Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098c304e460183003092ab4cef0911a6d951098fd86f7b9f99a7ca0d0eac3a79
+oid sha256:46952c1c4497aa95e4ad76b794335eb5808f1c058dad43746b9b083bd4559901
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e16f97ff37ac3144fdf8f544f5361f218249bc173b75db531c8e8ed7a3627c
+oid sha256:51b547daa019dd4bffd00a62507eb645719b3acbeb1b7d2c709c17e5d617d30a
 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:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007993605115907274,
+  "epoch": 0.01598721023181455,
   "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": 9e-05,
       "loss": 10.3798,
       "step": 9
+    },
+    {
+      "epoch": 0.009592326139088728,
+      "grad_norm": 0.021697159856557846,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.3783,
+      "step": 12
+    },
+    {
+      "epoch": 0.011990407673860911,
+      "grad_norm": 0.023643912747502327,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.3788,
+      "step": 15
+    },
+    {
+      "epoch": 0.012789768185451638,
+      "eval_loss": 10.377732276916504,
+      "eval_runtime": 3.896,
+      "eval_samples_per_second": 135.266,
+      "eval_steps_per_second": 67.762,
+      "step": 16
+    },
+    {
+      "epoch": 0.014388489208633094,
+      "grad_norm": 0.027424972504377365,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3787,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 372654931968.0,
+  "total_flos": 732234252288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null