Training in progress, step 180, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a758220ef8bbff8c6d1485db235840ad8309e777eecc16a2a36538d98a5d0984
+oid sha256:133c80160271e4ee303a39ebbcac2ba90475e81972268eda8240ef021606ce06
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a604243df1dc8a4ee575d18a1d0d45254a9a949ce6f6f087a9c9a807f2dd45ff
+oid sha256:022053f484369f1c2fe6c5ac9387cfd79d83f6019f7b9da3652fc52af5a8b30a
 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": 388.323,
       "eval_steps_per_second": 64.85,
       "step": 160
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.784702479839325,
+      "learning_rate": 3.439823377039599e-07,
+      "loss": 19.52422180175781,
+      "step": 165
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.6510916948318481,
+      "learning_rate": 2.570315127454452e-07,
+      "loss": 19.38793029785156,
+      "step": 170
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.7473388910293579,
+      "learning_rate": 1.8198692990167497e-07,
+      "loss": 19.620166015625,
+      "step": 175
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9092379212379456,
+      "learning_rate": 1.1936121976767767e-07,
+      "loss": 19.587705993652342,
+      "step": 180
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.07433333333333333,
+      "eval_loss": 9.763090133666992,
+      "eval_runtime": 2.562,
+      "eval_samples_per_second": 390.315,
+      "eval_steps_per_second": 65.183,
+      "step": 180
     }
   ],
   "logging_steps": 5,