Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61bffa07b45ea172ed2e6316fca83698825d827432b4eaa5d1e39c152b7de39b
+oid sha256:dd298c5fcda0612c1e18f0260e0bd93397e2c3f765056b53e7ef9e5dc828ee96
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8514b4945a797b24abc9ae3ec07458e72f84f4934fbd92b37d3888f233f8e67b
+oid sha256:3332bb290f42088fe9bf51bd93283775353bb5178c67e92d107baab15df76b33
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b03f74e10591ff22477365642275703166a34b306471da2a9df3e87497356f
+oid sha256:711796bafdc96291445baaa7500e0225de597273f70515e4b639ff3ce6d4e57c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0471ce3745a36e49a3e0d19eac020ddc42dff8b92447d06fa38e6a682e228b19
+oid sha256:28f9eb0c69e2570740da7219ce2550d9ec1f1cae9401a3fd6e61ae4b99913ab1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01,
+  "epoch": 0.012,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -358,6 +358,76 @@
       "learning_rate": 0.0002976012024048096,
       "loss": 78.96190795898437,
       "step": 500
+    },
+    {
+      "epoch": 0.0102,
+      "grad_norm": 9.10632610321045,
+      "learning_rate": 0.00029754108216432863,
+      "loss": 78.6921875,
+      "step": 510
+    },
+    {
+      "epoch": 0.0104,
+      "grad_norm": 9.557915687561035,
+      "learning_rate": 0.0002974809619238477,
+      "loss": 71.66650390625,
+      "step": 520
+    },
+    {
+      "epoch": 0.0106,
+      "grad_norm": 8.777642250061035,
+      "learning_rate": 0.0002974208416833667,
+      "loss": 70.4987548828125,
+      "step": 530
+    },
+    {
+      "epoch": 0.0108,
+      "grad_norm": 13.94754409790039,
+      "learning_rate": 0.0002973607214428857,
+      "loss": 72.32754516601562,
+      "step": 540
+    },
+    {
+      "epoch": 0.011,
+      "grad_norm": 8.856101989746094,
+      "learning_rate": 0.0002973006012024048,
+      "loss": 70.21427612304687,
+      "step": 550
+    },
+    {
+      "epoch": 0.0112,
+      "grad_norm": 9.487411499023438,
+      "learning_rate": 0.0002972404809619238,
+      "loss": 76.47840576171875,
+      "step": 560
+    },
+    {
+      "epoch": 0.0114,
+      "grad_norm": 8.979376792907715,
+      "learning_rate": 0.00029718036072144287,
+      "loss": 77.88162231445312,
+      "step": 570
+    },
+    {
+      "epoch": 0.0116,
+      "grad_norm": 9.910178184509277,
+      "learning_rate": 0.0002971202404809619,
+      "loss": 77.7337646484375,
+      "step": 580
+    },
+    {
+      "epoch": 0.0118,
+      "grad_norm": 5.745482444763184,
+      "learning_rate": 0.00029706012024048096,
+      "loss": 71.672021484375,
+      "step": 590
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 9.654470443725586,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 74.40623168945312,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -377,7 +447,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8161860202859520.0,
+  "total_flos": 8779456241464320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null