Training in progress, step 180, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a00591a10d82f6557751ef50942d0ad93eeda3f86a7c867897288c8d46be94
+oid sha256:dcb7712ecbc26e46fa1695be4f15524e8e397fe53946c0a08a6cdcc5983ad689
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218ed3f5c01b608a4eab64004982b2a70a6a0c504c2a4c9cdff60b6a404df174
+oid sha256:a3b3faf55cdd05d5adfa4583fbdd03a8035aa4ea04b098bd35a60e2170d02ba5
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befd409d384ef0f0f1c800aced192285a039968aa574627a06cdbfeed65d40df
+oid sha256:a14ea651aa56969d3e22c9ba563855987e3222470a3a49128fb73a819760aa1e
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb3a39b961047b7cdf3f3152552e802c79a68dc6cf0def914d9209b6b209d37
+oid sha256:f420a398e501a060ab026373fbb64a49ebca6f8ce9e0b9e60155447b04592b02
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 0.9,
   "eval_steps": 20,
-  "global_step": 160,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -304,6 +304,43 @@
       "eval_samples_per_second": 365.156,
       "eval_steps_per_second": 60.981,
       "step": 160
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.2776707112789154,
+      "learning_rate": 3.439823377039599e-07,
+      "loss": 22.04285583496094,
+      "step": 165
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2490997463464737,
+      "learning_rate": 2.570315127454452e-07,
+      "loss": 21.98439178466797,
+      "step": 170
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.2551729679107666,
+      "learning_rate": 1.8198692990167497e-07,
+      "loss": 21.973941040039062,
+      "step": 175
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.32327187061309814,
+      "learning_rate": 1.1936121976767767e-07,
+      "loss": 21.965573120117188,
+      "step": 180
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.006654739379883,
+      "eval_runtime": 2.4962,
+      "eval_samples_per_second": 400.614,
+      "eval_steps_per_second": 66.903,
+      "step": 180
     }
   ],
   "logging_steps": 5,