Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563791682d8f743fe93ee6d69a628dd087d932d2b829d02f21de71c147d69f44
+oid sha256:9f34cdaea4db397ec327640114a7dc8b57e3b3c769a55b85c3349e53b73ae9b6
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4993a5a7e97de8e88e475965f17fb0479e89e242c129e49c55fda454ca509b5f
+oid sha256:949dc39af51e47bfec8a45eea34f5a03ef275bcabd9fd70a2df48b64dc1e3656
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a2086dc733593a9f4737ff44dbb5766249059e6c44ce6127be02fabcb9cbe6
+oid sha256:b56b73ba5f2d662c92296e87599e4454df3aa952447ac02ee3c950d1f55780e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009300162752848175,
+  "epoch": 0.01860032550569635,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 1.671,
       "step": 9
+    },
+    {
+      "epoch": 0.01116019530341781,
+      "grad_norm": 1.5108683109283447,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.5883,
+      "step": 12
+    },
+    {
+      "epoch": 0.013950244129272262,
+      "grad_norm": 1.0921416282653809,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.5418,
+      "step": 15
+    },
+    {
+      "epoch": 0.01488026040455708,
+      "eval_loss": 1.5838655233383179,
+      "eval_runtime": 89.5798,
+      "eval_samples_per_second": 5.057,
+      "eval_steps_per_second": 2.534,
+      "step": 16
+    },
+    {
+      "epoch": 0.016740292955126714,
+      "grad_norm": 1.2232215404510498,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5445,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4118062710128640.0,
+  "total_flos": 8236125420257280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null