Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a61fd73bc588dbdc24db480c467fa85865340704d30acbb701842098e2e69f
+oid sha256:96363d74eb8e505e30e70175f38cf365c3d95b9352b85ccbcdda14b0b97b0604
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b1a7761b758c7fd9d022ced7c255b59c0684b9396756996b22a9e7e9bd5c35b
+oid sha256:9032c06bd1a8e5aba237fba062e9b942284f080fef0916342f268300ad8d5730
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c102029d2f3d2ad8c4cbe0e9eb23a6db91408d1239150f6a5fe227f52911673
+oid sha256:0a76e94d15e6f47128689bef83934eee553e34dee3554bde049b53753e0e7480
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa8492157bf2c1d0061046d13454f95f14ea95d23b20e0a054ab57ecde42b5d
+oid sha256:2c3f10b5ea24e9191e915e4456d16cc3b17d3916946799417c52e3e474e43201
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.117206982543641,
+  "epoch": 3.3250207813798838,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -136,6 +136,13 @@
       "learning_rate": 7.536159600997507e-06,
       "loss": 0.3313,
       "step": 7500
+    },
+    {
+      "epoch": 3.3250207813798838,
+      "grad_norm": 0.9092524647712708,
+      "learning_rate": 6.704904405652536e-06,
+      "loss": 0.3265,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -155,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.826690984312832e+16,
+  "total_flos": 1.948482562424832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null