Training in progress, step 9000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af860c731cb9e45b9f42a34e51237ce465b8fedfbf8bb67f8cd78f5ec9245722
+oid sha256:c9836f9cf3d0339e206ab208c57537b159a8badbe0a852177fd0ec6d8b1f6ad0
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06e00f01e8ddc2da284d5972a314608b20449af0742e1f51803c13d70983553b
+oid sha256:e907b70c528f0f3c900ecd0a580e1e7bf75451d7c3d91445a6c19352c25ffeba
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b95016e498763380b87827c3c299016c6b9cfb8011e8962d026d673b242c281
+oid sha256:577ee5fbac3851526675e760511f1aa023cdc3e11cb46aedca8accc5a3d2710d
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2cfd92f75a8a8524159c58ce7d52a6880278954694731b8071536b3902c6c11
+oid sha256:0a211f6b09806a1f2d5eddb77c770eb7b75d720b085cb229aabd42fd55a4bfb0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.79721918450242,
+  "epoch": 17.99718793938447,
   "eval_steps": 500,
-  "global_step": 8900,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -766,6 +766,21 @@
       "learning_rate": 4.066666666666667e-05,
       "loss": 1.2278,
       "step": 8900
+    },
+    {
+      "epoch": 17.99718793938447,
+      "grad_norm": 0.22143380343914032,
+      "learning_rate": 4e-05,
+      "loss": 1.229,
+      "step": 9000
+    },
+    {
+      "epoch": 17.99718793938447,
+      "eval_loss": 1.1009384393692017,
+      "eval_runtime": 781.433,
+      "eval_samples_per_second": 19.864,
+      "eval_steps_per_second": 2.484,
+      "step": 9000
     }
   ],
   "logging_steps": 100,
@@ -785,7 +800,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3890516768952156e+19,
+  "total_flos": 1.4046591740140323e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null