Training in progress, step 253, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d670e3d79bfffb5e042b5a3ce721b3dac237b5e9f862d93b021230929bd440
+oid sha256:267e55ad7755dee82f46dba719e2576737b5ea75c1b5332dddec46d9480748b8
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c4b9a1038c3864c6aebfb5f80fb47be5cb30b63f2ac18316cd50f58f7c5813
+oid sha256:af61f8af3746a56d2a96b75db1276aa71c671ea7b6ce344d3463d7e1c88aad06
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7657b3ddb2232aa8012a32fb00c3fb92277ec0be13fceb0c90bdaa595cabccac
+oid sha256:8e2b56357fd5416f4374499b12d61ad0d3c5063c6569083ab07fd9fe96b503d0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6886145404663924,
+  "epoch": 0.6941015089163237,
   "eval_steps": 500,
-  "global_step": 251,
+  "global_step": 253,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1764,6 +1764,20 @@
       "learning_rate": 8.560606060606061e-05,
       "loss": 1.1737,
       "step": 251
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 0.18938620388507843,
+      "learning_rate": 8.484848484848486e-05,
+      "loss": 1.148,
+      "step": 252
+    },
+    {
+      "epoch": 0.6941015089163237,
+      "grad_norm": 0.14747262001037598,
+      "learning_rate": 8.40909090909091e-05,
+      "loss": 1.1205,
+      "step": 253
     }
   ],
   "logging_steps": 1,
@@ -1783,7 +1797,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1050607333850726e+17,
+  "total_flos": 3.127961028837335e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null