Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be0baf9cda41e263fd80618baa5e2f59a5a168e2ac3b3d3b81d360a4aafb9332
+oid sha256:ab2d003b3861ec7d04e5f7f88e4417142aa1b2dfb0c110bf13d0e909aee2f32d
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b7145b9cc8702a5055b11432bdca180b9b55b81b469911481c77865131f9f9
+oid sha256:899cb87c5442975b61713fd531c4b4c84b7036c65e4545bf70b027e9bec32edd
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1ece0846e2afe71b4b44981fd9a82ee7e8be48b72c44e6ff1c690617d2b724
+oid sha256:2412e58659b4595b55ebc80aad185d444a38f0e07e4587790eeac6b8391a6f6c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05486968449931413,
+  "epoch": 0.07133058984910837,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,48 @@
       "learning_rate": 4e-05,
       "loss": 1.7553,
       "step": 20
+    },
+    {
+      "epoch": 0.05761316872427984,
+      "grad_norm": 0.42597419023513794,
+      "learning_rate": 4.2e-05,
+      "loss": 1.8115,
+      "step": 21
+    },
+    {
+      "epoch": 0.06035665294924554,
+      "grad_norm": 0.37801623344421387,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.7161,
+      "step": 22
+    },
+    {
+      "epoch": 0.06310013717421124,
+      "grad_norm": 0.35600143671035767,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.7315,
+      "step": 23
+    },
+    {
+      "epoch": 0.06584362139917696,
+      "grad_norm": 0.4111214280128479,
+      "learning_rate": 4.8e-05,
+      "loss": 1.7091,
+      "step": 24
+    },
+    {
+      "epoch": 0.06858710562414266,
+      "grad_norm": 0.4117395579814911,
+      "learning_rate": 5e-05,
+      "loss": 1.7026,
+      "step": 25
+    },
+    {
+      "epoch": 0.07133058984910837,
+      "grad_norm": 0.4069993197917938,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.6733,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -166,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.508763359401165e+16,
+  "total_flos": 3.230939998237901e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null