Training in progress, step 11000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54954af78d21501178aa62df97e4be776d44dff55739ccefcf53cd7aa892ad26
+oid sha256:e3a0e2b33440e51ec5afaa9bceea1c288d9657bf3b8d6477901b57ab4f99641a
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c0891fae01c1d6432579b2b936d4b0012c9b7ac7ea43bb5023b807960238aa
+oid sha256:da957680fc308ae8f23a6a07af9ba45df45de1cfad126fe2f8836f917c2f2881
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b862f636711227d7ee569cee2e33728ccc9fbbf65bc11cd093eb1d516eb0a06e
+oid sha256:33d2eb1e169756c46d6c6d7c2575b85482625ca646133d87a3e817fb42a9ce0c
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d45e2a529ec73c259dc8a505fb5d678af9533763a932c892160c698a82dd89e
+oid sha256:14aec4c753424fead7a2d96d42e6a407ee1f923d3dd1f5ba9f206ce6413ba33c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.796594282143417,
+  "epoch": 21.996563037025464,
   "eval_steps": 500,
-  "global_step": 10900,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -938,6 +938,21 @@
       "learning_rate": 2.733333333333333e-05,
       "loss": 1.2294,
       "step": 10900
+    },
+    {
+      "epoch": 21.996563037025464,
+      "grad_norm": 0.245674729347229,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.2217,
+      "step": 11000
+    },
+    {
+      "epoch": 21.996563037025464,
+      "eval_loss": 1.092257022857666,
+      "eval_runtime": 780.2283,
+      "eval_samples_per_second": 19.894,
+      "eval_steps_per_second": 2.488,
+      "step": 11000
     }
   ],
   "logging_steps": 100,
@@ -957,7 +972,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.701197956523439e+19,
+  "total_flos": 1.7168054536422556e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null