Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:682347369938a6b248be485042904639060d57afc95863e315a0254c0fc84d85
+oid sha256:0a107b193279e45b3c47d625dbffc72bdf31bd36a58097516c0af99d322be39d
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c029563114eddb6462262929e4ae0c034f88455adf24d731fba7ec07fd7615db
+oid sha256:c23ba1378d182d69c9d07eae2084ea1184f08f80c66b5c2fc8410d0286692fe7
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ad3b13fe0fb3cf191e6f3eee9378319e3ba008cef668b62e2ba7e986b55ec0
+oid sha256:adc1ecde98f5cd453994b34432b806c3d96cdc21302732cdbc449d980e314ce4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028288543140028287,
+  "epoch": 0.03771805752003772,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 12.979,
       "eval_steps_per_second": 1.628,
       "step": 15
+    },
+    {
+      "epoch": 0.033946251768033946,
+      "grad_norm": 0.29951444268226624,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.2599,
+      "step": 18
+    },
+    {
+      "epoch": 0.03771805752003772,
+      "eval_loss": 1.3078007698059082,
+      "eval_runtime": 68.8442,
+      "eval_samples_per_second": 12.971,
+      "eval_steps_per_second": 1.627,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.168380245147648e+16,
+  "total_flos": 2.914871804952576e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null