Training in progress, step 5000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6bb0b2cec7dc64f0af46afa2b02f194aa462b8988801e2e4745f8fa2534d1b
+oid sha256:6e419d24688ac019899a50fa3ce9890dfee2c364a2c8d9dbc79460fa819290e8
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7cc39daabd7a9b6cf9547dc9f2e67fcdcaee859f2ffd9a5951bff5ee807e77
+oid sha256:3c0e4745a181cf222ad182a5398705ee67df3a42fcd8cbd25a5083afb43425fc
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a760749fd116630cde5751ade399c8fc4db67179112bf0943279a27fabe50d0
+oid sha256:6be8e91b42742a7fc696a54c21b9f58cad4f4a06c38e2d087a62eeffeda24c3e
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38266f6cb5deecc74eba12934513eb63bf16beecebcaf6118d632bda28a37867
+oid sha256:bbe4f7637c0a3dbe68486f699bdaf3bb84765a4a49b403618ff00aa8caca3ddb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.798468989220435,
+  "epoch": 9.998437744102484,
   "eval_steps": 500,
-  "global_step": 4900,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -422,6 +422,21 @@
       "learning_rate": 6.733333333333333e-05,
       "loss": 1.2581,
       "step": 4900
+    },
+    {
+      "epoch": 9.998437744102484,
+      "grad_norm": 0.1944326013326645,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.2515,
+      "step": 5000
+    },
+    {
+      "epoch": 9.998437744102484,
+      "eval_loss": 1.1215333938598633,
+      "eval_runtime": 779.443,
+      "eval_samples_per_second": 19.914,
+      "eval_steps_per_second": 2.49,
+      "step": 5000
     }
   ],
   "logging_steps": 100,
@@ -441,7 +456,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.64759117638769e+18,
+  "total_flos": 7.803666147575857e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null