Training in progress, step 700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd298c5fcda0612c1e18f0260e0bd93397e2c3f765056b53e7ef9e5dc828ee96
+oid sha256:eb6f8a4c71659aafc5d698b24d92000166e62b98d0a890b89501b9a4781bc981
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3332bb290f42088fe9bf51bd93283775353bb5178c67e92d107baab15df76b33
+oid sha256:6a3418f7557da2479bea92e3d8f042da6bfcb9d9191cf39c8a909b1433e82c08
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711796bafdc96291445baaa7500e0225de597273f70515e4b639ff3ce6d4e57c
+oid sha256:e153e7ac99a45d390bef333d0c839de8b829e6cf174508b6f317b3fb7550ce99
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f9eb0c69e2570740da7219ce2550d9ec1f1cae9401a3fd6e61ae4b99913ab1
+oid sha256:26190536bb49f49f7e44c120697c0e6b6c7e45ebca58eedf944e71fd9beb322d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012,
+  "epoch": 0.014,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -428,6 +428,76 @@
       "learning_rate": 0.00029699999999999996,
       "loss": 74.40623168945312,
       "step": 600
+    },
+    {
+      "epoch": 0.0122,
+      "grad_norm": 8.696991920471191,
+      "learning_rate": 0.000296939879759519,
+      "loss": 74.297412109375,
+      "step": 610
+    },
+    {
+      "epoch": 0.0124,
+      "grad_norm": 11.501073837280273,
+      "learning_rate": 0.00029687975951903805,
+      "loss": 70.46600952148438,
+      "step": 620
+    },
+    {
+      "epoch": 0.0126,
+      "grad_norm": 6.01923131942749,
+      "learning_rate": 0.0002968196392785571,
+      "loss": 68.65836181640626,
+      "step": 630
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 7.358704090118408,
+      "learning_rate": 0.0002967595190380761,
+      "loss": 69.74998779296875,
+      "step": 640
+    },
+    {
+      "epoch": 0.013,
+      "grad_norm": 9.420614242553711,
+      "learning_rate": 0.0002966993987975952,
+      "loss": 76.11289672851562,
+      "step": 650
+    },
+    {
+      "epoch": 0.0132,
+      "grad_norm": 8.627158164978027,
+      "learning_rate": 0.0002966392785571142,
+      "loss": 77.244384765625,
+      "step": 660
+    },
+    {
+      "epoch": 0.0134,
+      "grad_norm": 8.27780818939209,
+      "learning_rate": 0.00029657915831663323,
+      "loss": 72.63546142578124,
+      "step": 670
+    },
+    {
+      "epoch": 0.0136,
+      "grad_norm": 8.197218894958496,
+      "learning_rate": 0.0002965190380761523,
+      "loss": 75.8551513671875,
+      "step": 680
+    },
+    {
+      "epoch": 0.0138,
+      "grad_norm": 9.352670669555664,
+      "learning_rate": 0.00029645891783567133,
+      "loss": 70.17238159179688,
+      "step": 690
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 10.278020858764648,
+      "learning_rate": 0.0002963987975951904,
+      "loss": 72.43441772460938,
+      "step": 700
     }
   ],
   "logging_steps": 10,
@@ -447,7 +517,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8779456241464320.0,
+  "total_flos": 9442605667530240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null