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:b07c4d4c298d67a03418122862fdcc86b54210e9a055d3ff0e2f424107515339
+oid sha256:e828ec98552a9166b72035a401249abea023a537da7904e720609021c2c91bea
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf9f021ca867a726e9eb269fca993e70b83c75bb499e438dd8eb7d6a826169b
+oid sha256:0ab6448068b45bdeec015c36f59cd5051d7fccbf3d5f7ccfc72e09f622f448d2
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aaa6d8a69d8299a907823adc599422c15491312a4bfb634b6631045d063f404
+oid sha256:c0703adaab0d533041f4917d10f6d3f0def78a785902d98446d8621844b85ea1
 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": 0.12072434607645875,
+  "epoch": 0.16096579476861167,
   "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": 6.336,
       "eval_steps_per_second": 0.819,
       "step": 15
+    },
+    {
+      "epoch": 0.1448692152917505,
+      "grad_norm": 0.11892444640398026,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0165,
+      "step": 18
+    },
+    {
+      "epoch": 0.16096579476861167,
+      "eval_loss": 0.013070314191281796,
+      "eval_runtime": 32.9925,
+      "eval_samples_per_second": 6.335,
+      "eval_steps_per_second": 0.818,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.525540736237568e+16,
+  "total_flos": 5.958628636046131e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null