Training in progress, step 59, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ff1f1fc595ad8133f8b71ea00894b44d45ba33fe7f73a1870f3098a549c854
+oid sha256:e986d849d397f1dfe71a0947a97c8f30985df37fcc73fade493d2d8d46b1cacb
 size 100198584

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f874e97b84685154a02975aaf603049cb990103be4e0b0c51158a10fe11b6e
+oid sha256:9beab69120b8470ba5993d628bb2552a1d7a60b206e9b9165ea3374b579b5c86
 size 50675156

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1353723be4c6fe076940e8befb2fc2a9d06d490d30020d9bfe5043cd2525797
+oid sha256:8da99b8ae5f5d39bfda5424154d9614466b3a6382198e7aa65c1c031599a0314
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06720847411195324,
+  "epoch": 0.08620217331750525,
   "eval_steps": 500,
-  "global_step": 46,
+  "global_step": 59,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,6 +329,97 @@
       "learning_rate": 9.200000000000002e-06,
       "loss": 1.9289,
       "step": 46
+    },
+    {
+      "epoch": 0.06866952789699571,
+      "grad_norm": 0.24804741144180298,
+      "learning_rate": 9.4e-06,
+      "loss": 1.9128,
+      "step": 47
+    },
+    {
+      "epoch": 0.07013058168203817,
+      "grad_norm": 0.2629912197589874,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.8998,
+      "step": 48
+    },
+    {
+      "epoch": 0.07159163546708064,
+      "grad_norm": 0.22671160101890564,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.8634,
+      "step": 49
+    },
+    {
+      "epoch": 0.07305268925212309,
+      "grad_norm": 0.22378858923912048,
+      "learning_rate": 1e-05,
+      "loss": 1.9038,
+      "step": 50
+    },
+    {
+      "epoch": 0.07451374303716556,
+      "grad_norm": 0.25769534707069397,
+      "learning_rate": 1.02e-05,
+      "loss": 1.8324,
+      "step": 51
+    },
+    {
+      "epoch": 0.07597479682220802,
+      "grad_norm": 0.22694693505764008,
+      "learning_rate": 1.04e-05,
+      "loss": 1.8374,
+      "step": 52
+    },
+    {
+      "epoch": 0.07743585060725047,
+      "grad_norm": 0.23865583539009094,
+      "learning_rate": 1.0600000000000002e-05,
+      "loss": 1.9129,
+      "step": 53
+    },
+    {
+      "epoch": 0.07889690439229294,
+      "grad_norm": 0.23314256966114044,
+      "learning_rate": 1.0800000000000002e-05,
+      "loss": 1.8512,
+      "step": 54
+    },
+    {
+      "epoch": 0.0803579581773354,
+      "grad_norm": 0.2111833393573761,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.8608,
+      "step": 55
+    },
+    {
+      "epoch": 0.08181901196237787,
+      "grad_norm": 0.24742205440998077,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 1.9129,
+      "step": 56
+    },
+    {
+      "epoch": 0.08328006574742032,
+      "grad_norm": 0.2268109768629074,
+      "learning_rate": 1.14e-05,
+      "loss": 1.7996,
+      "step": 57
+    },
+    {
+      "epoch": 0.08474111953246279,
+      "grad_norm": 0.24065515398979187,
+      "learning_rate": 1.16e-05,
+      "loss": 1.9203,
+      "step": 58
+    },
+    {
+      "epoch": 0.08620217331750525,
+      "grad_norm": 0.23937389254570007,
+      "learning_rate": 1.18e-05,
+      "loss": 1.8845,
+      "step": 59
     }
   ],
   "logging_steps": 1,
@@ -348,7 +439,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.114263583383142e+16,
+  "total_flos": 6.568072173368525e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null