Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c6a8c655007d84ac76394a247f427e66fe08cd90d8ffdd75feeac3fbbea920
+oid sha256:d9f710d7b155dd0bdd33bb4093b02fa6963a0315061109995bce175a9a55a979
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7f998ff8f8aff7406f9490528e40274b133f166b436fbbfcd1cae57cc5aa12
+oid sha256:c75c92e333d1de9554669c6ae6e46435d1d25a46ad4e19214a74a0a0a8a53ee0
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:277b0429d16d58780d4725b042a414911208f1d2c65970c7ba826c69701d9ba5
+oid sha256:8122a4d1b9798cf1f1461f171747fe649310ff601bff86f819cc87bc3f680ac9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07956104252400549,
+  "epoch": 0.09053497942386832,
   "eval_steps": 500,
-  "global_step": 29,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -210,6 +210,34 @@
       "learning_rate": 5.8e-05,
       "loss": 1.7039,
       "step": 29
+    },
+    {
+      "epoch": 0.0823045267489712,
+      "grad_norm": 0.5381506085395813,
+      "learning_rate": 6e-05,
+      "loss": 1.5768,
+      "step": 30
+    },
+    {
+      "epoch": 0.0850480109739369,
+      "grad_norm": 0.4311385750770569,
+      "learning_rate": 6.2e-05,
+      "loss": 1.5598,
+      "step": 31
+    },
+    {
+      "epoch": 0.0877914951989026,
+      "grad_norm": 0.38209667801856995,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.511,
+      "step": 32
+    },
+    {
+      "epoch": 0.09053497942386832,
+      "grad_norm": 0.35374918580055237,
+      "learning_rate": 6.6e-05,
+      "loss": 1.4692,
+      "step": 33
     }
   ],
   "logging_steps": 1,
@@ -229,7 +257,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.611550557083238e+16,
+  "total_flos": 4.091028305037312e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null