Training in progress, step 120, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5b9baf6de14780fa86a9b96945cdf7b72a2583aad39bcb5b7af228742f8ade
+oid sha256:d47f50d75e32624acd21703332c797184b665fb4d2b10847a7d7de1432abb3a1
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e9dc05c94cca6b374b4e8da945f6ab78f100d5bbd3f9b87005250dd7e07039
+oid sha256:f1345b0a7769c8848417baabda9535c454ba0aef0691913ff0f8c0d83f03bfc3
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d655e73147f6c05694f6b0b5c2c321535c695e45d8c7329d033e75bc36a25404
+oid sha256:443907af357cccf92496cdd4e04b21f17558d4acf38fddc732c70cd7db47e70d
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
+oid sha256:cc32de04bd8951ded22e38a3a317dcc3e3d6e420820aadb0c1fc7777161631b4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.6,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -193,6 +193,43 @@
       "eval_samples_per_second": 383.201,
       "eval_steps_per_second": 63.995,
       "step": 100
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.24510444700717926,
+      "learning_rate": 2.033067889532717e-06,
+      "loss": 21.980421447753905,
+      "step": 105
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.24764317274093628,
+      "learning_rate": 1.8678188313486012e-06,
+      "loss": 21.973478698730467,
+      "step": 110
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.28122493624687195,
+      "learning_rate": 1.7034727045763157e-06,
+      "loss": 21.949703979492188,
+      "step": 115
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.250843346118927,
+      "learning_rate": 1.541152159906497e-06,
+      "loss": 21.94451141357422,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.010734558105469,
+      "eval_runtime": 2.7011,
+      "eval_samples_per_second": 370.215,
+      "eval_steps_per_second": 61.826,
+      "step": 120
     }
   ],
   "logging_steps": 5,