Training in progress, step 83, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c76ec859b365599be866d9b318eaa5a3c0499ba81d80d398aa979cdfba1c6c
+oid sha256:c997ba06eb3c43b4beeaddc7da4021790886b44b0d7da5f2d90a4488a82d9d66
 size 100198584

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e9b8c9e59c83006ff910343ed6eca79ef202fa67271f9cc6d22fd7e1e81e005
+oid sha256:90e5a5fa2804c3f250c6b3046be48e9a28dc91a2bd321a4a53cebc3472ff01ca
 size 50675156

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3ec25a8057e7278bf9e7cd6eb504c67f0a3c505cd58623e3273b98ac77f202
+oid sha256:b6c2c803e63719a38ab78de645a182ebd31fb27bd73de5f12bc1f2831c268ff7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2194787379972565,
+  "epoch": 0.22770919067215364,
   "eval_steps": 500,
-  "global_step": 80,
+  "global_step": 83,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,6 +567,27 @@
       "learning_rate": 0.00016,
       "loss": 1.1684,
       "step": 80
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.06477335095405579,
+      "learning_rate": 0.000162,
+      "loss": 1.1851,
+      "step": 81
+    },
+    {
+      "epoch": 0.22496570644718794,
+      "grad_norm": 0.0677405372262001,
+      "learning_rate": 0.000164,
+      "loss": 1.093,
+      "step": 82
+    },
+    {
+      "epoch": 0.22770919067215364,
+      "grad_norm": 0.06988447159528732,
+      "learning_rate": 0.000166,
+      "loss": 1.2542,
+      "step": 83
     }
   ],
   "logging_steps": 1,
@@ -586,7 +607,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.29379718260736e+17,
+  "total_flos": 2.3801435722727424e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null