Training in progress, step 11500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8033aac43721e5faa657d96399c8fbe165ff32991793e1979ec7c86cc5e973
+oid sha256:7882460c4f89afea817defb9e7103055122074330104827dcfbc7a40b4ceb304
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6a135df03ce780080e7a469152b37447383728aef1ea68e2ec7595d105b22a
+oid sha256:370fca27e9ba98192af16e473c9be53a4cc95e12cf83ab41554d3bd46c2a422a
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ad3e03ea8f1373be4094c36a51a592911fcd41841d1f34997a6e6d354f36eb
+oid sha256:dad5a406c0b21888c6cc412d600eb31f96157740bdf983f2af4d739cb7c2302f
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c5035fa2112ddcadfc8569c177cf4a1b5a136573a2d394a844790425be035f3
+oid sha256:61a5a7162bbfbe481fd963774b42902fa7fef8be20d3c03f10ae987b8f806295
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.796438056553665,
+  "epoch": 22.996406811435712,
   "eval_steps": 500,
-  "global_step": 11400,
+  "global_step": 11500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -981,6 +981,21 @@
       "learning_rate": 2.4e-05,
       "loss": 1.2221,
       "step": 11400
+    },
+    {
+      "epoch": 22.996406811435712,
+      "grad_norm": 0.24230831861495972,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.2226,
+      "step": 11500
+    },
+    {
+      "epoch": 22.996406811435712,
+      "eval_loss": 1.1027547121047974,
+      "eval_runtime": 779.9282,
+      "eval_samples_per_second": 19.902,
+      "eval_steps_per_second": 2.489,
+      "step": 11500
     }
   ],
   "logging_steps": 100,
@@ -1000,7 +1015,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7792345264304947e+19,
+  "total_flos": 1.7948420235493114e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null