Training in progress, step 9500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18610916b9c673dab5c6882b780a62845c873d2c799ed874ab52e599ac3bb2da
+oid sha256:309aafbf30a829d12f65fa62be415d46a4f998d976c9c151c96e502f6c22af33
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffa99dfca11d28940b83257f420a8866ccecd954b7d059a5ef4ecb1a47de2c9b
+oid sha256:f61164e41900b12e3720ec2180f98395f29ad9dbf83f7fc80fd3bc883daa97fb
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b1f5cb0a7cc9995b5c483d304c23830306a1fc4c4676dff3bd5ac5b73c09c1
+oid sha256:4e8ccc74c26087b6591ff930167cf20bf94e18277027d8ae50d69b554d664499
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:320edc62b9a77cb6db46c18993bf705328fc5437b8f6124a25ea16d34aae731c
+oid sha256:86cc14001d5ebceb36b6cb983dfe849eeafb30020d0541882152e463d2cc7990
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.79706295891267,
+  "epoch": 18.99703171379472,
   "eval_steps": 500,
-  "global_step": 9400,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -809,6 +809,21 @@
       "learning_rate": 3.733333333333334e-05,
       "loss": 1.2278,
       "step": 9400
+    },
+    {
+      "epoch": 18.99703171379472,
+      "grad_norm": 0.2299690842628479,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 1.223,
+      "step": 9500
+    },
+    {
+      "epoch": 18.99703171379472,
+      "eval_loss": 1.1021497249603271,
+      "eval_runtime": 781.5015,
+      "eval_samples_per_second": 19.862,
+      "eval_steps_per_second": 2.484,
+      "step": 9500
     }
   ],
   "logging_steps": 100,
@@ -828,7 +843,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4670882468022714e+19,
+  "total_flos": 1.482695743921088e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null