Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96363d74eb8e505e30e70175f38cf365c3d95b9352b85ccbcdda14b0b97b0604
+oid sha256:23750eae96fff9283e7ae8f0bab6faf349cb0a7eb7d62a4385617e3c105b050a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9032c06bd1a8e5aba237fba062e9b942284f080fef0916342f268300ad8d5730
+oid sha256:c090d1b505cdd524b425c56d229c74e521a9cfcd2e83913f4b04cd9a688c0244
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a76e94d15e6f47128689bef83934eee553e34dee3554bde049b53753e0e7480
+oid sha256:6d6f9191f2eaf4a4097874de4a821f2a97252f64a38cda2d145c006040151b30
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3f10b5ea24e9191e915e4456d16cc3b17d3916946799417c52e3e474e43201
+oid sha256:432af5fdf516a60295d78030fa17670f1cdc61fda7d1429429265938440f5257
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.3250207813798838,
+  "epoch": 3.5328345802161265,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,13 @@
       "learning_rate": 6.704904405652536e-06,
       "loss": 0.3265,
       "step": 8000
+    },
+    {
+      "epoch": 3.5328345802161265,
+      "grad_norm": 0.7057175040245056,
+      "learning_rate": 5.873649210307565e-06,
+      "loss": 0.3219,
+      "step": 8500
     }
   ],
   "logging_steps": 500,
@@ -162,7 +169,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.948482562424832e+16,
+  "total_flos": 2.070274140536832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null