0.9821714285714286"}
+{"t": "2026-10-05T21:13:58Z", "level": "INFO", "event": "checkpoint_saved", "msg": "[checkpoint_saved] step 1500 (interval) (step=1500, epoch=2, mb=1953)", "step": 1500, "epoch": 2, "mb": 1953.0}

experiments/EXP_134_davidnet-e2e_s7/metrics/training_history.csv

@@ -1,2 +1,3 @@
 epoch,step,lr,train/v,train/a,train/quad,train/loc,train/sync,train/dis,train/total,val/v_loss,val/a_loss,val/quad_loss,val/loc_loss,val/sync_loss,val/dis_loss,val/loss,val/video_auc,val/video_f1@0.5,val/audio_auc,val/audio_f1@0.5,val/clip_auc,val/clip_f1@0.5,val/mean_auc,val/quad_macro_f1,epoch_seconds,val_seconds
 1,543,2.961518973100432e-05,0.0250449418889137,0.006414689948824734,0.10523473196678439,0.10316326157981015,1.7438979102761707,0.011497428312434164,0.3111981663501433,0.2242186783050294,1.941705847526757e-05,0.6451838786324515,0.6158926675352492,0.4603520943568303,0.016218503750860692,0.9024334369048189,0.9587809523809524,0.9379128137384413,1.0,1.0,0.966051364365971,0.9662162162162162,0.9793904761904761,0.8839382392897173,934.6,70.9
+2,1086,2.5391566924870616e-05,0.03010753179524702,0.007398241517931824,0.11942002415181373,0.12104001648840226,1.5129483630863563,0.010871686670812564,0.3101178020447159,0.23230381943089573,0.0032711590443798197,0.8161946674269319,0.7933969634072408,0.4234119745401236,0.011451273526136691,1.083857118549685,0.9643428571428572,0.8918128654970761,1.0,0.9904761904761905,0.9769181380417336,0.9435294117647058,0.9821714285714286,0.8377312475256351,942.6,71.0