Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb16afbe7524348a06544914004158b2534f89c032277f333643abd0a417a5b8
+oid sha256:d30d26407626d20c85e45e0d07e586b8d7bd417756db4f6f64ac6dd47b687963
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1083e36bba4cf01be960f46a4a1ba15d45aa1eae0ec11b7beb912fd0608e31d6
+oid sha256:407c65b743768aa1f1c133e87c9da8e69c27559f32277ff756bad0868db09767
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b090e1f86b76a06cb60aa45f28e8025e59770199151361dd1dc8b664660ce4b
+oid sha256:cd29364c179bbae80a4e5f5a5c20d5c32ab12b18ea0b2becd6f8e4dd05b25d8d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014309301045679693,
+  "epoch": 0.028618602091359385,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 31.296,
       "eval_steps_per_second": 15.689,
       "step": 10
+    },
+    {
+      "epoch": 0.01651073197578426,
+      "grad_norm": 0.19784417748451233,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.1716,
+      "step": 15
+    },
+    {
+      "epoch": 0.02201430930104568,
+      "grad_norm": 0.503454327583313,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0933,
+      "step": 20
+    },
+    {
+      "epoch": 0.02201430930104568,
+      "eval_loss": 0.08446875214576721,
+      "eval_runtime": 12.3137,
+      "eval_samples_per_second": 31.104,
+      "eval_steps_per_second": 15.592,
+      "step": 20
+    },
+    {
+      "epoch": 0.0275178866263071,
+      "grad_norm": 0.3515614867210388,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.05,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 377293167919104.0,
+  "total_flos": 760981135294464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null