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:fabda56934d3d2bc2b3b07326b25c55bef6d8fcc0c1c820e58572fed5e9d869c
+oid sha256:5746549a1e92d4dc4f92122782383cc00a7ac92e8089ff9ef6497b69b930974c
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8851674d86db17546a34cc04a44c8b7edf122fc176368c9ce8aa6929699ab104
+oid sha256:ba0ed148826db60c0c69a18bb6b2268d8fbb3f7a445faa5a83ef4e303e73f9f4
 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": 0.04395604395604396,
+  "epoch": 0.08791208791208792,
   "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": 10.363,
       "step": 9
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 0.05579746142029762,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.3738,
+      "step": 12
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.04492007568478584,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.3696,
+      "step": 15
+    },
+    {
+      "epoch": 0.07032967032967033,
+      "eval_loss": 10.365509986877441,
+      "eval_runtime": 0.4005,
+      "eval_samples_per_second": 239.726,
+      "eval_steps_per_second": 119.863,
+      "step": 16
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.061128389090299606,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3732,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 261512232960.0,
+  "total_flos": 523024465920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null