Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238b5d7e130ce1c26b0a2f151e294bd75a478cf35a8d78789ba0e3eb306a8dcd
+oid sha256:142a2a63f3c13f07e686b28fa844ce8e9dca826ff65edabb78c3bc27e9d08a3e
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe1b4e63c0bf83d4930ead6dee0f28bf8b6043d0b7b3df5c3703bbd31f660ea
+oid sha256:96a35d8cd2124fb1679ce12ad2dea71ace997a17209d004c867412f4fa7e73f3
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f4699b11df86350ce746228bc86b78aa2b77e7bf6d49eda68bc3ebb21718be
+oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
 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": 0.0003141739581206114,
+  "epoch": 0.0006283479162412228,
   "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": 11.9321,
       "step": 9
+    },
+    {
+      "epoch": 0.00037700874974473366,
+      "grad_norm": 0.18955875933170319,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.926,
+      "step": 12
+    },
+    {
+      "epoch": 0.00047126093718091706,
+      "grad_norm": 0.18303273618221283,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.9305,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005026783329929782,
+      "eval_loss": 11.925522804260254,
+      "eval_runtime": 293.3563,
+      "eval_samples_per_second": 45.685,
+      "eval_steps_per_second": 22.843,
+      "step": 16
+    },
+    {
+      "epoch": 0.0005655131246171005,
+      "grad_norm": 0.23181599378585815,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9254,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2539027169280.0,
+  "total_flos": 5078054338560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null