Training in progress, step 10000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6deea05c166b89fc877ff2e3f92f12973dd0d4ad7605db80ff585b7d98a8fe47
+oid sha256:ecd1fc5c8da7c050619b407dd084aa990ead2c6fec6eb111fc201509346958c7
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cce451040d8df50777438a10389a653ccc5f6777ba24e9c371e90b67b46f8d1
+oid sha256:be49256bb2edba16c12830df1c5c1a06e23d2bb1aae783665c50494fee944421
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56eab8a6ae855f6d831826ceedcd72e607560d7887ae0f290c0ac887815f7455
+oid sha256:4becb485a2cd02f3a3b0a515c805eaabfaedf718cdc3db25566fd5a31a5b45b1
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7727bca6739367d2a9130b4e43b9681ded2d27ee732ac63a61df75ffcc18c7fd
+oid sha256:5d2b5d60ff91ead9ec927864763541792fd18ea815396832b0b5ebde2fdb0c80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.796906733322917,
+  "epoch": 19.996875488204967,
   "eval_steps": 500,
-  "global_step": 9900,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -852,6 +852,21 @@
       "learning_rate": 3.4000000000000007e-05,
       "loss": 1.2232,
       "step": 9900
+    },
+    {
+      "epoch": 19.996875488204967,
+      "grad_norm": 0.24202196300029755,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.2213,
+      "step": 10000
+    },
+    {
+      "epoch": 19.996875488204967,
+      "eval_loss": 1.0894185304641724,
+      "eval_runtime": 781.2073,
+      "eval_samples_per_second": 19.869,
+      "eval_steps_per_second": 2.485,
+      "step": 10000
     }
   ],
   "logging_steps": 100,
@@ -871,7 +886,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5451248167093273e+19,
+  "total_flos": 1.560732313828144e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null