Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4711c604191c70b1e9a248ff89ea22db5362690aa8037aa62c5c84d06fc55f81
+oid sha256:f7a164557eb74ce102f82cd4df90a332f6f0dfbadf4438231beee9da629f888f
 size 8297288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:663863afca4c95a45977985d1fcd4fa2b26b80e962ef1e6075fe7371d1abb417
+oid sha256:4637fdfb65a1f9530af247946f9f8924232074d8c79ff8668d3484deeb6283b7
 size 16761163

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6eb5b1a4961028fe68de934a271b3920cdc97935fe1a1ad9fd0f05662957a2
+oid sha256:26d1df2276f727e3cca661e1a84a63428c1b4328b6b80b1d5325b41c0298da4d
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7092e272a6bfc2c815a87505efd3c62d8b3b8462044807a20f9427f7f599c43
+oid sha256:4b89e7f9c8e503d4cfdc04fb61835e00a23616af74eceff894d548f5f90cea56
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f810a5865983beee2c8a2c1261e8005dbb8b6e24c20d69bc4958ca74ac736911
+oid sha256:b1cfc743553d4d9ba9acea35cf048c15e0c667b2f4210c4a170ee0849112d83b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 200,
   "best_metric": 0.6018396615982056,
   "best_model_checkpoint": "./t5gemma-math-corrector/checkpoint-200",
-  "epoch": 1.9238171611868484,
+  "epoch": 2.5645549318364074,
   "eval_steps": 200,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -116,6 +116,42 @@
       "eval_samples_per_second": 50.737,
       "eval_steps_per_second": 12.781,
       "step": 600
+    },
+    {
+      "epoch": 2.0834001603849237,
+      "grad_norm": 0.13095279037952423,
+      "learning_rate": 3.408551068883611e-05,
+      "loss": 0.0009,
+      "step": 650
+    },
+    {
+      "epoch": 2.2437850842020852,
+      "grad_norm": 0.1417347490787506,
+      "learning_rate": 2.8147268408551068e-05,
+      "loss": 0.0005,
+      "step": 700
+    },
+    {
+      "epoch": 2.4041700080192463,
+      "grad_norm": 0.07039827853441238,
+      "learning_rate": 2.2209026128266035e-05,
+      "loss": 0.0005,
+      "step": 750
+    },
+    {
+      "epoch": 2.5645549318364074,
+      "grad_norm": 0.2078932374715805,
+      "learning_rate": 1.6270783847980998e-05,
+      "loss": 0.0005,
+      "step": 800
+    },
+    {
+      "epoch": 2.5645549318364074,
+      "eval_loss": 3.8249130249023438,
+      "eval_runtime": 5.2131,
+      "eval_samples_per_second": 50.258,
+      "eval_steps_per_second": 12.66,
+      "step": 800
     }
   ],
   "logging_steps": 50,
@@ -130,7 +166,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -139,12 +175,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2318240219922432.0,
+  "total_flos": 3090020422385664.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null