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:ad1a773616361c749092eb62b0e24d5b863592a5fb8c5271c46c02984fe187a0
+oid sha256:ec8ea4240868ab68021d7c618fd481db422fd28ae24a14fa4a4975ad91922b4c
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7317aa695b1e0f14b65b12e70ca6dcaf534f216c5275165bf6dbacd93500bb1b
+oid sha256:6860bc3f496e1bfe2eb6c361346c64e597e874fa4c92bd35b27e2f1cd30c171c
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870bff235260a948396f89eba7aa8360caaf7dcd6a760faaaac5c6a1a745f7f5
+oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
 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": 0.005684240443370754,
+  "epoch": 0.011368480886741509,
   "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": 10.3758,
       "step": 9
+    },
+    {
+      "epoch": 0.006821088532044906,
+      "grad_norm": 0.04945020750164986,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.3754,
+      "step": 12
+    },
+    {
+      "epoch": 0.008526360665056132,
+      "grad_norm": 0.049591515213251114,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.3742,
+      "step": 15
+    },
+    {
+      "epoch": 0.009094784709393207,
+      "eval_loss": 10.3734769821167,
+      "eval_runtime": 2.4224,
+      "eval_samples_per_second": 305.896,
+      "eval_steps_per_second": 153.154,
+      "step": 16
+    },
+    {
+      "epoch": 0.010231632798067358,
+      "grad_norm": 0.039638299494981766,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3758,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 268050038784.0,
+  "total_flos": 536100077568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null