Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1756695100508f384748848f37362c0a92701451378276e043ef7f3c362dfcd4
+oid sha256:bfce90cfa170aef88c690e4a132ce9c46e751e36155e82a6769570f3e0f435e9
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8773d9266c62da06bf399f56cb0c16d50f2c1a26ea46e2b85554430db8143450
+oid sha256:2870ce18d3035e65ec736b772491c2d3f8b826f33e07ceed35f88fb275880632
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72de1dad8d6233809f2cfc8005c48069a201d59ec0aed6d89a2e0fa5965139f5
+oid sha256:9a8f0c85caf6dd2f34d726a24b370bad056914b0890ab902dc89abc74fd551d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fd91438459da8cfd11b42ba89bb250b1431fb386cdd7af85c96ff891f5bd392
+oid sha256:895abc0a481d6da002e834c516bb491f258499e49a03e72fe347ca7cdb6aea8f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6625103906899419,
+  "epoch": 1.8703241895261846,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -71,6 +71,13 @@
       "learning_rate": 8.92213909670269e-06,
       "loss": 0.3444,
       "step": 4000
+    },
+    {
+      "epoch": 1.8703241895261846,
+      "grad_norm": 0.5239430069923401,
+      "learning_rate": 7.536713771127737e-06,
+      "loss": 0.3383,
+      "step": 4500
     }
   ],
   "logging_steps": 500,
@@ -90,7 +97,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9742717291069440.0,
+  "total_flos": 1.096063307218944e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null