Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c75afc4454c317820c28f0b8767fc1d0e296f811be2d358074f0962c3a92a0dc
+oid sha256:a3ab11b8c73ee400173269240a9ee526a173fe24b4846ec6276209d48e3921c8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c48d5d0b029ff84e7c576db4a79a77df4a67a90ad8d2c052ee78e81af7d4ab4
+oid sha256:14f55a19caca743c769bc49611fea58f1c0c84160ec7d085287e4f98fbeacc39
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51bb05fc29594cc193be5173cacc60d64b2a0f1c5177c1b27e9bea76ed3f55a4
+oid sha256:b5007a051c4c84b8c41ca3a808e63a3b0686551683b6849b8ef5d494e7531a3a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005594405594405594,
+  "epoch": 0.011188811188811189,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 10.044,
       "eval_steps_per_second": 1.256,
       "step": 9
+    },
+    {
+      "epoch": 0.007459207459207459,
+      "grad_norm": 2.609468698501587,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 4.8802,
+      "step": 12
+    },
+    {
+      "epoch": 0.009324009324009324,
+      "grad_norm": 2.8223719596862793,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 4.5065,
+      "step": 15
+    },
+    {
+      "epoch": 0.011188811188811189,
+      "grad_norm": 2.5072696208953857,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 3.8598,
+      "step": 18
+    },
+    {
+      "epoch": 0.011188811188811189,
+      "eval_loss": 3.936025381088257,
+      "eval_runtime": 269.871,
+      "eval_samples_per_second": 10.042,
+      "eval_steps_per_second": 1.256,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.928906937257165e+16,
+  "total_flos": 3.783625146158285e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null