Checkpoint at step 160

checkpoints/{checkpoint-120 → checkpoint-160}/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1089598fbbb6f42b40c814d31bde5be78a9aa6b9e1d526deecac6341630b1dbb
+oid sha256:7a241063a39f1ff9a6cffbf934ac8f5410f497d18f46d2ce0d2c28579b8a0d78
 size 4997867120

checkpoints/{checkpoint-120 → checkpoint-160}/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5fa112c67dad1fe88ed491b543147a93367b9895a08c34c1cab77a38255157
+oid sha256:5f7852608c5311f834372b7a4e2987475df5a4f5162eb68e6e35d2a5ec4f706a
 size 3856242664

checkpoints/{checkpoint-120 → checkpoint-160}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:583766715e9d087db5ea3d414a714aed34c29f8a9aa087daf8f91541d3045939
+oid sha256:3cd468102392da025529f8eb11dc3bc0ad37dcf17afae5eb6d4164d29b18a0b8
 size 25858571

checkpoints/{checkpoint-120 → checkpoint-160}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1667f35815259ae6fd1ff856a03958895cb054d32709d591bfa61b2107504cb1
+oid sha256:acda1dbd18939debf680533b87259bb4016966fb65eb95873938a85d449a03f3
 size 1465

checkpoints/{checkpoint-120 → checkpoint-160}/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0058867896760426055,
+  "epoch": 0.00784905290139014,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,34 @@
       "learning_rate": 1.945716154349248e-06,
       "loss": 105.1651,
       "step": 120
+    },
+    {
+      "epoch": 0.006377355482379489,
+      "grad_norm": 37.75,
+      "learning_rate": 2.1092217135382606e-06,
+      "loss": 105.2588,
+      "step": 130
+    },
+    {
+      "epoch": 0.006867921288716374,
+      "grad_norm": 38.25,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 104.3058,
+      "step": 140
+    },
+    {
+      "epoch": 0.007358487095053257,
+      "grad_norm": 40.0,
+      "learning_rate": 2.4362328319162854e-06,
+      "loss": 104.7016,
+      "step": 150
+    },
+    {
+      "epoch": 0.00784905290139014,
+      "grad_norm": 41.0,
+      "learning_rate": 2.5997383911052975e-06,
+      "loss": 103.8965,
+      "step": 160
     }
   ],
   "logging_steps": 10,
@@ -111,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2192885491236864e+17,
+  "total_flos": 4.292384732164915e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

logs/events.out.tfevents.1756423478.a504719e5285.5303.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc912cce9c971c2228a279552d23f535c7f9e93d9f8fc1310ecb3a06c65cbcdb
-size 8150
+oid sha256:8dbea690e061baa450cf674bd6e421f7e190ad7bc183e118e9f19c9bcc140e4f
+size 8572