Training in progress, step 222, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86b6df3e2bd04be35a5d8200190ba034db516cef958ead8265e932ca906205b
+oid sha256:e649179d25abb8b493fc0fa18c2b521b47943b801294a991c276b7922365e6d5
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6803ce1d00c1e14e0ff8a69baa2dbfd9d9584e5f294187fee81afb8f3d39476
+oid sha256:da6bd97d4eed46e88e6e0d223dbf0c299fe484eb3d1b03477720413855e98ec2
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1054bd185923ae37e2cfd534bc8fc8be8ffcde679164453af8b8b105ec92295a
+oid sha256:2474da71ed85520e26ac27838c56d44531f642c902e456e7613e2cf2dd3c2f55
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5953360768175583,
+  "epoch": 0.6090534979423868,
   "eval_steps": 500,
-  "global_step": 217,
+  "global_step": 222,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1526,6 +1526,41 @@
       "learning_rate": 0.00011136363636363636,
       "loss": 1.2697,
       "step": 217
+    },
+    {
+      "epoch": 0.598079561042524,
+      "grad_norm": 0.21464407444000244,
+      "learning_rate": 0.00011060606060606061,
+      "loss": 1.2269,
+      "step": 218
+    },
+    {
+      "epoch": 0.6008230452674898,
+      "grad_norm": 0.1585656851530075,
+      "learning_rate": 0.00010984848484848484,
+      "loss": 1.116,
+      "step": 219
+    },
+    {
+      "epoch": 0.6035665294924554,
+      "grad_norm": 0.28340986371040344,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 1.2534,
+      "step": 220
+    },
+    {
+      "epoch": 0.6063100137174211,
+      "grad_norm": 0.2463023066520691,
+      "learning_rate": 0.00010833333333333333,
+      "loss": 1.2119,
+      "step": 221
+    },
+    {
+      "epoch": 0.6090534979423868,
+      "grad_norm": 0.1642024666070938,
+      "learning_rate": 0.00010757575757575758,
+      "loss": 1.1755,
+      "step": 222
     }
   ],
   "logging_steps": 1,
@@ -1545,7 +1580,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.687823948889252e+17,
+  "total_flos": 2.7504424597856256e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null