Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1055aee84441a1c8fd6c9274ed61b986ba524e5ccaa969ec2bfa35db030fb041
+oid sha256:9f85f6fab64d5699cc202131a72f26c8ce5de0c0d9a99b7ab5850d2dcc6157cb
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30aaa0326da154e08592e0ba390386b4f7c35df1eaaa8aca3e4ec678f0194888
+oid sha256:09dcdc31df69f9b5ef85357de1624681e8592d949b7e83fdda317e74436ccbe3
 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": 0.0004064049418840933,
+  "epoch": 0.0008128098837681866,
   "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": 11.7622,
       "step": 9
+    },
+    {
+      "epoch": 0.000487685930260912,
+      "grad_norm": 0.046722933650016785,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.7637,
+      "step": 12
+    },
+    {
+      "epoch": 0.00060960741282614,
+      "grad_norm": 0.04540090635418892,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.7614,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006502479070145493,
+      "eval_loss": 11.760395050048828,
+      "eval_runtime": 49.1458,
+      "eval_samples_per_second": 210.822,
+      "eval_steps_per_second": 105.421,
+      "step": 16
+    },
+    {
+      "epoch": 0.000731528895391368,
+      "grad_norm": 0.0367448627948761,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.7622,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1018500218880.0,
+  "total_flos": 2037000437760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null