Checkpoint at step 120

checkpoints/{checkpoint-80 → checkpoint-100}/small_experts_and_gates.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18f5bc94ce657ff2622e730419e52a30ceebcb5e01cdd278338e0e14c0f1077
+oid sha256:5d82bd84ff634baa4c51f97ea7bdffe07cf48171eadc3909c4eda856acde3a7f
 size 206711911

checkpoints/{checkpoint-80 → checkpoint-120}/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82affd842ec486fef2da08a6bc5620d759625dcd2a9671f7e1633db3e23e8154
+oid sha256:7e66835c11c328972e5c3aca4ca33c740b7b0924674ea7c46ac5446b1cf72ad6
 size 4998915096

checkpoints/{checkpoint-80 → checkpoint-120}/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a982717a3e6e6f33e64b592ba98c998d77f1fea7b50229735c94b491857b47a7
+oid sha256:f95028f4f23f7f97e6f957a116ae7ed5c1786b70714c46acf32d598c0364f37a
 size 4998953920

checkpoints/{checkpoint-80 → checkpoint-120}/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2321b2ac4c163adff676d015f90a88da265a1515998048140c100ab1b50a7643
+oid sha256:86d89d2e973ee1a7c4643e686f2f4e2dd39b66cee244338e1595f7d822241999
 size 4046769808

checkpoints/{checkpoint-80 → checkpoint-120}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60afe906089703ce8ff6dc7db2e543bedd92d9c1554d99f956ac873fa29965c8
-size 394655075
+oid sha256:bfccbd1c3cfda9ff3b0843fbb0c24ab4f3b3011f1c72f27af1f8a92e90cf5f9b
+size 395446581

checkpoints/{checkpoint-80 → checkpoint-120}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d484e81fa22cdbcf66c2585a42950fa1db3e6db36dd8936a72f76c2844202008
+oid sha256:1667f35815259ae6fd1ff856a03958895cb054d32709d591bfa61b2107504cb1
 size 1465

checkpoints/{checkpoint-80 → checkpoint-120}/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00392452645069507,
+  "epoch": 0.0058867896760426055,
   "eval_steps": 500,
-  "global_step": 80,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,34 @@
       "learning_rate": 1.2916939175931983e-06,
       "loss": 108.4838,
       "step": 80
+    },
+    {
+      "epoch": 0.0044150922570319545,
+      "grad_norm": 59.75,
+      "learning_rate": 1.4551994767822106e-06,
+      "loss": 104.6467,
+      "step": 90
+    },
+    {
+      "epoch": 0.004905658063368838,
+      "grad_norm": 53.25,
+      "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
     }
   ],
   "logging_steps": 10,
@@ -83,7 +111,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1764976553230336e+17,
+  "total_flos": 3.2647464829845504e+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 sha256:10f992425880062aee94cbc0044c2e5c836f3e78a7ddc54153790b6921b487bb
-size 7314
+oid sha256:7b5ad60d0cdc6173b79cac2415fd5d95271d4885f84a9e2f16600ff1587d6e7b
+size 7728