Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133c80160271e4ee303a39ebbcac2ba90475e81972268eda8240ef021606ce06
+oid sha256:6e95a88630e617675befbab4e666351d69d856382da4bda087bb3a19eedb9b10
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022053f484369f1c2fe6c5ac9387cfd79d83f6019f7b9da3652fc52af5a8b30a
+oid sha256:6169a4394a09d1aa6e26376804969472c16f7db53679a1fb38b5bf24149df51f
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a14ea651aa56969d3e22c9ba563855987e3222470a3a49128fb73a819760aa1e
+oid sha256:0bef41f725df412ca95cdfe05f60b1b444d77c340f60fb943e0b05b8ff85dc70
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f420a398e501a060ab026373fbb64a49ebca6f8ce9e0b9e60155447b04592b02
+oid sha256:ab66db99117673b461ceb8f3865fe0441f45aa01085a419aba1737c22700a3ed
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9,
+  "epoch": 1.0,
   "eval_steps": 20,
-  "global_step": 180,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -341,6 +341,43 @@
       "eval_samples_per_second": 390.315,
       "eval_steps_per_second": 65.183,
       "step": 180
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.7244570255279541,
+      "learning_rate": 6.958217944530287e-08,
+      "loss": 19.646340942382814,
+      "step": 185
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.8131192922592163,
+      "learning_rate": 3.2989850255235265e-08,
+      "loss": 19.582081604003907,
+      "step": 190
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.8881648182868958,
+      "learning_rate": 9.834194909977168e-09,
+      "loss": 19.577865600585938,
+      "step": 195
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9109742641448975,
+      "learning_rate": 2.7339001506199164e-10,
+      "loss": 19.3023681640625,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.07755555555555556,
+      "eval_loss": 9.678764343261719,
+      "eval_runtime": 2.5817,
+      "eval_samples_per_second": 387.336,
+      "eval_steps_per_second": 64.685,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -355,7 +392,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }