Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5125b9652a194d124705ef0e0bfe0dec5d09258a760f1f2183c2a53cf6e17bae
+oid sha256:ba6e3e7b0b3db904a75b7b7f672093292e9b94f8d52f666348a4eaaa7e25a445
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a52ec998177e44ef559c31552acbc7295e0d1058a27732c80aef8565839d56
+oid sha256:f89ce4a9ac9690a0a349478c68d909ac5e179a031966799d0ce5c9db447e6f9c
 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": 0.00299311583358276,
+  "epoch": 0.00598623166716552,
   "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": 10.3775,
       "step": 9
+    },
+    {
+      "epoch": 0.0035917390002993114,
+      "grad_norm": 0.03667126223444939,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.3771,
+      "step": 12
+    },
+    {
+      "epoch": 0.004489673750374139,
+      "grad_norm": 0.04212287440896034,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.3768,
+      "step": 15
+    },
+    {
+      "epoch": 0.004788985333732416,
+      "eval_loss": 10.37470531463623,
+      "eval_runtime": 12.8704,
+      "eval_samples_per_second": 109.32,
+      "eval_steps_per_second": 54.699,
+      "step": 16
+    },
+    {
+      "epoch": 0.005387608500448967,
+      "grad_norm": 0.041185591369867325,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3743,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 523024465920.0,
+  "total_flos": 1046048931840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null