Checkpoint at step 140

checkpoints/{checkpoint-100 → checkpoint-120}/small_experts_and_gates.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d82bd84ff634baa4c51f97ea7bdffe07cf48171eadc3909c4eda856acde3a7f
+oid sha256:5c4282873095c301aad8677e55b64e83a15193d69857156b21ac921601b9db90
 size 206711911

checkpoints/{checkpoint-100 → checkpoint-140}/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:306ae2c5a62a9d5985833823942be31e4af511252576cd26b40a35b7d9201283
+oid sha256:404f0b9cc259501002abdac229154ab82b25dce489f20b2ad7811e76750e80c6
 size 4998915096

checkpoints/{checkpoint-100 → checkpoint-140}/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3799244485da1d90d05ca0b89bec8a7fe2e5476a63c730756f9b69c4e67d4e6f
+oid sha256:c9255dee9fd14085ad154062aa5a4d782bacda8f23d257ecbd73e24520d75a1a
 size 4998953920

checkpoints/{checkpoint-100 → checkpoint-140}/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb7bd262681ea7437fa4a014046e12ecb56c73fd62debb8d2d232f416305560
+oid sha256:7b9619e71d94a27e6c67f8c6018879e79f7dae707fb58af374b594ec6559a171
 size 4046769808

checkpoints/{checkpoint-100 → checkpoint-140}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81c59ba9675a87d095d8a3b1b6affbaa56688ab72a82724c47d00c8b7f93657
-size 395050796
+oid sha256:1494d3ec81551393518ff51ef9ffe3873120be3340ab65d29b5e757e6e372351
+size 395446581

checkpoints/{checkpoint-100 → checkpoint-140}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:528392556c02087909bc6166c540e006acf7c36a66f3053e5688b159ec58a0e0
+oid sha256:2ec75cf6ac19343a75daf1406106e27065bad1d0cafbfb1bdf22f7c2520d0b45
 size 1465

checkpoints/{checkpoint-100 → checkpoint-140}/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004905658063368838,
+  "epoch": 0.006867921288716374,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,6 +78,34 @@
       "learning_rate": 1.618705035971223e-06,
       "loss": 105.9295,
       "step": 100
+    },
+    {
+      "epoch": 0.005396223869705722,
+      "grad_norm": 55.0,
+      "learning_rate": 1.7822105951602354e-06,
+      "loss": 105.9408,
+      "step": 110
+    },
+    {
+      "epoch": 0.0058867896760426055,
+      "grad_norm": 44.0,
+      "learning_rate": 1.945716154349248e-06,
+      "loss": 106.3008,
+      "step": 120
+    },
+    {
+      "epoch": 0.006377355482379489,
+      "grad_norm": 52.75,
+      "learning_rate": 2.1092217135382606e-06,
+      "loss": 105.7874,
+      "step": 130
+    },
+    {
+      "epoch": 0.006867921288716374,
+      "grad_norm": 61.0,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 106.241,
+      "step": 140
     }
   ],
   "logging_steps": 10,
@@ -97,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.720622069153792e+17,
+  "total_flos": 3.808870896815309e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

logs/events.out.tfevents.1756831118.5624918391e3.1490.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5ad60d0cdc6173b79cac2415fd5d95271d4885f84a9e2f16600ff1587d6e7b
-size 7728
+oid sha256:c4b1226d54f75f50b5c509e0f0ce1396b81d70aab5a9b09e731c5b5a3f103929
+size 8150