Training in progress, step 37500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd691e92552d902e006c1dbd51666fbe879b2be04760327e9ca887670be688f
+oid sha256:eccce9825a6e6348256698faab746bf337537d7559919bf091704418e3ecaaa5
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f14ad18c691195cd15268660ba702ce3fc7337f8480e501b361bd9677af8b07e
+oid sha256:5767ff2839f2befc3509511517661e7ee746fd7345f573d42e39ce30e6d908e8
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:810ed5e7c2ae1b96c2bbc38902777e6779874b7cdcf097af17b2123a3bf9831a
+oid sha256:8ffd6cc317d4a23512c42e23cd9356ee5c984750b736bc7a53cf0419eccfd496
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f866da3a9c3c847bb3514492ca12f1bdef65b499f47966b6692e65b75559e3e5
+oid sha256:26829b102f440c540dc7e3f1f0e0d969a25f498ec8a83042cddb35cab37b0ab3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.466666666666667,
+  "epoch": 2.5,
   "eval_steps": 500,
-  "global_step": 37000,
+  "global_step": 37500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2613,6 +2613,41 @@
       "learning_rate": 3.561777777777778e-06,
       "loss": 0.0522,
       "step": 37000
+    },
+    {
+      "epoch": 2.473333333333333,
+      "grad_norm": 0.2838660180568695,
+      "learning_rate": 3.5173333333333336e-06,
+      "loss": 0.0485,
+      "step": 37100
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.26960739493370056,
+      "learning_rate": 3.472888888888889e-06,
+      "loss": 0.0516,
+      "step": 37200
+    },
+    {
+      "epoch": 2.486666666666667,
+      "grad_norm": 0.19472958147525787,
+      "learning_rate": 3.428444444444445e-06,
+      "loss": 0.0551,
+      "step": 37300
+    },
+    {
+      "epoch": 2.493333333333333,
+      "grad_norm": 0.22085241973400116,
+      "learning_rate": 3.384e-06,
+      "loss": 0.0555,
+      "step": 37400
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.32543325424194336,
+      "learning_rate": 3.3395555555555558e-06,
+      "loss": 0.0517,
+      "step": 37500
     }
   ],
   "logging_steps": 100,
@@ -2632,7 +2667,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.012576780288e+16,
+  "total_flos": 9.1343683584e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null