Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68430ed90582ec36ba6c0f053827de6305df7b0426b8c522ee8f1f603f0a87d6
+oid sha256:a74deab4d5ba77c9a4f7e81a067b1f2a8d7194079d99dac030fe35e4b6a40176
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0871ab613a3719279157cedf4662a8676a4c76739dabf3cde23efb35114018aa
+oid sha256:3ab8082debf1af3df9983d50166b3db7c9650aa6ee53e9bef56f61c588805d2d
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d1ea809ba32b7efd678ae04203f4d557f85f71b36f396a16e0baf7241d69c8
+oid sha256:f9deec2bbc6049590c0611b7f75fd56a9cf2bc765b789590cd118585901f6530
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889f6fc92910dc1617d7e2b8e49ec9358ef58d2162623ab1d55db477fded32fc
+oid sha256:1c2eb03e04e9ec3d534ee7aa67476af96452e64bad29591c419a0c652481ee2b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.3,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,43 @@
       "eval_samples_per_second": 185.881,
       "eval_steps_per_second": 31.042,
       "step": 40
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.21822796761989594,
+      "learning_rate": 3.6921905048418706e-06,
+      "loss": 21.950730895996095,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.22425295412540436,
+      "learning_rate": 3.598375993789849e-06,
+      "loss": 21.952291870117186,
+      "step": 50
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.2449563443660736,
+      "learning_rate": 3.4936429539683075e-06,
+      "loss": 21.959083557128906,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.21149370074272156,
+      "learning_rate": 3.3787068182371314e-06,
+      "loss": 21.980178833007812,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 7.827788649706458e-06,
+      "eval_loss": 10.983661651611328,
+      "eval_runtime": 5.397,
+      "eval_samples_per_second": 185.287,
+      "eval_steps_per_second": 30.943,
+      "step": 60
     }
   ],
   "logging_steps": 5,