Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3816f49bd52d199166073f1e810a2d01dfe18365cc7ba6ee4efaaae798c4a82f
+oid sha256:3ab03aeb09d3336fe5a7caa6e00c5224a6b4b2a6b314d06beb1f5c7c0a93a2da
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aefad1889c4fbc31909cfd241741bb8263dbbb769bad6b17fffa5651ffbb95d3
+oid sha256:905e6f57a6f7cf66f09d18fd6f41c7601b54a6c2f6b10dcbaf64bd00c1a5674b
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b67ea89a31547b36f6bfc109d5f131bed98ffc306f8d9845e2f10c3458408c0
+oid sha256:d50f61a9d24412ccb5614996adc0c93b90c6c68062631ebea450b2af34b256f3
 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": 0.014803849000740192,
+  "epoch": 0.029607698001480384,
   "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": 10.3732,
       "step": 9
+    },
+    {
+      "epoch": 0.01776461880088823,
+      "grad_norm": 0.03467576950788498,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.3733,
+      "step": 12
+    },
+    {
+      "epoch": 0.02220577350111029,
+      "grad_norm": 0.04072782024741173,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.3737,
+      "step": 15
+    },
+    {
+      "epoch": 0.023686158401184307,
+      "eval_loss": 10.372544288635254,
+      "eval_runtime": 2.6949,
+      "eval_samples_per_second": 105.757,
+      "eval_steps_per_second": 53.064,
+      "step": 16
+    },
+    {
+      "epoch": 0.026646928201332347,
+      "grad_norm": 0.03554646670818329,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3728,
+      "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