Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be4767b437fbc4c7c39707c48fa92943e3ad141030625b52bf0098f03bf586c
+oid sha256:b8adf86e102e6669d7d744eac25012232cacd9e2c2b5577eb27edd8f31747996
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3818ce85ef6d6e0e908a42d47e066e971c6db7a774a6799318dece03583582f7
+oid sha256:591e8884025421ed099e3e74468620c5d3e460172062eb8910a9338a65fd6793
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb25411738bca161ae6c2a26729b40a97bf70b0a9dd21a74fbe66345edda273f
+oid sha256:a518030d53de0f16e895fae2210619017ee14ab7fb9e1626b05ae41a39c13ac2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4002ec401b29865a446966ea49bed4e5a8d21c249b3ecaee3b7efb93937ff037
+oid sha256:f72ea6df83991d3025ed7e36df9a5c32138772ee24f1af389000a804685c36c9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0781379883624274,
+  "epoch": 2.28595178719867,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,13 @@
       "learning_rate": 1.1690773067331672e-05,
       "loss": 0.3488,
       "step": 5000
+    },
+    {
+      "epoch": 2.28595178719867,
+      "grad_norm": 0.8203754425048828,
+      "learning_rate": 1.086118038237739e-05,
+      "loss": 0.3526,
+      "step": 5500
     }
   ],
   "logging_steps": 500,
@@ -112,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.217793989541888e+16,
+  "total_flos": 1.339585567653888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null