Training in progress, step 11, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146d162f21d6885a599ae47823186efd669faffd51555aea28ea2980c3ba276d
+oid sha256:629db8cf23e899c4a1d0ad2f03caf7a3c1f7569a0139b10beb95ee76d2d6685c
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28337b7c2b425365ede002b7367ded19801e6211d9e7a1fe9480d2ff0a4306db
+oid sha256:e5461333e6d10ede58b763d6eb558df9db689d78e862e3c2faf55f5879cb5868
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea1738558a9366d944e7310c6a878fb018ff37640bc9d856eea647247684a83
+oid sha256:067de29fd76e5b21e65ed03c922d7a9b0927f4b7b4ac92e2cac2ad1d9bdb3591
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02194787379972565,
+  "epoch": 0.03017832647462277,
   "eval_steps": 500,
-  "global_step": 8,
+  "global_step": 11,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,27 @@
       "learning_rate": 1.6000000000000003e-05,
       "loss": 1.984,
       "step": 8
+    },
+    {
+      "epoch": 0.024691358024691357,
+      "grad_norm": 1.2035481929779053,
+      "learning_rate": 1.8e-05,
+      "loss": 1.928,
+      "step": 9
+    },
+    {
+      "epoch": 0.027434842249657063,
+      "grad_norm": 1.0602883100509644,
+      "learning_rate": 2e-05,
+      "loss": 1.9322,
+      "step": 10
+    },
+    {
+      "epoch": 0.03017832647462277,
+      "grad_norm": 0.9456723928451538,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.9257,
+      "step": 11
     }
   ],
   "logging_steps": 1,
@@ -82,7 +103,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9823019497033728.0,
+  "total_flos": 1.367494067331072e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null