updating checkpoint

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4efbc81738ec44d43994a1a3f640fb7daea9a9268fe76dcd7da67d5b59605d
+oid sha256:dbbc7d0f1174219b77e846a3c2767109cc8f0639110c67a37339732d73f40756
 size 1115513717

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8818c6d636ff2cf5bd1a4936a2230a09dfa55f4d9ce2516fb1761e6f0876cf6f
+oid sha256:e558e6a30229b2432e7a7ee37a0976551f92117d61f9d0f02ef3619a789c092d
 size 557969145

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2dea4db0d2c926af8e1008bb554c75f5983a75707920c5b130ea897f93a0f4
-size 17499
+oid sha256:09fbbdc16e4d6b0d4e17fb8f40aa87eaefda890b1fa4959f0e75ee7a604c14a2
+size 17563

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686904ef871802c06d2c9e60092097c43dcf861babbc0c238724c4d02607fc94
+oid sha256:dc8bd72a8131c0be5e00b479acad1450e08dcde0c0e0e169420fa6c4fc9b63d7
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8875083203905036,
-  "global_step": 4000,
+  "epoch": 2.884402041269137,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -54,11 +54,119 @@
       "learning_rate": 4.112491679609496e-05,
       "loss": 0.2778,
       "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.0015531395606834e-05,
+      "loss": 0.2674,
+      "step": 4500
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.89061459951187e-05,
+      "loss": 0.2421,
+      "step": 5000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.7796760594630574e-05,
+      "loss": 0.2353,
+      "step": 5500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.668737519414245e-05,
+      "loss": 0.2299,
+      "step": 6000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.5577989793654314e-05,
+      "loss": 0.2231,
+      "step": 6500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 3.446860439316619e-05,
+      "loss": 0.2186,
+      "step": 7000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.335921899267806e-05,
+      "loss": 0.2128,
+      "step": 7500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.224983359218993e-05,
+      "loss": 0.2068,
+      "step": 8000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.11404481917018e-05,
+      "loss": 0.203,
+      "step": 8500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.003106279121367e-05,
+      "loss": 0.2002,
+      "step": 9000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.8921677390725536e-05,
+      "loss": 0.1852,
+      "step": 9500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.781229199023741e-05,
+      "loss": 0.182,
+      "step": 10000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.6702906589749283e-05,
+      "loss": 0.1842,
+      "step": 10500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.559352118926115e-05,
+      "loss": 0.1801,
+      "step": 11000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 2.4484135788773022e-05,
+      "loss": 0.1764,
+      "step": 11500
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.3374750388284892e-05,
+      "loss": 0.1772,
+      "step": 12000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.2265364987796762e-05,
+      "loss": 0.1731,
+      "step": 12500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2.1155979587308632e-05,
+      "loss": 0.1711,
+      "step": 13000
     }
   ],
   "max_steps": 22535,
   "num_train_epochs": 5,
-  "total_flos": 9755783331840000.0,
+  "total_flos": 3.170301849501696e+16,
   "trial_name": null,
   "trial_params": null
 }