Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a2f62efd0d71d0d134266e515dda3b88038f99e0b24c6a836737401f2339a3
+oid sha256:07e1ddb55498e50628c3310f9086dc621dc5fb0c6268ed92605cab47f2644b67
 size 2964338224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9bb165d055492bacaa7fc7f6a4b7aa35f27f884ae2282741026ab19d8357fdb
+oid sha256:d3df4c3f5410aef96aa5d1b1220d16d0e42419e2f967dd28291d6cd8a4e444dc
 size 1485440604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c200f8fdcde78c415e4babf1b6f200bbf13323757b5b248ace34314bfbe3fd44
+oid sha256:927fd63e57181ecc0ac827facbdec2bc46e991f92e1716e5d98f2005a0b865c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6894075403949731,
+  "epoch": 0.9192100538599641,
   "eval_steps": 500,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,34 @@
       "learning_rate": 4.970701059450872e-05,
       "loss": 2.2359,
       "step": 12
+    },
+    {
+      "epoch": 0.7468581687612208,
+      "grad_norm": 1.6817108392715454,
+      "learning_rate": 4.934238559694448e-05,
+      "loss": 2.2229,
+      "step": 13
+    },
+    {
+      "epoch": 0.8043087971274686,
+      "grad_norm": 1.6007517576217651,
+      "learning_rate": 4.8834909801373264e-05,
+      "loss": 2.203,
+      "step": 14
+    },
+    {
+      "epoch": 0.8617594254937163,
+      "grad_norm": 1.457571029663086,
+      "learning_rate": 4.8187561277552374e-05,
+      "loss": 2.0994,
+      "step": 15
+    },
+    {
+      "epoch": 0.9192100538599641,
+      "grad_norm": 1.486559271812439,
+      "learning_rate": 4.740413892402639e-05,
+      "loss": 2.1777,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -110,7 +138,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8132581322686464.0,
+  "total_flos": 1.0873463700504576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null