Training in progress, step 46500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36cf0603c7daac3e8ed590090bcf677f50dccc7cd1d396cc2534c536d8ef5ab1
+oid sha256:34add1e167467d9f589f5c4ec23a18d7e92be6230f07341b5544923f93feab04
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c019e8b6aa64d4ba31d0d7d4b1bb427ab8e78e240572d25da85d969eb311e683
+oid sha256:c1d56ed2fb7b607e26743805c29ee357f094e57ed6ee26216438c18cf1869028
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7f4e1eca9309d1d98afa1140a219e6354390e4eff786b2f5b9b5e736195e76
+oid sha256:c7c8f79644f2475985f4dd054bfb47e766f1a32cf2d648a1047db22199979bcd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee89a7efb22e08ab90c8b6a16d6b67293611a17a0121ecbac30fb8a1fc489b33
+oid sha256:8cbb74bfdb77ddeb784b29549bc2d93ad8bb0b96ccaad9f3fb435b18007153dd
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2784,
+  "epoch": 0.2976,
   "eval_steps": 500,
-  "global_step": 43500,
+  "global_step": 46500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -616,6 +616,48 @@
       "learning_rate": 4.3042560000000004e-05,
       "loss": 0.3505,
       "step": 43500
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 0.7914199829101562,
+      "learning_rate": 4.2962560000000005e-05,
+      "loss": 0.3439,
+      "step": 44000
+    },
+    {
+      "epoch": 0.2848,
+      "grad_norm": 0.7488194704055786,
+      "learning_rate": 4.288256e-05,
+      "loss": 0.349,
+      "step": 44500
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.8654124736785889,
+      "learning_rate": 4.280256e-05,
+      "loss": 0.3491,
+      "step": 45000
+    },
+    {
+      "epoch": 0.2912,
+      "grad_norm": 0.6817401647567749,
+      "learning_rate": 4.272272e-05,
+      "loss": 0.3447,
+      "step": 45500
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 0.6439715623855591,
+      "learning_rate": 4.2642720000000006e-05,
+      "loss": 0.3453,
+      "step": 46000
+    },
+    {
+      "epoch": 0.2976,
+      "grad_norm": 1.3840138912200928,
+      "learning_rate": 4.256272e-05,
+      "loss": 0.3445,
+      "step": 46500
     }
   ],
   "logging_steps": 500,
@@ -635,7 +677,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1191734591488e+17,
+  "total_flos": 2.2653233528832e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null