Training in progress, step 12000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb77d7d570661585169f276ba2af872b16bd30ad343d8c208da992d9da8e7cf
+oid sha256:f395e496621b7032d1b0d7a06fe55747a519694eb3cbf9921f55e1ae957a919d
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924b725b7e1204f28edf1e0a514696b0cc3b3379036637fcb7f015379c0fb456
+oid sha256:3ad76905f926c95599cf7f4e28e6d0206d7af8f1ade288c2c73f1ca0232a6d40
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5ea6feef52f164377ed93bed2dbd484bac24983bc81e5264cf26241ecf793dd
+oid sha256:6e242f2818e9dde5ec7a4736f1896a4fb18f6d870fac4f0630bc5afddcb4a29c
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded0ce8c2d8686604f40889683ca39879633e7c6e7afea5372290e03f7c87cea
+oid sha256:997376d97a66d723eb71715005de65897518b02a368a9b5bed65c4567e1a22ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.796281830963913,
+  "epoch": 23.99625058584596,
   "eval_steps": 500,
-  "global_step": 11900,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1024,6 +1024,21 @@
       "learning_rate": 2.0666666666666666e-05,
       "loss": 1.2247,
       "step": 11900
+    },
+    {
+      "epoch": 23.99625058584596,
+      "grad_norm": 0.2477530688047409,
+      "learning_rate": 2e-05,
+      "loss": 1.2161,
+      "step": 12000
+    },
+    {
+      "epoch": 23.99625058584596,
+      "eval_loss": 1.0947577953338623,
+      "eval_runtime": 781.3136,
+      "eval_samples_per_second": 19.867,
+      "eval_steps_per_second": 2.484,
+      "step": 12000
     }
   ],
   "logging_steps": 100,
@@ -1043,7 +1058,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8572710963375505e+19,
+  "total_flos": 1.8728785934563672e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null