Training in progress, step 220, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a2d8d92b7aec96d9b14e81e189bc382a21f701046b64d2d6c1d3ef716d9aa7
+oid sha256:38525614635b5a1802bada9dfb35967342f89a8f39cef59178364b0e09a3606b
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b441fb5dbf3019df142c9903ff4c022684a426738037ca9497630d406c1fa24e
+oid sha256:73c8b2403ce009418422c824501cf772c8ea12de61f38702a0e9951a24f18af6
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa42d9ab242502b58d07b8b399771dd60f43b4e7a5af9c3ff254d71b99c0a81
+oid sha256:bfb84979c669ccc8d28e35aa58c2587b05a8b6df327dd2931fe3015d79e3a7fb
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae2157ab127357b0e63187d087d7f205cbb57eef57e30a483bf9215a428c1446
+oid sha256:fdb198a10323219718c28f69eda76ef66dcd9b432d9acb59767df7cf35ba400d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
+oid sha256:134925db3ae71cb88cb92756cc2cdea3066935b4ecbf838e78bbfa60c95c3818
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.384615384615385,
+  "epoch": 16.923076923076923,
   "eval_steps": 40,
-  "global_step": 200,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,20 @@
       "eval_samples_per_second": 284.328,
       "eval_steps_per_second": 4.546,
       "step": 200
+    },
+    {
+      "epoch": 16.153846153846153,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 9.4734,
+      "step": 210
+    },
+    {
+      "epoch": 16.923076923076923,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.4381,
+      "step": 220
     }
   ],
   "logging_steps": 10,
@@ -214,7 +228,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 81831709900800.0,
+  "total_flos": 90014880890880.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null