Training in progress, step 8000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9199c58a0e18f6b20cd590e32c01edcc53cc30d656e858f90c63854fd0b6904
+oid sha256:bb868b29e58bf8c78ce45a1b7498706a01c148fc1d6c204402f3c93fdec2ea97
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e4c03a222e16e99e9720067ab049b60c35901ce97933852ed8035f575d9d35
+oid sha256:6a201495d35e68f6f3576b9f05bf7f8b32603dbfcf5301daa2ab84cb859a01e4
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d97fc2860205491c7e62a329fa7e1a38b4205dc52aa4d5fd276acf955995202
+oid sha256:c45011e9e908a25b146a61274c6f6396b1e263759e4756ddca5d58769c8f6c19
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a0479a2cd7c6c12ef80c1a2f8d1061865d0e9e997e771a694b192ac7bb6fce
+oid sha256:fde31ec0ebaeae228855c86a6651c3eabaacfa49bd688d66859eba6a7eca5a40
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.797531635681924,
+  "epoch": 15.997500390563975,
   "eval_steps": 500,
-  "global_step": 7900,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -680,6 +680,21 @@
       "learning_rate": 4.7333333333333336e-05,
       "loss": 1.2317,
       "step": 7900
+    },
+    {
+      "epoch": 15.997500390563975,
+      "grad_norm": 0.22215193510055542,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.2302,
+      "step": 8000
+    },
+    {
+      "epoch": 15.997500390563975,
+      "eval_loss": 1.1039363145828247,
+      "eval_runtime": 781.5664,
+      "eval_samples_per_second": 19.86,
+      "eval_steps_per_second": 2.483,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -699,7 +714,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.232978537081104e+19,
+  "total_flos": 1.2485860341999206e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null